Journal of Jilin University(Engineering and Technology Edition) ›› 2026, Vol. 56 ›› Issue (7): 1970-1983.doi: 10.13229/j.cnki.jdxbgxb.20250002

Previous Articles    

Gait recognition using dual⁃channel generative adversarial network with style encoding integration

Hang ZHOU1(),Ke-wei SONG1,Yuan-hao XU2,Ye-hong CHEN1,Jiang JIANG1   

  1. 1.School of Electronic and Information Engineering，Beijing Jiaotong University，Beijing 100044，China
    2.Municipal Engineering Branch，Shenzhen Luqiao Construction Group Co. ，Ltd. ，Shenzhen 518024，China
  • Received:2025-01-02 Online:2026-07-01 Published:2026-08-12

RICH HTML

 0   

PDF (PC)

2

Abstract:

Aiming at the problems of poor cross-view adaptability and insufficient model training stability existing in current gait recognition technologies， a dual-channel spatiotemporal convolutional generative adversarial network （GAN） model that incorporates style encoding was proposed. The model employs a dual-channel spatiotemporal convolutional network to extract complex spatiotemporal and gait features from gait images， while a style encoder is introduced to minimize the semantic discrepancies between the generated images and the original ones， thereby enhancing the stability of the generator. Experimental results on the CASIA-B dataset demonstrate that， compared to GaitGAN， the proposed model achieves recognition rate improvements of 23%， 28%， and 22% at three representative gait angles of 54°， 90°， and 126°， respectively. Additionally， the method shows strong applicability on the OU-MVLP large-scale cross-view gait database， achieving an average recognition accuracy of 89.1%， significantly improving cross-view gait recognition performance.

Key words: gait recognition, cross-view, spatio-temporal convolutional network, style encoder, generative adversarial network

CLC Number: 

  • TP391

Fig.1

Schematic diagram of the GaitGAN principle"

Fig.2

Schematic diagram of the GaitGAN network structure"

Fig.3

Overall network framework of the DSCGAN-SE"

Fig.4

Network architecture of DSCGAN-SE generator"

Table 1

Generator network architecture parameter settings"

区域划分层类型卷积核步长深度归一化激活函数
空间层卷积层1×91128-ReLU
空间层卷积层1×71128-ReLU
空间层卷积层1×51128-ReLU
空间层卷积层3×311BNReLU
特征连接全连接层-----
时间层卷积层9×11128-ReLU
时间层卷积层7×11128-ReLU
时间层卷积层5×11128-ReLU
时间层卷积层3×311BNReLU
特征连接全连接层-----
残差层卷积层9×9164BNReLU
残差层卷积层7×71128BNReLU
残差层卷积层5×51256BNReLU
残差层卷积层3×31128BNReLU
残差层卷积层3×3164-ReLU
残差层卷积层3×311-Tanh

Fig.5

Schematic diagram of the real discriminator Dop network architecture in DSCGAN-SE"

Table 2

Real discriminator Dop network architecture parameter settings"

层类型卷积核步长深度归一化激活函数
卷积层3×3264BNLeakyReLU
卷积层3×32128BNLeakyReLU
卷积层3×32256BNLeakyReLU
卷积层3×32384BNLeakyReLU
输出层3×331-Sigmoid

Fig.6

Schematic diagram of the identity discriminator Dtp network architecture in DSCGAN-SE"

Table 3

Identity discriminator Dtp network architecture parameter settings"

层类型卷积核步长深度归一化激活函数
卷积层3×3296BNLeakyReLU
卷积层3×32192BNLeakyReLU
卷积层3×32384BNLeakyReLU
卷积层3×32768BNLeakyReLU
输出层3×331-Sigmoid

Fig.7

Schematic diagram of the style encoder network architecture"

Table 4

Style encoder network architecture parameter settings"

层类型卷积核步长深度归一化激活函数
卷积层3×3164BNLeakyReLU
卷积层3×31128BNLeakyReLU
卷积层3×31256BNLeakyReLU
卷积层3×31128BNLeakyReLU
卷积层3×3164BNLeakyReLU
卷积层3×311-LeakyReLU
全连接层-----

Fig.8

Synthetic gait energy image（GEI）"

Fig.9

Recognition accuracy at various angles for three cases with the same viewpoint on CASIA-B dataset"

