Deep nested U-structure network with frequency attention for building semantic segmentation
Abstract The automated segmentation of buildings from remotely sensed imagery has undergone extensive research and application across various industrial domains. Despite this, several challenges persist, including incomplete internal extraction, low accuracy in edge segmentation, and difficulties in...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-13890-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849344908935036928 |
|---|---|
| author | Khaled Moghalles Zaid Al-Huda Dalal AL-Alimi Yeong Hyeon Gu Mugahed A. Al-antari |
| author_facet | Khaled Moghalles Zaid Al-Huda Dalal AL-Alimi Yeong Hyeon Gu Mugahed A. Al-antari |
| author_sort | Khaled Moghalles |
| collection | DOAJ |
| description | Abstract The automated segmentation of buildings from remotely sensed imagery has undergone extensive research and application across various industrial domains. Despite this, several challenges persist, including incomplete internal extraction, low accuracy in edge segmentation, and difficulties in predicting irregular targets. We have introduced a novel approach to address these issues: an end-to-end residual U-structure embedded within a U-Net, enhanced by a frequency attention module and a hybrid loss function. The novel residual U-structure is introduced to replace the encode-decode blocks of traditional U-Nets, and the hybrid loss function is utilized to guide segmentation for more complete and accurate segmentation masks. A frequency attention module is also implemented to emphasize essential features and minimize irrelevant ones. A comparison of the proposed framework with other baseline schemes was conducted on four benchmark data sets, and the experimental results demonstrate that our framework performs better segmentation than other baseline state-of-the-art schemes. |
| format | Article |
| id | doaj-art-0025f7a2a7fb40f58ff531db809a7a10 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-0025f7a2a7fb40f58ff531db809a7a102025-08-20T03:42:33ZengNature PortfolioScientific Reports2045-23222025-08-0115111610.1038/s41598-025-13890-8Deep nested U-structure network with frequency attention for building semantic segmentationKhaled Moghalles0Zaid Al-Huda1Dalal AL-Alimi2Yeong Hyeon Gu3Mugahed A. Al-antari4School of Information Science and Technology, Southwest Jiaotong UniversityStirling College, Chengdu UniversityFaculty of Engineering, Sana’a UniversityDepartment of Artificial Intelligence and Data Science, College of AI Convergence, Sejong UniversityDepartment of Artificial Intelligence and Data Science, College of AI Convergence, Sejong UniversityAbstract The automated segmentation of buildings from remotely sensed imagery has undergone extensive research and application across various industrial domains. Despite this, several challenges persist, including incomplete internal extraction, low accuracy in edge segmentation, and difficulties in predicting irregular targets. We have introduced a novel approach to address these issues: an end-to-end residual U-structure embedded within a U-Net, enhanced by a frequency attention module and a hybrid loss function. The novel residual U-structure is introduced to replace the encode-decode blocks of traditional U-Nets, and the hybrid loss function is utilized to guide segmentation for more complete and accurate segmentation masks. A frequency attention module is also implemented to emphasize essential features and minimize irrelevant ones. A comparison of the proposed framework with other baseline schemes was conducted on four benchmark data sets, and the experimental results demonstrate that our framework performs better segmentation than other baseline state-of-the-art schemes.https://doi.org/10.1038/s41598-025-13890-8Building extractionResidual U-structureRemote sensingConvolution neural networks |
| spellingShingle | Khaled Moghalles Zaid Al-Huda Dalal AL-Alimi Yeong Hyeon Gu Mugahed A. Al-antari Deep nested U-structure network with frequency attention for building semantic segmentation Scientific Reports Building extraction Residual U-structure Remote sensing Convolution neural networks |
| title | Deep nested U-structure network with frequency attention for building semantic segmentation |
| title_full | Deep nested U-structure network with frequency attention for building semantic segmentation |
| title_fullStr | Deep nested U-structure network with frequency attention for building semantic segmentation |
| title_full_unstemmed | Deep nested U-structure network with frequency attention for building semantic segmentation |
| title_short | Deep nested U-structure network with frequency attention for building semantic segmentation |
| title_sort | deep nested u structure network with frequency attention for building semantic segmentation |
| topic | Building extraction Residual U-structure Remote sensing Convolution neural networks |
| url | https://doi.org/10.1038/s41598-025-13890-8 |
| work_keys_str_mv | AT khaledmoghalles deepnestedustructurenetworkwithfrequencyattentionforbuildingsemanticsegmentation AT zaidalhuda deepnestedustructurenetworkwithfrequencyattentionforbuildingsemanticsegmentation AT dalalalalimi deepnestedustructurenetworkwithfrequencyattentionforbuildingsemanticsegmentation AT yeonghyeongu deepnestedustructurenetworkwithfrequencyattentionforbuildingsemanticsegmentation AT mugahedaalantari deepnestedustructurenetworkwithfrequencyattentionforbuildingsemanticsegmentation |