A Method Of Motion Capture From The Multi-view Video Sequence
This paper proposes a method of motion capture using joint skeleton tracking and surface estimation from the multi-view video sequence, which can capture the performance of a human or an animal. Given an articulated template model and silhouettes from a multi-view image sequence, our approach recovers not only the movement of the skeleton, but also the possibly non-rigid temporal deformation of the 3D surface. While large scale deformations or fast movements are captured by the skeleton pose and approximate surface skinning, true small scale deformations or are captured by fitting the surface to the silhouette. We further propose a novel optimization scheme for skeleton-based pose estimation that exploits the skeletons tree structure to split the optimization problem into a local one and a lower dimensional global one. We show on various sequences that our approach can capture the 3D motion of animals and humans accurately even in the case of rapid movements and wide apparel.
Motion capture Multi-view Skeleton-based Pose estimation Surface Estimation
Hui-Xiang XU SU YU Zhi-Hong Yang Zhi-Chao LI
Department of Information EngineeringZhongZhou Universityzhengzhou , Henan, 450044, China Department of Information EngineeringZhongZhou Universityzhengzhou , Henan, 450044, Chin Department of Information Engineering ZhongZhou University zhengzhou , Henan, 450044, China
国际会议
成都
英文
1-4
2010-08-20（万方平台首次上网日期，不代表论文的发表时间）