Robust Model-Based Monocular Pose Initialization for Noncooperative Spacecraft Rendezvous
Abstract
This work addresses the design and validation of a robust monocular vision-based pose initialization architecture for close-range onorbit-servicing and formation-flying applications. The aim is to rapidly determine the pose of a passive space resident object using its known three-dimensional wireframe model and a single low-resolution two-dimensional image collected on board the servicer spacecraft. In contrast to previous works, the proposed architecture is onboard executable and capable of estimating the pose of the client without the use of fiducial markers and without any a priori range measurements or state information. A novel feature detection method based on the filtering of the weak image gradients is used to identify the true edges of the client in the image, even in presence of the Earth in background. The detected features are synthesized using simple geometric constraints to dramatically reduce the search space of the feature correspondence problem, which is solved using the method. This approach is proven to be an order of magnitude faster than the state-of-the-art random sample consensus methods. A fast Newton–Raphson method that minimizes the fit error between corresponding image and model features is employed to refine the pose estimate and to resolve pose ambiguity. The proposed methodology is tested using actual space imagery collected during the PRISMA mission at about a 700 km altitude and a 10 m interspacecraft separation.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Sharma et al.'s conventional image-processing method can only detect 20% of the images and takes a long time to develop 3D-2D correspondence.
“This method can only detect 20% of the images and takes a long time to develop 3D-2D correspondence.”
From Transformer Network-Aided Relative Pose Estimation for Non-cooperative Spacecraft Using Vision Sensor (2024) · cites this paper as [13]
Our work has performed better than [13,16,31] in translation and rotational errors.
“Our work has performed better than [13,16,31] in translation and rotational errors.”
From Transformer Network-Aided Relative Pose Estimation for Non-cooperative Spacecraft Using Vision Sensor (2024) · cites this paper as [13]
Sharma et al. [13] uses a conventional key points detection method that can only provide 20% of the solution due to this issue.
“The work proposed by Sharma et al. [13] uses a conventional key points detection method that can only provide 20% of the solution due to this issue.”
From Transformer Network-Aided Relative Pose Estimation for Non-cooperative Spacecraft Using Vision Sensor (2024) · cites this paper as Sharma et al. [13]
The WGE method returned a much higher robustness with respect to Earth in the background compared to the other methods.
“the WGE method returned a much higher robustness with respect to Earth in the background compared to the other methods.”
From Review of the robustness and applicability of monocular pose estimation systems for relative navigation with an uncooperative spacecraft (2019) · cites this paper as [9]
Capuano et al. demonstrated robustness of their IP with respect to Earth in the background by including a background removal step similar to the WGE in [9], using a Prewitt operator with a gradient filter.
“By including a background removal step sim-330 ilar to the WGE in [9], which makes use of a Prewitt operator in combination with a gradient filter, the authors could also demonstrate the robustness of their IP with respect to the Earth in the background.”
From Review of the robustness and applicability of monocular pose estimation systems for relative navigation with an uncooperative spacecraft (2019) · cites this paper as [9]
Sharma et al. [9] proved that the EPnP method has the highest success rate and offers superior performance in both pose accuracy and runtime when compared with other state-of-the-art PnP solvers.
“In a recent effort, Sharma et al. [9] further 395 proved that the EPnP method has the highest success rate and offers a superior performance in terms of both pose accuracy and runtime when compared with other state-of-the-art PnP solvers.”
From Review of the robustness and applicability of monocular pose estimation systems for relative navigation with an uncooperative spacecraft (2019) · cites this paper as [9]
Recent advancements in IP algorithms based on corners/edges detection showed an improvement in robustness with respect to Earth in the background.
“On the other hand, the recent advancements in the IP algorithms based on corners/edges detection showed an improvement in the robustness of such methods with respect to the Earth in the background [9].”
From Review of the robustness and applicability of monocular pose estimation systems for relative navigation with an uncooperative spacecraft (2019) · cites this paper as [9]
The system proposed in [9] is robust to image background due to the WGE.
