Crater matching algorithm based on feature descriptor

Abstract

In the field of visual navigation, crater is an ideal navigation landmark on planet surface, because of its universality and significance. During the descent phase of lander, crater needs to be extracted and matched. However, as the landing proceeds, images taken by the on-board camera will change, such as the variation of scale, translation, rotation, illumination which will increase the difficulty of the matching algorithm.This paper proposes a more accurate and faster crater matching algorithm based on feature descriptor. This algorithm is designed for navigation during the descending phase. It has the invariance of scaling, rotation, illumination. First, this algorithm extracts circular arc by Gaussian Pyramid and ELSD algorithm, so that this algorithm has the invariance against scale variation. Then, in order to describe the circular arc, this algorithm determine the direction of the circular arc by the direction histogram. And this algorithm constructs the circular arc band descriptors in the support region to achieve translation, rotation and illumination invariance. At last, matching criteria is the combination of the Nearest Neighbor Distance Ratio (NNDR) and the Euclidean distance constraint. The results are obtained under different image variations. The matching results show that this crater matching algorithm has high crater correct extracting and matching rate and high computationally efficient.