start the frame rate tracker

Update attributes name to pull through the FPS

.dockerignore

@@ -1 +1,6 @@
-README.md
+README.md
+docs/
+.gitignore
+debug
+config/
+*.pyc

.github/FUNDING.yml

@@ -0,0 +1 @@
+github: blakeblackshear

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,55 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**Version of frigate**
+What version are you using?
+
+**Config file**
+Include your full config file wrapped in back ticks.
+```
+config here
+```
+
+**Logs**
+```
+Include relevant log output here
+```
+
+**Frigate debug stats**
+```
+Output from frigate's /debug/stats endpoint
+```
+
+**FFprobe from your camera**
+
+Run the following command and paste output below
+```
+ffprobe <stream_url>
+```
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**Computer Hardware**
+ - OS: [e.g. Ubuntu, Windows]
+ - Virtualization: [e.g. Proxmox, Virtualbox]
+ - Coral Version: [e.g. USB, PCIe, None]
+ - Network Setup: [e.g. Wired, WiFi]
+
+**Camera Info:**
+ - Manufacturer: [e.g. Dahua]
+ - Model: [e.g. IPC-HDW5231R-ZE]
+ - Resolution: [e.g. 720p]
+ - FPS: [e.g. 5]
+
+**Additional context**
+Add any other context about the problem here.

.gitignore

@@ -1,2 +1,4 @@
 *.pyc 
 debug
+.vscode
+config/config.yml

Dockerfile

@@ -1,107 +0,0 @@
-FROM ubuntu:16.04
-
-# Install system packages
-RUN apt-get -qq update && apt-get -qq install --no-install-recommends -y python3 \ 
- python3-dev \
- python-pil \
- python-lxml \
- python-tk \
- build-essential \
- cmake \ 
- git \ 
- libgtk2.0-dev \ 
- pkg-config \ 
- libavcodec-dev \ 
- libavformat-dev \ 
- libswscale-dev \ 
- libtbb2 \
- libtbb-dev \ 
- libjpeg-dev \
- libpng-dev \
- libtiff-dev \
- libjasper-dev \
- libdc1394-22-dev \
- x11-apps \
- wget \
- vim \
- ffmpeg \
- unzip \
- libusb-1.0-0-dev \
- python3-setuptools \
- python3-numpy \
- zlib1g-dev \
- libgoogle-glog-dev \
- swig \
- libunwind-dev \
- libc++-dev \
- libc++abi-dev \
- build-essential \
- && rm -rf /var/lib/apt/lists/* 
-
-# Install core packages 
-RUN wget -q -O /tmp/get-pip.py --no-check-certificate https://bootstrap.pypa.io/get-pip.py && python3 /tmp/get-pip.py
-RUN  pip install -U pip \
- numpy \
- pillow \
- matplotlib \
- notebook \
- Flask \
- imutils \
- paho-mqtt \
- PyYAML
-
-# Install tensorflow models object detection
-RUN GIT_SSL_NO_VERIFY=true git clone -q https://github.com/tensorflow/models /usr/local/lib/python3.5/dist-packages/tensorflow/models
-RUN wget -q -P /usr/local/src/ --no-check-certificate https://github.com/google/protobuf/releases/download/v3.5.1/protobuf-python-3.5.1.tar.gz
-
-# Download & build protobuf-python
-RUN cd /usr/local/src/ \
- && tar xf protobuf-python-3.5.1.tar.gz \
- && rm protobuf-python-3.5.1.tar.gz \
- && cd /usr/local/src/protobuf-3.5.1/ \
- && ./configure \
- && make \
- && make install \
- && ldconfig \
- && rm -rf /usr/local/src/protobuf-3.5.1/
-
-# Download & build OpenCV
-RUN wget -q -P /usr/local/src/ --no-check-certificate https://github.com/opencv/opencv/archive/4.0.1.zip
-RUN cd /usr/local/src/ \
- && unzip 4.0.1.zip \
- && rm 4.0.1.zip \
- && cd /usr/local/src/opencv-4.0.1/ \
- && mkdir build \
- && cd /usr/local/src/opencv-4.0.1/build \ 
- && cmake -D CMAKE_INSTALL_TYPE=Release -D CMAKE_INSTALL_PREFIX=/usr/local/ .. \
- && make -j4 \
- && make install \
- && rm -rf /usr/local/src/opencv-4.0.1
-
-# Download and install EdgeTPU libraries
-RUN wget -q -O edgetpu_api.tar.gz --no-check-certificate http://storage.googleapis.com/cloud-iot-edge-pretrained-models/edgetpu_api.tar.gz
-
-RUN tar xzf edgetpu_api.tar.gz \
-  && cd python-tflite-source \
-  && cp -p libedgetpu/libedgetpu_x86_64.so /lib/x86_64-linux-gnu/libedgetpu.so \
-  && cp edgetpu/swig/compiled_so/_edgetpu_cpp_wrapper_x86_64.so edgetpu/swig/_edgetpu_cpp_wrapper.so \
-  && cp edgetpu/swig/compiled_so/edgetpu_cpp_wrapper.py edgetpu/swig/ \
-  && python3 setup.py develop --user
-
-# Minimize image size 
-RUN (apt-get autoremove -y; \
-     apt-get autoclean -y)
-
-# symlink the model and labels
-RUN ln -s /python-tflite-source/edgetpu/test_data/mobilenet_ssd_v2_coco_quant_postprocess_edgetpu.tflite /frozen_inference_graph.pb
-RUN ln -s /python-tflite-source/edgetpu/test_data/coco_labels.txt /label_map.pbtext
-
-# Set TF object detection available
-ENV PYTHONPATH "$PYTHONPATH:/usr/local/lib/python3.5/dist-packages/tensorflow/models/research:/usr/local/lib/python3.5/dist-packages/tensorflow/models/research/slim"
-RUN cd /usr/local/lib/python3.5/dist-packages/tensorflow/models/research && protoc object_detection/protos/*.proto --python_out=.
-
-WORKDIR /opt/frigate/
-ADD frigate frigate/
-COPY detect_objects.py .
-
-CMD ["python3", "-u", "detect_objects.py"]

LICENSE

@@ -1,661 +1,21 @@
-                    GNU AFFERO GENERAL PUBLIC LICENSE
-                       Version 3, 19 November 2007
-
- Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
- Everyone is permitted to copy and distribute verbatim copies
- of this license document, but changing it is not allowed.
-
-                            Preamble
-
-  The GNU Affero General Public License is a free, copyleft license for
-software and other kinds of works, specifically designed to ensure
-cooperation with the community in the case of network server software.
-
-  The licenses for most software and other practical works are designed
-to take away your freedom to share and change the works.  By contrast,
-our General Public Licenses are intended to guarantee your freedom to
-share and change all versions of a program--to make sure it remains free
-software for all its users.
-
-  When we speak of free software, we are referring to freedom, not
-price.  Our General Public Licenses are designed to make sure that you
-have the freedom to distribute copies of free software (and charge for
-them if you wish), that you receive source code or can get it if you
-want it, that you can change the software or use pieces of it in new
-free programs, and that you know you can do these things.
-
-  Developers that use our General Public Licenses protect your rights
-with two steps: (1) assert copyright on the software, and (2) offer
-you this License which gives you legal permission to copy, distribute
-and/or modify the software.
-
-  A secondary benefit of defending all users' freedom is that
-improvements made in alternate versions of the program, if they
-receive widespread use, become available for other developers to
-incorporate.  Many developers of free software are heartened and
-encouraged by the resulting cooperation.  However, in the case of
-software used on network servers, this result may fail to come about.
-The GNU General Public License permits making a modified version and
-letting the public access it on a server without ever releasing its
-source code to the public.
-
-  The GNU Affero General Public License is designed specifically to
-ensure that, in such cases, the modified source code becomes available
-to the community.  It requires the operator of a network server to
-provide the source code of the modified version running there to the
-users of that server.  Therefore, public use of a modified version, on
-a publicly accessible server, gives the public access to the source
-code of the modified version.
-
-  An older license, called the Affero General Public License and
-published by Affero, was designed to accomplish similar goals.  This is
-a different license, not a version of the Affero GPL, but Affero has
-released a new version of the Affero GPL which permits relicensing under
-this license.
-
-  The precise terms and conditions for copying, distribution and
-modification follow.
-
-                       TERMS AND CONDITIONS
-
-  0. Definitions.
-
-  "This License" refers to version 3 of the GNU Affero General Public License.
-
-  "Copyright" also means copyright-like laws that apply to other kinds of
-works, such as semiconductor masks.
-
-  "The Program" refers to any copyrightable work licensed under this
-License.  Each licensee is addressed as "you".  "Licensees" and
-"recipients" may be individuals or organizations.
-
-  To "modify" a work means to copy from or adapt all or part of the work
-in a fashion requiring copyright permission, other than the making of an
-exact copy.  The resulting work is called a "modified version" of the
-earlier work or a work "based on" the earlier work.
-
-  A "covered work" means either the unmodified Program or a work based
-on the Program.
-
-  To "propagate" a work means to do anything with it that, without
-permission, would make you directly or secondarily liable for
-infringement under applicable copyright law, except executing it on a
-computer or modifying a private copy.  Propagation includes copying,
-distribution (with or without modification), making available to the
-public, and in some countries other activities as well.
-
-  To "convey" a work means any kind of propagation that enables other
-parties to make or receive copies.  Mere interaction with a user through
-a computer network, with no transfer of a copy, is not conveying.
-
-  An interactive user interface displays "Appropriate Legal Notices"
-to the extent that it includes a convenient and prominently visible
-feature that (1) displays an appropriate copyright notice, and (2)
-tells the user that there is no warranty for the work (except to the
-extent that warranties are provided), that licensees may convey the
-work under this License, and how to view a copy of this License.  If
-the interface presents a list of user commands or options, such as a
-menu, a prominent item in the list meets this criterion.
-
-  1. Source Code.
-
-  The "source code" for a work means the preferred form of the work
-for making modifications to it.  "Object code" means any non-source
-form of a work.
-
-  A "Standard Interface" means an interface that either is an official
-standard defined by a recognized standards body, or, in the case of
-interfaces specified for a particular programming language, one that
-is widely used among developers working in that language.
-
-  The "System Libraries" of an executable work include anything, other
-than the work as a whole, that (a) is included in the normal form of
-packaging a Major Component, but which is not part of that Major
-Component, and (b) serves only to enable use of the work with that
-Major Component, or to implement a Standard Interface for which an
-implementation is available to the public in source code form.  A
-"Major Component", in this context, means a major essential component
-(kernel, window system, and so on) of the specific operating system
-(if any) on which the executable work runs, or a compiler used to
-produce the work, or an object code interpreter used to run it.
-
-  The "Corresponding Source" for a work in object code form means all
-the source code needed to generate, install, and (for an executable
-work) run the object code and to modify the work, including scripts to
-control those activities.  However, it does not include the work's
-System Libraries, or general-purpose tools or generally available free
-programs which are used unmodified in performing those activities but
-which are not part of the work.  For example, Corresponding Source
-includes interface definition files associated with source files for
-the work, and the source code for shared libraries and dynamically
-linked subprograms that the work is specifically designed to require,
-such as by intimate data communication or control flow between those
-subprograms and other parts of the work.
-
-  The Corresponding Source need not include anything that users
-can regenerate automatically from other parts of the Corresponding
-Source.
-
-  The Corresponding Source for a work in source code form is that
-same work.
-
-  2. Basic Permissions.
-
-  All rights granted under this License are granted for the term of
-copyright on the Program, and are irrevocable provided the stated
-conditions are met.  This License explicitly affirms your unlimited
-permission to run the unmodified Program.  The output from running a
-covered work is covered by this License only if the output, given its
-content, constitutes a covered work.  This License acknowledges your
-rights of fair use or other equivalent, as provided by copyright law.
-
-  You may make, run and propagate covered works that you do not
-convey, without conditions so long as your license otherwise remains
-in force.  You may convey covered works to others for the sole purpose
-of having them make modifications exclusively for you, or provide you
-with facilities for running those works, provided that you comply with
-the terms of this License in conveying all material for which you do
-not control copyright.  Those thus making or running the covered works
-for you must do so exclusively on your behalf, under your direction
-and control, on terms that prohibit them from making any copies of
-your copyrighted material outside their relationship with you.
-
-  Conveying under any other circumstances is permitted solely under
-the conditions stated below.  Sublicensing is not allowed; section 10
-makes it unnecessary.
-
-  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
-
-  No covered work shall be deemed part of an effective technological
-measure under any applicable law fulfilling obligations under article
-11 of the WIPO copyright treaty adopted on 20 December 1996, or
-similar laws prohibiting or restricting circumvention of such
-measures.
-
-  When you convey a covered work, you waive any legal power to forbid
-circumvention of technological measures to the extent such circumvention
-is effected by exercising rights under this License with respect to
-the covered work, and you disclaim any intention to limit operation or
-modification of the work as a means of enforcing, against the work's
-users, your or third parties' legal rights to forbid circumvention of
-technological measures.
-
-  4. Conveying Verbatim Copies.
-
-  You may convey verbatim copies of the Program's source code as you
-receive it, in any medium, provided that you conspicuously and
-appropriately publish on each copy an appropriate copyright notice;
-keep intact all notices stating that this License and any
-non-permissive terms added in accord with section 7 apply to the code;
-keep intact all notices of the absence of any warranty; and give all
-recipients a copy of this License along with the Program.
-
-  You may charge any price or no price for each copy that you convey,
-and you may offer support or warranty protection for a fee.
-
-  5. Conveying Modified Source Versions.
-
-  You may convey a work based on the Program, or the modifications to
-produce it from the Program, in the form of source code under the
-terms of section 4, provided that you also meet all of these conditions:
-
-    a) The work must carry prominent notices stating that you modified
-    it, and giving a relevant date.
-
-    b) The work must carry prominent notices stating that it is
-    released under this License and any conditions added under section
-    7.  This requirement modifies the requirement in section 4 to
-    "keep intact all notices".
-
-    c) You must license the entire work, as a whole, under this
-    License to anyone who comes into possession of a copy.  This
-    License will therefore apply, along with any applicable section 7
-    additional terms, to the whole of the work, and all its parts,
-    regardless of how they are packaged.  This License gives no
-    permission to license the work in any other way, but it does not
-    invalidate such permission if you have separately received it.
-
-    d) If the work has interactive user interfaces, each must display
-    Appropriate Legal Notices; however, if the Program has interactive
-    interfaces that do not display Appropriate Legal Notices, your
-    work need not make them do so.
-
-  A compilation of a covered work with other separate and independent
-works, which are not by their nature extensions of the covered work,
-and which are not combined with it such as to form a larger program,
-in or on a volume of a storage or distribution medium, is called an
-"aggregate" if the compilation and its resulting copyright are not
-used to limit the access or legal rights of the compilation's users
-beyond what the individual works permit.  Inclusion of a covered work
-in an aggregate does not cause this License to apply to the other
-parts of the aggregate.
-
-  6. Conveying Non-Source Forms.
-
-  You may convey a covered work in object code form under the terms
-of sections 4 and 5, provided that you also convey the
-machine-readable Corresponding Source under the terms of this License,
-in one of these ways:
-
-    a) Convey the object code in, or embodied in, a physical product
-    (including a physical distribution medium), accompanied by the
-    Corresponding Source fixed on a durable physical medium
-    customarily used for software interchange.
-
-    b) Convey the object code in, or embodied in, a physical product
-    (including a physical distribution medium), accompanied by a
-    written offer, valid for at least three years and valid for as
-    long as you offer spare parts or customer support for that product
-    model, to give anyone who possesses the object code either (1) a
-    copy of the Corresponding Source for all the software in the
-    product that is covered by this License, on a durable physical
-    medium customarily used for software interchange, for a price no
-    more than your reasonable cost of physically performing this
-    conveying of source, or (2) access to copy the
-    Corresponding Source from a network server at no charge.
-
-    c) Convey individual copies of the object code with a copy of the
-    written offer to provide the Corresponding Source.  This
-    alternative is allowed only occasionally and noncommercially, and
-    only if you received the object code with such an offer, in accord
-    with subsection 6b.
-
-    d) Convey the object code by offering access from a designated
-    place (gratis or for a charge), and offer equivalent access to the
-    Corresponding Source in the same way through the same place at no
-    further charge.  You need not require recipients to copy the
-    Corresponding Source along with the object code.  If the place to
-    copy the object code is a network server, the Corresponding Source
-    may be on a different server (operated by you or a third party)
-    that supports equivalent copying facilities, provided you maintain
-    clear directions next to the object code saying where to find the
-    Corresponding Source.  Regardless of what server hosts the
-    Corresponding Source, you remain obligated to ensure that it is
-    available for as long as needed to satisfy these requirements.
-
-    e) Convey the object code using peer-to-peer transmission, provided
-    you inform other peers where the object code and Corresponding
-    Source of the work are being offered to the general public at no
-    charge under subsection 6d.
-
-  A separable portion of the object code, whose source code is excluded
-from the Corresponding Source as a System Library, need not be
-included in conveying the object code work.
-
-  A "User Product" is either (1) a "consumer product", which means any
-tangible personal property which is normally used for personal, family,
-or household purposes, or (2) anything designed or sold for incorporation
-into a dwelling.  In determining whether a product is a consumer product,
-doubtful cases shall be resolved in favor of coverage.  For a particular
-product received by a particular user, "normally used" refers to a
-typical or common use of that class of product, regardless of the status
-of the particular user or of the way in which the particular user
-actually uses, or expects or is expected to use, the product.  A product
-is a consumer product regardless of whether the product has substantial
-commercial, industrial or non-consumer uses, unless such uses represent
-the only significant mode of use of the product.
-
-  "Installation Information" for a User Product means any methods,
-procedures, authorization keys, or other information required to install
-and execute modified versions of a covered work in that User Product from
-a modified version of its Corresponding Source.  The information must
-suffice to ensure that the continued functioning of the modified object
-code is in no case prevented or interfered with solely because
-modification has been made.
-
-  If you convey an object code work under this section in, or with, or
-specifically for use in, a User Product, and the conveying occurs as
-part of a transaction in which the right of possession and use of the
-User Product is transferred to the recipient in perpetuity or for a
-fixed term (regardless of how the transaction is characterized), the
-Corresponding Source conveyed under this section must be accompanied
-by the Installation Information.  But this requirement does not apply
-if neither you nor any third party retains the ability to install
-modified object code on the User Product (for example, the work has
-been installed in ROM).
-
-  The requirement to provide Installation Information does not include a
-requirement to continue to provide support service, warranty, or updates
-for a work that has been modified or installed by the recipient, or for
-the User Product in which it has been modified or installed.  Access to a
-network may be denied when the modification itself materially and
-adversely affects the operation of the network or violates the rules and
-protocols for communication across the network.
-
-  Corresponding Source conveyed, and Installation Information provided,
-in accord with this section must be in a format that is publicly
-documented (and with an implementation available to the public in
-source code form), and must require no special password or key for
-unpacking, reading or copying.
-
-  7. Additional Terms.
-
-  "Additional permissions" are terms that supplement the terms of this
-License by making exceptions from one or more of its conditions.
-Additional permissions that are applicable to the entire Program shall
-be treated as though they were included in this License, to the extent
-that they are valid under applicable law.  If additional permissions
-apply only to part of the Program, that part may be used separately
-under those permissions, but the entire Program remains governed by
-this License without regard to the additional permissions.
-
-  When you convey a copy of a covered work, you may at your option
-remove any additional permissions from that copy, or from any part of
-it.  (Additional permissions may be written to require their own
-removal in certain cases when you modify the work.)  You may place
-additional permissions on material, added by you to a covered work,
-for which you have or can give appropriate copyright permission.
-
-  Notwithstanding any other provision of this License, for material you
-add to a covered work, you may (if authorized by the copyright holders of
-that material) supplement the terms of this License with terms:
-
-    a) Disclaiming warranty or limiting liability differently from the
-    terms of sections 15 and 16 of this License; or
-
-    b) Requiring preservation of specified reasonable legal notices or
-    author attributions in that material or in the Appropriate Legal
-    Notices displayed by works containing it; or
-
-    c) Prohibiting misrepresentation of the origin of that material, or
-    requiring that modified versions of such material be marked in
-    reasonable ways as different from the original version; or
-
-    d) Limiting the use for publicity purposes of names of licensors or
-    authors of the material; or
-
-    e) Declining to grant rights under trademark law for use of some
-    trade names, trademarks, or service marks; or
-
-    f) Requiring indemnification of licensors and authors of that
-    material by anyone who conveys the material (or modified versions of
-    it) with contractual assumptions of liability to the recipient, for
-    any liability that these contractual assumptions directly impose on
-    those licensors and authors.
-
-  All other non-permissive additional terms are considered "further
-restrictions" within the meaning of section 10.  If the Program as you
-received it, or any part of it, contains a notice stating that it is
-governed by this License along with a term that is a further
-restriction, you may remove that term.  If a license document contains
-a further restriction but permits relicensing or conveying under this
-License, you may add to a covered work material governed by the terms
-of that license document, provided that the further restriction does
-not survive such relicensing or conveying.
-
-  If you add terms to a covered work in accord with this section, you
-must place, in the relevant source files, a statement of the
-additional terms that apply to those files, or a notice indicating
-where to find the applicable terms.
-
-  Additional terms, permissive or non-permissive, may be stated in the
-form of a separately written license, or stated as exceptions;
-the above requirements apply either way.
-
-  8. Termination.
-
-  You may not propagate or modify a covered work except as expressly
-provided under this License.  Any attempt otherwise to propagate or
-modify it is void, and will automatically terminate your rights under
-this License (including any patent licenses granted under the third
-paragraph of section 11).
-
-  However, if you cease all violation of this License, then your
-license from a particular copyright holder is reinstated (a)
-provisionally, unless and until the copyright holder explicitly and
-finally terminates your license, and (b) permanently, if the copyright
-holder fails to notify you of the violation by some reasonable means
-prior to 60 days after the cessation.
-
-  Moreover, your license from a particular copyright holder is
-reinstated permanently if the copyright holder notifies you of the
-violation by some reasonable means, this is the first time you have
-received notice of violation of this License (for any work) from that
-copyright holder, and you cure the violation prior to 30 days after
-your receipt of the notice.
-
-  Termination of your rights under this section does not terminate the
-licenses of parties who have received copies or rights from you under
-this License.  If your rights have been terminated and not permanently
-reinstated, you do not qualify to receive new licenses for the same
-material under section 10.
-
-  9. Acceptance Not Required for Having Copies.
-
-  You are not required to accept this License in order to receive or
-run a copy of the Program.  Ancillary propagation of a covered work
-occurring solely as a consequence of using peer-to-peer transmission
-to receive a copy likewise does not require acceptance.  However,
-nothing other than this License grants you permission to propagate or
-modify any covered work.  These actions infringe copyright if you do
-not accept this License.  Therefore, by modifying or propagating a
-covered work, you indicate your acceptance of this License to do so.
-
-  10. Automatic Licensing of Downstream Recipients.
-
-  Each time you convey a covered work, the recipient automatically
-receives a license from the original licensors, to run, modify and
-propagate that work, subject to this License.  You are not responsible
-for enforcing compliance by third parties with this License.
-
-  An "entity transaction" is a transaction transferring control of an
-organization, or substantially all assets of one, or subdividing an
-organization, or merging organizations.  If propagation of a covered
-work results from an entity transaction, each party to that
-transaction who receives a copy of the work also receives whatever
-licenses to the work the party's predecessor in interest had or could
-give under the previous paragraph, plus a right to possession of the
-Corresponding Source of the work from the predecessor in interest, if
-the predecessor has it or can get it with reasonable efforts.
-
-  You may not impose any further restrictions on the exercise of the
-rights granted or affirmed under this License.  For example, you may
-not impose a license fee, royalty, or other charge for exercise of
-rights granted under this License, and you may not initiate litigation
-(including a cross-claim or counterclaim in a lawsuit) alleging that
-any patent claim is infringed by making, using, selling, offering for
-sale, or importing the Program or any portion of it.
-
-  11. Patents.
-
-  A "contributor" is a copyright holder who authorizes use under this
-License of the Program or a work on which the Program is based.  The
-work thus licensed is called the contributor's "contributor version".
-
-  A contributor's "essential patent claims" are all patent claims
-owned or controlled by the contributor, whether already acquired or
-hereafter acquired, that would be infringed by some manner, permitted
-by this License, of making, using, or selling its contributor version,
-but do not include claims that would be infringed only as a
-consequence of further modification of the contributor version.  For
-purposes of this definition, "control" includes the right to grant
-patent sublicenses in a manner consistent with the requirements of
-this License.
-
-  Each contributor grants you a non-exclusive, worldwide, royalty-free
-patent license under the contributor's essential patent claims, to
-make, use, sell, offer for sale, import and otherwise run, modify and
-propagate the contents of its contributor version.
-
-  In the following three paragraphs, a "patent license" is any express
-agreement or commitment, however denominated, not to enforce a patent
-(such as an express permission to practice a patent or covenant not to
-sue for patent infringement).  To "grant" such a patent license to a
-party means to make such an agreement or commitment not to enforce a
-patent against the party.
-
-  If you convey a covered work, knowingly relying on a patent license,
-and the Corresponding Source of the work is not available for anyone
-to copy, free of charge and under the terms of this License, through a
-publicly available network server or other readily accessible means,
-then you must either (1) cause the Corresponding Source to be so
-available, or (2) arrange to deprive yourself of the benefit of the
-patent license for this particular work, or (3) arrange, in a manner
-consistent with the requirements of this License, to extend the patent
-license to downstream recipients.  "Knowingly relying" means you have
-actual knowledge that, but for the patent license, your conveying the
-covered work in a country, or your recipient's use of the covered work
-in a country, would infringe one or more identifiable patents in that
-country that you have reason to believe are valid.
-
-  If, pursuant to or in connection with a single transaction or
-arrangement, you convey, or propagate by procuring conveyance of, a
-covered work, and grant a patent license to some of the parties
-receiving the covered work authorizing them to use, propagate, modify
-or convey a specific copy of the covered work, then the patent license
-you grant is automatically extended to all recipients of the covered
-work and works based on it.
-
-  A patent license is "discriminatory" if it does not include within
-the scope of its coverage, prohibits the exercise of, or is
-conditioned on the non-exercise of one or more of the rights that are
-specifically granted under this License.  You may not convey a covered
-work if you are a party to an arrangement with a third party that is
-in the business of distributing software, under which you make payment
-to the third party based on the extent of your activity of conveying
-the work, and under which the third party grants, to any of the
-parties who would receive the covered work from you, a discriminatory
-patent license (a) in connection with copies of the covered work
-conveyed by you (or copies made from those copies), or (b) primarily
-for and in connection with specific products or compilations that
-contain the covered work, unless you entered into that arrangement,
-or that patent license was granted, prior to 28 March 2007.
-
-  Nothing in this License shall be construed as excluding or limiting
-any implied license or other defenses to infringement that may
-otherwise be available to you under applicable patent law.
-
-  12. No Surrender of Others' Freedom.
-
-  If conditions are imposed on you (whether by court order, agreement or
-otherwise) that contradict the conditions of this License, they do not
-excuse you from the conditions of this License.  If you cannot convey a
-covered work so as to satisfy simultaneously your obligations under this
-License and any other pertinent obligations, then as a consequence you may
-not convey it at all.  For example, if you agree to terms that obligate you
-to collect a royalty for further conveying from those to whom you convey
-the Program, the only way you could satisfy both those terms and this
-License would be to refrain entirely from conveying the Program.
-
-  13. Remote Network Interaction; Use with the GNU General Public License.
-
-  Notwithstanding any other provision of this License, if you modify the
-Program, your modified version must prominently offer all users
-interacting with it remotely through a computer network (if your version
-supports such interaction) an opportunity to receive the Corresponding
-Source of your version by providing access to the Corresponding Source
-from a network server at no charge, through some standard or customary
-means of facilitating copying of software.  This Corresponding Source
-shall include the Corresponding Source for any work covered by version 3
-of the GNU General Public License that is incorporated pursuant to the
-following paragraph.
-
-  Notwithstanding any other provision of this License, you have
-permission to link or combine any covered work with a work licensed
-under version 3 of the GNU General Public License into a single
-combined work, and to convey the resulting work.  The terms of this
-License will continue to apply to the part which is the covered work,
-but the work with which it is combined will remain governed by version
-3 of the GNU General Public License.
-
-  14. Revised Versions of this License.
-
-  The Free Software Foundation may publish revised and/or new versions of
-the GNU Affero General Public License from time to time.  Such new versions
-will be similar in spirit to the present version, but may differ in detail to
-address new problems or concerns.
-
-  Each version is given a distinguishing version number.  If the
-Program specifies that a certain numbered version of the GNU Affero General
-Public License "or any later version" applies to it, you have the
-option of following the terms and conditions either of that numbered
-version or of any later version published by the Free Software
-Foundation.  If the Program does not specify a version number of the
-GNU Affero General Public License, you may choose any version ever published
-by the Free Software Foundation.
-
-  If the Program specifies that a proxy can decide which future
-versions of the GNU Affero General Public License can be used, that proxy's
-public statement of acceptance of a version permanently authorizes you
-to choose that version for the Program.
-
-  Later license versions may give you additional or different
-permissions.  However, no additional obligations are imposed on any
-author or copyright holder as a result of your choosing to follow a
-later version.
-
-  15. Disclaimer of Warranty.
-
-  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
-APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
-HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
-OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
-THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
-IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
-ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
-
-  16. Limitation of Liability.
-
-  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
-WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
-THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
-GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
-USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
-DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
-PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
-EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
-SUCH DAMAGES.
-
-  17. Interpretation of Sections 15 and 16.
-
-  If the disclaimer of warranty and limitation of liability provided
-above cannot be given local legal effect according to their terms,
-reviewing courts shall apply local law that most closely approximates
-an absolute waiver of all civil liability in connection with the
-Program, unless a warranty or assumption of liability accompanies a
-copy of the Program in return for a fee.
-
-                     END OF TERMS AND CONDITIONS
-
-            How to Apply These Terms to Your New Programs
-
-  If you develop a new program, and you want it to be of the greatest
-possible use to the public, the best way to achieve this is to make it
-free software which everyone can redistribute and change under these terms.
-
-  To do so, attach the following notices to the program.  It is safest
-to attach them to the start of each source file to most effectively
-state the exclusion of warranty; and each file should have at least
-the "copyright" line and a pointer to where the full notice is found.
-
-    <one line to give the program's name and a brief idea of what it does.>
-    Copyright (C) <year>  <name of author>
-
-    This program is free software: you can redistribute it and/or modify
-    it under the terms of the GNU Affero General Public License as published
-    by the Free Software Foundation, either version 3 of the License, or
-    (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU Affero General Public License for more details.
-
-    You should have received a copy of the GNU Affero General Public License
-    along with this program.  If not, see <https://www.gnu.org/licenses/>.
-
-Also add information on how to contact you by electronic and paper mail.
-
-  If your software can interact with users remotely through a computer
-network, you should also make sure that it provides a way for users to
-get its source.  For example, if your program is a web application, its
-interface could display a "Source" link that leads users to an archive
-of the code.  There are many ways you could offer source, and different
-solutions will be better for different programs; see section 13 for the
-specific requirements.
-
-  You should also get your employer (if you work as a programmer) or school,
-if any, to sign a "copyright disclaimer" for the program, if necessary.
-For more information on this, and how to apply and follow the GNU AGPL, see
-<https://www.gnu.org/licenses/>.
+The MIT License
+
+Copyright (c) 2020 Blake Blackshear
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

Makefile

@@ -0,0 +1,37 @@
+default_target: amd64_frigate
+
+amd64_wheels:
+	docker build --tag blakeblackshear/frigate-wheels:amd64 --file docker/Dockerfile.wheels .
+
+amd64_ffmpeg:
+	docker build --tag blakeblackshear/frigate-ffmpeg:amd64 --file docker/Dockerfile.ffmpeg.amd64 .
+
+amd64_frigate:
+	docker build --tag frigate-base --build-arg ARCH=amd64 --file docker/Dockerfile.base .
+	docker build --tag frigate --file docker/Dockerfile.amd64 .
+
+amd64_all: amd64_wheels amd64_ffmpeg amd64_frigate
+
+aarch64_wheels:
+	docker build --tag blakeblackshear/frigate-wheels:aarch64 --file docker/Dockerfile.wheels.aarch64 .
+
+aarch64_ffmpeg:
+	docker build --tag blakeblackshear/frigate-ffmpeg:aarch64 --file docker/Dockerfile.ffmpeg.aarch64 .
+
+aarch64_frigate:
+	docker build --tag frigate-base --build-arg ARCH=aarch64 --file docker/Dockerfile.base .
+	docker build --tag frigate --file docker/Dockerfile.aarch64 .
+
+armv7_all: armv7_wheels armv7_ffmpeg armv7_frigate
+
+armv7_wheels:
+	docker build --tag blakeblackshear/frigate-wheels:armv7 --file docker/Dockerfile.wheels .
+
+armv7_ffmpeg:
+	docker build --tag blakeblackshear/frigate-ffmpeg:armv7 --file docker/Dockerfile.ffmpeg.armv7 .
+
+armv7_frigate:
+	docker build --tag frigate-base --build-arg ARCH=armv7 --file docker/Dockerfile.base .
+	docker build --tag frigate --file docker/Dockerfile.armv7 .
+
+armv7_all: armv7_wheels armv7_ffmpeg armv7_frigate

README.md

@@ -1,98 +1,781 @@
-# Frigate - Realtime Object Detection for RTSP Cameras
-**Note:** This version requires the use of a [Google Coral USB Accelerator](https://coral.withgoogle.com/products/accelerator/)
+<p align="center">
+  <img width="40%" align="center" alt="logo" src="docs/frigate.png">
+</p>
 
-Uses OpenCV and Tensorflow to perform realtime object detection locally for RTSP cameras. Designed for integration with HomeAssistant or others via MQTT.
+# Frigate - NVR With Realtime Object Detection for IP Cameras
+Uses OpenCV and Tensorflow to perform realtime object detection locally for IP cameras. Designed for integration with HomeAssistant or others via MQTT.
 
