Semantic Segmentation-Based Building Footprint Extraction Using Very High-Resolution Satellite Images and Multi-Source GIS Data

Automatic extraction of building footprints from high-resolution satellite imagery has become an important and challenging research issue receiving greater attention. Many recent studies have explored different deep learning-based semantic segmentation methods for improving the accuracy of building...

Full description

Bibliographic Details
Main Authors: Weijia Li, Conghui He, Jiarui Fang, Juepeng Zheng, Haohuan Fu, Le Yu
Format: Article
Language:English
Published: MDPI AG 2019-02-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/11/4/403
_version_ 1798031509622358016
author Weijia Li
Conghui He
Jiarui Fang
Juepeng Zheng
Haohuan Fu
Le Yu
author_facet Weijia Li
Conghui He
Jiarui Fang
Juepeng Zheng
Haohuan Fu
Le Yu
author_sort Weijia Li
collection DOAJ
description Automatic extraction of building footprints from high-resolution satellite imagery has become an important and challenging research issue receiving greater attention. Many recent studies have explored different deep learning-based semantic segmentation methods for improving the accuracy of building extraction. Although they record substantial land cover and land use information (e.g., buildings, roads, water, etc.), public geographic information system (GIS) map datasets have rarely been utilized to improve building extraction results in existing studies. In this research, we propose a U-Net-based semantic segmentation method for the extraction of building footprints from high-resolution multispectral satellite images using the SpaceNet building dataset provided in the DeepGlobe Satellite Challenge of IEEE Conference on Computer Vision and Pattern Recognition 2018 (CVPR 2018). We explore the potential of multiple public GIS map datasets (OpenStreetMap, Google Maps, and MapWorld) through integration with the WorldView-3 satellite datasets in four cities (Las Vegas, Paris, Shanghai, and Khartoum). Several strategies are designed and combined with the U-Net⁻based semantic segmentation model, including data augmentation, post-processing, and integration of the GIS map data and satellite images. The proposed method achieves a total F1-score of 0.704, which is an improvement of 1.1% to 12.5% compared with the top three solutions in the SpaceNet Building Detection Competition and 3.0% to 9.2% compared with the standard U-Net⁻based method. Moreover, the effect of each proposed strategy and the possible reasons for the building footprint extraction results are analyzed substantially considering the actual situation of the four cities.
first_indexed 2024-04-11T19:58:38Z
format Article
id doaj.art-f34d0711a786411686362274c4a19199
institution Directory Open Access Journal
issn 2072-4292
language English
last_indexed 2024-04-11T19:58:38Z
publishDate 2019-02-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj.art-f34d0711a786411686362274c4a191992022-12-22T04:05:50ZengMDPI AGRemote Sensing2072-42922019-02-0111440310.3390/rs11040403rs11040403Semantic Segmentation-Based Building Footprint Extraction Using Very High-Resolution Satellite Images and Multi-Source GIS DataWeijia Li0Conghui He1Jiarui Fang2Juepeng Zheng3Haohuan Fu4Le Yu5Ministry of Education Key Laboratory for Earth System Modeling, Department of Earth System Science, Tsinghua University, Beijing 100084, ChinaDepartment of Computer Science, Tsinghua University, Beijing 100084, ChinaDepartment of Computer Science, Tsinghua University, Beijing 100084, ChinaMinistry of Education Key Laboratory for Earth System Modeling, Department of Earth System Science, Tsinghua University, Beijing 100084, ChinaMinistry of Education Key Laboratory for Earth System Modeling, Department of Earth System Science, Tsinghua University, Beijing 100084, ChinaMinistry of Education Key Laboratory for Earth System Modeling, Department of Earth System Science, Tsinghua University, Beijing 100084, ChinaAutomatic extraction of building footprints from high-resolution satellite imagery has become an important and challenging research issue receiving greater attention. Many recent studies have explored different deep learning-based semantic segmentation methods for improving the accuracy of building extraction. Although they record substantial land cover and land use information (e.g., buildings, roads, water, etc.), public geographic information system (GIS) map datasets have rarely been utilized to improve building extraction results in existing studies. In this research, we propose a U-Net-based semantic segmentation method for the extraction of building footprints from high-resolution multispectral satellite images using the SpaceNet building dataset provided in the DeepGlobe Satellite Challenge of IEEE Conference on Computer Vision and Pattern Recognition 2018 (CVPR 2018). We explore the potential of multiple public GIS map datasets (OpenStreetMap, Google Maps, and MapWorld) through integration with the WorldView-3 satellite datasets in four cities (Las Vegas, Paris, Shanghai, and Khartoum). Several strategies are designed and combined with the U-Net⁻based semantic segmentation model, including data augmentation, post-processing, and integration of the GIS map data and satellite images. The proposed method achieves a total F1-score of 0.704, which is an improvement of 1.1% to 12.5% compared with the top three solutions in the SpaceNet Building Detection Competition and 3.0% to 9.2% compared with the standard U-Net⁻based method. Moreover, the effect of each proposed strategy and the possible reasons for the building footprint extraction results are analyzed substantially considering the actual situation of the four cities.https://www.mdpi.com/2072-4292/11/4/403building extractiondeep learningsemantic segmentationdata fusionhigh-resolution satellite imagesGIS data
spellingShingle Weijia Li
Conghui He
Jiarui Fang
Juepeng Zheng
Haohuan Fu
Le Yu
Semantic Segmentation-Based Building Footprint Extraction Using Very High-Resolution Satellite Images and Multi-Source GIS Data
Remote Sensing
building extraction
deep learning
semantic segmentation
data fusion
high-resolution satellite images
GIS data
title Semantic Segmentation-Based Building Footprint Extraction Using Very High-Resolution Satellite Images and Multi-Source GIS Data
title_full Semantic Segmentation-Based Building Footprint Extraction Using Very High-Resolution Satellite Images and Multi-Source GIS Data
title_fullStr Semantic Segmentation-Based Building Footprint Extraction Using Very High-Resolution Satellite Images and Multi-Source GIS Data
title_full_unstemmed Semantic Segmentation-Based Building Footprint Extraction Using Very High-Resolution Satellite Images and Multi-Source GIS Data
title_short Semantic Segmentation-Based Building Footprint Extraction Using Very High-Resolution Satellite Images and Multi-Source GIS Data
title_sort semantic segmentation based building footprint extraction using very high resolution satellite images and multi source gis data
topic building extraction
deep learning
semantic segmentation
data fusion
high-resolution satellite images
GIS data
url https://www.mdpi.com/2072-4292/11/4/403
work_keys_str_mv AT weijiali semanticsegmentationbasedbuildingfootprintextractionusingveryhighresolutionsatelliteimagesandmultisourcegisdata
AT conghuihe semanticsegmentationbasedbuildingfootprintextractionusingveryhighresolutionsatelliteimagesandmultisourcegisdata
AT jiaruifang semanticsegmentationbasedbuildingfootprintextractionusingveryhighresolutionsatelliteimagesandmultisourcegisdata
AT juepengzheng semanticsegmentationbasedbuildingfootprintextractionusingveryhighresolutionsatelliteimagesandmultisourcegisdata
AT haohuanfu semanticsegmentationbasedbuildingfootprintextractionusingveryhighresolutionsatelliteimagesandmultisourcegisdata
AT leyu semanticsegmentationbasedbuildingfootprintextractionusingveryhighresolutionsatelliteimagesandmultisourcegisdata