基于帧差能量图行质量向量的步态识别算法

doi:10.11772/j.issn.1001-9081.2014.05.1364

计算机应用 ›› 2014, Vol. 34 ›› Issue (5): 1364-1368.DOI: 10.11772/j.issn.1001-9081.2014.05.1364

基于帧差能量图行质量向量的步态识别算法

李锐,陈勇,余磊

重庆师范大学计算机与信息科学学院，重庆 401331

收稿日期:2013-11-14 修回日期:2013-12-12 发布日期:2014-05-30 出版日期:2014-05-01
通讯作者: 陈勇
作者简介:李锐(1984-),女,河南泌阳人,硕士研究生,主要研究方向：数字图像处理；陈勇(1971-)，男，重庆巴南人，副教授，博士，主要研究方向：信息安全、数字图像处理、智能计算；余磊(1980-)，男，湖南岳阳人，副教授，博士，主要研究方向：模式识别、图像处理、机器学习。
基金资助:
国家自然科学基金资助项目;重庆市教委基金资助项目;重庆市教委科技项目

Gait recognition based on row mass vector of frame difference energy image

LI Rui,CHEN Yong,YU Lei

College of Computer and Information Science, Chongqing Normal University, Chongqing 401331, China

Received:2013-11-14 Revised:2013-12-12 Online:2014-05-30 Published:2014-05-01
Contact: CHEN Yong
Supported by:
National Natural Science Foundation;The Science and Technology Project Affiliated to the Education Department of Chongqing

摘要/Abstract

摘要：

为了有效地捕捉步态的连续性动态信息，快速进行身份认证和识别，提出一种以帧差能量图（FDEI）的行质量向量作为步态特征的步态识别方法。该算法通过目标检测、二值化、形态学处理、连通性分析等预处理后得到步态轮廓图像，并利用其序列的宽度进行准周期性分析，再用连续隐马尔可夫模型(CHMM)对所提取的步态帧差能量图行质量向量进行模型参数训练和识别。在CASIA数据库上进行了仿真实验，结果表明该算法具有特征提取简单、特征维数低、识别速度快和识别率高的优点，可以满足实时识别的需要。

Abstract:

To effectively capture the dynamic information of the gait and accelerate the authentication and identification, a novel gait recognition algorithm was presented in this paper, which employed the row mass vector of the Frame Difference Energy Image (FDEI) as the gait features. The gait contour images were extracted through the object detection, binarization, morphological process and connectivity analysis of the original images. Using the width of the contour images sequence, the quasi-periodicity analysis and the row mass vector of the frame difference image were obtained, then the Continuous Hidden Markov Model (CHMM) was employed to train and recognize the parameters of model. The proposed algorithm was applied to Central Asia Student International Academic (CASIA) gait database. The experimental results show that it can easily extract the features of the gait with low dimension, achieving fast recognition speed and high recognition rate, so it can be used for real-time gait recognition.

中图分类号:

TP391

李锐陈勇余磊. 基于帧差能量图行质量向量的步态识别算法[J]. 计算机应用, 2014, 34(5): 1364-1368.

LI Rui CHEN Yong YU Lei. Gait recognition based on row mass vector of frame difference energy image[J]. Journal of Computer Applications, 2014, 34(5): 1364-1368.

