Classification – Page 2

Classification and Recognition Approaches for the BIM Modeling of Architectural Elements

This paper investigates automated approaches for the recognition, classification, and parametric modeling of architectural elements within BIM environments. The research focuses on the integration of image-based and point cloud data with algorithmic and AI-driven methods to support the transition from manual Scan-to-BIM workflows to automated digital reconstruction processes.

The proposed methodology combines visual programming, scripting techniques, and machine learning algorithms to segment, classify, and reconstruct architectural components such as columns, wood trusses, and walls. The workflow includes data acquisition, algorithm definition, training and testing phases, and the generation of parametric BIM objects through API-based implementation. Case studies demonstrate how geometric rules derived from architectural treatises and historiographic knowledge can be encoded into parametric systems, enabling both reconstruction and validation of architectural elements. Results highlight the potential of automated classification and recognition techniques to improve efficiency and reproducibility in BIM modeling, while emphasizing the ongoing need for interpretation and refinement due to the complexity and variability of historical architecture.

Digital Heritage Documentation. Mapping Features Through Automatic, Critical-Interpretative Procedures

This paper investigates how automatic and semi-automatic digital procedures can improve the documentation, interpretation, and conservation management of cultural heritage through advanced analysis of 3D survey data. The study focuses on the extraction and classification of architectural surface features—such as materials, construction techniques, decay patterns, moisture, deposits, and structural conditions—starting from terrestrial laser scanning and photogrammetric datasets. Particular attention is given to the underused diagnostic potential of laser scanner intensity values, which can reveal variations in material reflectance and hidden anomalies not always visible to the naked eye. The author proposes a workflow combining manual annotation, semantic segmentation, machine learning classification, and integration into H-BIM and semantic web platforms. Existing point clouds are reused as training datasets to define value clusters associated with conservation issues and material categories. The research argues that AI-supported thematic mapping can reduce processing time, improve diagnostic reliability, and transform dense survey models into actionable information systems for heritage managers, restorers, and public administrations.

Real-Time Identification of Artifacts:Synthetic Data for AI Model

The collections represent the constitutive element and the raison d’être of each museum. Their man-agement, care and dissemination are therefore a task of primary importance for every museum. Applying new Artificial Intelligence technologies in this area could lead to new initiatives. However, the development of certain tools requires structured and labeled datasets for the training phases which are not always easily available. The proposed contribution is within the domain of the construction of specific datasets with low budget tools and explores the results of a first step in this direction by testing algorithms for the recognition and labeling of heritage objects. The developed workflow is part of a first prototype that could be used both in heritage dissemination or gamification applications, and for use in heritage research tools.

Image Segmentation Procedure for Mapping Spatial Quality of Slow Routes

The current research aims at investigating the potential of Image Segmentation (IS) as a data source for mapping, with a bottom-up approach, the spatial quality of slow routes, localized in the territories “in-between” the main cities. The paper analyses two different case studies in Lombardy and Molise regions, where a different territorial configuration and data are available. The IS method, that computes area percentages in the street-level imagery by using Pixellab/TensorFlow digital environment, has been applied for detecting three different environments that are intersected by the selected routes and that are also detectable by using GIS tools: open spaces, built environment and rows of trees. These have been considered as relevant since they affect the users’ perception of the places in a different way. The research points out how the IS method can be complementary to the GIS-based detection method to collect more detailed geo-information about the places, but also a very powerful tool to catch geo-information by the street-level imagery, in the territories where no thematic geospatial data are available.

Connection & Knowledge: from AR to AI. The Case of Sicilian Lighthouses

The development of ever new and innovative technologies is now able to significantly enrich the numerous possibilities in the field of research, use, enhancement and understanding of the existing cultural heritage. In this sense, the initiatives in the field of augmented reality and artificial intelligence appear to be a possible asset through which to undertake connection and mixing networks between the intrinsic and extrinsic data that characterize buildings. The use of semantic and ontological data – that is fields based on an increasingly solid interoperability and exchange of data – make it possible to develop a mutual knowledge in a relationship of connection between territory and architecture. This contribution, therefore, investigates the possible application of augmented reality and artificial intelli-gence in the context of Sicilian lighthouses, or a heritage characterized by well-defined architectural and landscape components.

