A Vision-Based Pose Estimation of a Non-Cooperative Target Based on a Self-Supervised Transformer Network
In the realm of non-cooperative space security and on-orbit service, a significant challenge is accurately determining the pose of abandoned satellites using imaging sensors. Traditional methods for estimating the position of the target encounter problems with stray light interference in space, lead...
| প্রধান লেখক: | , , , , , , , , |
|---|---|
| বিন্যাস: | প্রবন্ধ |
| ভাষা: | English |
| প্রকাশিত: |
MDPI AG
2023-11-01
|
| মালা: | Aerospace |
| বিষয়গুলি: | |
| অনলাইন ব্যবহার করুন: | https://www.mdpi.com/2226-4310/10/12/997 |
| _version_ | 1827576056914116608 |
|---|---|
| author | Quan Sun Xuhui Pan Xiao Ling Bo Wang Qinghong Sheng Jun Li Zhijun Yan Ke Yu Jiasong Wang |
| author_facet | Quan Sun Xuhui Pan Xiao Ling Bo Wang Qinghong Sheng Jun Li Zhijun Yan Ke Yu Jiasong Wang |
| author_sort | Quan Sun |
| collection | DOAJ |
| description | In the realm of non-cooperative space security and on-orbit service, a significant challenge is accurately determining the pose of abandoned satellites using imaging sensors. Traditional methods for estimating the position of the target encounter problems with stray light interference in space, leading to inaccurate results. Conversely, deep learning techniques require a substantial amount of training data, which is especially difficult to obtain for on-orbit satellites. To address these issues, this paper introduces an innovative binocular pose estimation model based on a Self-supervised Transformer Network (STN) to achieve precise pose estimation for targets even under poor imaging conditions. The proposed method generated simulated training samples considering various imaging conditions. Then, by combining the concepts of convolutional neural networks (CNN) and SIFT features for each sample, the proposed method minimized the disruptive effects of stray light. Furthermore, the feedforward network in the Transformer employed in the proposed method was replaced with a global average pooling layer. This integration of CNN’s bias capabilities compensates for the limitations of the Transformer in scenarios with limited data. Comparative analysis against existing pose estimation methods highlights the superior robustness of the proposed method against variations caused by noisy sample sets. The effectiveness of the algorithm is demonstrated through simulated data, enhancing the current landscape of binocular pose estimation technology for non-cooperative targets in space. |
| first_indexed | 2024-03-08T21:05:40Z |
| format | Article |
| id | doaj.art-91e9a4da9f3c489b9c20c835e67bb32b |
| institution | Directory Open Access Journal |
| issn | 2226-4310 |
| language | English |
| last_indexed | 2024-03-08T21:05:40Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Aerospace |
| spelling | doaj.art-91e9a4da9f3c489b9c20c835e67bb32b2023-12-22T13:45:10ZengMDPI AGAerospace2226-43102023-11-01101299710.3390/aerospace10120997A Vision-Based Pose Estimation of a Non-Cooperative Target Based on a Self-Supervised Transformer NetworkQuan Sun0Xuhui Pan1Xiao Ling2Bo Wang3Qinghong Sheng4Jun Li5Zhijun Yan6Ke Yu7Jiasong Wang8College of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaCollege of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaCollege of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaCollege of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaCollege of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaCollege of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaCollege of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaShanghai Electro-Mechanical Engineering Institute, Shanghai 200041, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaIn the realm of non-cooperative space security and on-orbit service, a significant challenge is accurately determining the pose of abandoned satellites using imaging sensors. Traditional methods for estimating the position of the target encounter problems with stray light interference in space, leading to inaccurate results. Conversely, deep learning techniques require a substantial amount of training data, which is especially difficult to obtain for on-orbit satellites. To address these issues, this paper introduces an innovative binocular pose estimation model based on a Self-supervised Transformer Network (STN) to achieve precise pose estimation for targets even under poor imaging conditions. The proposed method generated simulated training samples considering various imaging conditions. Then, by combining the concepts of convolutional neural networks (CNN) and SIFT features for each sample, the proposed method minimized the disruptive effects of stray light. Furthermore, the feedforward network in the Transformer employed in the proposed method was replaced with a global average pooling layer. This integration of CNN’s bias capabilities compensates for the limitations of the Transformer in scenarios with limited data. Comparative analysis against existing pose estimation methods highlights the superior robustness of the proposed method against variations caused by noisy sample sets. The effectiveness of the algorithm is demonstrated through simulated data, enhancing the current landscape of binocular pose estimation technology for non-cooperative targets in space.https://www.mdpi.com/2226-4310/10/12/997non-cooperative targetsstray light interferencevision-based pose estimationself-supervised transformer network |
| spellingShingle | Quan Sun Xuhui Pan Xiao Ling Bo Wang Qinghong Sheng Jun Li Zhijun Yan Ke Yu Jiasong Wang A Vision-Based Pose Estimation of a Non-Cooperative Target Based on a Self-Supervised Transformer Network Aerospace non-cooperative targets stray light interference vision-based pose estimation self-supervised transformer network |
| title | A Vision-Based Pose Estimation of a Non-Cooperative Target Based on a Self-Supervised Transformer Network |
| title_full | A Vision-Based Pose Estimation of a Non-Cooperative Target Based on a Self-Supervised Transformer Network |
| title_fullStr | A Vision-Based Pose Estimation of a Non-Cooperative Target Based on a Self-Supervised Transformer Network |
| title_full_unstemmed | A Vision-Based Pose Estimation of a Non-Cooperative Target Based on a Self-Supervised Transformer Network |
| title_short | A Vision-Based Pose Estimation of a Non-Cooperative Target Based on a Self-Supervised Transformer Network |
| title_sort | vision based pose estimation of a non cooperative target based on a self supervised transformer network |
| topic | non-cooperative targets stray light interference vision-based pose estimation self-supervised transformer network |
| url | https://www.mdpi.com/2226-4310/10/12/997 |
| work_keys_str_mv | AT quansun avisionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT xuhuipan avisionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT xiaoling avisionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT bowang avisionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT qinghongsheng avisionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT junli avisionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT zhijunyan avisionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT keyu avisionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT jiasongwang avisionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT quansun visionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT xuhuipan visionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT xiaoling visionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT bowang visionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT qinghongsheng visionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT junli visionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT zhijunyan visionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT keyu visionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork AT jiasongwang visionbasedposeestimationofanoncooperativetargetbasedonaselfsupervisedtransformernetwork |