Fig.10

Recognition accuracy at various angles for three cases excluding the same perspective on CASIA-B dataset"

Table 5

Cross-perspective recognition accuracy of the CASIA-B dataset under normal conditions"

数据库视角/（°）检索库中11个视角
包含相同视角排除相同视角
00.980.86
180.980.88
360.980.89
540.980.88
720.980.87
900.980.89
1080.970.87
1260.970.88
1440.970.87
1620.980.85
1800.980.86

Table 6

Cross-perspective recognition accuracy of the CASIA-B dataset with a bag"

数据库视角/（°）检索库中11个视角
包含相同视角排除相同视角
00.750.57
180.740.58
360.750.59
540.760.59
720.730.59
900.740.60
1080.730.60
1260.740.59
1440.740.57
1620.740.57
1800.740.57

Table 7

Cross-perspective recognition accuracy of the CASIA-B dataset under coat wearing conditions"

数据库视角/（°）检索库中11个视角
包含相同视角排除相同视角
00.420.41
180.410.42
360.410.42
540.410.41
720.420.41
900.440.43
1080.420.42
1260.420.42
1440.410.41
1620.410.41
1800.410.41

Fig.11

Recognition accuracy at various angles for three cases excluding the same perspective on OU-MVLP Dataset"

Table 8

Recognition accuracy at various angles in the OU-MVLP dataset excluding identical viewpoints"

数据库视角/（°）检索库中14个视角
包含相同视角排除相同视角
00.880.87
150.880.87
300.870.86
450.870.86
600.890.88
750.930.92
900.940.94
1800.880.87
1950.870.86
2100.870.86
2250.880.86
2400.890.87
2550.880.87
2700.880.88

Table 9

Impact of dual-channel spatiotemporal convolution and style encoder on cross-view recognition accuracy based on the CASIA-B dataset"

网络模型验证角度平均值
54°90°126°
GaitGAN0.650.610.660.64
GaitGAN+双通道时空卷积网络+风格编码器0.880.890.880.88

Fig.12

Visualization results of DSCGAN-SE model's original viewpoint and target viewpoint gait image transformations based on the CASIA-B dataset"

Fig.13

Visualization results of DSCGAN-SE model's original viewpoint and target viewpoint gait image transformations based on the OU-MVLP dataset"

Table 10

Comparison of average recognition rates during normal walking （based on the CASIA-B dataset）"

模型验证角度
54°90°126°平均
GaitGAN0.650.610.660.64
TCC-GAN0.810.730.790.78
SE-CLGait0.760.760.690.73
Dtrain-GAN0.640.610.680.64
SA-GAN0.810.720.800.77
本文0.880.890.880.88

Table 11

Comparison of recognition accuracy of various methods on the OU-MVLP dataset"

