Online Multiple Object Tracking Using Min-Cost Flow on Temporal Window for Autonomous Driving

doi:10.3390/wevj14090243

	Online Multiple Object Tracking Using Min-Cost Flow on Temporal Window for Autonomous Driving
	Wei, Hongjian 1,2; Huang, Yingping 2; Zhang, Qian 3; Guo, Zhiyang 4
	2023-09
发表期刊	WORLD ELECTRIC VEHICLE JOURNAL
ISSN	2032-6653
卷号	14 期号:9
摘要	Multiple object tracking (MOT), as a core technology for environment perception in autonomous driving, has attracted attention from researchers. Combing the advantages of batch global optimization, we present a novel online MOT framework for autonomous driving, consisting of feature extraction and data association on a temporal window. In the feature extraction stage, we design a three-channel appearance feature extraction network based on metric learning by using ResNet50 as the backbone network and the triplet loss function and employ a Kalman Filter with a constant acceleration motion model to optimize and predict the object bounding box information, so as to obtain reliable and discriminative object representation features. For data association, to reduce the ID switches, the min-cost flow of global association is introduced within the temporal window composed of consecutive multi-frame images. The trajectories within the temporal window are divided into two categories, active trajectories and inactive trajectories, and the appearance, motion affinities between each category of trajectories, and detections are calculated, respectively. Based on this, a sparse affinity network is constructed, and the data association is achieved using the min-cost flow problem of the network. Qualitative experimental results on KITTI MOT public benchmark dataset and real-world campus scenario sequences validate the effectiveness and robustness of our method. Compared with the homogeneous, vision-based MOT methods, quantitative experimental results demonstrate that our method has competitive advantages in terms of higher order tracking accuracy, association accuracy, and ID switches.
关键词	multiple object tracking MULTIOBJECT TRACKING min-cost flow feature extraction data association on temporal window autonomous driving
DOI	10.3390/wevj14090243
收录类别	ESCI
语种	英语
WOS研究方向	Engineering ; Transportation
WOS类目	Engineering, Electrical & Electronic ; Transportation Science & Technology
WOS记录号	WOS:001078190100001
出版者	MDPI
原始文献类型	Article
引用统计	被引频次[WOS]：0 [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.library.ouchn.edu.cn/handle/39V7QQFX/168684
专题	国家开放大学江苏分部
通讯作者	Wei, Hongjian
作者单位	1.Fuyang Normal Univ, Sch Phys & Elect Engn, Fuyang 236037, Peoples R China; 2.Univ Shanghai Sci & Technol, Sch Opt Elect & Comp Engn, Shanghai 200093, Peoples R China; 3.Jiangsu Open Univ, Sch Informat Technol, Nanjing 210036, Peoples R China; 4.Jiangsu Shipping Coll, Sch Traff Engn, Nantong 226010, Peoples R China
推荐引用方式 GB/T 7714	Wei, Hongjian,Huang, Yingping,Zhang, Qian,et al. Online Multiple Object Tracking Using Min-Cost Flow on Temporal Window for Autonomous Driving[J]. WORLD ELECTRIC VEHICLE JOURNAL,2023,14(9).
APA	Wei, Hongjian,Huang, Yingping,Zhang, Qian,&Guo, Zhiyang.(2023).Online Multiple Object Tracking Using Min-Cost Flow on Temporal Window for Autonomous Driving.WORLD ELECTRIC VEHICLE JOURNAL,14(9).
MLA	Wei, Hongjian,et al."Online Multiple Object Tracking Using Min-Cost Flow on Temporal Window for Autonomous Driving".WORLD ELECTRIC VEHICLE JOURNAL 14.9(2023).