Generative adversarial networks with texture recovery and physical constraints for remote sensing image dehazing

Abstract The scattering of tiny particles in the atmosphere causes a haze effect on remote sensing images captured by satellites and similar devices, significantly disrupting subsequent image recognition and classification. A generative adversarial network named TRPC-GAN with texture recovery and ph...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanfei Jia, Wenshuo Yu, Liquan Zhao
Format: Article
Language:English
Published: Nature Portfolio 2024-12-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-83088-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850035246941077504
author Yanfei Jia
Wenshuo Yu
Liquan Zhao
author_facet Yanfei Jia
Wenshuo Yu
Liquan Zhao
author_sort Yanfei Jia
collection DOAJ
description Abstract The scattering of tiny particles in the atmosphere causes a haze effect on remote sensing images captured by satellites and similar devices, significantly disrupting subsequent image recognition and classification. A generative adversarial network named TRPC-GAN with texture recovery and physical constraints is proposed to mitigate this impact. This network not only effectively removes haze but also better preserves the texture information of the original remote sensing image, thereby enhancing the visual quality of the dehazed image. A multi-scale module is proposed to extract feature information of remote sensing images, allowing it to capture image features from different receptive fields. Simultaneously, an attention module is designed further to guide the network’s focus towards important feature information. In addition, a multi-scale adversarial network is proposed to better restore both global and local information about the original image. Introducing a physical constraint loss function to improve the loss function of the original generative adversarial network allows for better preservation of the physical characteristics of remote sensing images. Simulation experiments on synthetic and natural hazy remote sensing image datasets are conducted. The results demonstrate that the dehazing performance of the TRPC-GAN method surpasses the other four methods.
format Article
id doaj-art-c25d01659ead41debc45a9eb465df0e0
institution DOAJ
issn 2045-2322
language English
publishDate 2024-12-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-c25d01659ead41debc45a9eb465df0e02025-08-20T02:57:32ZengNature PortfolioScientific Reports2045-23222024-12-0114111610.1038/s41598-024-83088-xGenerative adversarial networks with texture recovery and physical constraints for remote sensing image dehazingYanfei Jia0Wenshuo Yu1Liquan Zhao2College of Electrical and Electronic Information Engineering, Beihua UniversityDepartment of Instrument Science and Electrical Engineering, Jilin UniversityCollege of Electrical Engineering, Northeast Electric Power UniversityAbstract The scattering of tiny particles in the atmosphere causes a haze effect on remote sensing images captured by satellites and similar devices, significantly disrupting subsequent image recognition and classification. A generative adversarial network named TRPC-GAN with texture recovery and physical constraints is proposed to mitigate this impact. This network not only effectively removes haze but also better preserves the texture information of the original remote sensing image, thereby enhancing the visual quality of the dehazed image. A multi-scale module is proposed to extract feature information of remote sensing images, allowing it to capture image features from different receptive fields. Simultaneously, an attention module is designed further to guide the network’s focus towards important feature information. In addition, a multi-scale adversarial network is proposed to better restore both global and local information about the original image. Introducing a physical constraint loss function to improve the loss function of the original generative adversarial network allows for better preservation of the physical characteristics of remote sensing images. Simulation experiments on synthetic and natural hazy remote sensing image datasets are conducted. The results demonstrate that the dehazing performance of the TRPC-GAN method surpasses the other four methods.https://doi.org/10.1038/s41598-024-83088-xRemote sensingDeep learningGenerative adversarial networksTexture recovery and physical constraints
spellingShingle Yanfei Jia
Wenshuo Yu
Liquan Zhao
Generative adversarial networks with texture recovery and physical constraints for remote sensing image dehazing
Scientific Reports
Remote sensing
Deep learning
Generative adversarial networks
Texture recovery and physical constraints
title Generative adversarial networks with texture recovery and physical constraints for remote sensing image dehazing
title_full Generative adversarial networks with texture recovery and physical constraints for remote sensing image dehazing
title_fullStr Generative adversarial networks with texture recovery and physical constraints for remote sensing image dehazing
title_full_unstemmed Generative adversarial networks with texture recovery and physical constraints for remote sensing image dehazing
title_short Generative adversarial networks with texture recovery and physical constraints for remote sensing image dehazing
title_sort generative adversarial networks with texture recovery and physical constraints for remote sensing image dehazing
topic Remote sensing
Deep learning
Generative adversarial networks
Texture recovery and physical constraints
url https://doi.org/10.1038/s41598-024-83088-x
work_keys_str_mv AT yanfeijia generativeadversarialnetworkswithtexturerecoveryandphysicalconstraintsforremotesensingimagedehazing
AT wenshuoyu generativeadversarialnetworkswithtexturerecoveryandphysicalconstraintsforremotesensingimagedehazing
AT liquanzhao generativeadversarialnetworkswithtexturerecoveryandphysicalconstraintsforremotesensingimagedehazing