Non-Cooperative Spacecraft Pose Estimation Based on Feature Point Distribution Selection Learning

To address the limitations of inadequate real-time performance and robustness encountered in estimating the pose of non-cooperative spacecraft during on-orbit missions, a novel method of feature point distribution selection learning is proposed. This approach utilizes a non-coplanar key point selection network with uncertainty prediction, pioneering in its capability to accurately estimate the pose of non-cooperative spacecraft, thereby representing a significant advancement in the field. Initially, the feasibility of designing a non-coplanar key point selection network was analyzed based on the influence of sensor layout on the pose measurement. Subsequently, the key point selection network was designed and trained, leveraging images extracted from the spacecraft detection network. The network detected 11 pre-selected key points with distinctive features and was able to accurately predict their uncertainties and relative positional relationships. Upon selection of the key points exhibiting low uncertainty and non-coplanar relative positions, we utilized the EPnP algorithm to achieve accurate pose estimation of the target spacecraft. Our experimental evaluation on the SPEED dataset, which comes from the International Satellite Attitude Estimation Competition, validates the effectiveness of our key point selection network, significantly enhancing estimation accuracy and timeliness compared to other monocular spacecraft attitude estimation methods. This advancement provides robust technological support for spacecraft guidance, control, and proximity operations in orbital service missions.