Research on computer vision-based unmarked satellite pose estimation is gaining increasing attention in fields such as intelligent control, industrial communication, and automation technology. A novel unmarked satellite pose estimation method based on semi-supervised domain adaptation and information augmentation is proposed. Efficient pseudo- label generation is achieved by utilizing the homography properties of satellites. Additionally, data enhancement is performed using limited target datasets, sparse satellite feature information, and image preprocessing. The augmented target dataset undergoes filtering and semi-supervised training through iterative merging of source and target datasets until optimization of the loss function related to pixel differences is accomplished. Finally, geometric constraint equations are constructed using the 2D keypoints and the 3D skeleton model of the satellite, with these equations being solved to obtain the satellite’s pose. Extensive experiments are conducted on common satellite pose estimation datasets, and the effectiveness of the proposed method is demonstrated.
Lo BruttoMEboleseDDardanelliG. 3d modelling of a historical building using close-range photogrammetry and remotely piloted aircraft system (rpas). Int Arch Photogram Rem Sens Spatial Inf Sci2018; 42: 599–606.
2.
ZhongJLeiTYaoG, et al.Fast aircraft detection using cascaded discriminative model in photoelectric sensing system. Opt Rev2017; 24: 383–397.
3.
KaraffaŠBrédaRHlinkováM. Movement analysis of the aircraft optoelectronic tracking system in lateral plane. In: 2022 New Trends in Aviation Development (NTAD), Novy Smokovec, Slovakia, 24–25 November 2022.
4.
FournierE. Wind tunnel investigation of grid fin and conventional planar control surfaces. In: 39th Aerospace Sciences Meeting and Exhibit, Reno, NV, 8–11 January 2001.
5.
DeSpiritoJVaughnMWashingtonW. Subsonic flow cfd investigation of canard-controlled missile with planar and grid fins. In: 41st Aerospace Sciences Meeting and Exhibit, Reno, NV, 6–9 January 2003.
6.
PanHHuangJQinS. High accurate estimation of relative pose of cooperative space targets based on measurement of monocular vision imaging. Optik2014; 125(13): 3127–3133.
7.
WangHZhangWDongA. Modeling and validation of photometric characteristics of space targets oriented to space-based observation. Appl Opt2012; 51(32): 7810–7819.
8.
SellmaierFBogeTSpurmannJ, et al.On-orbit servicing missions: challenges and solutions for spacecraft operations. In: SpaceOps 2010 Conference Delivering on the Dream Hosted by NASA Marshall SpaceFlight Center and Organized by AIAA, Huntsville, Alabama, 25–30 April 2010.
9.
XuXWanMGeJ, et al.Color- polarnet: residual dense network-based chromatic intensity- polarization imaging in low-light environment. IEEE Trans Instrum Meas2022; 71: 1–10.
10.
KramerELParkerWEMastersonRA. Vision-based spacecraft relative pose estimation in variable lighting conditions. In: 2022 IEEE Aerospace Conference (AERO), Big Sky, MT, 5–12 March 2022.
11.
TzschichholzTMaLSchillingK. Model- based spacecraft pose estimation and motion prediction using a photonic mixer device camera. Acta Astronaut2011; 68(7-8): 1156–1167.
12.
HuangHSongBZhaoG, et al.End-to-end monocular pose estimation for uncooperative spacecraft based on direct regression network. IEEE Trans Aero Electron Syst2023; 59: 5378–5389.
13.
ZhangHYiJWangL, et al.Non-cooperative satellite pose estimation based on cpms. In: 2023 3rd Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS), Shenyang, 25–27 February 2023.
14.
HuangHZhaoGGuD, et al.Non-model-based monocular pose estimation network for uncooperative spacecraft using convolutional neural network. IEEE Sens J2021; 21(21): 24579–24590.
15.
