Versenden
Drucken
Mohammadi, Reza und Datcu, Mihai (2021) Earth Observation Image Semantics: Latent Dirichlet Allocation Based Information Discovery. In: International Geoscience and Remote Sensing Symposium (IGARSS), Seiten 2620-2623. Institute of Electrical and Electronics Engineers. IGARSS 2021, 2021-07-11 - 2021-07-16, Brussels, Belgium. doi: 10.1109/IGARSS47720.2021.9553122. ISBN 978-1-6654-0369-6. ISSN 2153-7003.
![[img]](https://elib.dlr.de/style/images/fileicons/application_pdf.png) |
PDF
975kB |
Offizielle URL: https://ieeexplore.ieee.org/document/9553122
Kurzfassung
Land cover maps are among the most important products of Remote Sensing (RS) imagery. Despite remarkable advancements in land cover classification techniques, abundant detailed information in the very high-resolution RS images necessitates further improvements to harness the data and discover detailed semantic information. Moreover, scarcity of the labelled data and its quality is a major limitation in RS land cover mapping. In the present study, Latent Dirichlet Allocation is employed for semantic discovery in RS images and a novel kernel-based Bag of Visual Words model is proposed for land cover mapping.
| elib-URL des Eintrags: | https://elib.dlr.de/144966/ | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Dokumentart: | Konferenzbeitrag (Vortrag) | ||||||||||||
| Titel: | Earth Observation Image Semantics: Latent Dirichlet Allocation Based Information Discovery | ||||||||||||
| Autoren: |
| ||||||||||||
| Datum: | Juli 2021 | ||||||||||||
| Erschienen in: | International Geoscience and Remote Sensing Symposium (IGARSS) | ||||||||||||
| Referierte Publikation: | Ja | ||||||||||||
| Open Access: | Ja | ||||||||||||
| Gold Open Access: | Nein | ||||||||||||
| In SCOPUS: | Ja | ||||||||||||
| In ISI Web of Science: | Nein | ||||||||||||
| DOI: | 10.1109/IGARSS47720.2021.9553122 | ||||||||||||
| Seitenbereich: | Seiten 2620-2623 | ||||||||||||
| Verlag: | Institute of Electrical and Electronics Engineers | ||||||||||||
| ISSN: | 2153-7003 | ||||||||||||
| ISBN: | 978-1-6654-0369-6 | ||||||||||||
| Status: | veröffentlicht | ||||||||||||
| Stichwörter: | Latent Dirichlet Allocation, Semantic Discovery, Bag of Visual Words, Topic Modeling, Classification | ||||||||||||
| Veranstaltungstitel: | IGARSS 2021 | ||||||||||||
| Veranstaltungsort: | Brussels, Belgium | ||||||||||||
| Veranstaltungsart: | internationale Konferenz | ||||||||||||
| Veranstaltungsbeginn: | 11 Juli 2021 | ||||||||||||
| Veranstaltungsende: | 16 Juli 2021 | ||||||||||||
| 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 - Künstliche Intelligenz | ||||||||||||
| Standort: | Oberpfaffenhofen | ||||||||||||
| Institute & Einrichtungen: | Institut für Methodik der Fernerkundung > EO Data Science | ||||||||||||
| Hinterlegt von: | Otgonbaatar, Soronzonbold | ||||||||||||
| Hinterlegt am: | 18 Nov 2021 12:32 | ||||||||||||
| Letzte Änderung: | 24 Apr 2024 20:44 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags
