Enhancing Very High-Resolution Satellite Images At 15 cm: A Novel Pipeline With Synthetic Data and Single Image Super Resolution

Jangir, Sandeep Kumar und Bahmanyar, Reza (2023) Enhancing Very High-Resolution Satellite Images At 15 cm: A Novel Pipeline With Synthetic Data and Single Image Super Resolution. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 2670 -2689. IEEE - Institute of Electrical and Electronics Engineers. doi: 10.1109/JSTARS.2023.3346181. ISSN 1939-1404.

PDF - Verlagsversion (veröffentlichte Fassung)
96MB

Offizielle URL: https://ieeexplore.ieee.org/document/10372096

Kurzfassung

Employing a two-step pipeline that encompasses an image-to-image translation and a superresolution (SR) network, we significantly enhance satellite images with a ground sample distance (GSD) of 30 cm to a superior 15 cm GSD. Our translation network learns from the characteristics of satellite images and replicates these onto aerial images with a GSD of 15 cm, creating a tailored training dataset. The SR network then uses this dataset to train and render enhanced satellite images at a GSD of 15 cm. This innovative approach can provide a cost-effective substitute for commercial high-definition images, and broadens the usage of high-quality data across various applications.

elib-URL des Eintrags:

https://elib.dlr.de/202089/

Dokumentart:

Zeitschriftenbeitrag

Titel:

Enhancing Very High-Resolution Satellite Images At 15 cm: A Novel Pipeline With Synthetic Data and Single Image Super Resolution

Autoren:

Autoren	Institution oder E-Mail-Adresse	Autoren-ORCID-iD	ORCID Put Code
Jangir, Sandeep Kumar	Sandeep.Jangir (at) dlr.de	https://orcid.org/0009-0009-0466-2144	150907706
Bahmanyar, Reza	reza.bahmanyar (at) dlr.de	https://orcid.org/0000-0002-6999-714X	150907707

Datum:

22 Dezember 2023

Erschienen in:

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

Referierte Publikation:

Open Access:

Gold Open Access:

In SCOPUS:

In ISI Web of Science:

Band:

DOI:

10.1109/JSTARS.2023.3346181

Seitenbereich:

2670 -2689

Verlag:

IEEE - Institute of Electrical and Electronics Engineers

ISSN:

1939-1404

Status:

veröffentlicht

Stichwörter:

15 cm ground sample distance (GSD), aerial and satellite image enhancement, image-to-image (I2I) translation, Super Resolution (SR)

HGF - Forschungsbereich:

Luftfahrt, Raumfahrt und Verkehr

HGF - Programm:

Verkehr

HGF - Programmthema:

Straßenverkehr

DLR - Schwerpunkt:

Verkehr

DLR - Forschungsgebiet:

V ST Straßenverkehr

DLR - Teilgebiet (Projekt, Vorhaben):

V - KoKoVI - Koordinierter kooperativer Verkehr mit verteilter, lernender Intelligenz

Standort:

Oberpfaffenhofen

Institute & Einrichtungen:

Institut für Methodik der Fernerkundung > Photogrammetrie und Bildanalyse

Hinterlegt von:

Jangir, Sandeep Kumar

Hinterlegt am:

17 Jan 2024 10:29

Letzte Änderung:

19 Jan 2024 07:15

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags