Combining ICESat-2 photons and Google Earth Satellite images for building height extraction
Building heights are one of the crucial data for comprehending the functions of urban systems. Employing optical remote sensing imagery, the shadow-based method is one of the most promising methods which have been proposed for estimating building height. However, the existing shadow-based studies fo...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-03-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843223000353 |
| _version_ | 1811163484608528384 |
|---|---|
| author | Yi Zhao Bin Wu Qiaoxuan Li Lei Yang Hongchao Fan Jianping Wu Bailang Yu |
| author_facet | Yi Zhao Bin Wu Qiaoxuan Li Lei Yang Hongchao Fan Jianping Wu Bailang Yu |
| author_sort | Yi Zhao |
| collection | DOAJ |
| description | Building heights are one of the crucial data for comprehending the functions of urban systems. Employing optical remote sensing imagery, the shadow-based method is one of the most promising methods which have been proposed for estimating building height. However, the existing shadow-based studies for building height estimation are restricted to a small area due to the lack of building height annotations and ignorance of building azimuth variations. The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) allows large-scale building height retrieval in the along-track direction and thus can be taken as ground truth building height annotations to support the shadow-based algorithms for large-scale building height extraction. Here, we proposed an approach for extracting building height by combining Google Earth Satellite (GES) images and ICESat-2 photons. Building and shadow instances were first extracted using a U-Net deep learning framework. Based on the building height annotations retrieved from ICESat-2 photons, an improved shadow-based building height estimation model by minimizing the global error across all sample buildings was developed. A typical urban area located in the city center of Shanghai, China with an area of around 90 km2 was selected to validate the proposed method. In total 15,966 buildings were successfully extracted and the results indicated that the estimated building heights have high accuracy with an absolute mean error of 4.08 m. Moreover, the proposed method shows a better performance compared to the existing shadow-based method and existing building height datasets. The method holds great potential for large-scale building-level height retrieval which contributes to further studies of urban morphologies. |
| first_indexed | 2024-04-10T15:06:37Z |
| format | Article |
| id | doaj.art-9f225e79ada545c3aac540b24f052687 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-04-10T15:06:37Z |
| publishDate | 2023-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-9f225e79ada545c3aac540b24f0526872023-02-15T04:27:34ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322023-03-01117103213Combining ICESat-2 photons and Google Earth Satellite images for building height extractionYi Zhao0Bin Wu1Qiaoxuan Li2Lei Yang3Hongchao Fan4Jianping Wu5Bailang Yu6Key Laboratory of Geographic Information Science (Ministry of Education), East China Normal University, Shanghai 200241, China; School of Geographic Sciences, East China Normal University, Shanghai 200241, China; Department of Civil and Environmental Engineering, Norwegian University of Science and Technology, Trondheim 7491, NorwayKey Laboratory of Geographic Information Science (Ministry of Education), East China Normal University, Shanghai 200241, China; School of Geospatial Engineering and Science, Sun Yat-sen University, Zhuhai 519082, China; Corresponding authors at: Key Laboratory of Geographic Information Science (Ministry of Education), East China Normal University, Shanghai 200241, China.Key Laboratory of Geographic Information Science (Ministry of Education), East China Normal University, Shanghai 200241, China; School of Geographic Sciences, East China Normal University, Shanghai 200241, ChinaKey Laboratory of Geographic Information Science (Ministry of Education), East China Normal University, Shanghai 200241, China; School of Geographic Sciences, East China Normal University, Shanghai 200241, ChinaDepartment of Civil and Environmental Engineering, Norwegian University of Science and Technology, Trondheim 7491, NorwayKey Laboratory of Geographic Information Science (Ministry of Education), East China Normal University, Shanghai 200241, China; School of Geographic Sciences, East China Normal University, Shanghai 200241, ChinaKey Laboratory of Geographic Information Science (Ministry of Education), East China Normal University, Shanghai 200241, China; School of Geographic Sciences, East China Normal University, Shanghai 200241, China; Corresponding authors at: Key Laboratory of Geographic Information Science (Ministry of Education), East China Normal University, Shanghai 200241, China.Building heights are one of the crucial data for comprehending the functions of urban systems. Employing optical remote sensing imagery, the shadow-based method is one of the most promising methods which have been proposed for estimating building height. However, the existing shadow-based studies for building height estimation are restricted to a small area due to the lack of building height annotations and ignorance of building azimuth variations. The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) allows large-scale building height retrieval in the along-track direction and thus can be taken as ground truth building height annotations to support the shadow-based algorithms for large-scale building height extraction. Here, we proposed an approach for extracting building height by combining Google Earth Satellite (GES) images and ICESat-2 photons. Building and shadow instances were first extracted using a U-Net deep learning framework. Based on the building height annotations retrieved from ICESat-2 photons, an improved shadow-based building height estimation model by minimizing the global error across all sample buildings was developed. A typical urban area located in the city center of Shanghai, China with an area of around 90 km2 was selected to validate the proposed method. In total 15,966 buildings were successfully extracted and the results indicated that the estimated building heights have high accuracy with an absolute mean error of 4.08 m. Moreover, the proposed method shows a better performance compared to the existing shadow-based method and existing building height datasets. The method holds great potential for large-scale building-level height retrieval which contributes to further studies of urban morphologies.http://www.sciencedirect.com/science/article/pii/S1569843223000353Building heightICESat-2Google Earth imagesBuilding shadowU-Net |
| spellingShingle | Yi Zhao Bin Wu Qiaoxuan Li Lei Yang Hongchao Fan Jianping Wu Bailang Yu Combining ICESat-2 photons and Google Earth Satellite images for building height extraction International Journal of Applied Earth Observations and Geoinformation Building height ICESat-2 Google Earth images Building shadow U-Net |
| title | Combining ICESat-2 photons and Google Earth Satellite images for building height extraction |
| title_full | Combining ICESat-2 photons and Google Earth Satellite images for building height extraction |
| title_fullStr | Combining ICESat-2 photons and Google Earth Satellite images for building height extraction |
| title_full_unstemmed | Combining ICESat-2 photons and Google Earth Satellite images for building height extraction |
| title_short | Combining ICESat-2 photons and Google Earth Satellite images for building height extraction |
| title_sort | combining icesat 2 photons and google earth satellite images for building height extraction |
| topic | Building height ICESat-2 Google Earth images Building shadow U-Net |
| url | http://www.sciencedirect.com/science/article/pii/S1569843223000353 |
| work_keys_str_mv | AT yizhao combiningicesat2photonsandgoogleearthsatelliteimagesforbuildingheightextraction AT binwu combiningicesat2photonsandgoogleearthsatelliteimagesforbuildingheightextraction AT qiaoxuanli combiningicesat2photonsandgoogleearthsatelliteimagesforbuildingheightextraction AT leiyang combiningicesat2photonsandgoogleearthsatelliteimagesforbuildingheightextraction AT hongchaofan combiningicesat2photonsandgoogleearthsatelliteimagesforbuildingheightextraction AT jianpingwu combiningicesat2photonsandgoogleearthsatelliteimagesforbuildingheightextraction AT bailangyu combiningicesat2photonsandgoogleearthsatelliteimagesforbuildingheightextraction |