This book is one of the first books to focus on visual event detection. It demonstrates that computer vision research has matured to a point where meaningful visual event detection can be achieved. The authors propose that the exact object and motion information is not necessary to achieve video event detection. They show that some visual events are sufficiently described by little more than the broad categories of the constituent objects and their qualitative motions. The Video Computing book series provides a forum for the dissemination of innovative research results for computer vision, image processing, database and computer graphics researchers. Visual Event Detection will be of interest to those working in video analysis, video understanding, video compression, image understanding, and artificial intelligence.