Articles producció científica> Enginyeria Informàtica i Matemàtiques

Explainable, automated urban interventions to improve pedestrian and vehicle safety

  • Identification data

    Identifier: imarina:9189728
    Authors:
    Bustos, CRhoads, DSole-Ribalta, AMasip, DArenas, ALapedriza, ABorge-Holthoefer, J
    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.
  • Others:

    Author, as appears in the article.: Bustos, C; Rhoads, D; Sole-Ribalta, A; Masip, D; Arenas, A; Lapedriza, A; Borge-Holthoefer, J
    Department: Enginyeria Informàtica i Matemàtiques
    URV's Author/s: Arenas Moreno, Alejandro / BORGE HOLTHOEFER, JAVIER
    Keywords: Vehicles Urban transport Transportation safety Transportation planning Transportation development Traffic safety Sustainable transport systems Sustainability Public data source Public authorities Pedestrian safety Pedestrian Numerical model Mapillary Machine learning Internet Image segmentation Hazards Governmental initiatives Google street view Deep learning Data handling Convolutional neural networks Computer vision techniques Computational tools Computational methods Computational approach Artificial neural network Activation mapping Activation analysis
    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.
    Thematic Areas: Transportation science & technology Transportation Management science and operations research Engenharias iv Engenharias iii Engenharias i Computer science applications Civil and structural engineering Ciencias sociales Ciência da computação Automotive engineering
    licence for use: https://creativecommons.org/licenses/by/3.0/es/
    Author's mail: alexandre.arenas@urv.cat
    Author identifier: 0000-0003-0937-0334
    Record's date: 2024-09-28
    Papper version: info:eu-repo/semantics/publishedVersion
    Link to the original source: https://www.sciencedirect.com/science/article/pii/S0968090X21000498?via%3Dihub
    Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
    Papper original source: Transportation Research Part C-Emerging Technologies. 125 (103018): 103018-
    APA: Bustos, C; Rhoads, D; Sole-Ribalta, A; Masip, D; Arenas, A; Lapedriza, A; Borge-Holthoefer, J (2021). Explainable, automated urban interventions to improve pedestrian and vehicle safety. Transportation Research Part C-Emerging Technologies, 125(103018), 103018-. DOI: 10.1016/j.trc.2021.103018
    Article's DOI: 10.1016/j.trc.2021.103018
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2021
    Publication Type: Journal Publications
  • Keywords:

    Automotive Engineering,Civil and Structural Engineering,Computer Science Applications,Management Science and Operations Research,Transportation,Transportation Science & Technology
    Vehicles
    Urban transport
    Transportation safety
    Transportation planning
    Transportation development
    Traffic safety
    Sustainable transport systems
    Sustainability
    Public data source
    Public authorities
    Pedestrian safety
    Pedestrian
    Numerical model
    Mapillary
    Machine learning
    Internet
    Image segmentation
    Hazards
    Governmental initiatives
    Google street view
    Deep learning
    Data handling
    Convolutional neural networks
    Computer vision techniques
    Computational tools
    Computational methods
    Computational approach
    Artificial neural network
    Activation mapping
    Activation analysis
    Transportation science & technology
    Transportation
    Management science and operations research
    Engenharias iv
    Engenharias iii
    Engenharias i
    Computer science applications
    Civil and structural engineering
    Ciencias sociales
    Ciência da computação
    Automotive engineering
  • Documents:

  • Cerca a google

    Search to google scholar