A Hierarchical Graph Matching Based Key Point Correspondence Method For Large Distance Rover Localization

Key point correspondence plays a critical role in large distance lunar rover localization and navigation, which can decrease accumulative errors and facilitate the rover to approach probing target accurately. Lunar surface images often contain similar patterns, noisy points and obvious illumination changes, especially along with large distance movement, overlapping regions of image pairs have large deformations and sorely different scales. Traditional appearance based matching methods fail in such conditions as local appearance features become less distinctive. In this paper, we proposed a novel hierarchical graph matching strategy to fully utilize structure property of key points. For vertexes in bigger scale, their neighborhood graphs in smaller scale are regarded as vertex labels and the differences of neighborhood graphs are regarded as differences of vertexes. Based on the new strategy, both global and local constraint are considered such that the dependency on local appearance is alleviated. Furthermore, an active key point detection method is proposed to serve the graph matching method for better performance. Finally, several experiments are conducted on lunar surface images collected by Chang'E-3 rover, which demonstrates the robustness and effectiveness of the proposed method.