Extracting buildings from high-resolution remote sensing imagery (HRSI) is of great significance to emergency management, land resource utilization and analysis, as well as city planning and construction. However, due to the complex backgrounds and diverse appearances and different sizes of buildings in HRSI, most existing methods for automatic building extraction are difficult to obtain strong building feature representation from low-level and high-level features. Furthermore, existing research mainly focused on regional accuracy, while less attention was paid to the description of building boundaries. In this paper, MSB-Net, an end-to-end neural network, is proposed to address these issues. A multi-scale feature fusion module (MSFFM) is designed to capture and fuse multi-scale features. A local branch (LB) constructed by the MSFFM and position attention, is used to obtain long range of context information between different positions and extract the essential features of buildings (e.g., shapes, edges) from low-level features. And a global branch (GB) is designed to use the MSFFM and channel attention to enhance high-level features. Therefore, our method can not only obtain information on building-related attribute categories, but also capture the rich context information in channel dimensions. The boundary enhancement and completion module (BECM) take the output of the GB and LB as input to search for the missing parts and details of buildings to improve the segmentation accuracy and boundary quality. Our method is tested on two public building datasets and achieves superior classification performance.
Index Terms-multi-scale feature fusion, boundary enhancement, building extraction
I. INTRODUCTIONxtracting buildings from high-resolution remote sensing imagery (HRSI) can be of great help in various fields, including emergency management, land resource utilization, city planning and construction [1],[2], [3] and so on. With the improvement of HRSI data quality Th is paragraph of the first footnote will contain the date on which you submitted your paper for review, which is populated by IEEE. It is IEEE style to display support information, including sponsor and financial support acknowledgment, here and not in an acknowledgment section at the end of the article. For example, "This work was supported in part by the U.S. Department of Commerce under Grant 123456." The name of the corresponding author appears after the financial information, e.g.