Using Orthophoto for Building Boundary Sharpening in the Digital Surface Model

TL;DR

This paper introduces a method to improve building boundary accuracy in digital surface models by using orthophoto-derived line segments to refine results from semi-global matching stereo algorithms.

Contribution

It proposes two novel post-processing techniques utilizing orthophoto information to sharpen building boundaries in DSMs generated by SGM, addressing smoothing issues at depth discontinuities.

Findings

The methods effectively sharpen building boundaries in DSMs.

Experimental results demonstrate robustness across satellite datasets.

The approach improves boundary accuracy without extensive additional data.

Abstract

Nowadays dense stereo matching has become one of the dominant tools in 3D reconstruction of urban regions for its low cost and high flexibility in generating dense 3D points. However, state-of-the-art stereo matching algorithms usually apply a semi-global matching (SGM) strategy. This strategy normally assumes the surface geometry pieceswise planar, where a smooth penalty is imposed to deal with non-texture or repeating-texture areas. This on one hand, generates much smooth surface models, while on the other hand, may partially leads to smoothing on depth discontinuities, particularly for fence-shaped regions or densely built areas with narrow streets. To solve this problem, in this work, we propose to use the line segment information extracted from the corresponding orthophoto as a pose-processing tool to sharpen the building boundary of the Digital Surface Model (DSM) generated by SGM. Two methods which are based on graph-cut and plane fitting are proposed and compared. Experimental results on several satellite datasets with ground truth show the robustness and effectiveness of the proposed DSM sharpening method.