Abstract
Gait recognition in the wild is a cutting-edge topic in biometrics and computer vision. Since people is less cooperative in the wild scenario, view angles, walking direction and pace cannot be controlled. It leads to high variance of effective sequence length and bad spatial alignment of adjacent frames, which degrades current temporal modeling method in gait recognition. To address the aforementioned issue, we propose a multi-level and multi-time span aggregation (MTA) approach for comprehensive spatio-temporal gait feature learning. With embedded MTA modules, a novel gait recognition architecture is proposed. Results of extensive experiments on three large public gait datasets suggest that our method achieves an excellent improvement on gait recognition performance, especially on the task of gait recognition in the wild.
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
Wu, Z., Huang, Y., Wang, L., Wang, X., Tan, T.: A comprehensive study on cross-view gait based human identification with deep CNNs. TPAMI 39, 209–226 (2017)
Zhu, Z., et al.: Gait recognition in the wild: a benchmark. In: ICCV (2021)
Zheng, J., Liu, X., Liu, W., He, L., Yan, C., Mei, T.: Gait recognition in the wild with dense 3D representations and a benchmark. In: CVPR (2022)
Zheng, J., et al.: Gait recognition in the wild with multi-hop temporal switch. In: ACM Multimedia (2022)
Fan, C., Liang, J., Shen, C., Hou, S., Huang, Y., Yu, S.: OpenGait: revisiting gait recognition toward better practicality. In: CVPR (2023)
Chao, H., He, Y., Zhang, J., Feng, J.: GaitSet: regarding gait as a set for cross-view gait recognition. In: AAAI (2019)
Fan, C., et al.: Gaitpart: temporal part-based model for gait recognition. In: CVPR (2020)
Lin, B., Zhang, S., Yu, X.: Gait recognition via effective global-local feature representation and local temporal aggregation. In: ICCV (2021)
Sepas-Moghaddam, A., Etemad, A.: Deep gait recognition: a survey. TPAMI 45, 264–284 (2023)
Takemura, N., Makihara, Y., Muramatsu, D., Echigo, T., Yagi, Y.: Multi-view large population gait dataset and its performance evaluation for cross-view gait recognition. CVA 10, 1–14 (2018)
Yu, S., Tan, D., Tan, T.: A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. In: ICPR (2006)
Song, C., Huang, Y., Wang, W., Wang, L.: CASIA-E: a large comprehensive dataset for gait recognition. TPAMI 45, 2801–2815 (2023)
Fan, D.-P., Ji, G.-P., Xu, P., Cheng, M.-M., Sakaridis, C., Gool, L.C.: Advances in deep concealed scene understanding. Visual Intell. 1, 16 (2023)
Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification. In: CVPR Workshops (2019)
Han, J., Bhanu, B.: Individual recognition using gait energy image. TPAMI 28, 316–322 (2006)
Xing, W., Li, Y., Zhang, S.: View-invariant gait recognition method by three-dimensional convolutional neural network. JEI 27, 013010 (2018)
Liang, J., Fan, C., Hou, S., Shen, C., Huang, Y., Yu, S.: GaitEdge: beyond plain end-to-end gait recognition for better practicality. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. Lecture Notes in Computer Science, vol. 13665, pp. 375–390. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-20065-6_22
Xu, C., Makihara, Y., Li, X., Yagi, Y.: Occlusion-aware human mesh model-based gait recognition. TIFS 18, 1309–1321 (2023)
Huang, X., Wang, X., He, B., He, S., Liu, W., Feng, B.: STAR: spatio-temporal augmented relation network for gait recognition. TBIOM 5, 115–125 (2023)
Zhang, Y., Huang, Y., Yu, S., Wang, L.: Cross-view gait recognition by discriminative feature learning. TIP 29, 1001–1015 (2020)
Lin, B., Zhang, S., Bao, F.: Gait recognition with multiple-temporal-scale 3D convolutional neural network. In: ACM Multimedia (2020)
Huang, X., et al.: Context-sensitive temporal feature learning for gait recognition. In: CVPR (2021)
Fu, Y., et al.: Horizontal pyramid matching for person re-identification. In: AAAI (2019)
Hou, S., Liu, X., Cao, C., Huang, Y.: Set residual network for silhouette-based gait recognition. TBIOM 3, 384–393 (2021)
Huang, Z., et al.: 3D local convolutional neural networks for gait recognition. In: ICCV (2021)
Hou, S., Liu, X., Cao, C., Huang, Y.: Gait quality aware network: toward the interpretability of silhouette-based gait recognition. TNNLS (2022)
Acknowledgement
This work was supported by the Key Program of National Natural Science Foundation of China (Grant No. U20B2069).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhu, S., Zhang, S., Li, A., Wang, Y. (2023). Multiple Temporal Aggregation Embedding for Gait Recognition in the Wild. In: Jia, W., et al. Biometric Recognition. CCBR 2023. Lecture Notes in Computer Science, vol 14463. Springer, Singapore. https://doi.org/10.1007/978-981-99-8565-4_26
Download citation
DOI: https://doi.org/10.1007/978-981-99-8565-4_26
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8564-7
Online ISBN: 978-981-99-8565-4
eBook Packages: Computer ScienceComputer Science (R0)