Jacob Lucas, The Boeing Company; Trent Kyono, The Boeing Company; Michael Werth, The Boeing Company; Justin Fletcher, Odyssey Systems Consulting; Ian McQuaid, AFRL
Keywords: Convolutional Neural Netrorks, Machine Learning, Imaging, SSA
Abstract:
The Space-object National Imagery Interpretability Rating Scale (Space NIIRS or SNIIRS) allows human analysts to provide a quantitative score of image quality based on identification of target features. It is naturally difficult to automate this scoring process, not only because the scale is based on identifiable features but also because the images may be in an almost-resolved image quality regime that is difficult to handle for traditional machine vision techniques. In this paper we explore using a convolutional neural network to automatically produce SNIIRS scores from images of LEO satellites. The neural network is trained with a catalog of analyst-graded images of resolved space objects and then its performance is assessed by comparing the network accuracy to that of a trained analyst.
Date of Conference: September 17-20, 2019
Track: Machine Learning for SSA Applications