Structural Constraint Data Association for Online Multi-object Tracking

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

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Online two-dimensional (2D) multi-object tracking (MOT) is a challenging task when the objects of interest have similar appearances. In that case, the motion of objects is another helpful cue for tracking and discriminating multiple objects. However, when using a single moving camera for online 2D MOT, observable motion cues are contaminated by global camera movements and, thus, are not always predictable. To deal with unexpected camera motion, we propose a new data association method that effectively exploits structural constraints in the presence of large camera motion. In addition, to reduce incorrect associations with mis-detections and false positives, we develop a novel event aggregation method to integrate assignment costs computed by structural constraints. We also utilize structural constraints to track missing objects when they are re-detected again. By doing this, identities of the missing objects can be retained continuously. Experimental results validated the effectiveness of the proposed data association algorithm under unexpected camera motions. In addition, tracking results on a large number of benchmark datasets demonstrated that the proposed MOT algorithm performs robustly and favorably against various online methods in terms of several quantitative metrics, and that its performance is comparable to offline methods.

Original languageEnglish
JournalInternational Journal of Computer Vision
Volume127
Issue number1
DOIs
Publication statusPublished - 2019 Jan 15

Fingerprint

Cameras
Agglomeration
Costs

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

@article{6f99b70f86e649d9af91e275ada729e3,
title = "Structural Constraint Data Association for Online Multi-object Tracking",
abstract = "Online two-dimensional (2D) multi-object tracking (MOT) is a challenging task when the objects of interest have similar appearances. In that case, the motion of objects is another helpful cue for tracking and discriminating multiple objects. However, when using a single moving camera for online 2D MOT, observable motion cues are contaminated by global camera movements and, thus, are not always predictable. To deal with unexpected camera motion, we propose a new data association method that effectively exploits structural constraints in the presence of large camera motion. In addition, to reduce incorrect associations with mis-detections and false positives, we develop a novel event aggregation method to integrate assignment costs computed by structural constraints. We also utilize structural constraints to track missing objects when they are re-detected again. By doing this, identities of the missing objects can be retained continuously. Experimental results validated the effectiveness of the proposed data association algorithm under unexpected camera motions. In addition, tracking results on a large number of benchmark datasets demonstrated that the proposed MOT algorithm performs robustly and favorably against various online methods in terms of several quantitative metrics, and that its performance is comparable to offline methods.",
author = "Yoon, {Ju Hong} and Lee, {Chang Ryeol} and Yang, {Ming Hsuan} and Yoon, {Kuk Jin}",
year = "2019",
month = "1",
day = "15",
doi = "10.1007/s11263-018-1087-1",
language = "English",
volume = "127",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer Netherlands",
number = "1",

}

Structural Constraint Data Association for Online Multi-object Tracking. / Yoon, Ju Hong; Lee, Chang Ryeol; Yang, Ming Hsuan; Yoon, Kuk Jin.

In: International Journal of Computer Vision, Vol. 127, No. 1, 15.01.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Structural Constraint Data Association for Online Multi-object Tracking

AU - Yoon, Ju Hong

AU - Lee, Chang Ryeol

AU - Yang, Ming Hsuan

AU - Yoon, Kuk Jin

PY - 2019/1/15

Y1 - 2019/1/15

N2 - Online two-dimensional (2D) multi-object tracking (MOT) is a challenging task when the objects of interest have similar appearances. In that case, the motion of objects is another helpful cue for tracking and discriminating multiple objects. However, when using a single moving camera for online 2D MOT, observable motion cues are contaminated by global camera movements and, thus, are not always predictable. To deal with unexpected camera motion, we propose a new data association method that effectively exploits structural constraints in the presence of large camera motion. In addition, to reduce incorrect associations with mis-detections and false positives, we develop a novel event aggregation method to integrate assignment costs computed by structural constraints. We also utilize structural constraints to track missing objects when they are re-detected again. By doing this, identities of the missing objects can be retained continuously. Experimental results validated the effectiveness of the proposed data association algorithm under unexpected camera motions. In addition, tracking results on a large number of benchmark datasets demonstrated that the proposed MOT algorithm performs robustly and favorably against various online methods in terms of several quantitative metrics, and that its performance is comparable to offline methods.

AB - Online two-dimensional (2D) multi-object tracking (MOT) is a challenging task when the objects of interest have similar appearances. In that case, the motion of objects is another helpful cue for tracking and discriminating multiple objects. However, when using a single moving camera for online 2D MOT, observable motion cues are contaminated by global camera movements and, thus, are not always predictable. To deal with unexpected camera motion, we propose a new data association method that effectively exploits structural constraints in the presence of large camera motion. In addition, to reduce incorrect associations with mis-detections and false positives, we develop a novel event aggregation method to integrate assignment costs computed by structural constraints. We also utilize structural constraints to track missing objects when they are re-detected again. By doing this, identities of the missing objects can be retained continuously. Experimental results validated the effectiveness of the proposed data association algorithm under unexpected camera motions. In addition, tracking results on a large number of benchmark datasets demonstrated that the proposed MOT algorithm performs robustly and favorably against various online methods in terms of several quantitative metrics, and that its performance is comparable to offline methods.

UR - http://www.scopus.com/inward/record.url?scp=85046038698&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046038698&partnerID=8YFLogxK

U2 - 10.1007/s11263-018-1087-1

DO - 10.1007/s11263-018-1087-1

M3 - Article

AN - SCOPUS:85046038698

VL - 127

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 1

ER -