Automated LoD-2 Model Reconstruction from Very-HighResolution Satellite-derived Digital Surface Model and Orthophoto
This addresses the problem of efficient 3D urban modeling for applications like urban planning, but it is incremental, building on existing methods with refinements.
The paper tackles automated reconstruction of Level of Detail 2 (LoD-2) building models from satellite data by proposing a model-driven method that decomposes complex building polygons into elementary rectangles and fits 3D models, achieving high-quality results as evaluated on diverse urban datasets.
In this paper, we propose a model-driven method that reconstructs LoD-2 building models following a "decomposition-optimization-fitting" paradigm. The proposed method starts building detection results through a deep learning-based detector and vectorizes individual segments into polygons using a "three-step" polygon extraction method, followed by a novel grid-based decomposition method that decomposes the complex and irregularly shaped building polygons to tightly combined elementary building rectangles ready to fit elementary building models. We have optionally introduced OpenStreetMap (OSM) and Graph-Cut (GC) labeling to further refine the orientation of 2D building rectangle. The 3D modeling step takes building-specific parameters such as hip lines, as well as non-rigid and regularized transformations to optimize the flexibility for using a minimal set of elementary models. Finally, roof type of building models s refined and adjacent building models in one building segment are merged into the complex polygonal model. Our proposed method has addressed a few technical caveats over existing methods, resulting in practically high-quality results, based on our evaluation and comparative study on a diverse set of experimental datasets of cities with different urban patterns.