Special Issue "Point Cloud and Image Analysis for the Measurement of the Physical Form of Cities"

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Urban Remote Sensing".

Deadline for manuscript submissions: 31 August 2021.

Special Issue Editors

Dr. Lucía Díaz-Vilariño
E-Mail Website
Guest Editor
Applied Geotechnologies Research Group, Campus Universitario de Vigo, Universidade de Vigo, CINTECX, As Lagoas, Marcosende, 36310 Vigo, Spain
Interests: point cloud processing; 3D digital modeling; spatial analysis
Special Issues and Collections in MDPI journals
Prof. Dr. Antonio Fernández
E-Mail Website
Guest Editor
Department of Engineering Design, Universidade de Vigo, Rúa Maxwell s/n, 36310 Vigo, Spain
Interests: image processing; machine learning; computer vision; texture analysis
Special Issues and Collections in MDPI journals
Dr. Vítor Oliveira
E-Mail Website
Guest Editor
CITTA (Centro de Investigação do Território, Transportes e Ambiente), Faculdade de Engenharia, Universidade do Porto, s/n, R. Dr. Roberto Frias, 4200-465 Porto, Portugal
Interests: urban morphology; urban planning; architecture; cities

Special Issue Information

Dear Colleagues,

In the recent years, remote sensing has become a de facto technology for documenting and modelling the physical form of cities. Remote sensing—terrestrial, aerial, and satellite—has proven to be a suitable approach to effectively collect data at a large scale. Indeed, advances in the integration of sensors in terrestrial mobile platforms, together with the increasingly lower costs of technology, have significantly improved the availability and quality of data. As a result, automated data analysis has become a hot research topic.

Despite the potential of remote sensing for accurately measuring and modelling the physical form of cities, its use has not yet been adopted by the urban morphology community. Researchers in this area have traditionally used simple, two-dimensional representations to characterize city forms. In contrast, the remote sensing approach to urban modelling relies on complex, three-dimensional models that are built from a huge amount of data. Moving from two- to three-dimensional representations requires careful considerations of the costs and benefits associated with such a transition. Complex 3D models may provide rich insights not only on city forms, but also on the process of urban landscape formation, but in order for this approach to be effective, it is of paramount importance to clearly distinguish which data are relevant and which are superfluous.

This Special Issue aims at collecting the recent advances in the use of remote sensing data for the measurement of the physical form of cities. We welcome submissions on the integration of measurement techniques with existing morphological theories, concepts, and methods. Specific topics include, but are not limited to, the following:

  • New remote sensing technologies for urban measurement;
  • Image processing for large-scale urban modelling;
  • 3D modelling of urban areas from point cloud processing;
  • Spatial analysis of urban-landscape changes;
  • 3D analysis of urban landscape;
  • 3D space syntax;
  • Urban structure analysis based on 2D and/or 3D morphology;
  • Impacts of 3D morphology on the urban environment and ecology.

Dr. Lucía Díaz-Vilariño
Dr. Antonio Fernández
Dr. Vítor Oliveira
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:


Deep Learning Segmentation and Classification for Urban Village Using a Worldview Satellite Image Based on U-Net
Remote Sens. 2020, 12(10), 1574; https://0-doi-org.brum.beds.ac.uk/10.3390/rs12101574 - 15 May 2020
Cited by 12 | Viewed by 1581
Unplanned urban settlements exist worldwide. The geospatial information of these areas is critical for urban management and reconstruction planning but usually unavailable. Automatically characterizing individual buildings in the unplanned urban village using remote sensing imagery is very challenging due to complex landscapes and [...] Read more.
Unplanned urban settlements exist worldwide. The geospatial information of these areas is critical for urban management and reconstruction planning but usually unavailable. Automatically characterizing individual buildings in the unplanned urban village using remote sensing imagery is very challenging due to complex landscapes and high-density settlements. The newly emerging deep learning method provides the potential to characterize individual buildings in a complex urban village. This study proposed an urban village mapping paradigm based on U-net deep learning architecture. The study area is located in Guangzhou City, China. The Worldview satellite image with eight pan-sharpened bands at a 0.5-m spatial resolution and building boundary vector file were used as research purposes. There are ten sites of the urban villages included in this scene of the Worldview image. The deep neural network model was trained and tested based on the selected six and four sites of the urban village, respectively. Models for building segmentation and classification were both trained and tested. The results indicated that the U-net model reached overall accuracy over 86% for building segmentation and over 83% for the classification. The F1-score ranged from 0.9 to 0.98 for the segmentation, and from 0.63 to 0.88 for the classification. The Interaction over Union reached over 90% for the segmentation and 86% for the classification. The superiority of the deep learning method has been demonstrated through comparison with Random Forest and object-based image analysis. This study fully showed the feasibility, efficiency, and potential of the deep learning in delineating individual buildings in the high-density urban village. More importantly, this study implied that through deep learning methods, mapping unplanned urban settlements could further characterize individual buildings with considerable accuracy. Full article
Show Figures

Graphical abstract

Planned Papers

The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.