视角/（°）基于全部14个视角的注册库
GEINetMvGGANGaitSetGaitGAN2FSEAMTSGM

本文

模型

平均值0.350.580.870.870.880.800.88
00.110.520.790.810.810.640.87
150.290.620.870.880.900.790.87
300.410.630.890.900.890.870.86
450.450.570.900.900.900.880.86
600.390.550.880.880.890.800.88
750.410.640.880.890.890.840.92
900.380.610.870.880.880.810.94
1800.140.540.810.830.830.650.87
1950.330.580.860.870.880.780.86
2100.430.590.890.890.890.850.86
2250.450.580.890.890.890.870.86
2400.390.560.870.870.880.790.86
2550.400.570.870.880.880.830.87
2700.360.560.860.860.860.790.87
[1] 李贻斌, 郭佳旻, 张勤.人体步态识别方法与技术[J].吉林大学学报: 工学版,2020, 50(1):1 -18.
Li Yi-bin, Guo Jia-min, Zhang Qin. Methods and technologies for human gait recognition[J]. Journal of Jilin University (Engineering and Technology Edition), 2020, 50(1): 1-18.
[2] Sepas-Moghaddam A, Etemad A. Deep gait recognition: a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(1): 264-284.
[3] 段成阁, 刘康康, 李福全. 步态识别技术综述[J]. 中国人民公安大学学报: 自然科学版, 2022, 28(4):75-80.
Duan Cheng-ge, Liu Kang-kang, Li Fu-quan. Overview of gait recognition technology[J]. Journal of People's Public Security University of China (Natural Science Edition), 2022, 28(4): 75-80.
[4] 刘晓芳, 周航, 韩权, 等. 基于视觉的步态识别研究综述[J]. 小型微型计算机系统,2018, 39(8): 1685-1692.
Liu Xiao-fang, Zhou Hang, Han Quan, et al. Review of vision-based gait recognition research[J]. Mini-Micro Systems, 2018, 39(8): 1685-1692.
[5] 刘相锋, 周航. 步态识别技术及其在视频监控中的应用[J]. 电视技术,2011, 35(1): 119-121.
Liu Xiang-feng, Zhou Hang. Gait recognition technology and its application in video surveillance[J]. Television Technology, 2011, 35(1): 119-121.
[6] 陈福仕, 沈尧, 周池春, 等. 无监督学习步态识别综述[J].计算机科学与探索,2024,18(8): 2014-2033.
Chen Fu-shi, Shen Yao, Zhou Chi-chun, et al. A review of unsupervised learning for gait recognition[J]. Computer Science and Exploration, 2024, 18(8): 2014-2033.
[7] Chao H Q, Wang K, He Y W, et al. GaitSet:cross-view gait recognition through utilizing gait as a deep set[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(7): 3467-3478.
[8] Limcharoen P, Khamsemanan N, Nattee C. Gait recognition and re-identification based on regional LSTM for 2-second walks[J].IEEE Access, 2021, 9: 112057-112068.
[9] Goodfellow I, Pougetabadie J, Mirza M, et al.Generative adversarial nets[C]∥Advances in Neural Information Processing Systems, Quebec, Canada, 2014: 2672-2680.
[10] Aljazaerly M A A, Makihara Y, Muramatsu D, et al. Batch hard contrastive loss and its application to cross-view gait recognition[J]. IEEE Access, 2023, 11: 31177-31187.
[11] Wang L H, Xiao P F, Zhang X L, et al. A fine-grained unsupervised domain adaptation framework for semantic segmentation of remote sensing images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2026,16: 4109-4121.
[12] Yu S, Chen H E, Reyes B G, et al. GaitGAN: invariant gait feature extraction using generative adversarial networks[C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA, 2017: 532-539.
[13] Yu S Q, Tan D L, Tan T N. A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition[C]∥Proc of the 18th International Conference on Pattern Recognition, Washington, USA, 2006: 441-444.
[14] Xu C, Makihara Y, Liao R, et al. Applications: real-time gait-based age estimation and gender classification from a single image[C]∥Proceedings of the 2021 IEEE/CVF Winter Conference on Applications of Computer Vision, online, 2021: 3459-3469.
[15] 王宇, 夏懿. 基于双通道循环一致性GAN的跨视角步态识别研究[J]. 计算机应用研究, 2022, 39(1):259-264.
Wang Yu, Xia Yi. Cross-view gait recognition based on dual-channel cycle-consistent GAN[J]. Computer Applications and Research, 2022, 39(1): 259-264.
[16] 张云佐, 董旭. 基于双分支时空步态特征融合的深度学习步态识别[J]. 控制与决策, 2024,39(4): 1403-1408.
Zhang Yun-zhuo, Dong Xu. Gait recognition based on dual-branch spatiotemporal feature fusion using deep learning[J]. Control and Decision, 2024, 39(4): 1403-1408.
[17] 李凯, 曹可凡, 沈皓凝. 基于步态序列的跨视角步态识别[J]. 河北大学学报: 自然科学版, 2021, 41(3):311-320.
Li Kai, Cao Ke-fan, Shen Hao-ning. Cross-view gait recognition based on gait sequences[J]. Journal of Hebei University (Natural Science Edition), 2021, 41(3): 311-320.
[18] 张红颖, 包雯静. 融合自注意力机制的生成对抗网络跨视角步态识别[J]. 中国图象图形学报, 2022, 27(4): 1097-1109.
Zhang Hong-ying, Bao Wen-jing. Cross-view gait recognition using generative adversarial networks with self-attention mechanism[J]. Journal of Image and Graphics, 2022, 27(4): 1097-1109.
