Mirrors/blakeblackshear.frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2024-11-21 19:07:46 +01:00
Code Issues Projects Releases Wiki Activity
NVR with realtime local object detection for IP cameras
1,382 Commits 60 Branches 126 Tags 151 MiB
Python 47.8%
TypeScript 47.5%
CSS 1.4%
C++ 1.1%
Dockerfile 0.7%
Other 1.5%
4383b883c0
Go to file
Nate Meyer 4383b883c0
Refactor to simplify support for additional detector types (#3656) 
* Refactor EdgeTPU and CPU model handling to detector submodules.

* Fix selecting the correct detection device type from the config

* Remove detector type check when creating ObjectDetectProcess

* Fixes after rebasing to 0.11

* Add init file to detector folder

* Rename to detect_api

Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>

* Add unit test for LocalObjectDetector class

* Add configuration for model inputs
Support transforming detection regions to RGB or BGR.
Support specifying the input tensor shape.  The tensor shape has a standard format ["BHWC"] when handed to the detector, but can be transformed in the detector to match the model shape using the model  input_tensor config.

* Add documentation for new model config parameters

* Add input tensor transpose to LocalObjectDetector

* Change the model input tensor config to use an enumeration

* Updates for model config documentation

Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
2022-11-03 21:23:09 -05:00
.devcontainer include prettier in extensions 2022-04-10 09:11:16 -05:00
.github Merge remote-tracking branch 'origin/master' into release-0.11.0 2022-09-22 18:42:20 -05:00
docker Add go2rtc and add restream role / live source (#4082) 2022-11-02 06:36:09 -05:00
docs Refactor to simplify support for additional detector types (#3656) 2022-11-03 21:23:09 -05:00
frigate Refactor to simplify support for additional detector types (#3656) 2022-11-03 21:23:09 -05:00
migrations Limit recording retention to available storage (#3942) 2022-10-09 06:28:26 -05:00
web Bump vite from 2.8.6 to 2.9.13 in /web (#3885) 2022-11-02 06:51:31 -05:00
.dockerignore swr events refactor 2022-03-11 07:49:06 -06:00
.gitignore feat: Timeline UI (#2830) 2022-02-27 08:04:12 -06:00
.pylintrc use fstr log style 2021-02-25 07:01:59 -06:00
benchmark.py Refactor to simplify support for additional detector types (#3656) 2022-11-03 21:23:09 -05:00
docker-compose.yml Add go2rtc and add restream role / live source (#4082) 2022-11-02 06:36:09 -05:00
labelmap.txt refactor and reduce false positives 2020-09-17 07:37:27 -05:00
LICENSE switch to MIT license 2020-07-26 12:07:47 -05:00
Makefile increment version 2022-10-08 19:32:45 -05:00
process_clip.py Refactor to simplify support for additional detector types (#3656) 2022-11-03 21:23:09 -05:00
README.md update docs url 2021-09-26 16:43:26 -05:00
requirements-dev.txt Use requirement file for pip installs (#3090) 2022-04-12 07:21:21 -05:00
requirements-wheels.txt switch back to upgraded numpy 2022-07-04 16:51:48 -05:00
requirements.txt Use requirement file for pip installs (#3090) 2022-04-12 07:21:21 -05:00
test.db-journal Add go2rtc and add restream role / live source (#4082) 2022-11-02 06:36:09 -05:00

README.md

logo

Frigate - NVR With Realtime Object Detection for IP Cameras

A complete and local NVR designed for Home Assistant with AI object detection. Uses OpenCV and Tensorflow to perform realtime object detection locally for IP cameras.

Use of a Google Coral Accelerator is optional, but highly recommended. The Coral will outperform even the best CPUs and can process 100+ FPS with very little overhead.

  • Tight integration with Home Assistant via a custom component
  • 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
  • Records video with retention settings based on detected objects
  • 24/7 recording
  • Re-streaming via RTMP to reduce the number of connections to your camera

Documentation

View the documentation at https://docs.frigate.video

Donations

If you would like to make a donation to support development, please use Github Sponsors.

Screenshots

Integration into Home Assistant

Also comes with a builtin UI:

Events