Online multi-object tracking via structural constraint event aggregation

Ju Hong Yoon, Chang Ryeol Lee, Ming Hsuan Yang, Kuk Jin Yoon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

82 Citations (Scopus)

Abstract

Multi-object tracking (MOT) becomes more challenging when objects of interest have similar appearances. In that case, the motion cues are particularly useful for discriminating multiple objects. However, for online 2D MOT in scenes acquired from moving cameras, observable motion cues are complicated by global camera movements and thus not always smooth or predictable. To deal with such unexpected camera motion for online 2D MOT, a structural motion constraint between objects has been utilized thanks to its robustness to camera motion. In this paper, we propose a new data association method that effectively exploits structural motion constraints in the presence of large camera motion. In addition, to further improve the robustness of data association against mis-detections and false positives, a novel event aggregation approach is developed to integrate structural constraints in assignment costs for online MOT. Experimental results on a large number of datasets demonstrate the effectiveness of the proposed algorithm for online 2D MOT.

Original languageEnglish
Title of host publicationProceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
PublisherIEEE Computer Society
Pages1392-1400
Number of pages9
ISBN (Electronic)9781467388504
DOIs
Publication statusPublished - 2016 Dec 9
Event29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, United States
Duration: 2016 Jun 262016 Jul 1

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2016-December
ISSN (Print)1063-6919

Conference

Conference29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
CountryUnited States
CityLas Vegas
Period16/6/2616/7/1

Fingerprint

Agglomeration
Cameras
Costs

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Yoon, J. H., Lee, C. R., Yang, M. H., & Yoon, K. J. (2016). Online multi-object tracking via structural constraint event aggregation. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 (pp. 1392-1400). [7780524] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December). IEEE Computer Society. https://doi.org/10.1109/CVPR.2016.155
Yoon, Ju Hong ; Lee, Chang Ryeol ; Yang, Ming Hsuan ; Yoon, Kuk Jin. / Online multi-object tracking via structural constraint event aggregation. Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 2016. pp. 1392-1400 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{e304bd3254964d19965f1b9e528c1b7a,
title = "Online multi-object tracking via structural constraint event aggregation",
abstract = "Multi-object tracking (MOT) becomes more challenging when objects of interest have similar appearances. In that case, the motion cues are particularly useful for discriminating multiple objects. However, for online 2D MOT in scenes acquired from moving cameras, observable motion cues are complicated by global camera movements and thus not always smooth or predictable. To deal with such unexpected camera motion for online 2D MOT, a structural motion constraint between objects has been utilized thanks to its robustness to camera motion. In this paper, we propose a new data association method that effectively exploits structural motion constraints in the presence of large camera motion. In addition, to further improve the robustness of data association against mis-detections and false positives, a novel event aggregation approach is developed to integrate structural constraints in assignment costs for online MOT. Experimental results on a large number of datasets demonstrate the effectiveness of the proposed algorithm for online 2D MOT.",
author = "Yoon, {Ju Hong} and Lee, {Chang Ryeol} and Yang, {Ming Hsuan} and Yoon, {Kuk Jin}",
year = "2016",
month = "12",
day = "9",
doi = "10.1109/CVPR.2016.155",
language = "English",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "1392--1400",
booktitle = "Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016",
address = "United States",

}

Yoon, JH, Lee, CR, Yang, MH & Yoon, KJ 2016, Online multi-object tracking via structural constraint event aggregation. in Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016., 7780524, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-December, IEEE Computer Society, pp. 1392-1400, 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, United States, 16/6/26. https://doi.org/10.1109/CVPR.2016.155

Online multi-object tracking via structural constraint event aggregation. / Yoon, Ju Hong; Lee, Chang Ryeol; Yang, Ming Hsuan; Yoon, Kuk Jin.

Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 2016. p. 1392-1400 7780524 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Online multi-object tracking via structural constraint event aggregation

AU - Yoon, Ju Hong

AU - Lee, Chang Ryeol

AU - Yang, Ming Hsuan

AU - Yoon, Kuk Jin

PY - 2016/12/9

Y1 - 2016/12/9

N2 - Multi-object tracking (MOT) becomes more challenging when objects of interest have similar appearances. In that case, the motion cues are particularly useful for discriminating multiple objects. However, for online 2D MOT in scenes acquired from moving cameras, observable motion cues are complicated by global camera movements and thus not always smooth or predictable. To deal with such unexpected camera motion for online 2D MOT, a structural motion constraint between objects has been utilized thanks to its robustness to camera motion. In this paper, we propose a new data association method that effectively exploits structural motion constraints in the presence of large camera motion. In addition, to further improve the robustness of data association against mis-detections and false positives, a novel event aggregation approach is developed to integrate structural constraints in assignment costs for online MOT. Experimental results on a large number of datasets demonstrate the effectiveness of the proposed algorithm for online 2D MOT.

AB - Multi-object tracking (MOT) becomes more challenging when objects of interest have similar appearances. In that case, the motion cues are particularly useful for discriminating multiple objects. However, for online 2D MOT in scenes acquired from moving cameras, observable motion cues are complicated by global camera movements and thus not always smooth or predictable. To deal with such unexpected camera motion for online 2D MOT, a structural motion constraint between objects has been utilized thanks to its robustness to camera motion. In this paper, we propose a new data association method that effectively exploits structural motion constraints in the presence of large camera motion. In addition, to further improve the robustness of data association against mis-detections and false positives, a novel event aggregation approach is developed to integrate structural constraints in assignment costs for online MOT. Experimental results on a large number of datasets demonstrate the effectiveness of the proposed algorithm for online 2D MOT.

UR - http://www.scopus.com/inward/record.url?scp=84986317212&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986317212&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2016.155

DO - 10.1109/CVPR.2016.155

M3 - Conference contribution

AN - SCOPUS:84986317212

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 1392

EP - 1400

BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

PB - IEEE Computer Society

ER -

Yoon JH, Lee CR, Yang MH, Yoon KJ. Online multi-object tracking via structural constraint event aggregation. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society. 2016. p. 1392-1400. 7780524. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2016.155