From Raster Predictions to Vector Layers of Buildings: A Computational Geometry Approach

Learning - based approaches are now typically used to extract building rooftop from overhead imagery. However, converting boundaries of segmented objects from raster format to vector coordinates remains a challenging problem. Using re-cent advances in multi-task learning, we propose a fast and scalable approach, based on a polygonal partitioning of the space and discrete optimization, to deliver accurate and sim-ple vectorized building rooftops, that are compared to those produced by state-of-the-art techniques.