Band Reconstruction Using a Modified UNet for Sentinel-2 Images
Multispectral (MS) remote sensing images are of great interest for various applications, yet, quite often, an MS product exhibits one or more noisy bands, strip lines, or even missing bands, which leads to decreased confidence in the information it contains. Meeting this challenge, this article prop...
Published in: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
IEEE - Institute of Electrical and Electronics Engineers
2023
|
Subjects: | |
Online Access: | https://elib.dlr.de/201625/ https://elib.dlr.de/201625/1/Band_Reconstruction_Using_a_Modified_UNet_for_Sentinel-2_Images.pdf https://ieeexplore.ieee.org/document/10128669/authors#authors |
id |
ftdlr:oai:elib.dlr.de:201625 |
---|---|
record_format |
openpolar |
spelling |
ftdlr:oai:elib.dlr.de:201625 2024-02-11T10:06:56+01:00 Band Reconstruction Using a Modified UNet for Sentinel-2 Images Neagoe, Iulia Faur, D. Vaduva, C. Datcu, Mihai 2023-05 application/pdf https://elib.dlr.de/201625/ https://elib.dlr.de/201625/1/Band_Reconstruction_Using_a_Modified_UNet_for_Sentinel-2_Images.pdf https://ieeexplore.ieee.org/document/10128669/authors#authors en eng IEEE - Institute of Electrical and Electronics Engineers https://elib.dlr.de/201625/1/Band_Reconstruction_Using_a_Modified_UNet_for_Sentinel-2_Images.pdf Neagoe, Iulia und Faur, D. und Vaduva, C. und Datcu, Mihai (2023) Band Reconstruction Using a Modified UNet for Sentinel-2 Images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16, Seiten 6739-6757. IEEE - Institute of Electrical and Electronics Engineers. doi:10.1109/JSTARS.2023.3276912 <https://doi.org/10.1109/JSTARS.2023.3276912>. ISSN 1939-1404. cc_by EO Data Science Zeitschriftenbeitrag PeerReviewed 2023 ftdlr https://doi.org/10.1109/JSTARS.2023.3276912 2024-01-22T00:24:13Z Multispectral (MS) remote sensing images are of great interest for various applications, yet, quite often, an MS product exhibits one or more noisy bands, strip lines, or even missing bands, which leads to decreased confidence in the information it contains. Meeting this challenge, this article proposes a UNet-based neural network architecture to reconstruct a spectral band. The worst case scenario is considered, that of a missing band, the reconstruction being performed based on the available bands. Besides the comparison with state-of-the-art methods, both the qualitative and quantitative analyses are fulfilled considering several metrics: root-mean-square error, structural similarity index, signal-to-reconstruction error, peak-signal-to-noise ratio, and spectral angle mapper. The experiments focus on Sentinel-2 open data within the Copernicus program. Various patterns of urban areas, agricultural regions, and regions from North Pole or Kyiv, Ukraine are included in our dataset to prove the efficiency of band reconstruction regardless of land-cover diversity. Article in Journal/Newspaper North Pole German Aerospace Center: elib - DLR electronic library North Pole IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 16 6739 6757 |
institution |
Open Polar |
collection |
German Aerospace Center: elib - DLR electronic library |
op_collection_id |
ftdlr |
language |
English |
topic |
EO Data Science |
spellingShingle |
EO Data Science Neagoe, Iulia Faur, D. Vaduva, C. Datcu, Mihai Band Reconstruction Using a Modified UNet for Sentinel-2 Images |
topic_facet |
EO Data Science |
description |
Multispectral (MS) remote sensing images are of great interest for various applications, yet, quite often, an MS product exhibits one or more noisy bands, strip lines, or even missing bands, which leads to decreased confidence in the information it contains. Meeting this challenge, this article proposes a UNet-based neural network architecture to reconstruct a spectral band. The worst case scenario is considered, that of a missing band, the reconstruction being performed based on the available bands. Besides the comparison with state-of-the-art methods, both the qualitative and quantitative analyses are fulfilled considering several metrics: root-mean-square error, structural similarity index, signal-to-reconstruction error, peak-signal-to-noise ratio, and spectral angle mapper. The experiments focus on Sentinel-2 open data within the Copernicus program. Various patterns of urban areas, agricultural regions, and regions from North Pole or Kyiv, Ukraine are included in our dataset to prove the efficiency of band reconstruction regardless of land-cover diversity. |
format |
Article in Journal/Newspaper |
author |
Neagoe, Iulia Faur, D. Vaduva, C. Datcu, Mihai |
author_facet |
Neagoe, Iulia Faur, D. Vaduva, C. Datcu, Mihai |
author_sort |
Neagoe, Iulia |
title |
Band Reconstruction Using a Modified UNet for Sentinel-2 Images |
title_short |
Band Reconstruction Using a Modified UNet for Sentinel-2 Images |
title_full |
Band Reconstruction Using a Modified UNet for Sentinel-2 Images |
title_fullStr |
Band Reconstruction Using a Modified UNet for Sentinel-2 Images |
title_full_unstemmed |
Band Reconstruction Using a Modified UNet for Sentinel-2 Images |
title_sort |
band reconstruction using a modified unet for sentinel-2 images |
publisher |
IEEE - Institute of Electrical and Electronics Engineers |
publishDate |
2023 |
url |
https://elib.dlr.de/201625/ https://elib.dlr.de/201625/1/Band_Reconstruction_Using_a_Modified_UNet_for_Sentinel-2_Images.pdf https://ieeexplore.ieee.org/document/10128669/authors#authors |
geographic |
North Pole |
geographic_facet |
North Pole |
genre |
North Pole |
genre_facet |
North Pole |
op_relation |
https://elib.dlr.de/201625/1/Band_Reconstruction_Using_a_Modified_UNet_for_Sentinel-2_Images.pdf Neagoe, Iulia und Faur, D. und Vaduva, C. und Datcu, Mihai (2023) Band Reconstruction Using a Modified UNet for Sentinel-2 Images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16, Seiten 6739-6757. IEEE - Institute of Electrical and Electronics Engineers. doi:10.1109/JSTARS.2023.3276912 <https://doi.org/10.1109/JSTARS.2023.3276912>. ISSN 1939-1404. |
op_rights |
cc_by |
op_doi |
https://doi.org/10.1109/JSTARS.2023.3276912 |
container_title |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
container_volume |
16 |
container_start_page |
6739 |
op_container_end_page |
6757 |
_version_ |
1790604977204363264 |