Multi-object tracking with robust object regression and association

Li, Yi-fan, Ji, Hong-bing, Chen, Xi, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 and Yang, Yong-liang 2023. Multi-object tracking with robust object regression and association. Computer Vision and Image Understanding 227 , 103586. 10.1016/j.cviu.2022.103586

Preview

PDF - Accepted Post-Print Version Download (12MB) | Preview

Abstract

Tracking-by-regression is a new paradigm for online Multi-Object Tracking (MOT). It unifies detection and tracking into a single network by associating targets through regression, significantly reducing the complexity of data association. However, owing to noisy features from nearby occlusions and distractors, the regression is vulnerable and unaware of the inter-object occlusions and intra-class distractors. Thus the regressed bounding boxes can be wrongly suppressed or easily drift. Meanwhile, the commonly used bounding box-based post-processing is unable to remedy false negatives and false assignments caused by regression. To address these challenges, we present to leverage regression tubes as input for the regression-based tracker, which provides spatial–temporal information to enhance the tracking performance. Specially, we propose a novel tube re-localization strategy that obtains robust regressions and recovers missed targets. A tube-based NMS (T-NMS) strategy to manage the regressions at the tube level is also proposed, including a tube IoU (T-IoU) scheme for measuring positional relation and tube re-scoring (T-RS) to evaluate the quality of candidate tubes. Finally, a tube re-assignment strategy is further employed for robust cost measurement and to revise false assignments using motion cues. We evaluate our method on benchmarks, including MOT16, MOT17, and MOT20. The results show that our method can significantly improve the baseline, mitigate the challenges of the regression-based tracker, and achieve very competitive tracking performance.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Additional Information:	License information from Publisher: LICENSE 1: Title: This article is under embargo with an end date yet to be finalised.
Publisher:	Elsevier
ISSN:	1077-3142
Date of First Compliant Deposit:	21 November 2022
Date of Acceptance:	10 November 2022
Last Modified:	15 Nov 2023 18:29
URI:	https://orca.cardiff.ac.uk/id/eprint/154315

Actions (repository staff only)

Edit Item