Accurate Camera Registration in Urban Environments Using High-Level Feature Matching

We propose a method for accurate camera pose estimation in urban environments from single images and 2D maps made of the surrounding buildings’ outlines. Our approach bridges the gap between learning-based approaches and geometric approaches: We use recent semantic segmentation techniques for extracting the buildings’ edges and the façades’ normals in the images and minimal solvers [14] to compute the camera pose accurately and robustly. We propose two such minimal solvers: one based on three correspondences of buildings’ corners from the image and the 2D map and another one based on two corner correspondences plus one façade correspondence. We show on a challenging dataset that, compared to recent state-of-the-art [1], this approach is both, faster and more accurate.