-- Leverages multiprocessing and threads heavily with an emphasis on realtime over processing every frame
-- Allows you to define specific regions (squares) in the image to look for objects
-- No motion detection (for now)
-- Object detection with Tensorflow runs in a separate thread
-- Object info is published over MQTT for integration into HomeAssistant as a binary sensor
-- An endpoint is available to view an MJPEG stream for debugging
+Use of a [Google Coral Accelerator](https://coral.ai/products/) is optional, but highly recommended. The Coral will outperform even the best CPUs and can process 100+ FPS with very little overhead.
 
-![Diagram](diagram.png)
+- Designed to minimize resource use and maximize performance by only looking for objects when and where it is necessary
+- Leverages multiprocessing heavily with an emphasis on realtime over processing every frame
+- Uses a very low overhead motion detection to determine where to run object detection
+- Object detection with TensorFlow runs in separate processes for maximum FPS
+- Communicates over MQTT for easy integration into other systems
 
-## Example video (from older version)
-You see multiple bounding boxes because it draws bounding boxes from all frames in the past 1 second where a person was detected. Not all of the bounding boxes were from the current frame.
-[![](http://img.youtube.com/vi/nqHbCtyo4dY/0.jpg)](http://www.youtube.com/watch?v=nqHbCtyo4dY "Frigate")
+## Documentation
+- [How Frigate Works](docs/how-frigate-works.md)
+- [Recommended Hardware](#recommended-hardware)
+- [Installing](#installing)
+- [Configuration File](#configuration)
+- [Optimizing Performance](#optimizing-performance)
+- [Detectors](#detectors)
+- [Object Filters](#object-filters)
+- [Masks](#masks)
+- [Zones](#zones)
+- [Integration with HomeAssistant](#integration-with-homeassistant)
+- [MQTT Topics](#mqtt-topics)
+- [HTTP Endpoints](#http-endpoints)
+- [Custom Models](#custom-models)
+- [Troubleshooting](#troubleshooting)
 
-## Getting Started
-Build the container with
-```
-docker build -t frigate .
-```
+## Recommended Hardware
+|Name|Inference Speed|Notes|
+|----|---------------|-----|
+|Atomic Pi|16ms|Good option for a dedicated low power board with a small number of cameras. Can leverage Intel QuickSync for stream decoding.|
+|Intel NUC NUC7i3BNK|8-10ms|Great performance. Can handle many cameras at 5fps depending on typical amounts of motion.|
+|BMAX B2 Plus|10-12ms|Good balance of performance and cost. Also capable of running many other services at the same time as frigate.|
+|Minisforum GK41|9-10ms|Great alternative to a NUC with dual Gigabit NICs. Easily handles several 1080p cameras.|
+|Raspberry Pi 3B (32bit)|60ms|Can handle a small number of cameras, but the detection speeds are slow due to USB 2.0.|
+|Raspberry Pi 4 (32bit)|15-20ms|Can handle a small number of cameras. The 2GB version runs fine.|
+|Raspberry Pi 4 (64bit)|10-15ms|Can handle a small number of cameras. The 2GB version runs fine.|
 
-The `mobilenet_ssd_v2_coco_quant_postprocess_edgetpu.tflite` model is included and used by default. You can use your own model and labels by mounting files in the container at `/frozen_inference_graph.pb` and `/label_map.pbtext`. Models must be compatible with the Coral according to [this](https://coral.withgoogle.com/models/).
+[Back to top](#documentation)
 
-Run the container with
-```
-docker run --rm \
---privileged \
--v /dev/bus/usb:/dev/bus/usb \
--v <path_to_config_dir>:/config:ro \
--p 5000:5000 \
--e RTSP_PASSWORD='password' \
-frigate:latest
-```
+## Installing
 
-Example docker-compose:
-```
+### HassOS Addon
+HassOS users can install via the addon repository. Frigate requires that an MQTT server be running.
+1. Navigate to Supervisor > Add-on Store > Repositories
+1. Add https://github.com/blakeblackshear/frigate-hass-addons
+1. Setup your configuration in the `Configuration` tab
+1. Start the addon container
+
+### Docker
+Make sure you choose the right image for your architecture:
+|Arch|Image Name|
+|-|-|
+|amd64|blakeblackshear/frigate:stable-amd64|
+|armv7|blakeblackshear/frigate:stable-armv7|
+|aarch64|blakeblackshear/frigate:stable-aarch64|
+
+It is recommended to run with docker-compose:
+```yaml
   frigate:
     container_name: frigate
     restart: unless-stopped
     privileged: true
-    image: frigate:latest
+    image: blakeblackshear/frigate:stable-amd64
     volumes:
       - /dev/bus/usb:/dev/bus/usb
+      - /etc/localtime:/etc/localtime:ro
       - <path_to_config>:/config
+      - <path_to_directory_for_clips>:/clips      
+      - type: tmpfs # 1GB of memory, reduces SSD/SD Card wear
+        target: /cache
+        tmpfs:
+          size: 100000000
     ports:
       - "5000:5000"
     environment:
-      RTSP_PASSWORD: "password"
+      FRIGATE_RTSP_PASSWORD: "password"
+    healthcheck:
+      test: ["CMD", "wget" , "-q", "-O-", "http://localhost:5000"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+      start_period: 3m
 ```
 
-A `config.yml` file must exist in the `config` directory. See example [here](config/config.yml).
+If you can't use docker compose, you can run the container with:
+```bash
+docker run --rm \
+--name frigate \
+--privileged \
+-v /dev/bus/usb:/dev/bus/usb \
+-v <path_to_config_dir>:/config:ro \
+-v /etc/localtime:/etc/localtime:ro \
+-p 5000:5000 \
+-e FRIGATE_RTSP_PASSWORD='password' \
+blakeblackshear/frigate:stable-amd64
+```
 
-Access the mjpeg stream at `http://localhost:5000/<camera_name>` and the best person snapshot at `http://localhost:5000/<camera_name>/best_person.jpg`
+### Kubernetes
+Use the [helm chart](https://github.com/k8s-at-home/charts/tree/master/charts/frigate).
+
+### Virtualization
+For ideal performance, Frigate needs access to underlying hardware for the Coral and GPU devices for ffmpeg decoding. Running Frigate in a VM on top of Proxmox, ESXi, Virtualbox, etc. is not recommended. The virtualization layer typically introduces a sizable amount of overhead for communication with Coral devices.
+
+#### Proxmox
+Some people have had success running Frigate in LXC directly with the following config:
+```
+arch: amd64
+cores: 2
+features: nesting=1
+hostname: FrigateLXC
+memory: 4096
+net0: name=eth0,bridge=vmbr0,firewall=1,hwaddr=2E:76:AE:5A:58:48,ip=dhcp,ip6=auto,type=veth
+ostype: debian
+rootfs: local-lvm:vm-115-disk-0,size=12G
+swap: 512
+lxc.cgroup.devices.allow: c 189:385 rwm
+lxc.mount.entry: /dev/dri/renderD128 dev/dri/renderD128 none bind,optional,create=file
+lxc.mount.entry: /dev/bus/usb/004/002 dev/bus/usb/004/002 none bind,optional,create=file
+lxc.apparmor.profile: unconfined
+lxc.cgroup.devices.allow: a
+lxc.cap.drop:
+```
+
+### Calculating shm-size
+The default shm-size of 64m is fine for setups with 3 or less 1080p cameras. If frigate is exiting with "Bus error" messages, it could be because you have too many high resolution cameras and you need to specify a higher shm size.
+
+You can calculate the necessary shm-size for each camera with the following formula:
+```
+(width * height * 1.5 * 7 + 270480)/1048576 = <shm size in mb>
+```
+[Back to top](#documentation)
+
+## Configuration
+HassOS users can manage their configuration directly in the addon Configuration tab. For other installations, the default location for the config file is `/config/config.yml`. This can be overridden with the `CONFIG_FILE` environment variable. Camera specific ffmpeg parameters are documented [here](docs/cameras.md).
+
+```yaml
+# Optional: port for http server (default: shown below)
+web_port: 5000
+
+# Optional: detectors configuration
+# USB Coral devices will be auto detected with CPU fallback
+detectors:
+  # Required: name of the detector
+  coral:
+    # Required: type of the detector
+    # Valid values are 'edgetpu' (requires device property below) and 'cpu'.
+    type: edgetpu
+    # Optional: device name as defined here: https://coral.ai/docs/edgetpu/multiple-edgetpu/#using-the-tensorflow-lite-python-api
+    device: usb
+
+# Required: mqtt configuration
+mqtt:
+  # Required: host name
+  host: mqtt.server.com
+  # Optional: port (default: shown below)
+  port: 1883
+  # Optional: topic prefix (default: shown below)
+  # WARNING: must be unique if you are running multiple instances
+  topic_prefix: frigate
+  # Optional: client id (default: shown below)
+  # WARNING: must be unique if you are running multiple instances
+  client_id: frigate
+  # Optional: user
+  user: mqtt_user
+  # Optional: password
+  # NOTE: Environment variables that begin with 'FRIGATE_' may be referenced in {}. 
+  #       eg. password: '{FRIGATE_MQTT_PASSWORD}'
+  password: password
+
+# Optional: Global configuration for saving clips
+save_clips:
+  # Optional: Maximum length of time to retain video during long events. (default: shown below)
+  # NOTE: If an object is being tracked for longer than this amount of time, the cache
+  #       will begin to expire and the resulting clip will be the last x seconds of the event.
+  max_seconds: 300
+  # Optional: Location to save event clips. (default: shown below)
+  clips_dir: /clips
+  # Optional: Location to save cache files for creating clips. (default: shown below)
+  # NOTE: To reduce wear on SSDs and SD cards, use a tmpfs volume.
+  cache_dir: /cache
+
+# Optional: Global ffmpeg args
+# "ffmpeg" + global_args + input_args + "-i" + input + output_args
+ffmpeg:
+  # Optional: global ffmpeg args (default: shown below)
+  global_args:
+    - -hide_banner
+    - -loglevel
+    - panic
+  # Optional: global hwaccel args (default: shown below)
+  # NOTE: See hardware acceleration docs for your specific device
+  hwaccel_args: []
+  # Optional: global input args (default: shown below)
+  input_args:
+    - -avoid_negative_ts
+    - make_zero
+    - -fflags
+    - nobuffer
+    - -flags
+    - low_delay
+    - -strict
+    - experimental
+    - -fflags
+    - +genpts+discardcorrupt
+    - -rtsp_transport
+    - tcp
+    - -stimeout
+    - '5000000'
+    - -use_wallclock_as_timestamps
+    - '1'
+  # Optional: global output args (default: shown below)
+  output_args:
+    - -f
+    - rawvideo
+    - -pix_fmt
+    - yuv420p
+
+# Optional: Global object filters for all cameras.
+# NOTE: can be overridden at the camera level
+objects:
+  # Optional: list of objects to track from labelmap.txt (default: shown below)
+  track:
+    - person
+  # Optional: filters to reduce false positives for specific object types
+  filters:
+    person:
+      # Optional: minimum width*height of the bounding box for the detected object (default: 0)
+      min_area: 5000
+      # Optional: maximum width*height of the bounding box for the detected object (default: max_int)
+      max_area: 100000
+      # Optional: minimum score for the object to initiate tracking (default: shown below)
+      min_score: 0.5
+      # Optional: minimum decimal percentage for tracked object's computed score to be considered a true positive (default: shown below)
+      threshold: 0.85
+
+# Required: configuration section for cameras
+cameras:
+  # Required: name of the camera
+  back:
+    # Required: ffmpeg settings for the camera
+    ffmpeg:
+      # Required: Source passed to ffmpeg after the -i parameter.
+      # NOTE: Environment variables that begin with 'FRIGATE_' may be referenced in {}
+      input: rtsp://viewer:{FRIGATE_RTSP_PASSWORD}@10.0.10.10:554/cam/realmonitor?channel=1&subtype=2
+      # Optional: camera specific global args (default: inherit)
+      global_args:
+      # Optional: camera specific hwaccel args (default: inherit)
+      hwaccel_args:
+      # Optional: camera specific input args (default: inherit)
+      input_args:
+      # Optional: camera specific output args (default: inherit)
+      output_args:
+    
+    # Optional: height of the frame
+    # NOTE: Recommended to set this value, but frigate will attempt to autodetect.
+    height: 720
+    # Optional: width of the frame
+    # NOTE: Recommended to set this value, but frigate will attempt to autodetect.
+    width: 1280
+    # Optional: desired fps for your camera
+    # NOTE: Recommended value of 5. Ideally, try and reduce your FPS on the camera.
+    #       Frigate will attempt to autodetect if not specified.
+    fps: 5
+
+    # Optional: motion mask
+    # NOTE: see docs for more detailed info on creating masks
+    mask: poly,0,900,1080,900,1080,1920,0,1920
+
+    # Optional: timeout for highest scoring image before allowing it
+    # to be replaced by a newer image. (default: shown below)
+    best_image_timeout: 60
+
+    # Optional: camera specific mqtt settings
+    mqtt:
+      # Optional: crop the camera frame to the detection region of the object (default: False)
+      crop_to_region: True
+      # Optional: resize the image before publishing over mqtt
+      snapshot_height: 300
+
+    # Optional: zones for this camera
+    zones:
+      # Required: name of the zone
+      # NOTE: This must be different than any camera names, but can match with another zone on another
+      #       camera.
+      front_steps:
+        # Required: List of x,y coordinates to define the polygon of the zone.
+        # NOTE: Coordinates can be generated at https://www.image-map.net/
+        coordinates: 545,1077,747,939,788,805
+        # Optional: Zone level object filters.
+        # NOTE: The global and camera filters are applied upstream.
+        filters:
+          person:
+            min_area: 5000
+            max_area: 100000
+            threshold: 0.8
+
+    # Optional: save clips configuration
+    # NOTE: This feature does not work if you have added "-vsync drop" in your input params. 
+    #       This will only work for camera feeds that can be copied into the mp4 container format without
+    #       encoding such as h264. It may not work for some types of streams.
+    save_clips:
+      # Required: enables clips for the camera (default: shown below)
+      enabled: False
+      # Optional: Number of seconds before the event to include in the clips (default: shown below)
+      pre_capture: 30
+      # Optional: Objects to save clips for. (default: all tracked objects)
+      objects:
+        - person      
+
+    # Optional: Configuration for the snapshots in the debug view and mqtt
+    snapshots:
+      # Optional: print a timestamp on the snapshots (default: shown below)
+      show_timestamp: True
+      # Optional: draw zones on the debug mjpeg feed (default: shown below)
+      draw_zones: False
+      # Optional: draw bounding boxes on the mqtt snapshots (default: shown below)
+      draw_bounding_boxes: True
+
+    # Optional: Camera level object filters config. If defined, this is used instead of the global config.
+    objects:
+      track:
+        - person
+        - car
+      filters:
+        person:
+          min_area: 5000
+          max_area: 100000
+          min_score: 0.5
+          threshold: 0.85
+```
+[Back to top](#documentation)
+
+## Optimizing Performance
+- **Google Coral**: It is strongly recommended to use a Google Coral, but Frigate will fall back to CPU in the event one is not found. Offloading TensorFlow to the Google Coral is an order of magnitude faster and will reduce your CPU load dramatically. A $60 device will outperform $2000 CPU.
+- **Resolution**: Choose a camera resolution where the smallest object you want to detect barely fits inside a 300x300px square. The model used by Frigate is trained on 300x300px images, so you will get worse performance and no improvement in accuracy by using a larger resolution since Frigate resizes the area where it is looking for objects to 300x300 anyway.
+- **FPS**: 5 frames per second should be adequate. Higher frame rates will require more CPU usage without improving detections or accuracy. Reducing the frame rate on your camera will have the greatest improvement on system resources.
+- **Hardware Acceleration**: Make sure you configure the `hwaccel_args` for your hardware. They provide a significant reduction in CPU usage if they are available.
+- **Masks**: Masks can be used to ignore motion and reduce your idle CPU load. If you have areas with regular motion such as timestamps or trees blowing in the wind, frigate will constantly try to determine if that motion is from a person or other object you are tracking. Those detections not only increase your average CPU usage, but also clog the pipeline for detecting objects elsewhere. If you are experiencing high values for `detection_fps` when no objects of interest are in the cameras, you should use masks to tell frigate to ignore movement from trees, bushes, timestamps, or any part of the image where detections should not be wasted looking for objects.
+
+### FFmpeg Hardware Acceleration
+Frigate works on Raspberry Pi 3b/4 and x86 machines. It is recommended to update your configuration to enable hardware accelerated decoding in ffmpeg. Depending on your system, these parameters may not be compatible.
+
+Raspberry Pi 3/4 (32-bit OS):
+```yaml
+ffmpeg:
+  hwaccel_args:
+    - -c:v
+    - h264_mmal
+```
+
+Raspberry Pi 3/4 (64-bit OS)
+```yaml
+ffmpeg:
+  hwaccel_args:
+    - -c:v
+    - h264_v4l2m2m
+```
+
+Intel-based CPUs (<10th Generation) via Quicksync (https://trac.ffmpeg.org/wiki/Hardware/QuickSync)
+```yaml
+ffmpeg:
+  hwaccel_args:
+    - -hwaccel
+    - vaapi
+    - -hwaccel_device
+    - /dev/dri/renderD128
+    - -hwaccel_output_format
+    - yuv420p
+```
+
+Intel-based CPUs (>=10th Generation) via Quicksync (https://trac.ffmpeg.org/wiki/Hardware/QuickSync)
+**Note:** You also need to set `LIBVA_DRIVER_NAME=iHD` as an environment variable on the container.
+```yaml
+ffmpeg:
+  hwaccel_args:
+    - -hwaccel
+    - vaapi
+    - -hwaccel_device
+    - /dev/dri/renderD128
+```
+
+[Back to top](#documentation)
+
+## Detectors
+By default Frigate will look for a USB Coral device and fall back to the CPU if it cannot be found. If you have PCI or multiple Coral devices, you need to configure your detector devices in the config file. When using multiple detectors, they run in dedicated processes, but pull from a common queue of requested detections across all cameras.
+
+Frigate supports `edgetpu` and `cpu` as detector types. The device value should be specified according to the [Documentation for the TensorFlow Lite Python API](https://coral.ai/docs/edgetpu/multiple-edgetpu/#using-the-tensorflow-lite-python-api).
+
+Single USB Coral:
+```yaml
+detectors:
+  coral:
+    type: edgetpu
+    device: usb
+```
+
+Multiple USB Corals:
+```yaml
+detectors:
+  coral1:
+    type: edgetpu
+    device: usb:0
+  coral2:
+    type: edgetpu
+    device: usb:1
+```
+
+Mixing Corals:
+```yaml
+detectors:
+  coral_usb:
+    type: edgetpu
+    device: usb
+  coral_pci:
+    type: edgetpu
+    device: pci
+```
+
+CPU Detectors (not recommended):
+```yaml
+detectors:
+  cpu1:
+    type: cpu
+  cpu2:
+    type: cpu
+```
+[Back to top](#documentation)
+
+## Reducing False Positives
+Tune your object filters to adjust false positives: `min_area`, `max_area`, `min_score`, `threshold`.
+
+For object filters in your configuration, any single detection below `min_score` will be ignored as a false positive. `threshold` is based on the median of the history of scores (padded to 3 values) for a tracked object. Consider the following frames when `min_score` is set to 0.6 and threshold is set to 0.85:
+
+| Frame | Current Score | Score History | Computed Score | Detected Object |
+| --- | --- | --- | --- | --- |
+| 1 | 0.7 | 0.0, 0, 0.7 | 0.0 | No
+| 2 | 0.55 | 0.0, 0.7, 0.0 | 0.0 | No
+| 3 | 0.85 | 0.7, 0.0, 0.85 | 0.7 | No
+| 4 | 0.90 | 0.7, 0.85, 0.95, 0.90 | 0.875 | Yes
+| 5 | 0.88 | 0.7, 0.85, 0.95, 0.90, 0.88 | 0.88 | Yes
+| 6 | 0.95 | 0.7, 0.85, 0.95, 0.90, 0.88, 0.95 | 0.89 | Yes
+
+In frame 2, the score is below the `min_score` value, so frigate ignores it and it becomes a 0.0. The computed score is the median of the score history (padding to at least 3 values), and only when that computed score crosses the `threshold` is the object marked as a true positive. That happens in frame 4 in the example.
+
+[Back to top](#documentation)
+
+## Masks
+The following types of masks are supported:
+- `poly`: (Recommended) List of x,y points like zone configuration
+- `base64`: Base64 encoded image file
+- `image`: Image file in the `/config` directory
+
+`base64` and `image` masks must be the same aspect ratio and resolution as your camera. 
+
+The mask in the second image would limit motion detection on this camera to only the front yard and not the street. 
+
+<a href="docs/example-mask-check-point.png"><img src="docs/example-mask-check-point.png" height="300"></a>
+<a href="docs/example-mask.bmp"><img src="docs/example-mask.bmp" height="300"></a>
+<a href="docs/example-mask-overlay.png"><img src="docs/example-mask-overlay.png" height="300"></a>
+
+To create a poly mask:
+1. Download a camera snapshot image with the same resolution as the camera feed (`/<camera_name>/latest.jpg`).
+1. Upload the image to https://www.image-map.net/
+1. Select "shape" poly - start in the lowest left corner and place the first marker (point) and continue upwards and then to the right until the polygon shape covers the area that you want to mask out (ignore). 
+1. When you are finished with the polygon click "Show me the code!" and copy all coordinates (point), ie. `"0,461,3,0,1919,0,1919,843,1699,492,1344,458,1346,336,973,317,869,375,866,432"` 
+1. Adjust any -1 values to 0 and then add it all to the configuration (see the example configuration for correct indentation and placement)
+
+Example of a finished row corresponding to the below example image:
+```yaml
+mask: 'poly,0,461,3,0,1919,0,1919,843,1699,492,1344,458,1346,336,973,317,869,375,866,432'
+```
+    
+<a href="docs/example-mask-poly.png"><img src="docs/example-mask-poly.png" height="300"></a>
+
+You can test your mask by temporarily configuring it as a [zone](#zones) and enabling `draw_zones` in your config. Zones are visible on the [MJPEG feed](#camera_name).
+
+[Back to top](#documentation)
+
+## Zones
+Zones allow you to define a specific area of the frame and apply additional filters for object types so you can determine whether or not an object is within a particular area. Zones cannot have the same name as a camera. If desired, a single zone can include multiple cameras if you have multiple cameras covering the same area by configuring zones with the same name for each camera.
+
+During testing, `draw_zones` should be set in the config to draw the zone on the frames so you can adjust as needed. The zone line will increase in thickness when any object enters the zone. Zones are visible on the [MJPEG feed](#camera_name).
+
+![Zone Example](docs/zone_example.jpg)
+
+[Back to top](#documentation)
+
+## Recording Clips
+**Note**: Previous versions of frigate included `-vsync drop` in input parameters. This is not compatible with FFmpeg's segment feature and must be removed from your input parameters if you have overrides set.
+
+Frigate can save video clips without any CPU overhead for encoding by simply copying the stream directly with FFmpeg. It leverages FFmpeg's segment functionality to maintain a cache of video for each camera. The cache files are written to disk at `cache_dir` and do not introduce memory overhead. When an object is being tracked, it will extend the cache to ensure it can assemble a clip when the event ends. Once the event ends, it again uses FFmpeg to assemble a clip by combining the video clips without any encoding by the CPU. Assembled clips are are saved to the `clips_dir` directory along with a json file containing the current information about the tracked object.
+
+### Global Configuration Options
+- `max_seconds`: This limits the size of the cache when an object is being tracked. If an object is stationary and being tracked for a long time, the cache files will expire and this value will be the maximum clip length for the *end* of the event. For example, if this is set to 300 seconds and an object is being tracked for 600 seconds, the clip will end up being the last 300 seconds. Defaults to 300 seconds.
+
+### Per-camera Configuration Options
+- `pre_capture`: Defines how much time should be included in the clip prior to the beginning of the event. Defaults to 30 seconds.
+- `objects`: List of object types to save clips for. Object types here must be listed for tracking at the camera or global configuration. Defaults to all tracked objects.
+
+[Back to top](#documentation)
 
 ## Integration with HomeAssistant
-```
+Setup a camera, binary_sensor, sensor and optionally automation as shown for each camera you define in frigate. Replace <camera_name> with the camera name as defined in the frigate `config.yml` (The `frigate_coral_fps` and `frigate_coral_inference` sensors only need to be defined once)
+
+```yaml
 camera:
-  - name: Camera Last Person
-    platform: generic
-    still_image_url: http://<ip>:5000/<camera_name>/best_person.jpg
+  - name: <camera_name> Last Person
+    platform: mqtt
+    topic: frigate/<camera_name>/person/snapshot
+  - name: <camera_name> Last Car
+    platform: mqtt
+    topic: frigate/<camera_name>/car/snapshot
+
+binary_sensor:
+  - name: <camera_name> Person
+    platform: mqtt
+    state_topic: "frigate/<camera_name>/person"
+    device_class: motion
+    availability_topic: "frigate/available"
 
 sensor:
-  - name: Camera Person
-    platform: mqtt
-    state_topic: "frigate/<camera_name>/objects"
-    value_template: '{{ value_json.person }}'
-    device_class: moving
-    availability_topic: "frigate/available"
+  - platform: rest
+    name: Frigate Debug
+    resource: http://localhost:5000/debug/stats
+    scan_interval: 5
+    json_attributes:
+      - <camera_name>
+      - detection_fps
+      - detectors
+    value_template: 'OK'  
+  - platform: template
+    sensors:
+      <camera_name>_fps: 
+        value_template: '{{ states.sensor.frigate_debug.attributes["<camera_name>"]["camera_fps"] }}'
+        unit_of_measurement: 'FPS'
+      <camera_name>_skipped_fps: 
+        value_template: '{{ states.sensor.frigate_debug.attributes["<camera_name>"]["skipped_fps"] }}'
+        unit_of_measurement: 'FPS'
+      <camera_name>_detection_fps: 
+        value_template: '{{ states.sensor.frigate_debug.attributes["<camera_name>"]["detection_fps"] }}'
+        unit_of_measurement: 'FPS'
+      frigate_detection_fps: 
+        value_template: '{{ states.sensor.frigate_debug.attributes["detection_fps"] }}'
+        unit_of_measurement: 'FPS'
+      frigate_coral_inference:
+        value_template: '{{ states.sensor.frigate_debug.attributes["detectors"]["coral"]["inference_speed"] }}' 
+        unit_of_measurement: 'ms'
+        
+automation:
+  - alias: Alert me if a person is detected while armed away
+    trigger: 
+      platform: state
+      entity_id: binary_sensor.camera_person
+      from: 'off'
+      to: 'on'
+    condition:
+      - condition: state
+        entity_id: alarm_control_panel.home_alarm
+        state: armed_away
+    action:
+      - service: notify.user_telegram
+        data:
+          message: "A person was detected."
+          data:
+            photo:
+              - url: http://<ip>:5000/<camera_name>/person/best.jpg
+                caption: A person was detected.        
 ```
 
-## Tips
-- Lower the framerate of the RTSP feed on the camera to reduce the CPU usage for capturing the feed
+[Back to top](#documentation)
+
+## HTTP Endpoints
+A web server is available on port 5000 with the following endpoints.
+
+### `/<camera_name>`
+An mjpeg stream for debugging. Keep in mind the mjpeg endpoint is for debugging only and will put additional load on the system when in use. 
+
+You can access a higher resolution mjpeg stream by appending `h=height-in-pixels` to the endpoint. For example `http://localhost:5000/back?h=1080`. You can also increase the FPS by appending `fps=frame-rate` to the URL such as `http://localhost:5000/back?fps=10` or both with `?fps=10&h=1000`
+
+### `/<camera_name>/<object_name>/best.jpg[?h=300&crop=1]`
+The best snapshot for any object type. It is a full resolution image by default.
+
+Example parameters:
+- `h=300`: resizes the image to 300 pixes tall
+- `crop=1`: crops the image to the region of the detection rather than returning the entire image
+
+### `/<camera_name>/latest.jpg[?h=300]`
+The most recent frame that frigate has finished processing. It is a full resolution image by default.
+
+Example parameters:
+- `h=300`: resizes the image to 300 pixes tall
+
+### `/debug/stats`
+Contains some granular debug info that can be used for sensors in HomeAssistant.
+
+Sample response:
+```jsonc
+{
+    /* Per Camera Stats */
+    "back": {
+        /***************
+        * Frames per second being consumed from your camera. If this is higher
+        * than it is supposed to be, you should set -r FPS in your input_args.
+        * camera_fps = process_fps + skipped_fps
+        ***************/
+        "camera_fps": 5.0,
+        /***************
+        * Number of times detection is run per second. This can be higher than
+        * your camera FPS because frigate often looks at the same frame multiple times
+        * or in multiple locations
+        ***************/
+        "detection_fps": 1.5,
+        /***************
+        * PID for the ffmpeg process that consumes this camera
+        ***************/
+        "ffmpeg_pid": 27,
+        /***************
+        * Timestamps of frames in various parts of processing
+        ***************/
+        "frame_info": {
+            /***************
+            * Timestamp of the frame frigate is running object detection on.
+            ***************/
+            "detect": 1596994991.91426,
+            /***************
+            * Timestamp of the frame frigate is processing detected objects on.
+            * This is where MQTT messages are sent, zones are checked, etc.
+            ***************/
+            "process": 1596994991.91426,
+            /***************
+            * Timestamp of the frame frigate last read from ffmpeg.
+            ***************/
+            "read": 1596994991.91426
+        },
+        /***************
+        * PID for the process that runs detection for this camera
+        ***************/
+        "pid": 34,
+        /***************
+        * Frames per second being processed by frigate.
+        ***************/
+        "process_fps": 5.1,
+        /***************
+        * Timestamp when the detection process started looking for a frame. If this value stays constant
+        * for a long time, that means there aren't any frames in the frame queue.
+        ***************/
+        "read_start": 1596994991.943814,
+        /***************
+        * Frames per second skip for processing by frigate.
+        ***************/
+        "skipped_fps": 0.0
+    },
+    /***************
+    * Sum of detection_fps across all cameras and detectors. 
+    * This should be the sum of all detection_fps values from cameras.
+    ***************/
+    "detection_fps": 5.0,
+    /* Detectors Stats */
+    "detectors": {
+      "coral": {
+          /***************
+          * Timestamp when object detection started. If this value stays non-zero and constant
+          * for a long time, that means the detection process is stuck.
+          ***************/
+          "detection_start": 0.0,
+          /***************
+          * Time spent running object detection in milliseconds.
+          ***************/
+          "inference_speed": 10.48,
+          /***************
+          * PID for the shared process that runs object detection on the Coral.
+          ***************/
+          "pid": 25321
+      }
+    }
+}
+```
+
+[Back to top](#documentation)
+
+## MQTT Topics
+These are the MQTT messages generated by Frigate. The default topic_prefix is `frigate`, but can be changed in the config file.
+
+### `frigate/available`
+Designed to be used as an availability topic with HomeAssistant. Possible message are:
+"online": published when frigate is running (on startup)
+"offline": published right before frigate stops
+
+### `frigate/<camera_name>/<object_name>`
+Publishes `ON` or `OFF` and is designed to be used a as a binary sensor in HomeAssistant for whether or not that object type is detected.
+
+### `frigate/<camera_name>/<object_name>/snapshot`
+Publishes a jpeg encoded frame of the detected object type. When the object is no longer detected, the highest confidence image is published or the original image
+is published again.
+
+The height and crop of snapshots can be configured in the config.
+
+### `frigate/<camera_name>/events/start`
+Message published at the start of any tracked object. JSON looks as follows:
+```json
+{
+    "label": "person",
+    "score": 0.87890625,
+    "box": [
+        95,
+        155,
+        581,
+        1182
+    ],
+    "area": 499122,
+    "region": [
+        0,
+        132,
+        1080,
+        1212
+    ],
+    "frame_time": 1600208805.60284,
+    "centroid": [
+        338,
+        668
+    ],
+    "id": "1600208805.60284-k1l43p",
+    "start_time": 1600208805.60284,
+    "top_score": 0.87890625,
+    "zones": [],
+    "score_history": [
+        0.87890625
+    ],
+    "computed_score": 0.0,
+    "false_positive": true
+}
+```
+
+### `frigate/<camera_name>/events/end`
+Same as `frigate/<camera_name>/events/start`, but with an `end_time` property as well.
+
+### `frigate/<zone_name>/<object_name>`
+Publishes `ON` when the object enters the zone and `OFF` when the object disappears or exits the zone. Designed to be used a as a binary sensor in HomeAssistant for whether or not that object type is detected in the zone.
+
+[Back to top](#documentation)
+
+## Custom Models
+Models for both CPU and EdgeTPU (Coral) are bundled in the image. You can use your own models with volume mounts:
+- CPU Model: `/cpu_model.tflite`
+- EdgeTPU Model: `/edgetpu_model.tflite`
+- Labels: `/labelmap.txt`
+
+### Customizing the Labelmap
+The labelmap can be customized to your needs. A common reason to do this is to combine multiple object types that are easily confused when you don't need to be as granular such as car/truck. You must retain the same number of labels, but you can change the names. To change:
+
+- Download the [COCO labelmap](https://dl.google.com/coral/canned_models/coco_labels.txt)
+- Modify the label names as desired. For example, change `7 truck` to `7 car`
+- Mount the new file at `/labelmap.txt` in the container with an additional volume
+  ```
+  -v ./config/labelmap.txt:/labelmap.txt
+  ```
+
+[Back to top](#documentation)
+
+## Troubleshooting
+
+### "ffmpeg didnt return a frame. something is wrong"
+Turn on logging for the camera by overriding the global_args and setting the log level to `info`:
+```yaml
+ffmpeg:
+  global_args:
+    - -hide_banner
+    - -loglevel
+    - info
+```
+
+### "On connect called"
+If you see repeated "On connect called" messages in your config, check for another instance of frigate. This happens when multiple frigate containers are trying to connect to mqtt with the same client_id.
+
+[Back to top](#documentation)
 