“The proposed system is in fact robust to the background of the 440 images due to the WGE”
From Review of the robustness and applicability of monocular pose estimation systems for relative navigation with an uncooperative spacecraft (2019) · cites this paper as [9]
The pose estimation scheme proposed in [9] is a good candidate for pose initialization because its IP system is robust and it has been tested for several illumination conditions and with the Earth in the background.
“From the comparison, it can be concluded that the pose estimation scheme proposed in [9] is a good candidate for the pose initialization, given the robustness of its IP system and the fact that it has been tested for several illumination conditions as well as with the Earth in the background.”
From Review of the robustness and applicability of monocular pose estimation systems for relative navigation with an uncooperative spacecraft (2019) · cites this paper as [9]
Monocular navigation ensures rapid pose determination under low power and mass requirements.
“However, systems based solely on monocular cameras are currently being investigated given the fact that monocular navigation ensures rapid pose determination under low power and mass requirements [9]”
From Review of the robustness and applicability of monocular pose estimation systems for relative navigation with an uncooperative spacecraft (2019) · cites this paper as [9]
The limited amount of realistic space images available in [15], [24] and [9] could not represent all challenging orbital scenarios for which a specific camera-target-Sun-Earth geometry would affect pose estimation accuracy.
“Also, the limited amount of realistic space images available in [15], [24] and [9] could not represent all the 450 challenging orbital scenarios for which a specific camera-target-Sun-Earth geometry would affect the pose estimation accuracy.”
From Review of the robustness and applicability of monocular pose estimation systems for relative navigation with an uncooperative spacecraft (2019) · cites this paper as [9]
The system proposed in [9] is computationally efficient.
“and it is computationally efficient.”
From Review of the robustness and applicability of monocular pose estimation systems for relative navigation with an uncooperative spacecraft (2019) · cites this paper as [9]
The system proposed in [9] requires no a-priori knowledge of the target spacecraft's pose.
“it requires no a-priori knowledge of the target spacecraft's pose, and it is computationally efficient.”
From Review of the robustness and applicability of monocular pose estimation systems for relative navigation with an uncooperative spacecraft (2019) · cites this paper as [9]
The IP algorithm in [9] is robust with respect to Earth in the background when Earth's horizon is not in the FoV.
“Robust when Earth's horizon”
From Review of the robustness and applicability of monocular pose estimation systems for relative navigation with an uncooperative spacecraft (2019) · cites this paper as [9]
Spacecraft pose estimation networks are exclusively trained on synthetic images because acquiring large sets of real images is difficult.
“Due to the difficulty of acquiring large sets of real images, spacecraft pose estimation networks are exclusively trained on synthetic ones.”
From Domain Generalization for In-Orbit 6D Pose Estimation (2025) · cites this paper as [18]
Synthetic spacecraft images do not capture the illumination conditions encountered in orbit.
“because those images do not capture the illumination conditions encountered in orbit”
From Domain Generalization for In-Orbit 6D Pose Estimation (2025) · cites this paper as [18]
Pose estimation networks trained on synthetic images face a domain gap and do not generalize to real images.
“Due to these mismatches between the synthetic and real domains, those solutions encounter significant generalization issues.”
