Automatic Detection and Tracking of Abandoned Objects

In recent years, visual surveillance has gained importance in security, law enforcement and military applications. Due to the wide use of video surveillance systems, the amount of data that has to be monitored and interpreted has increased enormously. Nowadays, the pure mass of information that has to be handled by the operators of such systems has overgrown their capabilities. It is therefore crucial to support human operators with (semi-)automatic surveillance systems which notify their supervisors in case of an incident potentially relevant to security. In this paper, we present a tracking/surveillance system that supports a human operator by automatically detecting abandoned objects and drawing the operator’s attention to such events. It consists of two major parts: A Bayesian multi-people tracker that explains as much of the scene as possible and a blob-based object detection system that identifies abandoned objects using the unexplained image parts. If a potentially abandoned object is detected, the operator is notified and the system provides the appropriate key frames for interpreting the incident.