-## Future improvements
-- [x] Remove motion detection for now
-- [x] Try running object detection in a thread rather than a process
-- [x] Implement min person size again
-- [x] Switch to a config file
-- [x] Handle multiple cameras in the same container
-- [ ] Attempt to figure out coral symlinking
-- [ ] Add object list to config with min scores for mqtt
-- [ ] Move mjpeg encoding to a separate process
-- [ ] Simplify motion detection (check entire image against mask, resize instead of gaussian blur)
-- [ ] See if motion detection is even worth running
-- [ ] Scan for people across entire image rather than specfic regions
-- [ ] Dynamically resize detection area and follow people
-- [ ] Add ability to turn detection on and off via MQTT
-- [ ] Output movie clips of people for notifications, etc.
-- [ ] Integrate with homeassistant push camera
-- [ ] Merge bounding boxes that span multiple regions
-- [ ] Implement mode to save labeled objects for training
-- [ ] Try and reduce CPU usage by simplifying the tensorflow model to just include the objects we care about
-- [ ] Look into GPU accelerated decoding of RTSP stream
-- [ ] Send video over a socket and use JSMPEG
-- [x] Look into neural compute stick

benchmark.py

@@ -0,0 +1,93 @@
+import os
+from statistics import mean
+import multiprocessing as mp
+import numpy as np
+import datetime
+from frigate.edgetpu import LocalObjectDetector, EdgeTPUProcess, RemoteObjectDetector, load_labels
+
+my_frame = np.expand_dims(np.full((300,300,3), 1, np.uint8), axis=0)
+labels = load_labels('/labelmap.txt')
+
+######
+# Minimal same process runner
+######
+# object_detector = LocalObjectDetector()
+# tensor_input = np.expand_dims(np.full((300,300,3), 0, np.uint8), axis=0)
+
+# start = datetime.datetime.now().timestamp()
+
+# frame_times = []
+# for x in range(0, 1000):
+#   start_frame = datetime.datetime.now().timestamp()
+
+#   tensor_input[:] = my_frame
+#   detections = object_detector.detect_raw(tensor_input)
+#   parsed_detections = []
+#   for d in detections:
+#       if d[1] < 0.4:
+#           break
+#       parsed_detections.append((
+#           labels[int(d[0])],
+#           float(d[1]),
+#           (d[2], d[3], d[4], d[5])
+#       ))
+#   frame_times.append(datetime.datetime.now().timestamp()-start_frame)
+
+# duration = datetime.datetime.now().timestamp()-start
+# print(f"Processed for {duration:.2f} seconds.")
+# print(f"Average frame processing time: {mean(frame_times)*1000:.2f}ms")
+
+
+def start(id, num_detections, detection_queue, event):
+  object_detector = RemoteObjectDetector(str(id), '/labelmap.txt', detection_queue, event)
+  start = datetime.datetime.now().timestamp()
+
+  frame_times = []
+  for x in range(0, num_detections):
+    start_frame = datetime.datetime.now().timestamp()
+    detections = object_detector.detect(my_frame)
+    frame_times.append(datetime.datetime.now().timestamp()-start_frame)
+
+  duration = datetime.datetime.now().timestamp()-start
+  object_detector.cleanup()
+  print(f"{id} - Processed for {duration:.2f} seconds.")
+  print(f"{id} - FPS: {object_detector.fps.eps():.2f}")
+  print(f"{id} - Average frame processing time: {mean(frame_times)*1000:.2f}ms")
+
+######
+# Separate process runner
+######
+# event = mp.Event()
+# detection_queue = mp.Queue()
+# edgetpu_process = EdgeTPUProcess(detection_queue, {'1': event}, 'usb:0')
+
+# start(1, 1000, edgetpu_process.detection_queue, event)
+# print(f"Average raw inference speed: {edgetpu_process.avg_inference_speed.value*1000:.2f}ms")
+
+####
+# Multiple camera processes
+####
+camera_processes = []
+
+events = {}
+for x in range(0, 10):
+  events[str(x)] = mp.Event()
+detection_queue = mp.Queue()
+edgetpu_process_1 = EdgeTPUProcess(detection_queue, events, 'usb:0')
+edgetpu_process_2 = EdgeTPUProcess(detection_queue, events, 'usb:1')
+
+for x in range(0, 10):
+  camera_process = mp.Process(target=start, args=(x, 300, detection_queue, events[str(x)]))
+  camera_process.daemon = True
+  camera_processes.append(camera_process)
+
+start_time = datetime.datetime.now().timestamp()
+
+for p in camera_processes:
+  p.start()
+
+for p in camera_processes:
+  p.join()
+
+duration = datetime.datetime.now().timestamp()-start_time
+print(f"Total - Processed for {duration:.2f} seconds.")

config/config.yml

@@ -1,29 +0,0 @@
-web_port: 5000
-
-mqtt:
-  host: mqtt.server.com
-  topic_prefix: frigate
-
-cameras:
-  back:
-    rtsp:
-      user: viewer
-      host: 10.0.10.10
-      port: 554
-      # values that begin with a "$" will be replaced with environment variable
-      password: $RTSP_PASSWORD
-      path: /cam/realmonitor?channel=1&subtype=2
-    mask: back-mask.bmp
-    regions:
-      - size: 350
-        x_offset: 0
-        y_offset: 300
-        min_person_area: 5000
-      - size: 400
-        x_offset: 350
-        y_offset: 250
-        min_person_area: 2000
-      - size: 400
-        x_offset: 750
-        y_offset: 250
-        min_person_area: 2000

detect_objects.py

@@ -1,90 +1,441 @@
+import faulthandler; faulthandler.enable()
+import os
+import signal
+import sys
+import traceback
+import signal
 import cv2
 import time
+import datetime
 import queue
 import yaml
+import json
+import threading
+import multiprocessing as mp
+import subprocess as sp
 import numpy as np
-from flask import Flask, Response, make_response
+import logging
+from flask import Flask, Response, make_response, jsonify, request
 import paho.mqtt.client as mqtt
 
-from frigate.video import Camera
-from frigate.object_detection import PreppedQueueProcessor
+from frigate.video import capture_camera, track_camera, get_ffmpeg_input, get_frame_shape, CameraCapture, start_or_restart_ffmpeg
+from frigate.object_processing import TrackedObjectProcessor
+from frigate.events import EventProcessor
+from frigate.util import EventsPerSecond
+from frigate.edgetpu import EdgeTPUProcess
 
-with open('/config/config.yml') as f:
-    CONFIG = yaml.safe_load(f)
+FRIGATE_VARS = {k: v for k, v in os.environ.items() if k.startswith('FRIGATE_')}
+
+CONFIG_FILE = os.environ.get('CONFIG_FILE', '/config/config.yml')
+
+if CONFIG_FILE.endswith(".yml"):
+    with open(CONFIG_FILE) as f:
+        CONFIG = yaml.safe_load(f)
+elif CONFIG_FILE.endswith(".json"):
+    with open(CONFIG_FILE) as f:
+        CONFIG = json.load(f)
+
+CACHE_DIR = CONFIG.get('save_clips', {}).get('cache_dir', '/cache')
+CLIPS_DIR = CONFIG.get('save_clips', {}).get('clips_dir', '/clips')
+
+if not os.path.exists(CACHE_DIR) and not os.path.islink(CACHE_DIR):
+    os.makedirs(CACHE_DIR)
+if not os.path.exists(CLIPS_DIR) and not os.path.islink(CLIPS_DIR):
+    os.makedirs(CLIPS_DIR)
 
 MQTT_HOST = CONFIG['mqtt']['host']
 MQTT_PORT = CONFIG.get('mqtt', {}).get('port', 1883)
 MQTT_TOPIC_PREFIX = CONFIG.get('mqtt', {}).get('topic_prefix', 'frigate')
 MQTT_USER = CONFIG.get('mqtt', {}).get('user')
 MQTT_PASS = CONFIG.get('mqtt', {}).get('password')
+if not MQTT_PASS is None:
+    MQTT_PASS = MQTT_PASS.format(**FRIGATE_VARS)
+MQTT_CLIENT_ID = CONFIG.get('mqtt', {}).get('client_id', 'frigate')
+
+# Set the default FFmpeg config
+FFMPEG_CONFIG = CONFIG.get('ffmpeg', {})
+FFMPEG_DEFAULT_CONFIG = {
+    'global_args': FFMPEG_CONFIG.get('global_args', 
+        ['-hide_banner','-loglevel','panic']),
+    'hwaccel_args': FFMPEG_CONFIG.get('hwaccel_args',
+        []),
+    'input_args': FFMPEG_CONFIG.get('input_args',
+        ['-avoid_negative_ts', 'make_zero',
+         '-fflags', 'nobuffer',
+         '-flags', 'low_delay',
+         '-strict', 'experimental',
+         '-fflags', '+genpts+discardcorrupt',
+         '-rtsp_transport', 'tcp',
+         '-stimeout', '5000000',
+         '-use_wallclock_as_timestamps', '1']),
+    'output_args': FFMPEG_CONFIG.get('output_args',
+        ['-f', 'rawvideo',
+         '-pix_fmt', 'yuv420p'])
+}
+
+GLOBAL_OBJECT_CONFIG = CONFIG.get('objects', {})
 
 WEB_PORT = CONFIG.get('web_port', 5000)
-DEBUG = (CONFIG.get('debug', '0') == '1')
+DETECTORS = CONFIG.get('detectors', {'coral': {'type': 'edgetpu', 'device': 'usb'}})
+
+class FrigateWatchdog(threading.Thread):
+    def __init__(self, camera_processes, config, detectors, detection_queue, out_events, tracked_objects_queue, stop_event):
+        threading.Thread.__init__(self)
+        self.camera_processes = camera_processes
+        self.config = config
+        self.detectors = detectors
+        self.detection_queue = detection_queue
+        self.out_events = out_events
+        self.tracked_objects_queue = tracked_objects_queue
+        self.stop_event = stop_event
+
+    def run(self):
+        time.sleep(10)
+        while True:
+            # wait a bit before checking
+            time.sleep(10)
+
+            if self.stop_event.is_set():
+                print(f"Exiting watchdog...")
+                break
+
+            now = datetime.datetime.now().timestamp()
+
+            # check the detection processes
+            for detector in self.detectors.values():
+                detection_start = detector.detection_start.value
+                if (detection_start > 0.0 and 
+                    now - detection_start > 10):
+                    print("Detection appears to be stuck. Restarting detection process")
+                    detector.start_or_restart()
+                elif not detector.detect_process.is_alive():
+                    print("Detection appears to have stopped. Restarting detection process")
+                    detector.start_or_restart()
+
+            # check the camera processes
+            for name, camera_process in self.camera_processes.items():
+                process = camera_process['process']
+                if not process.is_alive():
+                    print(f"Track process for {name} is not alive. Starting again...")
+                    camera_process['camera_fps'].value = 0.0
+                    camera_process['process_fps'].value = 0.0
+                    camera_process['detection_fps'].value = 0.0
+                    camera_process['read_start'].value = 0.0
+                    process = mp.Process(target=track_camera, args=(name, self.config,
+                        self.detection_queue, self.out_events[name], self.tracked_objects_queue, camera_process, self.stop_event))
+                    process.daemon = True
+                    camera_process['process'] = process
+                    process.start()
+                    print(f"Track process started for {name}: {process.pid}")
 
 def main():
+    stop_event = threading.Event()
     # connect to mqtt and setup last will
     def on_connect(client, userdata, flags, rc):
         print("On connect called")
+        if rc != 0:
+            if rc == 3:
+                print ("MQTT Server unavailable")
+            elif rc == 4:
+                print ("MQTT Bad username or password")
+            elif rc == 5:
+                print ("MQTT Not authorized")
+            else:
+                print ("Unable to connect to MQTT: Connection refused. Error code: " + str(rc))
         # publish a message to signal that the service is running
         client.publish(MQTT_TOPIC_PREFIX+'/available', 'online', retain=True)
-    client = mqtt.Client()
+    client = mqtt.Client(client_id=MQTT_CLIENT_ID)
     client.on_connect = on_connect
     client.will_set(MQTT_TOPIC_PREFIX+'/available', payload='offline', qos=1, retain=True)
     if not MQTT_USER is None:
         client.username_pw_set(MQTT_USER, password=MQTT_PASS)
     client.connect(MQTT_HOST, MQTT_PORT, 60)
     client.loop_start()
-    
-    # Queue for prepped frames, max size set to (number of cameras * 5)
-    max_queue_size = len(CONFIG['cameras'].items())*5
-    prepped_frame_queue = queue.Queue(max_queue_size)
 
-    cameras = {}
+    ##
+    # Setup config defaults for cameras
+    ##
     for name, config in CONFIG['cameras'].items():
-        cameras[name] = Camera(name, config, prepped_frame_queue, client, MQTT_TOPIC_PREFIX)
+        config['snapshots'] = {
+            'show_timestamp': config.get('snapshots', {}).get('show_timestamp', True),
+            'draw_zones': config.get('snapshots', {}).get('draw_zones', False),
+            'draw_bounding_boxes': config.get('snapshots', {}).get('draw_bounding_boxes', True)
+        }
+        config['zones'] = config.get('zones', {})
 
-    prepped_queue_processor = PreppedQueueProcessor(
-        cameras,
-        prepped_frame_queue
-    )
-    prepped_queue_processor.start()
+    # Queue for cameras to push tracked objects to
+    tracked_objects_queue = mp.Queue(maxsize=len(CONFIG['cameras'].keys())*2)
 
-    for name, camera in cameras.items():
-        camera.start()
-        print("Capture process for {}: {}".format(name, camera.get_capture_pid()))
+    # Queue for clip processing
+    event_queue = mp.Queue()
+
+    # create the detection pipes and shms
+    out_events = {}
+    camera_shms = []
+    for name in CONFIG['cameras'].keys():
+        out_events[name] = mp.Event()
+        shm_in = mp.shared_memory.SharedMemory(name=name, create=True, size=300*300*3)
+        shm_out = mp.shared_memory.SharedMemory(name=f"out-{name}", create=True, size=20*6*4)
+        camera_shms.append(shm_in)
+        camera_shms.append(shm_out)
+
+    detection_queue = mp.Queue()
+
+    detectors = {}
+    for name, detector in DETECTORS.items():
+        if detector['type'] == 'cpu':
+            detectors[name] = EdgeTPUProcess(detection_queue, out_events=out_events, tf_device='cpu')
+        if detector['type'] == 'edgetpu':
+            detectors[name] = EdgeTPUProcess(detection_queue, out_events=out_events, tf_device=detector['device'])
+
+    # create the camera processes
+    camera_process_info = {}
+    for name, config in CONFIG['cameras'].items():
+        # Merge the ffmpeg config with the global config
+        ffmpeg = config.get('ffmpeg', {})
+        ffmpeg_input = get_ffmpeg_input(ffmpeg['input'])
+        ffmpeg_global_args = ffmpeg.get('global_args', FFMPEG_DEFAULT_CONFIG['global_args'])
+        ffmpeg_hwaccel_args = ffmpeg.get('hwaccel_args', FFMPEG_DEFAULT_CONFIG['hwaccel_args'])
+        ffmpeg_input_args = ffmpeg.get('input_args', FFMPEG_DEFAULT_CONFIG['input_args'])
+        ffmpeg_output_args = ffmpeg.get('output_args', FFMPEG_DEFAULT_CONFIG['output_args'])
+        if not config.get('fps') is None:
+            ffmpeg_output_args = ["-r", str(config.get('fps'))] + ffmpeg_output_args
+        if config.get('save_clips', {}).get('enabled', False):
+            ffmpeg_output_args = [
+                "-f",
+                "segment",
+                "-segment_time",
+                "10",
+                "-segment_format",
+                "mp4",
+                "-reset_timestamps",
+                "1",
+                "-strftime",
+                "1",
+                "-c",
+                "copy",
+                "-an",
+                "-map",
+                "0",
+                f"{os.path.join(CACHE_DIR, name)}-%Y%m%d%H%M%S.mp4"
+            ] + ffmpeg_output_args
+        ffmpeg_cmd = (['ffmpeg'] +
+                ffmpeg_global_args +
+                ffmpeg_hwaccel_args +
+                ffmpeg_input_args +
+                ['-i', ffmpeg_input] +
+                ffmpeg_output_args +
+                ['pipe:'])
+        
+        config['ffmpeg_cmd'] = ffmpeg_cmd
+        
+        if 'width' in config and 'height' in config:
+            frame_shape = (config['height'], config['width'], 3)
+        else:
+            frame_shape = get_frame_shape(ffmpeg_input)
+        
+        config['frame_shape'] = frame_shape
+        config['take_frame'] = config.get('take_frame', 1)
+
+        camera_process_info[name] = {
+            'camera_fps': mp.Value('d', 0.0),
+            'skipped_fps': mp.Value('d', 0.0),
+            'process_fps': mp.Value('d', 0.0),
+            'detection_fps': mp.Value('d', 0.0),
+            'detection_frame': mp.Value('d', 0.0),
+            'read_start': mp.Value('d', 0.0),
+            'ffmpeg_pid': mp.Value('i', 0),
+            'frame_queue': mp.Queue(maxsize=2)
+        }
+
+        # merge global object config into camera object config
+        camera_objects_config = config.get('objects', {})
+        # get objects to track for camera
+        objects_to_track = camera_objects_config.get('track', GLOBAL_OBJECT_CONFIG.get('track', ['person']))
+        # get object filters
+        object_filters = camera_objects_config.get('filters', GLOBAL_OBJECT_CONFIG.get('filters', {}))
+        config['objects'] = {
+            'track': objects_to_track,
+            'filters': object_filters
+        }
+
+        capture_process = mp.Process(target=capture_camera, args=(name, config,
+            camera_process_info[name], stop_event))
+        capture_process.daemon = True
+        camera_process_info[name]['capture_process'] = capture_process
+
+        camera_process = mp.Process(target=track_camera, args=(name, config,
+            detection_queue, out_events[name], tracked_objects_queue, camera_process_info[name], stop_event))
+        camera_process.daemon = True
+        camera_process_info[name]['process'] = camera_process
+
+    # start the camera_processes
+    for name, camera_process in camera_process_info.items():
+        camera_process['capture_process'].start()
+        print(f"Camera capture process started for {name}: {camera_process['capture_process'].pid}")
+        camera_process['process'].start()
+        print(f"Camera process started for {name}: {camera_process['process'].pid}")
+
+    event_processor = EventProcessor(CONFIG, camera_process_info, CACHE_DIR, CLIPS_DIR, event_queue, stop_event)
+    event_processor.start()
+    
+    object_processor = TrackedObjectProcessor(CONFIG['cameras'], client, MQTT_TOPIC_PREFIX, tracked_objects_queue, event_queue, stop_event)
+    object_processor.start()
+    
+    frigate_watchdog = FrigateWatchdog(camera_process_info, CONFIG['cameras'], detectors, detection_queue, out_events, tracked_objects_queue, stop_event)
+    frigate_watchdog.start()
+
+    def receiveSignal(signalNumber, frame):
+        print('Received:', signalNumber)
+        stop_event.set()
+        event_processor.join()
+        object_processor.join()
+        frigate_watchdog.join()
+
+        for detector in detectors.values():
+            detector.stop()
+        for shm in camera_shms:
+            shm.close()
+            shm.unlink()
+        sys.exit()
+    
+    signal.signal(signal.SIGTERM, receiveSignal)
+    signal.signal(signal.SIGINT, receiveSignal)
 
     # create a flask app that encodes frames a mjpeg on demand
     app = Flask(__name__)
+    log = logging.getLogger('werkzeug')
+    log.setLevel(logging.ERROR)
 
-    @app.route('/<camera_name>/best_person.jpg')
-    def best_person(camera_name):
-        best_person_frame = cameras[camera_name].get_best_person()
-        if best_person_frame is None:
-            best_person_frame = np.zeros((720,1280,3), np.uint8)
-        ret, jpg = cv2.imencode('.jpg', best_person_frame)
-        response = make_response(jpg.tobytes())
-        response.headers['Content-Type'] = 'image/jpg'
-        return response
+    @app.route('/')
+    def ishealthy():
+        # return a healh
+        return "Frigate is running. Alive and healthy!"
+
+    @app.route('/debug/stack')
+    def processor_stack():
+        frame = sys._current_frames().get(object_processor.ident, None)
+        if frame:
+            return "<br>".join(traceback.format_stack(frame)), 200
+        else:
+            return "no frame found", 200
+
+    @app.route('/debug/print_stack')
+    def print_stack():
+        pid = int(request.args.get('pid', 0))
+        if pid == 0:
+            return "missing pid", 200
+        else:
+            os.kill(pid, signal.SIGUSR1)
+            return "check logs", 200
+
+    @app.route('/debug/stats')
+    def stats():
+        stats = {}
+
+        total_detection_fps = 0
+
+        for name, camera_stats in camera_process_info.items():
+            total_detection_fps += camera_stats['detection_fps'].value
+            stats[name] = {
+                'camera_fps': round(camera_stats['camera_fps'].value, 2),
+                'process_fps': round(camera_stats['process_fps'].value, 2),
+                'skipped_fps': round(camera_stats['skipped_fps'].value, 2),
+                'detection_fps': round(camera_stats['detection_fps'].value, 2),
+                'pid': camera_stats['process'].pid,
+                'capture_pid': camera_stats['capture_process'].pid,
+                'frame_info': {
+                    'detect': camera_stats['detection_frame'].value,
+                    'process': object_processor.camera_data[name]['current_frame_time']
+                }
+            }
+        
+        stats['detectors'] = {}
+        for name, detector in detectors.items():
+            stats['detectors'][name] = {
+                'inference_speed': round(detector.avg_inference_speed.value*1000, 2),
+                'detection_start': detector.detection_start.value,
+                'pid': detector.detect_process.pid
+            }
+        stats['detection_fps'] = round(total_detection_fps, 2)
+
+        return jsonify(stats)
+
+    @app.route('/<camera_name>/<label>/best.jpg')
+    def best(camera_name, label):
+        if camera_name in CONFIG['cameras']:
+            best_object = object_processor.get_best(camera_name, label)
+            best_frame = best_object.get('frame')
+            if best_frame is None:
+                best_frame = np.zeros((720,1280,3), np.uint8)
+            else:
+                best_frame = cv2.cvtColor(best_frame, cv2.COLOR_YUV2BGR_I420)
+            
+            crop = bool(request.args.get('crop', 0, type=int))
+            if crop:
+                region = best_object.get('region', [0,0,300,300])
+                best_frame = best_frame[region[1]:region[3], region[0]:region[2]]
+            
+            height = int(request.args.get('h', str(best_frame.shape[0])))
+            width = int(height*best_frame.shape[1]/best_frame.shape[0])
+
+            best_frame = cv2.resize(best_frame, dsize=(width, height), interpolation=cv2.INTER_AREA)
+            ret, jpg = cv2.imencode('.jpg', best_frame)
+            response = make_response(jpg.tobytes())
+            response.headers['Content-Type'] = 'image/jpg'
+            return response
+        else:
+            return "Camera named {} not found".format(camera_name), 404
 
     @app.route('/<camera_name>')
     def mjpeg_feed(camera_name):
-        # return a multipart response
-        return Response(imagestream(camera_name),
-                        mimetype='multipart/x-mixed-replace; boundary=frame')
+        fps = int(request.args.get('fps', '3'))
+        height = int(request.args.get('h', '360'))
+        if camera_name in CONFIG['cameras']:
+            # return a multipart response
+            return Response(imagestream(camera_name, fps, height),
+                            mimetype='multipart/x-mixed-replace; boundary=frame')
+        else:
+            return "Camera named {} not found".format(camera_name), 404
+    
+    @app.route('/<camera_name>/latest.jpg')
+    def latest_frame(camera_name):
+        if camera_name in CONFIG['cameras']:
+            # max out at specified FPS
+            frame = object_processor.get_current_frame(camera_name)
+            if frame is None:
+                frame = np.zeros((720,1280,3), np.uint8)
 
-    def imagestream(camera_name):
+            height = int(request.args.get('h', str(frame.shape[0])))
+            width = int(height*frame.shape[1]/frame.shape[0])
+
+            frame = cv2.resize(frame, dsize=(width, height), interpolation=cv2.INTER_AREA)
+
+            ret, jpg = cv2.imencode('.jpg', frame)
+            response = make_response(jpg.tobytes())
+            response.headers['Content-Type'] = 'image/jpg'
+            return response
+        else:
+            return "Camera named {} not found".format(camera_name), 404
+            
+    def imagestream(camera_name, fps, height):
         while True:
-            # max out at 5 FPS
-            time.sleep(0.2)
-            frame = cameras[camera_name].get_current_frame_with_objects()
-            # encode the image into a jpg
+            # max out at specified FPS
+            time.sleep(1/fps)
+            frame = object_processor.get_current_frame(camera_name, draw=True)
+            if frame is None:
+                frame = np.zeros((height,int(height*16/9),3), np.uint8)
+
+            width = int(height*frame.shape[1]/frame.shape[0])
+            frame = cv2.resize(frame, dsize=(width, height), interpolation=cv2.INTER_LINEAR)
+
             ret, jpg = cv2.imencode('.jpg', frame)
             yield (b'--frame\r\n'
                 b'Content-Type: image/jpeg\r\n\r\n' + jpg.tobytes() + b'\r\n\r\n')
 
     app.run(host='0.0.0.0', port=WEB_PORT, debug=False)
 
-    camera.join()
+    object_processor.join()
 
 if __name__ == '__main__':
-    main()
+    main()

docker/Dockerfile.aarch64

@@ -0,0 +1,22 @@
+FROM frigate-base
+LABEL maintainer "blakeb@blakeshome.com"
+
+ENV DEBIAN_FRONTEND=noninteractive
+# Install packages for apt repo
+RUN apt-get -qq update \
+    && apt-get -qq install --no-install-recommends -y \
+        # ffmpeg runtime dependencies
+        libgomp1 \
+        # runtime dependencies
+        libopenexr24 \
+        libgstreamer1.0-0 \
+        libgstreamer-plugins-base1.0-0 \
+        libopenblas-base \
+        libjpeg-turbo8 \
+        libpng16-16 \
+        libtiff5 \
+        libdc1394-22 \
+    ## Tensorflow lite
+    && pip3 install https://dl.google.com/coral/python/tflite_runtime-2.1.0.post1-cp38-cp38-linux_aarch64.whl \
+    && rm -rf /var/lib/apt/lists/* \
+    && (apt-get autoremove -y; apt-get autoclean -y)

docker/Dockerfile.amd64

@@ -0,0 +1,18 @@
+FROM frigate-base
+LABEL maintainer "blakeb@blakeshome.com"
+
+# By default, use the i965 driver
+ENV LIBVA_DRIVER_NAME=i965
+# Install packages for apt repo
+RUN apt-get -qq update \
+    && apt-get -qq install --no-install-recommends -y \
+        # ffmpeg dependencies
+        libgomp1 \
+        # VAAPI drivers for Intel hardware accel
+        libva-drm2 libva2 i965-va-driver vainfo intel-media-va-driver \
+        ## Tensorflow lite
+    && wget -q https://dl.google.com/coral/python/tflite_runtime-2.1.0.post1-cp38-cp38-linux_x86_64.whl \
+    && python3.8 -m pip install tflite_runtime-2.1.0.post1-cp38-cp38-linux_x86_64.whl \
+    && rm tflite_runtime-2.1.0.post1-cp38-cp38-linux_x86_64.whl \
+    && rm -rf /var/lib/apt/lists/* \
+    && (apt-get autoremove -y; apt-get autoclean -y)

docker/Dockerfile.armv7

@@ -0,0 +1,24 @@
+FROM frigate-base
+LABEL maintainer "blakeb@blakeshome.com"
+
+ENV DEBIAN_FRONTEND=noninteractive
+# Install packages for apt repo
+RUN apt-get -qq update \
+    && apt-get -qq install --no-install-recommends -y \
+        # ffmpeg runtime dependencies
+        libgomp1 \
+        # runtime dependencies
+        libopenexr24 \
+        libgstreamer1.0-0 \
+        libgstreamer-plugins-base1.0-0 \
+        libopenblas-base \
+        libjpeg-turbo8 \
+        libpng16-16 \
+        libtiff5 \
+        libdc1394-22 \
+        libaom0 \
+        libx265-179 \
+    ## Tensorflow lite
+    && pip3 install https://dl.google.com/coral/python/tflite_runtime-2.1.0.post1-cp38-cp38-linux_armv7l.whl \
+    && rm -rf /var/lib/apt/lists/* \
+    && (apt-get autoremove -y; apt-get autoclean -y)

docker/Dockerfile.base

@@ -0,0 +1,44 @@
+ARG ARCH=amd64
+FROM blakeblackshear/frigate-wheels:${ARCH} as wheels
+FROM blakeblackshear/frigate-ffmpeg:${ARCH} as ffmpeg
+
+FROM ubuntu:20.04
+LABEL maintainer "blakeb@blakeshome.com"
+
+COPY --from=ffmpeg /usr/local /usr/local/
+
+COPY --from=wheels /wheels/. /wheels/
+
+ENV FLASK_ENV=development
+ENV DEBIAN_FRONTEND=noninteractive
+# Install packages for apt repo
+RUN apt-get -qq update \
+    && apt-get upgrade -y \
+    && apt-get -qq install --no-install-recommends -y \
+    gnupg wget unzip tzdata \
+    && apt-get -qq install --no-install-recommends -y \
+        python3-pip \
+    && pip3 install -U /wheels/*.whl \
+    && APT_KEY_DONT_WARN_ON_DANGEROUS_USAGE=DontWarn apt-key adv --fetch-keys https://packages.cloud.google.com/apt/doc/apt-key.gpg \
+    && echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" > /etc/apt/sources.list.d/coral-edgetpu.list \
+    && echo "libedgetpu1-max libedgetpu/accepted-eula select true" | debconf-set-selections \
+    && apt-get -qq update && apt-get -qq install --no-install-recommends -y \
+        libedgetpu1-max \
+    && rm -rf /var/lib/apt/lists/* /wheels \
+    && (apt-get autoremove -y; apt-get autoclean -y)
+
+# get model and labels
+ARG MODEL_REFS=7064b94dd5b996189242320359dbab8b52c94a84
+COPY labelmap.txt /labelmap.txt
+RUN wget -q https://github.com/google-coral/edgetpu/raw/$MODEL_REFS/test_data/ssd_mobilenet_v2_coco_quant_postprocess_edgetpu.tflite -O /edgetpu_model.tflite
+RUN wget -q https://github.com/google-coral/edgetpu/raw/$MODEL_REFS/test_data/ssd_mobilenet_v2_coco_quant_postprocess.tflite -O /cpu_model.tflite
+
+RUN mkdir /cache /clips
+
+WORKDIR /opt/frigate/
+ADD frigate frigate/
+COPY detect_objects.py .
+COPY benchmark.py .
+COPY process_clip.py .
+
+CMD ["python3", "-u", "detect_objects.py"]

docker/Dockerfile.ffmpeg.aarch64

@@ -0,0 +1,533 @@
+# inspired by:
+# https://github.com/collelog/ffmpeg/blob/master/4.3.1-alpine-rpi4-arm64v8.Dockerfile
+# https://github.com/mmastrac/ffmpeg-omx-rpi-docker/blob/master/Dockerfile
+# https://github.com/jrottenberg/ffmpeg/pull/158/files
+# https://github.com/jrottenberg/ffmpeg/pull/239
+FROM        ubuntu:20.04 AS base
+
+WORKDIR     /tmp/workdir
+
+ENV     DEBIAN_FRONTEND=noninteractive
+RUN     apt-get -yqq update && \
+        apt-get install -yq --no-install-recommends ca-certificates expat libgomp1 && \
+        apt-get autoremove -y && \
+        apt-get clean -y
+
+FROM base as build
+
+ENV         FFMPEG_VERSION=4.3.1 \
+            AOM_VERSION=v1.0.0 \
+            FDKAAC_VERSION=0.1.5 \
+            FONTCONFIG_VERSION=2.12.4 \
+            FREETYPE_VERSION=2.5.5 \
+            FRIBIDI_VERSION=0.19.7 \
+            KVAZAAR_VERSION=1.2.0 \
+            LAME_VERSION=3.100 \
+            LIBASS_VERSION=0.13.7 \
+            LIBPTHREAD_STUBS_VERSION=0.4 \
+            LIBVIDSTAB_VERSION=1.1.0 \
+            LIBXCB_VERSION=1.13.1 \
+            XCBPROTO_VERSION=1.13 \
+            OGG_VERSION=1.3.2 \
+            OPENCOREAMR_VERSION=0.1.5 \
+            OPUS_VERSION=1.2 \
+            OPENJPEG_VERSION=2.1.2 \
+            THEORA_VERSION=1.1.1 \
+            VORBIS_VERSION=1.3.5 \
+            VPX_VERSION=1.8.0 \
+            WEBP_VERSION=1.0.2 \
+            X264_VERSION=20170226-2245-stable \
+            X265_VERSION=3.1.1 \
+            XAU_VERSION=1.0.9 \
+            XORG_MACROS_VERSION=1.19.2 \
+            XPROTO_VERSION=7.0.31 \
+            XVID_VERSION=1.3.4 \
+            LIBXML2_VERSION=2.9.10 \
+            LIBBLURAY_VERSION=1.1.2 \
+            LIBZMQ_VERSION=4.3.2 \
+            SRC=/usr/local
+
+ARG         FREETYPE_SHA256SUM="5d03dd76c2171a7601e9ce10551d52d4471cf92cd205948e60289251daddffa8 freetype-2.5.5.tar.gz"
+ARG         FRIBIDI_SHA256SUM="3fc96fa9473bd31dcb5500bdf1aa78b337ba13eb8c301e7c28923fea982453a8 0.19.7.tar.gz"
+ARG         LIBASS_SHA256SUM="8fadf294bf701300d4605e6f1d92929304187fca4b8d8a47889315526adbafd7 0.13.7.tar.gz"
+ARG         LIBVIDSTAB_SHA256SUM="14d2a053e56edad4f397be0cb3ef8eb1ec3150404ce99a426c4eb641861dc0bb v1.1.0.tar.gz"
+ARG         OGG_SHA256SUM="e19ee34711d7af328cb26287f4137e70630e7261b17cbe3cd41011d73a654692 libogg-1.3.2.tar.gz"
+ARG         OPUS_SHA256SUM="77db45a87b51578fbc49555ef1b10926179861d854eb2613207dc79d9ec0a9a9 opus-1.2.tar.gz"
+ARG         THEORA_SHA256SUM="40952956c47811928d1e7922cda3bc1f427eb75680c3c37249c91e949054916b libtheora-1.1.1.tar.gz"
+ARG         VORBIS_SHA256SUM="6efbcecdd3e5dfbf090341b485da9d176eb250d893e3eb378c428a2db38301ce libvorbis-1.3.5.tar.gz"
+ARG         XVID_SHA256SUM="4e9fd62728885855bc5007fe1be58df42e5e274497591fec37249e1052ae316f xvidcore-1.3.4.tar.gz"
+ARG         LIBXML2_SHA256SUM="f07dab13bf42d2b8db80620cce7419b3b87827cc937c8bb20fe13b8571ee9501  libxml2-v2.9.10.tar.gz"
+ARG         LIBBLURAY_SHA256SUM="a3dd452239b100dc9da0d01b30e1692693e2a332a7d29917bf84bb10ea7c0b42 libbluray-1.1.2.tar.bz2"
+ARG         LIBZMQ_SHA256SUM="02ecc88466ae38cf2c8d79f09cfd2675ba299a439680b64ade733e26a349edeb v4.3.2.tar.gz"
+
+
+ARG         LD_LIBRARY_PATH=/opt/ffmpeg/lib
+ARG         MAKEFLAGS="-j2"
+ARG         PKG_CONFIG_PATH="/opt/ffmpeg/share/pkgconfig:/opt/ffmpeg/lib/pkgconfig:/opt/ffmpeg/lib64/pkgconfig"
+ARG         PREFIX=/opt/ffmpeg
+ARG         LD_LIBRARY_PATH="/opt/ffmpeg/lib:/opt/ffmpeg/lib64:/usr/lib64:/usr/lib:/lib64:/lib"
+
+
+RUN      buildDeps="autoconf \
+                    automake \
+                    cmake \
+                    curl \
+                    bzip2 \
+                    libexpat1-dev \
+                    g++ \
+                    gcc \
+                    git \
+                    gperf \
+                    libtool \
+                    make \
+                    nasm \
+                    perl \
+                    pkg-config \
+                    python \
+                    libssl-dev \
+                    yasm \
+                    linux-headers-raspi2 \
+                    libomxil-bellagio-dev \
+                    zlib1g-dev" && \
+        apt-get -yqq update && \
+        apt-get install -yq --no-install-recommends ${buildDeps}
+## opencore-amr https://sourceforge.net/projects/opencore-amr/
+RUN \
+        DIR=/tmp/opencore-amr && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://versaweb.dl.sourceforge.net/project/opencore-amr/opencore-amr/opencore-amr-${OPENCOREAMR_VERSION}.tar.gz | \
+        tar -zx --strip-components=1 && \
+        ./configure --prefix="${PREFIX}" --enable-shared  && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+## x264 http://www.videolan.org/developers/x264.html
+RUN \
+        DIR=/tmp/x264 && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://download.videolan.org/pub/videolan/x264/snapshots/x264-snapshot-${X264_VERSION}.tar.bz2 | \
+        tar -jx --strip-components=1 && \
+        ./configure --prefix="${PREFIX}" --enable-shared --enable-pic --disable-cli && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### x265 http://x265.org/
+RUN \
+        DIR=/tmp/x265 && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://download.videolan.org/pub/videolan/x265/x265_${X265_VERSION}.tar.gz  | \
+        tar -zx && \
+        cd x265_${X265_VERSION}/build/linux && \
+        sed -i "/-DEXTRA_LIB/ s/$/ -DCMAKE_INSTALL_PREFIX=\${PREFIX}/" multilib.sh && \
+        sed -i "/^cmake/ s/$/ -DENABLE_CLI=OFF/" multilib.sh && \
+        export CXXFLAGS="${CXXFLAGS} -fPIC" && \
+        ./multilib.sh && \
+        make -C 8bit install && \
+        rm -rf ${DIR}
+### libogg https://www.xiph.org/ogg/
+RUN \
+        DIR=/tmp/ogg && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO http://downloads.xiph.org/releases/ogg/libogg-${OGG_VERSION}.tar.gz && \
+        echo ${OGG_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f libogg-${OGG_VERSION}.tar.gz && \
+        ./configure --prefix="${PREFIX}" --enable-shared  && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### libopus https://www.opus-codec.org/
+RUN \
+        DIR=/tmp/opus && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://archive.mozilla.org/pub/opus/opus-${OPUS_VERSION}.tar.gz && \
+        echo ${OPUS_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f opus-${OPUS_VERSION}.tar.gz && \
+        autoreconf -fiv && \
+        ./configure --prefix="${PREFIX}" --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### libvorbis https://xiph.org/vorbis/
+RUN \
+        DIR=/tmp/vorbis && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO http://downloads.xiph.org/releases/vorbis/libvorbis-${VORBIS_VERSION}.tar.gz && \
+        echo ${VORBIS_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f libvorbis-${VORBIS_VERSION}.tar.gz && \
+        ./configure --prefix="${PREFIX}" --with-ogg="${PREFIX}" --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### libtheora http://www.theora.org/
+RUN \
+        DIR=/tmp/theora && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO http://downloads.xiph.org/releases/theora/libtheora-${THEORA_VERSION}.tar.gz && \
+        echo ${THEORA_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f libtheora-${THEORA_VERSION}.tar.gz && \
+        curl -sL 'http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.guess;hb=HEAD' -o config.guess && \
+        curl -sL 'http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.sub;hb=HEAD' -o config.sub && \
+        ./configure --prefix="${PREFIX}" --with-ogg="${PREFIX}" --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### libvpx https://www.webmproject.org/code/
+RUN \
+        DIR=/tmp/vpx && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://codeload.github.com/webmproject/libvpx/tar.gz/v${VPX_VERSION} | \
+        tar -zx --strip-components=1 && \
+        ./configure --prefix="${PREFIX}" --enable-vp8 --enable-vp9 --enable-vp9-highbitdepth --enable-pic --enable-shared \
+        --disable-debug --disable-examples --disable-docs --disable-install-bins  && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### libwebp https://developers.google.com/speed/webp/
+RUN \
+        DIR=/tmp/vebp && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://storage.googleapis.com/downloads.webmproject.org/releases/webp/libwebp-${WEBP_VERSION}.tar.gz | \
+        tar -zx --strip-components=1 && \
+        ./configure --prefix="${PREFIX}" --enable-shared  && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### libmp3lame http://lame.sourceforge.net/
+RUN \
+        DIR=/tmp/lame && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://versaweb.dl.sourceforge.net/project/lame/lame/$(echo ${LAME_VERSION} | sed -e 's/[^0-9]*\([0-9]*\)[.]\([0-9]*\)[.]\([0-9]*\)\([0-9A-Za-z-]*\)/\1.\2/')/lame-${LAME_VERSION}.tar.gz | \
+        tar -zx --strip-components=1 && \
+        ./configure --prefix="${PREFIX}" --bindir="${PREFIX}/bin" --enable-shared --enable-nasm --disable-frontend && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### xvid https://www.xvid.com/
+RUN \
+        DIR=/tmp/xvid && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO http://downloads.xvid.org/downloads/xvidcore-${XVID_VERSION}.tar.gz && \
+        echo ${XVID_SHA256SUM} | sha256sum --check && \
+        tar -zx -f xvidcore-${XVID_VERSION}.tar.gz && \
+        cd xvidcore/build/generic && \
+        ./configure --prefix="${PREFIX}" --bindir="${PREFIX}/bin" && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### fdk-aac https://github.com/mstorsjo/fdk-aac
+RUN \
+        DIR=/tmp/fdk-aac && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://github.com/mstorsjo/fdk-aac/archive/v${FDKAAC_VERSION}.tar.gz | \
+        tar -zx --strip-components=1 && \
+        autoreconf -fiv && \
+        ./configure --prefix="${PREFIX}" --enable-shared --datadir="${DIR}" && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+## openjpeg https://github.com/uclouvain/openjpeg
+RUN \
+        DIR=/tmp/openjpeg && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://github.com/uclouvain/openjpeg/archive/v${OPENJPEG_VERSION}.tar.gz | \
+        tar -zx --strip-components=1 && \
+        export CFLAGS="${CFLAGS} -DPNG_ARM_NEON_OPT=0" && \
+        cmake -DBUILD_THIRDPARTY:BOOL=ON -DCMAKE_INSTALL_PREFIX="${PREFIX}" . && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+## freetype https://www.freetype.org/
+RUN  \
+        DIR=/tmp/freetype && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://download.savannah.gnu.org/releases/freetype/freetype-${FREETYPE_VERSION}.tar.gz && \
+        echo ${FREETYPE_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f freetype-${FREETYPE_VERSION}.tar.gz && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+## libvstab https://github.com/georgmartius/vid.stab
+RUN  \
+        DIR=/tmp/vid.stab && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://github.com/georgmartius/vid.stab/archive/v${LIBVIDSTAB_VERSION}.tar.gz && \
+        echo ${LIBVIDSTAB_SHA256SUM} | sha256sum --check &&  \
+        tar -zx --strip-components=1 -f v${LIBVIDSTAB_VERSION}.tar.gz && \
+        cmake -DCMAKE_INSTALL_PREFIX="${PREFIX}" . && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+## fridibi https://www.fribidi.org/
+RUN  \
+        DIR=/tmp/fribidi && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://github.com/fribidi/fribidi/archive/${FRIBIDI_VERSION}.tar.gz && \
+        echo ${FRIBIDI_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f ${FRIBIDI_VERSION}.tar.gz && \
+        sed -i 's/^SUBDIRS =.*/SUBDIRS=gen.tab charset lib bin/' Makefile.am && \
+        ./bootstrap --no-config --auto && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make -j1 && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+## fontconfig https://www.freedesktop.org/wiki/Software/fontconfig/
+RUN  \
+        DIR=/tmp/fontconfig && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://www.freedesktop.org/software/fontconfig/release/fontconfig-${FONTCONFIG_VERSION}.tar.bz2 && \
+        tar -jx --strip-components=1 -f fontconfig-${FONTCONFIG_VERSION}.tar.bz2 && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+## libass https://github.com/libass/libass
+RUN  \
+        DIR=/tmp/libass && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://github.com/libass/libass/archive/${LIBASS_VERSION}.tar.gz && \
+        echo ${LIBASS_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f ${LIBASS_VERSION}.tar.gz && \
+        ./autogen.sh && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+## kvazaar https://github.com/ultravideo/kvazaar
+RUN \
+        DIR=/tmp/kvazaar && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://github.com/ultravideo/kvazaar/archive/v${KVAZAAR_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f v${KVAZAAR_VERSION}.tar.gz && \
+        ./autogen.sh && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/aom && \
+        git clone --branch ${AOM_VERSION} --depth 1 https://aomedia.googlesource.com/aom ${DIR} ; \
+        cd ${DIR} ; \
+        rm -rf CMakeCache.txt CMakeFiles ; \
+        mkdir -p ./aom_build ; \
+        cd ./aom_build ; \
+        cmake -DCMAKE_INSTALL_PREFIX="${PREFIX}" -DBUILD_SHARED_LIBS=1 ..; \
+        make ; \
+        make install ; \
+        rm -rf ${DIR}
+
+## libxcb (and supporting libraries) for screen capture https://xcb.freedesktop.org/
+RUN \
+        DIR=/tmp/xorg-macros && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://www.x.org/archive//individual/util/util-macros-${XORG_MACROS_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f util-macros-${XORG_MACROS_VERSION}.tar.gz && \
+        ./configure --srcdir=${DIR} --prefix="${PREFIX}" && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/xproto && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://www.x.org/archive/individual/proto/xproto-${XPROTO_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f xproto-${XPROTO_VERSION}.tar.gz && \
+        curl -sL 'http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.guess;hb=HEAD' -o config.guess && \
+        curl -sL 'http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.sub;hb=HEAD' -o config.sub && \
+        ./configure --srcdir=${DIR} --prefix="${PREFIX}" && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/libXau && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://www.x.org/archive/individual/lib/libXau-${XAU_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f libXau-${XAU_VERSION}.tar.gz && \
+        ./configure --srcdir=${DIR} --prefix="${PREFIX}" && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/libpthread-stubs && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://xcb.freedesktop.org/dist/libpthread-stubs-${LIBPTHREAD_STUBS_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f libpthread-stubs-${LIBPTHREAD_STUBS_VERSION}.tar.gz && \
+        ./configure --prefix="${PREFIX}" && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/libxcb-proto && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://xcb.freedesktop.org/dist/xcb-proto-${XCBPROTO_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f xcb-proto-${XCBPROTO_VERSION}.tar.gz && \
+        ACLOCAL_PATH="${PREFIX}/share/aclocal" ./autogen.sh && \
+        ./configure --prefix="${PREFIX}" && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/libxcb && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://xcb.freedesktop.org/dist/libxcb-${LIBXCB_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f libxcb-${LIBXCB_VERSION}.tar.gz && \
+        ACLOCAL_PATH="${PREFIX}/share/aclocal" ./autogen.sh && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+## libxml2 - for libbluray
+RUN \
+        DIR=/tmp/libxml2 && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://gitlab.gnome.org/GNOME/libxml2/-/archive/v${LIBXML2_VERSION}/libxml2-v${LIBXML2_VERSION}.tar.gz && \
+        echo ${LIBXML2_SHA256SUM} | sha256sum --check && \
+        tar -xz --strip-components=1 -f libxml2-v${LIBXML2_VERSION}.tar.gz && \
+        ./autogen.sh --prefix="${PREFIX}" --with-ftp=no --with-http=no --with-python=no && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+## libbluray - Requires libxml, freetype, and fontconfig
+RUN \
+        DIR=/tmp/libbluray && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://download.videolan.org/pub/videolan/libbluray/${LIBBLURAY_VERSION}/libbluray-${LIBBLURAY_VERSION}.tar.bz2 && \
+        echo ${LIBBLURAY_SHA256SUM} | sha256sum --check && \
+        tar -jx --strip-components=1 -f libbluray-${LIBBLURAY_VERSION}.tar.bz2 && \
+        ./configure --prefix="${PREFIX}" --disable-examples --disable-bdjava-jar --disable-static --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+## libzmq https://github.com/zeromq/libzmq/
+RUN \
+        DIR=/tmp/libzmq && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://github.com/zeromq/libzmq/archive/v${LIBZMQ_VERSION}.tar.gz && \
+        echo ${LIBZMQ_SHA256SUM} | sha256sum --check && \
+        tar -xz --strip-components=1 -f v${LIBZMQ_VERSION}.tar.gz && \
+        ./autogen.sh && \
+        ./configure --prefix="${PREFIX}" && \
+        make -j $(nproc) && \
+        make check && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+## ffmpeg https://ffmpeg.org/
+RUN  \
+        DIR=/tmp/ffmpeg && mkdir -p ${DIR} && cd ${DIR} && \
+        curl -sLO https://ffmpeg.org/releases/ffmpeg-${FFMPEG_VERSION}.tar.bz2 && \
+        tar -jx --strip-components=1 -f ffmpeg-${FFMPEG_VERSION}.tar.bz2
+
+RUN \
+        DIR=/tmp/ffmpeg && mkdir -p ${DIR} && cd ${DIR} && \
+        ./configure \
+        --disable-debug \
+        --disable-doc \
+        --disable-ffplay \
+        --enable-shared \
+        --enable-avresample \
+        --enable-libopencore-amrnb \
+        --enable-libopencore-amrwb \
+        --enable-gpl \
+        --enable-libass \
+        --enable-fontconfig \
+        --enable-libfreetype \
+        --enable-libvidstab \
+        --enable-libmp3lame \
+        --enable-libopus \
+        --enable-libtheora \
+        --enable-libvorbis \
+        --enable-libvpx \
+        --enable-libwebp \
+        --enable-libxcb \
+        --enable-libx265 \
+        --enable-libxvid \
+        --enable-libx264 \
+        --enable-nonfree \
+        --enable-openssl \
+        --enable-libfdk_aac \
+        --enable-postproc \
+        --enable-small \
+        --enable-version3 \
+        --enable-libbluray \
+        --enable-libzmq \
+        --extra-libs=-ldl \
+        --prefix="${PREFIX}" \
+        --enable-libopenjpeg \
+        --enable-libkvazaar \
+        --enable-libaom \
+        --extra-libs=-lpthread \
+        # --enable-omx \
+        # --enable-omx-rpi \
+        # --enable-mmal \
+        --enable-v4l2_m2m \
+        --enable-neon \
+        --extra-cflags="-I${PREFIX}/include" \
+        --extra-ldflags="-L${PREFIX}/lib" && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        make tools/zmqsend && cp tools/zmqsend ${PREFIX}/bin/ && \
+        make distclean && \
+        hash -r && \
+        cd tools && \
+        make qt-faststart && cp qt-faststart ${PREFIX}/bin/
+
+## cleanup
+RUN \
+        ldd ${PREFIX}/bin/ffmpeg | grep opt/ffmpeg | cut -d ' ' -f 3 | xargs -i cp {} /usr/local/lib/ && \
+        for lib in /usr/local/lib/*.so.*; do ln -s "${lib##*/}" "${lib%%.so.*}".so; done && \
+        cp ${PREFIX}/bin/* /usr/local/bin/ && \
+        cp -r ${PREFIX}/share/ffmpeg /usr/local/share/ && \
+        LD_LIBRARY_PATH=/usr/local/lib ffmpeg -buildconf && \
+        cp -r ${PREFIX}/include/libav* ${PREFIX}/include/libpostproc ${PREFIX}/include/libsw* /usr/local/include && \
+        mkdir -p /usr/local/lib/pkgconfig && \
+        for pc in ${PREFIX}/lib/pkgconfig/libav*.pc ${PREFIX}/lib/pkgconfig/libpostproc.pc ${PREFIX}/lib/pkgconfig/libsw*.pc; do \
+          sed "s:${PREFIX}:/usr/local:g" <"$pc" >/usr/local/lib/pkgconfig/"${pc##*/}"; \
+        done
+
+FROM        base AS release
+
+ENV         LD_LIBRARY_PATH=/usr/local/lib:/usr/local/lib64:/usr/lib:/usr/lib64:/lib:/lib64
+
+CMD         ["--help"]
+ENTRYPOINT  ["ffmpeg"]
+
+COPY --from=build /usr/local /usr/local/
+
+# Run ffmpeg with -c:v h264_v4l2m2m to enable HW accell for decoding on raspberry pi4 64-bit

