Cross-Domain Association Mining Based Generative Adversarial Network for Pansharpening
Multispectral (MS) pansharpening can improve the spatial resolution of MS images, which plays an increasingly important role in agriculture and environmental monitoring. Existing neural network-based methods tend to focus on global features of images, without considering the inherent relationships b...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9880485/ |
_version_ | 1798035795216433152 |
---|---|
author | Lijun He Wanyue Zhang Jiankang Shi Fan Li |
author_facet | Lijun He Wanyue Zhang Jiankang Shi Fan Li |
author_sort | Lijun He |
collection | DOAJ |
description | Multispectral (MS) pansharpening can improve the spatial resolution of MS images, which plays an increasingly important role in agriculture and environmental monitoring. Existing neural network-based methods tend to focus on global features of images, without considering the inherent relationships between similar substances in MS images. However, there is a high probability that different substances at the junction mix with each other, which leads to spectral distortion in the final pansharpened image. In this article, we propose a cross-domain association mining-based generative adversarial network for pansharpening, which consists of a spectral fidelity generator and dual discriminators. In our spectral fidelity generator, the cross-region similarity attention module is designed to establish dependencies between similar substances at different positions in the image, thereby leveraging the similar spectral features to generate pansharpened images with better spectral preservation. To mine the potential relationship between the MS image domain and the panchromatic image domain, we pretrain a spatial information extraction network. The network is then transferred to the dual-discriminator architecture to obtain the spatial information of the pansharpened images more accurately and prevent the loss of spatial details. The experimental results show that our method outperforms several state-of-the-art pansharpening methods in both quantitative and qualitative evaluations. |
first_indexed | 2024-04-11T21:03:13Z |
format | Article |
id | doaj.art-aefed4e03af04a0bb879d0e5a846e182 |
institution | Directory Open Access Journal |
issn | 2151-1535 |
language | English |
last_indexed | 2024-04-11T21:03:13Z |
publishDate | 2022-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
spelling | doaj.art-aefed4e03af04a0bb879d0e5a846e1822022-12-22T04:03:25ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01157770778310.1109/JSTARS.2022.32048249880485Cross-Domain Association Mining Based Generative Adversarial Network for PansharpeningLijun He0https://orcid.org/0000-0002-3911-8263Wanyue Zhang1Jiankang Shi2Fan Li3https://orcid.org/0000-0002-7566-1634Shaanxi Key Laboratory of Deep Space Exploration Intelligent Information Technology, School of Information and Communications Engineering, Xi'an Jiaotong University, Xi'an, ChinaShaanxi Key Laboratory of Deep Space Exploration Intelligent Information Technology, School of Information and Communications Engineering, Xi'an Jiaotong University, Xi'an, ChinaSchool of Automation Science and Engineering, Xi'an Jiaotong University, Xi'an, ChinaShaanxi Key Laboratory of Deep Space Exploration Intelligent Information Technology, School of Information and Communications Engineering, Xi'an Jiaotong University, Xi'an, ChinaMultispectral (MS) pansharpening can improve the spatial resolution of MS images, which plays an increasingly important role in agriculture and environmental monitoring. Existing neural network-based methods tend to focus on global features of images, without considering the inherent relationships between similar substances in MS images. However, there is a high probability that different substances at the junction mix with each other, which leads to spectral distortion in the final pansharpened image. In this article, we propose a cross-domain association mining-based generative adversarial network for pansharpening, which consists of a spectral fidelity generator and dual discriminators. In our spectral fidelity generator, the cross-region similarity attention module is designed to establish dependencies between similar substances at different positions in the image, thereby leveraging the similar spectral features to generate pansharpened images with better spectral preservation. To mine the potential relationship between the MS image domain and the panchromatic image domain, we pretrain a spatial information extraction network. The network is then transferred to the dual-discriminator architecture to obtain the spatial information of the pansharpened images more accurately and prevent the loss of spatial details. The experimental results show that our method outperforms several state-of-the-art pansharpening methods in both quantitative and qualitative evaluations.https://ieeexplore.ieee.org/document/9880485/Deep learningdual discriminatorsimage associationmultispectral (MS) pansharpening |
spellingShingle | Lijun He Wanyue Zhang Jiankang Shi Fan Li Cross-Domain Association Mining Based Generative Adversarial Network for Pansharpening IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Deep learning dual discriminators image association multispectral (MS) pansharpening |
title | Cross-Domain Association Mining Based Generative Adversarial Network for Pansharpening |
title_full | Cross-Domain Association Mining Based Generative Adversarial Network for Pansharpening |
title_fullStr | Cross-Domain Association Mining Based Generative Adversarial Network for Pansharpening |
title_full_unstemmed | Cross-Domain Association Mining Based Generative Adversarial Network for Pansharpening |
title_short | Cross-Domain Association Mining Based Generative Adversarial Network for Pansharpening |
title_sort | cross domain association mining based generative adversarial network for pansharpening |
topic | Deep learning dual discriminators image association multispectral (MS) pansharpening |
url | https://ieeexplore.ieee.org/document/9880485/ |
work_keys_str_mv | AT lijunhe crossdomainassociationminingbasedgenerativeadversarialnetworkforpansharpening AT wanyuezhang crossdomainassociationminingbasedgenerativeadversarialnetworkforpansharpening AT jiankangshi crossdomainassociationminingbasedgenerativeadversarialnetworkforpansharpening AT fanli crossdomainassociationminingbasedgenerativeadversarialnetworkforpansharpening |