Personal identification combining modified gait flow image and view

JIA Song-min; WANG Li-jia; WANG Shuang; LI Xiu-zhi

doi:10.3788/OPE.20122011.2500

您当前的位置：

首页 >

文章列表页 >

Personal identification combining modified gait flow image and view

Article | 更新时间：2020-08-12

- Personal identification combining modified gait flow image and view
- Optics and Precision Engineering Vol. 20, Issue 11, Pages: 2500-2506(2012)
- 作者机构：
  
  1. 北京工业大学电子信息与控制工程学院,北京 100124
  2. 河北工业职业技术学院信息工程与自动化系,河北石家庄 050000
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20122011.2500
  CLC： TP391.4
- Received：21 June 2012，
  
  Revised：30 August 2012，
  
  Published：10 November 2012
- 稿件说明：
移动端阅览
贾松敏, 王丽佳, 王爽, 李秀智. 改进的步态光流图与视角相结合的身份识别[J]. 光学精密工程, 2012,20(11): 2500-2506

JIA Song-min, WANG Li-jia, WANG Shuang, LI Xiu-zhi. Personal identification combining modified gait flow image and view[J]. Editorial Office of Optics and Precision Engineering, 2012,20(11): 2500-2506
贾松敏, 王丽佳, 王爽, 李秀智. 改进的步态光流图与视角相结合的身份识别[J]. 光学精密工程, 2012,20(11): 2500-2506 DOI： 10.3788/OPE.20122011.2500.

JIA Song-min, WANG Li-jia, WANG Shuang, LI Xiu-zhi. Personal identification combining modified gait flow image and view[J]. Editorial Office of Optics and Precision Engineering, 2012,20(11): 2500-2506 DOI： 10.3788/OPE.20122011.2500.

摘要

提出将改进的步态光流图(LK-GFI)与视角相结合的方法来解决步态识别易受视角影响的问题。该方法采用Lacus-Kanade (LK)光流法获得连续两帧侧影图像间的光流场

并构造步态特征图像LK-GFI

利用成像原理计算人的行走方向以确定视角。首先

离线建立目标在各视角下的LK-GFI数据库;然后

提取待识别人的当前视角和LK-GFI;最后

用欧式距离度量同一视角下待识别人与目标的LK-GFI之间的相似性。分别采用CASIA数据库和实际室内获得的步态序列对该方法进行了验证。结果显示

错误拒绝率分别为7.95%和9.12%

与采用传统的步态能量图(GEI)相比分别降低了12.5%和14.45%;与采用步态光流图(GFI)相比分别降低了7.77%和6.74%。该方法识别准确性高

实时性强

对多视角有较强的鲁棒性。

Abstract

A method combined the modified Lucas-Kanade Gait Flow Image (LK-GFI) with the view was proposed to solve the problem that personal identification based on a gait is sensitive to view change. The Lacus-Kanade optical method was used to compute the optical flow between two silhouettes to construct LK-GFI

and the view was obtained according to the walking direction of the person. The LK-GFI database for the target at different views was established

then the new person's view and LK-GFI were extracted. At last

the similarity between the new person's LK-GFI and the target's LK-GFI at the same view was computed by the Euclidian distance method. The performance of this method was evaluated on the data in the CASIA database and the data obtained in indoor lab environment

and the False Rejection Rate (FRR) is 7.95% and 9.12% respectively. It is reduced by 12.5% and 14.45% respectively compared with that of the Gait Energy Image (GEI)

and by 7.77% and 6.74% respectively compared with that of the Gait Flow Image (GFI). The proposed method has high recognition accuracy

strong real-time and the robustness to view changes.

关键词

Keywords

references

周志宇,杨卫成,汪亚明,等. 应用梯度矢量流Snake和灰预测的人脸轮廓跟踪[J]. 光学精密工程,2011,19(11):2744-2752. ZHOU ZH Y, YANG W CH, WANG Y M, et al.. Realization of face contour tracking by GVF Snake and grey prediction[J]. Opt. Precision Eng., 2011, 19(11): 2744-2752. (in Chinese)[2] 胡荣,王宏远. 对步态空时数据的连续特征子空间分析[J]. 中国图象图形学报,2011,16(4):625-633. HU R, WANG H Y. Recursive spatiotemporal subspace learning for gait recognition [J]. Journal of Image and Graphics, 2011, 16(4): 625-633. (in Chinese)[3] CHENG M H, HO M F, HUANG CH L. Gait analysis for human identification through manifold learning and HMM [J]. Pattern Recognition, 2008, 41(8): 2541-2553.[4] 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):1-9. WANG L, HU W M, TAN T N. Gait-based human identification [J]. Journal of Computers, 2003, 26(3): 1-9.(in Chinese)[5] 王利巧,裴亚南. 基于步态能量图和不变矩的身份识别算法[J]. 计算机与数字工程,2009,37(10):128-131. WANG L Q,PEI Y N. Human recognition based on gait energy image and invariant moments [J]. Computer & Digital Engineering, 2009, 37(10): 128-131.(in Chinese)[6] 赵黎丽,侯正信. 步态识别问题的特点及研究现状[J]. 中国图象图形学报,2006,11(2):151-161. ZHAO L L, HOU ZH X. Characteristics of gait recognition problem and a review of its research [J]. Journal of Image and Graphics, 2006, 11(2): 151-161. (in Chinese)[7] JU H, BHANU B. Individual recognition using gait energy image [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(2): 316-322.[8] LAM T H W, LEE R S T, ZHANG D. Human gait recognition by the fusion of motion and static spatio-temporal templates [J]. Pattern Recognition, 2007, 40(9): 2563-2573.[9] LAM T H W, CHEUNG K H, LIU J N K. Gait flow image: silhouette-based gait representation for human identification [J]. Pattern Recognition, 2011, 44(4): 973-987.[10] HUANG X X, BOULGOURIS N V. Human gait recognition based on multiview gait sequences [J]. EURASIP Journal on Advances in Signal Processing, 2008: 1-9.[11] KUSAKUNNIRAN W, WU Q, LI H D, et al.. Multiple views gait recognition using view transformation model based on optimized gait energy image. IEEE 12th International Conference on Computer Vision Workshops, Tyoto, P.R. Japan: ICCVW, 2009:1058-1064.[12] HAN X, LIU J W, LI L, et al.. Gait recognition considering directions of walking. IEEE Conference on Cybernetics and Intelligent Systems, Bangkok, P.R. Thailand: CIS, 2006:1-5.[13] 屠大维,江济良. 改进的光流运动图像分析方法及其应用[J]. 光学精密工程,2011,19(5):1159-1164. TU D W, JIANG J L. Improved algorithm for motion image analysis based on optical flow and its application[J]. Opt. Precision Eng., 2011, 19(5): 1159-1164. (in Chinese)[14] 曲兴华,宫辉,贾果欣. 数码相机的彩色图像预处理过程[J]. 光学精密工程, 2009, 17(1):207-212. QU X H, GONG H, JIA G X. Preprocessing of color image based on digital camera [J]. Opt. Precision Eng., 2009, 17(1): 207-212. (in Chinese)

Views

347

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Database engineering design

A Kind of Effective Method of Drawing Management in CAPP System

Material's Selection in CAE

Simulation System of Multimedia Laser Processing

A Software Tool for Creating SECMAI's Dutabase Automatically by TANGO's Database

Related Author

ZHONG Ping

XU Zhi-jun

WANG Jian-Li

CHEN Qi

NIU Xiao-Ming

Yang Hongbo

Guan Zhenzhong

He Bin

Related Institution

Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences

Changchun Institute of Optics and Fine Mechanics, Chinese Academy of Sciences

Changchun Institute of Optics Fine Mechanics, Chinese Academy of Sciences, Changchun, 130022

Changchun Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Changchun 130022

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