一种姿态无关的人体模型骨骼提取方法_于勇.pdfVIP

ISSNN 111777TP Journal of Computer Research and Development 5( 7) : 12 9 1258, 2008 1, 2, 3 1, 2 1, 2 1, 2, 3 于 勇 王兆其 夏时洪 毛天露 1 ( 100190) 2 ( 100190) 3 ( 1000 9) ( yyu@ ict. ac. cn) PoseIndependent Joint Extraction from Scanned Human Body 1, 2, 3 1, 2 1, 2 1, 2, 3 Yu Yong , Wang Zhaoqi , Xia Shihong , and M ao T ianlu 1 ( Vir tual R eality L abor atory , I nstitute of Comp uting T echnology , Chinese A cademy of Sciences , Beij ing 100190 2 ( K ey Labor atory of I ntelligent I nf ormation Pr ocess ing , I nstitute of Comp uting T echnology , Chinese A cademy of Sciences , Beij ing 100190 3 ( Gr ad uate Univers ity of Chines e A cademy of Sciences , Beij ing 1000 9 Abstract W ith the development of 3D scanning technique, joint extraction from scanned human body model is one of the most active research areas in virtual human modeling . Many different approaches have been proposed w ith the aim of extracting joints from scanned human body . But most of these methods can not guarantee poseindependence, w hile other methods w hich can ensure pose independence require manual intervention. To solve this problem, a new framew ork is presented for automatic poseindependent joint extraction from scanned human body . Firstly, a new Morse function is defined on the scanned human body shape as geodesic distance from points to a source point w hich can be extracted by a heuristic method. Secondly, the Morse function is calculated, and then feature points and topological structure of the model shape can be extracted automatically according to Morse theory. Finally, shape is divided into segments based on Morse function isolines, and joints can be extracted from the corre