Study On Moving Object Detection And Tracking In Video Surveillance

Intelligent Video Surveillance is to use the methods of digital image processing and computer's scensing to analyze automatically to obtain the target's orientation, recognition and track by using vidicon to record picture's series and we can analyze and judge target's actions. As an essential part of the automatic surveillance system, the research in this area can provide broad potential use in the future.This paper mainly discusses the fundamental theories and key technologies of Intelligent Video Surveillance. The following topics are researched in details, such as detection and extraction of moving objects with static background, detection of shadow of moving objects and tracking of moving objects and so on. We present a moving video object automatic detection and tracking algorithm based on dominant color in fixed background. Only color is a hint for video retrieval, and dominant color matching is used in frames and records the frame which object appears. Experiment results given in the thesis show that, the algorithm are simple, fast and robust. It can also partly solve the problem of, robust to the scale change and detour of non-grid object.