Special Issue "Automatic Feature Recognition from Point Clouds"

A special issue of ISPRS International Journal of Geo-Information (ISSN 2220-9964).

Deadline for manuscript submissions: closed (31 May 2021).

Special Issue Editors

Dr. Florent Poux
E-Mail Website
Guest Editor
Geomatics Unit, University of Liège, Allée du six Août, 19-4000 Liège, Belgium
Interests: point clouds; laser scanning; 3D modeling
Special Issues and Collections in MDPI journals
Dr. Roland Billen
E-Mail Website
Guest Editor
Geomatics Unit, University of Liège, Allée du six Août, 19 - 4000, Liège, Belgium
Interests: 3D GIS; Qualitative Spatial Reasoning; 3D data acquisition; GIS design; ontologies.

Special Issue Information

Dear Colleagues,

Over the past few decades, point clouds from reality capture devices have been major data sources used by the geo-information and remote sensing communities. Recently, processing massive geospatial point cloud data has drawn extensive attention from the robotics, computer vision and computer graphics communities. The drive of this call is primarily to grow interdisciplinary interaction, interoperable frameworks and collaboration in point cloud processing among geo-information, photogrammetry, remote sensing, computer vision, computer graphics and robotics.

Applications are numerous, and potentially increasing if we consider point clouds as digital reality assets. Yet, this expansion faces technical limitations mainly from the lack of semantic information within point ensembles. Connecting knowledge sources is still a very manual and time-consuming process which can suffer from error-prone human interpretation. This highlights a strong need for automated solutions to create coherent and structured information that can use relevant and flexible feature descriptors. This theme issue aims at gathering new insights in point cloud processing to better characterize these spatial datasets for various tasks while strongly considering interoperable usages. Specifically, application-driven processes linked to spatial information modelling (CAD, BIM, GIS), infrastructure management, cultural heritage and remote sensing applications are encouraged.

We anticipate that the advancement of data mining and the infatuation of reality capture will continue to push the research communities forward. Particularly, ways to obtain high-quality application-oriented labelled datasets will permit a wider dissemination of robust learning approaches. Henceforth, we encourage authors to submit original research articles, review papers and case studies from both theoretical and application-oriented perspectives on this significant and exciting subject. In more details, topics suitable for this Special Issue include (but are not necessarily limited to):

  • Georeferenced point clouds from laser scanners (mobile, hand-held, backpack-mounted, terrestrial, aerial)
  • Point clouds from panoramas, phone/cameras images, oblique and satellite imagery
  • Point Cloud segmentation, classification, semantic enrichment for application-driven scenario
  • Point Cloud structuration and knowledge integration
  • Point Cloud Knowledge extraction and high-performance feature extraction for large-scale datasets
  • 2D floorplan generation of indoor point clouds
  • Industrial applications with large-scale point clouds
  • Feature-based rendering and visualization of large-scale point clouds
  • Deep learning for point cloud processing

Dr. Florent Poux
Dr. Roland Billen
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. ISPRS International Journal of Geo-Information is an international peer-reviewed open access monthly 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 1400 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.

Keywords

  • Feature selection, feature recognition, feature extraction and feature fusion
  • Semantic segmentation, instance segmentation and object recognition
  • Feature-based classification, learning-based classification, deep learning
  • 3D Point Cloud, terrestrial laser scanner, LiDAR, photogrammetry
  • 3D data structure, knowledge integration, knowledge representation, ontology
  • Infrastructure, remote sensing, cultural heritage, BIM, CAD, GIS

Published Papers (2 papers)

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

Research

Article
CityJSON Building Generation from Airborne LiDAR 3D Point Clouds
ISPRS Int. J. Geo-Inf. 2020, 9(9), 521; https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi9090521 - 31 Aug 2020
Cited by 3 | Viewed by 1252
Abstract
The relevant insights provided by 3D City models greatly improve Smart Cities and their management policies. In the urban built environment, buildings frequently represent the most studied and modeled features. CityJSON format proposes a lightweight and developer-friendly alternative to CityGML. This paper proposes [...] Read more.
The relevant insights provided by 3D City models greatly improve Smart Cities and their management policies. In the urban built environment, buildings frequently represent the most studied and modeled features. CityJSON format proposes a lightweight and developer-friendly alternative to CityGML. This paper proposes an improvement to the usability of 3D models providing an automatic generation method in CityJSON, to ensure compactness, expressivity, and interoperability. In addition to a compliance rate in excess of 92% for geometry and topology, the generated model allows the handling of contextual information, such as metadata and refined levels of details (LoD), in a built-in manner. By breaking down the building-generation process, it creates consistent building objects from the unique source of Light Detection and Ranging (LiDAR) point clouds. Full article
(This article belongs to the Special Issue Automatic Feature Recognition from Point Clouds)
Show Figures

Figure 1

Article
Machine Learning Generalisation across Different 3D Architectural Heritage
ISPRS Int. J. Geo-Inf. 2020, 9(6), 379; https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi9060379 - 09 Jun 2020
Cited by 9 | Viewed by 1734
Abstract
The use of machine learning techniques for point cloud classification has been investigated extensively in the last decade in the geospatial community, while in the cultural heritage field it has only recently started to be explored. The high complexity and heterogeneity of 3D [...] Read more.
The use of machine learning techniques for point cloud classification has been investigated extensively in the last decade in the geospatial community, while in the cultural heritage field it has only recently started to be explored. The high complexity and heterogeneity of 3D heritage data, the diversity of the possible scenarios, and the different classification purposes that each case study might present, makes it difficult to realise a large training dataset for learning purposes. An important practical issue that has not been explored yet, is the application of a single machine learning model across large and different architectural datasets. This paper tackles this issue presenting a methodology able to successfully generalise to unseen scenarios a random forest model trained on a specific dataset. This is achieved looking for the best features suitable to identify the classes of interest (e.g., wall, windows, roof and columns). Full article
(This article belongs to the Special Issue Automatic Feature Recognition from Point Clouds)
Show Figures

Graphical abstract

Back to TopTop