No Cover Image

Conference Paper/Proceeding/Abstract 23 views

SIGNN - Star Identification using Graph Neural Networks

Floyd Hepburn-Dickins, Mark Jones Orcid Logo, Mike Edwards Orcid Logo, Jay Morgan Orcid Logo, Steve Bell

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Feb. 2025

Swansea University Authors: Floyd Hepburn-Dickins, Mark Jones Orcid Logo, Mike Edwards Orcid Logo, Jay Morgan Orcid Logo

Abstract

As a solution for the lost-in-space star identification problem we present Star Identification using Graph Neural Network (SIGNN), a novel approach using Graph Attention Networks. By representing the celestial sphere as a graph data structure, created from the ESA's Hipparcos catalogue, we are...

Full description

Published in: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Feb. 2025
Published:
URI: https://cronfa.swan.ac.uk/Record/cronfa68091
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: As a solution for the lost-in-space star identification problem we present Star Identification using Graph Neural Network (SIGNN), a novel approach using Graph Attention Networks. By representing the celestial sphere as a graph data structure, created from the ESA's Hipparcos catalogue, we are able to accurately capture the rich information and relationships within local star fields. Graph learning techniques allow our model to aggregate information and learn the relative importance of the nodes and structure within each stars local neighbourhood to it's identification. This approach, combined with our parametric data-generation and noise simulation, allows us to train a highly robust model capable of accurate star identification even under intensive noise, outperforming existing methods. Code and generation techniques will be available on github.com.
College: College of Science
Funders: EPSRC