Frigate is a complete and local NVR designed for Home Assistant with AI object detection. It uses OpenCV and Tensorflow to perform realtime object detection locally for IP cameras.
https://blakeblackshear.github.io/frigate/hardware
You can one-click-deploy this project to balena using the button below:
Alternatively, deployment can be carried out by manually creating a balenaCloud account and application, flashing a device, downloading the project and pushing it via the balena CLI.
FRIGATE_MQTT_USER
: Replaced at runtime infrigate.yml
FRIGATE_MQTT_PASSWORD
: Replaced at runtime infrigate.yml
FRIGATE_RTSP_USER
: Replaced at runtime infrigate.yml
FRIGATE_RTSP_PASSWORD
: Replaced at runtime infrigate.yml
TZ
: Inform services of the timezone in your locationSET_HOSTNAME
: Set a custom hostname on application start (default isfrigate
)
Once your device joins the fleet you'll need to allow some time for it to download the application and start the services.
When it's done you should be able to access the access the app at http://frigate.local.
Additional usage instructions for Frigate can be found here: https://blakeblackshear.github.io/frigate/.
There is an optional wyze-bridge
service in case you own Wyze cameras and want to connect them to Frigate.
Just add the environment variables WYZE_EMAIL
and WYZE_PASSWORD
to the wyze-bridge
service and
start adding cameras to the Frigate yml with the RTSP URL rtsp://wyze-bridge:8554/camera-nickname
.
Additional usage instructions can be found here: https://github.com/mrlt8/docker-wyze-bridge
Please open an issue or submit a pull request with any features, fixes, or changes.