MRA-SNet: Siamese Networks of Multiscale Residual and Attention for Change Detection in High-Resolution Remote Sensing Images

Remote sensing image change detection (CD) is an important task in remote sensing image analysis and is essential for an accurate understanding of changes in the Earth’s surface. The technology of deep learning (DL) is becoming increasingly popular in solving CD tasks for remote sensing images. Most...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xin Yang, Lei Hu, Yongmei Zhang, Yunqing Li
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	high-resolution remote sensing images change detection Multi-Res block Attention Gates Siamese network Science Q
Acceso en línea:	https://doaj.org/article/57d2cbf6db004119b53979631059922b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:57d2cbf6db004119b53979631059922b
record_format	dspace
spelling	oai:doaj.org-article:57d2cbf6db004119b53979631059922b2021-11-25T18:53:58ZMRA-SNet: Siamese Networks of Multiscale Residual and Attention for Change Detection in High-Resolution Remote Sensing Images10.3390/rs132245282072-4292https://doaj.org/article/57d2cbf6db004119b53979631059922b2021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4528https://doaj.org/toc/2072-4292Remote sensing image change detection (CD) is an important task in remote sensing image analysis and is essential for an accurate understanding of changes in the Earth’s surface. The technology of deep learning (DL) is becoming increasingly popular in solving CD tasks for remote sensing images. Most existing CD methods based on DL tend to use ordinary convolutional blocks to extract and compare remote sensing image features, which cannot fully extract the rich features of high-resolution (HR) remote sensing images. In addition, most of the existing methods lack robustness to pseudochange information processing. To overcome the above problems, in this article, we propose a new method, namely MRA-SNet, for CD in remote sensing images. Utilizing the UNet network as the basic network, the method uses the Siamese network to extract the features of bitemporal images in the encoder separately and perform the difference connection to better generate difference maps. Meanwhile, we replace the ordinary convolution blocks with Multi-Res blocks to extract spatial and spectral features of different scales in remote sensing images. Residual connections are used to extract additional detailed features. To better highlight the change region features and suppress the irrelevant region features, we introduced the Attention Gates module before the skip connection between the encoder and the decoder. Experimental results on a public dataset of remote sensing image CD show that our proposed method outperforms other state-of-the-art (SOTA) CD methods in terms of evaluation metrics and performance.Xin YangLei HuYongmei ZhangYunqing LiMDPI AGarticlehigh-resolution remote sensing imageschange detectionMulti-Res blockAttention GatesSiamese networkScienceQENRemote Sensing, Vol 13, Iss 4528, p 4528 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	high-resolution remote sensing images change detection Multi-Res block Attention Gates Siamese network Science Q
spellingShingle	high-resolution remote sensing images change detection Multi-Res block Attention Gates Siamese network Science Q Xin Yang Lei Hu Yongmei Zhang Yunqing Li MRA-SNet: Siamese Networks of Multiscale Residual and Attention for Change Detection in High-Resolution Remote Sensing Images
description	Remote sensing image change detection (CD) is an important task in remote sensing image analysis and is essential for an accurate understanding of changes in the Earth’s surface. The technology of deep learning (DL) is becoming increasingly popular in solving CD tasks for remote sensing images. Most existing CD methods based on DL tend to use ordinary convolutional blocks to extract and compare remote sensing image features, which cannot fully extract the rich features of high-resolution (HR) remote sensing images. In addition, most of the existing methods lack robustness to pseudochange information processing. To overcome the above problems, in this article, we propose a new method, namely MRA-SNet, for CD in remote sensing images. Utilizing the UNet network as the basic network, the method uses the Siamese network to extract the features of bitemporal images in the encoder separately and perform the difference connection to better generate difference maps. Meanwhile, we replace the ordinary convolution blocks with Multi-Res blocks to extract spatial and spectral features of different scales in remote sensing images. Residual connections are used to extract additional detailed features. To better highlight the change region features and suppress the irrelevant region features, we introduced the Attention Gates module before the skip connection between the encoder and the decoder. Experimental results on a public dataset of remote sensing image CD show that our proposed method outperforms other state-of-the-art (SOTA) CD methods in terms of evaluation metrics and performance.
format	article
author	Xin Yang Lei Hu Yongmei Zhang Yunqing Li
author_facet	Xin Yang Lei Hu Yongmei Zhang Yunqing Li
author_sort	Xin Yang
title	MRA-SNet: Siamese Networks of Multiscale Residual and Attention for Change Detection in High-Resolution Remote Sensing Images
title_short	MRA-SNet: Siamese Networks of Multiscale Residual and Attention for Change Detection in High-Resolution Remote Sensing Images
title_full	MRA-SNet: Siamese Networks of Multiscale Residual and Attention for Change Detection in High-Resolution Remote Sensing Images
title_fullStr	MRA-SNet: Siamese Networks of Multiscale Residual and Attention for Change Detection in High-Resolution Remote Sensing Images
title_full_unstemmed	MRA-SNet: Siamese Networks of Multiscale Residual and Attention for Change Detection in High-Resolution Remote Sensing Images
title_sort	mra-snet: siamese networks of multiscale residual and attention for change detection in high-resolution remote sensing images
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/57d2cbf6db004119b53979631059922b
work_keys_str_mv	AT xinyang mrasnetsiamesenetworksofmultiscaleresidualandattentionforchangedetectioninhighresolutionremotesensingimages AT leihu mrasnetsiamesenetworksofmultiscaleresidualandattentionforchangedetectioninhighresolutionremotesensingimages AT yongmeizhang mrasnetsiamesenetworksofmultiscaleresidualandattentionforchangedetectioninhighresolutionremotesensingimages AT yunqingli mrasnetsiamesenetworksofmultiscaleresidualandattentionforchangedetectioninhighresolutionremotesensingimages
_version_	1718410587696791552

MRA-SNet: Siamese Networks of Multiscale Residual and Attention for Change Detection in High-Resolution Remote Sensing Images

Ejemplares similares