Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Automatic Generation of Training Data for Land Use and Land Cover Classification by Fusing Heterogeneous Data Sets

 
: Schmitz, Sylvia; Weinmann, Martin; Weidner, Uwe; Hammer, Horst; Thiele, Antje

:
Volltext (PDF; )

Kersten, T.P. ; Deutsche Gesellschaft für Photogrammetrie, Fernerkundung und Geoinformation -DGPF-:
40. Wissenschaftlich-Technische Jahrestagung der DGPF 2020. Online resource : 4. - 6. März 2020, Stuttgart
Berlin: DGPF, 2020 (Publikationen der Deutschen Gesellschaft für Photogrammetrie, Fernerkundung und Geoinformation 29)
https://www.dgpf.de/src/tagung/jt2020/proceedings/start.html
S.73-86
Deutsche Gesellschaft für Photogrammetrie, Fernerkundung und Geoinformation (DGPF Wissenschaftlich-Technische Jahrestagung) <40, 2020, Stuttgart>
Englisch
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()

Abstract
Nowadays, automatic classification of remote sensing data can efficiently produce maps of land use and land cover, which provide an essential source of information in the field of environmental sciences. Most state-of-the-art algorithms use supervised learning methods that require a large amount of annotated training data. In order to avoid time-consuming manual labelling, we propose a method for the automatic annotation of remote sensing data that relies on available land use and land cover information. Using the example of automatic labelling of SAR data, we show how the Dempster-Shafer evidence theory can be used to fuse information from different land use and land cover products into one training data set. Our results confirm that the combination of information from OpenStreetMap, CORINE Land Cover 2018, Global Surface Water and the SAR data itself leads to reliable class assignments, and that this combination outperforms each considered single land use and land cover product.

: http://publica.fraunhofer.de/dokumente/N-621399.html