Urban visual clusters and road transport fatalities: A global city-level image analysis

Road traffic crashes are among the leading causes of death and injury worldwide. While urban planning and design are known to influence road safety, it is not clear how features of the built environment contribute to traffic fatalities. In this study, we analyze road fatality data from 106 cities ac...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhuangyuan Fan, Becky P.Y. Loo
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Communications in Transportation Research
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772424725000332
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849426934595846144
author Zhuangyuan Fan
Becky P.Y. Loo
author_facet Zhuangyuan Fan
Becky P.Y. Loo
author_sort Zhuangyuan Fan
collection DOAJ
description Road traffic crashes are among the leading causes of death and injury worldwide. While urban planning and design are known to influence road safety, it is not clear how features of the built environment contribute to traffic fatalities. In this study, we analyze road fatality data from 106 cities across six continents via a combination of computer vision and unsupervised clustering on 26.8 million Google Street View images. We use deep learning tools to extract 25 features from the images. Among these features, 19 are relatively static built environment features, and 6 are dynamic usage-related features (such as pedestrians, cars, buses, and bikes). On the basis of the built environment features, we group the urban streetscapes into six distinct visual clusters. We then examine how these clusters are related to city-level road fatality rates when various control variables (e.g., population size, carbon emissions, income, road length, road safety policy, and continent) and dynamic features are combined. Our findings show that cities with Open Arterials streetscape (extensive road surface, open-sky views, and railings) tend to have higher road fatality rates. After accounting for differences in the built environment, cities with better public transit (proxied by buses detected) tend to have fewer traffic deaths—specifically, a 1% increase in bus presence is linked to a 0.35% decrease in fatalities per 100,000 people. This study demonstrates the power of using widely available street view imagery to uncover global disparities in urban design and their connection to road safety.
format Article
id doaj-art-e4500bd53d9248999220bd65bcd9339e
institution Kabale University
issn 2772-4247
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Communications in Transportation Research
spelling doaj-art-e4500bd53d9248999220bd65bcd9339e2025-08-20T03:29:10ZengElsevierCommunications in Transportation Research2772-42472025-12-01510019310.1016/j.commtr.2025.100193Urban visual clusters and road transport fatalities: A global city-level image analysisZhuangyuan Fan0Becky P.Y. Loo1Department of Geography, The University of Hong Kong, Hong Kong, 999077, ChinaCorresponding author.; Department of Geography, The University of Hong Kong, Hong Kong, 999077, ChinaRoad traffic crashes are among the leading causes of death and injury worldwide. While urban planning and design are known to influence road safety, it is not clear how features of the built environment contribute to traffic fatalities. In this study, we analyze road fatality data from 106 cities across six continents via a combination of computer vision and unsupervised clustering on 26.8 million Google Street View images. We use deep learning tools to extract 25 features from the images. Among these features, 19 are relatively static built environment features, and 6 are dynamic usage-related features (such as pedestrians, cars, buses, and bikes). On the basis of the built environment features, we group the urban streetscapes into six distinct visual clusters. We then examine how these clusters are related to city-level road fatality rates when various control variables (e.g., population size, carbon emissions, income, road length, road safety policy, and continent) and dynamic features are combined. Our findings show that cities with Open Arterials streetscape (extensive road surface, open-sky views, and railings) tend to have higher road fatality rates. After accounting for differences in the built environment, cities with better public transit (proxied by buses detected) tend to have fewer traffic deaths—specifically, a 1% increase in bus presence is linked to a 0.35% decrease in fatalities per 100,000 people. This study demonstrates the power of using widely available street view imagery to uncover global disparities in urban design and their connection to road safety.http://www.sciencedirect.com/science/article/pii/S2772424725000332Road safetyImage analysisUrban visual clustersStreetscapeBuilt environmentUrban design
spellingShingle Zhuangyuan Fan
Becky P.Y. Loo
Urban visual clusters and road transport fatalities: A global city-level image analysis
Communications in Transportation Research
Road safety
Image analysis
Urban visual clusters
Streetscape
Built environment
Urban design
title Urban visual clusters and road transport fatalities: A global city-level image analysis
title_full Urban visual clusters and road transport fatalities: A global city-level image analysis
title_fullStr Urban visual clusters and road transport fatalities: A global city-level image analysis
title_full_unstemmed Urban visual clusters and road transport fatalities: A global city-level image analysis
title_short Urban visual clusters and road transport fatalities: A global city-level image analysis
title_sort urban visual clusters and road transport fatalities a global city level image analysis
topic Road safety
Image analysis
Urban visual clusters
Streetscape
Built environment
Urban design
url http://www.sciencedirect.com/science/article/pii/S2772424725000332
work_keys_str_mv AT zhuangyuanfan urbanvisualclustersandroadtransportfatalitiesaglobalcitylevelimageanalysis
AT beckypyloo urbanvisualclustersandroadtransportfatalitiesaglobalcitylevelimageanalysis