Dynamicity Adaptation for Multi-object Tracking and Segmentation: Toward Improved Association Correction

Abstract

Dynamicity is a critical and highly challenging aspect in Multi-Object Tracking and Segmentation (MOTS), significantly impeding the effective integration of diverse association cues. High dynamicity, such as severe occlusion or deformation, can distort appearance cues, leading to inaccurate inter-object relationships and misleading results. Conversely, in low dynamicity states, spatiotemporal consistency of appearance cues aids in recovering object states. To address this issue, we propose a straightforward, effective, and versatile Dynamicity Adaptation for Multi-object Tracking and Segmentation, named DA-Track. First, we leverage the sensitivity of appearance cues to dynamicity through pre-association, capturing dynamic behavior in objects. Second, Dynamicity Adaptation incorporates Dynamicity Selection to identify reliable appearance cues based on pre-association results and Occlusion Dynamicity Fusing to adaptively integrate appearance and motion cues by analyzing historical mask variations. Experiments on MOTS20 and KITTI MOTS datasets demonstrate DA-Track’s robust and reliable performance across diverse scenarios.