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

Abstract

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.

Optimized Views Photogrammetry: Precision Analysis and a Large-Scale Case Study in Qingdao

“…Satellite-based and aerial-based photogrammetric imaging systems can provide remote sensing (RS) data for 3-D reconstruction of large-scale topographic reliefs and urban buildings [3], [4], [5]. However, due to their high flight heights, such as hundreds of kilometers on satellites and a few kilometers on aerial planes, and fixed observation view points, these RS systems can only provide data with low spatial resolutions and limited acquisition abilities [6]. For reconstructing fine-scale 3-D models of complex urban scenes, it has become very urgent to meet the requirements for high timeliness and flexibility in data acquisition as well as high spatial resolution for collected images [7], [8].…”

High‐resolution quantification of building stock using multi‐source remote sensing imagery and deep learning

“…Despite the increasing research emphasis on remote sensing data applications for stock estimation, their potential is still underexploited. For example, the textural features of ORS can reflect ground conditions and effectively identify buildings (Cao & Huang, 2021; Shao et al., 2020; Wang et al., 2021) and roads (Das et al., 2011; Lv et al., 2017). However, most extant studies ignore the critical role of ORS characteristics during stock estimation.…”

DMU-Net: A Dual-Stream Multi-Scale U-Net Network Using Multi-Dimensional Spatial Information for Urban Building Extraction

“…Gaofen-7 (GF-7), one of China’s most advanced stereo observation satellites, provides DSM data with an elevation root mean square error lower than 1 m [ 15 ]. Stereo images acquired by GF-7 have been used in three-dimensional information extraction and modeling of urban buildings, showing the power to describe the vertical structure of urban features [ 16 , 17 ]. However, there have been studies using DSM data constructed from Pleiades or WorldView stereo satellite imagery for building extraction [ 18 , 19 ].…”