Database construction for vision aided navigation in planetary landing

In this paper, a novel database construction method for passive-image based navigation system within the planetary precise pin-point landing (PPL) background is presented. The key concept is selecting qualified visual features to construct the visual database by examining their contribution to the navigation system. We first define a metric named feature exploitability to evaluate the visual feature's distinctiveness and its spatial imagery distribution. After that, a greedy selection method is employed to construct the database by selecting features with high feature-exploitability scores. Then, a hierarchical feature retrieval method is proposed to achieve the adaptation of image-scale variation during landing and improve the efficiency of feature retrieval. To evaluate our proposed approach, the Monte Carlo simulation and an experimental test are conducted, simulation results show the advantage of the feature exploitability driven database construction method over other database construction methods and the necessity of proper database construction in a vision-aided navigation system for PPL mission.