The use of spherical cameras (with a field of view of 360°) is becoming increasingly popular for photogrammetric applications characterised by the opportunity to capture entire scenes in a relatively short time. This potential may be even more interesting for the digitisation of complex areas where, in addition to geometry, time, cost and social context play an important role. This contribution is part of this field of investigation by describing two experiments conducted on the use of an inexpensive 360° camera, the Insta360 OneX2, for the expeditious survey of residual spaces below road junctions. The area under investigation is a node in the city of Naples (Italy) located in the eastern area, considered particularly significant for the interaction between the geographical and infrastructural system. Two different approaches are tested starting from the acquisition of the spherical photographic dataset: the traditional one by means of photogrammetric software and the more economical and user-friendly one by employing the Matterport Capture application. Pros and cons of the two approaches are discussed: the first experimental results are encouraged and support the validity of the approach for surveying complex urban spaces.

In recent years, automatic segmentation and classification of data from digital surveys have taken a central role in built heritage studies. However, the application of Machine and Deep Learning (ML and DL) techniques for semantic segmentation of point clouds is complex in the context of historic architecture because it is characterized by high geometric and semantic variability. Data quality, subjectivity in manual labeling, and difficulty in defining consistent categories may compromise the effectiveness and reproducibility of the results. This study analyzes the influence of three key factors—annotator specialization, point cloud density, and sensor type—in the supervised classification of architectural elements by applying the Random Forest (RF) algorithm to datasets related to the architectural typology of the Franciscan cloister. The main innovation of the study lies in the development of an advanced feature selection technique, based on multibeam statistical analysis and evaluation of the p-value of each feature with respect to the target classes. The procedure makes it possible to identify the optimal radius for each feature, maximizing separability between classes and reducing semantic ambiguities. The approach, entirely in Python, automates the process of feature extraction, selection, and application, improving semantic consistency and classification accuracy.

The study proposes an optimized approach for feature selection in the semantic segmentation of point clouds within the architectural domain of cultural heritage, with a specific focus on historical monastic architecture. The goal is to enhance the automatic recognition and classification of architectural elements using the Random Forest algorithm, by reducing classifier dependency and increasing the model’s generalization capability. The developed method is based on a multiscale statistical selection of features, through p-value analysis and the optimization of influence radii, fully automating the process within a Python environment. The method was tested on a TLS point cloud dataset specifically built for Franciscan cloisters in the Campania region, segmented into ten architectural classes. The new approach builds upon the existing but implemented RF4PCC model, against which it was compared, showing significant improvements in the classification of minority classes, thanks to the adoption of the class_weight=”balanced” parameter and the expansion of the dataset. The analysis of feature_importances_ revealed biases related to class imbalance, which were addressed through regularization strategies and complexity control of the decision trees. Experimental results show an increase in the macro F1-score and greater fairness in class classification. The proposed approach proves effective for applications in the cultural heritage field, offering an interpretable, efficient, and adaptable method for complex architectural contexts.

In the field of cultural heritage, a significant amount of research has been conducted to allow domain experts to represent semantic data while keeping spatial references. The organization of architectural shapes in significant concepts, in the context of semantic annotation, is carried out in various ways. This chapter analyzes them, highlighting some substantial questions: the semantic ambiguity and the uncertainty. These questions are addressed after a careful reflection on the theoretical basis for a semantic reading of architecture. The chapter proposes some operative solutions: the use of an international thesaurus to resolve linguistic ambiguity; the coding of semantic maps to solve the annotation uncertainty.

Three-dimensional acquisition systems for architecture have significantly evolved over just a few decades, with them allowing point clouds to be generated through active and passive optical sensor equipment.Accuracy levels vary considerably in relation to both the equipment and techniques used, with the data obtained acting as a scaffolding for the creation of derived models that allow specific analyses to be carried out.Ongoing research on Palazzo Donn’Anna, a Neapolitan sixteenth-century building of particular historical and artistic value, is being carried out in this context and the first results are presented in this paper.The entire building has been the subject of an instrumental survey. The north-east façade was proposed as a case-study for the experimentation of diversified reality-based sensors so as to compare the accuracy and precision of the data. The comparison was also aimed at evaluating the performance of some processing softwares. Finally, in order to obtain an estimate of the data in the transcription from the point cloud to a derived 3D model, the reproduction of the same portion of the prospectus in a derivative model of both object-oriented and NURBS types was experimented.