Gool, “Real-time detection of unusual regions in image streams

Automatic and real-time identification of unusual incidents is important for event detection and alarm systems. In to-day’s camera surveillance solutions video streams are dis-played on-screen for human operators, e.g. in large multi-screen control centers. This in turn requires the attention of operators for unusual events and urgent response. This paper presents a method for the automatic identifi-cation of unusual visual content in video streams real-time. In contrast to explicitly modeling specific unusual events, the proposed approach incrementally learns the usual ap-pearances from the visual source and simultaneously iden-tifies potential unusual image regions in the scene. Exper-iments demonstrate the general applicability on a variety of large-scale datasets including different scenes from public web cams and from traffic monitoring. To further demon-strate the real-time capabilities of the unusual scene detec-tion we actively control a Pan-Tilt-Zoom camera to get close up views of the unusual incidents