Analyzing pedestrian behavior in crowds for automatic detection of congestions

Congestions in pedestrian traffic typically occur when the number of pedestrians exceeds the capacity of pedestrian facilities. In some cases, the pedestrian density reaches a critical level which may lead to a crowd stampede as happens rather frequently at mass gatherings, in stadiums or at train stations. In the past, research has focused on improving simulations of crowd motion in order to identify potentially dangerous locations and to direct pedestrian streams. Recently, works towards the automatic real-time detection of critical mass behavior based on optical flow computations have been proposed. In this paper, we verify these approaches by analyzing mircoscopic pedestrian behavior in congestions and conducting experiments on synthetic as well as on real datasets.