基于非对称双路识别网络的步态识别方法

doi:10.3778/j.issn.1002-8331.2008-0355

摘要/Abstract

摘要： 步态作为一种人体躯干、关节、上下肢及各肌群的周期性行为模式，是可用于身份识别过程的一种重要生物特征。针对现有的步态识别方法大都是基于步态轮廓图或者步态能量图提取的全局特征，而忽视了对细粒度步态信息的有效利用的问题，提出了一种包括全局通路和局部通路的非对称双路识别网络。其中全局通路采用三元组损失函数，用于提取步态的全局时空特征；局部通路采用交叉熵损失函数，用于识别步态中显著不同的局部特征。此外，在局部通路中加入了一个显著性特征检测器模块，用于实现有效的细粒度步态信息识别。在公开数据集CASIA-B和OU-ISIR-LP上进行了对比实验，结果表明，在跨视角和跨场景的环境下，该方法相对现有方法在步态识别的准确率方面都有显著提升。

关键词: 步态识别, 非对称双路网络, 显著性特征检测器

Abstract: As a periodic behavior pattern of the human torso, joints, lower and upper limbs, gait is an important biological feature that can be used in the identification process. In view of the fact that most of existing gait recognition methods are based on the global features extracted from gait silhouettes or gait energy images and neglect the effective use of fine-grained gait information, an asymmetric two-path identification network including the global path and the local path is proposed. The global path uses a triple loss function to extract the global spatio-temporal features of gait, while the local path uses a cross-entropy loss function to identify significantly different local features in gait. In addition, a novel module named salient local feature detector is added to the local path for recognizing fine-grained gait information effectively. Finally, comparative experiments are conducted on public datasets CASIA-B and OU-ISIR-LP, the results show that, in the cross-view and cross-scenario environment, the proposed method has a significant improvement in recognition accuracy compared to the existing methods.

Key words: gait recognition, asymmetric two-path network, salient local feature detector

周潇涵, 王修晖. 基于非对称双路识别网络的步态识别方法[J]. 计算机工程与应用, 2022, 58(4): 150-156.

ZHOU Xiaohan, WANG Xiuhui. Novel Gait Recognition Method Based on Asymmetric Two-Path Network[J]. Computer Engineering and Applications, 2022, 58(4): 150-156.

参考文献

[1] HAN J，BHANU B.Individual recognition using gait energy image[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2006，28（2）：316-322.
[2] ARIYANTO G，NIXON M S.Model-based 3D gait biometrics[C]//2011 International Joint Conference on Biometrics，2011：1-7.
[3] MURAMATSU D，MAKIHARA Y，YAGI Y，et al.Cross-view gait recognition by fusion of multiple transformation consistency measures[J].IET Biometrics，2015，4（2）：62-73.
[4] MURAMATSU D，MAKIHARA Y，YAGI Y，et al.View transformation model incorporating quality measures for cross-view gait recognition[J].IEEE Transactions on Systems，Man，and Cybernetics，2016，46（7）：1602-1615.
[5] SHIRAGA K，MAKIHARA Y，MURAMATSU D，et al.GEINet：view-invariant gait recognition using a convolutional neural network[C]//2016 International Conference on Biometrics，2016：1-8.
[6] WU Z，HUANG Y，WANG L，et al.A comprehensive study on cross-view gait based human identification with deep CNNs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2016，39（2）：209-226.
[7] 冯世灵，王修晖.结合非局部与分块特征的跨视角步态识别[J].模式识别与人工智能，2019，32（9）：821-827.
FENG S L，WANG X H.Cross-view gait recognition combined with non-local and part-level features[J].Pattern Recognition and Artificial Intelligence，2019，32（9）：821-827.
[8] WOLF T，BABAEE M，RIGOLL G，et al.Multi-view gait recognition using 3D convolutional neural networks[C]//2016 International Conference on Image Processing，2016：4165-4169.
[9] TONG S，FU Y，YUE X，et al.Multi-view gait recognition based on a spatial-temporal deep neural network[J].IEEE Access，2018，6：57583-57596.
[10] CHAO H，HE Y，ZHANG J，et al.GaitSet：regarding gait as a set for cross-view gait recognition[C]//33rd AAAI Conference on Artificial Intelligence，2019：8126-8133.
[11] HE Y，ZHANG J，SHAN H，et al.Multi-task GANs for view-specific feature learning in gait recognition[J].IEEE Transactions on Information Forensics and Security，2019，14（1）：102-113.
[12] YU S，CHEN H，REYES E B，et al.GaitGAN：invariant gait feature extraction using generative adversarial networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition，2017：532-539.
[13] ZHANG Z，TRAN L，YIN X，et al.Gait recognition via disentangled representation learning[C]//2019 IEEE Conference on Computer Vision and Pattern Recognition，2019：4710-4719.
[14] FU Y，WEI Y，ZHOU Y，et al.Horizontal pyramid matching for person re-identification[C]//33rd AAAI Conference on Artificial Intelligence，2019：8295-8302.
[15] ZHAO B，FENG J，WU X，et al.A survey on deep learning-based fine-grained object classification and semantic segmentation[J].International Journal of Automation and Computing，2017，14（2）：119-135.
[16] WANG Y，MORARIU V I，DAVIS L S，et al.Learning a discriminative filter bank within a CNN for fine-grained recognition[C]//2018 IEEE Conference on Computer Vision and Pattern Recognition，2018：4148-4157.
[17] LIN M，CHEN Q，YAN S.Network in network[J].arXiv：1312.
4400，2013.
[18] HERMANS A，BEYER L，LEIBE B，et al.In defense of the triplet loss for person re-identification[J].arXiv：1703.
07737，2017.
[19] YU S，TAN D，TAN T，et al.A framework for evaluating the effect of view angle，clothing and carrying condition on gait recognition[C]//2006 International Conference on Pattern Recognition，2006：441-444.
[20] IWAMA H，OKUMURA M，MAKIHARA Y，et al.The OU-ISIR gait database comprising the large population dataset and performance evaluation of gait recognition[J].IEEE Transactions on Information Forensics and Security，2012，7（5）：1511-1521.
[21] KINGMAD P，BA J.Adam：a method for stochastic optimization[J].arXiv：1412.6980，2014.
[22] HU M，WANG Y，ZHANG Z，et al.View-invariant discriminative projection for multi-view gait-based human identification[J].IEEE Transactions on Information Forensics and Security，2013，8（12）：2034-2045.
[23] KUSAKUNNIRAN W，WU Q，ZHANG J，et al.Support vector regression for multi-view gait recognition based on local motion feature selection[C]//2010 IEEE Conference on Computer Vision and Pattern Recognition，2010：974-981.
[24] XING X，WANG K，YAN T，et al.Complete canonical correlation analysis with application to multi-view gait recognition[J].Pattern Recognition，2016，50：107-117.