Hong, Danfeng und Chanussot, Jocelyn und Yokoya, Naoto und Heiden, Uta und Heldens, Wieke und Zhu, Xiao Xiang (2019) WU-Net: A Weakly-supervised Unmixing Network for Remotely Sensed Hyperspectral Imagery. In: 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Seiten 1-4. IGARSS 2019, 28. Juli - 2. Aug. 2019, Yokohama, Japan. doi: 10.1109/igarss.2019.8899865.
Dies ist die aktuellste Version dieses Eintrags.
PDF
613kB |
Kurzfassung
Recently, enormous efforts have been made to improve the performance of the linear or nonlinear mixing model for hyperspectral unmixing, yet their ability to handle spectral variability and extract physically meaningful endmembers remains limited. Based on the powerful learning ability of deep learning, we propose a weakly-supervised unmixing network, called WU-Net, to break the bottleneck. Beyond the autoencoder-like architecture, WU-Net learns an additional network from the pure or nearly-pure endmembers to correct the weights of another unmixing network towards a more accurate and interpretable unmixing solution, thus yielding a two-stream deep network. Experimental results conducted on two different datasets, one fully artificial simulation dataset and one simulated EnMap dataset generated from a real HyMap dataset, demonstrate the effectiveness and superiority of WU-Net over several state-of-the-art algorithms
elib-URL des Eintrags: | https://elib.dlr.de/128489/ | ||||||||||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Konferenzbeitrag (Vortrag) | ||||||||||||||||||||||||||||
Titel: | WU-Net: A Weakly-supervised Unmixing Network for Remotely Sensed Hyperspectral Imagery | ||||||||||||||||||||||||||||
Autoren: |
| ||||||||||||||||||||||||||||
Datum: | 2019 | ||||||||||||||||||||||||||||
Erschienen in: | 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) | ||||||||||||||||||||||||||||
Referierte Publikation: | Ja | ||||||||||||||||||||||||||||
Open Access: | Ja | ||||||||||||||||||||||||||||
Gold Open Access: | Nein | ||||||||||||||||||||||||||||
In SCOPUS: | Nein | ||||||||||||||||||||||||||||
In ISI Web of Science: | Nein | ||||||||||||||||||||||||||||
DOI: | 10.1109/igarss.2019.8899865 | ||||||||||||||||||||||||||||
Seitenbereich: | Seiten 1-4 | ||||||||||||||||||||||||||||
Status: | veröffentlicht | ||||||||||||||||||||||||||||
Stichwörter: | Deep learning, hyperspectral imagery,remote sensing, spectral unmixing, two-stream network,weakly-supervised, HyMap, EnMAP | ||||||||||||||||||||||||||||
Veranstaltungstitel: | IGARSS 2019 | ||||||||||||||||||||||||||||
Veranstaltungsort: | Yokohama, Japan | ||||||||||||||||||||||||||||
Veranstaltungsart: | internationale Konferenz | ||||||||||||||||||||||||||||
Veranstaltungsdatum: | 28. Juli - 2. Aug. 2019 | ||||||||||||||||||||||||||||
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 - Vorhaben hochauflösende Fernerkundungsverfahren (alt) | ||||||||||||||||||||||||||||
Standort: | Oberpfaffenhofen | ||||||||||||||||||||||||||||
Institute & Einrichtungen: | Institut für Methodik der Fernerkundung > EO Data Science Deutsches Fernerkundungsdatenzentrum > Dynamik der Landoberfläche | ||||||||||||||||||||||||||||
Hinterlegt von: | Hong, Danfeng | ||||||||||||||||||||||||||||
Hinterlegt am: | 22 Jul 2019 13:23 | ||||||||||||||||||||||||||||
Letzte Änderung: | 24 Jul 2023 11:57 |
Verfügbare Versionen dieses Eintrags
- WU-Net: A Weakly-supervised Unmixing Network for Remotely Sensed Hyperspectral Imagery. (deposited 22 Jul 2019 13:23) [Gegenwärtig angezeigt]
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags