Geometric Overpass Extraction from Vector Road Data and DSMs

We present a method to extract elevated road structures, typically overpassing other roads, transit lines, and watercourses. The technique uses a digital surface model (DSM) and roughly aligned vector road data and outputs geometry approximating the shape and elevation of the elevated road deck. Our method is robust against noise in DSM elevations and can recover elevated roads partially obscured by trees and other overpasses. We demonstrate our method parallelized over city-wide DSMs, and formulate a confidence metric ranking the fidelity of the reconstruction.

• Machine Perception