Attention Mechanism Cloud Detection With Modified FCN for Infrared Remote Sensing Images

Semantic segmentation (SS) has been widely applied for cloud detection (CD) in remote sensing images (RSIs) with high spatial and spectral resolution because of its effective pixel-level feature extraction structure. However, the typical model of lightweight SS, namely the fully convolutional networ...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Liyuan Li, Xiaoyan Li, Xin Liu, Wenwen Huang, Zhuoyue Hu, Fansheng Chen
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Cloud detection (CD) semantic segmentation (SS) fully convolutional network (FCN) attention mechanism (AM) remote sensing images (RSIs) Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/0e1e33c8355a4f999ab74fd40b07426c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0e1e33c8355a4f999ab74fd40b07426c
record_format	dspace
spelling	oai:doaj.org-article:0e1e33c8355a4f999ab74fd40b07426c2021-11-18T00:09:15ZAttention Mechanism Cloud Detection With Modified FCN for Infrared Remote Sensing Images2169-353610.1109/ACCESS.2021.3122162https://doaj.org/article/0e1e33c8355a4f999ab74fd40b07426c2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9584884/https://doaj.org/toc/2169-3536Semantic segmentation (SS) has been widely applied for cloud detection (CD) in remote sensing images (RSIs) with high spatial and spectral resolution because of its effective pixel-level feature extraction structure. However, the typical model of lightweight SS, namely the fully convolutional network (FCN) with only seven layers, has difficulty in extracting high-level features, and the heavy pyramid scene parsing network (PSPNet) with complicated calculations is not practical in real-time CD, let alone on-orbit CD. So, in view of the problems above, we propose a compact attention mechanism cloud detection network (AM-CDN) based on the modified FCN to refine and fuse the multi-scale features for on-orbit CD. Specifically, taking the FCN as the baseline, our model increases the numbers of hidden layers and adds the residual connections between the input and output to eliminate the network degradation and extract the advanced context feature maps effectively. To expand the receptive field without losing the spatial information, the ordinary convolutions in FCN are replaced by the dilated convolution in AM-CDN. And inspired by the selective kernels of human vision, we introduce the convolutional attention mechanism (AM) into the encoder to adaptively adjust the receptive field to highlight the key texture features. According to experimental results using Landsat-8 infrared RSIs, the accuracy of the proposed CD method is 95.31%, which is 10.17% higher than that of FCN. And the calculation complexity of AM-CDN is only 7.63% of that of PSPNet.Liyuan LiXiaoyan LiXin LiuWenwen HuangZhuoyue HuFansheng ChenIEEEarticleCloud detection (CD)semantic segmentation (SS)fully convolutional network (FCN)attention mechanism (AM)remote sensing images (RSIs)Electrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 150975-150983 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Cloud detection (CD) semantic segmentation (SS) fully convolutional network (FCN) attention mechanism (AM) remote sensing images (RSIs) Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Cloud detection (CD) semantic segmentation (SS) fully convolutional network (FCN) attention mechanism (AM) remote sensing images (RSIs) Electrical engineering. Electronics. Nuclear engineering TK1-9971 Liyuan Li Xiaoyan Li Xin Liu Wenwen Huang Zhuoyue Hu Fansheng Chen Attention Mechanism Cloud Detection With Modified FCN for Infrared Remote Sensing Images
description	Semantic segmentation (SS) has been widely applied for cloud detection (CD) in remote sensing images (RSIs) with high spatial and spectral resolution because of its effective pixel-level feature extraction structure. However, the typical model of lightweight SS, namely the fully convolutional network (FCN) with only seven layers, has difficulty in extracting high-level features, and the heavy pyramid scene parsing network (PSPNet) with complicated calculations is not practical in real-time CD, let alone on-orbit CD. So, in view of the problems above, we propose a compact attention mechanism cloud detection network (AM-CDN) based on the modified FCN to refine and fuse the multi-scale features for on-orbit CD. Specifically, taking the FCN as the baseline, our model increases the numbers of hidden layers and adds the residual connections between the input and output to eliminate the network degradation and extract the advanced context feature maps effectively. To expand the receptive field without losing the spatial information, the ordinary convolutions in FCN are replaced by the dilated convolution in AM-CDN. And inspired by the selective kernels of human vision, we introduce the convolutional attention mechanism (AM) into the encoder to adaptively adjust the receptive field to highlight the key texture features. According to experimental results using Landsat-8 infrared RSIs, the accuracy of the proposed CD method is 95.31%, which is 10.17% higher than that of FCN. And the calculation complexity of AM-CDN is only 7.63% of that of PSPNet.
format	article
author	Liyuan Li Xiaoyan Li Xin Liu Wenwen Huang Zhuoyue Hu Fansheng Chen
author_facet	Liyuan Li Xiaoyan Li Xin Liu Wenwen Huang Zhuoyue Hu Fansheng Chen
author_sort	Liyuan Li
title	Attention Mechanism Cloud Detection With Modified FCN for Infrared Remote Sensing Images
title_short	Attention Mechanism Cloud Detection With Modified FCN for Infrared Remote Sensing Images
title_full	Attention Mechanism Cloud Detection With Modified FCN for Infrared Remote Sensing Images
title_fullStr	Attention Mechanism Cloud Detection With Modified FCN for Infrared Remote Sensing Images
title_full_unstemmed	Attention Mechanism Cloud Detection With Modified FCN for Infrared Remote Sensing Images
title_sort	attention mechanism cloud detection with modified fcn for infrared remote sensing images
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/0e1e33c8355a4f999ab74fd40b07426c
work_keys_str_mv	AT liyuanli attentionmechanismclouddetectionwithmodifiedfcnforinfraredremotesensingimages AT xiaoyanli attentionmechanismclouddetectionwithmodifiedfcnforinfraredremotesensingimages AT xinliu attentionmechanismclouddetectionwithmodifiedfcnforinfraredremotesensingimages AT wenwenhuang attentionmechanismclouddetectionwithmodifiedfcnforinfraredremotesensingimages AT zhuoyuehu attentionmechanismclouddetectionwithmodifiedfcnforinfraredremotesensingimages AT fanshengchen attentionmechanismclouddetectionwithmodifiedfcnforinfraredremotesensingimages
_version_	1718425206283829248

Attention Mechanism Cloud Detection With Modified FCN for Infrared Remote Sensing Images

Ejemplares similares