Issue No. 05 - May (2012 vol. 34)
R. T. Collins , Dept. of Comput. Sci. & Eng., Penn State Univ., University Park, PA, USA
Weina Ge , Comput. Vision Lab., GE Global Res., Niskayuna, NY, USA
R. B. Ruback , Dept. of Sociology, Penn State Univ., University Park, PA, USA
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.
statistical analysis, image recognition, object tracking, pattern clustering, pedestrians, real-time situation awareness, vision-based analysis, pedestrian crowd dynamics, multiobject tracking, sociological model, human collective behavior, small group detection, bottom-up hierarchical clustering, generalized symmetric Hausdortf distance, pairwise proximity, pairwise velocity, real-world pedestrian scene, human-coded ground truth, substantial statistical agreement, human-perceived small group structure, crowd structure, automated crowd analysis, pedestrian group, Trajectory, Videos, Target tracking, Humans, Legged locomotion, Clustering algorithms, crowd dynamics., Pedestrian detection and tracking, pedestrian groups
R. T. Collins, Weina Ge, R. B. Ruback, "Vision-Based Analysis of Small Groups in Pedestrian Crowds", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 34, no. , pp. 1003-1016, May 2012, doi:10.1109/TPAMI.2011.176