Category: Research
-
NEOHAZ goes in the second round
The NEOHAZ project will be funded by the Heidelberg Academy of Sciences and Humanities for a second phase till the end of 2018. This prolonging enables further research about the integration of implicit knowledge from non-scientists in disaster management. The findings and methods of the first part will be used within the context of a…
-
Towards evaluating the mobile crowdsourcing of geographic information about human settlements
Geographic information crowdsourcing is an increasingly popular approach to derive geographic data about human settlements from remotely sensed imagery. However, crowdsourcing approaches are frequently associated with uncertainty about the quality of the information produced. Although previous studies have found acceptable quality of crowdsourced information in some application domains, there is still lack of research about…
-
DGPF Annual Meeting 2017 – Visual impressions
Three talks from GIScience Heidelberg were given at the Annual Meeting 2017 of the DGPF (German Society for Photogrammetry, Remote Sensing and Geoinformation) on 9 March 2017. Thanks a lot to Benni, Tomás and Sebastian for the very nice talks. More technical infos on the presented research can be found in the previous blog post…
-
A Framework of Quality Assessment Methods for Crowdsourced Geographic Information: a Systematic Literature Review
Crowdsourced Geographic Information (CGI) has emerged as a potential source of geographic information for different domains. Despite advantages associated with it, such information lacks quality assurance, since it is provided by different individuals. Several authors have investigated different approaches to assess CGI quality. Some of the existing methods have been summarized in different classification schemas.…
-
Call for Abstracts “3D-Punktwolken in der Geographie” – Deutscher Kongress für Geographie 2017 (Deadline 31. März 2017)
Wir laden alle herzlich dazu ein, einen Vortragsbeitrag (Abstract) zu unserer Fachsitzung “3D-Punktwolken in der Geographie – Erfassung, Analyse und Visualisierung” (LT6-FS4) für den Deutschen Kongress für Geographie am 30.9. – 5.10.2017 in Tübingen einzureichen. Für fachliche Fragen stehen die Fachsitzungsleiter Bernhard Höfle (Heidelberg) und Martin Rutzinger (Innsbruck) gerne zur Verfügung. Online Einreichung eines Abstracts:…
-
DGPF Annual Meeting 2017 – Three presentations from GIScience Heidelberg
At the Annual Meeting 2017 of the DGPF (German Society for Photogrammetry, Remote Sensing and Geoinformation) GIScience Heidelberg will contribute three talks on 9 March 2017. Citizen Science in Schulen: Entwicklung von 3D-MicroMapping zur Klassifikation von 3D-Punktwolken (Research Project: 3D-MAPP) The Heidelberg LiDAR Operations Simulator HELIOS as a Supporting Tool for Capturing and Preserving Cultural…
-
3rd PhD Colloquium of the DGK Section on Geoinformatics and the DGPF Working Group on Geoinformatics
On 7 March 2017 the 3rd PhD Colloquium of the DGK Section on Geoinformatics and the DGPF Working Group on Geoinformatics took place in Würzburg, Germany – organized by Prof. Jan-Henrik Haunert (Bonn) and Bernhard Höfle (Heidelberg). The presentations covered a wide range of topics (e.g. 3D indoor mapping, air pollution modeling, traffic time series…
-
Completeness of Citizen Science Biodiversity Data from a Volunteered Geographic Information Perspective
Observations of living organisms by citizen scientists that are reported to online portals are a valuable source of information. They are also a special kind of volunteered geographic information (VGI). VGI data have issues of completeness, which arise from biases caused by the opportunistic nature of the data collection process. We examined the completeness of…
-
Prize of “Runder Tisch GIS” for GIScience Master Thesis on Geospatial Analysis of the German Software Industry (Jan Kinne, Heidelberg)
The Master Thesis of Jan Kinne on the subject: “The Geographic Dispersal of the German Software Industry – Geospatial Analysis and Location Pattern Modeling” won the price “Nachwuchsförderpreis Geoinformatik 2017” of the “Runde Tisch GIS e.V.” in the category ‘Master Thesis’ with a value of 1.500 Euro. In addition Jan did also win the audience…
-
DeepVGI: Deep Learning with Volunteered Geographic Information
Deep learning techniques, esp. Convolutional Neural Networks (CNNs), are now widely studied for predictive analytics with remote sensing images, which can be further applied in different domains for ground object detection, population mapping, etc. These methods usually train predicting models with the supervision of a large set of training examples. However, finding ground truths especially…