Abstract
To solve multi-view problem in gait recognition, some methods based on Generative Adversarial Networks (GANs) are proposed. These methods mainly transformed multi-view gait features with walking variations into a common view without these variations. However, the direct pixel-to-pixel transformation would result to inefficient and inaccurate. Moreover, the transformed features often did not preserve enough identification information which would lead to accuracy decline. Besides, Gait Energy Image (GEI) often loses temporal information of sequences. To address these problems, Inception-encoder is proposed to extract effective gait features into feature vectors which are invariant to views and other walking variations by adopting generative constraints from GANs. To preserve more identification information, identification constraints is adopted from labels. Furthermore, inception model is embedded into the encoder for improving representation ability. Moreover, CL-GEI is proposed to preserve more temporal information. Experiments on CASIA-B and OU-ISIR prove the competitive performance of the combination of Inception-encoder with CL-GEI compared with the state-of-the-art.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein GAN (2017)
Feng, Y., Li, Y., Luo, J.: Learning effective gait features using LSTM. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 325–330. IEEE (2016)
Goodfellow, I.J., et al.: Generative adversarial nets. In: International Conference on Neural Information Processing Systems (2014)
He, K., Zhang, X., Ren, S., Jian, S.: Delving deep into rectifiers: Surpassing human-level performance on imagenet classification (2015)
He, Y., Zhang, J., Shan, H., Liang, W.: Multi-task GANs for view-specific feature learning in gait recognition. IEEE Trans. Inf. Forensics Secur. 14(1), 102–113 (2018)
Iwama, H., Okumura, M., Makihara, Y., Yagi, Y.: The OU-ISIR gait database comprising the large population dataset and performance evaluation of gait recognition. IEEE Trans. Inf. Forensics Secur. 7(5), 1511–1521 (2012)
Ju Han, B.B.: Individual recognition using gait energy image. IEEE Trans. Pattern Anal. Mach. Intell. 28(2), 316–322 (2006)
Mirza, M., Osindero, S.: Conditional generative adversarial nets. Computer Science, pp. 2672–2680 (2014)
Nixon, M.S., Tan, T., Chellappa, R.: Human Identification Based on Gait. Springer, New York (2006). https://doi.org/10.1007/978-0-387-29488-9
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. Computer Science (2015)
Shi, X., Chen, Z., Hao, W., Yeung, D.Y., Woo, W.C.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: International Conference on Neural Information Processing Systems (2015)
Shiraga, K., Makihara, Y., Muramatsu, D., Echigo, T., Yagi, Y.: Geinet: view-invariant gait recognition using a convolutional neural network. In: International Conference on Biometrics, pp. 1–8 (2016)
Shuai, Z., Zhang, J., Huang, K., Ran, H., Tan, T.: Robust view transformation model for gait recognition. In: IEEE International Conference on Image Processing (2011)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Computer Vision and Pattern Recognition (2016)
Takemura, N., Makihara, Y., Muramatsu, D., Echigo, T., Yagi, Y.: On input/output architectures for convolutional neural network-based cross-view gait recognition. IEEE Trans. Circuits Syst. Video Technol. 29(9), 2708–2719 (2017)
Tieleman, T., Hinton, G.: Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Netw. Mach. Learn. 4(2), 26–31 (2012)
Wolf, T., Babaee, M., Rigoll, G.: Multi-view gait recognition using 3D convolutional neural networks. In: IEEE International Conference on Image Processing, pp. 4165–4169 (2016)
Woo, S., Park, J., Lee, J.Y., So Kweon, I.: CBAM: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3–19 (2018)
Wu, Z., Huang, Y., Wang, L., Wang, X., Tan, T.: A comprehensive study on cross-view gait based human identification with deep CNNs. IEEE Trans. Pattern Anal. Mach. Intell. 39(2), 209–226 (2016)
Yu, S., Chen, H., Reyes, E.B.G., Poh, N.: GaitGAN: invariant gait feature extraction using generative adversarial networks. In: Computer Vision and Pattern Recognition Workshops (2017)
Yu, S., Chen, H., Wang, Q., Shen, L., Huang, Y.: Invariant feature extraction for gait recognition using only one uniform model. Neurocomputing 239, 81–93 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Huang, C., Song, Y., Wu, C. (2021). Multi-view Gait Recognition by Inception-Encoder and CL-GEI. In: Peng, Y., Hu, SM., Gabbouj, M., Zhou, K., Elad, M., Xu, K. (eds) Image and Graphics. ICIG 2021. Lecture Notes in Computer Science(), vol 12889. Springer, Cham. https://doi.org/10.1007/978-3-030-87358-5_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-87358-5_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87357-8
Online ISBN: 978-3-030-87358-5
eBook Packages: Computer ScienceComputer Science (R0)