F
Frigate
Frigate is a cutting-edge NVR with real-time object detection capabilities for IP cameras, optimized for handling continuous recording workloads.
v0.18.2 · Pre-1.0•MIT•Since Jan 2019•Has commercial version
Overall rating
activity, maturity, stars
8.8
/ 10
GitHub stars
37k
Contributors
414
Last commit
21h ago
Project age
7 years
About
Frigate is an advanced real-time video surveillance tool optimized for integrating with home assistant platforms. It focuses on utilizing machine learning for detecting and categorizing objects, thereby enhancing the accuracy and efficiency of security systems. Designed to be lightweight yet powerful, Frigate operates with minimal hardware requirements, making it accessible for a wide range of users.
Key Features
- 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