mirror of
https://github.com/blakeblackshear/frigate.git
synced 2026-05-01 19:17:41 +03:00
NVR with realtime local object detection for IP cameras
aicameragoogle-coralhome-assistanthome-automationhomeautomationmqttnvrobject-detectionrealtimertsptensorflow
e7684eddbf
This change adds first-class adaptive recording playback using main and sub recording variants. Frigate can now store multiple recording variants per camera, expose those variants through the recordings API, and serve variant-specific VOD playlists through routes such as /vod/variant/sub/....
The UI now uses the available recording variants and browser playback capability to choose an appropriate playback source, with a user-selectable Auto, Main, and Sub preference. This is applied across timeline playback, export preview, and object detail playback.
The backend also includes a fallback path for sub playback: when a native sub recording is not available for a requested time range, Frigate can generate a lower-resolution sub recording from the main segment, store it under the standard sub variant, and mark it with transcoded_from_main.
Additional changes include recording metadata for codec, resolution, bitrate, and variant; database migrations for recording variants and generated-sub tracking; tests for variant VOD selection and fallback behavior; improved storage graph sorting; and a small MQTT TLS guard so tls_insecure is only applied when TLS is configured.
Substream Configuration Examples
Record the main stream as the normal full-resolution recording and also record the camera substream as the sub variant:
cameras:
front_door:
ffmpeg:
inputs:
- path: rtsp://user:password@192.168.1.10:554/main
roles:
- record
record_variant: main
- path: rtsp://user:password@192.168.1.10:554/sub
roles:
- detect
- record
record_variant: sub
detect:
width: 640
height: 360
fps: 5
record:
enabled: true
Using go2rtc restreams:
go2rtc:
streams:
front_door:
- rtsp://user:password@192.168.1.10:554/main
front_door_sub:
- rtsp://user:password@192.168.1.10:554/sub
cameras:
front_door:
ffmpeg:
inputs:
- path: rtsp://127.0.0.1:8554/front_door
input_args: preset-rtsp-restream
roles:
- record
record_variant: main
- path: rtsp://127.0.0.1:8554/front_door_sub
input_args: preset-rtsp-restream
roles:
- detect
- record
record_variant: sub
detect:
width: 640
height: 360
fps: 5
record:
enabled: true
If record_variant is omitted on a record input, it defaults to main. Each camera can only use a given recording variant once, so the main and sub recording inputs should use distinct variant names.
|
||
|---|---|---|
| .cspell | ||
| .cursor/rules | ||
| .devcontainer | ||
| .github | ||
| .vscode | ||
| config | ||
| docker | ||
| docs | ||
| frigate | ||
| migrations | ||
| notebooks | ||
| scripts | ||
| transcode_proxy | ||
| web | ||
| .dockerignore | ||
| .gitignore | ||
| .pylintrc | ||
| audio-labelmap.txt | ||
| benchmark_motion.py | ||
| benchmark.py | ||
| CODEOWNERS | ||
| cspell.json | ||
| docker-compose.yml | ||
| generate_config_translations.py | ||
| labelmap.txt | ||
| LICENSE | ||
| Makefile | ||
| netlify.toml | ||
| package-lock.json | ||
| process_clip.py | ||
| pyproject.toml | ||
| README_CN.md | ||
| README.md | ||
| TRADEMARK.md | ||
Frigate NVR™ - Realtime Object Detection for IP Cameras
EnglishA 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 is highly recommended. AI accelerators will outperform even the best CPUs with very little overhead. See Frigate's supported object detectors.
- 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.
License
This project is licensed under the MIT License.
- Code: The source code, configuration files, and documentation in this repository are available under the MIT License. You are free to use, modify, and distribute the code as long as you include the original copyright notice.
- Trademarks: The "Frigate" name, the "Frigate NVR" brand, and the Frigate logo are trademarks of Frigate, Inc. and are not covered by the MIT License.
Please see our Trademark Policy for details on acceptable use of our brand assets.
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.
Copyright © 2026 Frigate, Inc.