Improving detection of asphalt distresses with deep learning-based diffusion model for intelligent road maintenance

Research on road infrastructure structural health monitoring is critical due to the increasing problem of deteriorated conditions. The traditional approach to pavement distress detection relies on human-based visual recognition, a time-consuming and labor-intensive method. While Deep Learning-based...

Descripción completa

Detalles Bibliográficos
Autores: Cano Ortiz, Saúl, Lloret Iglesias, Lara, Martínez Ruiz del Arbol, P., Castro-Fresno, Daniel
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2024
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/358370
Acceso en línea:http://hdl.handle.net/10261/358370
Access Level:acceso abierto
Palabra clave:Computer vision
Deep learning
Pavement distress detection
Road maintenance
Data augmentation
Diffusion model
id ES_2edb7b660de5cf4313f1df281e4ed09b
oai_identifier_str oai:digital.csic.es:10261/358370
network_acronym_str ES
network_name_str España
repository_id_str
spelling Improving detection of asphalt distresses with deep learning-based diffusion model for intelligent road maintenanceCano Ortiz, SaúlLloret Iglesias, LaraMartínez Ruiz del Arbol, P.Castro-Fresno, DanielComputer visionDeep learningPavement distress detectionRoad maintenanceData augmentationDiffusion modelResearch on road infrastructure structural health monitoring is critical due to the increasing problem of deteriorated conditions. The traditional approach to pavement distress detection relies on human-based visual recognition, a time-consuming and labor-intensive method. While Deep Learning-based computer vision systems are the most promising approach, they face the challenges of reduced performance due to the scarcity of labeled data due, high annotation costs misaligned with engineering applications, and limited instances of minority defects. This paper introduces a novel generative diffusion model for data augmentation, creating synthetic images of rare defects. It also investigates methods to enhance image quality and reduce production time. Compared to Generative Adversarial Networks, the optimal configuration excels in reliability, quality and diversity. After incorporating synthetic images into the training of our pavement distress detector, YOLOv5, its mean average precision has been enhanced. This computer-aided system enhances recognition and labelling efficiency, promoting intelligent maintenance and repairs.This work was supported by the MCIN/AEI/10.13039/501100011033 and “European Union NextGenerationEU/PRTR” under Grant [TED2021-129749B-I00].Peer reviewedElsevierMinisterio de Ciencia, Innovación y Universidades (España)Agencia Estatal de Investigación (España)Ministerio de Ciencia e Innovación (España)European CommissionConsejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]202420242024info:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501Publisher's versioninfo:eu-repo/semantics/publishedVersionapplication/pdfhttp://hdl.handle.net/10261/358370reponame:DIGITAL.CSIC. Repositorio Institucional del CSICinstname:Consejo Superior de Investigaciones Científicas (CSIC)Inglés#PLACEHOLDER_PARENT_METADATA_VALUE#info:eu-repo/grantAgreement/AEI//TED2021-129749B-I00The underlying dataset has been published as supplementary material of the article in the publisher platform at DOI 10.1016/j.dibe.2023.100315https://doi.org/10.1016/j.dibe.2023.100315Síinfo:eu-repo/semantics/openAccessoai:digital.csic.es:10261/3583702026-05-22T06:33:51Z
dc.title.none.fl_str_mv Improving detection of asphalt distresses with deep learning-based diffusion model for intelligent road maintenance
title Improving detection of asphalt distresses with deep learning-based diffusion model for intelligent road maintenance
spellingShingle Improving detection of asphalt distresses with deep learning-based diffusion model for intelligent road maintenance
Cano Ortiz, Saúl
Computer vision
Deep learning
Pavement distress detection
Road maintenance
Data augmentation
Diffusion model
title_short Improving detection of asphalt distresses with deep learning-based diffusion model for intelligent road maintenance
title_full Improving detection of asphalt distresses with deep learning-based diffusion model for intelligent road maintenance
title_fullStr Improving detection of asphalt distresses with deep learning-based diffusion model for intelligent road maintenance
title_full_unstemmed Improving detection of asphalt distresses with deep learning-based diffusion model for intelligent road maintenance
title_sort Improving detection of asphalt distresses with deep learning-based diffusion model for intelligent road maintenance
dc.creator.none.fl_str_mv Cano Ortiz, Saúl
Lloret Iglesias, Lara
Martínez Ruiz del Arbol, P.
Castro-Fresno, Daniel
author Cano Ortiz, Saúl
author_facet Cano Ortiz, Saúl
Lloret Iglesias, Lara
Martínez Ruiz del Arbol, P.
Castro-Fresno, Daniel
author_role author
author2 Lloret Iglesias, Lara
Martínez Ruiz del Arbol, P.
Castro-Fresno, Daniel
author2_role author
author
author
dc.contributor.none.fl_str_mv Ministerio de Ciencia, Innovación y Universidades (España)
Agencia Estatal de Investigación (España)
Ministerio de Ciencia e Innovación (España)
European Commission
Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]
dc.subject.none.fl_str_mv Computer vision
Deep learning
Pavement distress detection
Road maintenance
Data augmentation
Diffusion model
topic Computer vision
Deep learning
Pavement distress detection
Road maintenance
Data augmentation
Diffusion model
description Research on road infrastructure structural health monitoring is critical due to the increasing problem of deteriorated conditions. The traditional approach to pavement distress detection relies on human-based visual recognition, a time-consuming and labor-intensive method. While Deep Learning-based computer vision systems are the most promising approach, they face the challenges of reduced performance due to the scarcity of labeled data due, high annotation costs misaligned with engineering applications, and limited instances of minority defects. This paper introduces a novel generative diffusion model for data augmentation, creating synthetic images of rare defects. It also investigates methods to enhance image quality and reduce production time. Compared to Generative Adversarial Networks, the optimal configuration excels in reliability, quality and diversity. After incorporating synthetic images into the training of our pavement distress detector, YOLOv5, its mean average precision has been enhanced. This computer-aided system enhances recognition and labelling efficiency, promoting intelligent maintenance and repairs.
publishDate 2024
dc.date.none.fl_str_mv 2024
2024
2024
dc.type.none.fl_str_mv info:eu-repo/semantics/article
http://purl.org/coar/resource_type/c_6501
Publisher's version
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10261/358370
url http://hdl.handle.net/10261/358370
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv #PLACEHOLDER_PARENT_METADATA_VALUE#
info:eu-repo/grantAgreement/AEI//TED2021-129749B-I00
The underlying dataset has been published as supplementary material of the article in the publisher platform at DOI 10.1016/j.dibe.2023.100315
https://doi.org/10.1016/j.dibe.2023.100315
Sí
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:DIGITAL.CSIC. Repositorio Institucional del CSIC
instname:Consejo Superior de Investigaciones Científicas (CSIC)
instname_str Consejo Superior de Investigaciones Científicas (CSIC)
reponame_str DIGITAL.CSIC. Repositorio Institucional del CSIC
collection DIGITAL.CSIC. Repositorio Institucional del CSIC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869405438785617920
score 15,81155

Similares en LA Referencia