Multiple object tracking with extended occlusions

被引:0
|
作者
Lukavsky, Jiri [1 ,3 ]
Oksama, Lauri [2 ]
Dechterenko, Filip [1 ]
机构
[1] Czech Acad Sci, Inst Psychol, Prague, Czech Republic
[2] Univ Turku, Dept Psychol & Speech Language Pathol, Turku, Finland
[3] Czech Acad Sci, Inst Psychol, Hybernska 8, Prague 11000, Czech Republic
来源
基金
芬兰科学院;
关键词
Visual attention; visual memory; occlusion; multiple object tracking; multiple identity tracking; ATTENTIVE TRACKING; IDENTITY TRACKING; VISUAL-ATTENTION; WORKING-MEMORY; EYE-MOVEMENTS; INHIBITION; RESOURCES; BINDING; MODEL;
D O I
10.1177/17470218221142463
中图分类号
B84 [心理学];
学科分类号
04 ; 0402 ;
摘要
In everyday life, we often view objects through a limited aperture (e.g., soccer players on TV or cars slipping into our blind spot on a busy road), where objects often move out of view and reappear in a different place later. We modelled this situation in a series of multiple object tracking (MOT) experiments, in which we introduced a cover on the edges of the observed area and manipulated its width. This method introduced systematic occlusions, which were longer than those used in previous MOT studies. Experiment 1 (N = 50) showed that tracking under such conditions is possible, although difficult. An item-level analysis confirmed that people made more errors in targets that were covered longer and more often. In Experiment 2 (N = 50), we manipulated the tracking workload and found that the participants were less affected by the cover when the tracking load was low. In Experiment 3 (N = 50), we asked the participants to keep track of the objects' identities (multiple identity tracking [MIT]). Although MIT is subjectively more demanding, memorising identities improved performance in the most difficult cover conditions. Contrary to previous reports, we also found that even partial occlusions negatively affected tracking.
引用
收藏
页码:2094 / 2106
页数:13
相关论文
共 50 条
  • [1] DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions
    Fu, Teng
    Wang, Xiaocong
    Yu, Haiyang
    Niu, Ke
    Li, Bin
    Xue, Xiangyang
    [J]. PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 2734 - 2743
  • [2] Colour and feature based multiple object tracking under heavy occlusions
    Kumar, Pabboju Sateesh
    Guha, Prithwijit
    Mukerjee, Amitabha
    [J]. PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON ADVANCES IN PATTERN RECOGNITION, 2007, : 152 - +
  • [3] Multiple object juggling: Changing what is tracked during extended multiple object tracking
    Jeremy M. Wolfe
    Skyler S. Place
    Todd S. Horowitz
    [J]. Psychonomic Bulletin & Review, 2007, 14 : 344 - 349
  • [4] Multiple object juggling: Changing what is tracked during extended multiple object tracking
    Wolfe, Jeremy M.
    Place, Skyler S.
    Horowitz, Todd S.
    [J]. PSYCHONOMIC BULLETIN & REVIEW, 2007, 14 (02) : 344 - 349
  • [5] Multiple Extended Object Tracking Using Gaussian Processes
    Hirscher, Tobias
    Scheel, Alexander
    Reuter, Stephan
    Dietmayer, Klaus
    [J]. 2016 19TH INTERNATIONAL CONFERENCE ON INFORMATION FUSION (FUSION), 2016, : 868 - 875
  • [6] Improved Object Tracking Throughout Occlusions
    Gutev, Alexander
    Debono, Carl James
    [J]. IEEE EUROCON 2021 - 19TH INTERNATIONAL CONFERENCE ON SMART TECHNOLOGIES, 2021, : 179 - 185
  • [7] Dynamic center point learning for multiple object tracking under Severe occlusions
    Hu, Yaoqi
    Niu, Axi
    Sun, Jinqiu
    Zhu, Yu
    Yan, Qingsen
    Dong, Wei
    Wozniak, Marcin
    Zhang, Yanning
    [J]. KNOWLEDGE-BASED SYSTEMS, 2024, 300
  • [8] Object Tracking in the Presence of Occlusions Using Multiple Cameras: A Sensor Network Approach
    Ercan, Ali O.
    El Gamal, Abbas
    Guibas, Leonidas J.
    [J]. ACM TRANSACTIONS ON SENSOR NETWORKS, 2013, 9 (02)
  • [9] HOOT: Heavy Occlusions in Object Tracking Benchmark
    Sahin, Gozde
    Itti, Laurent
    [J]. 2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 4819 - 4828
  • [10] Extended Keyframe Detection with Stable Tracking for Multiple 3D Object Tracking
    Park, Youngmin
    Lepetit, Vincent
    Woo, Woontack
    [J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2011, 17 (11) : 1728 - 1735