The Application Study Of Non-rigid Motion Model In Gait Detection

With the fast development of city traffic, brake machine is one of the key equipments of city track traffic Automatic Fare Collection system . intellectual recognition system of brake machine require the non- contact type long-distance range the status recognition. gait discerns is a new developing field in biological pattern-recognition, human gait has a lot of advantages to other biological characteristics , one of the most outstanding points can still be perceived in remote cases.In this paper,we study a new approach for feature points correspondence in non-rigid image sequences. This new approach is applied in gait recognition ,and we havewrriten the code. Human wear the dark dress and paste white round paper on joint in the course of collection image sequence at first, . small round central point of spot can be as feature point.According to the very short time interval between consecutive frames in image sequences,the paper points out that the motion of feature points is smooth, and a cost function describes the smooth degree of motion feature points is presented.Then the object tracking technique is introduced into the tracking of feature points,using two 1D Kalman filter to track the two coordinates of feature points. The occlusion problem can be solved by the position prediction in the process of the tracking of feature points.Results show the approach can establish correct correspondence of feature points and can solve the problem of occlusion.In this paper, we give a brief instruction on the vision analysis of people motion and new developing gait recognition at first; explain characteristic algorithm in gait recognition that we study; introduce the theory knowledge used in algorithms; design the example of calculating finally, and analyse the outputs of result ;draw the curve. We have summarized and summed up the factor of influencing smooth degree in the course to the algorithm.