Machine-learned 3D Building Vectorization from Satellite Imagery
This work addresses the need for efficient 3D building modeling in geospatial applications, representing an incremental improvement over existing methods.
The paper tackles the problem of automatic 3D building reconstruction and vectorization from satellite imagery by using a machine learning approach that refines building shapes with a cGAN, detects roof features via semantic segmentation, and applies vectorization algorithms, achieving state-of-the-art performance on large-scale datasets.
We propose a machine learning based approach for automatic 3D building reconstruction and vectorization. Taking a single-channel photogrammetric digital surface model (DSM) and panchromatic (PAN) image as input, we first filter out non-building objects and refine the building shapes of input DSM with a conditional generative adversarial network (cGAN). The refined DSM and the input PAN image are then used through a semantic segmentation network to detect edges and corners of building roofs. Later, a set of vectorization algorithms are proposed to build roof polygons. Finally, the height information from the refined DSM is added to the polygons to obtain a fully vectorized level of detail (LoD)-2 building model. We verify the effectiveness of our method on large-scale satellite images, where we obtain state-of-the-art performance.