docker/Dockerfile.ffmpeg.amd64

@@ -0,0 +1,526 @@
+# inspired by:
+# https://github.com/collelog/ffmpeg/blob/master/4.3.1-alpine-rpi4-arm64v8.Dockerfile
+# https://github.com/jrottenberg/ffmpeg/pull/158/files
+# https://github.com/jrottenberg/ffmpeg/pull/239
+FROM        ubuntu:20.04 AS base
+
+WORKDIR     /tmp/workdir
+
+ENV     DEBIAN_FRONTEND=noninteractive
+RUN     apt-get -yqq update && \
+        apt-get install -yq --no-install-recommends ca-certificates expat libgomp1 && \
+        apt-get autoremove -y && \
+        apt-get clean -y
+
+FROM base as build
+
+ENV         FFMPEG_VERSION=4.3.1 \
+            AOM_VERSION=v1.0.0 \
+            FDKAAC_VERSION=0.1.5 \
+            FONTCONFIG_VERSION=2.12.4 \
+            FREETYPE_VERSION=2.5.5 \
+            FRIBIDI_VERSION=0.19.7 \
+            KVAZAAR_VERSION=1.2.0 \
+            LAME_VERSION=3.100 \
+            LIBASS_VERSION=0.13.7 \
+            LIBPTHREAD_STUBS_VERSION=0.4 \
+            LIBVIDSTAB_VERSION=1.1.0 \
+            LIBXCB_VERSION=1.13.1 \
+            XCBPROTO_VERSION=1.13 \
+            OGG_VERSION=1.3.2 \
+            OPENCOREAMR_VERSION=0.1.5 \
+            OPUS_VERSION=1.2 \
+            OPENJPEG_VERSION=2.1.2 \
+            THEORA_VERSION=1.1.1 \
+            VORBIS_VERSION=1.3.5 \
+            VPX_VERSION=1.8.0 \
+            WEBP_VERSION=1.0.2 \
+            X264_VERSION=20170226-2245-stable \
+            X265_VERSION=3.1.1 \
+            XAU_VERSION=1.0.9 \
+            XORG_MACROS_VERSION=1.19.2 \
+            XPROTO_VERSION=7.0.31 \
+            XVID_VERSION=1.3.4 \
+            LIBXML2_VERSION=2.9.10 \
+            LIBBLURAY_VERSION=1.1.2 \
+            LIBZMQ_VERSION=4.3.2 \
+            SRC=/usr/local
+
+ARG         FREETYPE_SHA256SUM="5d03dd76c2171a7601e9ce10551d52d4471cf92cd205948e60289251daddffa8 freetype-2.5.5.tar.gz"
+ARG         FRIBIDI_SHA256SUM="3fc96fa9473bd31dcb5500bdf1aa78b337ba13eb8c301e7c28923fea982453a8 0.19.7.tar.gz"
+ARG         LIBASS_SHA256SUM="8fadf294bf701300d4605e6f1d92929304187fca4b8d8a47889315526adbafd7 0.13.7.tar.gz"
+ARG         LIBVIDSTAB_SHA256SUM="14d2a053e56edad4f397be0cb3ef8eb1ec3150404ce99a426c4eb641861dc0bb v1.1.0.tar.gz"
+ARG         OGG_SHA256SUM="e19ee34711d7af328cb26287f4137e70630e7261b17cbe3cd41011d73a654692 libogg-1.3.2.tar.gz"
+ARG         OPUS_SHA256SUM="77db45a87b51578fbc49555ef1b10926179861d854eb2613207dc79d9ec0a9a9 opus-1.2.tar.gz"
+ARG         THEORA_SHA256SUM="40952956c47811928d1e7922cda3bc1f427eb75680c3c37249c91e949054916b libtheora-1.1.1.tar.gz"
+ARG         VORBIS_SHA256SUM="6efbcecdd3e5dfbf090341b485da9d176eb250d893e3eb378c428a2db38301ce libvorbis-1.3.5.tar.gz"
+ARG         XVID_SHA256SUM="4e9fd62728885855bc5007fe1be58df42e5e274497591fec37249e1052ae316f xvidcore-1.3.4.tar.gz"
+ARG         LIBXML2_SHA256SUM="f07dab13bf42d2b8db80620cce7419b3b87827cc937c8bb20fe13b8571ee9501  libxml2-v2.9.10.tar.gz"
+ARG         LIBBLURAY_SHA256SUM="a3dd452239b100dc9da0d01b30e1692693e2a332a7d29917bf84bb10ea7c0b42 libbluray-1.1.2.tar.bz2"
+ARG         LIBZMQ_SHA256SUM="02ecc88466ae38cf2c8d79f09cfd2675ba299a439680b64ade733e26a349edeb v4.3.2.tar.gz"
+
+
+ARG         LD_LIBRARY_PATH=/opt/ffmpeg/lib
+ARG         MAKEFLAGS="-j2"
+ARG         PKG_CONFIG_PATH="/opt/ffmpeg/share/pkgconfig:/opt/ffmpeg/lib/pkgconfig:/opt/ffmpeg/lib64/pkgconfig"
+ARG         PREFIX=/opt/ffmpeg
+ARG         LD_LIBRARY_PATH="/opt/ffmpeg/lib:/opt/ffmpeg/lib64:/usr/lib64:/usr/lib:/lib64:/lib"
+
+
+RUN      buildDeps="autoconf \
+                    automake \
+                    cmake \
+                    curl \
+                    bzip2 \
+                    libexpat1-dev \
+                    g++ \
+                    gcc \
+                    git \
+                    gperf \
+                    libtool \
+                    make \
+                    nasm \
+                    perl \
+                    pkg-config \
+                    python \
+                    libssl-dev \
+                    yasm \
+                    libva-dev \
+                    zlib1g-dev" && \
+        apt-get -yqq update && \
+        apt-get install -yq --no-install-recommends ${buildDeps}
+## opencore-amr https://sourceforge.net/projects/opencore-amr/
+RUN \
+        DIR=/tmp/opencore-amr && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://versaweb.dl.sourceforge.net/project/opencore-amr/opencore-amr/opencore-amr-${OPENCOREAMR_VERSION}.tar.gz | \
+        tar -zx --strip-components=1 && \
+        ./configure --prefix="${PREFIX}" --enable-shared  && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+## x264 http://www.videolan.org/developers/x264.html
+RUN \
+        DIR=/tmp/x264 && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://download.videolan.org/pub/videolan/x264/snapshots/x264-snapshot-${X264_VERSION}.tar.bz2 | \
+        tar -jx --strip-components=1 && \
+        ./configure --prefix="${PREFIX}" --enable-shared --enable-pic --disable-cli && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+### x265 http://x265.org/
+RUN \
+        DIR=/tmp/x265 && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://download.videolan.org/pub/videolan/x265/x265_${X265_VERSION}.tar.gz  | \
+        tar -zx && \
+        cd x265_${X265_VERSION}/build/linux && \
+        sed -i "/-DEXTRA_LIB/ s/$/ -DCMAKE_INSTALL_PREFIX=\${PREFIX}/" multilib.sh && \
+        sed -i "/^cmake/ s/$/ -DENABLE_CLI=OFF/" multilib.sh && \
+        ./multilib.sh && \
+        make -C 8bit install && \
+        rm -rf ${DIR}
+### libogg https://www.xiph.org/ogg/
+RUN \
+        DIR=/tmp/ogg && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO http://downloads.xiph.org/releases/ogg/libogg-${OGG_VERSION}.tar.gz && \
+        echo ${OGG_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f libogg-${OGG_VERSION}.tar.gz && \
+        ./configure --prefix="${PREFIX}" --enable-shared  && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+### libopus https://www.opus-codec.org/
+RUN \
+        DIR=/tmp/opus && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://archive.mozilla.org/pub/opus/opus-${OPUS_VERSION}.tar.gz && \
+        echo ${OPUS_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f opus-${OPUS_VERSION}.tar.gz && \
+        autoreconf -fiv && \
+        ./configure --prefix="${PREFIX}" --enable-shared && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+### libvorbis https://xiph.org/vorbis/
+RUN \
+        DIR=/tmp/vorbis && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO http://downloads.xiph.org/releases/vorbis/libvorbis-${VORBIS_VERSION}.tar.gz && \
+        echo ${VORBIS_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f libvorbis-${VORBIS_VERSION}.tar.gz && \
+        ./configure --prefix="${PREFIX}" --with-ogg="${PREFIX}" --enable-shared && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+### libtheora http://www.theora.org/
+RUN \
+        DIR=/tmp/theora && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO http://downloads.xiph.org/releases/theora/libtheora-${THEORA_VERSION}.tar.gz && \
+        echo ${THEORA_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f libtheora-${THEORA_VERSION}.tar.gz && \
+        ./configure --prefix="${PREFIX}" --with-ogg="${PREFIX}" --enable-shared && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+### libvpx https://www.webmproject.org/code/
+RUN \
+        DIR=/tmp/vpx && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://codeload.github.com/webmproject/libvpx/tar.gz/v${VPX_VERSION} | \
+        tar -zx --strip-components=1 && \
+        ./configure --prefix="${PREFIX}" --enable-vp8 --enable-vp9 --enable-vp9-highbitdepth --enable-pic --enable-shared \
+        --disable-debug --disable-examples --disable-docs --disable-install-bins  && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+### libwebp https://developers.google.com/speed/webp/
+RUN \
+        DIR=/tmp/vebp && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://storage.googleapis.com/downloads.webmproject.org/releases/webp/libwebp-${WEBP_VERSION}.tar.gz | \
+        tar -zx --strip-components=1 && \
+        ./configure --prefix="${PREFIX}" --enable-shared  && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+### libmp3lame http://lame.sourceforge.net/
+RUN \
+        DIR=/tmp/lame && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://versaweb.dl.sourceforge.net/project/lame/lame/$(echo ${LAME_VERSION} | sed -e 's/[^0-9]*\([0-9]*\)[.]\([0-9]*\)[.]\([0-9]*\)\([0-9A-Za-z-]*\)/\1.\2/')/lame-${LAME_VERSION}.tar.gz | \
+        tar -zx --strip-components=1 && \
+        ./configure --prefix="${PREFIX}" --bindir="${PREFIX}/bin" --enable-shared --enable-nasm --disable-frontend && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+### xvid https://www.xvid.com/
+RUN \
+        DIR=/tmp/xvid && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO http://downloads.xvid.org/downloads/xvidcore-${XVID_VERSION}.tar.gz && \
+        echo ${XVID_SHA256SUM} | sha256sum --check && \
+        tar -zx -f xvidcore-${XVID_VERSION}.tar.gz && \
+        cd xvidcore/build/generic && \
+        ./configure --prefix="${PREFIX}" --bindir="${PREFIX}/bin" && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+### fdk-aac https://github.com/mstorsjo/fdk-aac
+RUN \
+        DIR=/tmp/fdk-aac && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://github.com/mstorsjo/fdk-aac/archive/v${FDKAAC_VERSION}.tar.gz | \
+        tar -zx --strip-components=1 && \
+        autoreconf -fiv && \
+        ./configure --prefix="${PREFIX}" --enable-shared --datadir="${DIR}" && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+## openjpeg https://github.com/uclouvain/openjpeg
+RUN \
+        DIR=/tmp/openjpeg && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://github.com/uclouvain/openjpeg/archive/v${OPENJPEG_VERSION}.tar.gz | \
+        tar -zx --strip-components=1 && \
+        cmake -DBUILD_THIRDPARTY:BOOL=ON -DCMAKE_INSTALL_PREFIX="${PREFIX}" . && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+## freetype https://www.freetype.org/
+RUN  \
+        DIR=/tmp/freetype && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://download.savannah.gnu.org/releases/freetype/freetype-${FREETYPE_VERSION}.tar.gz && \
+        echo ${FREETYPE_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f freetype-${FREETYPE_VERSION}.tar.gz && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+## libvstab https://github.com/georgmartius/vid.stab
+RUN  \
+        DIR=/tmp/vid.stab && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://github.com/georgmartius/vid.stab/archive/v${LIBVIDSTAB_VERSION}.tar.gz && \
+        echo ${LIBVIDSTAB_SHA256SUM} | sha256sum --check &&  \
+        tar -zx --strip-components=1 -f v${LIBVIDSTAB_VERSION}.tar.gz && \
+        cmake -DCMAKE_INSTALL_PREFIX="${PREFIX}" . && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+## fridibi https://www.fribidi.org/
+RUN  \
+        DIR=/tmp/fribidi && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://github.com/fribidi/fribidi/archive/${FRIBIDI_VERSION}.tar.gz && \
+        echo ${FRIBIDI_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f ${FRIBIDI_VERSION}.tar.gz && \
+        sed -i 's/^SUBDIRS =.*/SUBDIRS=gen.tab charset lib bin/' Makefile.am && \
+        ./bootstrap --no-config --auto && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make -j1 && \
+        make install && \
+        rm -rf ${DIR}
+## fontconfig https://www.freedesktop.org/wiki/Software/fontconfig/
+RUN  \
+        DIR=/tmp/fontconfig && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://www.freedesktop.org/software/fontconfig/release/fontconfig-${FONTCONFIG_VERSION}.tar.bz2 && \
+        tar -jx --strip-components=1 -f fontconfig-${FONTCONFIG_VERSION}.tar.bz2 && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+## libass https://github.com/libass/libass
+RUN  \
+        DIR=/tmp/libass && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://github.com/libass/libass/archive/${LIBASS_VERSION}.tar.gz && \
+        echo ${LIBASS_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f ${LIBASS_VERSION}.tar.gz && \
+        ./autogen.sh && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+## kvazaar https://github.com/ultravideo/kvazaar
+RUN \
+        DIR=/tmp/kvazaar && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://github.com/ultravideo/kvazaar/archive/v${KVAZAAR_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f v${KVAZAAR_VERSION}.tar.gz && \
+        ./autogen.sh && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/aom && \
+        git clone --branch ${AOM_VERSION} --depth 1 https://aomedia.googlesource.com/aom ${DIR} ; \
+        cd ${DIR} ; \
+        rm -rf CMakeCache.txt CMakeFiles ; \
+        mkdir -p ./aom_build ; \
+        cd ./aom_build ; \
+        cmake -DCMAKE_INSTALL_PREFIX="${PREFIX}" -DBUILD_SHARED_LIBS=1 ..; \
+        make ; \
+        make install ; \
+        rm -rf ${DIR}
+
+## libxcb (and supporting libraries) for screen capture https://xcb.freedesktop.org/
+RUN \
+        DIR=/tmp/xorg-macros && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://www.x.org/archive//individual/util/util-macros-${XORG_MACROS_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f util-macros-${XORG_MACROS_VERSION}.tar.gz && \
+        ./configure --srcdir=${DIR} --prefix="${PREFIX}" && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/xproto && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://www.x.org/archive/individual/proto/xproto-${XPROTO_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f xproto-${XPROTO_VERSION}.tar.gz && \
+        ./configure --srcdir=${DIR} --prefix="${PREFIX}" && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/libXau && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://www.x.org/archive/individual/lib/libXau-${XAU_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f libXau-${XAU_VERSION}.tar.gz && \
+        ./configure --srcdir=${DIR} --prefix="${PREFIX}" && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/libpthread-stubs && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://xcb.freedesktop.org/dist/libpthread-stubs-${LIBPTHREAD_STUBS_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f libpthread-stubs-${LIBPTHREAD_STUBS_VERSION}.tar.gz && \
+        ./configure --prefix="${PREFIX}" && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/libxcb-proto && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://xcb.freedesktop.org/dist/xcb-proto-${XCBPROTO_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f xcb-proto-${XCBPROTO_VERSION}.tar.gz && \
+        ACLOCAL_PATH="${PREFIX}/share/aclocal" ./autogen.sh && \
+        ./configure --prefix="${PREFIX}" && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/libxcb && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://xcb.freedesktop.org/dist/libxcb-${LIBXCB_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f libxcb-${LIBXCB_VERSION}.tar.gz && \
+        ACLOCAL_PATH="${PREFIX}/share/aclocal" ./autogen.sh && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+
+## libxml2 - for libbluray
+RUN \
+        DIR=/tmp/libxml2 && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://gitlab.gnome.org/GNOME/libxml2/-/archive/v${LIBXML2_VERSION}/libxml2-v${LIBXML2_VERSION}.tar.gz && \
+        echo ${LIBXML2_SHA256SUM} | sha256sum --check && \
+        tar -xz --strip-components=1 -f libxml2-v${LIBXML2_VERSION}.tar.gz && \
+        ./autogen.sh --prefix="${PREFIX}" --with-ftp=no --with-http=no --with-python=no && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+
+## libbluray - Requires libxml, freetype, and fontconfig
+RUN \
+        DIR=/tmp/libbluray && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://download.videolan.org/pub/videolan/libbluray/${LIBBLURAY_VERSION}/libbluray-${LIBBLURAY_VERSION}.tar.bz2 && \
+        echo ${LIBBLURAY_SHA256SUM} | sha256sum --check && \
+        tar -jx --strip-components=1 -f libbluray-${LIBBLURAY_VERSION}.tar.bz2 && \
+        ./configure --prefix="${PREFIX}" --disable-examples --disable-bdjava-jar --disable-static --enable-shared && \
+        make && \
+        make install && \
+        rm -rf ${DIR}
+
+## libzmq https://github.com/zeromq/libzmq/
+RUN \
+        DIR=/tmp/libzmq && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://github.com/zeromq/libzmq/archive/v${LIBZMQ_VERSION}.tar.gz && \
+        echo ${LIBZMQ_SHA256SUM} | sha256sum --check && \
+        tar -xz --strip-components=1 -f v${LIBZMQ_VERSION}.tar.gz && \
+        ./autogen.sh && \
+        ./configure --prefix="${PREFIX}" && \
+        make && \
+        make check && \
+        make install && \
+        rm -rf ${DIR}
+
+## ffmpeg https://ffmpeg.org/
+RUN  \
+        DIR=/tmp/ffmpeg && mkdir -p ${DIR} && cd ${DIR} && \
+        curl -sLO https://ffmpeg.org/releases/ffmpeg-${FFMPEG_VERSION}.tar.bz2 && \
+        tar -jx --strip-components=1 -f ffmpeg-${FFMPEG_VERSION}.tar.bz2
+
+
+
+RUN \
+        DIR=/tmp/ffmpeg && mkdir -p ${DIR} && cd ${DIR} && \
+        ./configure \
+        --disable-debug \
+        --disable-doc \
+        --disable-ffplay \
+        --enable-shared \
+        --enable-avresample \
+        --enable-libopencore-amrnb \
+        --enable-libopencore-amrwb \
+        --enable-gpl \
+        --enable-libass \
+        --enable-fontconfig \
+        --enable-libfreetype \
+        --enable-libvidstab \
+        --enable-libmp3lame \
+        --enable-libopus \
+        --enable-libtheora \
+        --enable-libvorbis \
+        --enable-libvpx \
+        --enable-libwebp \
+        --enable-libxcb \
+        --enable-libx265 \
+        --enable-libxvid \
+        --enable-libx264 \
+        --enable-nonfree \
+        --enable-openssl \
+        --enable-libfdk_aac \
+        --enable-postproc \
+        --enable-small \
+        --enable-version3 \
+        --enable-libbluray \
+        --enable-libzmq \
+        --extra-libs=-ldl \
+        --prefix="${PREFIX}" \
+        --enable-libopenjpeg \
+        --enable-libkvazaar \
+        --enable-libaom \
+        --extra-libs=-lpthread \
+        --enable-vaapi \
+        --extra-cflags="-I${PREFIX}/include" \
+        --extra-ldflags="-L${PREFIX}/lib" && \
+        make && \
+        make install && \
+        make tools/zmqsend && cp tools/zmqsend ${PREFIX}/bin/ && \
+        make distclean && \
+        hash -r && \
+        cd tools && \
+        make qt-faststart && cp qt-faststart ${PREFIX}/bin/
+
+## cleanup
+RUN \
+        ldd ${PREFIX}/bin/ffmpeg | grep opt/ffmpeg | cut -d ' ' -f 3 | xargs -i cp {} /usr/local/lib/ && \
+        for lib in /usr/local/lib/*.so.*; do ln -s "${lib##*/}" "${lib%%.so.*}".so; done && \
+        cp ${PREFIX}/bin/* /usr/local/bin/ && \
+        cp -r ${PREFIX}/share/ffmpeg /usr/local/share/ && \
+        LD_LIBRARY_PATH=/usr/local/lib ffmpeg -buildconf && \
+        cp -r ${PREFIX}/include/libav* ${PREFIX}/include/libpostproc ${PREFIX}/include/libsw* /usr/local/include && \
+        mkdir -p /usr/local/lib/pkgconfig && \
+        for pc in ${PREFIX}/lib/pkgconfig/libav*.pc ${PREFIX}/lib/pkgconfig/libpostproc.pc ${PREFIX}/lib/pkgconfig/libsw*.pc; do \
+          sed "s:${PREFIX}:/usr/local:g" <"$pc" >/usr/local/lib/pkgconfig/"${pc##*/}"; \
+        done
+
+FROM        base AS release
+
+ENV         LD_LIBRARY_PATH=/usr/local/lib:/usr/local/lib64:/usr/lib:/usr/lib64:/lib:/lib64
+
+CMD         ["--help"]
+ENTRYPOINT  ["ffmpeg"]
+
+COPY --from=build /usr/local /usr/local/
+
+RUN \
+	apt-get update -y && \
+	apt-get install -y --no-install-recommends libva-drm2 libva2 i965-va-driver && \
+	rm -rf /var/lib/apt/lists/*

docker/Dockerfile.ffmpeg.armv7

@@ -0,0 +1,549 @@
+# inspired by:
+# https://github.com/collelog/ffmpeg/blob/master/4.3.1-alpine-rpi4-arm64v8.Dockerfile
+# https://github.com/mmastrac/ffmpeg-omx-rpi-docker/blob/master/Dockerfile
+# https://github.com/jrottenberg/ffmpeg/pull/158/files
+# https://github.com/jrottenberg/ffmpeg/pull/239
+FROM        ubuntu:20.04 AS base
+
+WORKDIR     /tmp/workdir
+
+ENV     DEBIAN_FRONTEND=noninteractive
+RUN     apt-get -yqq update && \
+        apt-get install -yq --no-install-recommends ca-certificates expat libgomp1 && \
+        apt-get autoremove -y && \
+        apt-get clean -y
+
+FROM base as build
+
+ENV         FFMPEG_VERSION=4.3.1 \
+            AOM_VERSION=v1.0.0 \
+            FDKAAC_VERSION=0.1.5 \
+            FONTCONFIG_VERSION=2.12.4 \
+            FREETYPE_VERSION=2.5.5 \
+            FRIBIDI_VERSION=0.19.7 \
+            KVAZAAR_VERSION=1.2.0 \
+            LAME_VERSION=3.100 \
+            LIBASS_VERSION=0.13.7 \
+            LIBPTHREAD_STUBS_VERSION=0.4 \
+            LIBVIDSTAB_VERSION=1.1.0 \
+            LIBXCB_VERSION=1.13.1 \
+            XCBPROTO_VERSION=1.13 \
+            OGG_VERSION=1.3.2 \
+            OPENCOREAMR_VERSION=0.1.5 \
+            OPUS_VERSION=1.2 \
+            OPENJPEG_VERSION=2.1.2 \
+            THEORA_VERSION=1.1.1 \
+            VORBIS_VERSION=1.3.5 \
+            VPX_VERSION=1.8.0 \
+            WEBP_VERSION=1.0.2 \
+            X264_VERSION=20170226-2245-stable \
+            X265_VERSION=3.1.1 \
+            XAU_VERSION=1.0.9 \
+            XORG_MACROS_VERSION=1.19.2 \
+            XPROTO_VERSION=7.0.31 \
+            XVID_VERSION=1.3.4 \
+            LIBXML2_VERSION=2.9.10 \
+            LIBBLURAY_VERSION=1.1.2 \
+            LIBZMQ_VERSION=4.3.3 \
+            SRC=/usr/local
+
+ARG         FREETYPE_SHA256SUM="5d03dd76c2171a7601e9ce10551d52d4471cf92cd205948e60289251daddffa8 freetype-2.5.5.tar.gz"
+ARG         FRIBIDI_SHA256SUM="3fc96fa9473bd31dcb5500bdf1aa78b337ba13eb8c301e7c28923fea982453a8 0.19.7.tar.gz"
+ARG         LIBASS_SHA256SUM="8fadf294bf701300d4605e6f1d92929304187fca4b8d8a47889315526adbafd7 0.13.7.tar.gz"
+ARG         LIBVIDSTAB_SHA256SUM="14d2a053e56edad4f397be0cb3ef8eb1ec3150404ce99a426c4eb641861dc0bb v1.1.0.tar.gz"
+ARG         OGG_SHA256SUM="e19ee34711d7af328cb26287f4137e70630e7261b17cbe3cd41011d73a654692 libogg-1.3.2.tar.gz"
+ARG         OPUS_SHA256SUM="77db45a87b51578fbc49555ef1b10926179861d854eb2613207dc79d9ec0a9a9 opus-1.2.tar.gz"
+ARG         THEORA_SHA256SUM="40952956c47811928d1e7922cda3bc1f427eb75680c3c37249c91e949054916b libtheora-1.1.1.tar.gz"
+ARG         VORBIS_SHA256SUM="6efbcecdd3e5dfbf090341b485da9d176eb250d893e3eb378c428a2db38301ce libvorbis-1.3.5.tar.gz"
+ARG         XVID_SHA256SUM="4e9fd62728885855bc5007fe1be58df42e5e274497591fec37249e1052ae316f xvidcore-1.3.4.tar.gz"
+ARG         LIBXML2_SHA256SUM="f07dab13bf42d2b8db80620cce7419b3b87827cc937c8bb20fe13b8571ee9501  libxml2-v2.9.10.tar.gz"
+ARG         LIBBLURAY_SHA256SUM="a3dd452239b100dc9da0d01b30e1692693e2a332a7d29917bf84bb10ea7c0b42 libbluray-1.1.2.tar.bz2"
+
+
+ARG         LD_LIBRARY_PATH=/opt/ffmpeg/lib
+ARG         MAKEFLAGS="-j2"
+ARG         PKG_CONFIG_PATH="/opt/ffmpeg/share/pkgconfig:/opt/ffmpeg/lib/pkgconfig:/opt/ffmpeg/lib64/pkgconfig:/opt/vc/lib/pkgconfig"
+ARG         PREFIX=/opt/ffmpeg
+ARG         LD_LIBRARY_PATH="/opt/ffmpeg/lib:/opt/ffmpeg/lib64:/usr/lib64:/usr/lib:/lib64:/lib:/opt/vc/lib"
+
+
+RUN      buildDeps="autoconf \
+                    automake \
+                    cmake \
+                    curl \
+                    bzip2 \
+                    libexpat1-dev \
+                    g++ \
+                    gcc \
+                    git \
+                    gperf \
+                    libtool \
+                    make \
+                    nasm \
+                    perl \
+                    pkg-config \
+                    python \
+                    sudo \
+                    libssl-dev \
+                    yasm \
+                    linux-headers-raspi2 \
+                    libomxil-bellagio-dev \
+                    libx265-dev \
+                    libaom-dev \
+                    zlib1g-dev" && \
+        apt-get -yqq update && \
+        apt-get install -yq --no-install-recommends ${buildDeps}
+## opencore-amr https://sourceforge.net/projects/opencore-amr/
+RUN \
+        DIR=/tmp/opencore-amr && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://versaweb.dl.sourceforge.net/project/opencore-amr/opencore-amr/opencore-amr-${OPENCOREAMR_VERSION}.tar.gz | \
+        tar -zx --strip-components=1 && \
+        ./configure --prefix="${PREFIX}" --enable-shared  && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+## x264 http://www.videolan.org/developers/x264.html
+RUN \
+        DIR=/tmp/x264 && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://download.videolan.org/pub/videolan/x264/snapshots/x264-snapshot-${X264_VERSION}.tar.bz2 | \
+        tar -jx --strip-components=1 && \
+        ./configure --prefix="${PREFIX}" --enable-shared --enable-pic --disable-cli && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+# ### x265 http://x265.org/
+# RUN \
+#         DIR=/tmp/x265 && \
+#         mkdir -p ${DIR} && \
+#         cd ${DIR} && \
+#         curl -sL https://download.videolan.org/pub/videolan/x265/x265_${X265_VERSION}.tar.gz  | \
+#         tar -zx && \
+#         cd x265_${X265_VERSION}/build/linux && \
+#         sed -i "/-DEXTRA_LIB/ s/$/ -DCMAKE_INSTALL_PREFIX=\${PREFIX}/" multilib.sh && \
+#         sed -i "/^cmake/ s/$/ -DENABLE_CLI=OFF/" multilib.sh && \
+#         # export CXXFLAGS="${CXXFLAGS} -fPIC" && \
+#         ./multilib.sh && \
+#         make -C 8bit install && \
+#         rm -rf ${DIR}
+### libogg https://www.xiph.org/ogg/
+RUN \
+        DIR=/tmp/ogg && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO http://downloads.xiph.org/releases/ogg/libogg-${OGG_VERSION}.tar.gz && \
+        echo ${OGG_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f libogg-${OGG_VERSION}.tar.gz && \
+        ./configure --prefix="${PREFIX}" --enable-shared  && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### libopus https://www.opus-codec.org/
+RUN \
+        DIR=/tmp/opus && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://archive.mozilla.org/pub/opus/opus-${OPUS_VERSION}.tar.gz && \
+        echo ${OPUS_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f opus-${OPUS_VERSION}.tar.gz && \
+        autoreconf -fiv && \
+        ./configure --prefix="${PREFIX}" --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### libvorbis https://xiph.org/vorbis/
+RUN \
+        DIR=/tmp/vorbis && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO http://downloads.xiph.org/releases/vorbis/libvorbis-${VORBIS_VERSION}.tar.gz && \
+        echo ${VORBIS_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f libvorbis-${VORBIS_VERSION}.tar.gz && \
+        ./configure --prefix="${PREFIX}" --with-ogg="${PREFIX}" --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### libtheora http://www.theora.org/
+RUN \
+        DIR=/tmp/theora && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO http://downloads.xiph.org/releases/theora/libtheora-${THEORA_VERSION}.tar.gz && \
+        echo ${THEORA_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f libtheora-${THEORA_VERSION}.tar.gz && \
+        curl -sL 'http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.guess;hb=HEAD' -o config.guess && \
+        curl -sL 'http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.sub;hb=HEAD' -o config.sub && \
+        ./configure --prefix="${PREFIX}" --with-ogg="${PREFIX}" --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### libvpx https://www.webmproject.org/code/
+RUN \
+        DIR=/tmp/vpx && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://codeload.github.com/webmproject/libvpx/tar.gz/v${VPX_VERSION} | \
+        tar -zx --strip-components=1 && \
+        ./configure --prefix="${PREFIX}" --enable-vp8 --enable-vp9 --enable-vp9-highbitdepth --enable-pic --enable-shared \
+        --disable-debug --disable-examples --disable-docs --disable-install-bins  && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### libwebp https://developers.google.com/speed/webp/
+RUN \
+        DIR=/tmp/vebp && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://storage.googleapis.com/downloads.webmproject.org/releases/webp/libwebp-${WEBP_VERSION}.tar.gz | \
+        tar -zx --strip-components=1 && \
+        ./configure --prefix="${PREFIX}" --enable-shared  && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### libmp3lame http://lame.sourceforge.net/
+RUN \
+        DIR=/tmp/lame && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://versaweb.dl.sourceforge.net/project/lame/lame/$(echo ${LAME_VERSION} | sed -e 's/[^0-9]*\([0-9]*\)[.]\([0-9]*\)[.]\([0-9]*\)\([0-9A-Za-z-]*\)/\1.\2/')/lame-${LAME_VERSION}.tar.gz | \
+        tar -zx --strip-components=1 && \
+        ./configure --prefix="${PREFIX}" --bindir="${PREFIX}/bin" --enable-shared --enable-nasm --disable-frontend && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### xvid https://www.xvid.com/
+RUN \
+        DIR=/tmp/xvid && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO http://downloads.xvid.org/downloads/xvidcore-${XVID_VERSION}.tar.gz && \
+        echo ${XVID_SHA256SUM} | sha256sum --check && \
+        tar -zx -f xvidcore-${XVID_VERSION}.tar.gz && \
+        cd xvidcore/build/generic && \
+        ./configure --prefix="${PREFIX}" --bindir="${PREFIX}/bin" && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+### fdk-aac https://github.com/mstorsjo/fdk-aac
+RUN \
+        DIR=/tmp/fdk-aac && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://github.com/mstorsjo/fdk-aac/archive/v${FDKAAC_VERSION}.tar.gz | \
+        tar -zx --strip-components=1 && \
+        autoreconf -fiv && \
+        ./configure --prefix="${PREFIX}" --enable-shared --datadir="${DIR}" && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+## openjpeg https://github.com/uclouvain/openjpeg
+RUN \
+        DIR=/tmp/openjpeg && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sL https://github.com/uclouvain/openjpeg/archive/v${OPENJPEG_VERSION}.tar.gz | \
+        tar -zx --strip-components=1 && \
+        export CFLAGS="${CFLAGS} -DPNG_ARM_NEON_OPT=0" && \
+        cmake -DBUILD_THIRDPARTY:BOOL=ON -DCMAKE_INSTALL_PREFIX="${PREFIX}" . && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+## freetype https://www.freetype.org/
+RUN  \
+        DIR=/tmp/freetype && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://download.savannah.gnu.org/releases/freetype/freetype-${FREETYPE_VERSION}.tar.gz && \
+        echo ${FREETYPE_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f freetype-${FREETYPE_VERSION}.tar.gz && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+## libvstab https://github.com/georgmartius/vid.stab
+RUN  \
+        DIR=/tmp/vid.stab && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://github.com/georgmartius/vid.stab/archive/v${LIBVIDSTAB_VERSION}.tar.gz && \
+        echo ${LIBVIDSTAB_SHA256SUM} | sha256sum --check &&  \
+        tar -zx --strip-components=1 -f v${LIBVIDSTAB_VERSION}.tar.gz && \
+        cmake -DCMAKE_INSTALL_PREFIX="${PREFIX}" . && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+## fridibi https://www.fribidi.org/
+RUN  \
+        DIR=/tmp/fribidi && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://github.com/fribidi/fribidi/archive/${FRIBIDI_VERSION}.tar.gz && \
+        echo ${FRIBIDI_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f ${FRIBIDI_VERSION}.tar.gz && \
+        sed -i 's/^SUBDIRS =.*/SUBDIRS=gen.tab charset lib bin/' Makefile.am && \
+        ./bootstrap --no-config --auto && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make -j1 && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+## fontconfig https://www.freedesktop.org/wiki/Software/fontconfig/
+RUN  \
+        DIR=/tmp/fontconfig && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://www.freedesktop.org/software/fontconfig/release/fontconfig-${FONTCONFIG_VERSION}.tar.bz2 && \
+        tar -jx --strip-components=1 -f fontconfig-${FONTCONFIG_VERSION}.tar.bz2 && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+## libass https://github.com/libass/libass
+RUN  \
+        DIR=/tmp/libass && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://github.com/libass/libass/archive/${LIBASS_VERSION}.tar.gz && \
+        echo ${LIBASS_SHA256SUM} | sha256sum --check && \
+        tar -zx --strip-components=1 -f ${LIBASS_VERSION}.tar.gz && \
+        ./autogen.sh && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+## kvazaar https://github.com/ultravideo/kvazaar
+RUN \
+        DIR=/tmp/kvazaar && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://github.com/ultravideo/kvazaar/archive/v${KVAZAAR_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f v${KVAZAAR_VERSION}.tar.gz && \
+        ./autogen.sh && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+# RUN \
+#         DIR=/tmp/aom && \
+#         git clone --branch ${AOM_VERSION} --depth 1 https://aomedia.googlesource.com/aom ${DIR} ; \
+#         cd ${DIR} ; \
+#         rm -rf CMakeCache.txt CMakeFiles ; \
+#         mkdir -p ./aom_build ; \
+#         cd ./aom_build ; \
+#         cmake -DCMAKE_INSTALL_PREFIX="${PREFIX}" -DBUILD_SHARED_LIBS=1 ..; \
+#         make ; \
+#         make install ; \
+#         rm -rf ${DIR}
+
+## libxcb (and supporting libraries) for screen capture https://xcb.freedesktop.org/
+RUN \
+        DIR=/tmp/xorg-macros && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://www.x.org/archive//individual/util/util-macros-${XORG_MACROS_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f util-macros-${XORG_MACROS_VERSION}.tar.gz && \
+        ./configure --srcdir=${DIR} --prefix="${PREFIX}" && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/xproto && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://www.x.org/archive/individual/proto/xproto-${XPROTO_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f xproto-${XPROTO_VERSION}.tar.gz && \
+        curl -sL 'http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.guess;hb=HEAD' -o config.guess && \
+        curl -sL 'http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.sub;hb=HEAD' -o config.sub && \
+        ./configure --srcdir=${DIR} --prefix="${PREFIX}" && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/libXau && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://www.x.org/archive/individual/lib/libXau-${XAU_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f libXau-${XAU_VERSION}.tar.gz && \
+        ./configure --srcdir=${DIR} --prefix="${PREFIX}" && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/libpthread-stubs && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://xcb.freedesktop.org/dist/libpthread-stubs-${LIBPTHREAD_STUBS_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f libpthread-stubs-${LIBPTHREAD_STUBS_VERSION}.tar.gz && \
+        ./configure --prefix="${PREFIX}" && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/libxcb-proto && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://xcb.freedesktop.org/dist/xcb-proto-${XCBPROTO_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f xcb-proto-${XCBPROTO_VERSION}.tar.gz && \
+        ACLOCAL_PATH="${PREFIX}/share/aclocal" ./autogen.sh && \
+        ./configure --prefix="${PREFIX}" && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+RUN \
+        DIR=/tmp/libxcb && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://xcb.freedesktop.org/dist/libxcb-${LIBXCB_VERSION}.tar.gz && \
+        tar -zx --strip-components=1 -f libxcb-${LIBXCB_VERSION}.tar.gz && \
+        ACLOCAL_PATH="${PREFIX}/share/aclocal" ./autogen.sh && \
+        ./configure --prefix="${PREFIX}" --disable-static --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+## libxml2 - for libbluray
+RUN \
+        DIR=/tmp/libxml2 && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://gitlab.gnome.org/GNOME/libxml2/-/archive/v${LIBXML2_VERSION}/libxml2-v${LIBXML2_VERSION}.tar.gz && \
+        echo ${LIBXML2_SHA256SUM} | sha256sum --check && \
+        tar -xz --strip-components=1 -f libxml2-v${LIBXML2_VERSION}.tar.gz && \
+        ./autogen.sh --prefix="${PREFIX}" --with-ftp=no --with-http=no --with-python=no && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+## libbluray - Requires libxml, freetype, and fontconfig
+RUN \
+        DIR=/tmp/libbluray && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://download.videolan.org/pub/videolan/libbluray/${LIBBLURAY_VERSION}/libbluray-${LIBBLURAY_VERSION}.tar.bz2 && \
+        echo ${LIBBLURAY_SHA256SUM} | sha256sum --check && \
+        tar -jx --strip-components=1 -f libbluray-${LIBBLURAY_VERSION}.tar.bz2 && \
+        ./configure --prefix="${PREFIX}" --disable-examples --disable-bdjava-jar --disable-static --enable-shared && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+## libzmq https://github.com/zeromq/libzmq/
+RUN \
+        DIR=/tmp/libzmq && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        curl -sLO https://github.com/zeromq/libzmq/archive/v${LIBZMQ_VERSION}.tar.gz && \
+        tar -xz --strip-components=1 -f v${LIBZMQ_VERSION}.tar.gz && \
+        ./autogen.sh && \
+        ./configure --prefix="${PREFIX}" && \
+        make -j $(nproc) && \
+        # make check && \
+        make -j $(nproc) install && \
+        rm -rf ${DIR}
+
+## userland https://github.com/raspberrypi/userland
+RUN \
+        DIR=/tmp/userland && \
+        mkdir -p ${DIR} && \
+        cd ${DIR} && \
+        git clone --depth 1 https://github.com/raspberrypi/userland.git . && \
+        ./buildme && \
+        rm -rf ${DIR}
+
+## ffmpeg https://ffmpeg.org/
+RUN  \
+        DIR=/tmp/ffmpeg && mkdir -p ${DIR} && cd ${DIR} && \
+        curl -sLO https://ffmpeg.org/releases/ffmpeg-${FFMPEG_VERSION}.tar.bz2 && \
+        tar -jx --strip-components=1 -f ffmpeg-${FFMPEG_VERSION}.tar.bz2
+
+RUN \
+        DIR=/tmp/ffmpeg && mkdir -p ${DIR} && cd ${DIR} && \
+        ./configure \
+        --disable-debug \
+        --disable-doc \
+        --disable-ffplay \
+        --enable-shared \
+        --enable-avresample \
+        --enable-libopencore-amrnb \
+        --enable-libopencore-amrwb \
+        --enable-gpl \
+        --enable-libass \
+        --enable-fontconfig \
+        --enable-libfreetype \
+        --enable-libvidstab \
+        --enable-libmp3lame \
+        --enable-libopus \
+        --enable-libtheora \
+        --enable-libvorbis \
+        --enable-libvpx \
+        --enable-libwebp \
+        --enable-libxcb \
+        --enable-libx265 \
+        --enable-libxvid \
+        --enable-libx264 \
+        --enable-nonfree \
+        --enable-openssl \
+        --enable-libfdk_aac \
+        --enable-postproc \
+        --enable-small \
+        --enable-version3 \
+        --enable-libbluray \
+        --enable-libzmq \
+        --extra-libs=-ldl \
+        --prefix="${PREFIX}" \
+        --enable-libopenjpeg \
+        --enable-libkvazaar \
+        --enable-libaom \
+        --extra-libs=-lpthread \
+        --enable-omx \
+        --enable-omx-rpi \
+        --enable-mmal \
+        --enable-v4l2_m2m \
+        --enable-neon \
+        --extra-cflags="-I${PREFIX}/include" \
+        --extra-ldflags="-L${PREFIX}/lib" && \
+        make -j $(nproc) && \
+        make -j $(nproc) install && \
+        make tools/zmqsend && cp tools/zmqsend ${PREFIX}/bin/ && \
+        make distclean && \
+        hash -r && \
+        cd tools && \
+        make qt-faststart && cp qt-faststart ${PREFIX}/bin/
+
+## cleanup
+RUN \
+        ldd ${PREFIX}/bin/ffmpeg | grep opt/ffmpeg | cut -d ' ' -f 3 | xargs -i cp {} /usr/local/lib/ && \
+        # copy userland lib too
+        ldd ${PREFIX}/bin/ffmpeg | grep opt/vc | cut -d ' ' -f 3 | xargs -i cp {} /usr/local/lib/ && \
+        for lib in /usr/local/lib/*.so.*; do ln -s "${lib##*/}" "${lib%%.so.*}".so; done && \
+        cp ${PREFIX}/bin/* /usr/local/bin/ && \
+        cp -r ${PREFIX}/share/ffmpeg /usr/local/share/ && \
+        LD_LIBRARY_PATH=/usr/local/lib ffmpeg -buildconf && \
+        cp -r ${PREFIX}/include/libav* ${PREFIX}/include/libpostproc ${PREFIX}/include/libsw* /usr/local/include && \
+        mkdir -p /usr/local/lib/pkgconfig && \
+        for pc in ${PREFIX}/lib/pkgconfig/libav*.pc ${PREFIX}/lib/pkgconfig/libpostproc.pc ${PREFIX}/lib/pkgconfig/libsw*.pc; do \
+          sed "s:${PREFIX}:/usr/local:g" <"$pc" >/usr/local/lib/pkgconfig/"${pc##*/}"; \
+        done
+
+FROM        base AS release
+
+ENV         LD_LIBRARY_PATH=/usr/local/lib:/usr/local/lib64:/usr/lib:/usr/lib64:/lib:/lib64
+
+RUN \
+        apt-get -yqq update && \
+        apt-get install -yq --no-install-recommends libx265-dev libaom-dev && \
+        apt-get autoremove -y && \
+        apt-get clean -y
+
+CMD         ["--help"]
+ENTRYPOINT  ["ffmpeg"]
+
+COPY --from=build /usr/local /usr/local/

docker/Dockerfile.wheels

@@ -0,0 +1,39 @@
+FROM ubuntu:20.04 as build
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN apt-get -qq update \
+    && apt-get -qq install -y \
+    python3 \
+    python3-dev \
+    wget \
+    # opencv dependencies
+    build-essential cmake git pkg-config libgtk-3-dev \
+    libavcodec-dev libavformat-dev libswscale-dev libv4l-dev \
+    libxvidcore-dev libx264-dev libjpeg-dev libpng-dev libtiff-dev \
+    gfortran openexr libatlas-base-dev libssl-dev\
+    libtbb2 libtbb-dev libdc1394-22-dev libopenexr-dev \
+    libgstreamer-plugins-base1.0-dev libgstreamer1.0-dev \
+    # scipy dependencies
+    gcc gfortran libopenblas-dev liblapack-dev cython
+
+RUN wget -q https://bootstrap.pypa.io/get-pip.py -O get-pip.py \
+    && python3 get-pip.py
+
+RUN pip3 install scikit-build
+
+RUN pip3 wheel --wheel-dir=/wheels \
+    opencv-python-headless \
+    numpy \
+    imutils \
+    scipy \
+    psutil \
+    Flask \
+    paho-mqtt \
+    PyYAML \
+    matplotlib \
+    click
+
+FROM scratch
+
+COPY --from=build /wheels /wheels

docker/Dockerfile.wheels.aarch64

@@ -0,0 +1,49 @@
+FROM ubuntu:20.04 as build
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN apt-get -qq update \
+    && apt-get -qq install -y \
+    python3 \
+    python3-dev \
+    wget \
+    # opencv dependencies
+    build-essential cmake git pkg-config libgtk-3-dev \
+    libavcodec-dev libavformat-dev libswscale-dev libv4l-dev \
+    libxvidcore-dev libx264-dev libjpeg-dev libpng-dev libtiff-dev \
+    gfortran openexr libatlas-base-dev libssl-dev\
+    libtbb2 libtbb-dev libdc1394-22-dev libopenexr-dev \
+    libgstreamer-plugins-base1.0-dev libgstreamer1.0-dev \
+    # scipy dependencies
+    gcc gfortran libopenblas-dev liblapack-dev cython
+
+RUN wget -q https://bootstrap.pypa.io/get-pip.py -O get-pip.py \
+    && python3 get-pip.py
+
+# need to build cmake from source because binary distribution is broken for arm64
+# https://github.com/scikit-build/cmake-python-distributions/issues/115
+# https://github.com/skvark/opencv-python/issues/366
+# https://github.com/scikit-build/cmake-python-distributions/issues/96#issuecomment-663062358
+RUN pip3 install scikit-build
+
+RUN git clone https://github.com/scikit-build/cmake-python-distributions.git \
+    && cd cmake-python-distributions/ \
+    && python3 setup.py bdist_wheel
+
+RUN pip3 install cmake-python-distributions/dist/*.whl
+
+RUN pip3 wheel --wheel-dir=/wheels \
+    opencv-python-headless \
+    numpy \
+    imutils \
+    scipy \
+    psutil \
+    Flask \
+    paho-mqtt \
+    PyYAML \
+    matplotlib \
+    click
+
+FROM scratch
+
+COPY --from=build /wheels /wheels

docs/cameras.md

@@ -0,0 +1,21 @@
+# Camera Specific Configuration
+Frigate should work with most RTSP cameras and h264 feeds such as Dahua.
+
+## RTMP Cameras
+The input parameters need to be adjusted for RTMP cameras
+```yaml
+ffmpeg:
+input_args:
+    - -avoid_negative_ts
+    - make_zero
+    - -fflags
+    - nobuffer
+    - -flags
+    - low_delay
+    - -strict
+    - experimental
+    - -fflags
+    - +genpts+discardcorrupt
+    - -use_wallclock_as_timestamps
+    - '1'
+```

docs/how-frigate-works.md

@@ -0,0 +1,10 @@
+# How Frigate Works
+Frigate is designed to minimize resource and maximize performance by only looking for objects when and where it is necessary
+
+![Diagram](diagram.png)
+
+## 1. Look for Motion
+
+## 2. Calculate Detection Regions
+
+## 3. Run Object Detection

frigate/edgetpu.py

@@ -0,0 +1,199 @@
+import os
+import datetime
+import hashlib
+import multiprocessing as mp
+import queue
+from multiprocessing.connection import Connection
+from abc import ABC, abstractmethod
+from typing import Dict
+import numpy as np
+import tflite_runtime.interpreter as tflite
+from tflite_runtime.interpreter import load_delegate
+from frigate.util import EventsPerSecond, listen, SharedMemoryFrameManager
+
+def load_labels(path, encoding='utf-8'):
+  """Loads labels from file (with or without index numbers).
+  Args:
+    path: path to label file.
+    encoding: label file encoding.
+  Returns:
+    Dictionary mapping indices to labels.
+  """
+  with open(path, 'r', encoding=encoding) as f:
+    lines = f.readlines()
+    if not lines:
+        return {}
+
+    if lines[0].split(' ', maxsplit=1)[0].isdigit():
+        pairs = [line.split(' ', maxsplit=1) for line in lines]
+        return {int(index): label.strip() for index, label in pairs}
+    else:
+        return {index: line.strip() for index, line in enumerate(lines)}
+
+class ObjectDetector(ABC):
+    @abstractmethod
+    def detect(self, tensor_input, threshold = .4):
+        pass
+
+class LocalObjectDetector(ObjectDetector):
+    def __init__(self, tf_device=None, labels=None):
+        self.fps = EventsPerSecond()
+        if labels is None:
+            self.labels = {}
+        else:
+            self.labels = load_labels(labels)
+
+        device_config = {"device": "usb"}
+        if not tf_device is None:
+            device_config = {"device": tf_device}
+
+        edge_tpu_delegate = None
+
+        if tf_device != 'cpu':
+            try:
+                print(f"Attempting to load TPU as {device_config['device']}")
+                edge_tpu_delegate = load_delegate('libedgetpu.so.1.0', device_config)
+                print("TPU found")
+            except ValueError:
+                print("No EdgeTPU detected. Falling back to CPU.")
+        
+        if edge_tpu_delegate is None:
+            self.interpreter = tflite.Interpreter(
+                model_path='/cpu_model.tflite')
+        else:
+            self.interpreter = tflite.Interpreter(
+                model_path='/edgetpu_model.tflite',
+                experimental_delegates=[edge_tpu_delegate])
+        
+        self.interpreter.allocate_tensors()
+
+        self.tensor_input_details = self.interpreter.get_input_details()
+        self.tensor_output_details = self.interpreter.get_output_details()
+    
+    def detect(self, tensor_input, threshold=.4):
+        detections = []
+
+        raw_detections = self.detect_raw(tensor_input)
+
+        for d in raw_detections:
+            if d[1] < threshold:
+                break
+            detections.append((
+                self.labels[int(d[0])],
+                float(d[1]),
+                (d[2], d[3], d[4], d[5])
+            ))
+        self.fps.update()
+        return detections
+
+    def detect_raw(self, tensor_input):
+        self.interpreter.set_tensor(self.tensor_input_details[0]['index'], tensor_input)
+        self.interpreter.invoke()
+        boxes = np.squeeze(self.interpreter.get_tensor(self.tensor_output_details[0]['index']))
+        label_codes = np.squeeze(self.interpreter.get_tensor(self.tensor_output_details[1]['index']))
+        scores = np.squeeze(self.interpreter.get_tensor(self.tensor_output_details[2]['index']))
+
+        detections = np.zeros((20,6), np.float32)
+        for i, score in enumerate(scores):
+            detections[i] = [label_codes[i], score, boxes[i][0], boxes[i][1], boxes[i][2], boxes[i][3]]
+        
+        return detections
+
+def run_detector(detection_queue, out_events: Dict[str, mp.Event], avg_speed, start, tf_device):
+    print(f"Starting detection process: {os.getpid()}")
+    listen()
+    frame_manager = SharedMemoryFrameManager()
+    object_detector = LocalObjectDetector(tf_device=tf_device)
+
+    outputs = {}
+    for name in out_events.keys():
+        out_shm = mp.shared_memory.SharedMemory(name=f"out-{name}", create=False)
+        out_np = np.ndarray((20,6), dtype=np.float32, buffer=out_shm.buf)
+        outputs[name] = {
+            'shm': out_shm,
+            'np': out_np
+        }
+    
+    while True:
+        connection_id = detection_queue.get()
+        input_frame = frame_manager.get(connection_id, (1,300,300,3))
+
+        if input_frame is None:
+            continue
+
+        # detect and send the output
+        start.value = datetime.datetime.now().timestamp()
+        detections = object_detector.detect_raw(input_frame)
+        duration = datetime.datetime.now().timestamp()-start.value
+        outputs[connection_id]['np'][:] = detections[:]
+        out_events[connection_id].set()
+        start.value = 0.0
+
+        avg_speed.value = (avg_speed.value*9 + duration)/10
+        
+class EdgeTPUProcess():
+    def __init__(self, detection_queue, out_events, tf_device=None):
+        self.out_events = out_events
+        self.detection_queue = detection_queue
+        self.avg_inference_speed = mp.Value('d', 0.01)
+        self.detection_start = mp.Value('d', 0.0)
+        self.detect_process = None
+        self.tf_device = tf_device
+        self.start_or_restart()
+    
+    def stop(self):
+        self.detect_process.terminate()
+        print("Waiting for detection process to exit gracefully...")
+        self.detect_process.join(timeout=30)
+        if self.detect_process.exitcode is None:
+            print("Detection process didnt exit. Force killing...")
+            self.detect_process.kill()
+            self.detect_process.join()
+
+    def start_or_restart(self):
+        self.detection_start.value = 0.0
+        if (not self.detect_process is None) and self.detect_process.is_alive():
+            self.stop()
+        self.detect_process = mp.Process(target=run_detector, args=(self.detection_queue, self.out_events, self.avg_inference_speed, self.detection_start, self.tf_device))
+        self.detect_process.daemon = True
+        self.detect_process.start()
+
+class RemoteObjectDetector():
+    def __init__(self, name, labels, detection_queue, event):
+        self.labels = load_labels(labels)
+        self.name = name
+        self.fps = EventsPerSecond()
+        self.detection_queue = detection_queue
+        self.event = event
+        self.shm = mp.shared_memory.SharedMemory(name=self.name, create=False)
+        self.np_shm = np.ndarray((1,300,300,3), dtype=np.uint8, buffer=self.shm.buf)
+        self.out_shm = mp.shared_memory.SharedMemory(name=f"out-{self.name}", create=False)
+        self.out_np_shm = np.ndarray((20,6), dtype=np.float32, buffer=self.out_shm.buf)
+    
+    def detect(self, tensor_input, threshold=.4):
+        detections = []
+
+        # copy input to shared memory
+        self.np_shm[:] = tensor_input[:]
+        self.event.clear()
+        self.detection_queue.put(self.name)
+        result = self.event.wait(timeout=10.0)
+
+        # if it timed out
+        if result is None:
+            return detections
+
+        for d in self.out_np_shm:
+            if d[1] < threshold:
+                break
+            detections.append((
+                self.labels[int(d[0])],
+                float(d[1]),
+                (d[2], d[3], d[4], d[5])
+            ))
+        self.fps.update()
+        return detections
+    
+    def cleanup(self):
+        self.shm.unlink()
+        self.out_shm.unlink()

frigate/events.py

@@ -0,0 +1,174 @@
+import os
+import time
+import psutil
+import threading
+from collections import defaultdict
+import json
+import datetime
+import subprocess as sp
+import queue
+
+class EventProcessor(threading.Thread):
+    def __init__(self, config, camera_processes, cache_dir, clip_dir, event_queue, stop_event):
+        threading.Thread.__init__(self)
+        self.config = config
+        self.camera_processes = camera_processes
+        self.cache_dir = cache_dir
+        self.clip_dir = clip_dir
+        self.cached_clips = {}
+        self.event_queue = event_queue
+        self.events_in_process = {}
+        self.stop_event = stop_event
+    
+    def refresh_cache(self):
+        cached_files = os.listdir(self.cache_dir)
+
+        files_in_use = []
+        for process_data in self.camera_processes.values():
+            try:
+                ffmpeg_process = psutil.Process(pid=process_data['ffmpeg_pid'].value)
+                flist = ffmpeg_process.open_files()
+                if flist:
+                    for nt in flist:
+                        if nt.path.startswith(self.cache_dir):
+                            files_in_use.append(nt.path.split('/')[-1])
+            except:
+                continue
+
+        for f in cached_files:
+            if f in files_in_use or f in self.cached_clips:
+                continue
+
+            camera = '-'.join(f.split('-')[:-1])
+            start_time = datetime.datetime.strptime(f.split('-')[-1].split('.')[0], '%Y%m%d%H%M%S')
+        
+            ffprobe_cmd = " ".join([
+                'ffprobe',
+                '-v',
+                'error',
+                '-show_entries',
+                'format=duration',
+                '-of',
+                'default=noprint_wrappers=1:nokey=1',
+                f"{os.path.join(self.cache_dir,f)}"
+            ])
+            p = sp.Popen(ffprobe_cmd, stdout=sp.PIPE, shell=True)
+            (output, err) = p.communicate()
+            p_status = p.wait()
+            if p_status == 0:
+                duration = float(output.decode('utf-8').strip())
+            else:
+                print(f"bad file: {f}")
+                os.remove(os.path.join(self.cache_dir,f))
+                continue
+
+            self.cached_clips[f] = {
+                'path': f,
+                'camera': camera,
+                'start_time': start_time.timestamp(),
+                'duration': duration
+            }
+
+        if len(self.events_in_process) > 0:
+            earliest_event = min(self.events_in_process.values(), key=lambda x:x['start_time'])['start_time']
+        else:
+            earliest_event = datetime.datetime.now().timestamp()
+
+        # if the earliest event exceeds the max seconds, cap it
+        max_seconds = self.config.get('save_clips', {}).get('max_seconds', 300)
+        if datetime.datetime.now().timestamp()-earliest_event > max_seconds:
+            earliest_event = datetime.datetime.now().timestamp()-max_seconds
+        
+        for f, data in list(self.cached_clips.items()):
+            if earliest_event-90 > data['start_time']+data['duration']:
+                del self.cached_clips[f]
+                os.remove(os.path.join(self.cache_dir,f))
+
+    def create_clip(self, camera, event_data, pre_capture):
+        # get all clips from the camera with the event sorted
+        sorted_clips = sorted([c for c in self.cached_clips.values() if c['camera'] == camera], key = lambda i: i['start_time'])
+
+        while sorted_clips[-1]['start_time'] + sorted_clips[-1]['duration'] < event_data['end_time']:
+            time.sleep(5)
+            self.refresh_cache()
+            # get all clips from the camera with the event sorted
+            sorted_clips = sorted([c for c in self.cached_clips.values() if c['camera'] == camera], key = lambda i: i['start_time'])
+        
+        playlist_start = event_data['start_time']-pre_capture
+        playlist_end = event_data['end_time']+5
+        playlist_lines = []
+        for clip in sorted_clips:
+            # clip ends before playlist start time, skip
+            if clip['start_time']+clip['duration'] < playlist_start:
+                continue
+            # clip starts after playlist ends, finish
+            if clip['start_time'] > playlist_end:
+                break
+            playlist_lines.append(f"file '{os.path.join(self.cache_dir,clip['path'])}'")
+            # if this is the starting clip, add an inpoint
+            if clip['start_time'] < playlist_start:
+                playlist_lines.append(f"inpoint {int(playlist_start-clip['start_time'])}")
+            # if this is the ending clip, add an outpoint
+            if clip['start_time']+clip['duration'] > playlist_end:
+                playlist_lines.append(f"outpoint {int(playlist_end-clip['start_time'])}")
+
+        clip_name = f"{camera}-{event_data['id']}"
+        ffmpeg_cmd = [
+            'ffmpeg',
+            '-y',
+            '-protocol_whitelist',
+            'pipe,file',
+            '-f',
+            'concat',
+            '-safe',
+            '0',
+            '-i',
+            '-',
+            '-c',
+            'copy',
+            f"{os.path.join(self.clip_dir, clip_name)}.mp4"
+        ]
+
+        p = sp.run(ffmpeg_cmd, input="\n".join(playlist_lines), encoding='ascii', capture_output=True)
+        if p.returncode != 0:
+            print(p.stderr)
+            return
+        
+        with open(f"{os.path.join(self.clip_dir, clip_name)}.json", 'w') as outfile:
+            json.dump(event_data, outfile)
+
+    def run(self):
+        while True:
+            if self.stop_event.is_set():
+                print(f"Exiting event processor...")
+                break
+
+            try:
+                event_type, camera, event_data = self.event_queue.get(timeout=10)
+            except queue.Empty:
+                if not self.stop_event.is_set():
+                    self.refresh_cache()
+                continue
+
+            self.refresh_cache()
+
+            save_clips_config = self.config['cameras'][camera].get('save_clips', {})
+
+            # if save clips is not enabled for this camera, just continue
+            if not save_clips_config.get('enabled', False):
+                continue
+
+            # if specific objects are listed for this camera, only save clips for them
+            if 'objects' in save_clips_config:
+                if not event_data['label'] in save_clips_config['objects']:
+                    continue
+
+            if event_type == 'start':
+                self.events_in_process[event_data['id']] = event_data
+
+            if event_type == 'end':
+                if len(self.cached_clips) > 0 and not event_data['false_positive']:
+                    self.create_clip(camera, event_data, save_clips_config.get('pre_capture', 30))
+                del self.events_in_process[event_data['id']]
+
+                

frigate/motion.py

@@ -0,0 +1,82 @@
+import cv2
+import imutils
+import numpy as np
+
+class MotionDetector():
+    def __init__(self, frame_shape, mask, resize_factor=4):
+        self.frame_shape = frame_shape
+        self.resize_factor = resize_factor
+        self.motion_frame_size = (int(frame_shape[0]/resize_factor), int(frame_shape[1]/resize_factor))
+        self.avg_frame = np.zeros(self.motion_frame_size, np.float)
+        self.avg_delta = np.zeros(self.motion_frame_size, np.float)
+        self.motion_frame_count = 0
+        self.frame_counter = 0
+        resized_mask = cv2.resize(mask, dsize=(self.motion_frame_size[1], self.motion_frame_size[0]), interpolation=cv2.INTER_LINEAR)
+        self.mask = np.where(resized_mask==[0])
+
+    def detect(self, frame):
+        motion_boxes = []
+
+        gray = frame[0:self.frame_shape[0], 0:self.frame_shape[1]]
+
+        # resize frame
+        resized_frame = cv2.resize(gray, dsize=(self.motion_frame_size[1], self.motion_frame_size[0]), interpolation=cv2.INTER_LINEAR)
+
+        # convert to grayscale
+        # resized_frame = cv2.cvtColor(resized_frame, cv2.COLOR_BGR2GRAY)
+
+        # mask frame
+        resized_frame[self.mask] = [255]
+
+        # it takes ~30 frames to establish a baseline
+        # dont bother looking for motion
+        if self.frame_counter < 30:
+            self.frame_counter += 1
+        else:
+            # compare to average
+            frameDelta = cv2.absdiff(resized_frame, cv2.convertScaleAbs(self.avg_frame))
+
+            # compute the average delta over the past few frames
+            # the alpha value can be modified to configure how sensitive the motion detection is.
+            # higher values mean the current frame impacts the delta a lot, and a single raindrop may
+            # register as motion, too low and a fast moving person wont be detected as motion
+            # this also assumes that a person is in the same location across more than a single frame
+            cv2.accumulateWeighted(frameDelta, self.avg_delta, 0.2)
+
+            # compute the threshold image for the current frame
+            current_thresh = cv2.threshold(frameDelta, 25, 255, cv2.THRESH_BINARY)[1]
+
+            # black out everything in the avg_delta where there isnt motion in the current frame
+            avg_delta_image = cv2.convertScaleAbs(self.avg_delta)
+            avg_delta_image[np.where(current_thresh==[0])] = [0]
+
+            # then look for deltas above the threshold, but only in areas where there is a delta
+            # in the current frame. this prevents deltas from previous frames from being included
+            thresh = cv2.threshold(avg_delta_image, 25, 255, cv2.THRESH_BINARY)[1]
+
+            # dilate the thresholded image to fill in holes, then find contours
+            # on thresholded image
+            thresh = cv2.dilate(thresh, None, iterations=2)
+            cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+            cnts = imutils.grab_contours(cnts)
+
+            # loop over the contours
+            for c in cnts:
+                # if the contour is big enough, count it as motion
+                contour_area = cv2.contourArea(c)
+                if contour_area > 100:
+                    x, y, w, h = cv2.boundingRect(c)
+                    motion_boxes.append((x*self.resize_factor, y*self.resize_factor, (x+w)*self.resize_factor, (y+h)*self.resize_factor))
+        
+        if len(motion_boxes) > 0:
+            self.motion_frame_count += 1
+            # TODO: this really depends on FPS
+            if self.motion_frame_count >= 10:
+                # only average in the current frame if the difference persists for at least 3 frames
+                cv2.accumulateWeighted(resized_frame, self.avg_frame, 0.2)
+        else:
+            # when no motion, just keep averaging the frames together
+            cv2.accumulateWeighted(resized_frame, self.avg_frame, 0.2)
+            self.motion_frame_count = 0
+
+        return motion_boxes

frigate/mqtt.py

@@ -1,33 +0,0 @@
-import json
-import threading
-
-class MqttObjectPublisher(threading.Thread):
-    def __init__(self, client, topic_prefix, objects_parsed, detected_objects):
-        threading.Thread.__init__(self)
-        self.client = client
-        self.topic_prefix = topic_prefix
-        self.objects_parsed = objects_parsed
-        self._detected_objects = detected_objects
-
-    def run(self):
-        last_sent_payload = ""
-        while True:
-
-            # initialize the payload
-            payload = {}
-
-            # wait until objects have been parsed
-            with self.objects_parsed:
-                self.objects_parsed.wait()
-
-            # add all the person scores in detected objects
-            detected_objects = self._detected_objects.copy()
-            person_score = sum([obj['score'] for obj in detected_objects if obj['name'] == 'person'])
-            # if the person score is more than 100, set person to ON
-            payload['person'] = 'ON' if int(person_score*100) > 100 else 'OFF'
-
-            # send message for objects if different
-            new_payload = json.dumps(payload, sort_keys=True)
-            if new_payload != last_sent_payload:
-                last_sent_payload = new_payload
-                self.client.publish(self.topic_prefix+'/objects', new_payload, retain=False)

frigate/object_detection.py

@@ -1,110 +0,0 @@
-import datetime
-import time
-import cv2
-import threading
-import numpy as np
-from edgetpu.detection.engine import DetectionEngine
-from . util import tonumpyarray
-
-# Path to frozen detection graph. This is the actual model that is used for the object detection.
-PATH_TO_CKPT = '/frozen_inference_graph.pb'
-# List of the strings that is used to add correct label for each box.
-PATH_TO_LABELS = '/label_map.pbtext'
-
-# Function to read labels from text files.
-def ReadLabelFile(file_path):
-    with open(file_path, 'r') as f:
-        lines = f.readlines()
-    ret = {}
-    for line in lines:
-        pair = line.strip().split(maxsplit=1)
-        ret[int(pair[0])] = pair[1].strip()
-    return ret
-
-class PreppedQueueProcessor(threading.Thread):
-    def __init__(self, cameras, prepped_frame_queue):
-
-        threading.Thread.__init__(self)
-        self.cameras = cameras
-        self.prepped_frame_queue = prepped_frame_queue
-        
-        # Load the edgetpu engine and labels
-        self.engine = DetectionEngine(PATH_TO_CKPT)
-        self.labels = ReadLabelFile(PATH_TO_LABELS)
-
-    def run(self):
-        # process queue...
-        while True:
-            frame = self.prepped_frame_queue.get()
-
-            # Actual detection.
-            objects = self.engine.DetectWithInputTensor(frame['frame'], threshold=0.5, top_k=3)
-            # parse and pass detected objects back to the camera
-            parsed_objects = []
-            for obj in objects:
-                box = obj.bounding_box.flatten().tolist()
-                parsed_objects.append({
-                            'frame_time': frame['frame_time'],
-                            'name': str(self.labels[obj.label_id]),
-                            'score': float(obj.score),
-                            'xmin': int((box[0] * frame['region_size']) + frame['region_x_offset']),
-                            'ymin': int((box[1] * frame['region_size']) + frame['region_y_offset']),
-                            'xmax': int((box[2] * frame['region_size']) + frame['region_x_offset']),
-                            'ymax': int((box[3] * frame['region_size']) + frame['region_y_offset'])
-                        })
-            self.cameras[frame['camera_name']].add_objects(parsed_objects)
-
-
-# should this be a region class?
-class FramePrepper(threading.Thread):
-    def __init__(self, camera_name, shared_frame, frame_time, frame_ready, 
-        frame_lock,
-        region_size, region_x_offset, region_y_offset,
-        prepped_frame_queue):
-
-        threading.Thread.__init__(self)
-        self.camera_name = camera_name
-        self.shared_frame = shared_frame
-        self.frame_time = frame_time
-        self.frame_ready = frame_ready
-        self.frame_lock = frame_lock
-        self.region_size = region_size
-        self.region_x_offset = region_x_offset
-        self.region_y_offset = region_y_offset
-        self.prepped_frame_queue = prepped_frame_queue
-
-    def run(self):
-        frame_time = 0.0
-        while True:
-            now = datetime.datetime.now().timestamp()
-
-            with self.frame_ready:
-                # if there isnt a frame ready for processing or it is old, wait for a new frame
-                if self.frame_time.value == frame_time or (now - self.frame_time.value) > 0.5:
-                    self.frame_ready.wait()
-            
-            # make a copy of the cropped frame
-            with self.frame_lock:
-                cropped_frame = self.shared_frame[self.region_y_offset:self.region_y_offset+self.region_size, self.region_x_offset:self.region_x_offset+self.region_size].copy()
-                frame_time = self.frame_time.value
-            
-            # convert to RGB
-            cropped_frame_rgb = cv2.cvtColor(cropped_frame, cv2.COLOR_BGR2RGB)
-            # Resize to 300x300 if needed
-            if cropped_frame_rgb.shape != (300, 300, 3):
-                cropped_frame_rgb = cv2.resize(cropped_frame_rgb, dsize=(300, 300), interpolation=cv2.INTER_LINEAR)
-            # Expand dimensions since the model expects images to have shape: [1, 300, 300, 3]
-            frame_expanded = np.expand_dims(cropped_frame_rgb, axis=0)
-
-            # add the frame to the queue
-            if not self.prepped_frame_queue.full():
-                self.prepped_frame_queue.put({
-                    'camera_name': self.camera_name,
-                    'frame_time': frame_time,
-                    'frame': frame_expanded.flatten().copy(),
-                    'region_size': self.region_size,
-                    'region_x_offset': self.region_x_offset,
-                    'region_y_offset': self.region_y_offset
-                })
-            else:
-                print("queue full. moving on")

