基于运动跟踪的动态手势识别算法分析-analysis of dynamic gesture recognition algorithm based on motion tracking.docxVIP

AbstractVision-based gesture recognition is a main research direction in human-computer interaction field. First, a camera captures the users gesture image sequence, and then the image sequence will be processed and analyzed. Finally, the users gestures will be changed into mouse or keyboard events which are comprehensible to the application program. Compared with the traditional human-computer interaction mode, the new interaction mode to control computer by using hand gestures can bring better user experience.This paper studies and realizes dynamic gesture recognition algorithm which is based on motion tracking. In this paper, the writer proposes an adaptive color segmentation algorithm. Specifically, at first it obtains natural complexion sample set and complexion sample set under illumination change through face detection. Then the color distribution histogram of these samples will be calculated and merged. Meanwhile, on the basis of the histogram distribution, the range of color segmentation will be shown. The writer proposes a real-time compression gesture-tracking algorithm, it gives the corresponding weight to the characteristic rectangle frames according to their regional position. By using Kalman filter, it can predict the position of tracking targets in next frame, and then search for the tracking targets around the predicted position. Some candidate samples will then be filtered based on complexion coverage area in the rectangle frame. Finally, the mapping of both operation space and display space are implemented, which makes it possible to control mouse movement by using gestures motion, and it also implements the recognition of some usual dynamic gestures based on an idea of mouse touch.The experimental result shows that the selfadaptive skin clolr segmentaiton algorithm in this thesis is more adaptable to different races or illumination than other existing methods; the modified tracing algorithm is more precise and more robust than the original algori