Robust Wind Turbine Blade Segmentation from RGB Images in the Wild

Trabajo presentado en la IEEE International Conference on Image Processing (ICIP), celebradad en Kuala Lumpur (Malasia), del 8 al 11 de octubre de 2023

Detalles Bibliográficos
Autores: Pérez-Gonzalo, Raül, Espersen, Andreas, Agudo Martínez, Antonio
Tipo de recurso: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2023
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/353412
Acceso en línea:http://hdl.handle.net/10261/353412
https://api.elsevier.com/content/abstract/scopus_id/85180796391
Access Level:acceso abierto
Palabra clave:Blade Inspections
Blade Segmentation
BU-Net
Hole Filling
Wind Turbine
id ES_433e2573d44a1bfee5e2fd1399b9545b
oai_identifier_str oai:digital.csic.es:10261/353412
network_acronym_str ES
network_name_str España
repository_id_str
spelling Robust Wind Turbine Blade Segmentation from RGB Images in the WildPérez-Gonzalo, RaülEspersen, AndreasAgudo Martínez, AntonioBlade InspectionsBlade SegmentationBU-NetHole FillingWind TurbineTrabajo presentado en la IEEE International Conference on Image Processing (ICIP), celebradad en Kuala Lumpur (Malasia), del 8 al 11 de octubre de 2023With the relentless growth of the wind industry, there is an imperious need to design automatic data-driven solutions for wind turbine maintenance. As structural health monitoring mainly relies on visual inspections, the first stage in any automatic solution is to identify the blade region on the image. Thus, we propose a novel segmentation algorithm that strengthens the U-Net results by a tailored loss, which pools the focal loss with a contiguity regularization term. To attain top performing results, a set of additional steps are proposed to ensure a reliable, generic, robust and efficient algorithm. First, we leverage our prior knowledge on the images by filling the holes enclosed by temporarily-classified blade pixels and by the image boundaries. Subsequently, the mislead classified pixels are successfully amended by training an on-the-fly random forest. Our algorithm demonstrates its effectiveness reaching a non-trivial 97.39% of accuracy.This work has been supported by the Innovation Fund Denmark under 2021 ID1044-0044A and by the project MoHuCo PID2020-120049RB-I00 funded by MCIN/AEI/10.13039/501100011033Peer reviewedInstitute of Electrical and Electronics EngineersInnovation Fund DenmarkAgencia Estatal de Investigación (España)Ministerio de Ciencia, Innovación y Universidades (España)Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]202420242023info:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501Postprintinfo:eu-repo/semantics/acceptedVersionapplication/pdfhttp://hdl.handle.net/10261/353412https://api.elsevier.com/content/abstract/scopus_id/85180796391reponame:DIGITAL.CSIC. Repositorio Institucional del CSICinstname:Consejo Superior de Investigaciones Científicas (CSIC)Inglés#PLACEHOLDER_PARENT_METADATA_VALUE#info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2020-120049RB-I00http://dx.doi.org/10.1109/ICIP49359.2023.10223165Síinfo:eu-repo/semantics/openAccessoai:digital.csic.es:10261/3534122026-05-22T06:33:51Z
dc.title.none.fl_str_mv Robust Wind Turbine Blade Segmentation from RGB Images in the Wild
title Robust Wind Turbine Blade Segmentation from RGB Images in the Wild
spellingShingle Robust Wind Turbine Blade Segmentation from RGB Images in the Wild
Pérez-Gonzalo, Raül
Blade Inspections
Blade Segmentation
BU-Net
Hole Filling
Wind Turbine
title_short Robust Wind Turbine Blade Segmentation from RGB Images in the Wild
title_full Robust Wind Turbine Blade Segmentation from RGB Images in the Wild
title_fullStr Robust Wind Turbine Blade Segmentation from RGB Images in the Wild
title_full_unstemmed Robust Wind Turbine Blade Segmentation from RGB Images in the Wild
title_sort Robust Wind Turbine Blade Segmentation from RGB Images in the Wild
dc.creator.none.fl_str_mv Pérez-Gonzalo, Raül
Espersen, Andreas
Agudo Martínez, Antonio
author Pérez-Gonzalo, Raül
author_facet Pérez-Gonzalo, Raül
Espersen, Andreas
Agudo Martínez, Antonio
author_role author
author2 Espersen, Andreas
Agudo Martínez, Antonio
author2_role author
author
dc.contributor.none.fl_str_mv Innovation Fund Denmark
Agencia Estatal de Investigación (España)
Ministerio de Ciencia, Innovación y Universidades (España)
Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]
dc.subject.none.fl_str_mv Blade Inspections
Blade Segmentation
BU-Net
Hole Filling
Wind Turbine
topic Blade Inspections
Blade Segmentation
BU-Net
Hole Filling
Wind Turbine
description Trabajo presentado en la IEEE International Conference on Image Processing (ICIP), celebradad en Kuala Lumpur (Malasia), del 8 al 11 de octubre de 2023
publishDate 2023
dc.date.none.fl_str_mv 2023
2024
2024
dc.type.none.fl_str_mv info:eu-repo/semantics/article
http://purl.org/coar/resource_type/c_6501
Postprint
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10261/353412
https://api.elsevier.com/content/abstract/scopus_id/85180796391
url http://hdl.handle.net/10261/353412
https://api.elsevier.com/content/abstract/scopus_id/85180796391
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/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2020-120049RB-I00
http://dx.doi.org/10.1109/ICIP49359.2023.10223165
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 Institute of Electrical and Electronics Engineers
publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers
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_ 1869407009948827648
score 15,811543

Similares en LA Referencia