Noise Robustness of Data-Driven Star Classification

Floyd Hepburn-Dickins, Michael Edwards

2023

Abstract

Celestial navigation has fallen into the background in light of newer technologies such as global positioning systems, but research into its core component, star pattern recognition, has remained an active area of study. We examine these methods and the viability of a data-driven approach to detecting and recognising stars within images taken from the Earth’s surface. We show that synthetic datasets, necessary due to a lack of labelled real image datasets, are able to appropriately simulate the night sky from a terrestrial perspective and that such an implementation can successfully perform star patter recognition in this domain. In this work we apply three kinds of noise in a parametric fashion; positional noise, false star noise, and dropped star noise. Results show that a pattern mining approach can accurately identify stars from night sky images and our results show the impact of the above noise types on classifier performance.

Paper Citation

in Harvard Style

Hepburn-Dickins F. and Edwards M. (2023). Noise Robustness of Data-Driven Star Classification. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 176-184. DOI: 10.5220/0011804000003411

in Bibtex Style

@conference{icpram23,
author={Floyd Hepburn-Dickins and Michael Edwards},
title={Noise Robustness of Data-Driven Star Classification},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={176-184},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011804000003411},
isbn={978-989-758-626-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Noise Robustness of Data-Driven Star Classification
SN - 978-989-758-626-2
AU - Hepburn-Dickins F.
AU - Edwards M.
PY - 2023
SP - 176
EP - 184
DO - 10.5220/0011804000003411