SharmaSBeierleCD’AmicoS. Pose estimation for non-cooperative spacecraft rendezvous using convolutional neural networks. In: 2018 IEEE Aerospace Conference, Big Sky, MT, 3–10 March 2018.
16.
SharmaSD’AmicoS. Pose estimation for non-cooperative rendezvous using neural networks. arXiv preprint arXiv:1906.09868, 2019.
17.
SongJDuarteRNabilA. Deep learning- based spacecraft relative navigation methods: a survey. Acta Astronaut2022; 191: 22–40.
18.
PedroFP¸GaoY. Deep learning for spacecraft pose estimation from photorealistic rendering. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), Paris, France, 31 May–31 August 2020.
19.
ThaweerathPKamsingPTorteekaP, et al.Vision-based spacecraft pose estimation via a deep convolutional neural network for noncooperative docking operations. Aerospace2020; 7(9): 126.
20.
HuYSpeiererSJakobW, et al.Wide-depth-range 6d object pose estimation in space. IN: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, 20–25 June 2021.
21.
KisantalMSharmaSParkTH, et al.Satellite pose estimation challenge: dataset, competition design, and results. IEEE Trans Aero Electron Syst2020; 56(5): 4083–4098.
22.
ParkTHMärtensMLecuyerG, et al.Speed+: next-generation dataset for spacecraft pose estimation across domain gap. In: 2022 IEEE Aerospace Conference (AERO), Big Sky, MT, 5–12 March 2022.
23.
RubleeEVincentRKonoligeK, et al.ORB: An efficient alternative to sift or surf. In: 2011 International Conference on Computer Vision, Barcelona, Spain, 6–13 November 2011.
24.
HarrisCStephensM, A combined corner and edge detector. In: Alvey Vision Conference, Manchester, 2 September1988.
25.
PřibylBZemčíkPČadíkM. Absolute pose estimation from line correspondences using direct linear transformation. Comput Vis Image Understand2017; 161: 130–144.
26.
HinterstoisserSCagniartCIlicS, et al.Gradient response maps for real-time detection of textureless objects. IEEE Trans Pattern Anal Mach Intell2011; 34(5): 876–888.
27.
WangZZhangZSunX, et al.Revisiting monocular satellite pose estimation with transformer. IEEE Trans Aero Electron Syst2022; 58(5): 4279–4294.
28.
YeRRenYZhuX, et al.An efficient pose estimation algorithm for non-cooperative space objects based on dual-channel transformer. Remote Sens2023; 15(22): 5278.
29.
ChenSYangWWangW, et al.Spacecraft homography pose estimation with single-stage deep convolutional neural network. Sensors2024; 24(6): 1828.
30.
WangZChenMGuoY, et al.Bridging the domain gap in satellite pose estimation: a self-training approach based on geometrical constraints. arXiv:2212.12103, 2023.
31.
LiPSunYWanX. Saliency based semi- supervised learning for orbiting satellite tracking. arXiv preprint arXiv:1909.03656, 2019.
32.
LiuKYuY. Revisiting the domain gap issue in non-cooperative spacecraft pose tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, 17–18 June 2024.
33.
ParkTHD’AmicoS. Robust multi-task learning and online refinement for spacecraft pose estimation across domain gap. Adv Space Res2024; 73(11): 5726–5740.
34.
LiCLiYZhuW, et al.Semi-supervised space target recognition algorithm based on integrated network of imaging and recognition in radar signal domain. IEEE Trans Aero Electron Syst2023; 60: 506–524.
35.
ZuoJZhangSZhangQ, et al.Crospace6d: leveraging geometric and motion cues for high-precision cross-domain 6dof pose estimation for non-cooperative spacecrafts. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, 17–18 June 2024.
36.
Pérez-VillarJIBGarcía-MartínÁBescósJ, et al.Spacecraft pose estimation: robust 2d and 3d-structural losses and unsupervised domain adaptation by inter-model consensus. IEEE Trans Aero Electron Syst2023; 60: 2515–2525.
