All apps · 0 apps

frigate

Overview

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. You can use an integrated or dedicated GPU (Intel/AMD/Nvidia) to decode your cameras' streams, and a detector such as a Google Coral, Hailo, OpenVINO (Intel GPU/NPU), an Nvidia GPU (TensorRT) or an AMD GPU (ROCm) for object detection. This is a general template: check every option and remove the devices and variables you are not going to use. Frigate creates a default config file in the config folder on first start. The WebUI uses https with a self-signed certificate; the admin password is printed in the container log on first start. Documentation: https://docs.frigate.video/

Readme

View on GitHub

logo

Frigate NVR™ - 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 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.

Requirements

PCIe Coral: install the Coral-Driver plugin from CA first (thanks to @ich777) and map /dev/apex_0.

- Nvidia GPU: install the Nvidia-Driver plugin from CA first (thanks to @ich777), choose the stable-tensorrt tag, add "--runtime=nvidia" to Extra Parameters and set "Nvidia Visible Devices" to your GPU UUID.

- AMD GPU: set the driver variable to "radeonsi"; for ROCm detection choose the stable-rocm tag and also map /dev/kfd.

- Raise --shm-size in Extra Parameters if you have many or high resolution cameras (see the docs).

Related apps

Explore more like this

Explore all

Home Automation Security

Links

Projectfrigate.video Supportforums.unraid.net Registrygithub.com Templategitlab.com

Details

Repository

ghcr.io/blakeblackshear/frigate:stable

Registry

https://github.com/blakeblackshear/frigate/pkgs/container/frigate

Last Updated2023-01-07

First Seen2022-09-23

Runtime arguments

Web UI: https://[IP]:[PORT:8971]
Network: bridge
Shell: bash
Privileged: false
Extra Params: --shm-size=512m --mount type=tmpfs,target=/tmp/cache,tmpfs-size=1000000000 --stop-timeout 30 --restart unless-stopped

Template configuration

Config PathPathrw

Config file and database.

Target: /config
Default: /mnt/user/appdata/frigate
Value: /mnt/user/appdata/frigate

Media PathPathrw

Recordings, snapshots and exports.

Target: /media/frigate
Default: /mnt/user/Media/frigate
Value: /mnt/user/Media/frigate

WebUI PortPorttcp

Authenticated UI and API (https, self-signed certificate by default). Reverse proxies should use this port.

Target: 8971
Default: 8971
Value: 8971

RTSP Restreaming PortPorttcp

Unauthenticated by default; authentication can be set in the go2rtc section of the config.

Target: 8554
Default: 8554
Value: 8554

WebRTC TCP PortPorttcp

Low latency live views and two-way talk.

Target: 8555
Default: 8555
Value: 8555

WebRTC UDP PortPortudp

Low latency live views and two-way talk.

Target: 8555
Default: 8555
Value: 8555

Frigate RTSP PasswordVariable

Optional: use it in your config as {FRIGATE_RTSP_PASSWORD} to keep camera passwords out of the file.

Target: FRIGATE_RTSP_PASSWORD

Frigate+ API KeyVariable

Optional: your Frigate+ API key.

Target: PLUS_API_KEY

Coral / Hailo MappingDevice

/dev/bus/usb for a USB Coral, /dev/apex_0 for a PCIe Coral (drivers first), /dev/hailo0 for Hailo. Remove this if you are not using it.

Target: /dev/bus/usb
Default: /dev/bus/usb
Value: /dev/bus/usb

Intel/AMD GPU MappingDevice

Intel/AMD GPU for decoding (and OpenVINO detection on Intel). Remove this if you are not using it.

Target: /dev/dri/renderD128
Default: /dev/dri/renderD128
Value: /dev/dri/renderD128

Intel/AMD GPU DriverVariable

iHD for recent Intel, i965 for older Intel, radeonsi for AMD. Remove this if you are not using it.

Target: LIBVA_DRIVER_NAME
Default: iHD
Value: iHD

Nvidia Visible DevicesVariable

Only for Nvidia: your GPU UUID, shown in the Nvidia Driver plugin. Remove this if you are not using it.

Target: NVIDIA_VISIBLE_DEVICES
Value: YOURGPUUUID

Nvidia Driver CapabilitiesVariable

Only for Nvidia. Remove this if you are not using it.

Target: NVIDIA_DRIVER_CAPABILITIES
Default: compute,utility,video
Value: compute,utility,video

LocaltimePathro

Host time zone.

Target: /etc/localtime
Default: /etc/localtime
Value: /etc/localtime

Library

Curated

Categories