Synthetic aperture radar image change detection based on convolutional‐curvelet neural network and partial graph‐cut

Abstract Synthetic aperture radar (SAR) images are widely applied in change detection tasks because of SAR's active imaging mechanism. However, SAR images suffer from speckle noise due to SAR reception coherence from distributed targets. This property of SAR increases the uncertainty of the ima...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Meng Jia, Cheng Zhang, Zhiqiang Zhao, Lei Wang
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2021
Materias:	Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/26ea4a506efb4043a1926f8442b6fd55
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:26ea4a506efb4043a1926f8442b6fd55
record_format	dspace
spelling	oai:doaj.org-article:26ea4a506efb4043a1926f8442b6fd552021-11-05T05:26:52ZSynthetic aperture radar image change detection based on convolutional‐curvelet neural network and partial graph‐cut1350-911X0013-519410.1049/ell2.12290https://doaj.org/article/26ea4a506efb4043a1926f8442b6fd552021-11-01T00:00:00Zhttps://doi.org/10.1049/ell2.12290https://doaj.org/toc/0013-5194https://doaj.org/toc/1350-911XAbstract Synthetic aperture radar (SAR) images are widely applied in change detection tasks because of SAR's active imaging mechanism. However, SAR images suffer from speckle noise due to SAR reception coherence from distributed targets. This property of SAR increases the uncertainty of the image pixels, making it difficult to accurately detect the changed regions from the background. To address this issue, this letter proposes a novel SAR image change detection method based on a convolutional‐curvelet neural network (CurveCNet) and partial graph‐cut. The curvelet transform is introduced into the convolutional neural network to retain the structural information in the SAR images and to suppress the speckle noise. In addition, to combine the merits of various difference images, training samples are jointly constructed and fed into the neural network for it to learn the implicit common hierarchical features. Finally, the partial graph‐cut approach is proposed to refine the pixel labels in the fuzzy region and inhibit outliers on the background for the resultant change map. Visual and quantitative results obtained on two real SAR image datasets have demonstrated the effectiveness and robustness of the proposed method.Meng JiaCheng ZhangZhiqiang ZhaoLei WangWileyarticleElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENElectronics Letters, Vol 57, Iss 23, Pp 876-878 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Electrical engineering. Electronics. Nuclear engineering TK1-9971 Meng Jia Cheng Zhang Zhiqiang Zhao Lei Wang Synthetic aperture radar image change detection based on convolutional‐curvelet neural network and partial graph‐cut
description	Abstract Synthetic aperture radar (SAR) images are widely applied in change detection tasks because of SAR's active imaging mechanism. However, SAR images suffer from speckle noise due to SAR reception coherence from distributed targets. This property of SAR increases the uncertainty of the image pixels, making it difficult to accurately detect the changed regions from the background. To address this issue, this letter proposes a novel SAR image change detection method based on a convolutional‐curvelet neural network (CurveCNet) and partial graph‐cut. The curvelet transform is introduced into the convolutional neural network to retain the structural information in the SAR images and to suppress the speckle noise. In addition, to combine the merits of various difference images, training samples are jointly constructed and fed into the neural network for it to learn the implicit common hierarchical features. Finally, the partial graph‐cut approach is proposed to refine the pixel labels in the fuzzy region and inhibit outliers on the background for the resultant change map. Visual and quantitative results obtained on two real SAR image datasets have demonstrated the effectiveness and robustness of the proposed method.
format	article
author	Meng Jia Cheng Zhang Zhiqiang Zhao Lei Wang
author_facet	Meng Jia Cheng Zhang Zhiqiang Zhao Lei Wang
author_sort	Meng Jia
title	Synthetic aperture radar image change detection based on convolutional‐curvelet neural network and partial graph‐cut
title_short	Synthetic aperture radar image change detection based on convolutional‐curvelet neural network and partial graph‐cut
title_full	Synthetic aperture radar image change detection based on convolutional‐curvelet neural network and partial graph‐cut
title_fullStr	Synthetic aperture radar image change detection based on convolutional‐curvelet neural network and partial graph‐cut
title_full_unstemmed	Synthetic aperture radar image change detection based on convolutional‐curvelet neural network and partial graph‐cut
title_sort	synthetic aperture radar image change detection based on convolutional‐curvelet neural network and partial graph‐cut
publisher	Wiley
publishDate	2021
url	https://doaj.org/article/26ea4a506efb4043a1926f8442b6fd55
work_keys_str_mv	AT mengjia syntheticapertureradarimagechangedetectionbasedonconvolutionalcurveletneuralnetworkandpartialgraphcut AT chengzhang syntheticapertureradarimagechangedetectionbasedonconvolutionalcurveletneuralnetworkandpartialgraphcut AT zhiqiangzhao syntheticapertureradarimagechangedetectionbasedonconvolutionalcurveletneuralnetworkandpartialgraphcut AT leiwang syntheticapertureradarimagechangedetectionbasedonconvolutionalcurveletneuralnetworkandpartialgraphcut
_version_	1718444456099708928

Synthetic aperture radar image change detection based on convolutional‐curvelet neural network and partial graph‐cut

Ejemplares similares