GKNet: Graph-based Keypoints Network for Monocular Pose Estimation of Non-cooperative Spacecraft

TL;DR

GKNet is a novel graph-based keypoints network designed for accurate monocular pose estimation of non-cooperative spacecraft, addressing challenges like symmetry and occlusion, validated on a new comprehensive dataset.

Contribution

Introduces GKNet, a graph-based keypoints detection method, and SKD, a new dataset for spacecraft keypoint detection, improving pose estimation accuracy.

Findings

GKNet outperforms existing keypoint detectors in accuracy.

The SKD dataset provides extensive data for spacecraft keypoint detection.

Extensive experiments validate the effectiveness of GKNet.

Abstract

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.