基于连续隐马尔科夫模型的步态识别

Human gait recognition based on continuous HMM

步态识别主要是通过人体走路的姿势来识别人的身份,近来年,步态作为一种生物特征识别技术备受计算机视觉研究者的关注.给出了基于连续隐马尔科夫的步态识别方法:研究了静止背景下人体步态的检测以及基于步态的人体身份识别技术,主要包括背景建模、人体检测、轮廓特征提取及连续隐马尔科夫识别和分类.在小数据库上取得了超过95%的识别率;实验结果表明,本方法有效.

Human gait recognition is the process of identifying individuals by their walking manners. The gait as one of biometrics has recently drawn attention to the computer vision researchers. In the paper, a gait recognition algorithm based on Continuous HMM is proposed. Researches contain the human gait detection on the stationary background and gait_based human identification. This method mainly includes background subtraction, human identification, silhouette feature extraction and Continuous HMM recognition and classification. Over 95% of recognition rate is obtained from the small database .The experimental result demonstrates that this method is effective.