NVR with realtime local object detection for IP cameras
Go to file
Nicolas Mowen 53315342c0
Improve object classification (#18908)
* Ui improvements

* Improve image cropping and model saving

* Improve naming

* Add logs for training

* Improve model labeling

* Don't set sub label for none object classification

* Cleanup
2025-06-27 06:28:40 -06:00
.cspell Fixes (#18304) 2025-05-19 14:43:22 -06:00
.devcontainer
.github cleanup variants (#18010) 2025-05-03 06:24:30 -06:00
.vscode
config
docker Improve logging (#18867) 2025-06-25 07:24:45 -06:00
docs feat: enable using GenAI for cameras with GenAI disabled from the API (#18616) 2025-06-07 13:43:29 -05:00
frigate Improve object classification (#18908) 2025-06-27 06:28:40 -06:00
migrations
notebooks Update yolonas docs (#17736) 2025-04-16 09:01:15 -06:00
web Improve object classification (#18908) 2025-06-27 06:28:40 -06:00
.dockerignore
.gitignore
.pylintrc
audio-labelmap.txt
benchmark_motion.py
benchmark.py Fix go2rtc init (#18708) 2025-06-13 12:09:51 -05:00
CODEOWNERS
cspell.json
docker-compose.yml Devcontainer: update Mosquitto from 1.6 to 2.0 (#17415) 2025-03-27 10:33:49 -06:00
labelmap.txt
LICENSE
Makefile 0.17 tweaks (#18892) 2025-06-26 07:32:48 -06:00
netlify.toml
package-lock.json
process_clip.py Improve async object detector support (#17712) 2025-04-15 08:55:38 -05:00
pyproject.toml Fix various typing issues (#18187) 2025-05-13 08:27:20 -06:00
README_CN.md Add chinese docs (#17954) 2025-05-06 08:49:49 -06:00
README.md Small Tweaks (#17652) 2025-04-11 08:21:01 -06:00

logo

Frigate - NVR With Realtime Object Detection for IP Cameras

Translation status
English

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 GPU or AI accelerator such as a Google Coral or Hailo is highly recommended. AI accelerators will outperform even the best CPUs 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

Live dashboard

Live dashboard

Streamlined review workflow

Streamlined review workflow

Multi-camera scrubbing

Multi-camera scrubbing

Built-in mask and zone editor

Multi-camera scrubbing

Translations

We use Weblate to support language translations. Contributions are always welcome.

Translation status