[19] Shiraga K, Makihara Y, Muramatsu D, et al. GEINet: view-invariant gait recognition using a convolutional neural network[C]∥Proceedings of the 2016 International Conference on Biometrics. Halmstad: Sweden, 2016: 1-8.
[20] Yu S, Liao R, An W, et al. GaitGANv2: Invariant gait feature extraction using generative adversarial networks[J]. Pattern Recognition, 2019, 87: 179-189.
[21] Chen X, Luo X, Weng J, et al. Multi-view gait image generation for cross-view gait recognition[J]. IEEE Transactions on Image Processing, 2021,30: 3041-3055.
[22] 陈万志, 唐浩博, 王天元. 融合轮廓增强和注意力机制的改进GaitSet步态识别方法[J]. 电子测量与仪器学报, 2024, 38(1): 203-210.
Chen Wan-zhi, Tang Hao-bo, Wang Tian-yuan. Improved GaitSet gait recognition method integrating contour enhancement and attention mechanism[J]. Journal of Electronic Measurement and Instrumentation, 2024, 38(1): 203-210.
[23] 汪堃, 雷一鸣, 张军平. 基于双流步态网络的跨视角步态识别[J]. 模式识别与人工智能, 2020, 33(5):383-392.
Wang Kun, Lei Yi-ming, Zhang Jun-ping. Cross-view gait recognition based on dual-stream gait network[J]. Pattern Recognition and Artificial Intelligence, 2020, 33(5): 383-392.
[1] Xin-hui LIU,Zhuo-qun CHEN,Yan LYU. Review of industrial fault diagnosis based on deep learning [J]. Journal of Jilin University(Engineering and Technology Edition), 2026, 56(7): 1759-1779.
[2] Le-ping LIN,Zhi SU,Ning OUYANG. Efficient gating and target region attention based real-time video super-resolution [J]. Journal of Jilin University(Engineering and Technology Edition), 2026, 56(3): 819-829.
[3] Yan PIAO,Ji-yuan KANG. RAUGAN：infrared image colorization method based on cycle generative adversarial networks [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(8): 2722-2731.
[4] Guang-wen LIU,Qi-ying ZHAO,Chao WANG,Lian-yu Gao,Hua CAI,Qiang FU. Progressive recursive generative adversarial network-based single-image rain removal algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(4): 1363-1373.
[5] Yuan JI,Ya-qi YU. Optimization algorithm for speech facial video generation based on dense convolutional generative adversarial networks and keyframes [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(3): 986-992.
[6] Hong ZHAO,Yu-xuan MA,Fu-rong SONG. Image adversarial examples generation based on Diff⁃AdvGAN [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(12): 4052-4062.
[7] Xiang-long LUO,Xin-yu WEI,Mao-jun ZHAO,Ruo-chen LIU. Image dehazing algorithm based on contrast learning and generative adversarial network [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(10): 3296-3308.
[8] Xiao-yue WEN,Guo-min QIAN,Hua-hua KONG,Yue-jie MIU,Dian-hai WANG. TrafficPro： a framework to predict link speeds on signalized urban traffic network [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(8): 2214-2222.
[9] Xin-gang GUO,Ying-chen HE,Chao CHENG. Noise-resistant multistep image super resolution network [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(7): 2063-2071.
[10] Feng-feng ZHOU,Tao YU,Yu-si FAN. Generative adversarial autoencoder integrated voting algorithm based on mass spectral data [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(10): 2969-2977.
[11] Yun-zuo ZHANG,Xu DONG,Zhao-quan CAI. Multi view gait cycle detection by fitting geometric features of lower limbs [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(9): 2611-2619.
[12] Wei LYU,Jia-ze HAN,Jing-hui CHU,Pei-guang JING. Multi⁃modal self⁃attention network for video memorability prediction [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(4): 1211-1219.
[13] Chun-yan ZENG,Kang YAN,Zhi-feng WANG,Zheng-hui WANG. Multi-scale generative adversarial network for image compressed sensing and reconstruction algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(10): 2923-2931.
[14] Hao-yu TIAN,Xin MA,Yi-bin LI. Skeleton-based abnormal gait recognition： a survey [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(4): 725-737.
[15] Le-ping LIN,Zeng-tong LU,Ning OUYANG. Face reconstruction and recognition in non⁃cooperative scenes [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(12): 2941-2946.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright © Journal of Jilin University(Engineering and Technology Edition), All Rights Reserved.
Tel: +86-431-85095297　Fax: +86-431-85094074　E-mail: xbgxb@jlu.edu.cn
Powered by Beijing Magtech Co. Ltd