Understanding Dynamic Social Grouping Behaviors of Pedestrians

Abstract

There have been many studies in the literature on social group recognition of crowds of pedestrians. However, most of these studies have approached the problem from a static point of view. A study on the dynamic property of social groups among people over time can provide significant insight into human behaviors and events. Inspired by sociological models of human collective behavior, in this work, we present a framework for characterizing hierarchical social groups based on evolving tracklet interaction network (ETIN) where the tracklets of pedestrians are represented as nodes and the their grouping behaviors are captured by the edges with associated weights. We use non-overlapping snapshots of the interaction network and develop the framework for a unified dynamic group identification and tracklet association. The approach is evaluated quantitatively and qualitatively on videos of pedestrian scenes where manually labeled ground-truth is given. The results of our approach are consistent to human-perceived dynamic social groups of the crowd. The performance analysis of our method shows that the approach is scalable and it provides situational awareness in a real-world scenarios.Index Terms-Dynamic social grouping behavior, pedestrian social groups, tracklet interaction network. 1932-4553

Detecting personality and emotion traits in crowds from video sequences

“…Surveillance, entertainment and social sciences are examples of fields that can benefit from the development of this area of study. Literature presents different applications of crowd analysis, like counting people in crowds [9,6], group and crowd movement and formation [41,45,38,26] and detection of social groups in crowds [40,39,21,10]. Normally, these approaches are based on personal tracking or optical flow algorithms, and handle with features like walking speed, directions and distances over time.…”

Multiperson Tracking by Online Learned Grouping Model With Nonlinear Motion Context

“…We evaluate our approach on four data sets: the CAVIAR data set [8], the TownCentre data set [35], the PETS2009 data set [36], and the UNIV data set [37]. The popular evaluation metrics defined in [38] and the CLEAR MOT metrics defined in [39] are used for performance comparison.…”

Grouping vehicles in Vehicular Social Networks

“…Grouping pedestrians has been presented in [8] depending on evolving track interaction network (ETIN). Tracks of pedestrians are represented as nodes whereas their behavior as weighted edges.…”