Research On The Moving Targets Detection In Video Surveillance System

Computer intelligent video surveillance system(CIVSS) can automatically analyse sequence image by the methods of computer vision and video analysis. The system can real-time detect, recognize, and track moving objects in a special environment. Furthermore, it can also analyse and judge the behavior of objects. The aims of CIVSS are to understand the meanings of video stream and to explain the scenes comprehensibly, hence to guide the action and make some decision.The moving targets detection is an important part of CIVSS. It is a key problem for video analysis and processing,such as computer security monitoring,the targets identification and tracking,moving imagr coding,content-based image retrieval.In order to track targets in complex environment and improve identification ability,the algorithm must be simple and efficient for improving response speed and achieving real-time processing.There are many difficult problem for moving target detection in theory and application.Many scholars have been researched on it and have been gotten massive success.Based on the success,moving target detection is researched.The main work of this paper is as followings:(1) used the auto-adapted value filter algorithm to carry on the pretreatment to the image, the elimination noise;(2) proposed a suppression luminous intensity change movement goal examination algorithm, this algorithm has solved background questions well and so on model extraction, renewal, background perturbation, outside illumination change.(3) pair divides the movement goal has removed the shadow part reasonably;The experiment indicated, this article introduced in the video frequency supervisory system movement goal examination method speed is quick, suits the application in the real time system, compatible and antijamming ability, can carry on the normal work under the different environment, the recognition rate is high, can carry on the application in reality.