Download
AB3DMOT is a real-time 3D multi-object tracking framework designed for applications such as autonomous driving and robotics perception. The system processes detection results from 3D object detectors that analyze LiDAR point clouds and uses them to track multiple objects across consecutive frames. Its tracking pipeline relies on a combination of classical algorithms, including a Kalman filter for state estimation and the Hungarian algorithm for data association between detected objects and existing tracks. This relatively simple design allows the tracker to achieve very high processing speeds while maintaining competitive tracking accuracy. The project also introduces new evaluation metrics specifically designed for assessing performance in 3D tracking benchmarks. The framework has been evaluated on widely used datasets such as KITTI and nuScenes and demonstrates strong performance compared with more complex tracking systems.
Features
- Real-time 3D multi-object tracking for autonomous perception systems
- Tracking-by-detection pipeline using LiDAR-based object detections
- Kalman filter for estimating object states across time
- Hungarian algorithm for data association between detections and tracks
- Evaluation metrics designed specifically for 3D tracking benchmarks
- High-speed tracking performance suitable for real-time robotics systems
Project Samples
