1,720,977 research outputs found
Automatic model-based segmentation for the scan-to-bim process applied to cultural heritage. A study focused on Masonry vaults
No full textScan-to-BIM for architectural heritage enhancement and preservation. Leading techniques and advanced automation processes
Full text linkThe digitisation of Architectural Heritage emerges as a pivotal and groundbreaking
practice crucial for the preservation and enhancement of cultural assets.
This significance becomes particularly pronounced in an era marked by profound
transformations and challenges across multiple fields.
By cutting-edge technologies within a scenario dominated by Artificial Intelligence,
which disrupts established paradigms and approaches, this initiative aims to address
the inherent challenges of long-term conservation. Simultaneously, it aspires to
achieve the broader objective of ensuring enhanced access and a more enriched experience
of historical monuments for both current and future generations, thereby
safeguarding their unique identities.
Heritage's vulnerability must be carefully weighed to strike a delicate balance between
accessibility and contemporary interpretation on the one hand, and authenticity and
integrity on the other. The hazards of digitisation, including the potential loss of stored
information or intentional obsolescence, are closely related to this susceptibility as
well as physical material modifications.
The present thesis, born out of these critical considerations, adopts comprehensive
and multidisciplinary approaches to delve into diverse themes converging within the
realm of architectural survey and drawing for heritage virtualisation.
Through extensive field research conducted in both Italy and Spain, the combined
methodologies of various surveying techniques and technologies, including LiDAR
and Photogrammetry, are thoroughly examined as foundational elements for the digital
acquisition of historical monuments. The resulting data, presented as point clouds,
images, and/or polygonal models, undergo a detailed processing and optimisation
phase employing semi-automatic procedures.
These procedures, primarily focusing on the semantic enrichment of architectural and
structural components, are geared towards facilitating an in-depth analysis of the
conservation status of the monument. This, in turn, translates into improved information management, providing crucial
support for subsequent phases involved in constructing the replicated model of the
architectural masterpiece.
Moving beyond the survey activity, the investigation advances towards Heritage Building
Information Modelling (HBIM) through the adoption of a Scan to BIM approach.
The latter is seamlessly integrated into a unified protocol, streamlining data processing
while ensuring adherence to health and safety regulations for the operator.
This methodology enables a thorough analysis and faithful digitisation of the reproduced
case studies, leveraging metric and geometric references guaranteed by the instrumentation
used, as well as semantic segmentation and classification of data derived
from the automations.
The proposed processes of automation, designed to accelerate processing times,
control operational costs, and enhance the precision and accuracy of results, are meticulously
crafted. Simultaneously, due consideration is given to the experience and
expertise of the operator involved in the activities, ensuring a thoughtful and conscious
approach throughout all stages of the process
Desarrollo del flujo de trabajo Mesh-to-BIM a través de VPL para apoyar el proceso de documentación del patrimonio histórico
No full textIn recent years, the HBIM (Heritage Building Information Modelling) approach is widely used
in heritage documentation and is mainly based on the Scan-to-BIM modeling process to manually
create the geometric model from the point cloud. This article illustrates a pipiline that introduces
semi-automatic operations for semantic identifi cation of architectural elements through the model-
based RANSAC (RANdom SAmple Consensus) algorithm on point clouds and the Visual
Programming Language (VPL) to reduce the manual process the construction of a BIM model
of the decorative apparatus, while maintaining the advantages of parametric and informative
modeling. The workfl ow has been tested on the Romanesque Church of All Saints of Trani
(12th century) in Italy
Integrated 3D survey techniques for historical architecture. The Church of S.Maria Veterana in Triggiano (Italy)
No full textIntegrated 3D survey techniques for historical architecture. The Church of S.Maria Veterana in Triggiano (Italy)
No full textEnhancing 3D Modeling Efficiency via Semi-Automatic Point Cloud Segmentation and Multi-Lod Mesh Reconstruction
