PDAA: An End-to-End Polygon Dynamic Adjustment Algorithm for Building Footprint Extraction
Buildings are a significant component of urban space and are essential to smart cities, catastrophe monitoring, and land use planning. However, precisely extracting building polygons from remote sensing images remains difficult because of the variety of building designs and intricate backgrounds. Th...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/14/2495 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849732916243857408 |
|---|---|
| author | Longjie Luo Jiangchen Cai Bin Feng Liufeng Tao |
| author_facet | Longjie Luo Jiangchen Cai Bin Feng Liufeng Tao |
| author_sort | Longjie Luo |
| collection | DOAJ |
| description | Buildings are a significant component of urban space and are essential to smart cities, catastrophe monitoring, and land use planning. However, precisely extracting building polygons from remote sensing images remains difficult because of the variety of building designs and intricate backgrounds. This paper proposes an end-to-end polygon dynamic adjustment algorithm (PDAA) to improve the accuracy and geometric consistency of building contour extraction by dynamically generating and optimizing polygon vertices. The method first locates building instances through the region of interest (RoI) to generate initial polygons, and then uses four core modules for collaborative optimization: (1) the feature enhancement module captures local detail features to improve the robustness of vertex positioning; (2) the contour vertex tuning module fine-tunes vertex coordinates through displacement prediction to enhance geometric accuracy; (3) the learnable redundant vertex removal module screens key vertices based on a classification mechanism to eliminate redundancy; and (4) the missing vertex completion module iteratively restores missed vertices to ensure the integrity of complex contours. PDAA dynamically adjusts the number of vertices to adapt to the geometric characteristics of different buildings, while simplifying the prediction process and reducing computational complexity. Experiments on public datasets such as WHU, Vaihingen, and Inria show that PDAA significantly outperforms existing methods in terms of average precision (AP) and polygon similarity (PolySim). It is at least 2% higher than existing methods in terms of average precision (AP), and the generated polygonal contours are closer to the real building geometry. Values of 75.4% AP and 84.9% PolySim were achieved on the WHU dataset, effectively solving the problems of redundant vertices and contour smoothing, and providing high-precision building vector data support for scenarios such as smart cities and emergency response. |
| format | Article |
| id | doaj-art-febcaae7d125414bae92ce5748d7e2a1 |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-febcaae7d125414bae92ce5748d7e2a12025-08-20T03:08:10ZengMDPI AGRemote Sensing2072-42922025-07-011714249510.3390/rs17142495PDAA: An End-to-End Polygon Dynamic Adjustment Algorithm for Building Footprint ExtractionLongjie Luo0Jiangchen Cai1Bin Feng2Liufeng Tao3Collaborative Innovation Center of Geo-Information Technology for Smart Central Plains, Zhengzhou 450046, ChinaSchool of Computer Science, China University Geoscience, Wuhan 430074, ChinaSchool of Computer Science, China University Geoscience, Wuhan 430074, ChinaCollaborative Innovation Center of Geo-Information Technology for Smart Central Plains, Zhengzhou 450046, ChinaBuildings are a significant component of urban space and are essential to smart cities, catastrophe monitoring, and land use planning. However, precisely extracting building polygons from remote sensing images remains difficult because of the variety of building designs and intricate backgrounds. This paper proposes an end-to-end polygon dynamic adjustment algorithm (PDAA) to improve the accuracy and geometric consistency of building contour extraction by dynamically generating and optimizing polygon vertices. The method first locates building instances through the region of interest (RoI) to generate initial polygons, and then uses four core modules for collaborative optimization: (1) the feature enhancement module captures local detail features to improve the robustness of vertex positioning; (2) the contour vertex tuning module fine-tunes vertex coordinates through displacement prediction to enhance geometric accuracy; (3) the learnable redundant vertex removal module screens key vertices based on a classification mechanism to eliminate redundancy; and (4) the missing vertex completion module iteratively restores missed vertices to ensure the integrity of complex contours. PDAA dynamically adjusts the number of vertices to adapt to the geometric characteristics of different buildings, while simplifying the prediction process and reducing computational complexity. Experiments on public datasets such as WHU, Vaihingen, and Inria show that PDAA significantly outperforms existing methods in terms of average precision (AP) and polygon similarity (PolySim). It is at least 2% higher than existing methods in terms of average precision (AP), and the generated polygonal contours are closer to the real building geometry. Values of 75.4% AP and 84.9% PolySim were achieved on the WHU dataset, effectively solving the problems of redundant vertices and contour smoothing, and providing high-precision building vector data support for scenarios such as smart cities and emergency response.https://www.mdpi.com/2072-4292/17/14/2495building footprint extractionpolygon dynamic adjustmentvertex optimizationremote sensing images |
| spellingShingle | Longjie Luo Jiangchen Cai Bin Feng Liufeng Tao PDAA: An End-to-End Polygon Dynamic Adjustment Algorithm for Building Footprint Extraction Remote Sensing building footprint extraction polygon dynamic adjustment vertex optimization remote sensing images |
| title | PDAA: An End-to-End Polygon Dynamic Adjustment Algorithm for Building Footprint Extraction |
| title_full | PDAA: An End-to-End Polygon Dynamic Adjustment Algorithm for Building Footprint Extraction |
| title_fullStr | PDAA: An End-to-End Polygon Dynamic Adjustment Algorithm for Building Footprint Extraction |
| title_full_unstemmed | PDAA: An End-to-End Polygon Dynamic Adjustment Algorithm for Building Footprint Extraction |
| title_short | PDAA: An End-to-End Polygon Dynamic Adjustment Algorithm for Building Footprint Extraction |
| title_sort | pdaa an end to end polygon dynamic adjustment algorithm for building footprint extraction |
| topic | building footprint extraction polygon dynamic adjustment vertex optimization remote sensing images |
| url | https://www.mdpi.com/2072-4292/17/14/2495 |
| work_keys_str_mv | AT longjieluo pdaaanendtoendpolygondynamicadjustmentalgorithmforbuildingfootprintextraction AT jiangchencai pdaaanendtoendpolygondynamicadjustmentalgorithmforbuildingfootprintextraction AT binfeng pdaaanendtoendpolygondynamicadjustmentalgorithmforbuildingfootprintextraction AT liufengtao pdaaanendtoendpolygondynamicadjustmentalgorithmforbuildingfootprintextraction |