Nicolas Mowen 19afb035ff Rewrite restream (#5106)
* Tear out restream config

* Rework birdseye restream

* Create go2rtc config handler

* Fix bug

* Write start script

* Rework style

* Fix python run syntax

* Output as json instead of yaml

* Put old live config back and fix birdseye references

* Fix camera webUI

* Add frigate env var subsitutions

* Fix webui checks

* Check keys

* Remove unused prest

* Fix tests

* Update restream docs

* Update restream docs

* Update live docs

* Update camera specific recommendation

* Update more docs

* add links for the docs

Co-authored-by: Felipe Santos <felipecassiors@gmail.com>

* Update note about supported audio codecs

* Move restream to go2rtc

* Docs fixes

* Add verification of stream name

* Ensure that webUI uses camera name

* Update docs to reflect new live stream name

* Fix check

* Formatting

* Remove audio from detect

Co-authored-by: Felipe Santos <felipecassiors@gmail.com>

* Fix docs

* Don't handle env variable substitution

* Add go2rtc version

* Clarify docs

Co-authored-by: Felipe Santos <felipecassiors@gmail.com>
2023-01-16 17:50:35 -06:00
2023-01-16 17:50:35 -06:00
2023-01-16 17:50:35 -06:00
2023-01-16 17:50:35 -06:00
2023-01-16 17:50:35 -06:00
2021-02-25 07:01:59 -06:00
2023-01-06 07:03:16 -06:00
2020-07-26 12:07:47 -05:00
2022-12-30 10:53:17 -06:00
2023-01-13 07:20:25 -06:00
2022-12-30 16:43:32 -06:00

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 RTSP to reduce the number of connections to your camera
  • WebRTC & MSE support for low-latency live view

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

Description
NVR with realtime local object detection for IP cameras
Readme 236 MiB
Languages
TypeScript 49.6%
Python 46.3%
CSS 1.1%
C++ 0.8%
Shell 0.7%
Other 1.3%