Geometric characterization and segmentation of historic buildings using classification algorithms and convolutional networks in HBIM

Building Information Models (BIM) are essential for managing information and creating 3D digital representations, especially in the study of historic buildings. However, generating BIM models from point clouds in these structures is challenging due to complex algorithms and architectural forms. Arti...

Descripción completa

Detalles Bibliográficos
Autores: Moyano Campos, Juan José, Musicco, Antonella, Nieto Julián, Juan Enrique, Domínguez Morales, Juan Pedro
Tipo de recurso: artículo
Fecha de publicación:2024
País:España
Institución:Consejo General de la Arquitectura Técnica de España (CGATE)
Repositorio:RIARTE
OAI Identifier:oai:www.riarte.es:20.500.12251/3782
Acceso en línea:http://hdl.handle.net/20.500.12251/3782
https://doi.org/10.1016/j.autcon.2024.105728
Access Level:acceso abierto
Palabra clave:Building Information Modeling (BIM)
Patrimonio histórico
Nube de puntos
Inteligencia Artificial
Aprendizaje adaptativo
Algoritmos
1203.09 Diseño Con Ayuda del Ordenador
1203.26 Simulación
3305.26 Edificios Públicos
id ES_6254da057d47d081ebc522a697dec9c8
oai_identifier_str oai:www.riarte.es:20.500.12251/3782
network_acronym_str ES
network_name_str España
repository_id_str
spelling Geometric characterization and segmentation of historic buildings using classification algorithms and convolutional networks in HBIMMoyano Campos, Juan JoséMusicco, AntonellaNieto Julián, Juan EnriqueDomínguez Morales, Juan PedroBuilding Information Modeling (BIM)Patrimonio históricoNube de puntosInteligencia ArtificialAprendizaje adaptativoAlgoritmos1203.09 Diseño Con Ayuda del Ordenador1203.26 Simulación3305.26 Edificios PúblicosBuilding Information Models (BIM) are essential for managing information and creating 3D digital representations, especially in the study of historic buildings. However, generating BIM models from point clouds in these structures is challenging due to complex algorithms and architectural forms. Artificial Intelligence (AI) technologies are beginning to automate point cloud classification and segmentation, but fully effective methods for historic buildings are still lacking. This study compares Machine Learning (ML) methodologies and a Deep Learning (DL) classifier. It evaluates the effectiveness of a neighbourhood algorithm with commercial software used by geometers and surveyors, and the applicability of convolutional networks. The methods tested include the Random Forest algorithm in MATLAB, commercial geomatics software, and a variant of the PointNet architecture for DL. The results are evaluated by BIM experts, highlighting the high effectiveness of these approaches and their potential contributions to the field.ELSEVIER2024info:eu-repo/semantics/articlehttp://hdl.handle.net/20.500.12251/3782https://doi.org/10.1016/j.autcon.2024.105728reponame:RIARTEinstname:Consejo General de la Arquitectura Técnica de España (CGATE)Ingléshttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:www.riarte.es:20.500.12251/37822026-06-02T12:44:41Z
dc.title.none.fl_str_mv Geometric characterization and segmentation of historic buildings using classification algorithms and convolutional networks in HBIM
title Geometric characterization and segmentation of historic buildings using classification algorithms and convolutional networks in HBIM
spellingShingle Geometric characterization and segmentation of historic buildings using classification algorithms and convolutional networks in HBIM
Moyano Campos, Juan José
Building Information Modeling (BIM)
Patrimonio histórico
Nube de puntos
Inteligencia Artificial
Aprendizaje adaptativo
Algoritmos
1203.09 Diseño Con Ayuda del Ordenador
1203.26 Simulación
3305.26 Edificios Públicos
title_short Geometric characterization and segmentation of historic buildings using classification algorithms and convolutional networks in HBIM
title_full Geometric characterization and segmentation of historic buildings using classification algorithms and convolutional networks in HBIM
title_fullStr Geometric characterization and segmentation of historic buildings using classification algorithms and convolutional networks in HBIM
title_full_unstemmed Geometric characterization and segmentation of historic buildings using classification algorithms and convolutional networks in HBIM
title_sort Geometric characterization and segmentation of historic buildings using classification algorithms and convolutional networks in HBIM
dc.creator.none.fl_str_mv Moyano Campos, Juan José
Musicco, Antonella
Nieto Julián, Juan Enrique
Domínguez Morales, Juan Pedro
author Moyano Campos, Juan José
author_facet Moyano Campos, Juan José
Musicco, Antonella
Nieto Julián, Juan Enrique
Domínguez Morales, Juan Pedro
author_role author
author2 Musicco, Antonella
Nieto Julián, Juan Enrique
Domínguez Morales, Juan Pedro
author2_role author
author
author
dc.subject.none.fl_str_mv Building Information Modeling (BIM)
Patrimonio histórico
Nube de puntos
Inteligencia Artificial
Aprendizaje adaptativo
Algoritmos
1203.09 Diseño Con Ayuda del Ordenador
1203.26 Simulación
3305.26 Edificios Públicos
topic Building Information Modeling (BIM)
Patrimonio histórico
Nube de puntos
Inteligencia Artificial
Aprendizaje adaptativo
Algoritmos
1203.09 Diseño Con Ayuda del Ordenador
1203.26 Simulación
3305.26 Edificios Públicos
description Building Information Models (BIM) are essential for managing information and creating 3D digital representations, especially in the study of historic buildings. However, generating BIM models from point clouds in these structures is challenging due to complex algorithms and architectural forms. Artificial Intelligence (AI) technologies are beginning to automate point cloud classification and segmentation, but fully effective methods for historic buildings are still lacking. This study compares Machine Learning (ML) methodologies and a Deep Learning (DL) classifier. It evaluates the effectiveness of a neighbourhood algorithm with commercial software used by geometers and surveyors, and the applicability of convolutional networks. The methods tested include the Random Forest algorithm in MATLAB, commercial geomatics software, and a variant of the PointNet architecture for DL. The results are evaluated by BIM experts, highlighting the high effectiveness of these approaches and their potential contributions to the field.
publishDate 2024
dc.date.none.fl_str_mv 2024
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/20.500.12251/3782
https://doi.org/10.1016/j.autcon.2024.105728
url http://hdl.handle.net/20.500.12251/3782
https://doi.org/10.1016/j.autcon.2024.105728
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv http://creativecommons.org/licenses/by-nc-nd/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv ELSEVIER
publisher.none.fl_str_mv ELSEVIER
dc.source.none.fl_str_mv reponame:RIARTE
instname:Consejo General de la Arquitectura Técnica de España (CGATE)
instname_str Consejo General de la Arquitectura Técnica de España (CGATE)
reponame_str RIARTE
collection RIARTE
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869409488561242112
score 15,812429

Similares en LA Referencia