Vision-based analysis of small groups in pedestrian crowds

Research output: Contribution to journalArticlepeer-review

282 Scopus citations


Building upon state-of-the-art algorithms for pedestrian detection and multi-object tracking, and inspired by sociological models of human collective behavior, we automatically detect small groups of individuals who are traveling together. These groups are discovered by bottom-up hierarchical clustering using a generalized, symmetric Hausdorff distance defined with respect to pairwise proximity and velocity. We validate our results quantitatively and qualitatively on videos of real-world pedestrian scenes. Where human-coded ground truth is available, we find substantial statistical agreement between our results and the human-perceived small group structure of the crowd. Results from our automated crowd analysis also reveal interesting patterns governing the shape of pedestrian groups. These discoveries complement current research in crowd dynamics, and may provide insights to improve evacuation planning and real-time situation awareness during public disturbances.

Original languageEnglish (US)
Article number5989835
Pages (from-to)1003-1016
Number of pages14
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number5
StatePublished - 2012

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics


Dive into the research topics of 'Vision-based analysis of small groups in pedestrian crowds'. Together they form a unique fingerprint.

Cite this