mirror of
https://github.com/blakeblackshear/frigate.git
synced 2025-12-10 00:07:21 -06:00
9d85136f8f
* fetch more from ffprobe * add detailed param to ffprobe endpoint * add dots variant to step indicator * add classname * tweak colors for dark mode to match figma * add step 1 form * add helper function for ffmpeg snapshot * add go2rtc stream add and ffprobe snapshot endpoints * add camera image and stream details on successful test * step 1 tweaks * step 2 and i18n * types * step 1 and 2 tweaks * add wizard to camera settings view * add data unit i18n keys * restream tweak * fix type * implement rough idea for step 3 * add api endpoint to delete stream from go2rtc * add main wizard dialog component * extract logic for friendly_name and use in wizard * add i18n and popover for brand url * add camera name to top * consolidate validation logic * prevent dialog from closing when clicking outside * center camera name on mobile * add help/docs link popovers * keep spaces in friendly name * add stream details to overlay like stats in liveplayer * add validation results pane to step 3 * ensure test is invalidated if stream is changed * only display validation results and enable save button if all streams have been tested * tweaks * normalize camera name to lower case and improve hash generation * move wizard to subfolder * tweaks * match look of camera edit form to wizard * move wizard and edit form to its own component * move enabled/disabled switch to management section * clean up * fixes * fix mobile
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.
