摘要
在智能交通系统中,车辆作为最普及的交通工具,常被不法分子利用,使其成为一种安全隐患,因此,实现监控设备下的车辆身份识别一直是一个研究热点。车辆标志(简称车标)是车辆的特殊身份,包含着车辆品牌制造商的基本信息,相比车牌、车型和车色,车标具有相对独立和可靠的特性。车辆标志识别能够快速、精准地缩小车辆查询范围,为案件侦破、交通自动化管理等有效降低搜索成本,因此车辆标志识别在车辆身份识别中尤其重要。本文对近十年内的主流车标识别方法进行了系统概述,为车标识别领域的后续研究者提供参考。1)简要阐述了在智能交通系统中车标识别技术的研究背景和重要性。2)根据车标识别过程中是否依赖手工提取特征,将目前国际主流的车标识别方法归纳为传统的车标识别方法和基于深度学习的车标识别方法,并分别总结了这两类方法的优劣。随后,分类、梳理和评价了这两类方法中现有的各种算法。3)针对车标数据集稀少导致难以评价各类算法性能、影响车标识别研究进展的问题,详细介绍了3种公开车标数据集:XMU(Xiamen University Vehicle Logo Dataset)、HFUT-VL(Vehicle Logo Dataset from Hefei University of Technology)和VLD-45(Vehicle Logo Dataset-45),并给出下载地址,可供研究者进行实验和测试。4)描述了4种常用的评价指标,并在公开数据集上基于这些评价指标对车标识别方法开展实验,并对实验结果进行比较和分析。5)综述现有车标识别技术中存在的一些问题与挑战,对未来车标识别的研究方向做出预测和展望。
In intelligent transportation systems(ITSs),vehicles are the most popular means of transportation.However,they become a security risk due to the frequent use by lawless elements.Thus,vehicle identification with use of monitoring equipment has become a research hotspot.Vehicle logo is the special identity of the vehicle,and it contains basic informa⁃tion of a vehicle brand manufacturer.Compared with the license plate,model,and color of the vehicle,the vehicle logo is relatively independent and reliable.The recognition of vehicle logos rapidly and accurately narrows down the scope of vehicle search,which makes it important in vehicle identification.This paper presents a systematic overview of the mainstream methods of vehicle logo recognition from the last decade to provide a reference for researchers in the field.The ini⁃tial discussion focuses on vehicle logo recognition,which is continuously under construction and development.Vehicle identification provides a strong support to the development and maturity of ITSs.Vehicle identity comprises four parts:vehicle logos,license plates,vehicle models,and vehicle colors.For the reduced algorithmic costs and increased accu⁃racy of vehicle identity recognition,vehicle logo recognition is the most suitable to be implemented for current needs.Sec⁃ond,the current international mainstream methods for vehicle logo recognition fall under classical and deep learning-based approaches,depending on their reliance on manual feature extraction.This section summarizes the advantages,disadvan⁃tages,and main ideas of both types of methods.Classical methods for the recognition of vehicle logos can design propri⁃etary solutions for problems specific to vehicle logo recognition.Such methods show minimal dependence on the number of training samples and had low hardware requirements.However,they require manual feature extraction and cannot learn vehicle logo features independently for automatic recognition.The classical method for vehicle logo recognition involves the following s
作者
李杨
肖建力
Li Yang;Xiao Jianli(School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China)
出处
《中国图象图形学报》
CSCD
北大核心
2024年第9期2650-2671,共22页
Journal of Image and Graphics
基金
国家自然科学基金项目(61603257)。
关键词
智能交通系统(ITSs)
车标识别
特征提取
图像分类
深度学习
综述
intelligent transportation systems(ITSs)
vehicle logo recognition
feature extraction
image classification
deep learning
review
