Saved in:
Bibliographic Details
Main Authors: Hammad, May, Hammad, Menatallh
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.26582
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909000734343168
author Hammad, May
Hammad, Menatallh
author_facet Hammad, May
Hammad, Menatallh
contents Reliable celestial attitude determination is a critical requirement for autonomous spacecraft navigation, yet traditional "Lost-in-Space" (LIS) algorithms often suffer from high computational overhead and sensitivity to sensor-induced noise. While deep learning has emerged as a promising alternative, standard regression models are often confounded by the non-Euclidean topology of the celestial sphere and by the periodic boundary conditions of Right Ascension (RA) and Declination (Dec). In this paper, we present Star-Fusion, a multi-modal architecture that reformulates orientation estimation as a discrete topological classification task. Our approach leverages spherical K-Means clustering to partition the celestial sphere into K topologically consistent regions, effectively mitigating coordinate wrapping artifacts. The proposed architecture employs a tripartite fusion strategy: a SwinV2-Tiny transformer backbone for photometric feature extraction, a convolutional heatmap branch for spatial grounding, and a coordinate-based MLP for geometric anchoring. Experimental evaluations on a synthetic Hipparcos-derived dataset demonstrate that Star-Fusion achieves a Top-1 accuracy of 93.4% and a Top-3 accuracy of 97.8%. Furthermore, the model exhibits high computational efficiency, maintaining an inference latency of 18.4 ms on resource-constrained COTS hardware, making it a viable candidate for real-time onboard deployment in next-generation satellite constellations.
format Preprint
id arxiv_https___arxiv_org_abs_2604_26582
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Star-Fusion: A Multi-modal Transformer Architecture for Discrete Celestial Orientation via Spherical Topology
Hammad, May
Hammad, Menatallh
Computer Vision and Pattern Recognition
Artificial Intelligence
Reliable celestial attitude determination is a critical requirement for autonomous spacecraft navigation, yet traditional "Lost-in-Space" (LIS) algorithms often suffer from high computational overhead and sensitivity to sensor-induced noise. While deep learning has emerged as a promising alternative, standard regression models are often confounded by the non-Euclidean topology of the celestial sphere and by the periodic boundary conditions of Right Ascension (RA) and Declination (Dec). In this paper, we present Star-Fusion, a multi-modal architecture that reformulates orientation estimation as a discrete topological classification task. Our approach leverages spherical K-Means clustering to partition the celestial sphere into K topologically consistent regions, effectively mitigating coordinate wrapping artifacts. The proposed architecture employs a tripartite fusion strategy: a SwinV2-Tiny transformer backbone for photometric feature extraction, a convolutional heatmap branch for spatial grounding, and a coordinate-based MLP for geometric anchoring. Experimental evaluations on a synthetic Hipparcos-derived dataset demonstrate that Star-Fusion achieves a Top-1 accuracy of 93.4% and a Top-3 accuracy of 97.8%. Furthermore, the model exhibits high computational efficiency, maintaining an inference latency of 18.4 ms on resource-constrained COTS hardware, making it a viable candidate for real-time onboard deployment in next-generation satellite constellations.
title Star-Fusion: A Multi-modal Transformer Architecture for Discrete Celestial Orientation via Spherical Topology
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2604.26582