Rotation and affine invariant accurate feature selection and matching method for RGBD images

Abstract

This paper introduced a novel affine, rotation invariant filtering feature matching model based on RGB and geometric-based images. The proposed model was implemented based on summation of epipolar distance of angles, scale estimation based on intensity gradients, and normal vector estimation by using geometric data. Since of former ordering, our method is affine and rotation invariant which provides robustness to our method. Comparable experiments with well stabilized descriptors such as BRAND, MSER, ORB, BRISK with our method. Our method achieved improved results under texture, geometry and a combination of both information.