SILO: A Machine Learning Dataset of Synthetic Ground-Based Observations of LEO Satellites

Images of space objects may have their interpretability assessed with a Space-object National Imagery Interpretability Rating Scale (SNIIRS) score. The rules for such scores are specific, but the process of rating a large number of images can be time-consuming even for a skilled analyst. As this scale is subjective and based on interpretability of resolved features, it is also difficult to provide automated SNIIRS assessments with a simple algorithmic procedure. A Convolutional Neural Network (CNN) may be able to solve this problem, but such an effort requires a large labeled dataset of images. In this paper we will describe the effort to use wave-optics simulations to generate a dataset of SNIIRS-scored images of Low Earth Orbit (LEO) satellites observed from a ground-based optical observatory with varied turbulence conditions. This first iteration of the Scored Images of LEO Objects (SILO) dataset is intended to serve as a foundation for deep learning efforts, similar to how MNIST and ImageNet have been foundational datasets in other machine vision domains. This dataset is already being used in numerous machine learning efforts, including those pertaining to using CNNs to perform image interpretability assessment and to produce higher-resolution image recoveries from degraded image sets. In this paper we also describe some of the other potential uses for this dataset.

[1]  Stuart Jefferies,et al.  Multiframe blind deconvolution for imaging in daylight and strong turbulence conditions , 2011, Optical Engineering + Applications.

[2]  Michael Kelley,et al.  National imagery interpretation rating system and the probabilities of detection, recognition, and identification , 1997 .

[3]  Brandoch Calef,et al.  Recent improvements in advanced automated post-processing at the AMOS observatories , 2015, 2015 IEEE Aerospace Conference.

[4]  James Demmel,et al.  IEEE Standard for Floating-Point Arithmetic , 2008 .

[5]  Michael C. Roggemann,et al.  Blind image quality metrics for optimal speckle image reconstruction in horizontal imaging scenarios , 2012 .

[6]  B. Welsh,et al.  Imaging Through Turbulence , 1996 .

[7]  Ce Zhang,et al.  Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit , 2017, ArXiv.

[8]  Honggang Bai.  The Design and Analysis Based on NIIRS for Remote Sensing Systems , 2012, 2012 Symposium on Photonics and Optoelectronics.

[9]  S. Gigan,et al.  Single-shot diffraction-limited imaging through scattering layers via bispectrum analysis. , 2016, Optics letters.

[10]  E. Kinkead,et al.  UNITED STATES AIR FORCE , 1995 .

[11]  Michael Roggemann,et al.  Improving optical imaging of dim SSA targets with simplified adaptive optics systems , 2018, 2018 IEEE Aerospace Conference.

[12]  Keith A. Bush,et al.  Satellite discrimination from active and passive polarization signatures: simulation predictions using the TASAT satellite model , 2002, SPIE Optics + Photonics.

[13]  Timothy J. Schulz,et al.  Multiframe blind deconvolution of astronomical images , 1993 .

[14]  Stuart M. Jefferies,et al.  Physically constrained iterative deconvolution of adaptive optics images , 1998, Remote Sensing.

[15]  David Blanchard,et al.  General Image Quality Equation; GIQE version 5 , 2015 .

[16]  Yikang Yang,et al.  Space targets adaptive optics images blind restoration by convolutional neural network , 2019, Optical Engineering.

[17]  Stacie Williams,et al.  A new performance metric for hybrid adaptive optics systems , 2014, 2014 IEEE Aerospace Conference.

[18]  Richard B Holmes,et al.  Analytical expressions for the log-amplitude correlation function for plane wave propagation in anisotropic non-Kolmogorov refractive turbulence. , 2012, Journal of the Optical Society of America. A, Optics, image science, and vision.

[19]  D. Buscher,et al.  Interferometric imaging of geo-synchronous satellites with ground-based telescopes , 2013, 2013 IEEE Aerospace Conference.

[20]  J C Leachtenauer,et al.  General Image-Quality Equation: GIQE. , 1997, Applied optics.

[21]  Peter Deutsch,et al.  GZIP file format specification version 4.3 , 1996, RFC.

[22]  F. E. Nicodemus,et al.  Geometrical considerations and nomenclature for reflectance , 1977 .

[23]  D. Fried.  Optical Resolution Through a Randomly Inhomogeneous Medium for Very Long and Very Short Exposures , 1966 .

[24]  Roberto Furfaro,et al.  Space Objects Classification via Light-Curve Measurements: Deep Convolutional Neural Networks and Model-based Transfer Learning , 2018 .

[25]  James F. Riker,et al.  The time-domain analysis simulation for advanced tracking (TASAT) approaches to compensated imaging , 1992, Defense, Security, and Sensing.

[26]  Robert K. Tyson,et al.  Field Guide to Adaptive Optics, Second Edition , 2012 .

[27]  John M. Irvine,et al.  National imagery interpretability rating scales (NIIRS): overview and methodology , 1997, Optics & Photonics.

[28]  Stuart Jefferies,et al.  Fast and optimal multiframe blind deconvolution algorithm for high-resolution ground-based imaging of space objects. , 2009, Applied optics.

[29]  J. Hardy,et al.  Adaptive Optics for Astronomical Telescopes , 1998 .

[30]  Brett J. Borghetti,et al.  Space Object Identification using Deep Neural Networks , 2018 .

[31]  Pedro Negrete-Regagnon,et al.  Practical aspects of image recovery by means of the bispectrum , 1996 .

[32]  J. Christou,et al.  Restoration of Astronomical Images by Iterative Blind Deconvolution , 1993 .

[33]  Genshe Chen,et al.  Space object classification using deep neural networks , 2018, 2018 IEEE Aerospace Conference.

[34]  Richard B Holmes,et al.  Analytical expressions for the log-amplitude correlation function for spherical wave propagation through anisotropic non-Kolmogorov atmosphere. , 2014, Journal of the Optical Society of America. A, Optics, image science, and vision.

[35]  Christopher J. Florio,et al.  The use of the general image quality equation in the design and evaluation of imaging systems , 2009, Optical Engineering + Applications.

[36]  Neil Davey,et al.  An automatic taxonomy of galaxy morphology using unsupervised machine learning , 2017, 1709.05834.

[37]  V. I. Talanov,et al.  Focusing of Light in Cubic Media , 1970 .