Resource-Exploration-Oriented Lunar Rocks Monocular Detection and 3D Pose Estimation
Lunar in situ resource utilization is a core goal in lunar exploration, with accurate lunar rock pose estimation being essential. To address the challenges posed by the lack of texture features and extreme lighting conditions, this study proposes the Simulation-YOLO-Hourglass-Transformer (SYHT) meth...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Aerospace |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2226-4310/12/1/4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589495765041152 |
|---|---|
| author | Jiayu Suo Hongfeng Long Yuebo Ma Yuhao Zhang Zhen Liang Chuan Yan Rujin Zhao |
| author_facet | Jiayu Suo Hongfeng Long Yuebo Ma Yuhao Zhang Zhen Liang Chuan Yan Rujin Zhao |
| author_sort | Jiayu Suo |
| collection | DOAJ |
| description | Lunar in situ resource utilization is a core goal in lunar exploration, with accurate lunar rock pose estimation being essential. To address the challenges posed by the lack of texture features and extreme lighting conditions, this study proposes the Simulation-YOLO-Hourglass-Transformer (SYHT) method. The method enhances accuracy and robustness in complex lunar environments, demonstrating strong adaptability and excellent performance, particularly in conditions of extreme lighting and scarce texture. This approach provides valuable insights for object pose estimation in lunar exploration tasks and lays the foundation for lunar resource development. First, the YOLO-Hourglass-Transformer (YHT) network is used to extract keypoint information from each rock and generate the corresponding 3D pose. Then, a lunar surface imaging physics simulation model is employed to generate simulated lunar rock data for testing the method. The experimental results show that the SYHT method performs exceptionally well on simulated lunar rock data, achieving a mean per-joint position error (MPJPE) of 37.93 mm and a percentage of correct keypoints (PCK) of 99.94%, significantly outperforming existing methods. Finally, transfer learning experiments on real-world datasets validate its strong generalization capability, highlighting its effectiveness for lunar rock pose estimation in both simulated and real lunar environments. |
| format | Article |
| id | doaj-art-bc53c97660f24bf8885ff7aed6faf0a2 |
| institution | Kabale University |
| issn | 2226-4310 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Aerospace |
| spelling | doaj-art-bc53c97660f24bf8885ff7aed6faf0a22025-01-24T13:15:24ZengMDPI AGAerospace2226-43102024-12-01121410.3390/aerospace12010004Resource-Exploration-Oriented Lunar Rocks Monocular Detection and 3D Pose EstimationJiayu Suo0Hongfeng Long1Yuebo Ma2Yuhao Zhang3Zhen Liang4Chuan Yan5Rujin Zhao6Institute of Optics and Electronics of Chinese Academy of Sciences, Chengdu 610209, ChinaInstitute of Optics and Electronics of Chinese Academy of Sciences, Chengdu 610209, ChinaInstitute of Optics and Electronics of Chinese Academy of Sciences, Chengdu 610209, ChinaInstitute of Optics and Electronics of Chinese Academy of Sciences, Chengdu 610209, ChinaInstitute of Optics and Electronics of Chinese Academy of Sciences, Chengdu 610209, ChinaInstitute of Optics and Electronics of Chinese Academy of Sciences, Chengdu 610209, ChinaInstitute of Optics and Electronics of Chinese Academy of Sciences, Chengdu 610209, ChinaLunar in situ resource utilization is a core goal in lunar exploration, with accurate lunar rock pose estimation being essential. To address the challenges posed by the lack of texture features and extreme lighting conditions, this study proposes the Simulation-YOLO-Hourglass-Transformer (SYHT) method. The method enhances accuracy and robustness in complex lunar environments, demonstrating strong adaptability and excellent performance, particularly in conditions of extreme lighting and scarce texture. This approach provides valuable insights for object pose estimation in lunar exploration tasks and lays the foundation for lunar resource development. First, the YOLO-Hourglass-Transformer (YHT) network is used to extract keypoint information from each rock and generate the corresponding 3D pose. Then, a lunar surface imaging physics simulation model is employed to generate simulated lunar rock data for testing the method. The experimental results show that the SYHT method performs exceptionally well on simulated lunar rock data, achieving a mean per-joint position error (MPJPE) of 37.93 mm and a percentage of correct keypoints (PCK) of 99.94%, significantly outperforming existing methods. Finally, transfer learning experiments on real-world datasets validate its strong generalization capability, highlighting its effectiveness for lunar rock pose estimation in both simulated and real lunar environments.https://www.mdpi.com/2226-4310/12/1/4pose estimationlunar exploration applicationstransformer-based architecturespatial feature extractionsimulation-YOLO-hourglass-transformer |
| spellingShingle | Jiayu Suo Hongfeng Long Yuebo Ma Yuhao Zhang Zhen Liang Chuan Yan Rujin Zhao Resource-Exploration-Oriented Lunar Rocks Monocular Detection and 3D Pose Estimation Aerospace pose estimation lunar exploration applications transformer-based architecture spatial feature extraction simulation-YOLO-hourglass-transformer |
| title | Resource-Exploration-Oriented Lunar Rocks Monocular Detection and 3D Pose Estimation |
| title_full | Resource-Exploration-Oriented Lunar Rocks Monocular Detection and 3D Pose Estimation |
| title_fullStr | Resource-Exploration-Oriented Lunar Rocks Monocular Detection and 3D Pose Estimation |
| title_full_unstemmed | Resource-Exploration-Oriented Lunar Rocks Monocular Detection and 3D Pose Estimation |
| title_short | Resource-Exploration-Oriented Lunar Rocks Monocular Detection and 3D Pose Estimation |
| title_sort | resource exploration oriented lunar rocks monocular detection and 3d pose estimation |
| topic | pose estimation lunar exploration applications transformer-based architecture spatial feature extraction simulation-YOLO-hourglass-transformer |
| url | https://www.mdpi.com/2226-4310/12/1/4 |
| work_keys_str_mv | AT jiayusuo resourceexplorationorientedlunarrocksmonoculardetectionand3dposeestimation AT hongfenglong resourceexplorationorientedlunarrocksmonoculardetectionand3dposeestimation AT yueboma resourceexplorationorientedlunarrocksmonoculardetectionand3dposeestimation AT yuhaozhang resourceexplorationorientedlunarrocksmonoculardetectionand3dposeestimation AT zhenliang resourceexplorationorientedlunarrocksmonoculardetectionand3dposeestimation AT chuanyan resourceexplorationorientedlunarrocksmonoculardetectionand3dposeestimation AT rujinzhao resourceexplorationorientedlunarrocksmonoculardetectionand3dposeestimation |