作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2020, Vol. 46 ›› Issue (11): 1-11. doi: 10.19678/j.issn.1000-3428.0058107

• 热点与综述 • 上一篇    下一篇

基于深度学习的车辆再识别研究进展

张小瑞a,b,c, 陈旋a, 孙伟b,d, 葛楷d   

  1. 南京信息工程大学 a. 计算机与软件学院;b. 江苏省大气环境与装备技术协同创新中心;c. 数字取证教育部工程研究中心;d. 自动化学院, 南京 210044
  • 收稿日期:2020-04-17 修回日期:2020-06-23 发布日期:2020-07-01
  • 作者简介:张小瑞(1979-),女,教授、博士,主研方向为图像处理、虚拟现实、数字取证;陈旋,硕士研究生;孙伟,副教授、博士;葛楷,本科生。
  • 基金资助:
    国家自然科学基金(61502240);江苏省自然科学基金(BK20191401)。

Progress of Vehicle Re-identification Research Based on Deep Learning

ZHANG Xiaoruia,b,c, CHEN Xuana, SUN Weib,d, GE Kaid   

  1. a. School of Computer and Software;b. Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology;c. Engineering Research Center of Digital Forensics of Ministry of Education;d. School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China
  • Received:2020-04-17 Revised:2020-06-23 Published:2020-07-01

摘要: 车辆再识别是计算机视觉领域一个前沿且具有挑战的课题,旨在非重叠视角域、多摄像头网络下进行车辆匹配。近年来,深度学习技术凭借其优越性能在车辆再识别任务中得到成功应用并成为研究热点。对此,阐述基于深度学习的车辆再识别研究现状,给出车辆再识别问题定义,指出只利用车牌和传统方法进行识别的局限性。从不同角度对现有方法进行分类和总结,列举4种常用的车辆再识别数据集,比较经典方法在其中的性能表现,为实际应用中合理选用提供参考。在此基础上,分析车辆再识别研究面临的挑战,并对其发展趋势进行展望。

关键词: 车辆再识别, 深度学习, 卷积神经网络, 智能交通系统, 计算机视觉

Abstract: Vehicle re-recognition is a frontier and challenging subject in the field of computer vision,which aims at vehicle matching in non-overlapping field of view and multi-camera network.In recent years,deep learning technology has been successfully applied in vehicle re-identification tasks and seen as a research hotspot by virtue of its superior performance.To this,this paper expounds the research status of vehicle re-recognition based on deep learning,gives the definition of the vehicle re-recognition problem,and points out the limitations of the traditional vehicle re-identification methods and number-plate-based re-identification methods.Then this paper classifies and summarizes existing methods from different perspectives.By listing four commonly used vehicle re-identification data sets and comparing the performance of the classical methods on them,this paper provides a reference for the rational selection of vehicle re-identification methods in practical applications.On this basis,the challenges to the vehicle re-identification research are analyzed,and the development trend is prospected.

Key words: vehicle re-identification, deep learning, Convolutional Neural Network(CNN), Intelligent Transportation System(ITS), computer vision

中图分类号: