Abstract
In this paper, we propose a novel deep learning based framework to effectively combine CNN (Convolutional Neural Network) and LSTM (Long Short-Term Memory) to facilitate accurate gait identification. Distinguished from traditional methods based on spatial information, our framework can take both spatial information and temporal cures into account. Meanwhile, its architecture applies novel hybrid layering structure, whose first layer is based CNN and aims at extracting gait’s spatial information. In the second layer, LSTM is used to obtain dynamic dependency among the gaits and thus achieve optimal modeling of sequential and spatial information of gait. Moreover, our architecture leads to (1) optimal contrastive loss and (2) maximized difference between inter-classes and minimized gap between intra-classes. Consequently, the recognition accuracy has been improved tremendously. Using the gait dataset CASIA-B test collection containing 124 subjects in different conditions and various views, our comprehensive experimental study demonstrates a variety of advantages over the state of the art approaches.
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
References
Bouchrika, I., Carter, J.N., Nixon, M.S.: Towards automated visual surveillance using gait for identity recognition and tracking across multiple non-intersecting cameras. Multimedia Tools Appl. 75(2), 1201–1221 (2016)
Liu, N., Lu, J., Tan, Y.P.: Joint subspace learning for view-invariant gait recognition. IEEE Signal Process. Lett. 18(7), 431–434 (2011)
Bashir, K., Xiang, T., Cross, G.S.: Correlation, view gait recognition using, strength. In: Proceedings of the DBLP British Machine Vision Conference, BMVC: Aberystwyth, UK, August 31 - September 3, 2010, pp. 1–11 (2010)
Zhao, G., Liu, G., Li, H., et al.: 3D gait recognition using multiple cameras. In: International Conference on Automatic Face and Gesture Recognition, pp. 529–534. IEEE Computer Society (2006)
Wu, Z., Huang, Y., Wang, L., et al.: A comprehensive study on cross-view gait based human identification with deep CNNs. IEEE Trans. Pattern Anal. Mach. Intell. 39(2), 209–226 (2016)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Zhang, C., Liu, W., Ma, H., et al.: Siamese neural network based gait recognition for human identification. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2832–2836. IEEE (2016)
Sun, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. Adv. Neural. Inf. Process. 27, 1988–1996 (2014)
Lee, C.S., Elgammal, A.: Gait tracking and recognition using person-dependent dynamic shape model (2006)
Cunado, D., Nixon, M.S., Carter, J.N.: Using gait as a biometric, via phase-weighted magnitude spectra. In: Bigün, J., Chollet, G., Borgefors, G. (eds.) AVBPA 1997. LNCS, vol. 1206, pp. 93–102. Springer, Heidelberg (1997). https://doi.org/10.1007/BFb0015984
Bobick, A.F., Johnson, A.Y.: Gait recognition using static, activity-specific parameters. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, vol. 1, pp. I-423-I-430. IEEE (2001)
Bouchrika, I., Nixon, M.S.: Model-based feature extraction for gait analysis and recognition. In: Gagalowicz, A., Philips, W. (eds.) MIRAGE 2007. LNCS, vol. 4418, pp. 150–160. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-71457-6_14
Wang, L., Ning, H., Tan, T., et al.: Fusion of static and dynamic body biometrics for gait recognition. In: IEEE International Conference on Computer Vision, p. 1449. IEEE Computer Society (2003)
Yam, C., Nixon, M.: Model-based gait recognition. In: Li, S.Z., Jain, A. (eds.) Enclycopedia of Biometrics, pp. 633–639. Springer, Boston (2009)
Abdelkader, C.B., Davis, L., Cutler, R.: Stride and cadence as a biometric in automatic person identification and verification. In: Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition, pp. 372–377. IEEE (2002)
Ning, H., Tan, T., Wang, L., et al.: Kinematics-based tracking of human walking in monocular video sequences. Image Vis. Comput. 22(5), 429–441 (2004)
Johnson, A.Y., Bobick, A.F.: A multi-view method for gait recognition using static body parameters. In: Bigun, J., Smeraldi, F. (eds.) AVBPA 2001. LNCS, vol. 2091, pp. 301–311. Springer, Heidelberg (2001). https://doi.org/10.1007/3-540-45344-X_44
Yam, C.Y.: Gait recognition by walking and running: a model-based approach 1–6 (2002)
Man, J., Bhanu, B.: Individual recognition using gait energy image. IEEE Trans. Pattern Anal. Mach. Intell. 28(2), 316–322 (2005)
Ajayi, R.: Gait recognition using pose kinematics and pose energy image. Sig. Process. 92(3), 780–792 (2012)
Chen, C., Liang, J., et al.: Frame difference energy image for gait recognition with incomplete silhouettes. Pattern Recogn. Lett. 30(11), 977–984 (2009)
Graves, A.: Generating sequences with recurrent neural networks. Comput. Sci. (2013)
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks, vol. 4, pp. 3104–3112 (2014)
Chao, H., He, Y., Zhang, J., et al.: GaitSet: regarding gait as a set for cross-view gait recognition (2018)
Liu, J., Sun, N., Li, X., Han, G., Yang, H., Sun, Q.: Rare bird sparse recognition via part-based gist feature fusion and regularized intraclass dictionary learning. Comput. Mater. Continua 55(3), 435–446 (2018)
Zhou, S., Liang, W., Li, J., Kim, J.-U.: Improved VGG model for road traffic sign recognition. Comput. Mater. Continua 57(1), 11–24 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Ling, H., Wu, J., Li, P. (2019). Towards Effective Gait Recognition Based on Comprehensive Temporal Information Combination. In: Sun, X., Pan, Z., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2019. Lecture Notes in Computer Science(), vol 11633. Springer, Cham. https://doi.org/10.1007/978-3-030-24265-7_38
Download citation
DOI: https://doi.org/10.1007/978-3-030-24265-7_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-24264-0
Online ISBN: 978-3-030-24265-7
eBook Packages: Computer ScienceComputer Science (R0)