In the Digital Cultural Heritage (DCH) domain, the semantic segmentation of 3D Point Clouds with Deep Learning (DL) techniques can help to recognize historical architectural elements, at an adequate level of detail, and thus speed up the process of modeling of historical buildings for developing BIM models from survey data, referred to as HBIM (Historical Building Information Modeling). In this paper, we propose a DL framework for Point Cloud segmentation, which employs an improved DGCNN (Dynamic Graph Convolutional Neural Network) by adding meaningful features such as normal and colour. The approach has been applied to a newly collected DCH Dataset which is publicy available: ArCH (Architectural Cultural Heritage) Dataset. This dataset comprises 11 labeled points clouds, derived from the union of several single scans or from the integration of the latter with photogrammetric surveys. The involved scenes are both indoor and outdoor, with churches, chapels, cloisters, porticoes and loggias covered by a variety of vaults and beared by many different types of columns. They belong to different historical periods and different styles, in order to make the dataset the least possible uniform and homogeneous (in the repetition of the architectural elements) and the results as general as possible. The experiments yield high accuracy, demonstrating the effectiveness and suitability of the proposed approach.

Exploiting the decrease of costs related to UAV technology, the humanitarian community started piloting the use of similar systems in humanitarian crises several years ago in different application fields, i.e., disaster mapping and information gathering, community capacity building, logistics and even transportation of goods. Part of the author’s group, composed of researchers in the field of applied geomatics, has been piloting the use of UAVs since 2006, with a specific focus on disaster management application. In the framework of such activities, a UAV deployment exercise was jointly organized with the Regional Civil Protection authority, mainly aimed at assessing the operational procedures to deploy UAVs for mapping purposes and the usability of the acquired data in an emergency response context. In the paper the technical features of the UAV platforms will be described, comparing the main advantages/disadvantages of fixed-wing versus rotor platforms. The main phases of the adopted operational procedure will be discussed and assessed especially in terms of time required to carry out each step, highlighting potential bottlenecks and in view of the national regulation framework, which is rapidly evolving. Different methodologies for the processing of the acquired data will be described and discussed, evaluating the fitness for emergency response applications.

In the photogrammetry field, interest in region detectors, which are widely used in Computer Vision, is quickly increasing due to the availability of new techniques. Images acquired by Mobile Mapping Technology, Oblique Photogrammetric Cameras or Unmanned Aerial Vehicles do not observe normal acquisition conditions. Feature extraction and matching techniques, which are traditionally used in photogrammetry, are usually inefficient for these applications as they are unable to provide reliable results under extreme geometrical conditions (convergent taking geometry, strong affine transformations, etc.) and for bad-textured images. A performance analysis of the SIFT technique in aerial and close-range photogrammetric applications is presented in this paper. The goal is to establish the suitability of the SIFT technique for automatic tie point extraction and approximate DSM (Digital Surface Model) generation. First, the performances of the SIFT operator have been compared with those provided by feature extraction and matching techniques used in photogrammetry. All these techniques have been implemented by the authors and validated on aerial and terrestrial images. Moreover, an auto-adaptive version of the SIFT operator has been developed, in order to improve the performances of the SIFT detector in relation to the texture of the images. The Auto-Adaptive SIFT operator (A² SIFT) has been validated on several aerial images, with particular attention to large scale aerial images acquired using mini-UAV systems.

The lack of benchmarking data for the semantic segmentation of digital heritage scenarios is hampering the development of automatic classification solutions in this field. Heritage 3D data feature complex structures and uncommon classes that prevent the simple deployment of available methods developed in other fields and for other types of data. The semantic classification of heritage 3D data would support the community in better understanding and analysing digital twins, facilitate restoration and conservation work, etc. In this paper, we present the first benchmark with millions of manually labelled 3D points belonging to heritage scenarios, realised to facilitate the development, training, testing and evaluation of machine and deep learning methods and algorithms in the heritage field. The proposed benchmark, available at http://archdataset.polito.it/, comprises datasets and classification results for better comparisons and insights into the strengths and weaknesses of different machine and deep learning approaches for heritage point cloud semantic segmentation, in addition to promoting a form of crowdsourcing to enrich the already annotated database.

This study describes the technical-systemic and conceptual-informative interoperability tests for the integration of a Historic Building Information Modeling (HBIM) model in a 3D Geographic Information System (GIS) environment aimed to provide complete and useful documentation for multiscale analyses on cultural heritage particularly exposed to risks. The case study of the San Lorenzo Church in Norcia (Italy) has been chosen given the urgent need to update the existing documentation for its protection and conservation issues, due to the extensive damage suffered after the series of earthquakes that occurred in central Italy starting from summer 2016. Different tests to evaluate two levels of conceptual interoperability (technical and semantic) when importing the HBIM model into a GIS environment were performed, whether with commercial software or with open source ones (ArcGIS Pro and QGIS, respectively). A data integration platform (Feature Manipulation Engine, FME) has been used for converting the IFC (Industry Foundation Classes) data format into the GML (Geography Markup Language) format, in order to obtain a unique and unified model and vocabulary for the 3D GIS project, structured with different levels of detail, according to CityGML standard. Finally, as HBIM-GIS integration is considered, the loss of geometric and informative data has been taken into account and evaluated.

During archaeological excavations it is important to monitor the new excavated areas and findings day by day in order to be able to plan future excavation activities. At present, this daily activity is usually performed by using total stations, which survey the changes of the archaeological site: the surveyors are asked to produce day by day draft plans and sections which allow archaeologists to plan their future activities. The survey is realized during the excavations or just at the end of every working day and drawings have to be produced as soon as possible in order to allow the comprehension of the work done and to plan the activities for the following day. By using this technique, all the measurements, even those not necessary for the day after, have to be acquired in order to avoid a ‘loss of memory’. A possible alternative to this traditional approach is aerial photogrammetry, if the images can be acquired quickly and at a taken distance able to guarantee the necessary accuracy of a few centimeters. Today the use of UAVs (Unmanned Aerial Vehicles) can be considered a proven technology able to acquire images at distances ranging from 4 m up to 20 m: and therefore as a possible monitoring system to provide the necessary information to the archaeologists day by day. The control network, usually present at each archaeological site, can give the stable control points useful for orienting a photogrammetric block acquired by using an UAV equipped with a calibrated digital camera and a navigation control system able to drive the aircraft following a pre-planned flight scheme. Modern digital photogrammetric software can solve for the block orientation and generate a DSM automatically, allowing rapid orthophoto generation and the possibility of producing sections and plans. The present paper describes a low cost UAV system realized by the research group of the Politecnico di Torino and tested on a Roman villa archaeological site located in Aquileia (Italy), a well-known UNESCO WHL site. The results of automatic orientation and orthophoto production are described in terms of their accuracy and the completeness of information guaranteed for archaeological site excavation management.