Human motion synthesis using window-based local principal component analysis

摘要：

This paper introduces an approach to performance ani- mation that uses window-based local principal component analysis (WLPCA). Our key idea is to construct a series of online window-based local models from a prerecorded motion database and utilize them to construct full-body human motion in a maximum a posteriori frame work (MAP). We have demonstrated the effectiveness of our approach by synthesizing a variety of human actions, such as walking, running, jumping, golf swinging and boxing. Given an appropriate motion capture database, the results are comparable in quality to the ground truth data. We have also evaluated the performance of our approach by leave-one-out experiments and by comparing to two baseline algorithms.

会议类型: 国际会议

会议名称: 2011国际计算机辅助设计与图形学学术会议(CAD/Graphics 2011)

会议地点: 济南

会议语种:英文

页码: 1-7

在线出版日期: 2011-09-15（万方平台首次上网日期，不代表论文的发表时间）