Vector Mapping Method for Buildings in Remote Sensing Images Based on Joint Semantic-Geometric Learning

An important high-precision building vector mapping method automatically delineates building polygons from high-resolution remote sensing images. Deep learning methods have greatly improved the accuracy of automatic building segmentation in remote sensing images. However, building polygons in vector forms have a compact and regular structured expression effect, which corresponds more with the application requirements of cartography and geographic information systems (GIS). We propose a vector mapping method for buildings in remote sensing images with joint semantic-geometric learning to generate building polygon vectors in remote sensing images automatically. The method, aiming to provide cartography and GIS data sources, consists of three modules: multi-task segmentation, contour regularization, and polygon optimization. To reduce missing extractions and mis-extractions and obtain a complete building segmentation mask, the multitask segmentation module performs joint semantic-geometric learning on three related tasks: building instance detection, pixel-wise contour segmentation, and edge extraction. The regularization module normalizes the segmentation mask expression using geometric constraints and image information, whereas the polygon optimization module combines geometric constraints with deep learning methods to ensure vectorization quality. The experimental results show that the proposed method adapts well to building vector extraction tasks under different scenarios and can generate building vector polygons that match the ground truth labels. This method offers significant advantages in solving problems, such as building polygon irregularity and vertex offset.