Street View Imagery in Traffic Crash and Road Safety Analysis: A Review

IF 2 4区社会学 Q3 ENVIRONMENTAL STUDIES

Applied Spatial Analysis and Policy Pub Date : 2025-04-24 DOI:10.1007/s12061-025-09653-7

Xinyue Ye, Shoujia Li, Wenjing Gong, Xiao Li, Xinyu Li, Bahar Dadashova, Wei Li, Jiaxin Du, Dayong Wu

{"title":"Street View Imagery in Traffic Crash and Road Safety Analysis: A Review","authors":"Xinyue Ye, Shoujia Li, Wenjing Gong, Xiao Li, Xinyu Li, Bahar Dadashova, Wei Li, Jiaxin Du, Dayong Wu","doi":"10.1007/s12061-025-09653-7","DOIUrl":null,"url":null,"abstract":"<div><p>Preventing traffic crashes presents a formidable challenge due to the intricate interplay between drivers and other participants within a complex urban infrastructure. In recent years, increasing studies on road safety involved computer vision and machine learning to detect visual features from street view imagery (SVI) and explore their impacts on crashes, though the recent progress is poorly understood. This paper conducted a comprehensive review of existing literature to investigate how SVI has been used in traffic crashes and road safety studies, utilizing a broad database collection including Scopus, Web of Science, and Transport Research International Documentation. We categorized SVI-generated features into two types of factors, explored their relationship with traffic crashes, and examined the prevalent detection models. Our review demonstrated that SVI plays an important role in capturing road design and driving environment factors, which significantly influence the frequency and risk of traffic crashes. These findings underscore the significant impact of these street visual factors on road safety. Through a systematic review of recent progress, we also identified challenges and future research opportunities for SVI applications in traffic crash study, such as the potential use of large language models.</p></div>","PeriodicalId":46392,"journal":{"name":"Applied Spatial Analysis and Policy","volume":"18 2","pages":""},"PeriodicalIF":2.0000,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Spatial Analysis and Policy","FirstCategoryId":"90","ListUrlMain":"https://link.springer.com/article/10.1007/s12061-025-09653-7","RegionNum":4,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENVIRONMENTAL STUDIES","Score":null,"Total":0}

引用次数: 0

Abstract

Preventing traffic crashes presents a formidable challenge due to the intricate interplay between drivers and other participants within a complex urban infrastructure. In recent years, increasing studies on road safety involved computer vision and machine learning to detect visual features from street view imagery (SVI) and explore their impacts on crashes, though the recent progress is poorly understood. This paper conducted a comprehensive review of existing literature to investigate how SVI has been used in traffic crashes and road safety studies, utilizing a broad database collection including Scopus, Web of Science, and Transport Research International Documentation. We categorized SVI-generated features into two types of factors, explored their relationship with traffic crashes, and examined the prevalent detection models. Our review demonstrated that SVI plays an important role in capturing road design and driving environment factors, which significantly influence the frequency and risk of traffic crashes. These findings underscore the significant impact of these street visual factors on road safety. Through a systematic review of recent progress, we also identified challenges and future research opportunities for SVI applications in traffic crash study, such as the potential use of large language models.

查看原文本刊更多论文

街景图像在交通事故与道路安全分析中的应用综述

在复杂的城市基础设施中，由于驾驶员和其他参与者之间错综复杂的相互作用，预防交通事故是一项艰巨的挑战。近年来，越来越多的道路安全研究涉及计算机视觉和机器学习来检测街景图像（SVI）的视觉特征并探索其对碰撞的影响，尽管最近的进展知之甚少。本文利用包括Scopus、Web of Science和Transport Research International Documentation在内的广泛数据库，对现有文献进行了全面的回顾，以调查SVI在交通事故和道路安全研究中的应用。我们将svi生成的特征分为两类因素，探讨了它们与交通事故的关系，并检查了流行的检测模型。我们的研究表明，SVI在捕捉道路设计和驾驶环境因素方面发挥了重要作用，这些因素对交通事故的频率和风险有显著影响。这些发现强调了这些街道视觉因素对道路安全的重大影响。通过对最近进展的系统回顾，我们还确定了SVI在交通碰撞研究中应用的挑战和未来的研究机会，例如大型语言模型的潜在使用。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Applied Spatial Analysis and Policy Multiple-

CiteScore

3.80

自引率

5.30%

发文量

期刊介绍： Description The journal has an applied focus: it actively promotes the importance of geographical research in real world settings It is policy-relevant: it seeks both a readership and contributions from practitioners as well as academics The substantive foundation is spatial analysis: the use of quantitative techniques to identify patterns and processes within geographic environments The combination of these points, which are fully reflected in the naming of the journal, establishes a unique position in the marketplace. RationaleA geographical perspective has always been crucial to the understanding of the social and physical organisation of the world around us. The techniques of spatial analysis provide a powerful means for the assembly and interpretation of evidence, and thus to address critical questions about issues such as crime and deprivation, immigration and demographic restructuring, retailing activity and employment change, resource management and environmental improvement. Many of these issues are equally important to academic research as they are to policy makers and Applied Spatial Analysis and Policy aims to close the gap between these two perspectives by providing a forum for discussion of applied research in a range of different contexts Topical and interdisciplinaryIncreasingly government organisations, administrative agencies and private businesses are requiring research to support their ‘evidence-based’ strategies or policies. Geographical location is critical in much of this work which extends across a wide range of disciplines including demography, actuarial sciences, statistics, public sector planning, business planning, economics, epidemiology, sociology, social policy, health research, environmental management. FocusApplied Spatial Analysis and Policy will draw on applied research from diverse problem domains, such as transport, policing, education, health, environment and leisure, in different international contexts. The journal will therefore provide insights into the variations in phenomena that exist across space, it will provide evidence for comparative policy analysis between domains and between locations, and stimulate ideas about the translation of spatial analysis methods and techniques across varied policy contexts. It is essential to know how to measure, monitor and understand spatial distributions, many of which have implications for those with responsibility to plan and enhance the society and the environment in which we all exist. Readership and Editorial BoardAs a journal focused on applications of methods of spatial analysis, Applied Spatial Analysis and Policy will be of interest to scholars and students in a wide range of academic fields, to practitioners in government and administrative agencies and to consultants in private sector organisations. The Editorial Board reflects the international and multidisciplinary nature of the journal.