frigate/object_processing.py

@@ -0,0 +1,393 @@
+import json
+import hashlib
+import datetime
+import time
+import copy
+import cv2
+import threading
+import queue
+import copy
+import numpy as np
+from collections import Counter, defaultdict
+import itertools
+import matplotlib.pyplot as plt
+from frigate.util import draw_box_with_label, SharedMemoryFrameManager
+from frigate.edgetpu import load_labels
+from typing import Callable, Dict
+from statistics import mean, median
+
+PATH_TO_LABELS = '/labelmap.txt'
+
+LABELS = load_labels(PATH_TO_LABELS)
+cmap = plt.cm.get_cmap('tab10', len(LABELS.keys()))
+
+COLOR_MAP = {}
+for key, val in LABELS.items():
+    COLOR_MAP[val] = tuple(int(round(255 * c)) for c in cmap(key)[:3])
+
+def zone_filtered(obj, object_config):
+    object_name = obj['label']
+
+    if object_name in object_config:
+        obj_settings = object_config[object_name]
+
+        # if the min area is larger than the
+        # detected object, don't add it to detected objects
+        if obj_settings.get('min_area',-1) > obj['area']:
+            return True
+        
+        # if the detected object is larger than the
+        # max area, don't add it to detected objects
+        if obj_settings.get('max_area', 24000000) < obj['area']:
+            return True
+
+        # if the score is lower than the threshold, skip
+        if obj_settings.get('threshold', 0) > obj['computed_score']:
+            return True
+        
+    return False
+
+# Maintains the state of a camera
+class CameraState():
+    def __init__(self, name, config, frame_manager):
+        self.name = name
+        self.config = config
+        self.frame_manager = frame_manager
+
+        self.best_objects = {}
+        self.object_status = defaultdict(lambda: 'OFF')
+        self.tracked_objects = {}
+        self.zone_objects = defaultdict(lambda: [])
+        self._current_frame = np.zeros((self.config['frame_shape'][0]*3//2, self.config['frame_shape'][1]), np.uint8)
+        self.current_frame_lock = threading.Lock()
+        self.current_frame_time = 0.0
+        self.previous_frame_id = None
+        self.callbacks = defaultdict(lambda: [])
+
+    def get_current_frame(self, draw=False):
+        with self.current_frame_lock:
+            frame_copy = np.copy(self._current_frame)
+            frame_time = self.current_frame_time
+            tracked_objects = copy.deepcopy(self.tracked_objects)
+        
+        frame_copy = cv2.cvtColor(frame_copy, cv2.COLOR_YUV2BGR_I420)
+        # draw on the frame
+        if draw:
+            # draw the bounding boxes on the frame
+            for obj in tracked_objects.values():
+                thickness = 2
+                color = COLOR_MAP[obj['label']]
+                
+                if obj['frame_time'] != frame_time:
+                    thickness = 1
+                    color = (255,0,0)
+
+                # draw the bounding boxes on the frame
+                box = obj['box']
+                draw_box_with_label(frame_copy, box[0], box[1], box[2], box[3], obj['label'], f"{int(obj['score']*100)}% {int(obj['area'])}", thickness=thickness, color=color)
+                # draw the regions on the frame
+                region = obj['region']
+                cv2.rectangle(frame_copy, (region[0], region[1]), (region[2], region[3]), (0,255,0), 1)
+            
+            if self.config['snapshots']['show_timestamp']:
+                time_to_show = datetime.datetime.fromtimestamp(frame_time).strftime("%m/%d/%Y %H:%M:%S")
+                cv2.putText(frame_copy, time_to_show, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, fontScale=.8, color=(255, 255, 255), thickness=2)
+
+            if self.config['snapshots']['draw_zones']:
+                for name, zone in self.config['zones'].items():
+                    thickness = 8 if any([name in obj['zones'] for obj in tracked_objects.values()]) else 2
+                    cv2.drawContours(frame_copy, [zone['contour']], -1, zone['color'], thickness)
+        
+        return frame_copy
+
+    def false_positive(self, obj):
+        # once a true positive, always a true positive
+        if not obj.get('false_positive', True):
+            return False
+
+        threshold = self.config['objects'].get('filters', {}).get(obj['label'], {}).get('threshold', 0.85)
+        if obj['computed_score'] < threshold:
+            return True
+        return False
+
+    def compute_score(self, obj):
+        scores = obj['score_history'][:]
+        # pad with zeros if you dont have at least 3 scores
+        if len(scores) < 3:
+            scores += [0.0]*(3 - len(scores))
+        return median(scores)
+
+    def on(self, event_type: str, callback: Callable[[Dict], None]):
+        self.callbacks[event_type].append(callback)
+
+    def update(self, frame_time, tracked_objects):
+        self.current_frame_time = frame_time
+        # get the new frame and delete the old frame
+        frame_id = f"{self.name}{frame_time}"
+        current_frame = self.frame_manager.get(frame_id, (self.config['frame_shape'][0]*3//2, self.config['frame_shape'][1]))
+
+        current_ids = tracked_objects.keys()
+        previous_ids = self.tracked_objects.keys()
+        removed_ids = list(set(previous_ids).difference(current_ids))
+        new_ids = list(set(current_ids).difference(previous_ids))
+        updated_ids = list(set(current_ids).intersection(previous_ids))
+
+        for id in new_ids:
+            self.tracked_objects[id] = tracked_objects[id]
+            self.tracked_objects[id]['zones'] = []
+
+            # start the score history
+            self.tracked_objects[id]['score_history'] = [self.tracked_objects[id]['score']]
+
+            # calculate if this is a false positive
+            self.tracked_objects[id]['computed_score'] = self.compute_score(self.tracked_objects[id])
+            self.tracked_objects[id]['false_positive'] = self.false_positive(self.tracked_objects[id])
+
+            # call event handlers
+            for c in self.callbacks['start']:
+                c(self.name, tracked_objects[id])
+        
+        for id in updated_ids:
+            self.tracked_objects[id].update(tracked_objects[id])
+
+            # if the object is not in the current frame, add a 0.0 to the score history
+            if self.tracked_objects[id]['frame_time'] != self.current_frame_time:
+                self.tracked_objects[id]['score_history'].append(0.0)
+            else:
+                self.tracked_objects[id]['score_history'].append(self.tracked_objects[id]['score'])
+            # only keep the last 10 scores
+            if len(self.tracked_objects[id]['score_history']) > 10:
+                self.tracked_objects[id]['score_history'] = self.tracked_objects[id]['score_history'][-10:]
+
+            # calculate if this is a false positive
+            self.tracked_objects[id]['computed_score'] = self.compute_score(self.tracked_objects[id])
+            self.tracked_objects[id]['false_positive'] = self.false_positive(self.tracked_objects[id])
+
+            # call event handlers
+            for c in self.callbacks['update']:
+                c(self.name, self.tracked_objects[id])
+        
+        for id in removed_ids:
+            # publish events to mqtt
+            self.tracked_objects[id]['end_time'] = frame_time
+            for c in self.callbacks['end']:
+                c(self.name, self.tracked_objects[id])
+            del self.tracked_objects[id]
+
+        # check to see if the objects are in any zones
+        for obj in self.tracked_objects.values():
+            current_zones = []
+            bottom_center = (obj['centroid'][0], obj['box'][3])
+            # check each zone
+            for name, zone in self.config['zones'].items():
+                contour = zone['contour']
+                # check if the object is in the zone
+                if (cv2.pointPolygonTest(contour, bottom_center, False) >= 0):
+                    # if the object passed the filters once, dont apply again
+                    if name in obj.get('zones', []) or not zone_filtered(obj, zone.get('filters', {})):
+                        current_zones.append(name)
+                    
+            obj['zones'] = current_zones
+
+        # maintain best objects
+        for obj in self.tracked_objects.values():
+            object_type = obj['label']
+            # if the object wasn't seen on the current frame, skip it
+            if obj['frame_time'] != self.current_frame_time or obj['false_positive']:
+                continue
+            obj_copy = copy.deepcopy(obj)
+            if object_type in self.best_objects:
+                current_best = self.best_objects[object_type]
+                now = datetime.datetime.now().timestamp()
+                # if the object is a higher score than the current best score 
+                # or the current object is older than desired, use the new object
+                if obj_copy['score'] > current_best['score'] or (now - current_best['frame_time']) > self.config.get('best_image_timeout', 60):
+                    obj_copy['frame'] = np.copy(current_frame)
+                    self.best_objects[object_type] = obj_copy
+                    for c in self.callbacks['snapshot']:
+                        c(self.name, self.best_objects[object_type])
+            else:
+                obj_copy['frame'] = np.copy(current_frame)
+                self.best_objects[object_type] = obj_copy
+                for c in self.callbacks['snapshot']:
+                    c(self.name, self.best_objects[object_type])
+        
+        # update overall camera state for each object type
+        obj_counter = Counter()
+        for obj in self.tracked_objects.values():
+            if not obj['false_positive']:
+                obj_counter[obj['label']] += 1
+                
+        # report on detected objects
+        for obj_name, count in obj_counter.items():
+            new_status = 'ON' if count > 0 else 'OFF'
+            if new_status != self.object_status[obj_name]:
+                self.object_status[obj_name] = new_status
+                for c in self.callbacks['object_status']:
+                    c(self.name, obj_name, new_status)
+
+        # expire any objects that are ON and no longer detected
+        expired_objects = [obj_name for obj_name, status in self.object_status.items() if status == 'ON' and not obj_name in obj_counter]
+        for obj_name in expired_objects:
+            self.object_status[obj_name] = 'OFF'
+            for c in self.callbacks['object_status']:
+                c(self.name, obj_name, 'OFF')
+            for c in self.callbacks['snapshot']:
+                c(self.name, self.best_objects[obj_name])
+        
+        with self.current_frame_lock:
+            self._current_frame = current_frame
+            if not self.previous_frame_id is None:
+                self.frame_manager.delete(self.previous_frame_id)
+            self.previous_frame_id = frame_id
+
+class TrackedObjectProcessor(threading.Thread):
+    def __init__(self, camera_config, client, topic_prefix, tracked_objects_queue, event_queue, stop_event):
+        threading.Thread.__init__(self)
+        self.camera_config = camera_config
+        self.client = client
+        self.topic_prefix = topic_prefix
+        self.tracked_objects_queue = tracked_objects_queue
+        self.event_queue = event_queue
+        self.stop_event = stop_event
+        self.camera_states: Dict[str, CameraState] = {}
+        self.frame_manager = SharedMemoryFrameManager()
+
+        def start(camera, obj):
+            # publish events to mqtt
+            self.client.publish(f"{self.topic_prefix}/{camera}/events/start", json.dumps(obj), retain=False)
+            self.event_queue.put(('start', camera, obj))
+
+        def update(camera, obj):
+            pass
+
+        def end(camera, obj):
+            self.client.publish(f"{self.topic_prefix}/{camera}/events/end", json.dumps(obj), retain=False)
+            self.event_queue.put(('end', camera, obj))
+        
+        def snapshot(camera, obj):
+            if not 'frame' in obj:
+                return
+            
+            best_frame = cv2.cvtColor(obj['frame'], cv2.COLOR_YUV2BGR_I420)
+            if self.camera_config[camera]['snapshots']['draw_bounding_boxes']:
+                thickness = 2
+                color = COLOR_MAP[obj['label']]
+                box = obj['box']
+                draw_box_with_label(best_frame, box[0], box[1], box[2], box[3], obj['label'], f"{int(obj['score']*100)}% {int(obj['area'])}", thickness=thickness, color=color)
+                
+            mqtt_config = self.camera_config[camera].get('mqtt', {'crop_to_region': False})
+            if mqtt_config.get('crop_to_region'):
+                region = obj['region']
+                best_frame = best_frame[region[1]:region[3], region[0]:region[2]]
+            if 'snapshot_height' in mqtt_config: 
+                height = int(mqtt_config['snapshot_height'])
+                width = int(height*best_frame.shape[1]/best_frame.shape[0])
+                best_frame = cv2.resize(best_frame, dsize=(width, height), interpolation=cv2.INTER_AREA)
+            
+            if self.camera_config[camera]['snapshots']['show_timestamp']:
+                time_to_show = datetime.datetime.fromtimestamp(obj['frame_time']).strftime("%m/%d/%Y %H:%M:%S")
+                size = cv2.getTextSize(time_to_show, cv2.FONT_HERSHEY_SIMPLEX, fontScale=1, thickness=2)
+                text_width = size[0][0]
+                text_height = size[0][1]
+                desired_size = max(200, 0.33*best_frame.shape[1])
+                font_scale = desired_size/text_width
+                cv2.putText(best_frame, time_to_show, (5, best_frame.shape[0]-7), cv2.FONT_HERSHEY_SIMPLEX, fontScale=font_scale, color=(255, 255, 255), thickness=2)
+
+            ret, jpg = cv2.imencode('.jpg', best_frame)
+            if ret:
+                jpg_bytes = jpg.tobytes()
+                self.client.publish(f"{self.topic_prefix}/{camera}/{obj['label']}/snapshot", jpg_bytes, retain=True)
+        
+        def object_status(camera, object_name, status):
+            self.client.publish(f"{self.topic_prefix}/{camera}/{object_name}", status, retain=False)
+
+        for camera in self.camera_config.keys():
+            camera_state = CameraState(camera, self.camera_config[camera], self.frame_manager)
+            camera_state.on('start', start)
+            camera_state.on('update', update)
+            camera_state.on('end', end)
+            camera_state.on('snapshot', snapshot)
+            camera_state.on('object_status', object_status)
+            self.camera_states[camera] = camera_state
+
+        self.camera_data = defaultdict(lambda: {
+            'best_objects': {},
+            'object_status': defaultdict(lambda: defaultdict(lambda: 'OFF')),
+            'tracked_objects': {},
+            'current_frame': np.zeros((720,1280,3), np.uint8),
+            'current_frame_time': 0.0,
+            'object_id': None
+        })
+        # {
+        #   'zone_name': {
+        #       'person': ['camera_1', 'camera_2']
+        #   }
+        # }
+        self.zone_data = defaultdict(lambda: defaultdict(lambda: set()))
+
+        # set colors for zones
+        all_zone_names = set([zone for config in self.camera_config.values() for zone in config['zones'].keys()])
+        zone_colors = {}
+        colors = plt.cm.get_cmap('tab10', len(all_zone_names))
+        for i, zone in enumerate(all_zone_names):
+            zone_colors[zone] = tuple(int(round(255 * c)) for c in colors(i)[:3])
+
+        # create zone contours
+        for camera_config in self.camera_config.values():
+            for zone_name, zone_config in camera_config['zones'].items():
+                zone_config['color'] = zone_colors[zone_name]
+                coordinates = zone_config['coordinates']
+                if isinstance(coordinates, list):
+                    zone_config['contour'] =  np.array([[int(p.split(',')[0]), int(p.split(',')[1])] for p in coordinates])
+                elif isinstance(coordinates, str):
+                    points = coordinates.split(',')
+                    zone_config['contour'] =  np.array([[int(points[i]), int(points[i+1])] for i in range(0, len(points), 2)])
+                else:
+                    print(f"Unable to parse zone coordinates for {zone_name} - {camera}")
+        
+    def get_best(self, camera, label):
+        best_objects = self.camera_states[camera].best_objects
+        if label in best_objects:
+            return best_objects[label]
+        else:
+            return {}
+    
+    def get_current_frame(self, camera, draw=False):
+        return self.camera_states[camera].get_current_frame(draw)
+
+    def run(self):
+        while True:
+            if self.stop_event.is_set():
+                print(f"Exiting object processor...")
+                break
+
+            try:
+                camera, frame_time, current_tracked_objects = self.tracked_objects_queue.get(True, 10)
+            except queue.Empty:
+                continue
+
+            camera_state = self.camera_states[camera]
+
+            camera_state.update(frame_time, current_tracked_objects)
+
+            # update zone status for each label
+            for zone in camera_state.config['zones'].keys():
+                # get labels for current camera and all labels in current zone
+                labels_for_camera = set([obj['label'] for obj in camera_state.tracked_objects.values() if zone in obj['zones'] and not obj['false_positive']])
+                labels_to_check = labels_for_camera | set(self.zone_data[zone].keys())
+                # for each label in zone
+                for label in labels_to_check:
+                    camera_list = self.zone_data[zone][label]
+                    # remove or add the camera to the list for the current label
+                    previous_state = len(camera_list) > 0
+                    if label in labels_for_camera:
+                        camera_list.add(camera_state.name)
+                    elif camera_state.name in camera_list:
+                        camera_list.remove(camera_state.name)
+                    new_state = len(camera_list) > 0
+                    # if the value is changing, send over MQTT
+                    if previous_state == False and new_state == True:
+                        self.client.publish(f"{self.topic_prefix}/{zone}/{label}", 'ON', retain=False)
+                    elif previous_state == True and new_state == False:
+                        self.client.publish(f"{self.topic_prefix}/{zone}/{label}", 'OFF', retain=False)

frigate/objects.py

@@ -2,95 +2,147 @@ import time
 import datetime
 import threading
 import cv2
-from object_detection.utils import visualization_utils as vis_util
+import itertools
+import copy
+import numpy as np
+import random
+import string
+import multiprocessing as mp
+from collections import defaultdict
+from scipy.spatial import distance as dist
+from frigate.util import draw_box_with_label, calculate_region
 
-class ObjectCleaner(threading.Thread):
-    def __init__(self, objects_parsed, detected_objects):
-        threading.Thread.__init__(self)
-        self._objects_parsed = objects_parsed
-        self._detected_objects = detected_objects
+class ObjectTracker():
+    def __init__(self, max_disappeared):
+        self.tracked_objects = {}
+        self.disappeared = {}
+        self.max_disappeared = max_disappeared
 
-    def run(self):
-        while True:
+    def register(self, index, obj):
+        rand_id = ''.join(random.choices(string.ascii_lowercase + string.digits, k=6))
+        id = f"{obj['frame_time']}-{rand_id}"
+        obj['id'] = id
+        obj['start_time'] = obj['frame_time']
+        obj['top_score'] = obj['score']
+        self.tracked_objects[id] = obj
+        self.disappeared[id] = 0
 
-            # wait a bit before checking for expired frames
-            time.sleep(0.2)
+    def deregister(self, id):
+        del self.tracked_objects[id]
+        del self.disappeared[id]
+    
+    def update(self, id, new_obj):
+        self.disappeared[id] = 0
+        self.tracked_objects[id].update(new_obj)
+        if self.tracked_objects[id]['score'] > self.tracked_objects[id]['top_score']:
+            self.tracked_objects[id]['top_score'] = self.tracked_objects[id]['score']
 
-            # expire the objects that are more than 1 second old
-            now = datetime.datetime.now().timestamp()
-            # look for the first object found within the last second
-            # (newest objects are appended to the end)
-            detected_objects = self._detected_objects.copy()
+    def match_and_update(self, frame_time, new_objects):
+        # group by name
+        new_object_groups = defaultdict(lambda: [])
+        for obj in new_objects:
+            new_object_groups[obj[0]].append({
+                'label': obj[0],
+                'score': obj[1],
+                'box': obj[2],
+                'area': obj[3],
+                'region': obj[4],
+                'frame_time': frame_time
+            })
+        
+        # update any tracked objects with labels that are not
+        # seen in the current objects and deregister if needed
+        for obj in list(self.tracked_objects.values()):
+            if not obj['label'] in new_object_groups:
+                if self.disappeared[obj['id']] >= self.max_disappeared:
+                    self.deregister(obj['id'])
+                else:
+                    self.disappeared[obj['id']] += 1
+        
+        if len(new_objects) == 0:
+            return
+        
+        # track objects for each label type
+        for label, group in new_object_groups.items():
+            current_objects = [o for o in self.tracked_objects.values() if o['label'] == label]
+            current_ids = [o['id'] for o in current_objects]
+            current_centroids = np.array([o['centroid'] for o in current_objects])
 
-            num_to_delete = 0
-            for obj in detected_objects:
-                if now-obj['frame_time']<2:
-                    break
-                num_to_delete += 1
-            if num_to_delete > 0:
-                del self._detected_objects[:num_to_delete]
+            # compute centroids of new objects
+            for obj in group:
+                centroid_x = int((obj['box'][0]+obj['box'][2]) / 2.0)
+                centroid_y = int((obj['box'][1]+obj['box'][3]) / 2.0)
+                obj['centroid'] = (centroid_x, centroid_y)
 
-                # notify that parsed objects were changed
-                with self._objects_parsed:
-                    self._objects_parsed.notify_all()
+            if len(current_objects) == 0:
+                for index, obj in enumerate(group):
+                    self.register(index, obj)
+                return
+            
+            new_centroids = np.array([o['centroid'] for o in group])
 
+            # compute the distance between each pair of tracked
+            # centroids and new centroids, respectively -- our
+            # goal will be to match each new centroid to an existing
+            # object centroid
+            D = dist.cdist(current_centroids, new_centroids)
 
-# Maintains the frame and person with the highest score from the most recent
-# motion event
-class BestPersonFrame(threading.Thread):
-    def __init__(self, objects_parsed, recent_frames, detected_objects):
-        threading.Thread.__init__(self)
-        self.objects_parsed = objects_parsed
-        self.recent_frames = recent_frames
-        self.detected_objects = detected_objects
-        self.best_person = None
-        self.best_frame = None
+            # in order to perform this matching we must (1) find the
+            # smallest value in each row and then (2) sort the row
+            # indexes based on their minimum values so that the row
+            # with the smallest value is at the *front* of the index
+            # list
+            rows = D.min(axis=1).argsort()
 
-    def run(self):
-        while True:
+            # next, we perform a similar process on the columns by
+            # finding the smallest value in each column and then
+            # sorting using the previously computed row index list
+            cols = D.argmin(axis=1)[rows]
 
-            # wait until objects have been parsed
-            with self.objects_parsed:
-                self.objects_parsed.wait()
+            # in order to determine if we need to update, register,
+            # or deregister an object we need to keep track of which
+            # of the rows and column indexes we have already examined
+            usedRows = set()
+            usedCols = set()
 
-            # make a copy of detected objects
-            detected_objects = self.detected_objects.copy()
-            detected_people = [obj for obj in detected_objects if obj['name'] == 'person']
+            # loop over the combination of the (row, column) index
+            # tuples
+            for (row, col) in zip(rows, cols):
+                # if we have already examined either the row or
+                # column value before, ignore it
+                if row in usedRows or col in usedCols:
+                    continue
 
-            # get the highest scoring person
-            new_best_person = max(detected_people, key=lambda x:x['score'], default=self.best_person)
+                # otherwise, grab the object ID for the current row,
+                # set its new centroid, and reset the disappeared
+                # counter
+                objectID = current_ids[row]
+                self.update(objectID, group[col])
 
-            # if there isnt a person, continue
-            if new_best_person is None:
-                continue
+                # indicate that we have examined each of the row and
+                # column indexes, respectively
+                usedRows.add(row)
+                usedCols.add(col)
 
-            # if there is no current best_person
-            if self.best_person is None:
-                self.best_person = new_best_person
-            # if there is already a best_person
+            # compute the column index we have NOT yet examined
+            unusedRows = set(range(0, D.shape[0])).difference(usedRows)
+            unusedCols = set(range(0, D.shape[1])).difference(usedCols)
+
+            # in the event that the number of object centroids is
+			# equal or greater than the number of input centroids
+			# we need to check and see if some of these objects have
+			# potentially disappeared
+            if D.shape[0] >= D.shape[1]:
+                for row in unusedRows:
+                    id = current_ids[row]
+
+                    if self.disappeared[id] >= self.max_disappeared:
+                        self.deregister(id)
+                    else:
+                        self.disappeared[id] += 1
+            # if the number of input centroids is greater
+            # than the number of existing object centroids we need to
+            # register each new input centroid as a trackable object
             else:
-                now = datetime.datetime.now().timestamp()
-                # if the new best person is a higher score than the current best person 
-                # or the current person is more than 1 minute old, use the new best person
-                if new_best_person['score'] > self.best_person['score'] or (now - self.best_person['frame_time']) > 60:
-                    self.best_person = new_best_person
-            
-            # make a copy of the recent frames
-            recent_frames = self.recent_frames.copy()
-            
-            if not self.best_person is None and self.best_person['frame_time'] in recent_frames:
-                best_frame = recent_frames[self.best_person['frame_time']]
-                best_frame = cv2.cvtColor(best_frame, cv2.COLOR_BGR2RGB)
-                # draw the bounding box on the frame
-                vis_util.draw_bounding_box_on_image_array(best_frame,
-                    self.best_person['ymin'],
-                    self.best_person['xmin'],
-                    self.best_person['ymax'],
-                    self.best_person['xmax'],
-                    color='red',
-                    thickness=2,
-                    display_str_list=["{}: {}%".format(self.best_person['name'],int(self.best_person['score']*100))],
-                    use_normalized_coordinates=False)
-
-                # convert back to BGR
-                self.best_frame = cv2.cvtColor(best_frame, cv2.COLOR_RGB2BGR)
+                for col in unusedCols:
+                    self.register(col, group[col])

frigate/util.py

@@ -1,5 +1,244 @@
+from abc import ABC, abstractmethod
+import datetime
+import time
+import signal
+import traceback
+import collections
 import numpy as np
+import cv2
+import threading
+import matplotlib.pyplot as plt
+import hashlib
+from multiprocessing import shared_memory
+from typing import AnyStr
 
-# convert shared memory array into numpy array
-def tonumpyarray(mp_arr):
-    return np.frombuffer(mp_arr.get_obj(), dtype=np.uint8)
+def draw_box_with_label(frame, x_min, y_min, x_max, y_max, label, info, thickness=2, color=None, position='ul'):
+    if color is None:
+        color = (0,0,255)
+    display_text = "{}: {}".format(label, info)
+    cv2.rectangle(frame, (x_min, y_min), (x_max, y_max), color, thickness)
+    font_scale = 0.5
+    font = cv2.FONT_HERSHEY_SIMPLEX
+    # get the width and height of the text box
+    size = cv2.getTextSize(display_text, font, fontScale=font_scale, thickness=2)
+    text_width = size[0][0]
+    text_height = size[0][1]
+    line_height = text_height + size[1]
+    # set the text start position
+    if position == 'ul':
+        text_offset_x = x_min
+        text_offset_y = 0 if y_min < line_height else y_min - (line_height+8)
+    elif position == 'ur':
+        text_offset_x = x_max - (text_width+8)
+        text_offset_y = 0 if y_min < line_height else y_min - (line_height+8)
+    elif position == 'bl':
+        text_offset_x = x_min
+        text_offset_y = y_max
+    elif position == 'br':
+        text_offset_x = x_max - (text_width+8)
+        text_offset_y = y_max
+    # make the coords of the box with a small padding of two pixels
+    textbox_coords = ((text_offset_x, text_offset_y), (text_offset_x + text_width + 2, text_offset_y + line_height))
+    cv2.rectangle(frame, textbox_coords[0], textbox_coords[1], color, cv2.FILLED)
+    cv2.putText(frame, display_text, (text_offset_x, text_offset_y + line_height - 3), font, fontScale=font_scale, color=(0, 0, 0), thickness=2)
+
+def calculate_region(frame_shape, xmin, ymin, xmax, ymax, multiplier=2):    
+    # size is larger than longest edge
+    size = int(max(xmax-xmin, ymax-ymin)*multiplier)
+    # dont go any smaller than 300
+    if size < 300:
+        size = 300
+    # if the size is too big to fit in the frame
+    if size > min(frame_shape[0], frame_shape[1]):
+        size = min(frame_shape[0], frame_shape[1])
+
+    # x_offset is midpoint of bounding box minus half the size
+    x_offset = int((xmax-xmin)/2.0+xmin-size/2.0)
+    # if outside the image
+    if x_offset < 0:
+        x_offset = 0
+    elif x_offset > (frame_shape[1]-size):
+        x_offset = (frame_shape[1]-size)
+
+    # y_offset is midpoint of bounding box minus half the size
+    y_offset = int((ymax-ymin)/2.0+ymin-size/2.0)
+    # if outside the image
+    if y_offset < 0:
+        y_offset = 0
+    elif y_offset > (frame_shape[0]-size):
+        y_offset = (frame_shape[0]-size)
+
+    return (x_offset, y_offset, x_offset+size, y_offset+size)
+
+def yuv_region_2_rgb(frame, region):
+    height = frame.shape[0]//3*2
+    width = frame.shape[1]
+    # make sure the size is a multiple of 4
+    size = (region[3] - region[1])//4*4
+
+    x1 = region[0] 
+    y1 = region[1]
+
+    uv_x1 = x1//2
+    uv_y1 = y1//4
+
+    uv_width = size//2
+    uv_height = size//4
+
+    u_y_start = height
+    v_y_start = height + height//4
+    two_x_offset = width//2
+
+    yuv_cropped_frame = np.zeros((size+size//2, size), np.uint8)
+    # y channel
+    yuv_cropped_frame[0:size, 0:size] = frame[y1:y1+size, x1:x1+size]
+    # u channel
+    yuv_cropped_frame[size:size+uv_height, 0:uv_width] = frame[uv_y1+u_y_start:uv_y1+u_y_start+uv_height, uv_x1:uv_x1+uv_width]
+    yuv_cropped_frame[size:size+uv_height, uv_width:size] = frame[uv_y1+u_y_start:uv_y1+u_y_start+uv_height, uv_x1+two_x_offset:uv_x1+two_x_offset+uv_width]
+    # v channel
+    yuv_cropped_frame[size+uv_height:size+uv_height*2, 0:uv_width] = frame[uv_y1+v_y_start:uv_y1+v_y_start+uv_height, uv_x1:uv_x1+uv_width]
+    yuv_cropped_frame[size+uv_height:size+uv_height*2, uv_width:size] = frame[uv_y1+v_y_start:uv_y1+v_y_start+uv_height, uv_x1+two_x_offset:uv_x1+two_x_offset+uv_width]
+
+    return cv2.cvtColor(yuv_cropped_frame, cv2.COLOR_YUV2RGB_I420)
+
+def intersection(box_a, box_b):
+    return (
+        max(box_a[0], box_b[0]),
+        max(box_a[1], box_b[1]),
+        min(box_a[2], box_b[2]),
+        min(box_a[3], box_b[3])
+    )
+
+def area(box):
+    return (box[2]-box[0] + 1)*(box[3]-box[1] + 1)
+    
+def intersection_over_union(box_a, box_b):
+    # determine the (x, y)-coordinates of the intersection rectangle
+    intersect = intersection(box_a, box_b)
+
+    # compute the area of intersection rectangle
+    inter_area = max(0, intersect[2] - intersect[0] + 1) * max(0, intersect[3] - intersect[1] + 1)
+
+    if inter_area == 0:
+        return 0.0
+    
+    # compute the area of both the prediction and ground-truth
+    # rectangles
+    box_a_area = (box_a[2] - box_a[0] + 1) * (box_a[3] - box_a[1] + 1)
+    box_b_area = (box_b[2] - box_b[0] + 1) * (box_b[3] - box_b[1] + 1)
+
+    # compute the intersection over union by taking the intersection
+    # area and dividing it by the sum of prediction + ground-truth
+    # areas - the interesection area
+    iou = inter_area / float(box_a_area + box_b_area - inter_area)
+
+    # return the intersection over union value
+    return iou
+
+def clipped(obj, frame_shape):
+    # if the object is within 5 pixels of the region border, and the region is not on the edge
+    # consider the object to be clipped
+    box = obj[2]
+    region = obj[4]
+    if ((region[0] > 5 and box[0]-region[0] <= 5) or 
+        (region[1] > 5 and box[1]-region[1] <= 5) or
+        (frame_shape[1]-region[2] > 5 and region[2]-box[2] <= 5) or
+        (frame_shape[0]-region[3] > 5 and region[3]-box[3] <= 5)):
+        return True
+    else:
+        return False
+
+class EventsPerSecond:
+    def __init__(self, max_events=1000):
+        self._start = None
+        self._max_events = max_events
+        self._timestamps = []
+    
+    def start(self):
+        self._start = datetime.datetime.now().timestamp()
+
+    def update(self):
+        if self._start is None:
+            self.start()
+        self._timestamps.append(datetime.datetime.now().timestamp())
+        # truncate the list when it goes 100 over the max_size
+        if len(self._timestamps) > self._max_events+100:
+            self._timestamps = self._timestamps[(1-self._max_events):]
+
+    def eps(self, last_n_seconds=10):
+        if self._start is None:
+            self.start()
+		# compute the (approximate) events in the last n seconds
+        now = datetime.datetime.now().timestamp()
+        seconds = min(now-self._start, last_n_seconds)
+        return len([t for t in self._timestamps if t > (now-last_n_seconds)]) / seconds
+
+def print_stack(sig, frame):
+    traceback.print_stack(frame)
+
+def listen():
+    signal.signal(signal.SIGUSR1, print_stack)
+
+class FrameManager(ABC):
+    @abstractmethod
+    def create(self, name, size) -> AnyStr:
+        pass
+
+    @abstractmethod
+    def get(self, name, timeout_ms=0):
+        pass
+
+    @abstractmethod
+    def close(self, name):
+        pass
+
+    @abstractmethod
+    def delete(self, name):
+        pass
+
+class DictFrameManager(FrameManager):
+    def __init__(self):
+        self.frames = {}
+    
+    def create(self, name, size) -> AnyStr:
+        mem = bytearray(size)
+        self.frames[name] = mem
+        return mem
+    
+    def get(self, name, shape):
+        mem = self.frames[name]
+        return np.ndarray(shape, dtype=np.uint8, buffer=mem)
+    
+    def close(self, name):
+        pass
+    
+    def delete(self, name):
+        del self.frames[name]
+
+class SharedMemoryFrameManager(FrameManager):
+    def __init__(self):
+        self.shm_store = {}
+    
+    def create(self, name, size) -> AnyStr:
+        shm = shared_memory.SharedMemory(name=name, create=True, size=size)
+        self.shm_store[name] = shm
+        return shm.buf
+
+    def get(self, name, shape):
+        if name in self.shm_store:
+            shm = self.shm_store[name]
+        else:
+            shm = shared_memory.SharedMemory(name=name)
+            self.shm_store[name] = shm
+        return np.ndarray(shape, dtype=np.uint8, buffer=shm.buf)
+
+    def close(self, name):
+        if name in self.shm_store:
+            self.shm_store[name].close()
+            del self.shm_store[name]
+
+    def delete(self, name):
+        if name in self.shm_store:
+            self.shm_store[name].close()
+            self.shm_store[name].unlink()
+            del self.shm_store[name]

frigate/video.py

@@ -2,267 +2,428 @@ import os
 import time
 import datetime
 import cv2
+import queue
 import threading
 import ctypes
 import multiprocessing as mp
-from object_detection.utils import visualization_utils as vis_util
-from . util import tonumpyarray
-from . object_detection import FramePrepper
-from . objects import ObjectCleaner, BestPersonFrame
-from . mqtt import MqttObjectPublisher
+import subprocess as sp
+import numpy as np
+import copy
+import itertools
+import json
+import base64
+from typing import Dict, List
+from collections import defaultdict
+from frigate.util import draw_box_with_label, yuv_region_2_rgb, area, calculate_region, clipped, intersection_over_union, intersection, EventsPerSecond, listen, FrameManager, SharedMemoryFrameManager
+from frigate.objects import ObjectTracker
+from frigate.edgetpu import RemoteObjectDetector
+from frigate.motion import MotionDetector
 