参考文献

［1］BEN X, XU S, WANG K. Review on pedestrian gait feature expression and recognition ［J］. Pattern Recognition and Artificial Intelligence, 2012,25(1):71-81.(贲晛烨,徐森,王科俊.行人步态的特征表达及识别综述［J］.模式识别与人工智能,2012,25(1):71-81.)
［2］CHAI Y, XIA T, HAN W, et al. State-of-the-art on gait recognition ［J］. Computer Science, 2012,39(6):10-15.(柴艳妹,夏天,韩文英,等.步态识别研究进展［J］.计算机科学,2012,39(6):10-15.)
［3］LI Y, JIANG T, QIAO Z, et al. General methods and development actuality of gait recognition ［C］// ICWAPR '07: International Conference on Wavelet Analysis and Pattern Recognition. Piscataway: IEEE Press, 2007,3:1333-1340.
［4］WANG L, TAN L, NING H, et al. Silhouette analysis-based gait recognition for human identification ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003,25(12):1505-1518.
［5］WANG L, TAN T, HU W, et al. Automatic gait recognition based on statistical shape analysis ［J］. IEEE Transactions on Image Processing, 2003,12(9):1120-1131.
［6］HAN J, BHANU B. Individual recognition using gait energy image ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006,28(2):316-322.
［7］CHEN C, LIANG J, ZHAO H, et al. Frame difference energy image for gait recognition with incomplete silhouettes ［J］. Pattern Recognition Letters, 2009,30(11):977-984.
［8］WANG K, BEN X, MENG W, et al. The gait recognition algorithm based on generalized principal component analysis research ［J］. Journal of Harbin Engineering University, 2009,30(9):1022-1028.(王科俊,贲晛烨,孟玮,等.基于广义主成分分析的步态识别算法研究［J］.哈尔滨工程大学学报,2009,30(9): 1022-1028.)
［9］WANG K, LIU L, BEN X, et al. Gait recognition algorithm based on gait energy images and two-dimensional principal component analysis ［J］. Journal of Image and Graphics, 2009,14(12):2503-2509. (王科俊,刘丽丽,贲晛烨,等.基于步态能量图像和2维主成分分析的步态识别方法［J］.中国图象图形学报,2009,14(12):2503-2509.)
［10］YOON B J, VAIDYANATHAN P P. Context-sensitive hidden Markov models for modeling long-range dependencies in symbol sequenees ［J］. IEEE Transactions on Signal Processing, 2006,54(11):4169-4184.
［11］HONG S, LEE H, NIZAMI I F, et al. A new gait representation for human identification: mass vector ［C］ // Proceedings of the 2007 2nd IEEE Conference on Industrial Electronics and Applications. Piscataway: IEEE Press, 2007:669-673.
［12］KALE A, SUNDARESAN A, RAJAGOPALAN A N, et al. Identification of humans using gait ［J］. IEEE Transactions on Image Processing, 2004,13(9):1163-1173.
［13］LI H. Statistical learning methods ［M］. Beijing: Tsinghua University Press, 2012.(李航.统计学习方法［M］.北京:清华大学出版社,2012.)
［14］BILMES J A. A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models ［R/OL］. ［2013-04-12］. http://melodi.ee.washington.edu/people/bilmes/mypapers/em.pdf.

[1]	张佳慧李晓明张嘉祥. 强化形态感知的路面缺陷检测算法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[2]	杨建锋陈斌李雨轩. 基于点云重构的自监督点云异常检测方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[3]	薛振华李强黄超. 视觉大模型驱动的像素级图像异常检测模型[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[4]	蒋畅江向杰何旭颖. 面向机械臂抓取的双目视觉目标定位算法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[5]	边小勇胡其仁袁培洋. 多注意力对比学习的红外小目标检测[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[6]	李钟华钟庚辛范萍朱恒亮. 通过边界挖掘和背景引导的伪装目标检测[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[7]	吴松霖张广朝姚远彭博. 基于判别区域引导的多视图困难气道识别[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[8]	李强白少雄熊源袁薇. 基于视觉大模型隐私保护的监控图像定位[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[9]	薛雅丽徐忠敏刘世豪. 基于多级小波残差网络的重力数据去噪方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[10]	况世雄姚俊波陆佳炜王琪冰肖刚. 基于动态图卷积网络的电梯乘客异常行为数据增强方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[11]	康斌陈斌王俊杰李昱林赵军智咸伟志. 基于多粒度共享语义中心关联的文本到人物检索方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[12]	张庆杨凡方宇涵. 基于多模态信息融合的中文拼写纠错算法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[13]	王昊王金伟程鑫张家伟吴昊罗向阳马宾. 彩色图像JPEG重压缩取证综述[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[14]	王磊胡节彭博. 用于半监督火灾检测的分布自适应和动态课程伪标签框架[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[15]	刘晋文王磊马博董瑞杨雅婷艾合塔木江·艾合麦提王欣乐. 基于弱监督模态语义增强的多模态有害信息检测方法 [J]. 《计算机应用》唯一官方网站, 0, (): 0-0.

基于帧差能量图行质量向量的步态识别算法

Gait recognition based on row mass vector of frame difference energy image

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics