Occlusion-Aware SORT: Observing Occlusion for Robust Multi-Object Tracking

TL;DR

This paper introduces OA-SORT, a novel occlusion-aware framework for multi-object tracking that improves robustness by analyzing occlusion status and reducing cost confusion without additional training.

Contribution

The paper proposes a training-free, plug-and-play occlusion-aware framework with modules that analyze occlusion, mitigate cost confusion, and enhance multi-object tracking performance.

Findings

OA-SORT achieves 63.1% HOTA on DanceTrack.

Integrating occlusion awareness improves existing trackers' performance.

The framework enhances robustness in multi-object tracking under occlusion.

Abstract

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.