2020-10-24 15:23:16 +02:00
< p align = "center" >
2021-01-21 01:26:49 +01:00
< img align = "center" alt = "logo" src = "docs/static/img/frigate.png" >
2020-10-24 15:23:16 +02:00
< / p >
2020-09-17 14:26:49 +02:00
# Frigate - NVR With Realtime Object Detection for IP Cameras
2021-01-21 01:26:49 +01:00
2020-12-05 02:06:20 +01:00
A complete and local NVR designed for HomeAssistant with AI object detection. Uses OpenCV and Tensorflow to perform realtime object detection locally for IP cameras.
2019-03-03 17:04:27 +01:00
2020-10-24 15:23:16 +02:00
Use of a [Google Coral Accelerator ](https://coral.ai/products/ ) is optional, but highly recommended. The Coral will outperform even the best CPUs and can process 100+ FPS with very little overhead.
2020-02-22 15:59:16 +01:00
2020-12-05 02:06:20 +01:00
- Tight integration with HomeAssistant via a [custom component ](https://github.com/blakeblackshear/frigate-hass-integration )
2020-10-24 15:23:16 +02:00
- Designed to minimize resource use and maximize performance by only looking for objects when and where it is necessary
2020-02-22 15:59:16 +01:00
- 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
2020-10-24 15:23:16 +02:00
- Object detection with TensorFlow runs in separate processes for maximum FPS
- Communicates over MQTT for easy integration into other systems
2020-12-05 02:06:20 +01:00
- 24/7 recording
- Re-streaming via RTMP to reduce the number of connections to your camera
2020-10-24 15:23:16 +02:00
## Documentation
2021-01-21 01:26:49 +01:00
View the documentation at https://blakeblackshear.github.io/frigate
