The paper shows an advancement of the research that the authors have been carrying out in recent years in semantic structuring of digital architectural representations field, with a focus on the issue of uncertainty of annotations. The studies carried out in this regard have shown how the domain experts specialization determines a vision and interpretation of the same architectural object that we could define “categorized”. The interest was, then, in verifying which categories of experts have a greater degree of agreement in classifying and segmenting architectural elements, to highlight which specializations contribute the most in enriching the semantic reasoning about such forms. Aiming to broaden this reasoning, the research was deepened with annotation sessions concerning architecture examples that didn’t correspond to the classical orders rule but included wider fields of historical heritage (from sacred to fortified architecture). The aim is to verify whether the uncertainty of annotation is actually ascribable to a specific segment of the historical heritage, for example, the classical world, or whether the question is broader and as such in needs deeper thinking.
3D Heritage Data Fruition and Management. Point Cloud Processing for Thematic Interpretation
Technologies and digital tools such as laser scanning and photogrammetry are nowadays widely used in the field of architectural heritage survey, being able of producing 3D models characterized by high metric and morphological accuracy. These databases are becoming essential also for the development of more effective interventions on heritage buildings. Despite the advancement of increasingly automated analytical procedures, the management and analysis of point cloud models can still be quite time-consuming and complex, depending on specific assessments to be carried out. In the direction of optimizing these processing steps, several research is being carried out by applying Artificial Intelligence processes to make predictions based on sample data. The aim of the paper is to analyse point clouds processing focusing on geometric and radiometric features for diagnostic analysis. A specific focus aims at analysing possible in-depth uses of the intensity value as a benchmark for historical surfaces assessment, toward an optimized models’ interpretation and classification of the 3D data points, integrating data and information from different sensors. Point clouds under analysis have been carried out by different acquisition techniques; this provides an interesting opportunity to compare the results in terms of intensity value produced by different sensors. The paper will analyse the State of the Art, also illustrating a set of outcomes obtained by the authors, deepening two specific case studies, in order to outline not only the main background and shortcomings in managing complex database, but also possible innovations pointing out new research questions.
From semantic-aware digital models to Augmented Reality applications for Architectural Heritage conservation and restoration
The paper presents the integration of Augmented Reality and Mixed Reality tools for the built Heritage management and control, both remote and on-site, and real time interaction, starting from a preliminary set of experimentation carried out for knowledge and tourism purposes.
Within the framework of these experimentations, specific data inventories are related to the IFC model, and all these data are collected on a cloud-based platform, allowing the “dialogue” among platform and applications. Therefore, BIM integration is the first step of the procedure, considering a workflow where data capturing, digital documentation, and data modeling and aggregation are the entry level to manage applications able to give an added value in gaining the greatest technical benefit from digitization. Mapping the main features and the state of conservation is the second step, including geometric features, historical knowledge, documents and pictures related to materials, diagnostic analysis, etc.
Starting from AR applications developed on several case studies, including historical buildings, museums and a church, aimed at an immersive on-site navigation thanks to a set of additional information related to the digital model, experimentations oriented to technical uses are presented.
An extension of applications for the analysis and interpretation of architectural heritage and technical uses can be an effective support in restoration, conservation and maintenance of historic buildings, by enhancing the real world through virtual objects and creating a new mixed reality environment for technical users.
Comparative Analyses Between Sensors and Digital Data for the Characterization of Historical Surfaces
In the “informational” potential included in 3D digital models obtained by laser scanner survey, several data can be processed in addition to geometric features in order to widen the application of digitization to conservation of Cultural Heritage. Among these data, the intensity value is a (potentially) powerful knowledge concerning the interpretation of surfaces. The visual-comparative analysis developed over years of experimentations demonstrate the need to target research towards comparative data, “sampling” the reflectance of different materials, measured with different sensors and in environments with different boundary conditions. If until recently the process already presented interesting research directions in terms of calibration or control of results on specific materials but difficult at a comparative level, today, thanks to new data segmentation processes and algorithmic procedures, advancements and further comparisons will be possible opening to new interpretative hypotheses. The paper explores ongoing experimentations aimed at comparing different radiometric and colorimetric data obtained by 3D surveying using different laser scanner technologies on historical surfaces, to support the identification of features directly on the 3D model. The goal is to test the link between the intensity value and materials, construction techniques, and decay pathologies, in order to use, in the future, also this parameter as a radiometric feature in machine learning segmentation and classification algorithms. The contribution develops and deepens at the application level the theoretical background and the first experiments carried out on two case studies.
Connecting geometry and semantics via artificial intelligence: from 3D classification of heritage data to H-BIM representations.
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.
Semantic segmentation through Artificial Intelligence from raw point clouds to H-BIM representation
This work describes a semi automatic workflow for the 3D reconstruction of Heritage Building Information Models from raw point clouds, based on Artificial Intelligence techniques. The BIM technology applied to historical architecture has made it possible to create a virtual repository of many heterogeneous pieces of information in order to make the process of storing and collecting data on the built heritage more effective. The modelling phase of an artefact is the most complex and problematic in terms of time, as the large architectural heritage of historical buildings does not allow the use of parametric models, so that manual modelling of components is required. Current scientific research focuses on automating this phase by means of segmentation and classification methods: these are based on associating different semantic information to the products of the three dimensional surveying as point clouds or polygonal meshes. To address these problems, the proposed approach relies on: (i) the application of machine learning algorithms with a multi level and multi resolution (MLMR) method to semantically classify 3D heritage data; (ii) the use of annotated data identified by relevant features to boost the scan to BIM process for 3D digital reconstruction. The procedure is tested and evaluated on the complex case of the Church of Santa Caterina d’Alessandria in Pisa, Italy. The classification results show the reliability and reproducibility of the developed method.
AR in the Architecture Domain: State of the Art
Augmented reality (AR) allows the real and digital worlds to converge and overlap in a new way of observation and understanding. The architectural field can significantly benefit from AR applications, due to their systemic complexity in terms of knowledge and process management. Global interest and many research challenges are focused on this field, thanks to the conjunction of technological and algorithmic developments from one side, and the massive digitization of built data. A significant quantity of research in the AEC and educational fields describes this state of the art. Moreover, it is a very fragmented domain, in which specific advances or case studies are often described without considering the complexity of the whole development process. The article illustrates the entire AR pipeline development in architecture, from the conceptual phase to its application, highlighting each step’s specific aspects. This storytelling aims to provide a general overview to a non-expert, deepening the topic and stimulating a democratization process. The aware and extended use of AR in multiple areas of application can lead a new way forward for environmental understanding, bridging the gap between real and virtual space in an innovative perception of architecture.
Visual Programming for a Machine Semi-Automatic Process of HBIM Models Geometric Evaluation
The topic of the relationship between digital restitutive model and measurement can find important development possibilities in machine procedures, in particular in the Historic Building Information Modeling (HBIM) field. In fact, BIM uses parameterized and pre-defined objects in special 3D libraries articulated according to the architectural components, not corresponding to ideal configurations. Moreover, BIM platforms are limited in modeling deformations, damages, and degradations. The paper investigates the advantages of using visual programming to increase the possibilities given by the BIM software, born for new buildings, by carrying out a semi-automatic assessment of the geometric reliability directly in the BIM environment. In particular, the algorithm compares model’s shapes with the cast of the artifact given by the point cloud, and declares it, by automatically filling a dedicated reliability parameter linked to the BIM model element.
A Proposal of Integration of Point Cloud Semantization and VPL for Architectural Heritage Parametric Modeling
Current architectural survey processes utilize point clouds generated by laser scanning and digital photogrammetry. Increasingly, these surveys produce 3D models, particularly parametric models, in what is known as the “scan to 3D model” or “scan to BIM” process. However, the phases of analysis and classification of architectural elements, segmentation and semantization of point clouds, and semi-automatic modeling remain complex and labor-intensive and require an active role commitment of the scholar or modeler. These steps are usually performed manually, resulting in high subjectivity and low reproducibility. This paper proposes a reproducible workflow that automatically segments point clouds, identifies geometric shapes by comparing them with a library of ideal geometries, and extracts necessary points for modeling through mathematical analysis. The extracted information is then processed using a visual programming algorithm, imported into the VPL environment, and used for automated modeling. Initial results from an ongoing experiment on the automated modeling of vaults using point clouds from surveys are presented.