AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Tsinghua Science and Technology Article
PDF (989.5 KB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access

GaitFFDA: Feature Fusion and Dual Attention Gait Recognition Model

Zhixiong Wu( ), Yong Cui
Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
Show Author Information

Abstract

Gait recognition has a wide range of application scenarios in the fields of intelligent security and transportation. Gait recognition currently faces challenges: inadequate feature methods for environmental interferences and insufficient local-global information correlation. To address these issues, we propose a gait recognition model based on feature fusion and dual attention. Our model utilizes the ResNet architecture as the backbone network for fundamental gait features extraction. Subsequently, the features from different network layers are passed through the feature pyramid for feature fusion, so that multi-scale local information can be fused into global information, providing a more complete feature representation. The dual attention module enhances the fused features in multiple dimensions, enabling the model to capture information from different semantics and scale information. Our model proves effective and competitive results on CASIA-B (NM: 95.6%, BG: 90.9%, CL: 73.7%) and OU-MVLP (88.1%). The results of related ablation experiments show that the model design is effective and has strong competitiveness.

Keywords

neural networkattention mechanismgait recognition

References

[1]

Y. W. He, J. P. Zhang, H. M. Shan, and L. Wang, Multi-task gans for view-specific feature learning in gait recognition, IEEE Transactions on Information Forensics and Security, vol. 14, pp. 102–113, 2019.
Crossref Google Scholar
[2]

M. Hu, Y. Wang, Z. Zhang, J. J. Little, and D. Huang, View-invariant discriminative projection for multi-view gait-based human identification, IEEE Trans. Inf. Forensics Secur., vol. 8, no. 12, pp. 2034–2045, 2013.
Crossref Google Scholar
[3]

N. Takemura, Y. Makihara, D. Muramatsu, T. Echigo, and Y. Yagi, On input/output architectures for convolutional neural network-based cross-view gait recognition, IEEE Trans. Circuits Syst. Video Technol., vol. 29, no. 9, pp. 2708–2719, 2019.
Crossref Google Scholar
[4]

Z. Wu, Y. Huang, L. Wang, X. Wang, and T. Tan, A comprehensive study on cross-view gait based human identification with deep CNNs, IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 2, pp. 209–226, 2017.
Crossref Google Scholar
[5]

J. G. Han and B. Bhanu, Individual recognition using gait energy image, IEEE Trans. Pattern Anal. Mach. Intell., vol. 28, no. 2, pp. 316–322, 2005.
Crossref Google Scholar
[6]
H. Q. Chao, Y. W. He, J. P. Zhang, and J. F. Feng, Gaitset: Regarding gait as a set for cross-view gait recognition, arXiv preprint arXiv:1811.06186, 2019.
Crossref
[7]

Y. Zhang, Y. Huang, S. Yu and L. Wang, Cross-View Gait Recognition by Discriminative Feature Learning, IEEE Transactions on Image Processing, vol. 29, pp. 1001–1015, 2020.
Crossref Google Scholar
[8]
C. Fan, Y. J. Peng, C. S. Cao, X. Liu, S. H. Hou, J. N. Chi, Y. Z. Huang, Q. Li, and Z. Q. He, Gaitpart: Temporal part-based model for gait recognition, in Proc. 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 14213–14221, 2020.
Crossref
[9]
X. H. Wu, W. Z. An, S. Q. Yu, W. Y. Guo, and E. B. G. Reyes, Spatial-temporal graph attention network for video-based gait recognition, in Proc. ACPR, Auckland, New Zealand, 2019.
[10]
R. J. Liao, C. S. Cao, E. B. G. Reyes, S. Q. Yu, and Y. Z. Huang, Pose-based temporal-spatial network (ptsn) for gait recognition with carrying and clothing variations, in Proc. CCBR, Shenzhen, China, 2017.
Crossref
[11]
G. Ariyanto, Model-based 3d gait biometrics, in Proc. 2011 Int. Joint Conf. on Biometrics (IJCB), Washington, DC, USA, pp. 1–7, 2011.
Crossref
[12]
Y. Liu, X. Jiang, T. F. Sun, and K. Xu, 3d gait recognition based on a cnn-lstm network with the fusion of skegei and da features, in Proc. 2019 16th IEEE Int. Conf. on Advanced Video and Signal Based Surveillance (AVSS), Taipei, China, pp. 1–8, 2019.
Crossref
[13]

T. Huynh-The, C.-H. Hua, N. A. Tu, and D.-S. Kim, Learning 3d spatiotemporal gait feature by convolutional network for person identification, Neuro-Computing, vol. 397, pp. 192–202, 2020.
Crossref Google Scholar
[14]
F. Ahmed, P. P. Paul, and M. Gavrilova, Kinect-based gait recognition using sequences of the most relevant joint relative angles, https://dspace5.zcu.cz/bitstream/11025/17149/1/Ahmed.pdf, 2015.
[15]
Y. Feng, Y. C. Li, and J. B. Luo, Learning effective gait features using lstm, in Proc. 2016 23rd Int. Conf. on Pattern Recognition (ICPR), Cancun, Mexico, pp. 325–330, 2016.
[16]
C. Wang, J. P. Zhang, J. Pu, X. R. Yuan, and L. Wang, Chrono-gait image: A novel temporal template for gait recognition, in Proc. European Conf. on Computer Vision, Crete, Greece, 2010.
Crossref
[17]