37.
Pérez-VillarJIBGarcía-MartínÁBescósJ. Spacecraft pose estimation based on unsupervised domain adaptation and on a 3d-guided loss combination. In: European Conference on Computer Vision. Cham: Springer, 2022.
38.
LeeTLeeB-UShinI, et al.Unsupervised domain adaptation for category-level object pose estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, 18–24 June 2022.
39.
WangCMartín-MartínRXuD, et al.6-pack: category-level 6d pose tracker with anchor-based keypoints. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), Paris, France, 31 May–31 August 2020.
40.
RathinamAVincentGAliMAM, et al.Spark 2022 dataset: spacecraft detection and trajectory estimation. Meyrin, Switzerland: Zenodo, 2022. https://doi.org/10.5281/ZENODO.6599762
41.
PaulyLLynn JamrozikMDel CastilloO. Lessons from a space lab — an image acquisition perspective. 2022. https://arxiv.org/abs/2208.08865
42.
LinT-YMaireMBelongieS, et al.Microsoft coco: common objects in context. In: Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, 2014, pp. 740–755.
43.
MalisEVillanuevaMV. Deeper understanding of the homography decomposition for vision- based control. Seville, Spain: University of Seville, 2007.
44.
WangC-YBochkovskiyALiaoH-YM. Yolov7: trainable bag-of-freebies sets new state-of- the-art for real-time object detectors. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Vancouver, BC, 17 June 2023.
45.
WangC-YBochkovskiyALiaoH-YM. Scaled-yolov4: scaling cross stage partial network. In: Proceedings of the IEEE/cvf conference on computer vision and pattern recognition, Nashville, TN, 20-25 June 2021.
46.
HeKZhangXRenS, et al.Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell2015; 37(9): 1904–1916.
47.
LiuSLuQQinH, et al.Path aggregation network for instance segmentation. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, 18–13 June 2018.
48.
WangJSunKChengT, et al.Deep high-resolution representation learning for visual recognition. IEEE Trans Pattern Anal Mach Intell2020; 43(10): 3349–3364.
49.
VincentLMoreno-NoguerFFuaP. Epnp: an accurate o(n) solution to the pnp problem. Int J Comput Vis2009; 81: 155–166.
50.
DonaldWM. An algorithm for least-squares estimation of nonlinear parameters. J Soc Ind Appl Math1963; 11(2): 431–441.
51.
ZhangYYouLYangL, et al.Monocular 6-dof pose estimation of spacecrafts utilizing self-iterative optimization and motion consistency. In: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, 17–18 June 2024.
52.
ZuoJZhangSZhangQ, et al.Crospace6d: leveraging geometric and motion cues for high-precision cross-domain 6dof pose estimation for non-cooperative spacecrafts. In: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, 17–18 June 2024.
53.
UlmerMDurnerMSundermeyerM, et al.6d object pose estimation from approximate 3d models for orbital robotics. In: 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Detroit, MI, 1–5 October 2023.
54.
AbidiMAChandraT. A new efficient and direct solution for pose estimation using quadrangular targets: algorithm and evaluation. IEEE Trans Pattern Anal Mach Intell1995; 17(5): 534–538.
55.
LeeC-HHuangT. Finding point correspondence and determining motion of a rigid object from two weak perspective views. Comput Vis Graph Image Process1990; 52(3): 309–327.
56.
LoweDG. Distinctive image features from scale- invariant keypoints. Int J Comput Vis2004; 60: 91–110.
57.
BayHTuytelaarsTVan GoolL. Surf: speeded up robust features. In: Computer Vision-ECCV 2006: 9th European Conference on Computer Vision, Graz, Austria, May 7-13, 2006. Proceedings, Part I 9. pp. 404–417.
58.
KamsingPCaoCZhaoY, et al.Joint iterative satellite pose estimation and particle swarm optimization. Appl Sci2025; 15(4): 2166.
