Motion Synthesis Based on Dimensionality Reduction

摘要：

In this paper we propose a method for human motion synthesis based on dimensionality reduction. The human motion can be considered as lying on a low dimensional intrinsic structure because of the coordination between the body parts, such as the arms and legs. Based on this assumption, new motion sequences can be generated from motion capture data by learning linear dynamic models of motion segments on the resulted space of dimensionality reduction. The synthesized motions are compared with the original motion, and good performance is observed.

关键词： human motion synthesis linear dynamic model dimensionality reduction

作者: Huiyang Qu Zhiwen Yu Xing Wang Hau-San Wong

作者单位: Department of Computer Science,City University of Hong Kong,China

会议类型: 国际会议

会议名称: The First IEEE International Conference on Ubi-Media Coputing and Workshops(第一届泛媒体处理国际会议)

会议地点: 兰州

会议语种:英文

在线出版日期: 2008-07-15（万方平台首次上网日期，不代表论文的发表时间）