Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (1): 157-163.DOI: 10.11772/j.issn.1001-9081.2020060890

Special Issue: 第八届中国数据挖掘会议(CCDM 2020)

• China Conference on Data Mining 2020 (CCDM 2020) • Previous Articles     Next Articles

Capsule network based on sharing transformation matrix and its cross-view gait recognition fused with view features

LI Kai, YUE Bingjie   

  1. School of Cyber Security and Computer, Hebei University, Baoding Hebei 071002, China
  • Received:2020-05-31 Revised:2020-08-07 Online:2021-01-10 Published:2020-11-12
  • Supported by:
    This work is partially supported by the Natural Science Foundation of Hebei Province (F2018201060).


李凯, 岳秉杰   

  1. 河北大学 网络空间安全与计算机学院, 河北 保定 071002
  • 通讯作者: 李凯
  • 作者简介:李凯(1963-),男,河北保定人,教授,博士,主要研究方向:机器学习、模式识别;岳秉杰(1995-),男,河北石家庄人,硕士研究生,主要研究方向:机器学习、计算机视觉。
  • 基金资助:

Abstract: Gait recognition has the advantages of requiring no contact, non-invasion and easy detection. However, for the cross-view gait recognition, the contour of pedestrians varies with the change of people's viewpoints, thus affecting the performance of gait recognition. Therefore, a capsule network with sharing transformation matrix and its improved dynamic routing algorithm were proposed, which reduce the network training parameters. On this basis, by fusing the view features and using Triplet loss and Margin loss, a cross-view gait recognition model fused with view features was proposed. Experimental result on CASIA-B dataset show that it is feasible to extract gait features using the capsule network with sharing transformation matrix. Under the conditions of normal walking, carrying a bag, and wearing a coat, the proposed model fusing view features has the recognition accuracy improved by 4.13% compared to the cross-view gait recognition method based on convolutional neural network, and has better performance for gait recognition across large views.

Key words: gait recognition, transformation matrix, capsule network, view feature, cross-view

摘要: 步态识别具有非接触性、非侵犯性、易感知等优势,然而,在跨视角的步态识别中,行人的轮廓会随人的视角的变化而不同,从而影响步态识别的性能。为此,提出了共享转换矩阵的胶囊网络及其改进的动态路由算法,从而减少了网络训练参数。在此基础上,通过融合视角特征,利用Triplet损失与Margin损失提出了融合视角特征的跨视角步态识别模型。在CASIA-B数据集上的实验结果表明,使用共享转换矩阵的胶囊网络提取步态特征是有效的,在正常行走、携带背包、穿戴外套条件下,所提融合视角特征的模型在识别准确率上比基于卷积神经网络的跨视角步态识别方法提高了4.13%,且对跨较大视角的步态识别具有更好的性能。

关键词: 步态识别, 转换矩阵, 胶囊网络, 视角特征, 跨视角

CLC Number: