Automated Interpretability Scoring of Ground-Based Observations of LEO Objects with Deep Learning

The Space-object National Imagery Interpretability Rating Scale (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. We use wave-optics simulation with varied turbulence strength to generate a dataset of images of Low-Earth Orbit (LEO) satellites observed from a ground-based optical observatory. SNIIRS scores are automatically generated for these images based on a combination of a priori knowledge of each object's simulated features and the simulated turbulence strength. A neural network is then trained to provide accurate SNIIRS scores from single images without being provided knowledge of the object model.

[1]  Yi Li,et al.  Convolutional Neural Networks for No-Reference Image Quality Assessment , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Linda M. Thomas,et al.  Atmospheric Propagation VIII , 2011 .

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

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

[5]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[7]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[8]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[9]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[11]  Brandoch Calef,et al.  Recovering astronomical images with deep neural network supported bispectrum processing , 2018 .

[12]  Richard B. Holmes,et al.  Phase screen simulations of laser propagation through non-Kolmogorov atmospheric turbulence , 2011, Defense + Commercial Sensing.

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

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

[15]  J. Mooney,et al.  Modular Mount Control System for Telescopes , 2017 .

[16]  Peyman Milanfar,et al.  NIMA: Neural Image Assessment , 2017, IEEE Transactions on Image Processing.

[17]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Determining Multi-frame Blind Deconvolution Resolvability using Deep Learning , 2019 .

[19]  François Chollet,et al.  Xception: Deep Learning with Depthwise Separable Convolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[21]  Fiona J Gilbert,et al.  Improving Workflow Efficiency for Mammography Using Machine Learning. , 2020, Journal of the American College of Radiology : JACR.

[22]  Stockholm University,et al.  Real-time multiframe blind deconvolution of solar images. , 2018, 1806.07150.

[23]  Levi Fussell,et al.  Forging new worlds: high-resolution synthetic galaxies with chained generative adversarial networks , 2018, Monthly Notices of the Royal Astronomical Society.