Abstract This paper presents some initial results on the use of hyperspectral imaging technology and machine learning to characterise the surface composition of space objects and reconstruct their attitude motion. The paper provides a preliminary demonstration that hyperspectral and multispectral analysis of the light absorbed, emitted and reflected by space objects can be used to identify, with some degree of accuracy, the materials composing their surface. The paper introduces a high-fidelity simulation model, developed to test this concept, and a validation of the model against experimental tests in a laboratory environment. The paper shows how to unmix the spectra to provide an estimation of the materials composing the surface facing the sensor. A machine learning approach is then proposed to reconstruct the attitude motion from the time series of spectra.
Highlights Demonstration of characterisation of space object composition using hyperspectral technology. Demonstration of attitude motion reconstruction from spectra with machine learning. High-fidelity model of the spectra received by a sensor. Validation of the simulation model in a laboratory environment.
Intelligent characterisation of space objects with hyperspectral imaging
Acta Astronautica ; 203 ; 510-534
2022-11-17
25 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Hyperspectral Imaging of Near-Earth Space Objects at the Phillips Laboratory
British Library Conference Proceedings | 1994
|Observation angle and plane characterisation for ISAR imaging of LEO space objects
Online Contents | 2016
|Hyperspectral Imaging from Space: Warfighter-1
British Library Conference Proceedings | 1999
|