Human Flow Statistic Algorithm Research Based On Stereo Vision

Along with the rapid development of economy,there are more and more large-scale activities take place in the city,and business competition becomes more and more incandescent.So the human flow statistic system which can offer the accurate human flow information to the security and business plan departments becomes hotspot of the research area.Simultaneously,binocular vision also becoming a research hotspot of the computer vision domain,and it also is widely applied in many domains.This paper studied on the most basic theory and algorithm in stereo vision,including camera calibration,stereo matching and so on,based on Marr visual computing theory.Stereo vision principle is also applied to targets detection and tracking areas,in order to implement the difficult function for the monocular vision system,and to build a human flow statistical system with high accuracy and strong real-time.The contributions are summarized as follows:1.This article referenced substantial domestic and foreign literature, in-depth study of the stereo vision camera calibration problem,and presented a new calibration plane based on genetic algorithm. Experiments show that this method is simple,high precision.2.In this paper focused on stereo matching algorithm which is the most basic issue in stereo vision,introduced the basic theory of stereo matching algorithm.And we presented an improved stereo matching algorithm based on SMP(single matching phase).3.We proposed a novel detection method based on stereo vision. First of all,it adopted a mixed Gaussian model of background modeling, and can get foreground for detection of the target area;then layered disparity algorithm used to extract the outline of the various levels of objectives.4.We proposed A Kalman-based prediction of multi-target tracking methods.This method is the use of Kalman filtering method to predict the location of objects,so as to achieve the purpose of multi-target tracking.5.This article constructed a human flow statistical systems Based on the above algorithm.Many experiments proved that the system has high accuracy and good anti-interference ability.