-# fetch the frames as fast a possible and store current frame in a shared memory array
-def fetch_frames(shared_arr, shared_frame_time, frame_lock, frame_ready, frame_shape, rtsp_url):
-    # convert shared memory array into numpy and shape into image array
-    arr = tonumpyarray(shared_arr).reshape(frame_shape)
+def get_frame_shape(source):
+    ffprobe_cmd = " ".join([
+        'ffprobe',
+        '-v',
+        'panic',
+        '-show_error',
+        '-show_streams',
+        '-of',
+        'json',
+        '"'+source+'"'
+    ])
+    print(ffprobe_cmd)
+    p = sp.Popen(ffprobe_cmd, stdout=sp.PIPE, shell=True)
+    (output, err) = p.communicate()
+    p_status = p.wait()
+    info = json.loads(output)
+    print(info)
 
-    # start the video capture
-    video = cv2.VideoCapture()
-    video.open(rtsp_url)
-    # keep the buffer small so we minimize old data
-    video.set(cv2.CAP_PROP_BUFFERSIZE,1)
+    video_info = [s for s in info['streams'] if s['codec_type'] == 'video'][0]
 
-    bad_frame_counter = 0
-    while True:
-        # check if the video stream is still open, and reopen if needed
-        if not video.isOpened():
-            success = video.open(rtsp_url)
-            if not success:
-                time.sleep(1)
-                continue
-        # grab the frame, but dont decode it yet
-        ret = video.grab()
-        # snapshot the time the frame was grabbed
-        frame_time = datetime.datetime.now()
-        if ret:
-            # go ahead and decode the current frame
-            ret, frame = video.retrieve()
-            if ret:
-                # Lock access and update frame
-                with frame_lock:
-                    arr[:] = frame
-                    shared_frame_time.value = frame_time.timestamp()
-                # Notify with the condition that a new frame is ready
-                with frame_ready:
-                    frame_ready.notify_all()
-                bad_frame_counter = 0
-            else:
-                print("Unable to decode frame")
-                bad_frame_counter += 1
-        else:
-            print("Unable to grab a frame")
-            bad_frame_counter += 1
-        
-        if bad_frame_counter > 100:
-            video.release()
+    if video_info['height'] != 0 and video_info['width'] != 0:
+        return (video_info['height'], video_info['width'], 3)
     
-    video.release()
-
-# Stores 2 seconds worth of frames when motion is detected so they can be used for other threads
-class FrameTracker(threading.Thread):
-    def __init__(self, shared_frame, frame_time, frame_ready, frame_lock, recent_frames):
-        threading.Thread.__init__(self)
-        self.shared_frame = shared_frame
-        self.frame_time = frame_time
-        self.frame_ready = frame_ready
-        self.frame_lock = frame_lock
-        self.recent_frames = recent_frames
-
-    def run(self):
-        frame_time = 0.0
-        while True:
-            now = datetime.datetime.now().timestamp()
-            # wait for a frame
-            with self.frame_ready:
-                # if there isnt a frame ready for processing or it is old, wait for a signal
-                if self.frame_time.value == frame_time or (now - self.frame_time.value) > 0.5:
-                    self.frame_ready.wait()
-            
-            # lock and make a copy of the frame
-            with self.frame_lock: 
-                frame = self.shared_frame.copy()
-                frame_time = self.frame_time.value
-            
-            # add the frame to recent frames
-            self.recent_frames[frame_time] = frame
-
-            # delete any old frames
-            stored_frame_times = list(self.recent_frames.keys())
-            for k in stored_frame_times:
-                if (now - k) > 2:
-                    del self.recent_frames[k]
-
-def get_frame_shape(rtsp_url):
-    # capture a single frame and check the frame shape so the correct array
-    # size can be allocated in memory
-    video = cv2.VideoCapture(rtsp_url)
+    # fallback to using opencv if ffprobe didnt succeed
+    video = cv2.VideoCapture(source)
     ret, frame = video.read()
     frame_shape = frame.shape
     video.release()
     return frame_shape
 
-def get_rtsp_url(rtsp_config):
-    if (rtsp_config['password'].startswith('$')):
-        rtsp_config['password'] = os.getenv(rtsp_config['password'][1:])
-    return 'rtsp://{}:{}@{}:{}{}'.format(rtsp_config['user'], 
-        rtsp_config['password'], rtsp_config['host'], rtsp_config['port'],
-        rtsp_config['path'])
+def get_ffmpeg_input(ffmpeg_input):
+    frigate_vars = {k: v for k, v in os.environ.items() if k.startswith('FRIGATE_')}
+    return ffmpeg_input.format(**frigate_vars)
 
-class Camera:
-    def __init__(self, name, config, prepped_frame_queue, mqtt_client, mqtt_prefix):
+def filtered(obj, objects_to_track, object_filters, mask=None):
+    object_name = obj[0]
+
+    if not object_name in objects_to_track:
+        return True
+    
+    if object_name in object_filters:
+        obj_settings = object_filters[object_name]
+
+        # if the min area is larger than the
+        # detected object, don't add it to detected objects
+        if obj_settings.get('min_area',-1) > obj[3]:
+            return True
+        
+        # if the detected object is larger than the
+        # max area, don't add it to detected objects
+        if obj_settings.get('max_area', 24000000) < obj[3]:
+            return True
+
+        # if the score is lower than the min_score, skip
+        if obj_settings.get('min_score', 0) > obj[1]:
+            return True
+    
+        # compute the coordinates of the object and make sure
+        # the location isnt outside the bounds of the image (can happen from rounding)
+        y_location = min(int(obj[2][3]), len(mask)-1)
+        x_location = min(int((obj[2][2]-obj[2][0])/2.0)+obj[2][0], len(mask[0])-1)
+
+        # if the object is in a masked location, don't add it to detected objects
+        if (not mask is None) and (mask[y_location][x_location] == 0):
+            return True
+        
+    return False
+
+def create_tensor_input(frame, region):
+    cropped_frame = yuv_region_2_rgb(frame, region)
+
+    # Resize to 300x300 if needed
+    if cropped_frame.shape != (300, 300, 3):
+        cropped_frame = cv2.resize(cropped_frame, dsize=(300, 300), interpolation=cv2.INTER_LINEAR)
+    
+    # Expand dimensions since the model expects images to have shape: [1, 300, 300, 3]
+    return np.expand_dims(cropped_frame, axis=0)
+
+def start_or_restart_ffmpeg(ffmpeg_cmd, frame_size, ffmpeg_process=None):
+    if not ffmpeg_process is None:
+        print("Terminating the existing ffmpeg process...")
+        ffmpeg_process.terminate()
+        try:
+            print("Waiting for ffmpeg to exit gracefully...")
+            ffmpeg_process.communicate(timeout=30)
+        except sp.TimeoutExpired:
+            print("FFmpeg didnt exit. Force killing...")
+            ffmpeg_process.kill()
+            ffmpeg_process.communicate()
+        ffmpeg_process = None
+
+    print("Creating ffmpeg process...")
+    print(" ".join(ffmpeg_cmd))
+    process = sp.Popen(ffmpeg_cmd, stdout = sp.PIPE, stdin = sp.DEVNULL, bufsize=frame_size*10, start_new_session=True)
+    return process
+
+def capture_frames(ffmpeg_process, camera_name, frame_shape, frame_manager: FrameManager, 
+    frame_queue, take_frame: int, fps:mp.Value, skipped_fps: mp.Value, 
+    stop_event: mp.Event, current_frame: mp.Value):
+
+    frame_num = 0
+    frame_size = frame_shape[0] * frame_shape[1] * 3 // 2
+    frame_rate = EventsPerSecond()
+    frame_rate.start()
+    skipped_eps = EventsPerSecond()
+    skipped_eps.start()
+    while True:
+        fps.value = frame_rate.eps()
+        skipped_fps = skipped_eps.eps()
+        if stop_event.is_set():
+            print(f"{camera_name}: stop event set. exiting capture thread...")
+            break
+
+        current_frame.value = datetime.datetime.now().timestamp()
+        frame_name = f"{camera_name}{current_frame.value}"
+        frame_buffer = frame_manager.create(frame_name, frame_size)
+        try:
+          frame_buffer[:] = ffmpeg_process.stdout.read(frame_size)
+        except:
+          print(f"{camera_name}: ffmpeg sent a broken frame. something is wrong.")
+
+          if ffmpeg_process.poll() != None:
+              print(f"{camera_name}: ffmpeg process is not running. exiting capture thread...")
+              frame_manager.delete(frame_name)
+              break
+          
+          continue
+
+        frame_rate.update()
+
+        frame_num += 1
+        if (frame_num % take_frame) != 0:
+            skipped_eps.update()
+            frame_manager.delete(frame_name)
+            continue
+
+        # if the queue is full, skip this frame
+        if frame_queue.full():
+            skipped_eps.update()
+            frame_manager.delete(frame_name)
+            continue
+
+        # close the frame
+        frame_manager.close(frame_name)
+
+        # add to the queue
+        frame_queue.put(current_frame.value)
+
+class CameraWatchdog(threading.Thread):
+    def __init__(self, name, config, frame_queue, camera_fps, ffmpeg_pid, stop_event):
+        threading.Thread.__init__(self)
         self.name = name
         self.config = config
-        self.detected_objects = []
-        self.recent_frames = {}
-        self.rtsp_url = get_rtsp_url(self.config['rtsp'])
-        self.regions = self.config['regions']
-        self.frame_shape = get_frame_shape(self.rtsp_url)
-        self.mqtt_client = mqtt_client
-        self.mqtt_topic_prefix = '{}/{}'.format(mqtt_prefix, self.name)
+        self.capture_thread = None
+        self.ffmpeg_process = None
+        self.stop_event = stop_event
+        self.camera_fps = camera_fps
+        self.ffmpeg_pid = ffmpeg_pid
+        self.frame_queue = frame_queue
+        self.frame_shape = self.config['frame_shape']
+        self.frame_size = self.frame_shape[0] * self.frame_shape[1] * 3 // 2
 
-        # compute the flattened array length from the shape of the frame
-        flat_array_length = self.frame_shape[0] * self.frame_shape[1] * self.frame_shape[2]
-        # create shared array for storing the full frame image data
-        self.shared_frame_array = mp.Array(ctypes.c_uint8, flat_array_length)
-        # create shared value for storing the frame_time
-        self.shared_frame_time = mp.Value('d', 0.0)
-        # Lock to control access to the frame
-        self.frame_lock = mp.Lock()
-        # Condition for notifying that a new frame is ready
-        self.frame_ready = mp.Condition()
-        # Condition for notifying that objects were parsed
-        self.objects_parsed = mp.Condition()
+    def run(self):
+        self.start_ffmpeg()
+        time.sleep(10)
+        while True:
+            if self.stop_event.is_set():
+                print(f"Exiting watchdog...")
+                break
 
-        # shape current frame so it can be treated as a numpy image
-        self.shared_frame_np = tonumpyarray(self.shared_frame_array).reshape(self.frame_shape)
+            now = datetime.datetime.now().timestamp()
 
-        # create the process to capture frames from the RTSP stream and store in a shared array
-        self.capture_process = mp.Process(target=fetch_frames, args=(self.shared_frame_array, 
-            self.shared_frame_time, self.frame_lock, self.frame_ready, self.frame_shape, self.rtsp_url))
-        self.capture_process.daemon = True
-
-        # for each region, create a separate thread to resize the region and prep for detection
-        self.detection_prep_threads = []
-        for region in self.config['regions']:
-            self.detection_prep_threads.append(FramePrepper(
-                self.name,
-                self.shared_frame_np,
-                self.shared_frame_time,
-                self.frame_ready,
-                self.frame_lock,
-                region['size'], region['x_offset'], region['y_offset'],
-                prepped_frame_queue
-            ))
-        
-        # start a thread to store recent motion frames for processing
-        self.frame_tracker = FrameTracker(self.shared_frame_np, self.shared_frame_time, 
-            self.frame_ready, self.frame_lock, self.recent_frames)
-        self.frame_tracker.start()
-
-        # start a thread to store the highest scoring recent person frame
-        self.best_person_frame = BestPersonFrame(self.objects_parsed, self.recent_frames, self.detected_objects)
-        self.best_person_frame.start()
-
-        # start a thread to expire objects from the detected objects list
-        self.object_cleaner = ObjectCleaner(self.objects_parsed, self.detected_objects)
-        self.object_cleaner.start()
-
-        # start a thread to publish object scores (currently only person)
-        mqtt_publisher = MqttObjectPublisher(self.mqtt_client, self.mqtt_topic_prefix, self.objects_parsed, self.detected_objects)
-        mqtt_publisher.start()
-
-        # load in the mask for person detection
-        if 'mask' in self.config:
-            self.mask = cv2.imread("/config/{}".format(self.config['mask']), cv2.IMREAD_GRAYSCALE)
-        else:
-            self.mask = np.zeros((self.frame_shape[0], self.frame_shape[1], 1), np.uint8)
-            self.mask[:] = 255
-    
-    def start(self):
-        self.capture_process.start()
-        # start the object detection prep threads
-        for detection_prep_thread in self.detection_prep_threads:
-            detection_prep_thread.start()
-    
-    def join(self):
-        self.capture_process.join()
-    
-    def get_capture_pid(self):
-        return self.capture_process.pid
-    
-    def add_objects(self, objects):
-        if len(objects) == 0:
-            return
-
-        for obj in objects:
-            if obj['name'] == 'person':
-                person_area = (obj['xmax']-obj['xmin'])*(obj['ymax']-obj['ymin'])
-                # find the matching region
-                region = None
-                for r in self.regions:
-                    if (
-                            obj['xmin'] >= r['x_offset'] and
-                            obj['ymin'] >= r['y_offset'] and
-                            obj['xmax'] <= r['x_offset']+r['size'] and
-                            obj['ymax'] <= r['y_offset']+r['size']
-                        ): 
-                        region = r
-                        break
-                
-                # if the min person area is larger than the
-                # detected person, don't add it to detected objects
-                if region and region['min_person_area'] > person_area:
-                    continue
+            if not self.capture_thread.is_alive():
+                self.start_ffmpeg()
+            elif now - self.capture_thread.current_frame.value > 5:
+                print(f"No frames received from {self.name} in 5 seconds. Exiting ffmpeg...")
+                self.ffmpeg_process.terminate()
+                try:
+                    print("Waiting for ffmpeg to exit gracefully...")
+                    self.ffmpeg_process.communicate(timeout=30)
+                except sp.TimeoutExpired:
+                    print("FFmpeg didnt exit. Force killing...")
+                    self.ffmpeg_process.kill()
+                    self.ffmpeg_process.communicate()
             
-                # compute the coordinates of the person and make sure
-                # the location isnt outide the bounds of the image (can happen from rounding)
-                y_location = min(int(obj['ymax']), len(self.mask)-1)
-                x_location = min(int((obj['xmax']-obj['xmin'])/2.0), len(self.mask[0])-1)
-
-                # if the person is in a masked location, continue
-                if self.mask[y_location][x_location] == [0]:
-                    continue
-
-            self.detected_objects.append(obj)
-
-        with self.objects_parsed:
-            self.objects_parsed.notify_all()
-
-    def get_best_person(self):
-        return self.best_person_frame.best_frame
+            # wait a bit before checking again
+            time.sleep(10)
     
-    def get_current_frame_with_objects(self):
-        # make a copy of the current detected objects
-        detected_objects = self.detected_objects.copy()
-        # lock and make a copy of the current frame
-        with self.frame_lock:
-            frame = self.shared_frame_np.copy()
+    def start_ffmpeg(self):
+      self.ffmpeg_process = start_or_restart_ffmpeg(self.config['ffmpeg_cmd'], self.frame_size)
+      self.ffmpeg_pid.value = self.ffmpeg_process.pid
+      self.capture_thread = CameraCapture(self.name, self.ffmpeg_process, self.frame_shape, self.frame_queue, 
+          self.config['take_frame'], self.camera_fps, self.stop_event)
+      self.capture_thread.start()
 
-        # convert to RGB for drawing
-        frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-        # draw the bounding boxes on the screen
-        for obj in detected_objects:
-            vis_util.draw_bounding_box_on_image_array(frame,
-                obj['ymin'],
-                obj['xmin'],
-                obj['ymax'],
-                obj['xmax'],
-                color='red',
-                thickness=2,
-                display_str_list=["{}: {}%".format(obj['name'],int(obj['score']*100))],
-                use_normalized_coordinates=False)
+class CameraCapture(threading.Thread):
+    def __init__(self, name, ffmpeg_process, frame_shape, frame_queue, take_frame, fps, stop_event):
+        threading.Thread.__init__(self)
+        self.name = name
+        self.frame_shape = frame_shape
+        self.frame_size = frame_shape[0] * frame_shape[1] * frame_shape[2]
+        self.frame_queue = frame_queue
+        self.take_frame = take_frame
+        self.fps = fps
+        self.skipped_fps = EventsPerSecond()
+        self.frame_manager = SharedMemoryFrameManager()
+        self.ffmpeg_process = ffmpeg_process
+        self.current_frame = mp.Value('d', 0.0)
+        self.last_frame = 0
+        self.stop_event = stop_event
 
-        for region in self.regions:
-            color = (255,255,255)
-            cv2.rectangle(frame, (region['x_offset'], region['y_offset']), 
-                (region['x_offset']+region['size'], region['y_offset']+region['size']), 
-                color, 2)
+    def run(self):
+        self.skipped_fps.start()
+        capture_frames(self.ffmpeg_process, self.name, self.frame_shape, self.frame_manager, self.frame_queue, self.take_frame,
+            self.fps, self.skipped_fps, self.stop_event, self.current_frame)
 
-        # convert back to BGR
-        frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)
+def capture_camera(name, config, process_info, stop_event):
+    frame_queue = process_info['frame_queue']
+    camera_watchdog = CameraWatchdog(name, config, frame_queue, process_info['camera_fps'], process_info['ffmpeg_pid'], stop_event)
+    camera_watchdog.start()
+    camera_watchdog.join()
 
-        return frame
+def track_camera(name, config, detection_queue, result_connection, detected_objects_queue, process_info, stop_event):
+    listen()
 
+    frame_queue = process_info['frame_queue']
 
+    frame_shape = config['frame_shape']
+
+    # Merge the tracked object config with the global config
+    camera_objects_config = config.get('objects', {})
+    objects_to_track = camera_objects_config.get('track', [])
+    object_filters = camera_objects_config.get('filters', {})
+
+    # load in the mask for object detection
+    if 'mask' in config:
+        if config['mask'].startswith('base64,'):
+            img = base64.b64decode(config['mask'][7:]) 
+            npimg = np.fromstring(img, dtype=np.uint8)
+            mask = cv2.imdecode(npimg, cv2.IMREAD_GRAYSCALE)
+        elif config['mask'].startswith('poly,'):
+            points = config['mask'].split(',')[1:]
+            contour =  np.array([[int(points[i]), int(points[i+1])] for i in range(0, len(points), 2)])
+            mask = np.zeros((frame_shape[0], frame_shape[1]), np.uint8)
+            mask[:] = 255
+            cv2.fillPoly(mask, pts=[contour], color=(0))
+        else:
+            mask = cv2.imread("/config/{}".format(config['mask']), cv2.IMREAD_GRAYSCALE)
+    else:
+        mask = None
+
+    if mask is None or mask.size == 0:
+        mask = np.zeros((frame_shape[0], frame_shape[1]), np.uint8)
+        mask[:] = 255
+
+    motion_detector = MotionDetector(frame_shape, mask, resize_factor=6)
+    object_detector = RemoteObjectDetector(name, '/labelmap.txt', detection_queue, result_connection)
+
+    object_tracker = ObjectTracker(10)
+
+    frame_manager = SharedMemoryFrameManager()
+
+    process_frames(name, frame_queue, frame_shape, frame_manager, motion_detector, object_detector,
+        object_tracker, detected_objects_queue, process_info, objects_to_track, object_filters, mask, stop_event)
+
+    print(f"{name}: exiting subprocess")
+
+def reduce_boxes(boxes):
+    if len(boxes) == 0:
+        return []
+    reduced_boxes = cv2.groupRectangles([list(b) for b in itertools.chain(boxes, boxes)], 1, 0.2)[0]
+    return [tuple(b) for b in reduced_boxes]
+
+def detect(object_detector, frame, region, objects_to_track, object_filters, mask):
+    tensor_input = create_tensor_input(frame, region)
+
+    detections = []
+    region_detections = object_detector.detect(tensor_input)
+    for d in region_detections:
+        box = d[2]
+        size = region[2]-region[0]
+        x_min = int((box[1] * size) + region[0])
+        y_min = int((box[0] * size) + region[1])
+        x_max = int((box[3] * size) + region[0])
+        y_max = int((box[2] * size) + region[1])
+        det = (d[0],
+            d[1],
+            (x_min, y_min, x_max, y_max),
+            (x_max-x_min)*(y_max-y_min),
+            region)
+        # apply object filters
+        if filtered(det, objects_to_track, object_filters, mask):
+            continue
+        detections.append(det)
+    return detections
+
+def process_frames(camera_name: str, frame_queue: mp.Queue, frame_shape, 
+    frame_manager: FrameManager, motion_detector: MotionDetector, 
+    object_detector: RemoteObjectDetector, object_tracker: ObjectTracker,
+    detected_objects_queue: mp.Queue, process_info: Dict,
+    objects_to_track: List[str], object_filters: Dict, mask, stop_event: mp.Event,
+    exit_on_empty: bool = False):
     
-        
+    fps = process_info['process_fps']
+    detection_fps = process_info['detection_fps']
+    current_frame_time = process_info['detection_frame']
+
+    fps_tracker = EventsPerSecond()
+    fps_tracker.start()
+
+    while True:
+        if stop_event.is_set() or (exit_on_empty and frame_queue.empty()):
+                print(f"Exiting track_objects...")
+                break
+
+        try:
+            frame_time = frame_queue.get(True, 10)
+        except queue.Empty:
+            continue
+
+        current_frame_time.value = frame_time
+
+        frame = frame_manager.get(f"{camera_name}{frame_time}", (frame_shape[0]*3//2, frame_shape[1]))
+
+        if frame is None:
+            print(f"{camera_name}: frame {frame_time} is not in memory store.")
+            continue
+
+        # look for motion
+        motion_boxes = motion_detector.detect(frame)
+
+        tracked_object_boxes = [obj['box'] for obj in object_tracker.tracked_objects.values()]
+
+        # combine motion boxes with known locations of existing objects
+        combined_boxes = reduce_boxes(motion_boxes + tracked_object_boxes)
+
+        # compute regions
+        regions = [calculate_region(frame_shape, a[0], a[1], a[2], a[3], 1.2)
+            for a in combined_boxes]
+
+        # combine overlapping regions
+        combined_regions = reduce_boxes(regions)
+
+        # re-compute regions
+        regions = [calculate_region(frame_shape, a[0], a[1], a[2], a[3], 1.0)
+            for a in combined_regions]
+
+        # resize regions and detect
+        detections = []
+        for region in regions:
+            detections.extend(detect(object_detector, frame, region, objects_to_track, object_filters, mask))
+        
+        #########
+        # merge objects, check for clipped objects and look again up to 4 times
+        #########
+        refining = True
+        refine_count = 0
+        while refining and refine_count < 4:
+            refining = False
+
+            # group by name
+            detected_object_groups = defaultdict(lambda: [])
+            for detection in detections:
+                detected_object_groups[detection[0]].append(detection)
+
+            selected_objects = []
+            for group in detected_object_groups.values():
+
+                # apply non-maxima suppression to suppress weak, overlapping bounding boxes
+                boxes = [(o[2][0], o[2][1], o[2][2]-o[2][0], o[2][3]-o[2][1])
+                    for o in group]
+                confidences = [o[1] for o in group]
+                idxs = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)
+
+                for index in idxs:
+                    obj = group[index[0]]
+                    if clipped(obj, frame_shape):
+                        box = obj[2]
+                        # calculate a new region that will hopefully get the entire object
+                        region = calculate_region(frame_shape, 
+                            box[0], box[1],
+                            box[2], box[3])
+                        
+                        selected_objects.extend(detect(object_detector, frame, region, objects_to_track, object_filters, mask))
+
+                        refining = True
+                    else:
+                        selected_objects.append(obj)            
+            # set the detections list to only include top, complete objects
+            # and new detections
+            detections = selected_objects
+
+            if refining:
+                refine_count += 1
+
+        # now that we have refined our detections, we need to track objects
+        object_tracker.match_and_update(frame_time, detections)
+
+        # add to the queue if not full
+        if(detected_objects_queue.full()):
+          frame_manager.delete(f"{camera_name}{frame_time}")
+          continue
+        else:
+          fps_tracker.update()
+          fps.value = fps_tracker.eps()
+          detected_objects_queue.put((camera_name, frame_time, object_tracker.tracked_objects))
+          detection_fps.value = object_detector.fps.eps()
+          frame_manager.close(f"{camera_name}{frame_time}")

labelmap.txt

@@ -0,0 +1,80 @@
+0  person
+1  bicycle
+2  car
+3  motorcycle
+4  airplane
+5  bus
+6  train
+7  car
+8  boat
+9  traffic light
+10  fire hydrant
+12  stop sign
+13  parking meter
+14  bench
+15  bird
+16  cat
+17  dog
+18  horse
+19  sheep
+20  cow
+21  elephant
+22  bear
+23  zebra
+24  giraffe
+26  backpack
+27  umbrella
+30  handbag
+31  tie
+32  suitcase
+33  frisbee
+34  skis
+35  snowboard
+36  sports ball
+37  kite
+38  baseball bat
+39  baseball glove
+40  skateboard
+41  surfboard
+42  tennis racket
+43  bottle
+45  wine glass
+46  cup
+47  fork
+48  knife
+49  spoon
+50  bowl
+51  banana
+52  apple
+53  sandwich
+54  orange
+55  broccoli
+56  carrot
+57  hot dog
+58  pizza
+59  donut
+60  cake
+61  chair
+62  couch
+63  potted plant
+64  bed
+66  dining table
+69  toilet
+71  tv
+72  laptop
+73  mouse
+74  remote
+75  keyboard
+76  cell phone
+77  microwave
+78  oven
+79  toaster
+80  sink
+81  refrigerator
+83  book
+84  clock
+85  vase
+86  scissors
+87  teddy bear
+88  hair drier
+89  toothbrush

process_clip.py

@@ -0,0 +1,152 @@
+import sys
+import click
+import os
+import datetime
+from unittest import TestCase, main
+from frigate.video import process_frames, start_or_restart_ffmpeg, capture_frames, get_frame_shape
+from frigate.util import DictFrameManager, SharedMemoryFrameManager, EventsPerSecond, draw_box_with_label
+from frigate.motion import MotionDetector
+from frigate.edgetpu import LocalObjectDetector
+from frigate.objects import ObjectTracker
+import multiprocessing as mp
+import numpy as np
+import cv2
+from frigate.object_processing import COLOR_MAP, CameraState
+
+class ProcessClip():
+    def __init__(self, clip_path, frame_shape, config):
+        self.clip_path = clip_path
+        self.frame_shape = frame_shape
+        self.camera_name = 'camera'
+        self.frame_manager = DictFrameManager()
+        # self.frame_manager = SharedMemoryFrameManager()
+        self.frame_queue = mp.Queue()
+        self.detected_objects_queue = mp.Queue()
+        self.camera_state = CameraState(self.camera_name, config, self.frame_manager)
+
+    def load_frames(self):
+        fps = EventsPerSecond()
+        skipped_fps = EventsPerSecond()
+        stop_event = mp.Event()
+        detection_frame = mp.Value('d', datetime.datetime.now().timestamp()+100000)
+        current_frame = mp.Value('d', 0.0)
+        ffmpeg_cmd = f"ffmpeg -hide_banner -loglevel panic -i {self.clip_path} -f rawvideo -pix_fmt rgb24 pipe:".split(" ")
+        ffmpeg_process = start_or_restart_ffmpeg(ffmpeg_cmd, self.frame_shape[0]*self.frame_shape[1]*self.frame_shape[2])
+        capture_frames(ffmpeg_process, self.camera_name, self.frame_shape, self.frame_manager, self.frame_queue, 1, fps, skipped_fps, stop_event, detection_frame, current_frame)
+        ffmpeg_process.wait()
+        ffmpeg_process.communicate()
+    
+    def process_frames(self, objects_to_track=['person'], object_filters={}):
+        mask = np.zeros((self.frame_shape[0], self.frame_shape[1], 1), np.uint8)
+        mask[:] = 255
+        motion_detector = MotionDetector(self.frame_shape, mask)
+
+        object_detector = LocalObjectDetector(labels='/labelmap.txt')
+        object_tracker = ObjectTracker(10)
+        process_fps = mp.Value('d', 0.0)
+        detection_fps = mp.Value('d', 0.0)
+        current_frame = mp.Value('d', 0.0)
+        stop_event = mp.Event()
+
+        process_frames(self.camera_name, self.frame_queue, self.frame_shape, self.frame_manager, motion_detector, object_detector, object_tracker, self.detected_objects_queue, 
+            process_fps, detection_fps, current_frame, objects_to_track, object_filters, mask, stop_event, exit_on_empty=True)
+    
+    def objects_found(self, debug_path=None):
+        obj_detected = False
+        top_computed_score = 0.0
+        def handle_event(name, obj):
+            nonlocal obj_detected
+            nonlocal top_computed_score
+            if obj['computed_score'] > top_computed_score:
+                top_computed_score = obj['computed_score']
+            if not obj['false_positive']:
+                obj_detected = True
+        self.camera_state.on('new', handle_event)
+        self.camera_state.on('update', handle_event)
+
+        while(not self.detected_objects_queue.empty()):
+            camera_name, frame_time, current_tracked_objects = self.detected_objects_queue.get()
+            if not debug_path is None:
+                self.save_debug_frame(debug_path, frame_time, current_tracked_objects.values())
+
+            self.camera_state.update(frame_time, current_tracked_objects)
+            for obj in self.camera_state.tracked_objects.values():
+                print(f"{frame_time}: {obj['id']} - {obj['computed_score']} - {obj['score_history']}")
+        
+        self.frame_manager.delete(self.camera_state.previous_frame_id)
+        
+        return {
+            'object_detected': obj_detected,
+            'top_score': top_computed_score
+        }
+    
+    def save_debug_frame(self, debug_path, frame_time, tracked_objects):
+        current_frame = self.frame_manager.get(f"{self.camera_name}{frame_time}", self.frame_shape)
+        # draw the bounding boxes on the frame
+        for obj in tracked_objects:
+            thickness = 2
+            color = (0,0,175)
+
+            if obj['frame_time'] != frame_time:
+                thickness = 1
+                color = (255,0,0)
+            else:
+                color = (255,255,0)
+
+            # draw the bounding boxes on the frame
+            box = obj['box']
+            draw_box_with_label(current_frame, box[0], box[1], box[2], box[3], obj['label'], f"{int(obj['score']*100)}% {int(obj['area'])}", thickness=thickness, color=color)
+            # draw the regions on the frame
+            region = obj['region']
+            draw_box_with_label(current_frame, region[0], region[1], region[2], region[3], 'region', "", thickness=1, color=(0,255,0))
+        
+        cv2.imwrite(f"{os.path.join(debug_path, os.path.basename(self.clip_path))}.{int(frame_time*1000000)}.jpg", cv2.cvtColor(current_frame, cv2.COLOR_RGB2BGR))
+
+@click.command()
+@click.option("-p", "--path", required=True, help="Path to clip or directory to test.")
+@click.option("-l", "--label", default='person', help="Label name to detect.")
+@click.option("-t", "--threshold", default=0.85, help="Threshold value for objects.")
+@click.option("--debug-path", default=None, help="Path to output frames for debugging.")
+def process(path, label, threshold, debug_path):
+    clips = []
+    if os.path.isdir(path):
+        files = os.listdir(path)
+        files.sort()
+        clips = [os.path.join(path, file) for file in files]
+    elif os.path.isfile(path):  
+        clips.append(path)
+
+    config = {
+        'snapshots': {
+            'show_timestamp': False, 
+            'draw_zones': False
+        },
+        'zones': {},
+        'objects': {
+            'track': [label],
+            'filters': {
+                'person': {
+                    'threshold': threshold
+                }
+            }
+        }
+    }
+
+    results = []
+    for c in clips:
+        frame_shape = get_frame_shape(c)
+        config['frame_shape'] = frame_shape
+        process_clip = ProcessClip(c, frame_shape, config)
+        process_clip.load_frames()
+        process_clip.process_frames(objects_to_track=config['objects']['track'])
+
+        results.append((c, process_clip.objects_found(debug_path)))
+
+    for result in results:
+        print(f"{result[0]}: {result[1]}")
+    
+    positive_count = sum(1 for result in results if result[1]['object_detected'])
+    print(f"Objects were detected in {positive_count}/{len(results)}({positive_count/len(results)*100:.2f}%) clip(s).")
+
+if __name__ == '__main__':
+    process()