<-上一篇/Previous Article 下一篇/Next Article->

[1]高海燕,阮秋琦.正面视角的步态识别[J].智能系统学报,2011,6(2):119-125.
　GAO Haiyan,RUAN Qiuqi.A gait recognition method based on frontview[J].CAAI Transactions on Intelligent Systems,2011,6(2):119-125.

点击复制

正面视角的步态识别

PDF下载 HTML

《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷: 6 期数: 2011年第2期页码: 119-125 栏目: 学术论文—机器感知与模式识别出版日期: 2011-04-25

Title:: A gait recognition method based on frontview

文章编号:: 1673-4785(2011)02-0119-07

作者:: 高海燕，阮秋琦; 北京交通大学信息科学研究所，北京 100044

Author(s):: GAO Haiyan, RUAN Qiuqi; Institute of Information Science, Beijing Jiaotong University, Beijing 100044, China

关键词:: 步态识别; 正面视角; 去除阴影; 傅里叶描述子; 步态模板

Keywords:: gait recognition; frontview; shadow removal; Fourier descriptors; gait template

分类号:: TP391.4

文献标志码:: A

摘要:: 现有的步态识别算法研究几乎全都是基于侧面步态的.提出一种基于正面视角的步态识别方法.首先归一化RGB颜色空间被用来检测和去除阴影，并用背景减除法提取二值化人体轮廓.提出一种专门适用于正面步态的周期检测方法，提取周期关键帧后跟踪轮廓线，并用改进的等角度采样法进行采样以减少计算量.简单高效的傅里叶描述子被用来提取特征向量，进行数据降维后构造步态模板.用最近邻和最近邻标本分类器分别进行分类.在CASIA数据库上的实验表明，该算法不仅具有较低的计算量而且表现出较好的识别性能.

Abstract:: Existing gait recognition methods are usually based on side view sequences; however, in this paper a new method for frontview gait recognition was proposed. First, a method of normalized RGB color space was used for detection and shadow removal and the binary silhouettes were extracted by background subtraction. Then, a special method for cyclic gait analysis based on a front view was performed to extract cyclic key frames. Next, body contours were tracked, and an improved equalangle sampling method was applied to reduce the number of computations. Next, the feature vectors were extracted efficiently. Fourier descriptors as data dimension were reduced, allowing the gait template vectors to be constructed. Finally, recognition was achieved separately by the nearest neighbor classifier NN and the nearest neighbor classifier with respect to the template ENN. Experimental results show that the proposed approach is not only efficient in computing, but also has an encouraging recognition performance in the CASIA database. 

参考文献/References:: ［1］JOHANNSON G. Visual perception of biological motion and a model for its analysis［J］. Perception Psychology, 1973, 14: 201211.
［2］NIYOGI S A, ADELSON E H. Analyzing and recognizing walking figures in XYT［J］//MIT Media Lab Vision and Modeling Group,223.
［3］CUNADO D, NIXON M, CATER J. Using gait as a biometric, via phaseweighted magnitude spectra［C］//Proc International Conference on Audioand Videobased Biometric Person Authentication. CransMontana, Switzerland, 1997: 95102.
［4］LEE L, GRIMSON W. Gait analysis for recognition and classification［C］//Proceedings of Fifth IEEE International Conference on Automatic Face and Gesture Recognition. Washington， DC, USA, 2002: 148155.
［5］YOO J H, NIXON M, HARRIS C J. Extracting human gait signatures by body segment properties［C］//IEEE Southwest Symposium on Image Analysis and Interpretation. Sante Fe, USA, 2002: 3539.
［6］KALE A, SUNDARESAN A, RAJAGOPALAN A, et al. Identification of humans using gait［J］. IEEE Transactions on Image Processing, 2004, 13(9): 11631173.
［7］LIU Z, SARKAR S. Simplest representation yet for gait recognition: averaged silhouette［C］//Proc 17th International Conference of Pattern Recognition. Tampa, USA, 2004, 4: 211214.
［8］YANG X, ZHOU Y, ZHANG T, et al. Gabor phase based gait recognition［J］. Electronics Letters, 2008, 44(10): 620621.
［9］张元元，吴晓娟，李秀媛,等．平行线约束下的视角无关步态识别算法［J］．智能系统学报， 2009， 4(3): 264269.
ZHANG Yuanyuan, WU Xiaojuan, LI Xiuyuan, et al. Viewpointindependent gait recognition with parallel line constraints［J］. CAAI Transactions on Intelligent Systems, 2009, 4(3): 264269.
［10］王亮，胡卫明，谭铁牛. 基于步态的身份识别［J］. 计算机学报， 2003， 26(3): 353360.
WANG Liang, HU Weiming, TAN Tieniu. Gaitbased human identification［J］. Chinese Journal of Computers, 2003, 26(3): 353360.
?［11］陈实. 基于计算机视觉的人体步态识别研究［D］. 西安：西安电子科技大学， 2008: 2025. CHEN Shi. Human gait recognition based computer vision［D］. Xi’an: Xidian University, 2008： 2025.
［12］WANG Aihua, LIU Jiwei. A gait recognition method based on positioning human body joints［C］//IEEE International Conference on Wavelet Analysis and Pattern Recognition. Beijing， 2007: 10671071.
［13］WANG Liang, TAN Tieniu, NING Huazhong, et al. Silhouette analysisbased gait recognition for human identification［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2003, 25(12): 15052528.
［14］李彬. 基于步态特征的身份识别研究［D］. 北京：北京科技大学， 2004: 3135. LI Bin. Study on gaitbased human identification［D］. Beijing： University of Science & Technology Beijing, 2004: 3135.
［15］韩鸿哲，李彬，王志良,等. 基于傅立叶描述子的步态识别［J］. 计算机工程， 2005， 31(2): 4849.
HAN Hongzhe, LI Bin, WANG Zhiliang, et al. Gait recognition based on Fourier descriptors［J］. Computer Engineering, 2005, 31(2): 4849.

