TY - JOUR
T1 - SR-net
T2 - satellite relative pose estimation network for a noncooperative target via RGB images
AU - Su, Di
AU - Zhang, Cheng
AU - Chen, Zhisheng
AU - Ji, Ruijing
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
PY - 2023/8
Y1 - 2023/8
N2 - Space exploration has drawn increasing attention to space control technology. For debris removal missions and on-orbit servicing, accurate pose estimation of a noncooperative target is critical. This article introduces the satellite relative pose estimation network (SR-Net) two-stage training method for a noncooperative target via RGB images. As the first stage in regressing the 3D translation, we combined the detection and translation regression modules into a single model. SR-Net decouples the translation and rotation information in stage two by utilizing classification instead of regression, using the detected picture as input and fitting a rotation by minimizing the weighted least squares. Furthermore, a large-scale dataset for 6-DoF pose estimation is introduced, which can be utilized as a benchmark for various state-of-the-art monocular vision-based 6-DoF pose estimation methods. Ablation studies are used to verify the effectiveness and scalability of each module. SR-Net can be added to a baseline model as a separate module to improve the 6-DoF pose estimation accuracy for noncooperative targets. The results are extremely encouraging since they show that using only vision data, it is feasible to accurately estimate the 6-DoF pose of a noncooperative target.
AB - Space exploration has drawn increasing attention to space control technology. For debris removal missions and on-orbit servicing, accurate pose estimation of a noncooperative target is critical. This article introduces the satellite relative pose estimation network (SR-Net) two-stage training method for a noncooperative target via RGB images. As the first stage in regressing the 3D translation, we combined the detection and translation regression modules into a single model. SR-Net decouples the translation and rotation information in stage two by utilizing classification instead of regression, using the detected picture as input and fitting a rotation by minimizing the weighted least squares. Furthermore, a large-scale dataset for 6-DoF pose estimation is introduced, which can be utilized as a benchmark for various state-of-the-art monocular vision-based 6-DoF pose estimation methods. Ablation studies are used to verify the effectiveness and scalability of each module. SR-Net can be added to a baseline model as a separate module to improve the 6-DoF pose estimation accuracy for noncooperative targets. The results are extremely encouraging since they show that using only vision data, it is feasible to accurately estimate the 6-DoF pose of a noncooperative target.
KW - CNN
KW - Noncooperative target
KW - Object detection
KW - Pose estimation
KW - Weighted least squares
UR - http://www.scopus.com/inward/record.url?scp=85150360312&partnerID=8YFLogxK
U2 - 10.1007/s11042-023-14791-6
DO - 10.1007/s11042-023-14791-6
M3 - Article
AN - SCOPUS:85150360312
SN - 1380-7501
VL - 82
SP - 31557
EP - 31573
JO - Multimedia Tools and Applications
JF - Multimedia Tools and Applications
IS - 20
ER -