Attention Enhanced U-Net for Building Extraction from Farmland Based on Google and WorldView-2 Remote Sensing Images

High-resolution remote sensing images contain abundant building information and provide an important data source for extracting buildings, which is of great significance to farmland preservation. However, the types of ground features in farmland are complex, the buildings are scattered and may be ob...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Chuangnong Li, Lin Fu, Qing Zhu, Jun Zhu, Zheng Fang, Yakun Xie, Yukun Guo, Yuhang Gong
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	building extraction farmland range attention enhancement U-Net network improvement multi-source remote sensing image Science Q
Acceso en línea:	https://doaj.org/article/0d9133170f2d4f958de925f6988ec018
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0d9133170f2d4f958de925f6988ec018
record_format	dspace
spelling	oai:doaj.org-article:0d9133170f2d4f958de925f6988ec0182021-11-11T18:55:49ZAttention Enhanced U-Net for Building Extraction from Farmland Based on Google and WorldView-2 Remote Sensing Images10.3390/rs132144112072-4292https://doaj.org/article/0d9133170f2d4f958de925f6988ec0182021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4411https://doaj.org/toc/2072-4292High-resolution remote sensing images contain abundant building information and provide an important data source for extracting buildings, which is of great significance to farmland preservation. However, the types of ground features in farmland are complex, the buildings are scattered and may be obscured by clouds or vegetation, leading to problems such as a low extraction accuracy in the existing methods. In response to the above problems, this paper proposes a method of attention-enhanced U-Net for building extraction from farmland, based on Google and WorldView-2 remote sensing images. First, a Resnet unit is adopted as the infrastructure of the U-Net network encoding part, then the spatial and channel attention mechanism module is introduced between the Resnet unit and the maximum pool and the multi-scale fusion module is added to improve the U-Net network. Second, the buildings found on WorldView-2 and Google images are extracted through farmland boundary constraints. Third, boundary optimization and fusion processing are carried out for the building extraction results on the WorldView-2 and Google images. Fourth, a case experiment is performed. The method in this paper is compared with semantic segmentation models, such as FCN8, U-Net, Attention_UNet, and DeepLabv3+. The experimental results indicate that this method attains a higher accuracy and better effect in terms of building extraction within farmland; the accuracy is 97.47%, the F1 score is 85.61%, the recall rate (Recall) is 93.02%, and the intersection of union (IoU) value is 74.85%. Hence, buildings within farming areas can be effectively extracted, which is conducive to the preservation of farmland.Chuangnong LiLin FuQing ZhuJun ZhuZheng FangYakun XieYukun GuoYuhang GongMDPI AGarticlebuilding extractionfarmland rangeattention enhancementU-Net network improvementmulti-source remote sensing imageScienceQENRemote Sensing, Vol 13, Iss 4411, p 4411 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	building extraction farmland range attention enhancement U-Net network improvement multi-source remote sensing image Science Q
spellingShingle	building extraction farmland range attention enhancement U-Net network improvement multi-source remote sensing image Science Q Chuangnong Li Lin Fu Qing Zhu Jun Zhu Zheng Fang Yakun Xie Yukun Guo Yuhang Gong Attention Enhanced U-Net for Building Extraction from Farmland Based on Google and WorldView-2 Remote Sensing Images
description	High-resolution remote sensing images contain abundant building information and provide an important data source for extracting buildings, which is of great significance to farmland preservation. However, the types of ground features in farmland are complex, the buildings are scattered and may be obscured by clouds or vegetation, leading to problems such as a low extraction accuracy in the existing methods. In response to the above problems, this paper proposes a method of attention-enhanced U-Net for building extraction from farmland, based on Google and WorldView-2 remote sensing images. First, a Resnet unit is adopted as the infrastructure of the U-Net network encoding part, then the spatial and channel attention mechanism module is introduced between the Resnet unit and the maximum pool and the multi-scale fusion module is added to improve the U-Net network. Second, the buildings found on WorldView-2 and Google images are extracted through farmland boundary constraints. Third, boundary optimization and fusion processing are carried out for the building extraction results on the WorldView-2 and Google images. Fourth, a case experiment is performed. The method in this paper is compared with semantic segmentation models, such as FCN8, U-Net, Attention_UNet, and DeepLabv3+. The experimental results indicate that this method attains a higher accuracy and better effect in terms of building extraction within farmland; the accuracy is 97.47%, the F1 score is 85.61%, the recall rate (Recall) is 93.02%, and the intersection of union (IoU) value is 74.85%. Hence, buildings within farming areas can be effectively extracted, which is conducive to the preservation of farmland.
format	article
author	Chuangnong Li Lin Fu Qing Zhu Jun Zhu Zheng Fang Yakun Xie Yukun Guo Yuhang Gong
author_facet	Chuangnong Li Lin Fu Qing Zhu Jun Zhu Zheng Fang Yakun Xie Yukun Guo Yuhang Gong
author_sort	Chuangnong Li
title	Attention Enhanced U-Net for Building Extraction from Farmland Based on Google and WorldView-2 Remote Sensing Images
title_short	Attention Enhanced U-Net for Building Extraction from Farmland Based on Google and WorldView-2 Remote Sensing Images
title_full	Attention Enhanced U-Net for Building Extraction from Farmland Based on Google and WorldView-2 Remote Sensing Images
title_fullStr	Attention Enhanced U-Net for Building Extraction from Farmland Based on Google and WorldView-2 Remote Sensing Images
title_full_unstemmed	Attention Enhanced U-Net for Building Extraction from Farmland Based on Google and WorldView-2 Remote Sensing Images
title_sort	attention enhanced u-net for building extraction from farmland based on google and worldview-2 remote sensing images
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/0d9133170f2d4f958de925f6988ec018
work_keys_str_mv	AT chuangnongli attentionenhancedunetforbuildingextractionfromfarmlandbasedongoogleandworldview2remotesensingimages AT linfu attentionenhancedunetforbuildingextractionfromfarmlandbasedongoogleandworldview2remotesensingimages AT qingzhu attentionenhancedunetforbuildingextractionfromfarmlandbasedongoogleandworldview2remotesensingimages AT junzhu attentionenhancedunetforbuildingextractionfromfarmlandbasedongoogleandworldview2remotesensingimages AT zhengfang attentionenhancedunetforbuildingextractionfromfarmlandbasedongoogleandworldview2remotesensingimages AT yakunxie attentionenhancedunetforbuildingextractionfromfarmlandbasedongoogleandworldview2remotesensingimages AT yukunguo attentionenhancedunetforbuildingextractionfromfarmlandbasedongoogleandworldview2remotesensingimages AT yuhanggong attentionenhancedunetforbuildingextractionfromfarmlandbasedongoogleandworldview2remotesensingimages
_version_	1718431627156127744

Attention Enhanced U-Net for Building Extraction from Farmland Based on Google and WorldView-2 Remote Sensing Images

Ejemplares similares