Abstract
Gait recognition has become a necessary integral part of emerging smart wearables. However, considering the limitations of wearable sensing, improving the recognition performance remains an open question. In this work, we tackle the problem of gait recognition by using a large set of multimodal sensing insole data from sixty-two participants reflecting kinetic and kinematic variables of natural gait outdoors. We used this dataset to leverage a novel recognition method involving a deep architecture combining a convolutional neural network, a long short-term memory network, and attention embedding. It allows grasping the temporal-spatial gait features completely. An essential part of this work is the comparative performance exploration of fixed-length and gait-cycle segmentation. The proposed framework allows accuracy of 99.73% when using gait-cycle segmentation. The results confirm that the hybrid deep learning model using multisensory, multimodal data can be effectively applied for identity recognition in an unconstrained environment.
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
Shaheed, K., et al.: A systematic review on physiological-based biometric recognition systems: current and future trends. Archives of Computational Methods in Engineering 28(7), 4917–4960 (2021). https://doi.org/10.1007/s11831-021-09560-3
Wan, C., Wang, L., Phoha, V.V. (eds.).: A Survey on Gait Recognition. ACM Computing Surveys (CSUR) 51(5), 1–35 (2018)
Wang, C., Li, Z., Sarpong, B.: Multimodal adaptive identity-recognition algorithm fused with gait perception. Big Data Mining and Analytics. 4(4), 223–232 (2021)
Zeng, X., Zhang, X., Yang, S., Shi, Z., Chi, C.: Gait-based implicit authentication using edge computing and deep learning for mobile devices. Sensors. 21(13), 4592 (2021)
Zou, Y., Libanori, A., Xu, J., Nashalian, A., Chen, J.: Triboelectric Nanogenerator Enabled Smart Shoes for Wearable Electricity Generation. Research. 2020 (2020)
Ivanov, K., et al.: Design of a Sensor Insole for Gait Analysis. In: Yu, H., Liu, J., Liu, L., Ju, Z., Liu, Y., Zhou, D. (eds.) ICIRA 2019. LNCS (LNAI), vol. 11743, pp. 433–444. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-27538-9_37
Ivanov, K., et al.: Identity recognition by walking outdoors using multimodal sensor insoles. IEEE Access. 8, 150797–150807 (2020)
Guo, X.X., Yang, H.Z.: An improved compromise for soft/hard thresholds in wavelet denoising. CAAI Transactions on Intelligent Systems. 222–225 (2008)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Wang, T., Xia, Y., Zhang, D.: Human gait recognition based on convolutional neural network and attention model. Chinese Journal of Sensors and Actuators. 32(07), 1027–1033 (2019)
Acknowledgments
This work was partially supported by Key R&D support projects of the Chengdu Science and Technology Bureau (No. 2021-YF05-02175-SN) and by the funding of the China Scholarship Council.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yue, J., Mei, Z., Ivanov, K., Li, Y., He, T., Zeng, H. (2022). Gait Recognition by Sensing Insole Using a Hybrid CNN-Attention-LSTM Network. In: Deng, W., et al. Biometric Recognition. CCBR 2022. Lecture Notes in Computer Science, vol 13628. Springer, Cham. https://doi.org/10.1007/978-3-031-20233-9_49
Download citation
DOI: https://doi.org/10.1007/978-3-031-20233-9_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20232-2
Online ISBN: 978-3-031-20233-9
eBook Packages: Computer ScienceComputer Science (R0)