Norfair is a customizable lightweight Python library for real-time multi-object tracking. Using Norfair, you can add tracking capabilities to any detector with just a few lines of code. Any detector expressing its detections as a series of (x, y) coordinates can be used with Norfair. This includes detectors performing tasks such as object or keypoint detection. It can easily be inserted into complex video processing pipelines to add tracking to existing projects. At the same time, it is possible to build a video inference loop from scratch using just Norfair and a detector. Supports moving camera, re-identification with appearance embeddings, and n-dimensional object tracking. Norfair provides several predefined distance functions to compare tracked objects and detections. The distance functions can also be defined by the user, enabling the implementation of different tracking strategies.
Features
- The only thing bounding inference speed will be the detection network feeding detections to Norfair
- Norfair provides several predefined distance functions to compare tracked objects and detections
- Supports moving camera, re-identification with appearance embeddings, and n-dimensional object tracking
- It can easily be inserted into complex video processing pipelines to add tracking to existing projects
- Any detector expressing its detections as a series of (x, y) coordinates can be used with Norfair
- At the same time, it is possible to build a video inference loop from scratch using just Norfair and a detector