Ground-based imaging of objects in Low Earth Orbit (LEO) is complicated by atmospheric turbulence, which make it difficult to identify key features or components on the object of interest. Many automated image reconstruction techniques are in use, but expert labor is needed to subjectively discern and identify truth features on a partially reconstructed image. In this paper, we present a deep learning approach for semantic segmentation of ground-based images of LEO objects. We investigate the performance under various atmospheric turbulence strengths in terms of the Fried parameter ($r_{0}$) and show the viability of this method.
Semantic Segmentation of Low Earth Orbit Satellites using Convolutional Neural Networks
2022-03-05
3593762 byte
Conference paper
Electronic Resource
English
Semantic Segmentation of Low Earth Object Satellites using Convolutional Neural Networks
British Library Conference Proceedings | 2021
|Networks of Low-Earth Orbit Store-and-Forward Satellites
Online Contents | 1995
|Networks of low-Earth orbit store-and-forward satellites
IEEE | 1995
|