DEM Densification Using Perspective Shape From Shading Through Multispectral Imagery

Abstract

Although photogrammetry has long been used as the primary method to produce digital elevation models (DEMs), there are still some locations that are not covered by multiangle images because of various limitations. Moreover, traditional interpolation methods for producing denser DEMs often cause oversmoothing, particularly over rough terrain. To formulate a robust procedure that is capable of reconstructing the terrain surface using sparse ground control points in heterogeneous areas, this letter describes an improved spatial enhancement method combining perspective shape from shading (SFS) using a single optical image. This method is called SFS-based densification using multispectral information (SDMI). First, the image irradiance equation based on the perspective Lambertian model is formulated as a static Hamilton–Jacobi equation and is solved using a fast sweeping strategy. We then reconstruct the relative surface shape and apply an edge-preserved iterative interpolation method to generate a higher resolution DEM grid. Multispectral information is used to reveal the actual surface reflection properties, and the land surface is classified into several types to better estimate surface reflectance. Experiments indicate that SDMI is effective for the interpolation of a sparse grid DEM over heterogeneous terrain.