A Real-Time Algorithm for Small Group Detection in Medium Density Crowds

Abstract

In this paper, we focus on the task of small group detection in crowded scenarios. Small groups are widely considered as one of the basic elements in crowds, so it is a major challenge to distinguish group members from the individuals in the crowd. It is also a basic problem in video surveillance and scene understanding. We propose a solution for this task, which could run in real time and could work in both low and medium density crowded scenes. In particular, we build a social force based collision avoidance model on each individual for goal direction prediction, and employ the predicted goal directions instead of traditional positions and velocities in collective motion detection to find group members. We evaluate our approach over three datasets including tens of challenging crowded scenarios. The experimental results demonstrate that our proposed approach is not only highly accurate but also improves the practical property performance compared to other state-of-the-art methods.