基于局部熵描述子的步态性别识别方法
|
摘要
采用局部熵描述子对步态运动历史图像进行信息提取,提出一种新的步态性别识别方法。首先进行步态周期检测,得到包含一个周期的运动历史图像,然后以该图像中每个像素点为中心计算其邻域的信息熵,作为局部熵描述子特征。再利用主成分分析法进行降维处理。最后使用该特征在CASIA B步态数据库上进行了性别分类实验。实验结果表明:所提方法具有很好的性别识别效果,平均识别率优于基本的运动历史图像和步态能量图等方法。
A new gait gender recognition method is proposed by using local entropy descriptor to extract information from gait motion history image. First,gait period detection is carried out to obtain a motion history image containing a period,and then the information entropy of neighborhood is calculated taking each pixel point as center,as the local entropy descriptor feature. Then the principal component analysis method is used to reduce the dimension. Finally,the gender classification experiment is carried out on the CASIA B gait database using this feature. Experimental results show that this method has good gender recognition effect,and the average recognition rate is better than the methods based on basic motion history image and gait energy image.
A new gait gender recognition method is proposed by using local entropy descriptor to extract information from gait motion history image. First,gait period detection is carried out to obtain a motion history image containing a period,and then the information entropy of neighborhood is calculated taking each pixel point as center,as the local entropy descriptor feature. Then the principal component analysis method is used to reduce the dimension. Finally,the gender classification experiment is carried out on the CASIA B gait database using this feature. Experimental results show that this method has good gender recognition effect,and the average recognition rate is better than the methods based on basic motion history image and gait energy image.
引文
[1] LEE L,GRIMSON W. Gait analysis for recognition and classification[C]∥IEEE International Conference on Automatic Face and Gesture Recognition,IEEE,2002:148-155.
[2]李占利,崔磊磊,刘金瑄.基于协同表示的步态识别[J].计算机应用研究,2016,33(9):2878-2880.
[3]史东承,贾令尧,梁超,等.基于相位一致性改进的步态识别方法[J].计算机工程,2017,43(10):198-202.
[4]王阳.基于特征点匹配的步态识别[J].传感器与微系统,2018,37(1):137-140.
[5]赵喜玲,张晓惠.基于动态特征和静态特征融合的步态识别方法[J].湘潭大学自然科学学报,2017,39(4):89-91.
[6]崔雪红,刘云,常伟,等.基于HOG特征的步态能量图身份识别算法[J].电子测量技术,2017,40(7):100-104.
[7]李晶,张菁,倪军.基于修正步态能量图和视角检测的步态识别方法[J].计算机科学,2016,43(8):300-303.
[8] BASHIR K,XIANG T,GONG S. Gait recognition using gait entropy image[C]∥International Conference on Crime Detection and Prevention,IET,2010:1-6.
[9] JEEVAN M,JAIN N,HANMANDLU M,et al. Gait recognition based on gait pal and pal entropy image[C]∥IEEE International Conference on Image Processing,IEEE,2013:4195-4199.
[10] SHARMA S,SHUKLA A,TIWARI R,et al. View variations effect in gait recognition and performance improvement using fusion[C]∥International Conference on Recent Advances in Information Technology,IEEE,2012:892-896.
[11] KUSAKUNNIRAN W,WU Q,ZHANG J,et al. A new viewinvariant feature for cross-view gait recognition[J]. IEEE Transactions on Information Forensics and Security,2013,8(10):1642-1653.
[12] DAVIS W J. Hierarchical motion history images for recognizing human motion[C]∥IEEE Workshop on Detection and Recognition of Events in Video,IEEE,2001:39-46.
[13]刘磊,杨鹏,刘作军.采用多核相关向量机的人体步态识别[J].浙江大学学报:工学版,2017,51(3):562-571.
[2]李占利,崔磊磊,刘金瑄.基于协同表示的步态识别[J].计算机应用研究,2016,33(9):2878-2880.
[3]史东承,贾令尧,梁超,等.基于相位一致性改进的步态识别方法[J].计算机工程,2017,43(10):198-202.
[4]王阳.基于特征点匹配的步态识别[J].传感器与微系统,2018,37(1):137-140.
[5]赵喜玲,张晓惠.基于动态特征和静态特征融合的步态识别方法[J].湘潭大学自然科学学报,2017,39(4):89-91.
[6]崔雪红,刘云,常伟,等.基于HOG特征的步态能量图身份识别算法[J].电子测量技术,2017,40(7):100-104.
[7]李晶,张菁,倪军.基于修正步态能量图和视角检测的步态识别方法[J].计算机科学,2016,43(8):300-303.
[8] BASHIR K,XIANG T,GONG S. Gait recognition using gait entropy image[C]∥International Conference on Crime Detection and Prevention,IET,2010:1-6.
[9] JEEVAN M,JAIN N,HANMANDLU M,et al. Gait recognition based on gait pal and pal entropy image[C]∥IEEE International Conference on Image Processing,IEEE,2013:4195-4199.
[10] SHARMA S,SHUKLA A,TIWARI R,et al. View variations effect in gait recognition and performance improvement using fusion[C]∥International Conference on Recent Advances in Information Technology,IEEE,2012:892-896.
[11] KUSAKUNNIRAN W,WU Q,ZHANG J,et al. A new viewinvariant feature for cross-view gait recognition[J]. IEEE Transactions on Information Forensics and Security,2013,8(10):1642-1653.
[12] DAVIS W J. Hierarchical motion history images for recognizing human motion[C]∥IEEE Workshop on Detection and Recognition of Events in Video,IEEE,2001:39-46.
[13]刘磊,杨鹏,刘作军.采用多核相关向量机的人体步态识别[J].浙江大学学报:工学版,2017,51(3):562-571.