Multimodal surveillance is the next-generation of surveillance technology, combining traditional video and audio surveillance with state-of-the art sensors. These systems can identify at great distances approaching vehicles or scan crowds of people to pinpoint a specific individual. Once solely used by the military, they are becoming more widely used by law enforcement, business, and even high-end homeowners. This cutting-edge resource brings together the field's leading experts who guide researchers, designers, engineers, and developers through this multifaceted technology. It discusses the latest high-end sensors for extremely accurate surveillance, as well as low-cost sensing solutions. Designers get insight into new powerful algorithms that integrate sensor data to provide meaningful information. Engineers and developers benefit from an indepth examination of architectures, performance, and systems evaluation.
Zhigang Zhu is an associate professor in the Computer Science Department, City College of New York. An associate editor of Machine Vision and Applications Journal, he has been involved in organizing such meetings as the IEEE Virtual Reality Conference, the International Workshop on Digital and Computational Video, and the IEEE International Workshop on Image and Video Registration. Thomas Huang is the William L. Everitt Distinguished Professor of the Department of Electrical and Computer Engineering and of the Coordinated Science Lab at the University of Illinois at Champaign-Urbana. He has garnered many professional honors including the Honda Lifetime Achievement Award, IEEE Third Millennium Medal, and the IEEE Jack S. Kilby Signal Processing Medal. He holds an M.S. and Sc.D. in electrical engineering from M.I.T.
Introduction: Multimodal Sensing, Data Fusion, and Surveillance.; Part I: Multimodal Sensors and Sensing Approaches.; Part II: Multimodal Integration Algorithms.; Part III: Multimodal Systems.