Detecting deviations from known paths and speeds in a surveillance situation
Robin Hosie, Svetha Venkatesh, GEOFF A. W. WEST · 1996
This paper presents techniques for analysing human behaviour via video surveillance. In known scenes under surveillance, common paths of movement between entry and exit points are obtained and classified. These are used, together with a priori velocity data, to serve as a model of normal traffic flow in the scene. Surveillance sequences are then processed to extract and track the movement of people in the scene, which is compared with the models to enable detection of abnormal movement. 1 Introduction There has been an marked interest in video surveillance as a means of crime detection and deterrence in recent times, and this is exhibited in the increase of closed circuit and remote-controlled cameras now displayed in many public locations. Monitoring the images from these cameras is a human-intensive and often tedious task, when undesirable events occur within long periods of normal activity. Automatic detection of these events would relieve the monitor of the often fruitless necess...