GKNet: Graph-based Keypoints Network for Monocular Pose Estimation of Non-cooperative Spacecraft
This work addresses a domain-specific problem for spacecraft on-orbit servicing, with incremental improvements in keypoint detection for pose estimation.
The paper tackles the problem of monocular pose estimation for non-cooperative spacecraft, which is crucial for on-orbit services, by proposing GKNet, a graph-based keypoints network that improves accuracy under structural symmetry and partial occlusion, achieving high accuracy compared to state-of-the-art methods.
Monocular pose estimation of non-cooperative spacecraft is significant for on-orbit service (OOS) tasks, such as satellite maintenance, space debris removal, and station assembly. Considering the high demands on pose estimation accuracy, mainstream monocular pose estimation methods typically consist of keypoint detectors and PnP solver. However, current keypoint detectors remain vulnerable to structural symmetry and partial occlusion of non-cooperative spacecraft. To this end, we propose a graph-based keypoints network for the monocular pose estimation of non-cooperative spacecraft, GKNet, which leverages the geometric constraint of keypoints graph. In order to better validate keypoint detectors, we present a moderate-scale dataset for the spacecraft keypoint detection, named SKD, which consists of 3 spacecraft targets, 90,000 simulated images, and corresponding high-precise keypoint annotations. Extensive experiments and an ablation study have demonstrated the high accuracy and effectiveness of our GKNet, compared to the state-of-the-art spacecraft keypoint detectors. The code for GKNet and the SKD dataset is available at https://github.com/Dongzhou-1996/GKNet.