SatSplatYOLO: 3D Gaussian Splatting-based Virtual Object Detection Ensembles for Satellite Feature Recognition
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916273931157504 |
|---|---|
| author | Nguyen, Van Minh Sandidge, Emma Mahendrakar, Trupti White, Ryan T. |
| author_facet | Nguyen, Van Minh Sandidge, Emma Mahendrakar, Trupti White, Ryan T. |
| contents | On-orbit servicing (OOS), inspection of spacecraft, and active debris removal (ADR). Such missions require precise rendezvous and proximity operations in the vicinity of non-cooperative, possibly unknown, resident space objects. Safety concerns with manned missions and lag times with ground-based control necessitate complete autonomy. In this article, we present an approach for mapping geometries and high-confidence detection of components of unknown, non-cooperative satellites on orbit. We implement accelerated 3D Gaussian splatting to learn a 3D representation of the satellite, render virtual views of the target, and ensemble the YOLOv5 object detector over the virtual views, resulting in reliable, accurate, and precise satellite component detections. The full pipeline capable of running on-board and stand to enable downstream machine intelligence tasks necessary for autonomous guidance, navigation, and control tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_02533 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SatSplatYOLO: 3D Gaussian Splatting-based Virtual Object Detection Ensembles for Satellite Feature Recognition Nguyen, Van Minh Sandidge, Emma Mahendrakar, Trupti White, Ryan T. Computer Vision and Pattern Recognition On-orbit servicing (OOS), inspection of spacecraft, and active debris removal (ADR). Such missions require precise rendezvous and proximity operations in the vicinity of non-cooperative, possibly unknown, resident space objects. Safety concerns with manned missions and lag times with ground-based control necessitate complete autonomy. In this article, we present an approach for mapping geometries and high-confidence detection of components of unknown, non-cooperative satellites on orbit. We implement accelerated 3D Gaussian splatting to learn a 3D representation of the satellite, render virtual views of the target, and ensemble the YOLOv5 object detector over the virtual views, resulting in reliable, accurate, and precise satellite component detections. The full pipeline capable of running on-board and stand to enable downstream machine intelligence tasks necessary for autonomous guidance, navigation, and control tasks. |
| title | SatSplatYOLO: 3D Gaussian Splatting-based Virtual Object Detection Ensembles for Satellite Feature Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.02533 |