This work presents an automatic technique for detection of abnormal events in crowds. Crowd behaviour is difficult to predict and might not be easily semantically translated. Moreover it is difficulty to track individuals in the crowd using state of the art tracking algorithms. Therefore we characterise crowd behaviour by observing the crowd optical flow and use unsupervised feature extraction to encode normal crowd behaviour. The unsupervised feature extraction applies spectral clustering to find the optimal number of models to represent normal motion patterns. The motion models are HMMs to cope with the variable number of motion samples that might be present in each observation window. The results on simulated crowds demonstrate the effectiveness of the approach for detecting crowd emergency scenarios.

Abstract

Abstract

This paper evaluates a technique for detection of abnormal events in crowds. We characterise crowd behaviour by observing the crowd optical flow and use unsupervised feature extraction to encode normal crowd behaviour. The unsupervised feature extraction applies spectral clustering to find the optimal number of models to represent normal motion patterns. The motion models are HMMs to cope with the variable number of motion samples that might be present in each observation window. The results on simulated crowds analyse the robustness of the approach for detecting crowd emergency scenarios observing the crowd at local and global levels. The results on normal real data show the effectiveness in modelling the more diverse behaviour present in normal crowds. These results improve our previous work in the detection of anomalies in pedestrian data.

-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.