基于类Haar特征模板匹配的多镜头步态识别算法  

Multiple Lens Gait Recognition Algorithm Based on Category Haar Feature Template Matching

作　　者：刘冠群[1,2] 罗桂琼 谭平[2] 

机构地区：[1]湖南广播电视大学网络资源系,长沙410004 [2]中南大学信息科学与工程学院,长沙410083

出　　处：《计算机工程》2017年第12期231-236,共6页Computer Engineering

基　　金：湖南省教育科学"十二五"规划课题(XJK014BXX005)

摘　　要：针对视频监控中步态识别算法准确度较低的问题,提出一种双边傅里叶校正点估计类Haar特征模板匹配的多镜头步态识别算法。根据视频监控的特点,使用图像点估计重构算法,设计一种无标记类Haar特征模板匹配的步态特征提取算法,进行步态的自动识别与提取。对不同镜头视角下特征运动角度提取差异,基于双边傅里叶级数实现观测角度校正,并依据高维特征空间设计自适应顺序前进浮动选择的搜索算法。在Southampton测试库上的仿真结果表明,该算法步态正确分类率达到96.3%,能有效提高分类识别精度。Aiming at the problem of low accuracy for the gait recognition in video surveillance, the bilateral Fourier calibration point estimation category Haar feature template matching based multiple lens gait recognition algorithm is proposed. According to the characteristics of video monitoring, the point estimation algorithm is used for image reconstruction and a markerless Haar feature template matching based feature extraction algorithm is designed to realize the automatic recognition and extraction of gait feature. According to the angles difference of feature extraction in motion, the bilateral Fourier is used for observation angle correction, and the adaptive sequential forward selection is designed for high dimensional feature extraction. Simulation results in the classification rate of the proposed motion angle can reach basically algorithm can reach about 96.3 % the same in different gait cycles. Southampton test database show that the correct , and through the observation angle correction, the gait

关 键 词：点估计 HAAR特征 模板匹配 步态识别 双边傅里叶级数 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]