Hard to Track Objects with Irregular Motions and Similar Appearances? Make It Easier by Buffering the Matching Space
Fan Yang, Shigeyuki Odashima, Shoichi Masui, Shan Jiang

TL;DR
This paper introduces the Cascaded Buffered IoU (C-BIoU) tracker, which improves multi-object tracking for irregular motions and similar appearances by expanding the matching space with buffers and cascaded matching, achieving state-of-the-art results.
Contribution
The paper presents a novel C-BIoU tracker that enhances object matching in challenging scenarios by buffering and cascaded matching, addressing limitations of appearance and motion features.
Findings
Achieves state-of-the-art results on MOT datasets with irregular motions.
Secures 2nd place in CVPR'22 SoccerNet MOT and ECCV'22 MOTComplex challenges.
Effectively handles objects with similar appearances and irregular movements.
Abstract
We propose a Cascaded Buffered IoU (C-BIoU) tracker to track multiple objects that have irregular motions and indistinguishable appearances. When appearance features are unreliable and geometric features are confused by irregular motions, applying conventional Multiple Object Tracking (MOT) methods may generate unsatisfactory results. To address this issue, our C-BIoU tracker adds buffers to expand the matching space of detections and tracks, which mitigates the effect of irregular motions in two aspects: one is to directly match identical but non-overlapping detections and tracks in adjacent frames, and the other is to compensate for the motion estimation bias in the matching space. In addition, to reduce the risk of overexpansion of the matching space, cascaded matching is employed: first matching alive tracks and detections with a small buffer, and then matching unmatched tracks and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Pose and Action Recognition · Video Surveillance and Tracking Methods · Gait Recognition and Analysis
