信息与控制2013，Vol.42Issue(4)：457-463,7.DOI:10.3724/SP.J.1219.2013.00457
基于CRM的人体动作识别
Human Action Recognition Based on CRM
摘要
Abstract
A human action recognition algorithm based on continuous-space relevance model (CRM) is proposed.Firstly,the algorithm automatically extracts human joint position.The human silhouette is characterized by the skeleton graph which is matched by dynamic time wrapping (DTW).The similar skeleton graph is used to find the template silhouette similar to the silhouette of the target,and the joint point position of the template silhouette is used to estimate the joint point position of the target.Finally,human actions are characterized by human joint point trajectories and recognized by CRM.This algorithm has been trained and tested on KTH human motion data set,Weizmann human action data set and Ballet data set.The results show that the recognition accuracy of this algorithm is either comparable to or much better than other sophisticated probabilistic models.关键词
人体动作识别/人体关节点/连续空间关系模型(CRM)/动态时间规整(DTW)Key words
human action recognition/ human joint point/ continuous-space relevance model (CRM)/ dynamic time wrapping (DTW)分类
信息技术与安全科学引用本文复制引用
黄金霞,夏利民,张伟..基于CRM的人体动作识别[J].信息与控制,2013,42(4):457-463,7.基金项目
国家自然科学基金资助项目(50808025) （50808025）
国家教育部博士点基金资助项目(20090162110057) （20090162110057）
湖南省科技厅一般项目(2011GK3213). （2011GK3213）
