Geospatial Crowdsourced Data - Validation and Classification

A special issue of Data (ISSN 2306-5729).

Deadline for manuscript submissions: closed (31 October 2018) | Viewed by 4464

Special Issue Editors

E-Mail Website
Guest Editor
Institute for Systems and Computers Engineering at Coimbra, Department of Mathematics, University of Coimbra, 3001-501 Coimbra, Portugal
Interests: spatial data validation and quality assessment; land use land cover mapping; volunteered geographic information; spatial data integration; remote sensing
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
1. School of Technology-IADE, Universidade Europeia, Lisbon, Portugal
2. Institute for Systems Engineering and Computers at Coimbra, Coimbra, Portugal
Interests: volunteered geographic information; geographic information science; land use and land cover mapping; spatial data infrastructure; geospatial data analytics

E-Mail Website1 Website2
Guest Editor
Department of Informatics Engineering, University of Coimbra, Pólo II da Universidade de Coimbra, 3030-290 Coimbra, Portugal
Interests: cyber-physical systems; data analysis and processing; intelligent systems; wireless sensor networks; sensor data fusion; remote and virtual laboratories; geographic information systems; soft computing; supervision and fault diagnosis; predictive maintenance
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

In the last decade, there was exponential growth in the number of projects that collect Crowdsourced Geospatial Data (CGD), also called Volunteered Geographical Information (VGI). This allows the collection of large volumes of data of many different types, such as georeferenced photographs (e.g., using Flickr or Instagram), tweets, the classification of what occurs at predefined locations (e.g., campaigns of GeoWiki or Ushahidi), the creation and classification of digital objects (e.g., vector data creation and classification in OpenStreetMap or Wikimapia) or the reporting of events (e.g., at portals of municipalities or Facebook).

This new way of collecting data, provided by regular citizens, potentially allows the obtainment of data that would not be otherwise available. However, this also means that there is usually no reference data available to assess their accuracy, which is one of the most important topics concerning the use of CGD for operational or scientific applications. Moreover, one of the main problems related to crowdsourced data is the quality of the data collected, as volunteers may create data with errors and/or limitations, such as the assignment of incorrect classifications to identified objects in an aerial or satellite images, geolocation with errors or low precision, uploading of wrong data, differences of interpretation among volunteers, incorrect use of the available tools to collect data, etc. All this makes CGD validation a hot topic, and further developments in the near future to make full use of the potential of CGD are needed.

On the other hand, the collection of large quantities of data requires the use of data mining and aggregation techniques to extract useful information to support decision making, thus increasing the value of using this type of data.

In the above context, we would like to invite you to submit original articles presenting results or new methods, frameworks or methodologies for CGD validation and classification, which may depend only on collected CGD or may include other types of data, such as data collected by physical sensors or remote sensing techniques. Articles about the communication of CGD quality, uncertainty or the extracted information are also welcome. Potential topics include, but are not limited to:

    • Big data
    • Classification
    • Data cleaning
    • Data integration
    • Data mining
    • Data validation
    • Data analytics
    • Performance of Methods
    • Physical sensors
    • Quality assessment
    • Remote sensors
    • Uncertainty
    • Visualization
Prof. Dr. Cidália Costa Fonte
Prof. Dr. Jacinto Estima
Prof. Dr. Alberto Cardoso
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at 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 submissions that pass pre-check are 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. Data 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 1600 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:


24 pages, 14905 KiB  
A Cluster Graph Approach to Land Cover Classification Boosting
by Lloyd Haydn Hughes, Simon Streicher, Ekaterina Chuprikova and Johan Du Preez
Data 2019, 4(1), 10; - 10 Jan 2019
Cited by 3 | Viewed by 3651
When it comes to land cover classification, the process of deriving the land classes is complex due to possible errors in algorithms, spatio-temporal heterogeneity of the Earth observation data, variation in availability and quality of reference data, or a combination of these. This [...] Read more.
When it comes to land cover classification, the process of deriving the land classes is complex due to possible errors in algorithms, spatio-temporal heterogeneity of the Earth observation data, variation in availability and quality of reference data, or a combination of these. This article proposes a probabilistic graphical model approach, in the form of a cluster graph, to boost geospatial classifications and produce a more accurate and robust classification and uncertainty product. Cluster graphs can be characterized as a means of reasoning about geospatial data such as land cover classifications by considering the effects of spatial distribution, and inter-class dependencies in a computationally efficient manner. To assess the capabilities of our proposed cluster graph boosting approach, we apply it to the field of land cover classification. We make use of existing land cover products (GlobeLand30, CORINE Land Cover) along with data from Volunteered Geographic Information (VGI), namely OpenStreetMap (OSM), to generate a boosted land cover classification and the respective uncertainty estimates. Our approach combines qualitative and quantitative components through the application of our probabilistic graphical model and subjective expert judgments. Evaluating our approach on a test region in Garmisch-Partenkirchen, Germany, our approach was able to boost the overall land cover classification accuracy by 1.4% when compared to an independent reference land cover dataset. Our approach was shown to be robust and was able to produce a diverse, feasible and spatially consistent land cover classification in areas of incomplete and conflicting evidence. On an independent validation scene, we demonstrated that our cluster graph boosting approach was generalizable even when initialized with poor prior assumptions. Full article
(This article belongs to the Special Issue Geospatial Crowdsourced Data - Validation and Classification)
Show Figures

Graphical abstract

Back to TopTop