Semantic Mapping of Architectural Heritage via Artificial Intelligence and H-BIM

Starting from the virtual photogrammetric 3D reconstruction, this work proposes a classification method, based on Artificial Intelligence, allowing to semi-automatically characterize the digital models of existing architectural heritage in terms of material mapping and/or decay condition. The obtained data, once classified, is used and transferred in BIM environment, so to favor the construction of in-formative models rich in analytical content. The proposed approach is described with reference to the significant case study of the Chiesa del Carmine in Pisa, for the study and restitution of the liturgical and decorative apparatus, as part of a large-scale research project, still underway, on the reconstruc-tion of the tramezzo screens for the churches of the Mendicant orders.

Supervised Classification Approach for the Estimation of Degradation

The study presents an innovative approach to classify geomaterials using supervised classification methods from orthophotos derived from UAV (Unmanned Aerial Vehicle) and photogrammetric processing. The case study examined is the Ponte Rotto, dating back to 20 BC, which in antiquity allowed the Appian Way to cross the Calore River – between the provinces of Avellino and Beneven-to – to continue towards the port of Brindisi. In previous studies, experts on geomaterial diagnosis estimated – from aerophotogrammetric orthophotos generated for both bridge elevations – the geo-materials and quantities used for the construction of the monument and an overview of the state of conservation of the monument studied. Orthophotos of facades were imported into CAD software and used as the basis for – according to a manual process – the mapping of the materials. The work presents the results according to automatic Machine Learning clustering from the same orthophotos to identify geomaterials.

Augmented Intelligence In Built Environment Projects

Ever-increasing levels of digital connectivity and ubiquitous sensing capacity offer opportunities to rethink traditional design and planning practices towards delivering more sustainable and resilient futures. Within this context, the chapter discusses how digital representation, Artificial Intelligence and collaborative processes can enable coping better with uncertainty by informing design and en-vironmental management moves. Through two distinct examples, one in the UK and one in Italy, it illustrates how data about the built environment can be collected, networked, and operationalised to deal better with complexity and make informed decisions which consider alternative courses of action and challenge pre-existing assumptions. Both cases presented highlight the importance to establish a two-way link between digital and physical infrastructures and the people.

AI for AEC: Open Data and VPL Approach for Urban Seismic Vulnerability

This contribution provides an overview of the VPL evolution and an application case concerning the classification of seismic vulnerability indices with AI. This research aims to contribute to the scientific debate on the use of these technologies in architecture, deepening the themes of seismic assessment on urban and territorial scale. The whole experimentation was conducted using only the potential of Grasshopper’s VPL and possessing, as basic knowledge, the main concepts of machine learning and supervised learning. The VPL is therefore an effective tool to introduce and disseminate the topics and applications of artificial intelligence within the AEC sector, effectively decreasing the gap between domain experts and programmers.

Machine Learning for Cultural Heritage Classification

Cultural Heritage (CH) assets may be defined as integrated spatial systems composed of inter-connected shapes. The classification and organization of geometries within a hierarchical system are functional to their correct interpretation, which is often performed using 3D point clouds. The recurring shapes recognition becomes a crucial activity, nowadays accelerated by Machine Learning (ML) procedures able to associate semantic meaning to geometric data. An interdisciplinary research team [1] has developed a ML supervised approach, tested on the Milan Cathedral and Pomposa Abbey datasets, which presents an innovative multi–level and multi–resolution classification (MLMR) process. The methodology improves the learning activity and optimizes the 3D classification by a hierarchical concept.