A Matching Algorithm for Lunar Rover Dual-Eye Vision System

Abstract

Firstly make original images to epipolar images without vertical parallax by elements of exterior orientation between two stations. Then, match points on epipolar images gradually by correlation coefficient match, and check the matched points by many rules. Secondly match accurately points by least squares image matching. Finally, establish Delaunay triangulated network between matched points and calculate relation coefficients of overlap regions between epipolar images. The experiment results indicate that the method can finish matching pictures of Lunar Rover quickly and reliably.