Interactive Surveillance Technologies for Dense Crowds

Abstract

We present an algorithm for realtime anomaly detection in low to medium density crowd videos using trajectory-level behavior learning. Our formulation combines online tracking algorithms from computer vision, non-linear pedestrian motion models from crowd simulation, and Bayesian learning techniques to automatically compute the trajectory-level pedestrian behaviors for each agent in the video. These learned behaviors are used to segment the trajectories and motions of different pedestrians or agents and detect anomalies. We demonstrate the interactive performance on the PETS ARENA dataset as well as indoor and outdoor crowd video benchmarks consisting of tens of human agents. We also discuss the implications of recent public policy and law enforcement issues relating to surveillance and our research.