The Eighth International Workshop on Visual Surveillance

Research into intelligent visual surveillance technologies has become one of the core problem areas of the computer vision research community. The field enjoys well-funded national and international funding programmes and boasts a plethora of start-up companies offering a wide range of intelligent CCTV products. Yet, despite the apparent success, the core problems remain as complex and varied as any in computer vision. The deployment of truly intelligent and robust surveillance systems face a number of specific challenges including the segmentation and tracking of individuals in crowded scenes; extracting body pose; characterization of threats; reduction in false alarm rates; automatic learning of human-oriented scene structure; and the semantic linkage between networks of cameras and other sensors. To address these challenges, contributions are particularly welcome in the following areas:

• Background and environment modelling
• Object tracking and classification
• Behaviour analysis and recognition
• Image database annotation and searching
• Event and activity modelling
• Analysis of groups and crowds
• Multi-Camera and multi-sensor calibration
• Performance evaluation
• Image-based sensor networks
• PTZ networks

 Held in conjunction with