VIDEO BASED MOTION TRAJECTORY ANALYSIS OF PEDESTRIANS

Abstract

In this thesis, a method to identify social groups of pedestrians from pedestrian crowd videos is proposed. It works based on the social psychological theory of pedestrian groups, monitoring whether the pedestrians move closely together in the same direction with almost the same velocity for a certain period of time. The pedestrian group features such as group size, group member locations, time of group identification are extracted and stored in a proposed data structure, termed as Pedestrian Group Record. Several applications utilzing the information in the Pedestrian Group Record are proposed, namely, pedestrian meeting-event detection, stall occupancy determination, people Counting, crowd density estimation and visual representations of pedestrian?s group history. Pedestrian motion changes which happen during the convergence of pedestrians to form a group is learnt using Support-Vector-Machines, to predict future pedestrian groups. A similar approach is proposed to predict approach of potential customers to food outlets.