Research On The Relative Technology Of Moving Object Detection In Intelligent Video Surveillance

Intelligent video surveillance is an emerging research direction in the field of computer vision. It focuses on how to describe, analysis and understand the contents of the surveillance video by using image and video processing technology and artificial intelligence techniques.Then it can control the video surveillance system according to the analysis results, making the video surveillance system have a higher level intelligence.The main research content of this paper is the detection method of moving targets in intelligent video surveillance. Aiming at the problems of the illumination change, complex background and shadow in the traditional target detecting methods, a novel algorithm which combines mixture Gaussian background models with edge detection and continuous frame difference, moving object detection method. In the method, background model was set up and updated through GMM on the time domain. Then the mixture method includes edge detection,continuous frame difference and mixture Gaussian background models was used to get the preliminary target, and perform further operation,to extract the final moving object. The method not only can satisfy the illumination changes and background scene disturbance, but also can overcome the problems of object detection inaccuracy, lacking of edge, empty of target and double-shadow phenomenon existing in common methods. The experimental results show that the method is easy to implement, has good real-time performance and robustness, and can detect the moving targets accurately.Moving object detection is an important part in intelligent video surveillance; otherwise,the detection of moving target’s shadow is also an important step in moving object detection.On the accuracy of shadow detection will affect the detection results of the object directly.Based on the variety of shadow detection method, we find that only using one feature can not make the result of detection accurately. Then we present a new method for shadow detection which contains color information, the invariance of optical and texture feature. Through the comprehensive analysis of the detecting results of three kinds of information, the shadow was effective determined. It gets ideal effect in the experiment when combining advantages of various methods.