Julia Yang, The Boeing Company; Jacob Lucas, The Boeing Company; Trent Kyono, The Boeing Company; Michael Abercrombie, The Boeing Company; Justin Fletcher, Odyssey Systems Consulting; Ian McQuaid, Air Force Research Laboratory
Keywords: Semantic Segmentation, Component Segmentation, Satellite Segmentation, Segmentation, LEO, Low Earth Objects, Atmospheric Turbulence, Imaging, Ground-based imaging, Neural Network, CNN, Machine Learning, SSA, SDA
Abstract:
Ground-based imaging of Low Earth Objects (LEO) is subject to perturbations by atmospheric turbulence, which makes it difficult to identify key features or components on the object of interest. Techniques for reconstructing images have been developed, but it is still up to a human to subjectively discern and identify truth features on a partially reconstructed image. In this paper, we present a neural network 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 (r0) and show the viability of this method.
Date of Conference: September 14-17, 2021
Track: Machine Learning for SSA Applications