相似文献/References:: [1]张元元,吴晓娟,李秀媛,等.平行线约束下的视角无关步态识别算法[J].智能系统学报,2009,4(3):264.
　ZHANG Yuan-yuan,WU Xiao-juan,LI Xiu-yuan,et al.Viewpointindependent gait recognition with parallel line constraints[J].CAAI Transactions on Intelligent Systems,2009,4():264.
[2]王科俊,贲晛烨,刘丽丽.采用Radon变换和二维主成分分析的步态识别算法[J].智能系统学报,2010,5(3):266.
　WANG Ke-jun,BEN Xian-ye,LIU Li-li.Gait recognition with Radon transform and D principal component analysis[J].CAAI Transactions on Intelligent Systems,2010,5():266.
[3]贲晛烨,王科俊,刘海洋.核方法的对比研究及在步态识别中的应用[J].智能系统学报,2011,6(1):63.
　BEN Xianye,WANG Kejun,LIU Haiyang.A comparative study on kernel methods and their applications to gait recognition[J].CAAI Transactions on Intelligent Systems,2011,6():63.
[4]杨静,阮秋琦,李小利.基于频谱分析的Procrustes统计步态识别算法[J].智能系统学报,2011,6(5):432.
　YANG Jing,RUAN Qiuqi,LI Xiaoli,et al.A Procrustes statistical gait recognition algorithm based on spectrum analysis[J].CAAI Transactions on Intelligent Systems,2011,6():432.
[5]贲晛烨,王科俊,马慧.视频下的正面人体身份自动识别[J].智能系统学报,2012,7(1):69.
　BEN Xianye,WANG Kejun,MA Hui.Videobased automatic frontview human identification[J].CAAI Transactions on Intelligent Systems,2012,7():69.
[6]李一波,李昆.双视角下多特征信息融合的步态识别[J].智能系统学报,2013,8(1):74.[doi:10.3969/j.issn.1673-4785.201209033]
　LI Yibo,LI Kun.Gait recognition based on dual view and multiple feature information fusion[J].CAAI Transactions on Intelligent Systems,2013,8():74.[doi:10.3969/j.issn.1673-4785.201209033]
[7]贲晛烨,张鹏,潘婷婷,等.线性插值框架下矩阵步态识别的性能分析[J].智能系统学报,2013,8(5):415.[doi:10.3969/j.issn.1673-4785.201110007]
　BEN Xianye,ZHANG Peng,PAN Tingting,et al.Performance analysis of matrix gait recognition under? linear interpolation framework[J].CAAI Transactions on Intelligent Systems,2013,8():415.[doi:10.3969/j.issn.1673-4785.201110007]

备注/Memo

收稿日期：2010-03-26.
基金项目：国家“973”计划资助项目(2004BC318005)；国家自然科学基金资助项目(60973060).
通信作者：高海燕.
?E-mail:hygao2010@163.com.
作者简介：高海燕，女，1985年生，硕士研究生，主要研究方向为图像处理、模式识别、步态识别.
阮秋琦，男，1944年生，教授，博士生导师，主要研究方向为图像处理、计算机视觉、模式识别、虚拟现实.曾多次获得省部级科技进步奖，发表学术论文350余篇，被SCI、EI、ISTP检索150余篇，出版专著4部.

更新日期/Last Update: 2011-05-19

正面视角的步态识别 PDF下载HTML

备注/Memo

正面视角的步态识别

PDF下载 HTML