Advertisement

Compensating Atmospheric Turbulence with Convolutional Neural Networks for Defocused Pupil Image Wave-Front Sensors

  • Sergio Luis Suárez Gómez
  • Carlos González-Gutiérrez
  • Enrique Díez Alonso
  • Jesús Daniel Santos Rodríguez
  • Laura Bonavera
  • Juan José Fernández Valdivia
  • José Manuel Rodríguez Ramos
  • Luis Fernando Rodríguez Ramos
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10870)

Abstract

Adaptive optics are techniques used for processing the spatial resolution of astronomical images taken from large ground-based telescopes. In this work are presented computational results from a modified curvature sensor, the Tomographic Pupil Image Wave-front Sensor (TPI-WFS), which measures the turbulence of the atmosphere, expressed in terms of an expansion over Zernike polynomials.

Convolutional Neural Networks (CNN) are presented as an alternative to the TPI-WFS reconstruction. This technique is a machine learning model of the family of artificial neural networks, which are widely known for its performance as modeling and prediction technique in complex systems. Results obtained from the reconstruction of the networks are compared with the TPI-WFS reconstruction by estimating errors and optical measurements (root mean square error, mean structural similarity and Strehl ratio).

Two different scenarios are set, attending to different resolutions for the reconstruction. The reconstructed wave-fronts from both techniques are compared for wave-fronts of 25 Zernike modes and 153 Zernike modes. In general, CNN trained as reconstructor showed better performance than the reconstruction in TPI-WFS for most of the turbulent profiles, but the most significant improvements were found for higher turbulent profiles that have the lowest r0 values.

