人体运动分割算法:序列局部弯曲的流形学习

Human Motion Segmentation Algorithm:Manifold Learning of Sequence Local Warp

针对已有的基于流形学习的分割算法多采取全局或局部线性化的学习策略,无法解决序列数据的局部高曲率问题,利用数据的几何特征描述运动的连贯性,提出一种时序流形学习的人体运动分割方法.该方法根据序列数据的局部弯曲指标描述人体运动的连贯性,利用过渡片段数据局部弯曲较大的特点寻找分割点;通过滤波技术及分段线性近似算法对局部弯曲指标数据进行处理,结合降维后的特征曲线实现人体运动时间序列的分割.对CMU人体运动捕获数据库等的实验结果表明,文中方法是有效的.

Most of segmentation methods based on manifold learning utilize globally or locally linear strategies. However, these linear strategies can not cope with the high curvature structure of sequence dataset. Considering the continuity of human motion and the local high curvature in human motion sequence, a segmentation method using manifold learning is proposed to deal with the segmentation problem in this paper. The method evaluates the coherence of human motion based on the local warp index of sequence data. As the transition clips between the certain adjacent motion units warp largely, the filtering technique as well as the piecewise linear representation is applied to deal with the motion sequence. The experimental results show that the proposed method combined with the characteristic curves of the dimensionality reduction is effective to the segmentation of the CMU human motion datasets etc..