| Video human motion analysis is an important research area which combines computer vision and graphics techniques. The focus of the research is in detecting and tracking figures in monocular or multicular videos, capturing and reconstructing the human motion, and then describing and interpreting the human behavior. This research has various applications in human animation, computer game, virtual reality and augmented reality, human-computer interaction, video surveillance, sports video analysis, computer-aided clinical diagnosis, and so on.This thesis focuses on the technology of tracking human motion, capturing two dimensional human motion and reconstructing three dimensional human in monocular videos. This work investigates on tracking and tectcting images, getting three dimensional human motion, reconstructing the three dimensional human skeleton sequence. So we can study the technology and rules of human motion. This thesis is anticipated to help obtain the abundant motion data from plenty of videos including movie, TV and sportsvideos, and enable the myriad activities of human created in virtual world.On the basis of sufficient review to the related works, the work in the thesis makes some main contributions in the field:(1) Giving a human motion model for capturing suitable for monocular videos: Mainly introduce the basic contents and methods of human motion gesture analysis and construction.(2) The article implements calibration of the camera based on OpenCV instead of traditional ways. The method ascertains the corner points and their coornidates on the calibration template automaticly and has a good precision.(3) Tracking and detecting the area of human motion by the way of background deduction with gaussian model.(4) All human's joints need to be marked with homemade marks, then computing barycenter coordinates of all the marked-points, finally reconstructing the three-dimension human motion skeleton sequence under the perspective projection. |
PDF Full Text Request