Please use this identifier to cite or link to this item:

http://hdl.handle.net/10609/128467
Title: Explainable, automated urban interventions to improve pedestrian and vehicle safety
Author: Bustos Rodriguez, Maria Cristina
Rhoads Everett, Daniel
Solé Ribalta, Albert
Masip Rodo, David  
Arenas Moreno, Àlex
Lapedriza Garcia, Agata
Borge Holthoefer, Javier  
Others: Universitat Oberta de Catalunya. Internet Interdisciplinary Institute (IN3)
Universitat Oberta de Catalunya (UOC)
MIT Media Lab
Keywords: deep learning
Google Street View
mapillary
pedestrian traffic safety
traffic safety
Issue Date: 23-Oct-2020
Publisher: Transportation Research Part C: Emerging Technologies
Citation: C. Bustos, D. Rhoads, A. Solé-Ribalta, D. Masip, A. Arenas, A. Lapedriza, J. Borge-Holthoefer. Explainable, automated urban interventions to improve pedestrian and vehicle safety, Transportation Research Part C: Emerging Technologies, Volume 125, 2021. doi: https://doi.org/10.1016/j.trc.2021.103018
Project identifier: info:eu-repo/grantAgreement/SPIP2017-02263
info:eu-repo/grantAgreement/TIN2015-66951-C2-2-R
info:eu-repo/grantAgreement/RTI2018-095232-B-C22
Also see: https://doi.org/10.1016/j.trc.2021.103018
Abstract: At the moment, urban mobility research and governmental initiatives are mostly focused on motor-related issues, e.g. the problems of congestion and pollution. And yet, we cannot disregard the most vulnerable elements in the urban landscape: pedestrians, exposed to higher risks than other road users. Indeed, safe, accessible, and sustainable transport systems in cities are a core target of the UN's 2030 Agenda. Thus, there is an opportunity to apply advanced computational tools to the problem of traffic safety, in regards especially to pedestrians, who have been often overlooked in the past. This paper combines public data sources, large-scale street imagery and computer vision techniques to approach pedestrian and vehicle safety with an automated, relatively simple, and universally-applicable data-processing scheme. The steps involved in this pipeline include the adaptation and training of a Residual Convolutional Neural Network to determine a hazard index for each given urban scene, as well as an interpretability analysis based on image segmentation and class activation mapping on those same images. Combined, the outcome of this computational approach is a fine-grained map of hazard levels across a city, and an heuristic to identify interventions that might simultaneously improve pedestrian and vehicle safety. The proposed framework should be taken as a complement to the work of urban planners and public authorities.
Language: English
URI: http://hdl.handle.net/10609/128467
ISSN: 0968-090XMIAR
Appears in Collections:Articles

Share:
Export:
Files in This Item:
File Description SizeFormat 
BRSRMALB_R2.pdfarticle22.3 MBAdobe PDFView/Open
BRSRMALB_si_R2.pdfdata source16.17 MBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons