A partition approach for robust gait recognition based on gait template fusion

Kejun WANG; Liangliang LIU; Xinnan DING; Kaiqiang YU; Gang HU

doi:10.1631/FITEE.2000377

Your Location：

Home >

Browse articles >

A partition approach for robust gait recognition based on gait template fusion

Regular Papers | Updated：2022-05-19

- A partition approach for robust gait recognition based on gait template fusion
  Enhanced Publication
- 一种基于分块步态模板的鲁棒性步态识别方法
- Frontiers of Information Technology & Electronic Engineering Vol. 22, Issue 5, Pages: 709-719(2021)
- Affiliations：
  
  College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, China
- Author bio：
  
  [ "Kejun WANG, E-mail: heukejun@126.com" ]
  Liangliang LIU, E-mail: liuliangliang@hrbeu.edu.cn
  [ "Xinnan DING, E-mail: dingxinnan@hrbeu.edu.cn" ]
  [ "Kaiqiang YU, E-mail: yukaiqiang@hrbeu.edu.cn" ]
  [ "Gang HU, E-mail: hugang@hrbeu.edu.cn" ]
- Funds：
- DOI：10.1631/FITEE.2000377
  CLC： TP391.4
- Published：2021-05，
  
  Published Online：24 April 2021，
  
  Received：25 July 2020，
  
  Revised：03 February 2021，
- Accepted：
Scan QR Code
KEJUN WANG, LIANGLIANG LIU, XINNAN DING, et al. A partition approach for robust gait recognition based on gait template fusion. [J]. Frontiers of information technology & electronic engineering, 2021, 22(5): 709-719.
DOI：

KEJUN WANG, LIANGLIANG LIU, XINNAN DING, et al. A partition approach for robust gait recognition based on gait template fusion. [J]. Frontiers of information technology & electronic engineering, 2021, 22(5): 709-719. DOI： 10.1631/FITEE.2000377.

摘要

步态识别具备远程识别的巨大潜力，但这种方法很容易受到与身份无关的因素影响，例如穿衣、随身携带的物体和角度。目前基于步态模板的方法可以有效表示步态特征。每一种步态模板都有其优势以及表征不同的显著信息。本文提出一种步态模板融合方法，以避免经典的步态模板（例如步态能量图像方法）的不足--经典步态模板表征的不完整信息对轮廓变化很敏感。所提步态模板融合方法采取分块的方法，以表征行人不同身体部位的不同步态习惯。根据人体各部分特点将融合的步态模板为3个部分（头部、躯干和腿部区域），然后将这3部分的步态模板分别输入卷积神经网络学习从而获得融合的步态特征。采用CASIA-B数据集进行充分的实验评估，并将所提方法与现有方法比较。实验结果表明，所提步态识别方法具有良好准确性和鲁棒性。

Abstract

Gait recognition has significant potential for remote human identification

but it is easily influenced by identity-unrelated factors such as clothing

carrying conditions

and view angles. Many gait templates have been presented that can effectively represent gait features. Each gait template has its advantages and can represent different prominent information. In this paper

gait template fusion is proposed to improve the classical representative gait template (such as a gait energy image) which represents incomplete information that is sensitive to changes in contour. We also present a partition method to reflect the different gait habits of different body parts of each pedestrian. The fused template is cropped into three parts (head

trunk

and leg regions) depending on the human body

and the three parts are then sent into the convolutional neural network to learn merged features. We present an extensive empirical evaluation of the CASIA-B dataset and compare the proposed method with existing ones. The results show good accuracy and robustness of the proposed method for gait recognition.

关键词

步态识别分块算法步态模板步态分析步态能量图深度卷积神经网络生物特征识别模式识别

Keywords

Gait recognitionPartition algorithmsGait templatesGait analysisGait energy imageDeep convolutional neural networksBiometrics recognitionPattern recognition

references

K Bashir, , , T Xiang, , , SG Gong. . Cross-view gait recognition using correlation strength. . Proc British Machine Vision Conf, , 2010a. . p.1--11. . DOI:10.5244/C.24.109http://doi.org/10.5244/C.24.109..

K Bashir, , , T Xiang, , , SG Gong. . Gait recognition without subject cooperation. . Patt Recogn Lett, , 2010b. . 31((13):):2052--2060. . DOI:10.1016/j.patrec.2010.05.027http://doi.org/10.1016/j.patrec.2010.05.027..

XY Ben, , , C Gong, , , P Zhang, , , 等. . Coupled patch alignment for matching cross-view gaits. . IEEE Trans Image Process, , 2019a. . 28((6):):3142--3157. . DOI:10.1109/TIP.2019.2894362http://doi.org/10.1109/TIP.2019.2894362..

XY Ben, , , P Zhang, , , ZH Lai, , , 等. . A general tensor representation framework for cross-view gait recognition. . Patt Recogn, , 2019b. . 9087--98. . DOI:10.1016/j.patcog.2019.01.017http://doi.org/10.1016/j.patcog.2019.01.017..

XY Ben, , , C Gong, , , P Zhang, , , 等. . Coupled bilinear discriminant projection for cross-view gait recognition. . IEEE Trans Circ Syst Video Technol, , 2020. . 30((3):):734--747. . DOI:10.1109/TCSVT.2019.2893736http://doi.org/10.1109/TCSVT.2019.2893736..

HQ Chao, , , YW He, , , JP Zhang, , , 等. . GaitSet: regarding gait as a set for cross-view gait recognition. . Proc AAAI Conf on Artificial Intelligence, , 2019. . p. 8126--8133. . DOI:10.1609/aaai.v33i01.33018126http://doi.org/10.1609/aaai.v33i01.33018126..

C Fan, , , YJ Peng, , , CS Cao, , , 等. . GaitPart: temporal part-based model for gait recognition. . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, , 2020. . p. 14213--14221. . DOI:10.1109/CVPR42600.2020.01423http://doi.org/10.1109/CVPR42600.2020.01423..

IJ Goodfellow, , , J Pouget-Abadie, , , M Mirza, , , 等. . Generative adversarial nets. . Proc 27th Int Conf on Neural Information Processing Systems, , 2014. . p. 2672--2680. . ..

J Han, , , B Bhanu. . Individual recognition using gait energy image. . IEEE Trans Patt Anal Mach Intell, , 2006. . 28((2):):316--323. . DOI:10.1109/TPAMI.2006.38http://doi.org/10.1109/TPAMI.2006.38..

YW He, , , JP Zhang, , , HM Shan, , , 等. . Multi-task GANs for view-specific feature learning in gait recognition. . IEEE Trans Inform Forens Secur, , 2019. . 14((1):):102--113. . DOI:10.1109/TIFS.2018.2844819http://doi.org/10.1109/TIFS.2018.2844819..

A Hossain, , , Y Makihara, , , JQ Wang, , , 等. . Clothing-invariant gait identification using part-based clothing categorization and adaptive weight control. . Patt Recogn, , 2010. . 43((6):):2281--2291. . DOI:10.1016/j.patcog.2009.12.020http://doi.org/10.1016/j.patcog.2009.12.020..

H Iwama, , , D Muramatsu, , , Y Makihara, , , 等. . Gait verification system for criminal investigation. . IPSJ Trans Comput Vis Appl, , 2013. . 5163--175. . DOI:10.2197/ipsjtcva.5.163http://doi.org/10.2197/ipsjtcva.5.163..

W Kusakunniran, , , Q Wu, , , J Zhang, , , 等. . Gait recognition under various viewing angles based on correlated motion regression. . IEEE Trans Circ Syst Video Technol, , 2012. . 22((6):):966--980. . DOI:10.1109/TCSVT.2012.2186744http://doi.org/10.1109/TCSVT.2012.2186744..

C Li, , , X Min, , , SQ Sun, , , 等. . DeepGait: a learning deep convolutional representation for view-invariant gait recognition using joint Bayesian. . Appl Sci, , 2017. . 7((3):):210DOI:10.3390/app7030210http://doi.org/10.3390/app7030210..

X Li, , , Y Makihara, , , C Xu, , , 等. . Gait recognition invariant to carried objects using alpha blending generative adversarial networks. . Patt Recogn, , 2020. . 105107376DOI:10.1016/j.patcog.2020.107376http://doi.org/10.1016/j.patcog.2020.107376..

ZW Lv, , , XL Xing, , , KJ Wang, , , 等. . Class energy image analysis for video sensor-based gait recognition: a review. . Sensors, , 2015. . 15((1):):932--964. . DOI:10.3390/s150100932http://doi.org/10.3390/s150100932..

Y Makihara, , , R Sagawa, , , Y Mukaigawa, , , 等. . Gait recognition using a view transformation model in the frequency domain. . Proc European Conf on Computer Vision, , 2006. . p.151--163. . DOI:10.1007/11744078_12http://doi.org/10.1007/11744078_12..

D Muramatsu, , , Y Makihara, , , Y Yagi. . View transformation model incorporating quality measures for cross-view gait recognition. . IEEE Trans Cybern, , 2016. . 46((7):):1602--1615. . DOI:10.1109/TCYB.2015.2452577http://doi.org/10.1109/TCYB.2015.2452577..

PJ Phillips. . Human identification technical challenges. . Proc Int Conf on Image Processing, , 2002. . p.49--52. . DOI:10.1109/ICIP.2002.1037956http://doi.org/10.1109/ICIP.2002.1037956..

I Rida, , , N Almaadeed, , , S Almaadeed. . Robust gait recognition: a comprehensive survey. . IET Biometr, , 2019. . 8((1):):14--28. . DOI:10.1049/iet-bmt.2018.5063http://doi.org/10.1049/iet-bmt.2018.5063..

S Sarkar, , , PJ Phillips, , , Z Liu, , , 等. . The humanid gait challenge problem: data sets, performance, and analysis. . IEEE Trans Patt Anal Mach Intell, , 2005. . 27((2):):162--177. . DOI:10.1109/TPAMI.2005.39http://doi.org/10.1109/TPAMI.2005.39..

K Shiraga, , , Y Makihara, , , D Muramatsu, , , 等. . GEINet: view-invariant gait recognition using a convolutional neural network. . Proc Int Conf on Biometrics, , 2016. . p.1--8. . DOI:10.1109/ICB.2016.7550060http://doi.org/10.1109/ICB.2016.7550060..

CF Song, , , YZ Huang, , , Y Huang, , , 等. . GaitNet: an end-to-end network for gait based human identification. . Patt Recogn, , 2019. . 96106988DOI:10.1016/j.patcog.2019.106988http://doi.org/10.1016/j.patcog.2019.106988..

C Wang, , , JP Zhang, , , L Wang, , , 等. . Human identification using temporal information preserving gait template. . IEEE Trans Patt Anal Mach Intell, , 2012. . 34((11):):2164--2176. . DOI:10.1109/TPAMI.2011.260http://doi.org/10.1109/TPAMI.2011.260..

KJ Wang, , , XL Xing, , , T Yan, , , 等. . Couple metric learning based on separable criteria with its application in cross-view gait recognition. . Proc 9th Chinese Conf on Biometric Recognition, , 2014. . p.347--356. . DOI:10.1007/978-3-319-12484-1_39http://doi.org/10.1007/978-3-319-12484-1_39..

YY Wang, , , CF Song, , , Y Huang, , , 等. . Learning view invariant gait features with Two-Stream GAN. . Neurocomputing, , 2019. . 339245--254. . DOI:10.1016/j.neucom.2019.02.025http://doi.org/10.1016/j.neucom.2019.02.025..

ZF Wu, , , YZ Huang, , , L Wang. . Learning representative deep features for image set analysis. . IEEE Trans Multim, , 2015. . 17((11):):1960--1968. . DOI:10.1109/TMM.2015.2477681http://doi.org/10.1109/TMM.2015.2477681..

ZF Wu, , , YZ Huang, , , L Wang, , , 等. . A comprehensive study on cross-view gait based human identification with deep CNNs. . IEEE Trans Patt Anal Mach Intell, , 2017. . 39((2):):209--226. . DOI:10.1109/TPAMI.2016.2545669http://doi.org/10.1109/TPAMI.2016.2545669..

XL Xing, , , KJ Wang, , , T Yan, , , 等. . Complete canonical correlation analysis with application to multi-view gait recognition. . Patt Recogn, , 2016. . 50107--117. . DOI:10.1016/j.patcog.2015.08.011http://doi.org/10.1016/j.patcog.2015.08.011..

SQ Yu, , , DL Tan, , , TN Tan. . A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. . Proc 18th Int Conf on Pattern Recognition, , 2006. . p.441--444. . DOI:10.1109/ICPR.2006.67http://doi.org/10.1109/ICPR.2006.67..

SQ Yu, , , HF Chen, , , EBG Reyes, , , 等. . GaitGAN: invariant gait feature extraction using generative adversarial networks. . Proc IEEE Conf on Computer Vision and Pattern Recognition Workshops, , 2017a. . p.532--539. . DOI:10.1109/CVPRW.2017.80http://doi.org/10.1109/CVPRW.2017.80..

SQ Yu, , , HF Chen, , , Q Wang, , , 等. . Invariant feature extraction for gait recognition using only one uniform model. . Neurocomputing, , 2017b. . 23981--93. . DOI:10.1016/j.neucom.2017.02.006http://doi.org/10.1016/j.neucom.2017.02.006..

EH Zhang, , , YW Zhao, , , W Xiong. . Active energy image plus 2DLPP for gait recognition. . Signal Process, , 2010. . 90((7):):2295--2302. . DOI:10.1016/j.sigpro.2010.01.024http://doi.org/10.1016/j.sigpro.2010.01.024..

P Zhang, , , Q Wu, , , JS Xu. . VN-GAN: identity-preserved variation normalizing GAN for gait recognition. . Proc Int Joint Conf on Neural Networks, , 2019. . p.1--8. . DOI:10.1109/IJCNN.2019.8852401http://doi.org/10.1109/IJCNN.2019.8852401..

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

Subspace transform induced robust similarity measure for facial images

Related Author

Jian ZHANG

Heng ZHANG

Li-ling BO

Hong-ran LI

Shuai XU

Dong-qing YUAN

Related Institution

Department of Computer Engineering, Jiangsu Ocean University

Department of Mathematics, Jiangsu Ocean University

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
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