AI based fusion of visible and thermal images for robust feature extraction for autonomous navigation of spacecraft missions to asteroids

Tools

Hall, Iain and Feng, Jinglang and Peng, Hao and Vasile, Massimiliano (2024) AI based fusion of visible and thermal images for robust feature extraction for autonomous navigation of spacecraft missions to asteroids. In: 2024 AAS/AIAA Astrodynamics Specialist Conference, 2024-08-11 - 2024-08-15.

[thumbnail of AI based Sensor Fusion for Robust Feature Extraction for Autonomous Navigation of Spacecraft Missions to Asteroids with application to ESA Hera mission]
Preview
 Text. Filename: AAS-24-232_1_.pdf
Accepted Author Manuscript
License: Strathprints license 1.0
Download (3MB)| Preview

Abstract

Missions to visit asteroids depend on autonomous navigation systems to carry out operations. The extraction of features for the estimation of the relative position and attitude (pose) of the asteroid is a key step but can be challenging in the poor illumination conditions which can occur for asteroids. We explore how data fusion using machine learning can potentially allow for more robust feature extraction. Different levels of fusing visible images and thermal images using Convolutional Neural Networks are developed and tested using synthetic images based on ESA’s Hera mission scenario.

ORCID iDs

Hall, Iain, Feng, Jinglang ORCID logoORCID: https://orcid.org/0000-0003-0376-886X, Peng, Hao and Vasile, Massimiliano ORCID logoORCID: https://orcid.org/0000-0001-8302-6465;
CORE (COnnecting REpositories)