No abstract

No abstract

No abstract

No abstract

Building extraction plays an important role in highresolution remote sensing image processing, which can be used as the basis for urban planning and demographic analysis. In recent years, many powerful general semantic segmentation models have emerged, but these models often perform poorly when transferred to remote sensing images because of the characteristics of remote sensing images. To this end, we propose a new deep learning network called Selective Non-Local ResUNeXt++ (SNLRUX++) for building extraction. Firstly, the cascaded multi-scale feature fusion is proposed to transform the high-performance image classification network ResNeXt into the segmentation network ResUNeXt++. Secondly, selective non-local operation is designed to establish long-range dependencies while avoiding introducing excessive noise and computational effort. Finally, multi-scale prediction is applied as deep supervision to accelerate training and convergence, and improves prediction performance of objects at different scales. The experimental results on two different remote sensing image datasets show the effectiveness and generalization ability of the proposed method.