Building Extraction From High-Resolution Multispectral and SAR Images Using a Boundary-Link Multimodal Fusion Network
Automatically extracting buildings with high precision from remote sensing images is crucial for various applications. Due to their distinct imaging modalities and complementary characteristics, optical and synthetic aperture radar (SAR) images serve as primary data sources for this task. We propose...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10824925/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586899498205184 |
|---|---|
| author | Zhe Zhao Boya Zhao Yuanfeng Wu Zutian He Lianru Gao |
| author_facet | Zhe Zhao Boya Zhao Yuanfeng Wu Zutian He Lianru Gao |
| author_sort | Zhe Zhao |
| collection | DOAJ |
| description | Automatically extracting buildings with high precision from remote sensing images is crucial for various applications. Due to their distinct imaging modalities and complementary characteristics, optical and synthetic aperture radar (SAR) images serve as primary data sources for this task. We propose a novel boundary-link multimodal fusion network for joint semantic segmentation to leverage the information in these images. An initial building extraction result is obtained from the multimodal fusion network, followed by refinement using building boundaries. The model achieves high-precision building delineation by leveraging building boundary and semantic information from optical and SAR images. It distinguishes buildings from the background in complex environments, such as dense urban areas or regions with mixed vegetation, particularly when small buildings lack distinct texture or color features. We conducted experiments using the MSAW dataset (RGB-NIR and SAR data) and DFC track2 datasets (RGB and SAR data). The results indicate that our model significantly enhances extraction accuracy and improves building boundary delineation. The intersection over union metric is 2.5% to 3.5% higher than that of other multimodal joint segmentation methods. |
| format | Article |
| id | doaj-art-f4574c1e5d344a67a7dccb3eecee9345 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-f4574c1e5d344a67a7dccb3eecee93452025-01-25T00:00:10ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01183864387810.1109/JSTARS.2025.352570910824925Building Extraction From High-Resolution Multispectral and SAR Images Using a Boundary-Link Multimodal Fusion NetworkZhe Zhao0https://orcid.org/0009-0000-3108-3820Boya Zhao1https://orcid.org/0000-0001-5620-406XYuanfeng Wu2https://orcid.org/0000-0001-8427-9851Zutian He3https://orcid.org/0009-0004-0646-8031Lianru Gao4https://orcid.org/0000-0003-3888-8124Key Laboratory of Computational Optical Imaging Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Computational Optical Imaging Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Computational Optical Imaging Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Computational Optical Imaging Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Computational Optical Imaging Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAutomatically extracting buildings with high precision from remote sensing images is crucial for various applications. Due to their distinct imaging modalities and complementary characteristics, optical and synthetic aperture radar (SAR) images serve as primary data sources for this task. We propose a novel boundary-link multimodal fusion network for joint semantic segmentation to leverage the information in these images. An initial building extraction result is obtained from the multimodal fusion network, followed by refinement using building boundaries. The model achieves high-precision building delineation by leveraging building boundary and semantic information from optical and SAR images. It distinguishes buildings from the background in complex environments, such as dense urban areas or regions with mixed vegetation, particularly when small buildings lack distinct texture or color features. We conducted experiments using the MSAW dataset (RGB-NIR and SAR data) and DFC track2 datasets (RGB and SAR data). The results indicate that our model significantly enhances extraction accuracy and improves building boundary delineation. The intersection over union metric is 2.5% to 3.5% higher than that of other multimodal joint segmentation methods.https://ieeexplore.ieee.org/document/10824925/Building extractionmultimodal segmentationmultispectralsynthetic aperture radar (SAR) |
| spellingShingle | Zhe Zhao Boya Zhao Yuanfeng Wu Zutian He Lianru Gao Building Extraction From High-Resolution Multispectral and SAR Images Using a Boundary-Link Multimodal Fusion Network IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Building extraction multimodal segmentation multispectral synthetic aperture radar (SAR) |
| title | Building Extraction From High-Resolution Multispectral and SAR Images Using a Boundary-Link Multimodal Fusion Network |
| title_full | Building Extraction From High-Resolution Multispectral and SAR Images Using a Boundary-Link Multimodal Fusion Network |
| title_fullStr | Building Extraction From High-Resolution Multispectral and SAR Images Using a Boundary-Link Multimodal Fusion Network |
| title_full_unstemmed | Building Extraction From High-Resolution Multispectral and SAR Images Using a Boundary-Link Multimodal Fusion Network |
| title_short | Building Extraction From High-Resolution Multispectral and SAR Images Using a Boundary-Link Multimodal Fusion Network |
| title_sort | building extraction from high resolution multispectral and sar images using a boundary link multimodal fusion network |
| topic | Building extraction multimodal segmentation multispectral synthetic aperture radar (SAR) |
| url | https://ieeexplore.ieee.org/document/10824925/ |
| work_keys_str_mv | AT zhezhao buildingextractionfromhighresolutionmultispectralandsarimagesusingaboundarylinkmultimodalfusionnetwork AT boyazhao buildingextractionfromhighresolutionmultispectralandsarimagesusingaboundarylinkmultimodalfusionnetwork AT yuanfengwu buildingextractionfromhighresolutionmultispectralandsarimagesusingaboundarylinkmultimodalfusionnetwork AT zutianhe buildingextractionfromhighresolutionmultispectralandsarimagesusingaboundarylinkmultimodalfusionnetwork AT lianrugao buildingextractionfromhighresolutionmultispectralandsarimagesusingaboundarylinkmultimodalfusionnetwork |