A Deep Learning-Based Framework for Automated Extraction of Building Footprint Polygons from Very High-Resolution Aerial Imagery
Accurate building footprint polygons provide essential data for a wide range of urban applications. While deep learning models have been proposed to extract pixel-based building areas from remote sensing imagery, the direct vectorization of pixel-based building maps often leads to building footprint...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/18/3630 |
| _version_ | 1797517338671579136 |
|---|---|
| author | Ziming Li Qinchuan Xin Ying Sun Mengying Cao |
| author_facet | Ziming Li Qinchuan Xin Ying Sun Mengying Cao |
| author_sort | Ziming Li |
| collection | DOAJ |
| description | Accurate building footprint polygons provide essential data for a wide range of urban applications. While deep learning models have been proposed to extract pixel-based building areas from remote sensing imagery, the direct vectorization of pixel-based building maps often leads to building footprint polygons with irregular shapes that are inconsistent with real building boundaries, making it difficult to use them in geospatial analysis. In this study, we proposed a novel deep learning-based framework for automated extraction of building footprint polygons (DLEBFP) from very high-resolution aerial imagery by combining deep learning models for different tasks. Our approach uses the U-Net, Cascade R-CNN, and Cascade CNN deep learning models to obtain building segmentation maps, building bounding boxes, and building corners, respectively, from very high-resolution remote sensing images. We used Delaunay triangulation to construct building footprint polygons based on the detected building corners with the constraints of building bounding boxes and building segmentation maps. Experiments on the Wuhan University building dataset and ISPRS Vaihingen dataset indicate that DLEBFP can perform well in extracting high-quality building footprint polygons. Compared with the other semantic segmentation models and the vector map generalization method, DLEBFP is able to achieve comparable mapping accuracies with semantic segmentation models on a pixel basis and generate building footprint polygons with concise edges and vertices with regular shapes that are close to the reference data. The promising performance indicates that our method has the potential to extract accurate building footprint polygons from remote sensing images for applications in geospatial analysis. |
| first_indexed | 2024-03-10T07:15:16Z |
| format | Article |
| id | doaj.art-44c2f9eb423b417aa979d84f1139088e |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T07:15:16Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-44c2f9eb423b417aa979d84f1139088e2023-11-22T15:06:01ZengMDPI AGRemote Sensing2072-42922021-09-011318363010.3390/rs13183630A Deep Learning-Based Framework for Automated Extraction of Building Footprint Polygons from Very High-Resolution Aerial ImageryZiming Li0Qinchuan Xin1Ying Sun2Mengying Cao3Guangdong Key Laboratory for Urbanization and Geo-Simulation, School of Geography and Planning, Sun Yat-sen University, Guangzhou 510275, ChinaGuangdong Key Laboratory for Urbanization and Geo-Simulation, School of Geography and Planning, Sun Yat-sen University, Guangzhou 510275, ChinaGuangdong Key Laboratory for Urbanization and Geo-Simulation, School of Geography and Planning, Sun Yat-sen University, Guangzhou 510275, ChinaGuangdong Key Laboratory for Urbanization and Geo-Simulation, School of Geography and Planning, Sun Yat-sen University, Guangzhou 510275, ChinaAccurate building footprint polygons provide essential data for a wide range of urban applications. While deep learning models have been proposed to extract pixel-based building areas from remote sensing imagery, the direct vectorization of pixel-based building maps often leads to building footprint polygons with irregular shapes that are inconsistent with real building boundaries, making it difficult to use them in geospatial analysis. In this study, we proposed a novel deep learning-based framework for automated extraction of building footprint polygons (DLEBFP) from very high-resolution aerial imagery by combining deep learning models for different tasks. Our approach uses the U-Net, Cascade R-CNN, and Cascade CNN deep learning models to obtain building segmentation maps, building bounding boxes, and building corners, respectively, from very high-resolution remote sensing images. We used Delaunay triangulation to construct building footprint polygons based on the detected building corners with the constraints of building bounding boxes and building segmentation maps. Experiments on the Wuhan University building dataset and ISPRS Vaihingen dataset indicate that DLEBFP can perform well in extracting high-quality building footprint polygons. Compared with the other semantic segmentation models and the vector map generalization method, DLEBFP is able to achieve comparable mapping accuracies with semantic segmentation models on a pixel basis and generate building footprint polygons with concise edges and vertices with regular shapes that are close to the reference data. The promising performance indicates that our method has the potential to extract accurate building footprint polygons from remote sensing images for applications in geospatial analysis.https://www.mdpi.com/2072-4292/13/18/3630building footprintmap vectorizationconvolutional neural networksemantic segmentation |
| spellingShingle | Ziming Li Qinchuan Xin Ying Sun Mengying Cao A Deep Learning-Based Framework for Automated Extraction of Building Footprint Polygons from Very High-Resolution Aerial Imagery Remote Sensing building footprint map vectorization convolutional neural network semantic segmentation |
| title | A Deep Learning-Based Framework for Automated Extraction of Building Footprint Polygons from Very High-Resolution Aerial Imagery |
| title_full | A Deep Learning-Based Framework for Automated Extraction of Building Footprint Polygons from Very High-Resolution Aerial Imagery |
| title_fullStr | A Deep Learning-Based Framework for Automated Extraction of Building Footprint Polygons from Very High-Resolution Aerial Imagery |
| title_full_unstemmed | A Deep Learning-Based Framework for Automated Extraction of Building Footprint Polygons from Very High-Resolution Aerial Imagery |
| title_short | A Deep Learning-Based Framework for Automated Extraction of Building Footprint Polygons from Very High-Resolution Aerial Imagery |
| title_sort | deep learning based framework for automated extraction of building footprint polygons from very high resolution aerial imagery |
| topic | building footprint map vectorization convolutional neural network semantic segmentation |
| url | https://www.mdpi.com/2072-4292/13/18/3630 |
| work_keys_str_mv | AT zimingli adeeplearningbasedframeworkforautomatedextractionofbuildingfootprintpolygonsfromveryhighresolutionaerialimagery AT qinchuanxin adeeplearningbasedframeworkforautomatedextractionofbuildingfootprintpolygonsfromveryhighresolutionaerialimagery AT yingsun adeeplearningbasedframeworkforautomatedextractionofbuildingfootprintpolygonsfromveryhighresolutionaerialimagery AT mengyingcao adeeplearningbasedframeworkforautomatedextractionofbuildingfootprintpolygonsfromveryhighresolutionaerialimagery AT zimingli deeplearningbasedframeworkforautomatedextractionofbuildingfootprintpolygonsfromveryhighresolutionaerialimagery AT qinchuanxin deeplearningbasedframeworkforautomatedextractionofbuildingfootprintpolygonsfromveryhighresolutionaerialimagery AT yingsun deeplearningbasedframeworkforautomatedextractionofbuildingfootprintpolygonsfromveryhighresolutionaerialimagery AT mengyingcao deeplearningbasedframeworkforautomatedextractionofbuildingfootprintpolygonsfromveryhighresolutionaerialimagery |