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...
| Autores: | , , , |
|---|---|
| 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 |
| Sumario: | 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. |
|---|