xingyizhou/CenterTrack
A real-time simultaneous object detection and tracking algorithm that localizes objects and predicts their temporal associations using center points.
Not currently ranked — collecting fresh signals.
star history
CenterTrack applies a detection model to pairs of images and prior-frame detections to simultaneously localize objects and predict their associations across frames. It achieves 67.3% MOTA on MOT17 at 22 FPS and 89.4% MOTA on KITTI, setting state-of-the-art results on both benchmarks. The method also extends to monocular 3D tracking by regressing additional spatial attributes, achieving 28.3% AMOTA@0.2 on nuScenes at 28 FPS.
Frequently asked
- What is xingyizhou/CenterTrack?
- A real-time simultaneous object detection and tracking algorithm that localizes objects and predicts their temporal associations using center points.
- Is CenterTrack open source?
- Yes — xingyizhou/CenterTrack is open source, released under the MIT license.
- What language is CenterTrack written in?
- xingyizhou/CenterTrack is primarily written in Python.
- How popular is CenterTrack?
- xingyizhou/CenterTrack has 2.5k stars on GitHub.
- Where can I find CenterTrack?
- xingyizhou/CenterTrack is on GitHub at https://github.com/xingyizhou/CenterTrack.