《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (6): 1884-1891.DOI: 10.11772/j.issn.1001-9081.2021040544

• 人工智能 • 上一篇    

基于联合条纹关系的车辆重识别

张廷萍1, 帅聪1(), 杨建喜1, 邹俊志2, 郁超顺3, 杜利芳3   

  1. 1.重庆交通大学 信息科学与工程学院, 重庆 400074
    2.重庆交通大学 土木工程学院, 重庆 400074
    3.重庆交通大学 交通运输学院, 重庆 400074
  • 收稿日期:2021-04-12 修回日期:2021-08-10 接受日期:2021-08-11 发布日期:2022-06-22 出版日期:2022-06-10
  • 通讯作者: 帅聪
  • 作者简介:张廷萍(1978—),女,贵州遵义人,教授,博士,主要研究方向:复杂网络节点重要度评估
    杨建喜(1977—),男,宁夏青铜峡人,教授,博士,主要研究方向:桥梁健康结构监测
    邹俊志(1994—),男,四川自贡人,硕士研究生,主要研究方向:桥梁健康结构监测
    郁超顺(1997—),男,上海人,硕士研究生,主要研究方向:车辆跟踪
    杜利芳(1997—),女,四川广元人,硕士研究生,主要研究方向:车辆重识别。
  • 基金资助:
    教育部人文社会科学研究一般项目(20YJAZH132);重庆市教委科学技术研究计划项目(KJZD?M202000702)

Re-identification of vehicles based on joint stripe relations

Tingping ZHANG1, Cong SHUAI1(), Jianxi YANG1, Junzhi ZOU2, Chaoshun YU3, Lifang DU3   

  1. 1.School of Information Science and Engineering,Chongqing Jiaotong University,Chongqing 400074,China
    2.School of Civil Engineering,Chongqing Jiaotong University,Chongqing 400074,China
    3.College of Traffic and Transportation,Chongqing Jiaotong University,Chongqing 400074,China
  • Received:2021-04-12 Revised:2021-08-10 Accepted:2021-08-11 Online:2022-06-22 Published:2022-06-10
  • Contact: Cong SHUAI
  • About author:ZHANG Tingping, born in 1978, Ph. D., professor. Her research interests include evaluation of node importance in complex networks.
    YANG Jianxi born in 1977, Ph. D., professor. His research interests include bridge health structure monitoring.
    ZOU Junzhi born in 1994, M. S. candidate. His research interests include bridge health structure monitoring.
    YU Chaoshun born in 1997, M. S. candidate. His research interests include vehicle tracking.
    DU Lifang born in 1997, M. S. candidate. Her research interests include vehicle re-identification.
  • Supported by:
    Humanities and Social Science Project of Ministry of Education(20YJAZH132);Science and Technology Research Program of Chongqing Municipal Education Commission(KJZD-M202000702)

摘要:

为了解决车辆重识别过程中因车辆特征图分块所导致的空间信息丢失问题,提出一种联合条纹特征之间关系的模块以弥补丢失的空间信息。首先,针对车辆特殊的物理结构,构建了一种双分支神经网络模型,对输出的特征图进行水平和垂直均等分割并在不同的神经网络分支上进行训练;然后,设计多激活值模块以减少噪声并丰富特征图信息;接着,使用三元组和交叉熵损失函数对不同的特征进行监督训练以约束类内距离并扩大类间距离;最后,设计批量归一化(BN)模块消除不同损失函数在优化方向上存在的差异,从而加速模型的收敛。使用所提方法在VeRi-776和VehicleID两个公共数据集上进行实验,结果表明该方法的Rank1值优于现有最好的方法VehicleNet,验证了其有效性。

关键词: 车辆重识别, 条纹关系, 特征图分块, 多激活值, 批量归一化

Abstract:

In order to solve the problem of spatial information loss caused by the splitting of vehicle feature maps in the process of vehicle re-identification, a module combining the relationship between stripe features was proposed to compensate for the lost spatial information. First, a two-branch neural network model was constructed for the special physical structure of the vehicle, and the output feature maps were divided horizontally and vertically equally and trained on different branches of the neural network. Then, a multi-activation value module was designed to reduce noise and enrich the feature map information. After that, triplet and cross-entropy loss functions were used to supervise the training of different features to restrict the intra-class distance and enlarge the inter-class distance. Finally, the Batch Normalization (BN) module was designed to eliminate the differences of different loss functions in the optimization direction, thereby accelerating the convergence of the model. Experimental results on two public datasets VeRi-776 and VehicleID show that the Rank1 value of the proposed method is better than that of the existing best method VehicleNet, which verifies the effectiveness of the proposed method.

Key words: vehicle re-identification, stripe relation, feature map splitting, multi-activation value, Batch Normalization (BN)

中图分类号: