Abstract
We proposed a new multi-view gait recognition model based on the generative adversarial network (GAN). Gait recognition has great advantages in long-distance human body recognition, but it is also very challenging. The appearance-based recognition method performs gait recognition based on the outer contour of the human body, but the appearance may change due to factors such as clothing and carrying objects. The method based on view transformation is recognized by converting the gait image to a 90° normal state. However, with the increase of the gait viewing angle difference, a larger transformation error will be produced, which will result in the loss of gait features, and a good recognition effect will not be achieved. In this paper, a GAN was used to convert the gait image of any states and views to the normal state of 54°, 90°, 126°, and realized the gait recognition based on the extracted invariant features. In order to reduce the loss of characteristic information during the view transformation, this paper introduced a residual structure in the network, which could retain more identity information while realizing the view transformation. Finally, the fusion model was used to fuse the recognition results of the three views in the recognition and decision-making stage. In order to verify the effectiveness of the model in this paper, we used the CASIA-B gait dataset to evaluate the performance of the model. The experimental results showed that the model in this paper had achieved a good recognition effect in the sequence of bag and coat. Compared with advanced networks such as SPAE, GaitGANV1 and GaitGANv2, the performance of this model was better, and it was more robust to changes in viewing and clothing.
Similar content being viewed by others
References
K J W, B B H, et al. Overview of gait recognition [J]. Chin J Image Gr, 2007, 12(7):1152–1160.
Iwashita Y, Ogawara K, Kurazume R (2014) Identification of people walking along curved trajectories[J]. Pattern Recognit Lett 48:60–69
Hossain MA, Makihara Y, Wang J et al (2010) Clothing-invariant gait identification using part-based clothing categorization and adaptive weight control[J]. Pattern Recogn 43(6):2281–2291
Singh S, Biswas K K. Biometric Gait Recognition with Carrying and Clothing Variants[J]. In: International conference on pattern recognition and machine intelligence, 2009.
Tanawongsuwan R, Bobick A. Gait recognition from time-normalized joint-angle trajectories in the walking plane[C]// Computer vision and pattern recognition, 2001. CVPR 2001. In: proceedings of the 2001 IEEE computer society conference on. IEEE, 2001.
Liang W, Ning H, Tan T, et al. Fusion of static and dynamic body biometrics for gait recognition[C]// In: proceedings ninth IEEE international conference on computer vision. IEEE, 2008.
Yang Y, Dan T, Li G. Gait recognition using flow histogram energy image[C]// 2014 22nd international conference on pattern recognition (ICPR). IEEE Comput Soci, 2014.
Zhang Y, Huang Y, Wang L, et al. A comprehensive study on gait biometrics using a joint CNN-based method[J]. Pattern Recognit, 2019, 93.
Aite Zhao, Junyu Dong, Jianbo Li, Lin Qi, Huiyu Zhou: Associated spatio-temporal capsule network for gait recognition. IEEE Trans Multimed (2021).
Hu H (2013) Enhanced gabor feature based classification using a regularized locally tensor discriminant model for multiview gait recognition[J]. IEEE Trans Circuits Syst Video Technol 23(7):1274–1286
Hu M, Wang Y, Zhang Z et al (2013) View-invariant discriminative projection for multi-view gait-based human identification[J]. IEEE Trans Inf Forensics Secur 8(12):2034–2045
Makihara Y, Sagawa R, Mukaigawa Y, et al. Gait recognition using a view transformation model in the frequency domain[C]// In: proceedings of the 9th european conference on computer vision - volume part III. Springer Berlin Heidelberg, 2006.
Kusakunniran W, Qiang W, Li H, et al. Multiple views gait recognition using view transformation model based on optimized gait energy image[C]// In: IEEE international conference on computer vision workshops. IEEE, 2010.
Shuai Z, Zhang J, Huang K, et al. Robust view transformation model for gait recognition[C]// In: IEEE international conference on image processing. IEEE, 2011.
Zhao G, Liu G, Hua L, et al. 3D gait recognition using multiple cameras[C]// Automatic face and gesture recognition, 2006. FGR 2006. 7th international conference on. IEEE, 2006.
Ariyanto G, Nixon M S. Model-based 3D gait biometrics[C]// In: international joint conference on biometrics. IEEE Computer Society, 2011.
D López-Fernández, Madrid-Cuevas F J, Carmona-Poyato A, et al. A new approach for multi-view gait recognition on unconstrained paths[J]. J Visual Commun Image Represent, 2016.
Zifeng Wu, Yongzhen, et al. (2016). A comprehensive study on cross-view gait based human identification with deep CNNs [J]. IEEE Trans Pattern Analy Mach Intel, 39(2):209–226.
Khan M H, Farid M S, Grzegorzek M. A non-linear view transformations model for cross-view gait recognition[J]. Neurocomputing, 2020, 402.
Yu S, Wang Q, Shen L, et al. View invariant gait recognition using only one uniform model[C]// 2016 23rd international conference on pattern recognition (ICPR). IEEE, 2016.
Yu S, Chen H, Reyes E, et al. GaitGAN: invariant gait feature extraction using generative adversarial networks[C]// Computer Vision & Pattern Recognition Workshops. IEEE, 2017.
Shiqi, Chen, Haifeng, et al. GaitGANv2: Invariant gait feature extraction using generative adversarial networks[J]. Pattern Recognit, 2019, 87:179–189.
Saad, M, Darwish. Design of adaptive biometric gait recognition algorithm with free walking directions[J]. IET Biom, 2017, 6(2):53–60.
Tjahjadi, Tardi, Das, et al. (2015). Robust view-invariant multiscale gait recognition[J]. Pattern Recognit: J Pattern Recognit Soci, 48(3):798–811.
Wang Y, Song C, Huang Y, et al. Learning view invariant gait features with Two-Stream GAN[J]. Neurocomputing, 2019, 339(APR.28):245–254.
Ju H, Bhanu B (2005) Individual recognition using gait energy image[J]. IEEE Trans Pattern Anal Mach Intell 28(2):316–322
Goodfellow IJ, Pouget-Abadie J, Mirza M et al (2014) Generative adversarial networks[J]. Adv Neural Inf Process Syst 3:2672–2680
Bashir K, Tao X, Gong S. Cross-view gait recognition using correlation strength[J]. Bmvc, 2011:1–11.
Zhang P, Wu Q, Xu J. VT-GAN: View Transformation GAN for Gait Recognition Across Views[C]// 2019 In: international joint conference on neural networks (IJCNN). IEEE, 2019.
Yoo D, Kim N, Park S, et al. Pixel-level domain transfer[C]//In: european conference on computer vision. Springer International Publishing, 2016.
Zhang K, Huang Y, Du Y, Wang L (2017) Facial expression recognition based on deep convolutional spatial-temporal networks. IEEE Trans Image Process 26(9):4193–4203
Y. Sun, X. Wang, X. Tang, Deep learning face representation from predicting10,000 classes, In: proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 1891–1898.
YHQ, M W, et al. (2020) Cross-view gait feature extraction based on generative confrontation network[J]. Comput Syst Appl, 29(01):168–174.
S. Yu, D. Tan, and T. Tan. A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. In ICPR, pages 441–444, August 2006.
Liao R, Yu S, An W et al (2019) A model-based gait recognition method with body pose and human prior knowledge[J]. Pattern Recognit 98:107069
Zhao L, Zhang R et al (2021) Gait recognition based on 3D spatiotemporal feature fusion based on deep learning [J]. Sens Microsyst 40(2):4
Zhang P, Wu Q, Xu J. VN-GAN: Identity-preserved Variation Normalizing GAN for Gait Recognition[C]// 2019 International Joint Conference on Neural Networks (IJCNN). 2019.
He Y, Zhang J, Shan H, et al. Multi-task GANs for view-specific feature learning in gait recognition[J]. In: IEEE Transsactions on Information Forensics & Security, 2018, pp 1–1.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wen, J., Shen, Y. & Yang, J. Multi-View Gait Recognition Based on Generative Adversarial Network. Neural Process Lett 54, 1855–1877 (2022). https://doi.org/10.1007/s11063-021-10709-1
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-021-10709-1