SVM-HMM Based Human Behavior Recognition

摘要：

　　In the field of human behavior recognition,a GMM-HMM system shows lower classification performance in short image sequences.The SVM-HMM,which has been successfully used in speech recognition,is introduced into behavior recognition in this paper.As one of the discriminate models,SVM is able to use less training samples to distinguish the differences of categories than GMM.Therefore,the part of GMM in the GMM-HMM system is replaced by SVM.The experimental results show that the SVM-HMM system achieves better performance for both short and long image sequences.

关键词： human behavior recognition support vector machine hidden markov model hybrid model

作者: Shanshan Han Minfei Zhang Penglin Li Jinjie Yao

作者单位: College of computer science and Technology,Zhejiang University of Technology,Hangzhou,China

会议类型: 国际会议

会议名称: The 9th International Conference on Pervasive Computing and Application(ICPCA 2014)(第九届全国普适计算学术会议、第九届全国人机交互联合学术会议)

会议地点: 南昌

会议语种:英文

页码: 1-12

在线出版日期: 2013-09-26（万方平台首次上网日期，不代表论文的发表时间）