Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhen, Yihao, Xu, Mingyue, Wang, Qiang, Fan, Baojie, Dong, Jiahua, Zhao, Tinghui, Fan, Huijie
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2407.01007
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918216686632960
author Zhen, Yihao
Xu, Mingyue
Wang, Qiang
Fan, Baojie
Dong, Jiahua
Zhao, Tinghui
Fan, Huijie
author_facet Zhen, Yihao
Xu, Mingyue
Wang, Qiang
Fan, Baojie
Dong, Jiahua
Zhao, Tinghui
Fan, Huijie
contents Multi-Camera Multi-Target (MCMT) tracking aims to locate and associate the same targets across multiple camera views. Existing methods typically adopt a two-stage framework, involving single-camera tracking followed by inter-camera tracking. However, in this paradigm, multi-view information is used only to recover missed matches in the first stage, providing a limited contribution to overall tracking. To address this issue, we propose GMT, a global MCMT tracking framework that jointly exploits intra-view and inter-view cues for tracking. Specifically, instead of assigning trajectories independently for each view, we integrate the same historical targets across different views as global trajectories, thereby reformulating the two-stage tracking as a unified global-level trajectory-target association process. We introduce a Cross-View Feature Consistency Enhancement (CFCE) module to align visual and spatial features across views, providing a consistent feature space for global trajectory modeling. With these aligned features, the Global Trajectory Association (GTA) module associates new detections with existing global trajectories, enabling direct use of multi-view information. Compared to the two-stage framework, GMT achieves significant improvements on existing datasets, with gains of up to 21.3 percent in CVMA and 17.2 percent in CVIDF1. Furthermore, we introduce VisionTrack, a high-quality, large-scale MCMT dataset providing significantly greater diversity than existing datasets. Our code and dataset will be released.
format Preprint
id arxiv_https___arxiv_org_abs_2407_01007
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GMT: Effective Global Framework for Multi-Camera Multi-Target Tracking
Zhen, Yihao
Xu, Mingyue
Wang, Qiang
Fan, Baojie
Dong, Jiahua
Zhao, Tinghui
Fan, Huijie
Computer Vision and Pattern Recognition
Multi-Camera Multi-Target (MCMT) tracking aims to locate and associate the same targets across multiple camera views. Existing methods typically adopt a two-stage framework, involving single-camera tracking followed by inter-camera tracking. However, in this paradigm, multi-view information is used only to recover missed matches in the first stage, providing a limited contribution to overall tracking. To address this issue, we propose GMT, a global MCMT tracking framework that jointly exploits intra-view and inter-view cues for tracking. Specifically, instead of assigning trajectories independently for each view, we integrate the same historical targets across different views as global trajectories, thereby reformulating the two-stage tracking as a unified global-level trajectory-target association process. We introduce a Cross-View Feature Consistency Enhancement (CFCE) module to align visual and spatial features across views, providing a consistent feature space for global trajectory modeling. With these aligned features, the Global Trajectory Association (GTA) module associates new detections with existing global trajectories, enabling direct use of multi-view information. Compared to the two-stage framework, GMT achieves significant improvements on existing datasets, with gains of up to 21.3 percent in CVMA and 17.2 percent in CVIDF1. Furthermore, we introduce VisionTrack, a high-quality, large-scale MCMT dataset providing significantly greater diversity than existing datasets. Our code and dataset will be released.
title GMT: Effective Global Framework for Multi-Camera Multi-Target Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.01007