MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking
This addresses tracking challenges in domains like sports and dance, but appears incremental as it modifies an existing component rather than introducing a new paradigm.
The paper tackled the problem of multi-object tracking in dynamic environments with complex motions and occlusions by replacing the Kalman filter with a learning-based motion model, resulting in advanced performance on datasets like DanceTrack and SportsMOT.
In the field of multi-object tracking (MOT), traditional methods often rely on the Kalman filter for motion prediction, leveraging its strengths in linear motion scenarios. However, the inherent limitations of these methods become evident when confronted with complex, nonlinear motions and occlusions prevalent in dynamic environments like sports and dance. This paper explores the possibilities of replacing the Kalman filter with a learning-based motion model that effectively enhances tracking accuracy and adaptability beyond the constraints of Kalman filter-based tracker. In this paper, our proposed method MambaMOT and MambaMOT+, demonstrate advanced performance on challenging MOT datasets such as DanceTrack and SportsMOT, showcasing their ability to handle intricate, non-linear motion patterns and frequent occlusions more effectively than traditional methods.