Skip navigation
Universidade de Brasília
Use este identificador para citar ou linkar para este item: http://repositorio.unb.br/handle/10482/51959
Arquivos associados a este item:
Arquivo Descrição TamanhoFormato 
ARTIGO_DeepLearningApplied.pdf13,95 MBAdobe PDFVisualizar/Abrir
Registro completo de metadados
Campo DCValorIdioma
dc.contributor.authorSantos, Lara Monalisa Alves dos-
dc.contributor.authorZanoni, Vanda Alice Garcia-
dc.contributor.authorBedin, Eduardo-
dc.contributor.authorPistori, Hemerson-
dc.date.accessioned2025-03-18T12:47:49Z-
dc.date.available2025-03-18T12:47:49Z-
dc.date.issued2023-
dc.identifier.citationSANTOS, Lara Monalisa Alves dos et al. Deep learning applied to equipment detection on flat roofs in images captured by UAV. Case Studies in Construction Materials, [S. l.], v. 18, e01917, Jul. 2023. DOI: https://doi.org/10.1016/j.cscm.2023.e01917. Disponível em: https://www.sciencedirect.com/science/article/pii/S2214509523000967?via%3Dihub#sec0005. Acesso em: 18 mar. 2025.pt_BR
dc.identifier.urihttp://repositorio.unb.br/handle/10482/51959-
dc.language.isoengpt_BR
dc.publisherElsevier Ltd.pt_BR
dc.rightsAcesso Abertopt_BR
dc.titleDeep learning applied to equipment detection on flat roofs in images captured by UAVpt_BR
dc.typeArtigopt_BR
dc.subject.keywordTelhado plano - manutençãopt_BR
dc.subject.keywordDetecção de equipamentospt_BR
dc.subject.keywordInspeção predialpt_BR
dc.subject.keywordVeículos aéreos não tripulados (VANTs)pt_BR
dc.subject.keywordVisão computacionalpt_BR
dc.subject.keywordAprendizado profundopt_BR
dc.rights.licenseThis is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).pt_BR
dc.identifier.doihttps://doi.org/10.1016/j.cscm.2023.e01917pt_BR
dc.description.abstract1Maintenance on flat roofs is a complex activity. Equipment improperly positioned on flat roofs hinders the correct drainage of water and makes maintenance services more difficult. This article presents an experiment with deep learning algorithms involving 330 images acquired in 9 buildings by Unmanned Aerial Vehicle-UAV. This dataset was created by the authors to optimize decision-making for maintenance through automated processes and is being used for the first time in this article. The dataset refers to condenser equipment positioned on flat roofs and was tested in six state-of-the-art object-detection deep learning algorithms: Region-based convolutional neural networks (Faster R-CNN), Focal Loss (Retina-Net), Adaptive Training Sample Selection (ATSS), VarifocalNet (Vfnet), Side-Aware Boundary Localization (SABL) and FoveaBox (Fovea). Nine performance metrics were applied, achieving successful results by Faster R-CNN (Recall=0.93, Fscore=0.93, MAE=0.43) followed by ATSS (Precision=0.95). In a system with many variables, the target is the identification of the best algorithm capable of solving the proposed problem. In conclusion, the types of errors analyzed in detection alert to the diversity of causes related to the inherent characteristics of flat roofs that induce network confusion.pt_BR
dc.identifier.orcidhttps://orcid.org/0000-0001-8181-760Xpt_BR
dc.contributor.affiliationUniversity of Brasíliapt_BR
dc.contributor.affiliationUniversity of Brasíliapt_BR
dc.contributor.affiliationDom Bosco Catholic Universitypt_BR
dc.contributor.affiliationDom Bosco Catholic Universitypt_BR
dc.contributor.affiliationFederal University of Mato Grosso do Sulpt_BR
dc.description.unidadeFaculdade de Arquitetura e Urbanismo (FAU)pt_BR
dc.description.unidadeDepartamento de Tecnologia em Arquitetura e Urbanismo (FAU TEC)pt_BR
dc.description.ppgPrograma de Pós-Graduação em Arquitetura e Urbanismopt_BR
Aparece nas coleções:Artigos publicados em periódicos e afins

Mostrar registro simples do item Visualizar estatísticas



Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.