Type of Paper: Article
Tentative Title: Introducing a new digital tool for 3D Space Syntax analysis: DepthSpace3D
Authors: Franklim Morais (LIA-ESAP), Jorge Vieira Vaz (LIA-ESAP), Catarina Ruivo (CIAUD-FAUL) and David Leite Viana (ISTAR-IUL)

Research framework: The contents of this paper come from the research project ‘OPOArch Formal Methods’, developed during two years (2016-18) at the Research Laboratory for Architecture (LIA), Oporto Arts University School (ESAP). This research was funded by NORTE2020, PT2020 and the European Union (EU). The project is still ongoing, mainly concerning the improvement of the software’s interface, to make it more user-friendly.

Research problem: Considering previous research developed by the authors on specific domains of Architecture and Urban Studies (A&US) using Space Syntax (SS) and the state of the art regarding 3D tools in configurational analysis to address issues like the measurement of the physical form of the cities, rough topography in urban spaces; dynamic volumetric geometry (size, elevation, interpenetration), joint analysis of the interior of each building and its urban environment (in particular, when there are high-rise buildings), the research problem focus on 3D SS analysis. The main question was to develop a new digital tool to increase the range of possibilities when targeting space configuration, accessibility and visibility analysis – that we named SCAVA.

Research main goal: To develop a new digital tool for 3D SS analysis, called DepthSpace3D (DS3D). The paper will demonstrate that the use of DS3D software can not only improve results of A&US, but is also capable of opening new trends. For instance, the statistical analysis of SS studies can demonstrate that Space Syntax is very proficient in Urban Studies, but is much less used in Architecture. A good conjecture is that architecture needs the volumetric and dynamic perception some architectural theoreticians pleaded for. 3D analysis could very well be a powerful tool in formalizing the classical theoretical architecture concepts such as proportions and scales, hierarchy or rhythm.

Research methodology: Based on quantitative approaches and formal methods in Architecture and Urbanism, the research was structured having in mind the following aspects –

i) A conceptual model – full 3D spaces, with three main conceptual spaces: the viewing, the viewed and the obstacle spaces. Viewing Space (with multiple Paths, with different visibility weights); Viewed Space (two-sided Surfaces and Global Volume), also with different visibility weights, and with the possibility to introduce properties or attributes to different regions of the space; Obstacle Space, with different and non-Boolean transparencies and opacities;

ii) A user-friendly interface: data input and results output in a 3D CAD tool; display of the results, either in graphical and numerical forms: 3D of the Viewed Surfaces, 3D of any slice of the Viewed Global Space, 2D of all the slices of the Viewed Global Space, 3D of the View Space;

iii) Special features accessible to the user: changes in the user interface (themes and masks); a growing geometry generator library; a generative grammar for the “space syntaxes” – with this tool, the study is not limited to the standard concepts (depth, isovist, connectivity, etc.) as the generation of new concepts can be formalized;

iv) An openness of DS3D: open Data Base with all the data (inputs and results) of the analyzed cases; open-source code;

v) Some case studies highlighting the real benefits of 3D analysis.

Paper’s discussion: The researchers of DS3D project have been able to confirm the value of SS in the analysis of A&US. Nevertheless, the lack of a powerful software tool with 3D SS analysis capability has been the cause of some restrictions in the deepening of the analysis in certain cases. For example, the work of the global analysis of the city of Maputo, by David Leite Viana, with intense use of SS 2D tools, could not deal with the problem of altimetry, since Maputo is well known for having a low town and an upper town. In the intensive use of SS to study segregation and privacy in thirteen collective housing achievements in twentieth-century Oporto, Catarina Ruivo concluded that 3D analysis could improve the results. Although SS 2D could deal fairly well with the interior of each home and the middle-scale urban environment, it could not manage the high-rise buildings as a whole, and also the relation of the building and its near environment treated as a unique domain of analysis. Therefore, the paper will go deeper introducing the new 3D digital tool for SS analysis.

Paper’s contribution to scientific knowledge: As mentioned, the paper will present DS3D, a 3D SS analysis software, free for academic use, that will make evident that new theoretical paths are able to be defined towards the improvement of A&US configurational analysis and the understanding of the physical form of the cities.

Back to TopTop