Synergistic-aware cascaded association and trajectory refinement for multi-object tracking

Abstract

Multi-object tracking (MOT) is a pivotal research area in computer vision. Effectively tracking objects in scenarios with frequent occlusions and crowded scenes has become a key challenge in MOT tasks. Existing tracking-by-detection (TbD) methods often rely on simple two-frame association techniques. However, in situations involving scale transformation or requiring long-term association, frequent occlusion between objects can lead to ID switches, especially in scenes with dense or highly intersecting objects. Therefore, we propose a synergistic-aware cascaded association and trajectory refinement method (SCTrack) for multi-object tracking. In the data association stage, we propose a synergistic-aware cascaded association method to construct a multi-perception affinity matrix for object association, and introduce the multi-frame collaborative distance calculation to enhance the robustness. To address the problem of trajectory fragmentation, we propose a dynamic confidence-driven trajectory refinement post-processing method. This method integrates confidence and feature information to calculate trajectory association, repair fragmented trajectories, and improve the overall robustness of the tracking algorithm. Extensive experiments on the MOT17, MOT20, and DanceTrack datasets validate SCTrack’s competitive performance.