elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Hybrid GAN and Spectral Angular Distance for Cloud Removal

Ghozatlou, Omid and Datcu, Mihai (2021) Hybrid GAN and Spectral Angular Distance for Cloud Removal. In: International Geoscience and Remote Sensing Symposium (IGARSS), pp. 2695-2698. Institute of Electrical and Electronics Engineers. IGARSS 2021, 11-16 July 2021, Brussels, Belgium. doi: 10.1109/IGARSS47720.2021.9554891. ISBN 978-1-6654-0369-6. ISSN 2153-7003.

[img] PDF
3MB

Official URL: https://ieeexplore.ieee.org/document/9554891

Abstract

This paper aims to present a new algorithm to remove thin clouds and retain information in corrupted images without the use of auxiliary data. By injecting physical properties into the cycle consistent generative adversarial network (GAN), we were able to convert a cloudy multispectral image to a cloudless image. To recover information beneath clouds and shadows we create a synthetic multispectral space to obtain illumination invariant features. Multispectral vectors were transformed from Cartesian coordinates to Polar coordinates to obtain spectral angular distance (SAD) then we employed them as input to train the deep neural network (DNN). Afterward, the outputs of DNN were transformed to Cartesian coordinates to obtain shadow and cloud-free multispectral images. The proposed method, Hybrid GAN-SAD yields trustworthy reconstructed results because of exploiting transparent information from certain multispectral bands to recover uncorrupted images.

Item URL in elib:https://elib.dlr.de/144963/
Document Type:Conference or Workshop Item (Speech)
Title:Hybrid GAN and Spectral Angular Distance for Cloud Removal
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Ghozatlou, OmidUniversity POLITEHNICA of BucharestUNSPECIFIED
Datcu, MihaiMihai.Datcu (at) dlr.deUNSPECIFIED
Date:July 2021
Journal or Publication Title:International Geoscience and Remote Sensing Symposium (IGARSS)
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:No
DOI :10.1109/IGARSS47720.2021.9554891
Page Range:pp. 2695-2698
Publisher:Institute of Electrical and Electronics Engineers
ISSN:2153-7003
ISBN:978-1-6654-0369-6
Status:Published
Keywords:Cloud Removal, Generative Adversarial Networks (GANs), Polar Coordinates, Multispectral Satellite Images
Event Title:IGARSS 2021
Event Location:Brussels, Belgium
Event Type:international Conference
Event Dates:11-16 July 2021
Organizer:Institute of Electrical and Electronics Engineers
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Artificial Intelligence
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Deposited By: Otgonbaatar, Soronzonbold
Deposited On:18 Nov 2021 12:27
Last Modified:01 Jul 2022 03:00

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.