Preface: 3D GeoInfo 2021

3D GeoInfo 2021, the 16th GeoInfo conference, is an annual ISPRS workshop offering a forum for leading international decision makers and prominent voices in the field of 3D Geoinformation across the academic, commercial, and public sectors. The 2021 workshop is organized in conjunction with the 7th International FIG workshop on 3D Cadastres. The 2021 event was held virtually. Topics included: 3D data creation and acquisition 3D data processing and analysis 3D data management - data quality, metadata, provenance and trust Data integration, information fusion, multi-modal data analysis 3D visualization, including gamification, virtual reality, augmented reality 3D and Artificial Intelligence/Machine Learning 3D and Big Data, parallel computing, cloud computing 3D city modeling, underground infrastructure modeling, topography, and bathymetry modeling Building Information Modeling, Digital Twins, Smart Cities, Smart Infrastructure Usability and Human-Computer interaction in 3D GIS 3D GIS, spatial analysis and other applications (such as 3D cadastral systems, land administration, utilities, asset management, infrastructure, navigation, urban planning, geology, archaeology, marine systems, simulations, autonomous vehicles, facilities management, energy modeling, disaster and risk management, pandemic monitoring) The 3D GeoInfo 2021 tracks received 73 manuscripts including 30 full papers and 43 extended abstracts. The manuscripts were reviewed with a double-blind review process by members of the organizing and scientific committee and external reviewers. Ultimately 24 papers were accepted for the ISPRS Annals and 24 papers for the ISPRS Archives. We thank all of the authors and reviewers for their contributions.We look forward to the 3D GeoInfo 2021 virtual oral presentations and the opportunity to exchange ideas within our workshop and with the presenters and visitors of the 7th International FIG workshop on 3D Cadastres.

Preface: 3D GeoInfo 2021

3D GeoInfo 2021, the 16th GeoInfo conference, is an annual ISPRS workshop offering a forum for leading international decision makers and prominent voices in the field of 3D Geoinformation across the academic, commercial, and public sectors. The 2021 workshop is organized in conjunction with the 7th International FIG workshop on 3D Cadastres. The 2021 event was held virtually. Topics included: 3D data creation and acquisition 3D data processing and analysis 3D data management - data quality, metadata, provenance and trust Data integration, information fusion, multi-modal data analysis 3D visualization, including gamification, virtual reality, augmented reality 3D and Artificial Intelligence/Machine Learning 3D and Big Data, parallel computing, cloud computing 3D city modeling, underground infrastructure modeling, topography, and bathymetry modeling Building Information Modeling, Digital Twins, Smart Cities, Smart Infrastructure Usability and Human-Computer interaction in 3D GIS 3D GIS, spatial analysis and other applications (such as 3D cadastral systems, land administration, utilities, asset management, infrastructure, navigation, urban planning, geology, archaeology, marine systems, simulations, autonomous vehicles, facilities management, energy modeling, disaster and risk management, pandemic monitoring) The 3D GeoInfo 2021 tracks received 73 manuscripts including 30 full papers and 43 extended abstracts. The manuscripts were reviewed with a double-blind review process by members of the organizing and scientific committee and external reviewers. Ultimately 24 papers were accepted for the ISPRS Annals and 24 papers for the ISPRS Archives. We thank all of the authors and reviewers for their contributions.We look forward to the 3D GeoInfo 2021 virtual oral presentations and the opportunity to exchange ideas within our workshop and with the presenters and visitors of the 7th International FIG workshop on 3D Cadastres.

Unsupervised spatial-awareness attention-based and multi-scale domain adaption network for point cloud classification

Domain adaption is a special transfer learning method, whose source domain and target domain generally have different data distribution, but need to complete the same task. There have been many significant types of research on domain adaptation in 2D images, but in 3D data processing, domain adaptation is still in its infancy. Therefore, we design a novel domain adaptive network to complete the unsupervised point cloud classification task. Specifically, we propose a multi-scale transform module to improve the feature extractor. Besides, a spatial-awareness attention module combined with channel attention to assign weights to each node is designed to represent hierarchically scaled features. We have validated the proposed method on the PointDA-10 dataset for domain adaption classification tasks. Empirically, it shows strong performance on par or even better than state-of-the-art.

