%0 Journal Article
%T Human gait recognition based on bilinear modeling and HMM<br>基于双线性建模及隐马尔可夫模型的步态识别算法
%A YUAN Qi
%A ZHAO Rong-chun
%A <br>袁琪
%A 赵荣椿
%J 计算机应用
%D 2007
%I 
%X Motivated by bi-factor-invariant human gait recognition problem,a new gait recognition algorithm was proposed in which two factors,generically called "style" and "content" were analyzed and manipulated.First,image sequences were clustered into a fixed number of content with fixed dynamics HMM-EM algorithm.Then the observation data were generated according to an asymmetric bilinear model.After that,SVD and NN were used to classify new sequences characterized by a different style label.Body width between vertical line through centroid and outer contour was used as the feature.Test on the CASIA datasets shows the proposed method's advantage in increasing the recognition rate and adapting to new styles or content.Some other facts affecting ID identification were also discussed.
%K asymmetric bilinear modeling
%K Expectation-Maximization (EM)
%K Hidden Markov Model (HMM) modeling<br>非对称双线性建模
%K 期望值最大化
%K 隐马尔可夫模型
%K 线性建模
%K 隐马尔可夫模型
%K 步态识别算法
%K modeling
%K bilinear
%K based
%K recognition
%K gait
%K 因素
%K 影响
%K 适应性
%K 判断
%K 内容类型
%K 判别率
%K 验证
%K 步态特征
%K 距离
%K 垂线
%K 质心
%K 轮廓
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=831E194C147C78FAAFCC50BC7ADD1732&aid=F777D43F2DA692EDBCFFDA3DF04A7235&yid=A732AF04DDA03BB3&vid=DB817633AA4F79B9&iid=E158A972A605785F&sid=547650636788ED84&eid=F3FF3E69C64937E9&journal_id=1001-9081&journal_name=计算机应用&referenced_num=0&reference_num=21