From Domain Generalization for In-Orbit 6D Pose Estimation (2025) · cites this paper as [18]
Cites
A Computational Approach to Edge Detection
Canny, J. (1986) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.1986.4767851 · Cited by 30,004 · see citing works
Fischler, M. A., & Bolles, R. C. (1981) · Communications of the ACM · doi:10.1145/358669.358692 · Cited by 25,893 · see citing works
A Combined Corner and Edge Detector
Harris, C., & Stephens, M. (1988) · Procedings of the Alvey Vision Conference 1988 · doi:10.5244/c.2.23 · Cited by 12,901 · see citing works
Use of the hough transformation to detect lines and curves in pictures
Duda, R. O., & Hart, P. E. (1972) · Communications of the ACM · doi:10.1145/361237.361242 · Cited by 6,633 · see citing works
Yılmaz, A., Javed, O., & Shah, M. A. (2006) · ACM Computing Surveys · doi:10.1145/1177352.1177355 · Cited by 4,807 · see citing works
Machine Learning for High-Speed Corner Detection
Rosten, E., & Drummond, T. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_34 · Cited by 4,555 · see citing works
Robust wide-baseline stereo from maximally stable extremal regions
Matas, J., Chum, O., Urban, M., & Pajdla, T. (2004) · Image and Vision Computing · doi:10.1016/j.imavis.2004.02.006 · Cited by 3,683 · see citing works
EPnP: An Accurate O(n) Solution to the PnP Problem
Lepetit, V., Moreno-Noguer, F., & Fua, P. (2009) · International Journal of Computer Vision · doi:10.1007/s11263-008-0152-6 · Cited by 3,298 · see citing works
Three-dimensional object recognition from single two-dimensional images
Lowe, D. G. (1987) · Artificial Intelligence · doi:10.1016/0004-3702(87)90070-1 · Cited by 1,283 · see citing works
Model-based object pose in 25 lines of code
DeMenthon, D., & Davis, L. S. (1995) · International Journal of Computer Vision · doi:10.1007/bf01450852 · Cited by 1,013 · see citing works
Complete solution classification for the perspective-three-point problem
Gao, X.-S., Hou, X.-R., Tang, J., & Cheng, H.-F. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1217599 · Cited by 976 · see citing works
Picture processing and psychopictorics
(1971) · Icarus · doi:10.1016/0019-1035(71)90136-9 · Cited by 766 · see citing works
New algorithms for 2D and 3D point matching
Gold, S., Rangarajan, A., Lu, C.-P., Pappu, S., & Mjolsness, E. (1998) · Pattern Recognition · doi:10.1016/s0031-3203(98)80010-1 · Cited by 580 · see citing works
Determination of the attitude of 3D objects from a single perspective view
Dhome, M., Richetin, M., Lapresté, J., & Rives, G. (1989) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.41365 · Cited by 461 · see citing works
Linear pose estimation from points or lines
Ansar, A. I., & Daniilidis, K. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1195992 · Cited by 438 · see citing works
On Detection of Multiple Object Instances Using Hough Transforms
Barinova, O., Lempitsky, V., & Kholi, P. K. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.79 · Cited by 237 · see citing works
SoftPOSIT: Simultaneous Pose and Correspondence Determination
David, P., Dementhon, D. F., Ramani Duraiswami, B., & Samet, H. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000025800.10423.1f · Cited by 237 · see citing works
3D object recognition using shape similiarity-based aspect graph
Cyr, C. M., & Kimia, B. B. (2002) · IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2001.937526 · Cited by 221 · see citing works
Vision-Based Sensor and Navigation System for Autonomous Air Refueling
Valasek, J., Gunnam, K., Kimmett, J., Tandale, M. D., Junkins, J. L., & Hughes, D. C. (2005) · Journal of Guidance Control and Dynamics · doi:10.2514/1.11934 · Cited by 196 · see citing works
Pose Estimation from Line Correspondences: A Complete Analysis and a Series of Solutions
Xu, C. Y., Zhang, L., Cheng, L., et al. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2582162 · Cited by 178 · see citing works
On the verification of hypothesized matches in model-based recognition
Grimson, W. E. L., & Huttenlocher, D. P. (1991) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.106994 · Cited by 136 · see citing works
Pose estimation of an uncooperative spacecraft from actual space imagery
D', S., Amico, N. A., Benn, M., & Jørgensen, J. L. (2014) · International Journal of Space Science and Engineering · doi:10.1504/ijspacese.2014.060600 · Cited by 132 · see citing works
The Restore-L Servicing Mission
