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

A Near Real-Time Automated Oil Spill Surveillance System Using SAR and its Application to a New Study Area

Yang, Yi-Jie und Schnupfhagn, Christoph (2024) A Near Real-Time Automated Oil Spill Surveillance System Using SAR and its Application to a New Study Area. In: 15th European Conference on Synthetic Aperture Radar, EUSAR 2024, Seiten 447-452. VDE. EUSAR 2024, 2024-04-23 - 2024-04-26, München, Germany. ISBN 978-380076287-6. ISSN 2197-4403.

[img] PDF - Nur DLR-intern zugänglich bis 1 September 2025
2MB

Offizielle URL: https://ieeexplore.ieee.org/document/10659580

Kurzfassung

This study proposes a near real-time oil spill surveillance system using Sentinel-1 synthetic aperture radar (SAR) imagery. The users only need to provide the coordinates of their areas of interest. With such information, the system automatically downloads the SAR scenes located within the study area and preprocesses those scenes with several corrections, such as noise removal and calibration. Afterwards, a custom-trained You Only Look Once version 4 (YOLOv4) object detector is applied to a YOLO-based Oil Detection Algorithm (YODA) for targeting oil slicks inside the SAR scenes. These oil slicks are defined by bounding boxes and fed to a segmentation algorithm for obtaining the exact locations covered by oil. This study selected the Southeastern Mediterranean Sea as a study area, where each Sentinel-1 track includes four continuous SAR scenes. From obtaining these four scenes to delivering oil slick binary masks to the users, it takes around 17 minutes for a computer with a GPU. The object detector was trained with a collection of oil slicks in the study area; however, it is feasible to extend the usage of the current system to other regions with further training on specific types and sources of oil slicks from the regions.

elib-URL des Eintrags:https://elib.dlr.de/202286/
Dokumentart:Konferenzbeitrag (Poster)
Titel:A Near Real-Time Automated Oil Spill Surveillance System Using SAR and its Application to a New Study Area
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Yang, Yi-JieYi-Jie.Yang (at) dlr.de / CAU Kiel, Germanyhttps://orcid.org/0000-0002-4098-8119NICHT SPEZIFIZIERT
Schnupfhagn, Christophchristoph.schnupfhagn (at) dlr.dehttps://orcid.org/0009-0009-3660-9727170600987
Datum:24 April 2024
Erschienen in:15th European Conference on Synthetic Aperture Radar, EUSAR 2024
Referierte Publikation:Nein
Open Access:Nein
Gold Open Access:Nein
In SCOPUS:Ja
In ISI Web of Science:Nein
Seitenbereich:Seiten 447-452
Verlag:VDE
ISSN:2197-4403
ISBN:978-380076287-6
Status:veröffentlicht
Stichwörter:Oceanography, SAR, oil pollution, oil spill surveillance, deep learning, Gulf of Mexico
Veranstaltungstitel:EUSAR 2024
Veranstaltungsort:München, Germany
Veranstaltungsart:internationale Konferenz
Veranstaltungsbeginn:23 April 2024
Veranstaltungsende:26 April 2024
Veranstalter :VDE
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 - SAR-Methoden
Standort: Bremen , Oberpfaffenhofen
Institute & Einrichtungen:Institut für Methodik der Fernerkundung > SAR-Signalverarbeitung
Hinterlegt von: Kaps, Ruth
Hinterlegt am:02 Mai 2024 15:09
Letzte Änderung:18 Nov 2024 14:11

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.