Robust Guided Matching and Multi-layer Feature Detection Applied to High Resolution Spherical Images

Abstract

We present a novel, robust guided matching technique. Given a set of calibrated spherical images along with the associated sparse 3D point cloud, our approach consiste tly finds matches across the images in a multilayer feature detection framework. New feature matches are used to refine existing 3D points or to add reliable ones to the point cloud, therefore improving scene represen tatio . We use real indoor and outdoor scenarios to validate the robustness of the proposed approach. Moreov e , we perform a quantitative evaluation of our technique to demonstrate its effectiveness.