TOPIC: A Parallel Association Paradigm for Multi-Object Tracking under Complex Motions and Diverse Scenes

TL;DR

This paper introduces a new dataset BEE24 highlighting complex motions in multi-object tracking and proposes a parallel association paradigm with the TOPIC mechanism, significantly improving tracking accuracy over existing methods.

Contribution

The paper presents a novel parallel association paradigm and the TOPIC mechanism that effectively utilize both motion and appearance features for improved multi-object tracking.

Findings

Achieved state-of-the-art performance on four public datasets and BEE24.

Reduced false negatives by 6% to 81% compared to single-feature paradigms.

Introduced BEE24 dataset focusing on complex motions and similar-appearing small objects.

Abstract

Video data and algorithms have been driving advances in multi-object tracking (MOT). While existing MOT datasets focus on occlusion and appearance similarity, complex motion patterns are widespread yet overlooked. To address this issue, we introduce a new dataset called BEE24 to highlight complex motions. Identity association algorithms have long been the focus of MOT research. Existing trackers can be categorized into two association paradigms: single-feature paradigm (based on either motion or appearance feature) and serial paradigm (one feature serves as secondary while the other is primary). However, these paradigms are incapable of fully utilizing different features. In this paper, we propose a parallel paradigm and present the Two rOund Parallel matchIng meChanism (TOPIC) to implement it. The TOPIC leverages both motion and appearance features and can adaptively select the preferable one as the assignment metric based on motion level. Moreover, we provide an Attention-based Appearance Reconstruction Module (AARM) to reconstruct appearance feature embeddings, thus enhancing the representation of appearance features. Comprehensive experiments show that our approach achieves state-of-the-art performance on four public datasets and BEE24. Moreover, BEE24 challenges existing trackers to track multiple similar-appearing small objects with complex motions over long periods, which is critical in real-world applications such as beekeeping and drone swarm surveillance. Notably, our proposed parallel paradigm surpasses the performance of existing association paradigms by a large margin, e.g., reducing false negatives by 6% to 81% compared to the single-feature association paradigm. The introduced dataset and association paradigm in this work offer a fresh perspective for advancing the MOT field. The source code and dataset are available at https://github.com/holmescao/TOPICTrack.