Interactive Surveillance Technologies for Dense Crowds

TL;DR

This paper introduces a real-time anomaly detection algorithm for dense crowds using trajectory behavior learning, combining tracking, crowd modeling, and Bayesian methods to identify unusual pedestrian movements.

Contribution

It presents a novel integrated approach that combines multiple techniques for improved anomaly detection in crowd videos, demonstrating effectiveness on various datasets.

Findings

Effective real-time anomaly detection in crowd videos.

Successful application on diverse indoor and outdoor datasets.

Discussion on policy implications of surveillance technology.

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.