Geometric characterization and segmentation of historic buildings using classification algorithms and convolutional networks in HBIM
Juan Moyano, Antonella Musicco, Juan E. Nieto-Julián, Juan P. Dominguez‐Morales
Abstract
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. • A comparative machine learning approach for point cloud classification is presented. • The results of the classification performance and effectiveness of the Random Forest algorithm, Cyclone and the PointNet convolutional network are revealed. • The methods described allow the classification and semantic segmentation of objects in complex historical structures. • The automation of structural components from a point cloud in HBIM is one of the main challenges that this research addresses.