A Large-Scale Mapping Scheme for Urban Building From Gaofen-2 Images Using Deep Learning and Hierarchical Approach

Urban buildings are essential components of cities and an indispensable source of urban geographic information. While there are many research efforts focused on urban buildings extraction, there are few studies on large-scale urban building mapping based on satellite images. In this research, a larg...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Dengji Zhou, Guizhou Wang, Guojin He, Ranyu Yin, Tengfei Long, Zhaoming Zhang, Sibao Chen, Bin Luo
Formato: article
Lenguaje:EN
Publicado: IEEE 2021
Materias:
Acceso en línea:https://doaj.org/article/69348794f74647b584c63f0c6cab3c5c
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:69348794f74647b584c63f0c6cab3c5c
record_format dspace
spelling oai:doaj.org-article:69348794f74647b584c63f0c6cab3c5c2021-11-23T00:00:43ZA Large-Scale Mapping Scheme for Urban Building From Gaofen-2 Images Using Deep Learning and Hierarchical Approach2151-153510.1109/JSTARS.2021.3123398https://doaj.org/article/69348794f74647b584c63f0c6cab3c5c2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9591376/https://doaj.org/toc/2151-1535Urban buildings are essential components of cities and an indispensable source of urban geographic information. While there are many research efforts focused on urban buildings extraction, there are few studies on large-scale urban building mapping based on satellite images. In this research, a large-scale urban building mapping scheme based on Gaofen-2 satellite (GF-2) images is proposed based on a hierarchical approach. In this hierarchical approach, urban buildings are regarded as a mixture of dense low-rise buildings (DLBs) and sparse independent buildings (SIBs) stacked in space, which are extracted by a semantic segmentation model and an instance segmentation model, respectively. In this study, GF-2 images and OpenStreetMap data were used to extract DLB using <inline-formula><tex-math notation="LaTeX">$U^2$</tex-math></inline-formula>-Net with focal loss. GF-2 images were used to extract SIB using an improved CenterMask model with a deformable convolution network and a spatial coordinate attention module. The main urban area within the 5th ring road of Beijing was selected as the study area. With the trained model, the GF-2 image tiles of Beijing input into the models to first derive coarse maps of DLB and SIB. Postprocessing optimization was performed after combining the maps. The accuracy assessment shows that the overall accuracy of large-scale urban building mapping using the hierarchical approach proposed in this article reaches 91.5&#x0025;, which is 4.8&#x0025; higher than that with a traditional method. Overall, the hierarchical approach proposed in this article is effective in large-scale urban building mapping and provides new application opportunities.Dengji ZhouGuizhou WangGuojin HeRanyu YinTengfei LongZhaoming ZhangSibao ChenBin LuoIEEEarticleDeep learningGaofen-2 (GF-2)hierarchical approachlarge-scale urban building mappingOpenStreetMap (OSM) roadOcean engineeringTC1501-1800Geophysics. Cosmic physicsQC801-809ENIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 11530-11545 (2021)
institution DOAJ
collection DOAJ
language EN
topic Deep learning
Gaofen-2 (GF-2)
hierarchical approach
large-scale urban building mapping
OpenStreetMap (OSM) road
Ocean engineering
TC1501-1800
Geophysics. Cosmic physics
QC801-809
spellingShingle Deep learning
Gaofen-2 (GF-2)
hierarchical approach
large-scale urban building mapping
OpenStreetMap (OSM) road
Ocean engineering
TC1501-1800
Geophysics. Cosmic physics
QC801-809
Dengji Zhou
Guizhou Wang
Guojin He
Ranyu Yin
Tengfei Long
Zhaoming Zhang
Sibao Chen
Bin Luo
A Large-Scale Mapping Scheme for Urban Building From Gaofen-2 Images Using Deep Learning and Hierarchical Approach
description Urban buildings are essential components of cities and an indispensable source of urban geographic information. While there are many research efforts focused on urban buildings extraction, there are few studies on large-scale urban building mapping based on satellite images. In this research, a large-scale urban building mapping scheme based on Gaofen-2 satellite (GF-2) images is proposed based on a hierarchical approach. In this hierarchical approach, urban buildings are regarded as a mixture of dense low-rise buildings (DLBs) and sparse independent buildings (SIBs) stacked in space, which are extracted by a semantic segmentation model and an instance segmentation model, respectively. In this study, GF-2 images and OpenStreetMap data were used to extract DLB using <inline-formula><tex-math notation="LaTeX">$U^2$</tex-math></inline-formula>-Net with focal loss. GF-2 images were used to extract SIB using an improved CenterMask model with a deformable convolution network and a spatial coordinate attention module. The main urban area within the 5th ring road of Beijing was selected as the study area. With the trained model, the GF-2 image tiles of Beijing input into the models to first derive coarse maps of DLB and SIB. Postprocessing optimization was performed after combining the maps. The accuracy assessment shows that the overall accuracy of large-scale urban building mapping using the hierarchical approach proposed in this article reaches 91.5&#x0025;, which is 4.8&#x0025; higher than that with a traditional method. Overall, the hierarchical approach proposed in this article is effective in large-scale urban building mapping and provides new application opportunities.
