2021-01-21 03:26:49 +03:00
---
id: index
2021-09-12 22:48:21 +03:00
title: Introduction
2021-01-21 03:26:49 +03:00
slug: /
---
2021-05-19 07:08:41 +03:00
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.
2021-01-21 03:26:49 +03:00
2021-09-12 22:48:21 +03:00
Use of a [Google Coral Accelerator ](https://coral.ai/products/ ) is optional, but strongly recommended. CPU detection should only be used for testing purposes. The Coral will outperform even the best CPUs and can process 100+ FPS with very little overhead.
2021-01-21 03:26:49 +03:00
2021-05-19 07:08:41 +03:00
- Tight integration with Home Assistant via a [custom component ](https://github.com/blakeblackshear/frigate-hass-integration )
2021-01-21 03:26:49 +03:00
- 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
2021-09-12 22:48:21 +03:00
- Recording with retention based on detected objects
2021-01-21 03:26:49 +03:00
- Re-streaming via RTMP to reduce the number of connections to your camera
2021-09-12 22:48:21 +03:00
- A dynamic combined camera view of all tracked cameras.
2021-01-21 03:26:49 +03:00
## Screenshots
2021-10-04 15:00:30 +03:00
2021-01-21 03:26:49 +03:00
2021-10-04 15:00:30 +03:00
