Uncertainty-aware Unsupervised Multi-Object Tracking

TL;DR

This paper introduces U2MOT, an uncertainty-aware unsupervised multi-object tracking framework that leverages uncertainty to improve feature consistency and achieve state-of-the-art results.

Contribution

It develops an uncertainty-based metric to verify and rectify associations, enhancing pseudo-tracklet accuracy and incorporating temporal information effectively.

Findings

U2MOT outperforms existing methods on MOT-Challenges and VisDrone-MOT benchmarks.

The uncertainty-based approach improves feature embedding consistency.

U2MOT achieves state-of-the-art performance among supervised and unsupervised trackers.

Abstract

Without manually annotated identities, unsupervised multi-object trackers are inferior to learning reliable feature embeddings. It causes the similarity-based inter-frame association stage also be error-prone, where an uncertainty problem arises. The frame-by-frame accumulated uncertainty prevents trackers from learning the consistent feature embedding against time variation. To avoid this uncertainty problem, recent self-supervised techniques are adopted, whereas they failed to capture temporal relations. The interframe uncertainty still exists. In fact, this paper argues that though the uncertainty problem is inevitable, it is possible to leverage the uncertainty itself to improve the learned consistency in turn. Specifically, an uncertainty-based metric is developed to verify and rectify the risky associations. The resulting accurate pseudo-tracklets boost learning the feature consistency. And accurate tracklets can incorporate temporal information into spatial transformation. This paper proposes a tracklet-guided augmentation strategy to simulate tracklets' motion, which adopts a hierarchical uncertainty-based sampling mechanism for hard sample mining. The ultimate unsupervised MOT framework, namely U2MOT, is proven effective on MOT-Challenges and VisDrone-MOT benchmark. U2MOT achieves a SOTA performance among the published supervised and unsupervised trackers.