format article
author Dengji Zhou
Guizhou Wang
Guojin He
Ranyu Yin
Tengfei Long
Zhaoming Zhang
Sibao Chen
Bin Luo
author_facet Dengji Zhou
Guizhou Wang
Guojin He
Ranyu Yin
Tengfei Long
Zhaoming Zhang
Sibao Chen
Bin Luo
author_sort Dengji Zhou
title A Large-Scale Mapping Scheme for Urban Building From Gaofen-2 Images Using Deep Learning and Hierarchical Approach
title_short A Large-Scale Mapping Scheme for Urban Building From Gaofen-2 Images Using Deep Learning and Hierarchical Approach
title_full A Large-Scale Mapping Scheme for Urban Building From Gaofen-2 Images Using Deep Learning and Hierarchical Approach
title_fullStr A Large-Scale Mapping Scheme for Urban Building From Gaofen-2 Images Using Deep Learning and Hierarchical Approach
title_full_unstemmed A Large-Scale Mapping Scheme for Urban Building From Gaofen-2 Images Using Deep Learning and Hierarchical Approach
title_sort large-scale mapping scheme for urban building from gaofen-2 images using deep learning and hierarchical approach
publisher IEEE
publishDate 2021
url https://doaj.org/article/69348794f74647b584c63f0c6cab3c5c
work_keys_str_mv AT dengjizhou alargescalemappingschemeforurbanbuildingfromgaofen2imagesusingdeeplearningandhierarchicalapproach
AT guizhouwang alargescalemappingschemeforurbanbuildingfromgaofen2imagesusingdeeplearningandhierarchicalapproach
AT guojinhe alargescalemappingschemeforurbanbuildingfromgaofen2imagesusingdeeplearningandhierarchicalapproach
AT ranyuyin alargescalemappingschemeforurbanbuildingfromgaofen2imagesusingdeeplearningandhierarchicalapproach
AT tengfeilong alargescalemappingschemeforurbanbuildingfromgaofen2imagesusingdeeplearningandhierarchicalapproach
AT zhaomingzhang alargescalemappingschemeforurbanbuildingfromgaofen2imagesusingdeeplearningandhierarchicalapproach
AT sibaochen alargescalemappingschemeforurbanbuildingfromgaofen2imagesusingdeeplearningandhierarchicalapproach
AT binluo alargescalemappingschemeforurbanbuildingfromgaofen2imagesusingdeeplearningandhierarchicalapproach
AT dengjizhou largescalemappingschemeforurbanbuildingfromgaofen2imagesusingdeeplearningandhierarchicalapproach
AT guizhouwang largescalemappingschemeforurbanbuildingfromgaofen2imagesusingdeeplearningandhierarchicalapproach
AT guojinhe largescalemappingschemeforurbanbuildingfromgaofen2imagesusingdeeplearningandhierarchicalapproach
AT ranyuyin largescalemappingschemeforurbanbuildingfromgaofen2imagesusingdeeplearningandhierarchicalapproach
AT tengfeilong largescalemappingschemeforurbanbuildingfromgaofen2imagesusingdeeplearningandhierarchicalapproach
AT zhaomingzhang largescalemappingschemeforurbanbuildingfromgaofen2imagesusingdeeplearningandhierarchicalapproach
AT sibaochen largescalemappingschemeforurbanbuildingfromgaofen2imagesusingdeeplearningandhierarchicalapproach
AT binluo largescalemappingschemeforurbanbuildingfromgaofen2imagesusingdeeplearningandhierarchicalapproach
_version_ 1718417379024699392