NVR with realtime local object detection for IP cameras
Go to file
gtsiam 3c015bf822
Do not migrate db to new config path (#14123)
I just saw this, and I would be very surprised by that behaviour as a
user. Changing the db path would randomly move the database, and
changing it back (or to anything, really) would not. These kinds of
advanced settings are generally expected to do one thing: Change the
path frigate opens the database from. The end.
2024-10-02 19:34:14 -06:00
.cspell Work through most of the cspell warnings in python (#13794) 2024-09-17 10:41:46 -05:00
.devcontainer Removed usage of PyYAML for config parsing. (#13883) 2024-09-22 10:56:57 -05:00
.github Bump docker/login-action from 3.2.0 to 3.3.0 (#12555) 2024-10-01 06:03:55 -06:00
.vscode Fix vscode launch configuration (#13795) 2024-09-17 10:42:10 -05:00
config
docker Improve rocm handling of different models (#14072) 2024-09-30 16:40:46 -05:00
docs Clean up hwaccel docs (#14117) 2024-10-02 08:58:53 -05:00
frigate Do not migrate db to new config path (#14123) 2024-10-02 19:34:14 -06:00
migrations Implement support for notifications (#12523) 2024-08-29 20:19:50 -06:00
notebooks
web Fix alert thumbnails on iOS and safari desktop (#14121) 2024-10-02 13:49:52 -06:00
.dockerignore
.gitignore Removed usage of PyYAML for config parsing. (#13883) 2024-09-22 10:56:57 -05:00
.pylintrc
audio-labelmap.txt
benchmark_motion.py
benchmark.py Custom classes for Process and Metrics (#13950) 2024-09-27 07:53:23 -05:00
CODEOWNERS Initial support for Hailo-8L (#12431) 2024-08-29 20:19:50 -06:00
cspell.json Work through most of the cspell warnings in python (#13794) 2024-09-17 10:41:46 -05:00
docker-compose.yml
labelmap.txt
LICENSE
Makefile Formatting improvements (#13765) 2024-09-17 07:39:44 -05:00
netlify.toml
package-lock.json Implement support for notifications (#12523) 2024-08-29 20:19:50 -06:00
process_clip.py Removed usage of PyYAML for config parsing. (#13883) 2024-09-22 10:56:57 -05:00
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