elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Impressum | Datenschutz | Kontakt | English
Schriftgröße: [-] Text [+]

Deep Learning for Mapping Forests with TanDEM-X

Bueso Bello, Jose Luis und Carcereri, Daniel und Gonzalez, Carolina und Martone, Michele und Rizzoli, Paola (2022) Deep Learning for Mapping Forests with TanDEM-X. In: Proceedings of the European Conference on Synthetic Aperture Radar, EUSAR. VDE Verlag GmbH. European Conference on Synthetic Aperture Radar (EUSAR), 2022-07-25 - 2022-07-27, Leipzig, Germany. ISSN 2197-4403.

[img] PDF
1MB

Kurzfassung

In a bistatic SAR system such as TanDEM-X, characterized by the absence of temporal decorrelation, the interferometric coherence adds valuable information to the common amplitude images, typically acquired by monostatic SAR systems. The interferometric SAR dataset, acquired to generate the TanDEM-X global Digital Elevation Model (DEM), represents a unique data source to derive land classification maps at global scale, such as the TanDEM-X Forest/Non-Forest Map and the TanDEM-X Water Body Layer. Both maps have as main input the interferometric coherence and are based on a supervised fuzzy clustering algorithm and on the watershed segmentation algorithm, respectively. Single images are classified with the corresponding algorithm and a final weighting mosaicking strategy of overlapping coverages is necessary to improve the final accuracy of the generated classification maps. In this work, we investigate the capabilities of using a state-of-the-art convolutional neural network (CNN) with TanDEM-X interferometric data for forest and water mapping on a large scale. An ad-hoc training strategy has been developed to train a U-Net-like architecture, which aims at balancing the training data set with respect all possible acquisition geometries that can be found in TanDEM-X acquisitions. The Amazon rainforest has been used as region of interest (ROI) to compare the improvement in image classification with respect to the reference fuzzy-clustering approach. On forest classification, a significant performance improvement with respect to the clustering approach, with an f-score increase of 0.13 has been measured. This classification improvement of the forested areas, as well as the capabilities of the U-Net to accurately classify water bodies without the necessity of mosaicking overlapping acquisitions to improve the final classification accuracy, make it possible to generate up to three time-tagged mosaics over the Amazon rainforest by utilizing the nominal TanDEM-X acquisitions between 2011 and 2017.

elib-URL des Eintrags:https://elib.dlr.de/148722/
Dokumentart:Konferenzbeitrag (Vortrag)
Titel:Deep Learning for Mapping Forests with TanDEM-X
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Bueso Bello, Jose LuisNICHT SPEZIFIZIERThttps://orcid.org/0000-0003-3464-2186NICHT SPEZIFIZIERT
Carcereri, DanielNICHT SPEZIFIZIERTNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Gonzalez, CarolinaNICHT SPEZIFIZIERThttps://orcid.org/0000-0002-9340-1887NICHT SPEZIFIZIERT
Martone, MicheleNICHT SPEZIFIZIERThttps://orcid.org/0000-0002-4601-6599NICHT SPEZIFIZIERT
Rizzoli, PaolaNICHT SPEZIFIZIERThttps://orcid.org/0000-0001-9118-2732NICHT SPEZIFIZIERT
Datum:Juli 2022
Erschienen in:Proceedings of the European Conference on Synthetic Aperture Radar, EUSAR
Referierte Publikation:Ja
Open Access:Ja
Gold Open Access:Nein
In SCOPUS:Ja
In ISI Web of Science:Nein
Verlag:VDE Verlag GmbH
ISSN:2197-4403
Status:veröffentlicht
Stichwörter:Synthetic Aperture Radar, TanDEM-X, rainforest, tropical forest, forest mapping, deforestation monitoring, deep learning, convolutional neural network
Veranstaltungstitel:European Conference on Synthetic Aperture Radar (EUSAR)
Veranstaltungsort:Leipzig, Germany
Veranstaltungsart:internationale Konferenz
Veranstaltungsdatum:2022-07-25 - 2022-07-27
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Raumfahrt
HGF - Programmthema:Erdbeobachtung
DLR - Schwerpunkt:Raumfahrt
DLR - Forschungsgebiet:R EO - Erdbeobachtung
DLR - Teilgebiet (Projekt, Vorhaben):R - Unterstützung TerraSAR-X/TanDEM-X Betrieb
Standort: Oberpfaffenhofen
Institute & Einrichtungen:Institut für Hochfrequenztechnik und Radarsysteme
Institut für Hochfrequenztechnik und Radarsysteme > Satelliten-SAR-Systeme
Hinterlegt von: Bueso Bello, Jose Luis
Hinterlegt am:09 Feb 2022 06:11
Letzte Änderung:28 Feb 2024 14:52

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

Blättern
Suchen
Hilfe & Kontakt
Informationen
electronic library verwendet EPrints 3.3.12
Gestaltung Webseite und Datenbank: Copyright © Deutsches Zentrum für Luft- und Raumfahrt (DLR). Alle Rechte vorbehalten.