基于灰度标准差的光流模型的步态识别算法  

Human Gait Recognition by Optical Flow Model Based on Gray Standard Deviation

作　　者：李蓉[1] 周维柏[1] 

机构地区：[1]华南师范大学增城学院,广东广州511363

出　　处：《昆明理工大学学报（理工版）》2010年第5期66-69,74,共5页Journal of Kunming University of Science and Technology(Natural Science Edition)

基　　金：广东省本科高等教育教学改革项目(项目编号:BKJG200765)

摘　　要：步态识别主要是通过人体走路的姿势来识别人的身份.提出了一种改进的光流法和隐马可夫模型相结合的技术,使用背景减除和阈值化为目标和背景图像建立模型,由使用灰度标准差筛选的光流法模型提取每一个运动目标的特征,取得时间序列的特征向量,把特征量化和状态分类的结果交给隐马可夫模型来判断运动目标的姿态.仿真实验表明,本算法识别率高,速度快.Human gait recognition is the process of identifying individuals by their walking manners,which combines the technology of an improved optical flow method and hidden Markov model.A model of the objectives and background image is firstly established with the adoption of the background subtraction and threshold.The features of a moving target are then extracted by the optical flow model based on the gray standard deviation to obtain the feature vectors of each frame.Hidden Markov model is finally employed to determine the moving target＇s posture.It is shown through the simulation that the approach enjoys excellent performance with high recognition speed and accuracy.

关 键 词：光流法 隐马可夫 步态特征 步态识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]