NVR with realtime local object detection for IP cameras
Go to file
Nicolas Mowen 2f69f5afe6
Add support for yolonas via ONNX and allow TensorRT execution provider to work correctly (#13776)
* Add support for yolonas in onnx

* Add correct deps

* Set ld library path

* Refactor cudnn to only be used in amd64

* Add onnx to docs and add explainer at the top

* Undo change

* Update comment

* Remove uneccesary

* Remove line change
2024-09-16 16:17:31 -05:00
.cspell
.devcontainer Configurable ffmpeg (#13722) 2024-09-13 15:14:51 -05:00
.github Hailo amd64 support (#12820) 2024-08-29 20:19:50 -06:00
.vscode
config
docker Add support for yolonas via ONNX and allow TensorRT execution provider to work correctly (#13776) 2024-09-16 16:17:31 -05:00
docs Add support for yolonas via ONNX and allow TensorRT execution provider to work correctly (#13776) 2024-09-16 16:17:31 -05:00
frigate Add support for yolonas via ONNX and allow TensorRT execution provider to work correctly (#13776) 2024-09-16 16:17:31 -05:00
migrations
notebooks
web stop web linter from complaining (#13755) 2024-09-15 11:43:03 -06:00
.dockerignore
.gitignore
.pylintrc
audio-labelmap.txt
benchmark_motion.py
benchmark.py
CODEOWNERS
cspell.json
docker-compose.yml
labelmap.txt
LICENSE
Makefile Update version 2024-08-29 20:19:50 -06:00
netlify.toml
package-lock.json
process_clip.py
pyproject.toml
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 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