Crowd Behavior Analysis via Curl and Divergence of Motion Trajectories

Shuang Wu, Hua Yang, Shibao Zheng, Hang Su, Yawen Fan, Ming Hsuan Yang

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

In the field of crowd behavior analysis, existing methods mainly focus on using local representations inspired by models found in other disciplines (e.g., fluid dynamics and social dynamics) to describe motion patterns. However, less attention is paid to exploiting motion structures (e.g., visual information contained in trajectories) for behavior analysis. In this paper, we consider both local characteristics and global structures of a motion vector field, and propose the Curl and Divergence of motion Trajectories (CDT) descriptors to describe collective motion patterns. To this end, a trajectory-based motion coding algorithm is designed to extract the CDT descriptors. For each motion vector field we construct its conjugate field, in which each vector is perpendicular to the counterpart in the original vector field. The trajectories in the motion and corresponding conjugate fields indicate the tangential and radial motion structures, respectively. By integrating curl (and divergence, respectively) along the tangential paths (and the radial paths, respectively), the CDT descriptors are extracted. We show that the proposed motion descriptors are scale- and rotation-invariant for effective crowd behavior analysis. For concreteness, we apply the CDT descriptors to identify five typical crowd behaviors (lane, clockwise arch, counterclockwise arch, bottleneck and fountainhead) with a pipeline including motion decomposition. Extensive experimental results on two benchmark datasets demonstrate the effectiveness of the CDT descriptors for describing and classifying crowd behaviors.

Original languageEnglish
Pages (from-to)499-519
Number of pages21
JournalInternational Journal of Computer Vision
Volume123
Issue number3
DOIs
Publication statusPublished - 2017 Jul 1

Fingerprint

Trajectories
Arches
Fluid dynamics
Pipelines
Decomposition

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Wu, Shuang ; Yang, Hua ; Zheng, Shibao ; Su, Hang ; Fan, Yawen ; Yang, Ming Hsuan. / Crowd Behavior Analysis via Curl and Divergence of Motion Trajectories. In: International Journal of Computer Vision. 2017 ; Vol. 123, No. 3. pp. 499-519.
@article{870a5496207f4520899650b143aa4e4b,
title = "Crowd Behavior Analysis via Curl and Divergence of Motion Trajectories",
abstract = "In the field of crowd behavior analysis, existing methods mainly focus on using local representations inspired by models found in other disciplines (e.g., fluid dynamics and social dynamics) to describe motion patterns. However, less attention is paid to exploiting motion structures (e.g., visual information contained in trajectories) for behavior analysis. In this paper, we consider both local characteristics and global structures of a motion vector field, and propose the Curl and Divergence of motion Trajectories (CDT) descriptors to describe collective motion patterns. To this end, a trajectory-based motion coding algorithm is designed to extract the CDT descriptors. For each motion vector field we construct its conjugate field, in which each vector is perpendicular to the counterpart in the original vector field. The trajectories in the motion and corresponding conjugate fields indicate the tangential and radial motion structures, respectively. By integrating curl (and divergence, respectively) along the tangential paths (and the radial paths, respectively), the CDT descriptors are extracted. We show that the proposed motion descriptors are scale- and rotation-invariant for effective crowd behavior analysis. For concreteness, we apply the CDT descriptors to identify five typical crowd behaviors (lane, clockwise arch, counterclockwise arch, bottleneck and fountainhead) with a pipeline including motion decomposition. Extensive experimental results on two benchmark datasets demonstrate the effectiveness of the CDT descriptors for describing and classifying crowd behaviors.",
author = "Shuang Wu and Hua Yang and Shibao Zheng and Hang Su and Yawen Fan and Yang, {Ming Hsuan}",
year = "2017",
month = "7",
day = "1",
doi = "10.1007/s11263-017-1005-y",
language = "English",
volume = "123",
pages = "499--519",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer Netherlands",
number = "3",

}

Crowd Behavior Analysis via Curl and Divergence of Motion Trajectories. / Wu, Shuang; Yang, Hua; Zheng, Shibao; Su, Hang; Fan, Yawen; Yang, Ming Hsuan.

In: International Journal of Computer Vision, Vol. 123, No. 3, 01.07.2017, p. 499-519.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Crowd Behavior Analysis via Curl and Divergence of Motion Trajectories

AU - Wu, Shuang

AU - Yang, Hua

AU - Zheng, Shibao

AU - Su, Hang

AU - Fan, Yawen

AU - Yang, Ming Hsuan

PY - 2017/7/1

Y1 - 2017/7/1

N2 - In the field of crowd behavior analysis, existing methods mainly focus on using local representations inspired by models found in other disciplines (e.g., fluid dynamics and social dynamics) to describe motion patterns. However, less attention is paid to exploiting motion structures (e.g., visual information contained in trajectories) for behavior analysis. In this paper, we consider both local characteristics and global structures of a motion vector field, and propose the Curl and Divergence of motion Trajectories (CDT) descriptors to describe collective motion patterns. To this end, a trajectory-based motion coding algorithm is designed to extract the CDT descriptors. For each motion vector field we construct its conjugate field, in which each vector is perpendicular to the counterpart in the original vector field. The trajectories in the motion and corresponding conjugate fields indicate the tangential and radial motion structures, respectively. By integrating curl (and divergence, respectively) along the tangential paths (and the radial paths, respectively), the CDT descriptors are extracted. We show that the proposed motion descriptors are scale- and rotation-invariant for effective crowd behavior analysis. For concreteness, we apply the CDT descriptors to identify five typical crowd behaviors (lane, clockwise arch, counterclockwise arch, bottleneck and fountainhead) with a pipeline including motion decomposition. Extensive experimental results on two benchmark datasets demonstrate the effectiveness of the CDT descriptors for describing and classifying crowd behaviors.

AB - In the field of crowd behavior analysis, existing methods mainly focus on using local representations inspired by models found in other disciplines (e.g., fluid dynamics and social dynamics) to describe motion patterns. However, less attention is paid to exploiting motion structures (e.g., visual information contained in trajectories) for behavior analysis. In this paper, we consider both local characteristics and global structures of a motion vector field, and propose the Curl and Divergence of motion Trajectories (CDT) descriptors to describe collective motion patterns. To this end, a trajectory-based motion coding algorithm is designed to extract the CDT descriptors. For each motion vector field we construct its conjugate field, in which each vector is perpendicular to the counterpart in the original vector field. The trajectories in the motion and corresponding conjugate fields indicate the tangential and radial motion structures, respectively. By integrating curl (and divergence, respectively) along the tangential paths (and the radial paths, respectively), the CDT descriptors are extracted. We show that the proposed motion descriptors are scale- and rotation-invariant for effective crowd behavior analysis. For concreteness, we apply the CDT descriptors to identify five typical crowd behaviors (lane, clockwise arch, counterclockwise arch, bottleneck and fountainhead) with a pipeline including motion decomposition. Extensive experimental results on two benchmark datasets demonstrate the effectiveness of the CDT descriptors for describing and classifying crowd behaviors.

UR - http://www.scopus.com/inward/record.url?scp=85015006244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015006244&partnerID=8YFLogxK

U2 - 10.1007/s11263-017-1005-y

DO - 10.1007/s11263-017-1005-y

M3 - Article

AN - SCOPUS:85015006244

VL - 123

SP - 499

EP - 519

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 3

ER -