No Train Yet Gain: Towards Generic Multi-Object Tracking in Sports and Beyond
This work addresses the problem of adaptable and generalizable multi-object tracking for sports analytics and beyond, offering an incremental improvement by integrating mask propagation into existing methods.
The paper tackles the challenge of multi-object tracking in sports and general scenarios by proposing McByte, a tracking-by-detection framework that uses temporally propagated segmentation masks for association without requiring training or per-video tuning. It demonstrates strong performance on datasets like SportsMOT, DanceTrack, SoccerNet-tracking 2022, and MOT17, showing improved robustness and generalizability.
Multi-object tracking (MOT) is essential for sports analytics, enabling performance evaluation and tactical insights. However, tracking in sports is challenging due to fast movements, occlusions, and camera shifts. Traditional tracking-by-detection methods require extensive tuning, while segmentation-based approaches struggle with track processing. We propose McByte, a tracking-by-detection framework that integrates temporally propagated segmentation mask as an association cue to improve robustness without per-video tuning. Unlike many existing methods, McByte does not require training, relying solely on pre-trained models and object detectors commonly used in the community. Evaluated on SportsMOT, DanceTrack, SoccerNet-tracking 2022 and MOT17, McByte demonstrates strong performance across sports and general pedestrian tracking. Our results highlight the benefits of mask propagation for a more adaptable and generalizable MOT approach. Code will be made available at https://github.com/tstanczyk95/McByte.