Title | ||
---|---|---|
Multiscale Feature Learning by Transformer for Building Extraction From Satellite Images |
Abstract | ||
---|---|---|
Extracting buildings from very high-resolution satellite images is a challenging yet important task for applications such as urban monitoring. Multiscale feature learning proves to be a potential solution toward accurate extraction of buildings. This study exploits a powerful multiscale feature learning module, a hierarchical vision transformer by shifted windows (swin), as a backbone within a building extraction network. To this end, we first designed a general structure for building extraction, consisting of a backbone to extract multiscale features and a head network to fuse and refine features. Then, we integrated swin into the structure as a backbone and utilized channel-wise and spatial-wise enhancement in a head network. Experimental results show that our method achieves improvements regarding both F1-score and intersection over union (IoU) compared to the multiple attending path neural network (MAP-Net), which is the current state-of-the-art (SOTA) algorithm for building extraction from remote sensing images. Our study thus confirms the potential of swin transformers as backbones for semantic segmentation tasks based on satellite images. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/LGRS.2022.3142279 | IEEE GEOSCIENCE AND REMOTE SENSING LETTERS |
Keywords | DocType | Volume |
Feature extraction, Buildings, Transformers, Satellites, Semantics, Windows, Training, Attention, building extraction, satellite remote sensing, semantic segmentation, transformer | Journal | 19 |
ISSN | Citations | PageRank |
1545-598X | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xi Chen | 1 | 333 | 70.76 |
Chunping Qiu | 2 | 0 | 0.68 |
Wenyue Guo | 3 | 0 | 1.01 |
Anzhu Yu | 4 | 0 | 0.68 |
Xiaochong Tong | 5 | 0 | 0.34 |
Michael Schmitt | 6 | 0 | 0.34 |