A Fusion Method of Optical Image and SAR Image Based on Dense-UGAN and Gram–Schmidt Transformation

To solve the problems such as obvious speckle noise and serious spectral distortion when existing fusion methods are applied to the fusion of optical and SAR images, this paper proposes a fusion method for optical and SAR images based on Dense-UGAN and Gram–Schmidt transformation. Firstly, dense con...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yingying Kong, Fang Hong, Henry Leung, Xiangyang Peng
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	image fusion generative adversarial network loss function Gram–Schmidt remote sensing image Science Q
Acceso en línea:	https://doaj.org/article/e9a6d445cddf4ff59587f1d9f5202c93
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e9a6d445cddf4ff59587f1d9f5202c93
record_format	dspace
spelling	oai:doaj.org-article:e9a6d445cddf4ff59587f1d9f5202c932021-11-11T18:52:32ZA Fusion Method of Optical Image and SAR Image Based on Dense-UGAN and Gram–Schmidt Transformation10.3390/rs132142742072-4292https://doaj.org/article/e9a6d445cddf4ff59587f1d9f5202c932021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4274https://doaj.org/toc/2072-4292To solve the problems such as obvious speckle noise and serious spectral distortion when existing fusion methods are applied to the fusion of optical and SAR images, this paper proposes a fusion method for optical and SAR images based on Dense-UGAN and Gram–Schmidt transformation. Firstly, dense connection with U-shaped network (Dense-UGAN) are used in GAN generator to deepen the network structure and obtain deeper source image information. Secondly, according to the particularity of SAR imaging mechanism, SGLCM loss for preserving SAR texture features and PSNR loss for reducing SAR speckle noise are introduced into the generator loss function. Meanwhile in order to keep more SAR image structure, SSIM loss is introduced to discriminator loss function to make the generated image retain more spatial features. In this way, the generated high-resolution image has both optical contour characteristics and SAR texture characteristics. Finally, the GS transformation of optical and generated image retains the necessary spectral properties. Experimental results show that the proposed method can well preserve the spectral information of optical images and texture information of SAR images, and also reduce the generation of speckle noise at the same time. The metrics are superior to other algorithms that currently perform well.Yingying KongFang HongHenry LeungXiangyang PengMDPI AGarticleimage fusiongenerative adversarial networkloss functionGram–Schmidtremote sensing imageScienceQENRemote Sensing, Vol 13, Iss 4274, p 4274 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	image fusion generative adversarial network loss function Gram–Schmidt remote sensing image Science Q
spellingShingle	image fusion generative adversarial network loss function Gram–Schmidt remote sensing image Science Q Yingying Kong Fang Hong Henry Leung Xiangyang Peng A Fusion Method of Optical Image and SAR Image Based on Dense-UGAN and Gram–Schmidt Transformation
description	To solve the problems such as obvious speckle noise and serious spectral distortion when existing fusion methods are applied to the fusion of optical and SAR images, this paper proposes a fusion method for optical and SAR images based on Dense-UGAN and Gram–Schmidt transformation. Firstly, dense connection with U-shaped network (Dense-UGAN) are used in GAN generator to deepen the network structure and obtain deeper source image information. Secondly, according to the particularity of SAR imaging mechanism, SGLCM loss for preserving SAR texture features and PSNR loss for reducing SAR speckle noise are introduced into the generator loss function. Meanwhile in order to keep more SAR image structure, SSIM loss is introduced to discriminator loss function to make the generated image retain more spatial features. In this way, the generated high-resolution image has both optical contour characteristics and SAR texture characteristics. Finally, the GS transformation of optical and generated image retains the necessary spectral properties. Experimental results show that the proposed method can well preserve the spectral information of optical images and texture information of SAR images, and also reduce the generation of speckle noise at the same time. The metrics are superior to other algorithms that currently perform well.
format	article
author	Yingying Kong Fang Hong Henry Leung Xiangyang Peng
author_facet	Yingying Kong Fang Hong Henry Leung Xiangyang Peng
author_sort	Yingying Kong
title	A Fusion Method of Optical Image and SAR Image Based on Dense-UGAN and Gram–Schmidt Transformation
title_short	A Fusion Method of Optical Image and SAR Image Based on Dense-UGAN and Gram–Schmidt Transformation
title_full	A Fusion Method of Optical Image and SAR Image Based on Dense-UGAN and Gram–Schmidt Transformation
title_fullStr	A Fusion Method of Optical Image and SAR Image Based on Dense-UGAN and Gram–Schmidt Transformation
title_full_unstemmed	A Fusion Method of Optical Image and SAR Image Based on Dense-UGAN and Gram–Schmidt Transformation
title_sort	fusion method of optical image and sar image based on dense-ugan and gram–schmidt transformation
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/e9a6d445cddf4ff59587f1d9f5202c93
work_keys_str_mv	AT yingyingkong afusionmethodofopticalimageandsarimagebasedondenseuganandgramschmidttransformation AT fanghong afusionmethodofopticalimageandsarimagebasedondenseuganandgramschmidttransformation AT henryleung afusionmethodofopticalimageandsarimagebasedondenseuganandgramschmidttransformation AT xiangyangpeng afusionmethodofopticalimageandsarimagebasedondenseuganandgramschmidttransformation AT yingyingkong fusionmethodofopticalimageandsarimagebasedondenseuganandgramschmidttransformation AT fanghong fusionmethodofopticalimageandsarimagebasedondenseuganandgramschmidttransformation AT henryleung fusionmethodofopticalimageandsarimagebasedondenseuganandgramschmidttransformation AT xiangyangpeng fusionmethodofopticalimageandsarimagebasedondenseuganandgramschmidttransformation
_version_	1718431737797672960

A Fusion Method of Optical Image and SAR Image Based on Dense-UGAN and Gram–Schmidt Transformation

Ejemplares similares