Occlusion-Robust Multi-Object Tracking with Adaptive Feature Management and Motion Compensation

Multi-object tracking (MOT) faces challenges in handling occlusions, feature degradation, and non-rigid motion. Existing methods relying on appearance-based re-identification (Re-ID) often struggle under occlusion, leading to frequent identity switches, while traditional motion models fail in dynamic scenarios. To address these issues, we propose an improved MOT framework integrating Score-based Gallery Management (SGM) to retain reliable Re-ID embeddings and Optical Flow-based Motion Compensation (OMC) to refine motion predictions. Our method achieves state-of-the-art performance on MOT20 and SportsMOT and exhibits competitive results on MOT17 and DanceTrack, demonstrating improved identity retention and tracking robustness in complex environments.