LSPnet: A 2D Localization-Oriented Spacecraft Pose Estimation Neural Network

Albert García, Mohamed Adel Musallam, Vincent Gaudillière, Enjie Ghorbel, Kassem Al Ismaeil, Marcos Damian Perez, Djamila Aouada

CVPRW 2021 pp. 2048-2056

doi:10.1109/CVPRW53098.2021.00233 /cvprw/2021/garcia2021cvprw-lspnet/

Abstract

Being capable of estimating the pose of uncooperative objects in space has been proposed as a key asset for enabling safe close-proximity operations such as space rendezvous, in-orbit servicing and active debris removal. Usual approaches for pose estimation involve classical computer vision-based solutions or the application of Deep Learning (DL) techniques. This work explores a novel DL-based methodology, using Convolutional Neural Networks (CNNs), for estimating the pose of uncooperative space-crafts. Contrary to other approaches, the proposed CNN directly regresses poses without needing any prior 3D information. Moreover, bounding boxes of the spacecraft in the image are predicted in a simple, yet efficient manner. The performed experiments show how this work competes with the state-of-the-art in uncooperative spacecraft pose estimation, including works which require 3D information as well as works which predict bounding boxes through sophisticated CNNs.

PDF CVPRW Semantic Scholar

Cite

Text

García et al. "LSPnet: A 2D Localization-Oriented Spacecraft Pose Estimation Neural Network." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00233

Markdown

[García et al. "LSPnet: A 2D Localization-Oriented Spacecraft Pose Estimation Neural Network." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/garcia2021cvprw-lspnet/) doi:10.1109/CVPRW53098.2021.00233

BibTeX

@inproceedings{garcia2021cvprw-lspnet,
  title     = {{LSPnet: A 2D Localization-Oriented Spacecraft Pose Estimation Neural Network}},
  author    = {García, Albert and Musallam, Mohamed Adel and Gaudillière, Vincent and Ghorbel, Enjie and Al Ismaeil, Kassem and Perez, Marcos Damian and Aouada, Djamila},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2021},
  pages     = {2048-2056},
  doi       = {10.1109/CVPRW53098.2021.00233},
  url       = {https://mlanthology.org/cvprw/2021/garcia2021cvprw-lspnet/}
}