Keywords

Adaptive optics TPI-WFS Convolutional Neural Networks 

References

  1. 1.
    Fried, D.L.: Probability of getting a lucky short-exposure image through turbulence. JOSA 68(12), 1651–1658 (1978)CrossRefGoogle Scholar
  2. 2.
    Brandner, W., Hormuth, F.: Lucky imaging in astronomy. In: Boffin, Henri M.J., Hussain, G., Berger, J.-P., Schmidtobreick, L. (eds.) Astronomy at High Angular Resolution. ASSL, vol. 439, pp. 1–16. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-39739-9_1CrossRefGoogle Scholar
  3. 3.
    Oscoz, A., Rebolo, R., López, R., Pérez-Garrido, A., Pérez, J.A., Hildebrandt, S., Rodríguez, L.F., Piqueras, J.J., Villó, I., González, J.M., et al.: FastCam: a new lucky imaging instrument for medium-sized telescopes. In: Ground-based and Airborne Instrumentation for Astronomy II, vol. 7014, p. 701447 (2008)Google Scholar
  4. 4.
    Roddier, F.: Adaptive optics in astronomy. Cambridge University Press, Cambridge (1999)CrossRefGoogle Scholar
  5. 5.
    Roddier, C., Roddier, F.: Wave-front reconstruction from defocused images and the testing of ground-based optical telescopes. JOSA A 10(11), 2277–2287 (1993)CrossRefGoogle Scholar
  6. 6.
    Colodro-Conde, C., Velasco, S., Fernández-Valdivia, J.J., López, R., Oscoz, A., Rebolo, R., Femenia, B., King, D.L., Labadie, L., Mackay, C., et al.: Laboratory and telescope demonstration of the TP3-WFS for the adaptive optics segment of AOLI. Mon. Not. R. Astron. Soc. 467(3), 2855–2868 (2017)CrossRefGoogle Scholar
  7. 7.
    Villar, J.R., Chira, C., Sedano, J., González, S., Trejo, J.M.: A hybrid intelligent recognition system for the early detection of strokes. Integr. Comput. Aided Eng. 22(3), 215–227 (2015)CrossRefGoogle Scholar
  8. 8.
    Villar, J.R., Menéndez, M., Sedano, J., de la Cal, E., González, V.M.: Analyzing accelerometer data for epilepsy episode recognition. In: Herrero, Á., Sedano, J., Baruque, B., Quintián, H., Corchado, E. (eds.) 10th International Conference on Soft Computing Models in Industrial and Environmental Applications. Advances in Intelligent Systems and Computing, vol. 368, pp. 39–48. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-19719-7_4CrossRefGoogle Scholar
  9. 9.
    Osborn, J., De Cos Juez, F.J., Guzman, D., Butterley, T., Myers, R., Guesalaga, A., Laine, J.: Using artificial neural networks for open-loop tomography. Opt. Express 20(3), 2420 (2012)CrossRefGoogle Scholar
  10. 10.
    de Cos Juez, F.J., Lasheras, F.S., Roqueñí, N., Osborn, J.: An ANN-based smart tomographic reconstructor in a dynamic environment. Sensors 12(7), 8895–8911 (2012)CrossRefGoogle Scholar
  11. 11.
    Osborn, J., Guzman, D., Juez, F.J.D.C., Basden, A.G., Morris, T.J., Gendron, E., Butterley, T., Myers, R.M., Guesalaga, A., Lasheras, F.S., Victoria, M.G., Rodríguez, M.L.S., Gratadour, D., Rousset, G.: Open-loop tomography with artificial neural networks on CANARY: on-sky results. Mon. Not. R. Astron. Soc. 441(3), 2508–2514 (2014)CrossRefGoogle Scholar
  12. 12.
    Suárez Gómez, S.L., Santos Rodríguez, J.D., Iglesias Rodríguez, F.J., de Cos Juez, F.J.: Analysis of the temporal structure evolution of physical systems with the self-organising tree algorithm (SOTA): application for validating neural network systems on adaptive optics data before on-sky implementation. Entropy 19(3), 103 (2017)CrossRefGoogle Scholar
  13. 13.
    Mirowski, P.W., LeCun, Y., Madhavan, D., Kuzniecky, R.: Comparing SVM and convolutional networks for epileptic seizure prediction from intracranial EEG. In: IEEE Workshop on Machine Learning for Signal Processing, 2008. MLSP 2008, pp. 244–249 (2008)Google Scholar
  14. 14.
    Nagi, J., Ducatelle, F., Di Caro, G.A., Cireşan, D., Meier, U., Giusti, A., Nagi, F., Schmidhuber, J., Gambardella, L.M.: Max-pooling convolutional neural networks for vision-based hand gesture recognition. In: 2011 IEEE International Conference on Signal and Image Processing Applications (ICSIPA), pp. 342–347 (2011)Google Scholar
  15. 15.
    Guzmán, D., de Cos Juez, F.J., Myers, R., Guesalaga, A., Lasheras, F.S.: Modeling a MEMS deformable mirror using non-parametric estimation techniques. Opt. Express 18(20), 21356–21369 (2010)CrossRefGoogle Scholar
  16. 16.
    Noll, R.J.: Zernike polynomials and atmospheric turbulence. JOsA 66(3), 207–211 (1976)CrossRefGoogle Scholar
  17. 17.
    Vidal, F., Gendron, E., Rousset, G.: Tomography approach for multi-object adaptive optics. JOSA A 27(11), A253–A264 (2010)CrossRefGoogle Scholar
  18. 18.
    Gómez, S.L.S., Gutiérrez, C.G., Rodríguez, J.D.S., Rodríguez, M.L.S., Lasheras, F.S., de Cos Juez, F.J.: Analysing the performance of a tomographic reconstructor with different neural networks frameworks. In: Madureira, A.M., Abraham, A., Gamboa, D., Novais, P. (eds.) ISDA 2016. AISC, vol. 557, pp. 1051–1060. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-53480-0_103CrossRefGoogle Scholar
  19. 19.
    van Dam, M.A., Lane, R.G.: Extended analysis of curvature sensing. JOSA A 19(7), 1390–1397 (2002)CrossRefGoogle Scholar
  20. 20.
    van Dam, M.A., Lane, R.G.: Wave-front sensing from defocused images by use of wave-front slopes. Appl. Opt. 41(26), 5497–5502 (2002)CrossRefGoogle Scholar
  21. 21.
    Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2323 (1998)CrossRefGoogle Scholar
  22. 22.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
  23. 23.
    Graves, A., Mohamed, A., Hinton, G.: Speech recognition with deep recurrent neural networks. Icassp 3, 6645–6649 (2013)Google Scholar
  24. 24.
    Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 807–814 (2010)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Sergio Luis Suárez Gómez
    • 1
  • Carlos González-Gutiérrez
    • 2
  • Enrique Díez Alonso
    • 2
  • Jesús Daniel Santos Rodríguez
    • 1
  • Laura Bonavera
    • 1
  • Juan José Fernández Valdivia
    • 3
  • José Manuel Rodríguez Ramos
    • 3
  • Luis Fernando Rodríguez Ramos
    • 4
  1. 1.Department of PhysicsUniversity of OviedoOviedoSpain
  2. 2.Prospecting and Exploitation of Mines DepartmentUniversity of OviedoOviedoSpain
  3. 3.Wooptix S.L.San Cristóbal de La LagunaSpain
  4. 4.Instituto de Astrofísica de CanariasSan Cristóbal de La LagunaSpain

Personalised recommendations