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

TL;DR

This paper introduces LSPnet, a CNN-based method for estimating spacecraft pose directly from images without prior 3D data, enabling safer space operations.

Contribution

LSPnet is a novel CNN architecture that directly regresses spacecraft pose and predicts bounding boxes efficiently, outperforming existing methods requiring 3D information.

Findings

Competitive with state-of-the-art methods

Does not require prior 3D information

Efficient bounding box prediction

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 spacecrafts. 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.