Characterisation of optical flow anomalies in pedestrian traffic

This paper applies a video modelling technique to a surveillance scenario where pedestrians are monitored to detect unusual events. The aim is to investigate the components of an automatic vision system capable of detecting normal and abnormal behaviour. Such a system has application in surveillance scenarios like town centre plazas, stadiums, train stations and shopping malls. Surveillance usually relies on tracking, but in crowded scenarios tracking is not reliable. Thus our framework for representation and analysis is based on optical flow to avoid tracking of individuals. We demonstrate that patterns derived from optical flow and encoded by a Hidden Markov Model are able to capture the dynamic evolution of normal behaviour allowing the classification of abnormal events.