摘要
借鉴人类视觉感知所具有的多尺度、多分辨性的特性,针对智能视频监控系统的人体运动行为识别,提出了一种基于多尺度特征的双层隐马尔可夫模型.根据人体行为关键姿态数确定HMM的状态数目,发掘人体运动行为隐藏的多尺度结构间的关系,将运动轨迹和人体姿态边缘小波矩2个不同尺度特征应用于2层HMM,提供更为丰富的行为尺度间的相关信息.分别用Weizmann人体行为数据库和自行拍摄的室内视频,对人体运动行为识别进行仿真实验,结果表明,五状态HMM模型更符合人体运动行为特点,基于多尺度特征的五状态双层隐马尔可夫模型具有较高的识别率.
Learning from multi-scale and multi-distinguish attributes of human beings＇ visual perception and aiming at human movement behavior recognition in intelligent video surveillance system,a double-layer hidden markov model（DL-HMM） is developed based on multi-scale behavior features.Considering the human behavior characteristics,the number of HMM states is according to the number of key gestures selected.Discovering the relationship between the multi-scale structures hidden in the human movement behavior,two different scale features-human motion trajectory and wavelet moment of human gesture＇s edge,are applied respectively in two layers of DL-HMM,so as to provide more scale information about behavior.Experiments,using Israel Weizmann human behavior database and human actions indoor recorded by ourselves,show the five-state HMM more accords with the human motion behavior characteristics,and the five-state DL-HMM based on multi-scale feature has a higher recognition rate compared with traditional methods using one layer HMM.
出处
《智能系统学报》
北大核心
2012年第6期512-517,共6页
CAAI Transactions on Intelligent Systems
基金
江苏省高校自然科学基金资助项目(09KJB510002)
江苏省博士后科研资助计划资助项目(1001027B)
南京工业大学青年学科基金资助项目(39710006)
关键词
双层隐马尔可夫模型
行为识别
多尺度特征
智能视频监控
double-layer HMM（DL-HMM）
behavior recognition
multi-scale feature
intelligent video surveillance