Use of Modern Technologies for the Conservation of Historical Heritage in Water Management

Historical monuments represent a cultural heritage that humanity has a duty to preserve and conserve. Lately all over the world, scanning these heritage objectives has become a priority, in order to preserve in the smallest details the used architecture. The work aims to complete the cultural heritage for Sânmihaiu Român hydro technical development built between 1912 and 1915, located on the Bega River in Western Romania, through modern mobile scanning technology, Leica Pegasus Backpack, necessary for the creation of a three-dimensional (3D) documentation, for the completion of the cultural heritage, and for the creation of a 3D database. The purpose of the scientific paper is restoring Sanmihaiu Roman Hidro technical Node, subject to degradation, in order to achieve the project “The navigable Bega”, waterway connection to Serbia. Collecting method of LiDAR data is Fused Slam, the acquisition of RINNEX data being made by placing a Leica GS08 Master Station. Visualization of quality graphics has been performed in Quality Control (QC) Tools. The scanning accuracy is between 2 and 3 cm and the 3D data processing was performed with the Cyclone Model version program, with SmartPick Point and Virtual Surveyor functions. The obtained point clouds will be of a great help in order to follow in time the construction which can be used whenever it will be needed by the designers and specialists in the field of hydrotechnics.

INCREASING TRACKING ROBUSTNESS FOR LOW-COMPLEXITY REAL-TIME RECONSTRUCTIONS WITH HANDHELD OPTICAL SCANNERS

By offering fast and flexible solutions to create 3D models, handheld scanners are currently under the focus of many research activities in various 3D data processing fields. The real-time constraint is still challenging to achieve especially when it comes with concurrent needs, such as level of accuracy in the data acquisition, easiness of recovering from scanning interruptions or loop closure abilities... Among them, object/scene tracking quality is one of the most critical. In this work, we describe two issues that affects its performance, focusing on the robustness of the process. Specifically, we encounter such issues at to two different steps while moving through the working pipeline of a prototype handheld scanner, i.e. (1) the data pre-processing before running a pairwise alignment between a frame and the model representation, called key-frame, and (2) the temporal and quality criteria that govern key-frame updates. Our approach simply consists in substituting the use of a rigid (uniform) pattern for sampling, with a random distribution of points. We then implement an adaptive statistical method to select suitable timing steps for key-frames refreshing, comparing this solution with a previous static one based on regular updating rate. We run experiments on a dataset created with our own scanner and we show that the adoption of such alternatives reduce the number of tracking failures, consequently increasing the robustness of the system, improving the quality of the alignments and preserving the real-time behavior of the device.

3D DATA PROCESSING TOWARD MAINTENANCE AND CONSERVATION. THE INTEGRATED DIGITAL DOCUMENTATION OF CASA DE VIDRO

<p><strong>Abstract.</strong> During the last decade, 3D integrated surveys and BIM modelling procedures have greatly improved the overall knowledge on some Brazilian Modernist buildings. In this framework, the <i>Casa de Vidro</i> 3D survey carried out by DIAPReM centre at Ferrara University, beside the important outputs, analysis and researches achieved from the point cloud database processing, was also useful to test several awareness increasing activities in cooperation with local stakeholders.</p><p>The first digital documentation test of the Casa de Vidro allowed verifying the feasibility of a full survey on the building towards the restoration and possible placement of new architectures into the garden as an archive-museum of the Lina Bo and P.M. Bardi Foundation. Later, full 3D integrated survey and diagnostic analysis were carried out to achieve the total digital documentation of the house sponsored by the Keeping it Modern initiative of Getty Foundation (Los Angeles). Following its characteristics, the survey had to take into consideration the different architectural features, up to the relationship of architecture and nature. These 3D documentation activities and the point cloud processing allowed several analysis in a multidisciplinary framework.</p>