Connecting Geometry and Semantics via Artificial Intelligence: From 3d Classification of Heritage Data to H-Bim Representations

Abstract

Abstract. Cultural heritage information systems, such as H-BIM, are becoming more and more widespread today, thanks to their potential to bring together, around a 3D representation, the wealth of knowledge related to a given object of study. However, the reconstruction of such tools starting from 3D architectural surveying is still largely deemed as a lengthy and time-consuming process, with inherent complexities related to managing and interpreting unstructured and unorganized data derived, e.g., from laser scanning or photogrammetry. Tackling this issue and starting from reality-based surveying, the purpose of this paper is to semi-automatically reconstruct parametric representations for H-BIM-related uses, by means of the most recent 3D data classification techniques that exploit Artificial Intelligence (AI). The presented methodology consists of a first semantic segmentation phase, aiming at the automatic recognition through AI of architectural elements of historic buildings within points clouds; a Random Forest classifier is used for the classification task, evaluating each time the performance of the predictive model. At a second stage, visual programming techniques are applied to the reconstruction of a conceptual mock-up of each detected element and to the subsequent propagation of the 3D information to other objects with similar characteristics. The resulting parametric model can be used for heritage preservation and dissemination purposes, as common practices implemented in modern H-BIM documentation systems. The methodology is tailored to representative case studies related to the typology of the medieval cloister and scattered over the Tuscan territory.

Visual Renovation of Cultural Heritage Buildings through Advanced Construction Materials - 2D-Printed Protective Cladding on Facade Scaffolds

“…Images as final products are practically identical copies of the original with high quality graphics and architectural authenticity. They can be graphically rendered in the groups of software to Given the latter and the provisions outlined in [8] artificial intelligence can successfully be implemented to train the algorithms for processing the input data from the graphics softwares. Thus, one can obtain image classes in formats, through parametric representations for H-BIM related applications.…”

“…The resulting parametric model can be used for the purpose of conservation and promotion of heritage, in packages of documentation systems. Confirmations that Scan-to-BIM reconstructions with the application of artificial intelligence (AI) to classify digital architectural heritage data such as the ones in [6] and [8] are becoming more common. This approach leads to solving a number of problems in mapping heritage buildings and monuments such as: time and labour consumption, creating libraries with graphic data, representing a comprehensively assembled architecture of the surveyed objects, increased graphics quality of the resulting images, etc.…”

“…After 2020 and the COVID-19 pandemic, the concept for the development of technical means of surveying and the accelerating and improving the processing of the received data to obtain the final product, have been further oriented towards the possibilities of operating image data aided by artificial intelligence [7,8].…”

From Scan-to-Bim to Heritage Building Information Modelling for an Ancient Arab-Norman Church

“…Research is trying to move to semi-automatic and automatic methods for data processing and modelling, but these approaches are still not inclusive for all CH specialists and preparing a discretisation of reality to be fed to automatisms is neither an immediate nor an easy task itself (Croce et al, 2021). The work focuses on the developmentthrough an organized workflow -of an accurate, flexible and customizable HBIM system aimed to manage the integrated information data which can be obtained by the methodological application of topographical, laser scanning and photogrammetric techniques on heritage buildings.…”

Machine learning for conservation of architectural heritage

“…Most of the studies are focusing on the diagnosis, analysis and classification of the structural components of historical buildings like domes, columns, vaults, etc. (Obeso et al, 2016;Llamas et al, 2017;Bassier et al, 2017;Grilli and Remondino, 2020;Croce et al, 2021;Pepe et al, 2022). Thus, aiming to contribute to the conservation and restoration by extracting valuable knowledge from the heritage images.…”