Reed, B. B., Smith, R. C., Naasz, B. J., Pellegrino, J. F., & Bacon, C. E. (2016) · AIAA SPACE 2016 · doi:10.2514/6.2016-5478 · Cited by 119 · see citing works
Appearance-based active object recognition
Borotschnig, H., Paletta, L., Prantl, M., et al. (2000) · Image and Vision Computing · doi:10.1016/s0262-8856(99)00075-x · Cited by 111 · see citing works
Comparative assessment of techniques for initial pose estimation using monocular vision
Sharma, S., & D׳Amico, S. (2016) · Acta Astronautica · doi:10.1016/j.actaastro.2015.12.032 · Cited by 94 · see citing works
Self-citationFast and Near-Optimal Guidance for Docking to Uncontrolled Spacecraft
Ventura, J., Ciarcià, M., Romano, M., et al. (2016) · Journal of Guidance Control and Dynamics · doi:10.2514/1.g001843 · Cited by 80 · see citing works
Self-citationRelative Navigation of Air Vehicles
Fosbury, A. M., & Crassidis, J. L. (2008) · Journal of Guidance Control and Dynamics · doi:10.2514/1.33698 · Cited by 73 · see citing works
Castellani, L. T., Llorente, S., Ibarz, J. M. F., Ruiz, M., Mestreau-Garreau, A., Cropp, A., & Santovincenzo, A. (2013) · International Journal of Space Science and Engineering · doi:10.1504/ijspacese.2013.059268 · Cited by 33 · see citing works
A CAD-based computer vision system
Byne, J. H. M., & Anderson, J. A. D. W. (1998) · Image and Vision Computing · doi:10.1016/s0262-8856(98)00100-0 · Cited by 33 · see citing works
Final commissioning of the PRISMA GPS navigation system
Ardaens, J.-S., D’Amico, S., & Montenbruck, O. (2012) · Journal of Aerospace Engineering Sciences and Applications · doi:10.7446/jaesa.0403.10 · Cited by 28 · see citing works
Self-citationKalman Filtering for Relative Spacecraft Attitude and Position Estimation: A Revisit
Zhang, L., Yang, H., Zhang, S., Cai, H., & Qian, S. (2014) · Journal of Guidance Control and Dynamics · doi:10.2514/1.g000204 · Cited by 24 · see citing works
Prox-1 University-Class Mission to Demonstrate Automated Proximity Operations
Spencer, D. A., Chait, S. B., Schulte, P. Z., Okseniuk, K. J., & Veto, M. (2016) · Journal of Spacecraft and Rockets · doi:10.2514/1.a33526 · Cited by 19 · see citing works
Vision-Based 3D Motion Estimation for On-Orbit Proximity Satellite Tracking and Navigation
Grompone, A. (2015) · Calhoun: The Naval Postgraduate School Institutional Archive (Naval Postgraduate School) · Cited by 13 · see citing works
Pose estimation for servicing of orbital replacement units in a cluttered enironment
Chien, C.-H., & Baker, K. (2004) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2004.1302533 · Cited by 10 · see citing works
Vision Based Navigation Sensors for Spacecraft Rendezvous and Docking
Benn, M. (2011) · Cited by 10 · see citing works
Autonomous Proximity Operations for Noncooperative Space Targets
Ventura, J. (2016) · mediaTUM – the media and publications repository of the Technical University Munich (Technical University Munich) · Cited by 5 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Spacecraft pose estimation dataset (speed)
Sharma, S., Park, T. H., & D'Amico, S. (2026) · Stanford Digital Repository · doi:10.25740/dz692fn7184 · Cited by 304
Self-citationSatellite Pose Estimation Challenge: Dataset, Competition Design, and Results
Kisantal, M., Sharma, S., Park, T. H., Izzo, D., Martens, M., & D'Amico, S. (2020) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2020.2989063 · Cited by 304 · see citing works
“[27], who additionally introduced weak gradient elimination technique to essentially separate the spacecraft’s edge features from the weak edge features of the background.”
Self-citationNeural Network-Based Pose Estimation for Noncooperative Spacecraft Rendezvous
Sharma, S., & D'Amico, S. (2020) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2020.2999148 · Cited by 196 · see citing works
Self-citationSatellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement
Chen, B., Cao, J., Parra, A., & Chin, T.-J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00343 · Cited by 203 · see citing works
Pasqualetto Cassinis, L., Fonod, R., & Gill, E. (2019) · Progress in Aerospace Sciences · doi:10.1016/j.paerosci.2019.05.008 · Cited by 156 · see citing works
Pauly, L., Rharbaoui, W., Shneider, C., Rathinam, A., Gaudillière, V., & Aouada, D. (2023) · Acta Astronautica · doi:10.1016/j.actaastro.2023.08.001 · Cited by 121 · see citing works
“Following this trend, the proposals of DL-based spacecraft pose estimation algorithms have outnumbered [151], [20] the classical featureengineering-based methods [32, 148, 87, 147, 135, 19] in recent years.”