Full text linkThe accuracy of 3D models in historical buildings is a debated topic due to the increasing demand for digital documentation and the need for automated post-processing methods to reduce manual labor and improve data analysis. The proposed method aims to improve 3D reconstruction efficiency for complex geometries exemplified by the Ognissanti Church of Trani (XII century), Italy. The methodology includes point cloud segmentation and classification algorithms, (RANSAC and Random Forest) to isolate architectural elements. The segmented portions undergo processing utilizing three 3D reconstruction algorithms: Alpha-Shape, Ball-Pivoting, and Poisson Surface Reconstruction. Customized settings enable polygonal meshes with varying levels of detail. Visual Programming Language operations refine the resulting meshes in terms of triangulation and computational efficiency, ensuring a high level of fidelity and applications in HBIM framework
Semantic Enrichment of Architectural Heritage Point Clouds Using Artificial Intelligence: The Palacio de Sástago in Zaragoza, Spain
Full text linkIn the current landscape dominated by Artificial Intelligence, the integration of Machine Learning and Deep Learning within the realm of Cultural Heritage, particularly within architectural contexts, is paramount for the efficient processing and interpretation of point clouds. These advanced methods facilitate automated segmentation and classification, significantly improving both the clarity and practical use of data acquired from laser scanning and photogrammetry. The present study investigates the Palacio de Sástago—a prominent Renaissance palace in Zaragoza, Spain—and introduces a cutting-edge modus operandi for the automated recognition of architectural elements within the palace’s inner courtyard. Employing the well-established Random Forest algorithm, implemented in a Python environment, the framework begins with a comprehensive evaluation of the geometric features identified in the LiDAR point cloud. This process employs the Mean Decrease in Impurity metric to evaluate the relevance of each variable. To boost the accuracy and efficiency of the final classifications, the features are refined post-assessment, enhancing both the training phase and the algorithm’s later evaluation. The research’s findings demonstrate significant potential, supporting advancements in CAD systems and HBIM that will enable more precise, automated modelling of architectural elements, thereby enhancing the accuracy of digital reconstructions and improving conservation planning for heritage sites
A point cloud classification method for the ScanToBIM process in Architectural Heritage
Full text linkHeritage Building Information Modelling (H-BIM) has completely changed the meaning of managing architectural sites and ancient buildings. Nowadays, the application of cutting-edge methods for analysis, conservation and restoration is made possible by the modern 3D scanning technologies, such as terrestrial laser scanners (TLS) and digital cameras, which produce highly accurate point clouds. Furthermore, as these files are time-consuming and computationally expensive, strategies are being developed to optimise their handling and to streamline the conversion of a point cloud into a BIM model, adopting Scan-to-BIM approaches and widespread Artificial intelligence.
In this scenario, the current work investigates the use of the CANUPO multiscale algorithm and the RANSAC model-fitting method for the classification of the staircase of Palazzo Nico, a neoclassical building in Gioia del Colle, Italy, using data obtained through TLS. The location’s geometry, which includes numerous floors, vaults, balustrades, and typical 19th-century-style ornate staircase, makes it an excellent case study for assessing the applicability of these tools, serving as a source base for additional modelling procedures
Aportaciones formales a la arquitectura defensiva en Pulia durante el periodo de la Corona de Aragón
Full text linkApulia, with its counties and duchies, was part of the Kingdom of Naples during the medieval period. After French domination, it was integrated into the Crown of Aragon, which meant an italianisation of the kingdom, governed by a faction of the House of Aragon-Italian, started by Alfonso V of Aragon and continued by his illegitimate son Ferrante. During this brief period, two important factors occurred: the introduction of gunpowder and the military technology of firearms, and the change in social organisation
at the turn of the Middle Ages and the Renaissance. During this period, with abundant conflicts in the area, the evolution of the castles can be observed in a few years, incorporating new construction solutions that would modify the shape of the castle, such as: barbicans, bastions, escarpments and counter-escarpments, fortified towers and ravelins. To obtain these results, a virtual model of some of the most representative castles was recreated using photogrammetric and laser scanning techniques
- …
