Multiple object tracking: A literature review

被引:405
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 215 条
  • [1] Alahi A., 2009, 2009 12 IEEE INT WOR, P1
  • [2] Ali S, 2008, LECT NOTES COMPUT SC, V5303, P1, DOI 10.1007/978-3-540-88688-4_1
  • [3] PoseTrack: A Benchmark for Human Pose Estimation and Tracking
    Andriluka, Mykhaylo
    Iqbal, Umar
    Insafutdinov, Eldar
    Pishchulin, Leonid
    Milan, Anton
    Gall, Juergen
    Schiele, Bernt
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 5167 - 5176
  • [4] Andriyenko A., 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), P1839, DOI 10.1109/ICCVW.2011.6130472
  • [5] Andriyenko A, 2012, PROC CVPR IEEE, P1926, DOI 10.1109/CVPR.2012.6247893
  • [6] Andriyenko A, 2011, PROC CVPR IEEE, P1265, DOI 10.1109/CVPR.2011.5995311
  • [7] Andriyenko A, 2010, LECT NOTES COMPUT SC, V6311, P466, DOI 10.1007/978-3-642-15549-9_34
  • [8] [Anonymous], 2009, Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS-Winter), DOI DOI 10.1109/PETS-WINTER.2009.5399488
  • [9] [Anonymous], 2006, P IEEE INT C COMPUTE, DOI 10.1109/CVPR.2006.94
  • [10] [Anonymous], ARXIV150401942