[1]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(05):415-425.[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(05):415-425.[doi:10.3969/j.issn.1673-4785.201110007]
点击复制

线性插值框架下矩阵步态识别的性能分析(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第8卷
期数:
2013年05期
页码:
415-425
栏目:
出版日期:
2013-10-25

文章信息/Info

Title:
Performance analysis of matrix gait recognition under  linear interpolation framework
文章编号:
1673-4785(2013)05-0415-11
作者:
贲晛烨1张鹏1潘婷婷1王科俊2
1.山东大学 信息科学与工程学院,山东 济南 250100; 2.哈尔滨工程大学 自动化学院,黑龙江 哈尔滨 150001
Author(s):
BEN Xianye 1 ZHANG Peng 1 PAN Tingting 1 WANG Kejun 2
1. School of Information Science and Engineering, Shandong University, Ji’nan 250100, China; 2. College of Automation, Harbin Engineering University, Harbin 150001, China
关键词:
步态识别矩阵步态识别线性插值框架步态周期检测Zernike矩伪Zernike矩
Keywords:
gait recognition matrix gait recognition linear interpolation framework gait period detection Zernike moment pseudoZernike moment
分类号:
TP391.41
DOI:
10.3969/j.issn.1673-4785.201110007
文献标志码:
A
摘要:
针对现有的步态周期检测方法检测效果不佳以及行走速度变化对步态识别性能有很大影响的问题,提出的基于矩的步态周期检测方法中,Zernike矩需要人体居中、尺度归一的前期预处理过程,而伪Zernike矩具有能描述运动图像的特点,它可以避免人体居中、尺度归一等处理,以便直接测试步态的周期性.根据行走时的两帧之间的特征取决于前一帧和后一帧的特征,提出了基于线性插值的矩阵步态识别算法框架,并且将投影特征、Hough变换特征、Trace变换特征和Fan-Beam映射特征应用在CASIA(B)步态库上,验证了框架的有效性,为解决步态识别问题带来新的方法与思路.这种基于线性插值的矩阵步态识别特征本质上是一种权值不同的能量形式.
Abstract:
The existing gait period detection methods are not ideal and the performance of gait recognition is significantly influenced by walking speed. Several novel gait period detection methods based on moments are proposed in this paper. The Zernike moment requires preprocessing including the assurance that the image of the human body is proportioned normally and is centered properly; the pseudo-Zernike moment may directly describe the motion image, and it may avoid the need for such processing of making the image of the human body centered and sized normally, so as to directly detect gait periodicity. As the features of one frame are only decided by those of the prior and the rear frames in walking, a framework for a matrix gait recognition algorithm based on linear interpolation is proposed. Subsequently, the projection features, Hough transform feature, Trace transform feature and Fan-Beam mapping feature are applied to the CASIA(B) gait database to prove the validity of the gait recognition framework. This brings new methods and understanding for solving gait recognition problems. This matrix gait recognition feature based on linear interpolation is essentially an energy form with different weighted values.

参考文献/References:

[1]贲晛烨.基于人体运动分析的步态识别算法研究[D]. 哈尔滨:哈尔滨工程大学, 2010.
[2]NIXON M S, CARTER J N, SHUTLER J D, et al. New advances in automatic gait recognition[J]. Information Security Technical Report, 2002, 7(4): 23-35.
[3]BOULGOURIS N V, HATZINAKOS D, PLATANIOTIS K N. Gait recognition: a challenging signal processing technology for biometric identification[J]. IEEE Signal Processing Magazine, 2005, 22(6): 78-90.
[4]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.
        BEN Xianye, XU Sen, WANG Kejun. Review on pedestrian gait feature expression and recognition[J]. Pattern Recognition and Artificial Intelligence, 2012, 25(1): 71-81.
[5]BOULGOURIS N V, PLATANIOTIS K N, HATZINAKOS D. Gait recognition using dynamic time warping[C]//Proceedings of the Fourth IEEE International Symposium on Multimedia Signal Processing. Siena, Italy, 2004: 263-266.
[6]BOULGOURIS N V, PLATANIOTIS K N, HATZINAKOS D. Gait recognition using linear time normalization[J]. Pattern Recognition, 2006, 39(5): 969-979.
[7]TIAN Guangjian, HU Fuyuan, ZHAO Rongchun. Gait recognition based on Fourier descriptors[C]//Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing. Hong Kong, China, 2004: 29-32.[8]HONG S, LEE H, NIZAMI I F, et al. A new gait representation for human identification: mass vector[C]//Proceedings of the 2nd IEEE Conference on Industrial Electronics and Applications. Harbin, China. 2007: 669-673.[9]NANDINI C, RAVIKUMAR C N. An approach to gait recognition[C]//International Symposium on Biometrics and Security Technologies. Islamabad, Pakistan, 2008: 1-3.
[10]BENABDELKADER C, CUTLER R, DAVIS L. Motion-based recognition of people in EigenGait space[C]//Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition. Washington, DC, USA, 2002: 267-272.
[11]YU Shiqi, WANG Liang, HUANG Kaiqi, et al. Gait analysis for human identification in frequency domain[C]//Proceedings of the 3rd International Conference on Image and Graphics. Hong Kong, China, 2004: 282-285.[12]XU Junhong, CONG Wang, LI Jin, et al. Gait recognition based on key frame and elliptical model[C]//Proceedings of 2010 IEEE International Conference on Information and Automation. Harbin, China, 2010: 2483-2487.
[13]WANG Kejun, BEN Xianye, ZHAO Yue. Gait period detection based on regional characteristics analysis[C]//Proceedings of the 2009 Chinese Conference on Pattern Recognition, and the CJK Joint Workshop on Pattern Recognition. Nanjing, China, 2009: 542-547.
[14]徐旦华,辜嘉,李松毅,等.Zernike矩的快速算法[J].东南大学学报:自然科学版, 2002, 32(2): 189-192.
         XU Danhua, GU Jia, LI Songyi, et al. Fast algorithm for computation of Zernike moments[J]. Journal of Southeast University: Natural Science Edition, 2002, 32(2): 189-192.
[15]叶斌,彭嘉雄.伪Zernike矩不变性分析及其改进研究[J].中国图象图形学报, 2003, 8(3): 246-252.
        YE BIN, PENG Jiaxiong. Improvement and invariance analysis of pseudo-Zernike moments[J]. Journal of Image and Graphics, 2003, 8(3): 246-252.
[16]秦开怀,王海颍,郑辑涛.一种基于Hough变换的圆和矩形的快速检测方法[J].中国图象图形学报, 2010, 15(1): 109-115.
        QIN Kaihuai, WANG Haiying, ZHENG Jitao. A unified approach based on Hough transform for quick detection of circles and rectangles[J]. Journal of Image and Graphics, 2010, 15(1): 109-115.
[17]KADYROV A, PETROU M. The trace transform and its applications[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(8): 811-828.
[18]高上凯.医学成像系统[M].北京:清华大学出版社, 2000.
[19]SARKAR S. The human ID gait challenge problem: data sets, performance and analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(2): 162-177.

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(03):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(05):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(03):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(05):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(01):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(05):63.
[4]高海燕,阮秋琦.正面视角的步态识别[J].智能系统学报,2011,6(02):119.
 GAO Haiyan,RUAN Qiuqi.A gait recognition method based on frontview[J].CAAI Transactions on Intelligent Systems,2011,6(05):119.
[5]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(05):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(05):432.
[6]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(01):69.
 BEN Xianye,WANG Kejun,MA Hui.Videobased automatic frontview human identification[J].CAAI Transactions on Intelligent Systems,2012,7(05):69.
[7]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(01):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(05):74.[doi:10.3969/j.issn.1673-4785.201209033]

备注/Memo

备注/Memo:
收稿日期:2011-10-19.     网络出版日期:2013-09-29. 
基金项目:国家自然科学基金资助项目(61201370);高等学校博士学科点专项科研基金资助项目(20120131120030);中国博士后科学基金面上项目(2013M530321);山东省博士后创新项目专项资金项目(201303100); 山东大学自主创新基金资助项目(2012GN043,2012DX007).
通信作者:贲晛烨. E-mail: benxianyeye@163.com.
作者简介:
贲晛烨,女,1983年生,讲师,硕士生导师,主要研究方向为模式识别、度量学习、超分辨率人脸识别、步态识别.申请国家发明专利13项,获得授权5项,发表学术论文40余篇,其中被SCI检索5篇、EI检索20余篇.
张鹏,男,1990年生,硕士研究生,主要研究方向为模式识别、生物特征识别,已申请国家发明专利6项. 
潘婷婷,女,1990年生,硕士研究生,主要研究方向为模式识别、生物特征识别,已申请国家发明专利3项. 
王科俊,男,1962年生,教授,博士生导师,博士,哈尔滨工程大学自动化学院模式识别与智能系统学科带头人.主要研究方向为模糊混沌神经网络、自适应逆控制理论、可拓控制、网络智能控制、模式识别、多模态生物特征识别、联脱机指纹考试身份鉴别系统、微小型机器人系统等.完成科研项目20余项,目前在研项目10余项.曾获得部级科技进步二等奖2项、三等奖3项,省高校科学技术一等奖1项、二等奖1项.获发明专利1项、公开3项,国家版权局软件著作权登记1项.发表学术论文180余篇,出版学术专著3部、国防教材1部,主审教材2部.
更新日期/Last Update: 2013-11-28