mirror of
https://github.com/blakeblackshear/frigate.git
synced 2025-12-10 00:07:21 -06:00
fbf4388b37
* don't flatten the search result cache when updating this would cause an infinite swr fetch if something was mutated and then fetch was called again * Properly sort keys for recording summary in StorageMetrics * tracked object description box tweaks * Remove ability to right click on elements inside of face popup * Update reprocess message * don't show object track until video metadata is loaded * fix blue line height calc for in progress events * Use timeline tab by default for notifications but add a query arg for customization * Try and improve notification opening behavior * Reduce review item buffering behavior * ensure logging config is passed to camera capture and tracker processes * ensure on demand recording stops when browser closes * improve active line progress height with resize observer * remove icons and duplicate find similar link in explore context menu * fix for initial broken image when creating trigger from explore * display friendly names for triggers in toasts * lpr and triggers docs updates * remove icons from dropdowns in face and classification * fix comma dangle linter issue * re-add incorrectly removed face library button icons * fix sidebar nav links on < 768px desktop layout * allow text to wrap on mark as reviewed button * match exact pixels * clarify LPR docs --------- Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
Frigate - NVR With Realtime Object Detection for IP Cameras
[English] | 简体中文
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
Streamlined review workflow
Multi-camera scrubbing
Built-in mask and zone editor
Translations
We use Weblate to support language translations. Contributions are always welcome.
