Logo do repositório
 
Publicação

Automating city accessibility constraints mapping through AI‐assisted scanning of street view imagery

2025-12-13Artigo científico Acesso aberto
Ver registo simples
datacite.subject.fosEngenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática
datacite.subject.sdg11:Cidades e Comunidades Sustentáveis
dc.contributor.authorSilva Moreira, Rui
dc.contributor.authorMoita, Sérgio
dc.contributor.authorTorres, José Manuel
dc.contributor.authorAlberto Ribeiro Gouveia, Feliz
dc.contributor.authorDinis, Maria Alzira Pimenta
dc.contributor.authorFerreira, Diogo
dc.contributor.authorPereira, Madalena Sofia Araujo
dc.contributor.authorGuerreiro, Maria João S.
dc.contributor.editorZhou, Guyue
dc.date.accessioned2026-03-06T10:40:26Z
dc.date.available2026-03-06T10:40:26Z
dc.date.issued2025-12-13
dc.descriptionhttps://creativecommons.org/licenses/by-nc-nd/4.0/ CC BY-NC-ND 4.0
dc.description.abstractUrban environments often pose challenges for individuals with mobility impairments due to inadequate pedestrian infrastructure. In addition, the lack of accurate mapping of accessibility features limits the ability to monitor and address these constraints effectively. This paper introduces a framework for Automating City Accessibility Mapping using AI (ACAMAI), that is, provides an AI-assisted pipeline for the automated identification and geolocation of urban accessibility constraints using Google Street View (GSV) panoramas. The ACAMAI pipeline comprises two main stages: (i) training a YOLOv8 object detector to recognise accessibility-related features, such as curb ramps, missing ramps, obstacles and surface problems, in 2D sidewalk images; and (ii) scanning 360° GSV panoramas by extracting multiple perspective views to be analysed by the trained model. The model was trained on a combination of international (Project Sidewalk Dataset—PSD) and local (Porto Dataset—PTD) datasets, achieving high performance across classes, including 91% recall and 85% precision for curb ramps. In the panorama scanning stage, using a fine angular iterative step (2°) maximised the recall, reaching 90% for curb ramps and 93% for obstacles in a locally annotated dataset (GSV Panorama Porto Dataset—GSV-PPD). Although this improved detection coverage, it also led to a high number of redundant predictions, which contributed to a reduced overall precision. Finally, identified constraints are georeferenced and mapped onto OpenStreetMap (OSM), supporting scalable and inclusive urban planning.eng
dc.identifier.citationAPA7th: Moreira, R. S., Moita, S., Torres, J. M., Gouveia, F., Dinis, M. A. P., Ferreira, D., Araújo, M., & Guerreiro, M. J. S. (2025). Automating City Accessibility Constraints Mapping Through AI‐Assisted Scanning of Street View Imagery [Original Research]. IET Smart Cities, 7(1), 1-16, Article e70020. https://doi.org/10.1049/smc2.70020
dc.identifier.doi10.1049/smc2.70020
dc.identifier.issn2631-7680
dc.identifier.issn2631-7680
dc.identifier.urihttp://hdl.handle.net/10284/15104
dc.language.isoeng
dc.peerreviewedyes
dc.publisherInstitution of Engineering and Technology (IET)
dc.relationhttps://doi.org/10.54499/2022.09218.PTDC
dc.relation.hasversionhttps://ietresearch.onlinelibrary.wiley.com/doi/abs/10.1049/smc2.70020
dc.relation.ispartofIET Smart Cities
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectArtificial intelligence
dc.subjectCity design
dc.subjectData analytics and machine learning
dc.subjectData structures
dc.subjectGovernance
dc.subjectPlanning and policy
dc.subjectSmart cities
dc.titleAutomating city accessibility constraints mapping through AI‐assisted scanning of street view imageryeng
dc.typejournal article
dspace.entity.typePublication
oaire.citation.endPage16
oaire.citation.issue1
oaire.citation.startPage1
oaire.citation.titleIET Smart Cities
oaire.citation.volume7
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameSilva Moreira
person.familyNameAlberto Ribeiro Gouveia
person.familyNameDinis
person.familyNamePereira
person.givenNameRui
person.givenNameFeliz
person.givenNameMaria Alzira Pimenta
person.givenNameMadalena Sofia Araujo
person.identifier929716
person.identifierir-LXnYAAAAJ
person.identifier493603
person.identifier.ciencia-idDC13-E8D1-FE93
person.identifier.ciencia-id591D-B804-FD3C
person.identifier.ciencia-id4710-147D-FDAF
person.identifier.orcid0000-0002-4123-0983
person.identifier.orcid0000-0001-7308-4522
person.identifier.orcid0000-0002-2198-6740
person.identifier.orcid0009-0005-2840-209X
person.identifier.ridK-3082-2016
person.identifier.ridF-3309-2011
person.identifier.scopus-author-id36911288700
person.identifier.scopus-author-id6602995624
person.identifier.scopus-author-id55539804000
relation.isAuthorOfPublication6182ee1b-8208-4d62-b0bf-c8c743a5cbfc
relation.isAuthorOfPublication01499975-f5ed-4c7b-be0d-9fd1a1134cf7
relation.isAuthorOfPublication1e85592a-e8e2-4aea-bd8e-1007c94388c0
relation.isAuthorOfPublicationec0f6f00-e3d9-4b46-8018-d41f5d1ccd8b
relation.isAuthorOfPublication.latestForDiscovery1e85592a-e8e2-4aea-bd8e-1007c94388c0

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
IET Smart Cities_2025.pdf
Tamanho:
3.24 MB
Formato:
Adobe Portable Document Format
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
4.03 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções

FCT (DCEA) - Artigos em Revistas Científicas Internacionais com Arbitragem Científica