Multiple object tracking: A literature review

被引:400
|
作者
Luo, Wenhan [1 ,2 ]
Xing, Junliang [3 ,6 ]
Milan, Anton [4 ]
Zhang, Xiaoqin [5 ]
Liu, Wei [1 ]
Kim, Tae-Kyun [2 ]
机构
[1] Tencent AI Lab, Shenzhen, Peoples R China
[2] Imperial Coll London, London, England
[3] Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
[4] Amazon Res & Dev Ctr, Berlin, Germany
[5] Wenzhou Univ, Wenzhou, Peoples R China
[6] Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
关键词
Multi-object tracking; Data association; Survey; MULTITARGET TRACKING; PERFORMANCE EVALUATION; MULTIOBJECT TRACKING; VISUAL SURVEILLANCE; MODEL; MOTION; ASSOCIATION; PROPAGATION; VEHICLE; SET;
D O I
10.1016/j.artint.2020.103448
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Multiple Object Tracking (MOT) has gained increasing attention due to its academic and commercial potential. Although different approaches have been proposed to tackle this problem, it still remains challenging due to factors like abrupt appearance changes and severe object occlusions. In this work, we contribute the first comprehensive and most recent review on this problem. We inspect the recent advances in various aspects and propose some interesting directions for future research. To the best of our knowledge, there has not been any extensive review on this topic in the community. We endeavor to provide a thorough review on the development of this problem in recent decades. The main contributions of this review are fourfold: 1) Key aspects in an MOT system, including formulation, categorization, key principles, evaluation of MOT are discussed; 2) Instead of enumerating individual works, we discuss existing approaches according to various aspects, in each of which methods are divided into different groups and each group is discussed in detail for the principles, advances and drawbacks; 3) We examine experiments of existing publications and summarize results on popular datasets to provide quantitative and comprehensive comparisons. By analyzing the results from different perspectives, we have verified some basic agreements in the field; and 4) We provide a discussion about issues of MOT research, as well as some interesting directions which will become potential research effort in the future. (C) 2021 Elsevier B.V. All rights reserved.
引用
收藏
页数:23
相关论文
共 50 条
  • [41] Recursive clustering for multiple object tracking
    Dubuisson, Severine
    2006 IEEE International Conference on Image Processing, ICIP 2006, Proceedings, 2006, : 2805 - 2808
  • [42] Remapping attention in multiple object tracking
    Howe, Piers D. L.
    Drew, Trafton
    Pinto, Yair
    Horowitz, Todd S.
    VISION RESEARCH, 2011, 51 (05) : 489 - 495
  • [43] Multiple Object Tracking with Correlation Learning
    Wang, Qiang
    Zheng, Yun
    Pan, Pan
    Xu, Yinghui
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 3875 - 3885
  • [44] Multiple object tracking by reliable tracklets
    Liang, Yingyi
    Lu, Xiaohuan
    He, Zhenyu
    Zheng, Yuan
    SIGNAL IMAGE AND VIDEO PROCESSING, 2019, 13 (04) : 823 - 831
  • [45] An algorithm for multiple object trajectory tracking
    Han, M
    Xu, W
    Tao, H
    Gong, Y
    PROCEEDINGS OF THE 2004 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, 2004, : 864 - 871
  • [46] Multiple object tracking with segmentation and interactive multiple model
    Qi, Ke
    Xu, Wenhao
    Chen, Wenbin
    Tao, Xi
    Chen, Peijia
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2024, 99
  • [47] Multiple sensor multiple object tracking with GMPHD filter
    Pham, Nam Trung
    Huang, Weimin
    Ong, S. H.
    2007 PROCEEDINGS OF THE 10TH INTERNATIONAL CONFERENCE ON INFORMATION FUSION, VOLS 1-4, 2007, : 904 - +
  • [48] Fluoroscopic tracking of multiple implanted fiducial markers using multiple object tracking
    Tang, Xiaoli
    Sharp, Greg C.
    Jiang, Steve B.
    PHYSICS IN MEDICINE AND BIOLOGY, 2007, 52 (14): : 4081 - 4098
  • [49] Online multiple object tracking via exchanging object context
    Yu, Hongyang
    Qin, Lei
    Huang, Qingming
    Yao, Hongxun
    NEUROCOMPUTING, 2018, 292 : 28 - 37
  • [50] Object centred optimisation process for robust multiple object tracking
    Connor, B
    Humphreys, DKP
    Smith, C
    SEVENTH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING AND ITS APPLICATIONS, 1999, (465): : 691 - 695