Inicio Explorar Axuda
Iniciar sesión
rootless
/
frigate
1
0
Fork 0
Ficheiros Incidencias 0 Pull Requests 0 Wiki

Sen descrición

Árbore: 75a01f657e
Ramas Etiquetas
frigate
ZIP TAR.GZ
Paul Armstrong 75a01f657e feat(web): make it possible to add to object masks %!s(int64=4) %!d(string=hai) anos
.github 6790467bbc docs: move docs to docusaurus %!s(int64=4) %!d(string=hai) anos
docker 144aff9b4e pin numpy %!s(int64=4) %!d(string=hai) anos
docs 15b5ffddd4 updating for docusaurus2 docs %!s(int64=4) %!d(string=hai) anos
frigate 630c2ee6f6 use sqlitequeuedb %!s(int64=4) %!d(string=hai) anos
migrations c770470b58 add database migrations %!s(int64=4) %!d(string=hai) anos
nginx 507ec13848 first pass at subfilter for ingress support %!s(int64=4) %!d(string=hai) anos
web 75a01f657e feat(web): make it possible to add to object masks %!s(int64=4) %!d(string=hai) anos
.dockerignore e8009c2d26 adding version endpoint %!s(int64=4) %!d(string=hai) anos
.gitignore c618867941 feat!: web user interface %!s(int64=4) %!d(string=hai) anos
LICENSE 53ccc903da switch to MIT license %!s(int64=4) %!d(string=hai) anos
Makefile ea53068432 update wheels version %!s(int64=4) %!d(string=hai) anos
README.md 27b659dde1 tweaking the docs %!s(int64=4) %!d(string=hai) anos
benchmark.py f946813ccb support multiple coral devices (fixes #100) %!s(int64=4) %!d(string=hai) anos
labelmap.txt acb75fa02d refactor and reduce false positives %!s(int64=4) %!d(string=hai) anos
run.sh 7aecf6c6de fix graceful exits %!s(int64=4) %!d(string=hai) anos

README.md

logo

Frigate - NVR With Realtime Object Detection for IP Cameras

A complete and local NVR designed for HomeAssistant 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 HomeAssistant 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 clips of detected objects
  • 24/7 recording
  • Re-streaming via RTMP to reduce the number of connections to your camera

Documentation

View the documentation at https://blakeblackshear.github.io/frigate

Screenshots

Integration into HomeAssistant

Also comes with a builtin UI:

Events