M. H. Ghaeminia and S. B. Shokouhi, Gsi: Efficient spatio-temporal template for human gait recognition, Int. J. Biom., vol. 10, pp. 29–51, 2018.
Crossref Google Scholar
[18]
K. Bashir, T. Xiang, and S. G. Gong, Feature selection on gait energy image for human identification, in Proc. 2008 IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Las Vegas, NV, USA, pp. 985–988, 2008.
Crossref
[19]

O. Elharrouss, N. Almaadeed, S. Al-Maadeed, and A. Bouridane, Gait recognition for person re-identification, J. Supercomput., vol. 77, no. 4, pp. 3653–3672, 2021.
Crossref Google Scholar
[20]
B. Lin, S. L. Zhang, and F. Bao, Gait recognition with multiple-temporal-scale 3d convolutional neural network, in Proc. of the 28th ACM Int. Conf. Multimedia, New York, NY, USA, 2020.
Crossref
[21]

G. H. Huang, Z. Lu, C. M. Pun, and L. L. Cheng, Flexible gait recognition based on flow regulation of local features between key frames, IEEE Access, vol. 8, pp. 75381–75392, 2020.
Crossref Google Scholar
[22]

R. J. Liao, S. Q. Yu, W. Z. An, and Y. Z. Huang, A model-based gait recognition method with body pose and human prior knowledge, Pattern Recognit., vol. 98, p. 107069, 2020.
Crossref Google Scholar
[23]
C. Fan, J. H. Liang, C. F. Shen, S. H. Hou, Y. Z. Huang, and S. Q. Yu, Opengait: Revisiting gait recognition towards better practicality, in Proc. of the IEEE/CVF Conf. on Computer Vision and Pattern Recognition, Vancouver, Canada, pp. 9707–9716, 2023.
Crossref
[24]
T.-Y. Lin, P. Dollár, R. B. Girshick, K. M. He, B. Hariharan, and S. J. Belongie, Feature pyramid networks for object detection, in Proc. 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 936–944, 2017.
Crossref
[25]
S. Liu, L. Qi, H. F. Qin, J. P. Shi, and J. Y. Jia, Path aggregation network for instance segmentation, in Proc. 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp. 8759–8768, 2018.
Crossref
[26]
M. X. Tan, R. M. Pang, and . V. Le, Efficient-det: Scalable and efficient object detection, in Proc. 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 10778–10787, 2020.
Crossref
[27]
S. Y. Qiao, L.-C. Chen, and A. L. Yuille, Detectors: Detecting objects with recursive feature pyramid and switchable atrous convolution, in Proc. 2021 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 2021.
Crossref
[28]
X. Y. Dai, Y. P. Chen, B. Xiao, D. D. Chen, M. C. Liu, L. Yuan, and L. Zhang, Dynamic head: Unifying object detection heads with attentions, in Proc. IEEE/CVF conference on computer vision and pattern recognition, Nashville, TN, USA, pp. 7373–7382, 2021.
Crossref
[29]
J. F. Dai, H. Z. Qi, Y. W. Xiong, Y. Li, G. D. Zhang, H. Hu, and Y. C. Wei, Deformable convolutional networks, in Proc. 2017 IEEE Int. Conf. on Computer Vision (ICCV), Venice, Italy, pp. 764–773, 2017.
Crossref
[30]

Y. Fu, Y. Wei, Y. Zhou, H. Shi, G. Huang, X. Wang, Z. Yao, and T. Huang, Horizontal pyramid matching for person re-identification, Proc. AAAI Conf. Artif. Intell., vol. 33, no. 1, pp. 8295–8302, 2019.
Crossref Google Scholar
[31]
S. H. Hou, C. S. Cao, X. Liu, and Y. Z. Huang, Gait lateral network: Learning discriminative and compact representations for gait recognition, in Proc. European Conf. on Computer Vision, Glasgow, UK, pp. 382–398, 2020.
Crossref
[32]
S. Yu, D. Tan, and T. Tan, A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition, in Proc. 18th Int. Conf. Pattern Recognition-Volume 04, Cambridge, UK, 2006, pp. 441–444.
[33]

N. Takemura, Y. Makihara, D. Muramatsu, T. Echigo, and Y. Yagi, Multi-view large population gait dataset and its performance evaluation for cross-view gait recognition, IPSJ Transactions on Computer Vision and Applications, vol. 10, pp. 1–14, 2018.
Crossref Google Scholar
[34]
K. Shiraga, Y. Makihara, D. Muramatsu, T. Echigo, and Y. Yagi, Geinet: View-invariant gait recognition using a convolutional neural network, in Proc. 2016 Int. Conf. on Biometrics (ICB), Halmstad, Sweden, pp. 1–8, 2016.
Crossref
Tsinghua Science and Technology
Volume 30 Issue 1,
February 2025
Pages 345-356
DOI: 10.26599/TST.2023.9010089
Cite this article:
Wu Z, Cui Y. GaitFFDA: Feature Fusion and Dual Attention Gait Recognition Model. Tsinghua Science and Technology, 2025, 30(1): 345-356. https://doi.org/10.26599/TST.2023.9010089

778

Views

278

Downloads

0

Crossref

0

Web of Science

0

Scopus

0

CSCD

Altmetrics
Received: 04 August 2023
Revised: 22 August 2023
Accepted: 26 August 2023
Published: 11 September 2024
© The Author(s) 2025.

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).
Return