Review of Pose Estimation Methods for Spacecraft Targets

doi:10.3969/j.issn.1671-0940.2025.01.008

Abstract

Abstract: Pose estimation of spacecraft targets is a key technology for achieving space operation tasks, such as the cleaning of failed satellites and the detection and scanning of non-cooperative targets. This paper reviews the target pose estimation methods based on image feature extraction and PnP, the target estimation methods based on registration, and the spacecraft target pose estimation methods based on deep learning, and introduces the corresponding research methods.

Key words: spacecraft, pose estimation, non-cooperative targets, feature extraction, deep learning

LI Shoucheng, LI Jing, CHEN Qiang, LI Xindong, WANG Junzheng. Review of Pose Estimation Methods for Spacecraft Targets[J]. AEROSPACE CHINA, 2025, 26(1): 53-58.

References

[1] Bay H, Ess A, Tuytelaars T, et al.Speeded-up robust features (SURF)[J]. Computer vision and image understanding, 2008, 110(3): 346-359.
[2] Rublee E, Rabaud V, Konolige K, et al.ORB: An efficient alternative to SIFT or SURF[C]. 2011 International Conference on Computer Vision. IEEE, 2011: 2564-2571.
[3] Von Gioi R G, Jakubowicz J, Morel J M, et al. LSD: A line segment detector[J]. Image Processing, 2012, 2: 35-55.
[4] ZHUANG S, ZOU D, PEI L, et al.A binary robust line descriptor[C]. International Conference on Indoor Positioning and Indoor Navigation. IEEE, 2016: 4-7.
[5] LI R, ZHOU Y, CHEN F, CHEN Y. Parallel vision-based pose estimation for non-cooperative spacecraft[J]. Advances in Mechanical Engineering, 2015:7(7)1-9.
[6] Sharma S, Ventura J, D’Amico S. Robust model-based monocular pose initialization for noncooperative spacecraft rendezvous[J]. Journal of Spacecraft and Rockets, 2018, 55(6): 1414-1429.
[7] HE M X.Research on simulation system for detection, tracking and capture of faulty spacecraft[D]. Master’s Thesis of Harbin Institute of Technology, 2021.
[8] DEND Z M.Spatial Target Reconstruction and pose estimation based on multi-view vision[D]. Master’s Thesis of Harbin Institute of Technology, 2023.
[9] CHEN R X.Research on binocular stereo vision target pose estimation method based on coplanar constraint[D]. Master’s Thesis of Tianjin University, 2020.
[10] ZHOU S J.Edge matching and relative pose estimation based on the movement of the target virtual model[D]. Master’s Thesis of University of Chinese Academy of Sciences, 2022.
[11] YANG N.Monocular vision pose estimation for the final approach phase of on-orbit spacecraft services[D]. Master’s Thesis of Nanjing University of Aeronautics and Astronautics, 2020.
[12] ZHANG J M.Pose estimation of non-cooperative target spacecraft based on deep learning [D]. Master’s Thesis of Chang’an University, 2024.
[13] WANG G L.Pose measurement method for non-cooperative spacecraft based on neural network [D]. Master’s Thesis of Harbin Institute of Technology, 2021.
[14] CHEN R A.Pose measurement method for non-cooperative target spacecraft based on domain adaptation [D]. Master’s Thesis of Harbin Institute of Technology, 2023.
[15] NAN X T.Research on small sample recognition and pose estimation algorithms for space targets based on deep learning [D]. Master’s Thesis of Xidian University, 2020.
[16] Lepetit V, Moreno-Noguer F, Fua P.EP n P: An accurate O (n) solution to the P n P problem[J]. International journal of computer vision, 2009, 81: 155-166.
[17] KNEIP L, LI H, SEO Y.UPnP: An Optimal O(n) Solution to the Absolute Pose Problem with Universal Applicability[C]. Computer Vision - ECCV. 2014.
[18] Mehralian M A, Soryani M.EKFPnP: extended Kalman filter for camera pose estimation in a sequence of images[J]. IET Image Processing, 2020, 14(15), 3774-3780.
[19] ZHOU H, ZHANG T, Jagadeesan, J.Re-weighting and 1-point RANSAC-Based PnP solution to handle outliers[J]. IEEE transactions on pattern analysis and machine intelligence, 2018, 41(12), 3022-3033.
[20] ZENG G, CHEN S, MU B, et al.Cpnp: Consistent pose estimator for perspective-n-point problem with bias elimination[C]. In 2023 IEEE International Conference on Robotics and Automation (ICRA), IEEE, 2023: 1940-1946.
[21] LIN Y Z.Pose estimation of spacecraft based on monocular RGB images[D]. Master’s Thesis of Zhejiang University, 2023.
[22] YUAN H, CHEN H, WU J, et al.Non-cooperative spacecraft pose estimation based on feature point distribution selection learning[J]. Aerospace, 2004, 11(7), 526.
[23] GUO W, HU W, LIU C.Improving ICP precision for spacecraft pose estimation[C]. In Advances in Guidance, Navigation and Control: Proceedings of 2020 International Conference on Guidance, Tianjin, China, 2020: 653-664.
[24] ZHU Y C.Research on relative pose measurement of non-cooperative targets based on SLAM[D]. Master’s Thesis of Harbin Institute of Technology, 2018.
[25] YANG Y.Spatial position and pose estimation and spacecraft identification based on lidar detection [D]. Master’s Thesis of Huazhong University of Science and Technology, 2021.
[26] FEND J Q, YANG Z G, ZHANG Z, et al.Point cloud model reconstruction and pose estimation of non-cooperative spacecraft without feature extraction[J]. Acta Optica Sinica, 2025, 45(7): 0712004-9.
[27] SHARMA S, D’Amico S. Pose estimation for non-cooperative rendezvous using neural networks[J]. arXiv preprint arXiv:1906.09868, 2019.
[28] LI D T.Visual pose estimation of non-cooperative targets and model predictive control for rendezvous and docking[D]. Master’s Thesis of Harbin Institute of Technology, 2020.
[29] PROENÇA P F, GAO Y. Deep learning for spacecraft pose estimation from photorealistic rendering[C]. 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020: 6007-6013.
[30] WANG Y J, YE R D, D X J. Spacecraft pose estimation network based on improved PoseNet[J]. Journal of Space Engineering University, 2025, 2(2): 32-39.
[31] LIU J H.Research on end-to-end non-cooperative target pose estimation method based on deep learning[D]. Master’s Thesis of University of Chinese Academy of Sciences, 2024.
[32] DOU K Y.Research on space target pose estimation method based on deep learning[J]. Master’s Thesis of North University of China, 2023.
[33] ZHAO H L.Research on monocular vision pose estimation method for non-cooperative spacecraft based on data-driven[D]. Doctoral Thesis of Harbin Institute of Technology, 2022.
[34] WEN Y, FU H, DEND Y, et al.FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects[C]. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
[35] ZHUANG C, LI S, DING H.Instance segmentation based 6D pose estimation of industrial objects using point clouds for robotic bin-picking[J]. Robotics and Computer-Integrated Manufacturing, 2023, 82: 102541.

ISSN 1671-0940

CN 11-4673/V