Pose estimation of landscape images using DEM and orthophotos

In this paper, we propose a methodology for the estimation of the pose of oblique landscape images. Knowledge about the pose is needed for using such images in augmented reality applications or to allow projection of pixels in a GIS for spatial analysis. We propose to estimate the pose using a 30 digital elevation model (OEM) rendered with an ortho-image as reference. Starting from a rough estimation, the pose is refined by exploiting correspondences detected with a local normalized cross-correlation method. Matches are searched between edge features extracted both in the query image and in a synthetic image generated from the DEM and the ortho-image. A RANSAC approach based on the camera model extracts the best matches. Few iterations of the algorithm provide a precise estimation of the pose, leading to a precise georeferencing of the query image. We tested the proposed methodology to images of a popular glacier in the south of Switzerland downloaded from Panoramio.