A new network-based intelligent surveillance system

Aiming at the shortcomings of prevalent visual surveillance systems, an intelligent surveillance system which can accomplish automatic detection and classification of moving objects by making use of the personal computer and network system is presented. This kind of surveillance system is provided with high performance/price ratio and the ability to realize all kinds of complex algorithms. In addition, the mature PC network makes it convenient to centrally manage the alarm log and image database so as to reduce the cost of every detection computer. Especially, the leader or administrator can view the interesting alarm log or image at his own office by a LAN (local area network) and intranet connection. Because of complex scenes and lots of disturbance in outdoor environments, such concepts as detecting block, extraction function, feature data and some key techniques such as projection histogram of silhouette pattern, accumulation based on space-time information and geometric model based on edge detection are presented to solve the difficulty of human body recognizing and decrease the ratio of missing alarm and false alarm