* Revise GPU and AI accelerator recommendations

Updated hardware recommendations for AI acceleration.

* Revise PCIe Coral driver installation instructions

Updated instructions for PCIe Coral driver installation.

* Revise Coral driver installation instructions

Updated driver installation instructions for PCIe and M.2 versions of Google Coral.

* Change PCIe Coral driver link in getting_started.md

Updated the link for PCIe Coral driver instructions.

* Change PCIe Coral driver link in installation guide

Updated the link for PCIe Coral driver instructions.

* Update Coral TPU recommendation in hardware documentation

Added a warning about the Coral TPU's recommendation status for new Frigate installations and suggested alternatives.

2025-10-26 06:56:01 -05:00

2.8 KiB

Raw Blame History

Frigate - NVR With Realtime Object Detection for IP Cameras

English

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, Integrated GPU, or AI accelerator such as a Hailo is highly recommended. Dedicated hardware 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