부산대학교 도서관

Building extraction from satellite images has been a hot research topic in the field of remote-sensing image analysis. Most of the related studies are focusing on urban areas with dense populations, while solutions for underpopulated mountainous areas are still missing. Given the scarcity of research materials, it is still an important topic for applications like mountain hazard damage management. To fill this gap, we present a new dataset for scattered mountainous area building segmentation, consisting of the manual labels and the coordinates of latitude and longitude for 2125 satellite images of 303 diverse human settlements in the mountainous areas of southwest China. Compared with the public remote-sensing image datasets, our dataset is very challenging with relatively low resolution (2.2 m/pixel) and small-object, blurry-boundary, and high-imbalance features. In this letter, we propose a novel copy-fusion (CF) data augmentation strategy and designed a VGG-16+U-Net with dice focal loss to address the difficulties in this building extraction task. Experimental results have shown that our approach has achieved 81.79% mean intersection over union (IoU) and outperformed the baseline building segmentation methods like HRNet, DeeplabV3+, and U-net+ResNet by 6.29%. Our dataset and model will be available at https://github.com/AngCV/SMAB_DATASET.