Occlusion-Aware SORT: Observing Occlusion for Robust Multi-Object Tracking
This work provides a reusable framework to improve multi-object tracking robustness for various applications by explicitly handling occlusion, which is an incremental improvement.
This paper addresses the challenge of positional cost confusion in 2D multi-object tracking (MOT) caused by partial occlusion. The proposed Occlusion-Aware SORT (OA-SORT) framework, which is plug-and-play and training-free, achieved HOTA of 63.1% and IDF1 of 64.2% on the DanceTrack test set, and improved HOTA and IDF1 by an average of 2.08% and 3.05% when integrated into four other trackers.
Multi-object tracking (MOT) involves analyzing object trajectories and counting the number of objects in video sequences. However, 2D MOT faces challenges due to positional cost confusion arising from partial occlusion. To address this issue, we present the novel Occlusion-Aware SORT (OA-SORT) framework, a plug-and-play and training-free framework that includes the Occlusion-Aware Module (OAM), the Occlusion-Aware Offset (OAO), and the Bias-Aware Momentum (BAM). Specifically, OAM analyzes the occlusion status of objects, where a Gaussian Map (GM) is introduced to reduce background influence. In contrast, OAO and BAM leverage the OAM-described occlusion status to mitigate cost confusion and suppress estimation instability. Comprehensive evaluations on the DanceTrack, SportsMOT, and MOT17 datasets demonstrate the importance of occlusion handling in MOT. On the DanceTrack test set, OA-SORT achieves 63.1% and 64.2% in HOTA and IDF1, respectively. Furthermore, integrating the Occlusion-Aware framework into the four additional trackers improves HOTA and IDF1 by an average of 2.08% and 3.05%, demonstrating the reusability of the occlusion awareness.