Developing a Method to Extract Building 3D Information from GF-7 Data

The three-dimensional (3D) information of buildings can describe the horizontal and vertical development of a city. The GaoFen-7 (GF-7) stereo-mapping satellite can provide multi-view and multi-spectral satellite images, which can clearly describe the fine spatial details within urban areas, while t...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jingyuan Wang, Xinli Hu, Qingyan Meng, Linlin Zhang, Chengyi Wang, Xiangchen Liu, Maofan Zhao
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	GF-7 image building footprint building height multi-view deep learning point cloud Science Q
Acceso en línea:	https://doaj.org/article/ff15bf8f5b5b4974a7c81ff6f083b7d5
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ff15bf8f5b5b4974a7c81ff6f083b7d5
record_format	dspace
spelling	oai:doaj.org-article:ff15bf8f5b5b4974a7c81ff6f083b7d52021-11-25T18:54:03ZDeveloping a Method to Extract Building 3D Information from GF-7 Data10.3390/rs132245322072-4292https://doaj.org/article/ff15bf8f5b5b4974a7c81ff6f083b7d52021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4532https://doaj.org/toc/2072-4292The three-dimensional (3D) information of buildings can describe the horizontal and vertical development of a city. The GaoFen-7 (GF-7) stereo-mapping satellite can provide multi-view and multi-spectral satellite images, which can clearly describe the fine spatial details within urban areas, while the feasibility of extracting building 3D information from GF-7 image remains understudied. This article establishes an automated method for extracting building footprints and height information from GF-7 satellite imagery. First, we propose a multi-stage attention U-Net (MSAU-Net) architecture for building footprint extraction from multi-spectral images. Then, we generate the point cloud from the multi-view image and construct normalized digital surface model (nDSM) to represent the height of off-terrain objects. Finally, the building height is extracted from the nDSM and combined with the results of building footprints to obtain building 3D information. We select Beijing as the study area to test the proposed method, and in order to verify the building extraction ability of MSAU-Net, we choose GF-7 self-annotated building dataset and a public dataset (WuHan University (WHU) Building Dataset) for model testing, while the accuracy is evaluated in detail through comparison with other models. The results are summarized as follows: (1) In terms of building footprint extraction, our method can achieve intersection-over-union indicators of 89.31% and 80.27% for the WHU Dataset and GF-7 self-annotated datasets, respectively; these values are higher than the results of other models. (2) The root mean square between the extracted building height and the reference building height is 5.41 m, and the mean absolute error is 3.39 m. In summary, our method could be useful for accurate and automatic 3D building information extraction from GF-7 satellite images, and have good application potential.Jingyuan WangXinli HuQingyan MengLinlin ZhangChengyi WangXiangchen LiuMaofan ZhaoMDPI AGarticleGF-7 imagebuilding footprintbuilding heightmulti-viewdeep learningpoint cloudScienceQENRemote Sensing, Vol 13, Iss 4532, p 4532 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	GF-7 image building footprint building height multi-view deep learning point cloud Science Q
spellingShingle	GF-7 image building footprint building height multi-view deep learning point cloud Science Q Jingyuan Wang Xinli Hu Qingyan Meng Linlin Zhang Chengyi Wang Xiangchen Liu Maofan Zhao Developing a Method to Extract Building 3D Information from GF-7 Data
description	The three-dimensional (3D) information of buildings can describe the horizontal and vertical development of a city. The GaoFen-7 (GF-7) stereo-mapping satellite can provide multi-view and multi-spectral satellite images, which can clearly describe the fine spatial details within urban areas, while the feasibility of extracting building 3D information from GF-7 image remains understudied. This article establishes an automated method for extracting building footprints and height information from GF-7 satellite imagery. First, we propose a multi-stage attention U-Net (MSAU-Net) architecture for building footprint extraction from multi-spectral images. Then, we generate the point cloud from the multi-view image and construct normalized digital surface model (nDSM) to represent the height of off-terrain objects. Finally, the building height is extracted from the nDSM and combined with the results of building footprints to obtain building 3D information. We select Beijing as the study area to test the proposed method, and in order to verify the building extraction ability of MSAU-Net, we choose GF-7 self-annotated building dataset and a public dataset (WuHan University (WHU) Building Dataset) for model testing, while the accuracy is evaluated in detail through comparison with other models. The results are summarized as follows: (1) In terms of building footprint extraction, our method can achieve intersection-over-union indicators of 89.31% and 80.27% for the WHU Dataset and GF-7 self-annotated datasets, respectively; these values are higher than the results of other models. (2) The root mean square between the extracted building height and the reference building height is 5.41 m, and the mean absolute error is 3.39 m. In summary, our method could be useful for accurate and automatic 3D building information extraction from GF-7 satellite images, and have good application potential.
format	article
author	Jingyuan Wang Xinli Hu Qingyan Meng Linlin Zhang Chengyi Wang Xiangchen Liu Maofan Zhao
author_facet	Jingyuan Wang Xinli Hu Qingyan Meng Linlin Zhang Chengyi Wang Xiangchen Liu Maofan Zhao
author_sort	Jingyuan Wang
title	Developing a Method to Extract Building 3D Information from GF-7 Data
title_short	Developing a Method to Extract Building 3D Information from GF-7 Data
title_full	Developing a Method to Extract Building 3D Information from GF-7 Data
title_fullStr	Developing a Method to Extract Building 3D Information from GF-7 Data
title_full_unstemmed	Developing a Method to Extract Building 3D Information from GF-7 Data
title_sort	developing a method to extract building 3d information from gf-7 data
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/ff15bf8f5b5b4974a7c81ff6f083b7d5
work_keys_str_mv	AT jingyuanwang developingamethodtoextractbuilding3dinformationfromgf7data AT xinlihu developingamethodtoextractbuilding3dinformationfromgf7data AT qingyanmeng developingamethodtoextractbuilding3dinformationfromgf7data AT linlinzhang developingamethodtoextractbuilding3dinformationfromgf7data AT chengyiwang developingamethodtoextractbuilding3dinformationfromgf7data AT xiangchenliu developingamethodtoextractbuilding3dinformationfromgf7data AT maofanzhao developingamethodtoextractbuilding3dinformationfromgf7data
_version_	1718410628300800000

Developing a Method to Extract Building 3D Information from GF-7 Data

Ejemplares similares