MethodDeep learning-based spacecraft relative navigation methods: A survey
Song, J., Rondao, D., & Aouf, N. (2022) · Acta Astronautica · doi:10.1016/j.actaastro.2021.10.025 · Cited by 106 · see citing works
“Experiments are also carried out to demonstrate two key features of SPN method and compare it with their previous work, namely CNN-based [6] and image processing-based feature detection and correspondence [34] methods.”
MethodSatellite Pose Estimation Competition 2021: Results and Analyses
Park, T. H., Märtens, M., Jawaid, M., Wang, Z., Chen, B., Chin, T.-J., Izzo, D., & D’Amico, S. (2023) · Acta Astronautica · doi:10.1016/j.actaastro.2023.01.002 · Cited by 91 · see citing works
Self-citationAutonomous relative navigation around uncooperative spacecraft based on a single camera
Pesce, V., Opromolla, R., Sarno, S., Lavagna, M., & Grassi, M. (2019) · Aerospace Science and Technology · doi:10.1016/j.ast.2018.11.042 · Cited by 80 · see citing works
Revisiting Monocular Satellite Pose Estimation With Transformer
Wang, Z., Zhang, Z., Sun, X., Li, Z., & Yu, Q. (2022) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2022.3161605 · Cited by 59 · see citing works
Huo, Y., Li, Z., & Zhang, F. (2020) · IEEE Access · doi:10.1109/access.2020.3041415 · Cited by 44 · see citing works
Deep learning for real-time satellite pose estimation on tensor processing units
Lotti, A., Modenini, D., Tortora, P., Saponara, M., & Perino, M. A. (2023) · Journal of Spacecraft and Rockets · doi:10.2514/1.a35496 · Cited by 39 · see citing works
Pose Estimation for Non-Cooperative Rendezvous Using Neural Networks
Sharma, S., & D'Amico, S. (2019) · arXiv · Cited by 40 · see citing works
Self-citationAhmed, J., Arshad, A., Bang, H., & Choi, Y. (2024) · International Journal of Aeronautical and Space Sciences · doi:10.1007/s42405-023-00703-3 · Cited by 11 · see citing works
Park, T. H., Bosse, J., & D'Amico, S. (2021) · arXiv · doi:10.48550/arxiv.2108.05529 · Cited by 10 · see citing works
Self-citationDomain Generalization for In-Orbit 6D Pose Estimation
Legrand, A., Detry, R., & De Vleeschouwer, C. (2025) · Journal of Aerospace Information Systems · doi:10.2514/1.i011498 · Cited by 7 · see citing works
- Authors
- Sharma, S., Ventura, J., & D’Amico, S.
- Affiliations
- Stanford University (US)
- Technical University of Munich (DE)
- Venue
- Journal of Spacecraft and Rockets
- Published
- 2018-11
- Volume
- 55
- Issue
- 6
- Pages
- 1414-1429
- ISSN
- 0022-4650 (ISSN-L)
- 1533-6794
- OpenAlex
- W2810416830
- Cited by
- 128
- References
- 36
- Citations by year
- 2026: 8 · 2025: 17 · 2024: 26 · 2023: 19 · 2022: 18 · 2021: 12 · 2020: 16 · 2019: 11 · 2018: 1
- FWCI
- 8.13
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of Spacecraft and Rockets (publishedVersion)
- Topics
- Physical Sciences › Engineering › Aerospace Engineering › Space Satellite Systems and Control
- Physical Sciences › Engineering › Aerospace Engineering › Spacecraft Dynamics and Control
- Physical Sciences › Engineering › Ocean Engineering › Satellite Image Processing and Photogrammetry
- Keywords
- monocular vision, pose initialization, spacecraft rendezvous, on-orbit servicing, formation flying, wireframe models, feature detection, edge detection, feature matching, PRISMA mission
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
