CoChat

Spacecraft Homography Pose Estimation with Single-Stage Deep Convolutional Neural Network

Open access

The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.

Abstract

Spacecraft pose estimation using computer vision has garnered increasing attention in research areas such as automation system theory, control theory, sensors and instruments, robot technology, and automation software. Confronted with the extreme environment of space, existing spacecraft pose estimation methods are predominantly multi-stage networks with complex operations. In this study, we propose an approach for spacecraft homography pose estimation with a single-stage deep convolutional neural network for the first time. We formulated a homomorphic geometric constraint equation for spacecraft with planar features. Additionally, we employed a single-stage 2D keypoint regression network to obtain homography 2D keypoint coordinates for spacecraft. After decomposition to obtain the rough spacecraft pose based on the homography matrix constructed according to the geometric constraint equation, a loss function based on pixel errors was employed to refine the spacecraft pose. We conducted extensive experiments using widely used spacecraft pose estimation datasets and compared our method with state-of-the-art techniques in the field to demonstrate its effectiveness.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/s24061828

Cites

41 of 41 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 The overall structure of the spacecraft on the image and the skeleton of the spacecraft’s solar panels.
Figure 1 The overall structure of the spacecraft on the image and the skeleton of the spacecraft’s solar panels.CC BY · PubMed Central
Figure 2 Illustrating the pipeline for the reconstruction process of the spacecraft 3D skeleton model and the generation of training labels.
Figure 2 Illustrating the pipeline for the reconstruction process of the spacecraft 3D skeleton model and the generation of training labels.CC BY · PubMed Central
Figure 3 Illustrating the architecture of the single-stage 2D keypoint regression network [32]. The input image is passed through the backbone [35] that generates feature maps at various scales: P3, P4, P5, P6. The output of feature fusion [36] is fed to the detection heads. Each detection head branches into a box head and keypoint head.
Figure 3 Illustrating the architecture of the single-stage 2D keypoint regression network [32]. The input image is passed through the backbone [35] that generates feature maps at various scales: P3, P4, P5, P6. The output of feature fusion [36] is fed to the detection heads. Each detection head branches into a box head and keypoint head.CC BY · PubMed Central
Figure 4 Illustrating the single-stage 2D keypoint regression network for the SPEC2021 dataset with semi-supervised domain adaptation.
Figure 4 Illustrating the single-stage 2D keypoint regression network for the SPEC2021 dataset with semi-supervised domain adaptation.CC BY · PubMed Central
Figure 5 In the SPEC2021 lightbox dataset, a comparison is conducted between the pose obtained using our proposed research method (est) and the pose ground truth (gt).
Figure 5 In the SPEC2021 lightbox dataset, a comparison is conducted between the pose obtained using our proposed research method (est) and the pose ground truth (gt).CC BY · PubMed Central
Figure 6 In the SPEC2021 sunlamp dataset, a comparison is conducted between the pose obtained using our proposed research method (est) and the pose ground truth (gt).
Figure 6 In the SPEC2021 sunlamp dataset, a comparison is conducted between the pose obtained using our proposed research method (est) and the pose ground truth (gt).CC BY · PubMed Central
Figure 7 In the SPEC2021 synthetic dataset, a comparison is conducted between the pose obtained using our proposed research method (est) and the pose ground truth (gt).
Figure 7 In the SPEC2021 synthetic dataset, a comparison is conducted between the pose obtained using our proposed research method (est) and the pose ground truth (gt).CC BY · PubMed Central
Figure 8 Illustrating the single-stage 2D keypoint regression network for the Soyuz dataset.
Figure 8 Illustrating the single-stage 2D keypoint regression network for the Soyuz dataset.CC BY · PubMed Central
Figure 9 In the URSO Soyuz dataset, a comparison was conducted between the pose obtained using our proposed research method (est) and the pose ground truth (gt).
Figure 9 In the URSO Soyuz dataset, a comparison was conducted between the pose obtained using our proposed research method (est) and the pose ground truth (gt).CC BY · PubMed Central
Figure 10 Illustrating the keypoint regression for the Soyuz spacecraft solar panels in the image through a single-stage spacecraft pose network.
Figure 10 Illustrating the keypoint regression for the Soyuz spacecraft solar panels in the image through a single-stage spacecraft pose network.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 1

  1. Sharma, S., and D’Amico, S. (2019). Pose estimation for non-cooperative rendezvous using neural networks. arXiv. · DOI · Paper page

Cited by

See all 12

Metadata

Authors
Chen, S., Yang, W., Wang, W., Mai, J., Liang, J., & Zhang, X.
Affiliations
Sun Yat-sen University (CN)
Corresponding author
Zhang, Xiaohu
Venue
Sensors
Publisher
MDPI AG
Published
2024-03-12
Volume
24
Issue
6
Pages
1828
ISSN
1424-8220 (ISSN-L)
OpenAlex
W4392752914
Cited by
12
References
39
Citations by year
2026: 4 · 2025: 7 · 2024: 1
FWCI
2.06
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
Sun Yat-sen University
Topics
  • Physical Sciences › Engineering › Aerospace Engineering › Space Satellite Systems and Control
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Engineering › Aerospace Engineering › Spacecraft Dynamics and Control
Keywords
spacecraft pose estimation, homography, planar features

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

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.