High Precision Restoration Method for Non-uniformly Warped Images

  • Kalyan Kumar Halder
  • Murat Tahtali
  • Sreenatha G. Anavatti
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8192)


This paper proposes a high accuracy image restoration technique to restore a quality image from the atmospheric turbulence degraded video sequence of a static scenery. This approach contains two major steps. In the first step, we employ a coarse-to-fine optical flow estimation technique to register all the frames of the video to a reference frame and determine the shift maps. In the second step, we use an iterative First Register Then Average And Subtract (iFRTAAS) method to correct the geometric distortions of the reference frame. We present a performance comparison between our proposed method and existing statistical method in terms of restoration accuracy. Simulation experiments show that our proposed method provides higher accuracy with substantial gain in processing time.


Atmospheric turbulence image registration image restoration and optical flow 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Tahtali, M., Fraser, D., Lambert, A.J.: Restoration of non-uniformly warped images using a typical frame as prototype. In: Proc. TENCON, pp. 1–6 (2005)Google Scholar
  2. 2.
    Tahtali, M., Lambert, A.J., Fraser, D.: Restoration of nonuniformly warped images using accurate frame by frame shiftmap accumulation. In: Proc. SPIE, vol. 6316 (2006)Google Scholar
  3. 3.
    Huebner, C.S., Greco, M.: Blind deconvolution algorithms for the restoration of atmospherically degraded imagery: a comparative analysis. In: Proc. SPIE, vol. 7108 (2008)Google Scholar
  4. 4.
    Li, D., Mersereau, R.M., Simske, S.: Atmospheric turbulence-degraded image restoration using principal components analysis. IEEE Geoscience and Remote Sensing Letters 4(3), 340–344 (2007)CrossRefGoogle Scholar
  5. 5.
    Zhu, X., Milanfar, P.: Image reconstruction from videos distorted by atmospheric turbulence. In: Proc. SPIE, vol. 7543 (2010)Google Scholar
  6. 6.
    Yan, L., Jin, M., Fang, H., Liu, H., Zhang, T.: Atmospheric-turbulence-degraded astronomical image restoration by minimizing second-order central moment. IEEE Geoscience and Remote Sensing Letters 9(4), 672–676 (2012)CrossRefGoogle Scholar
  7. 7.
    Zhang, S., Wu, Y., Zhao, J., Wang, J.: Astronomical image restoration through atmosphere turbulence by lucky imaging. In: Proc. SPIE, vol. 8009 (2011)Google Scholar
  8. 8.
    Gerwe, D.R., Plonus, M.A.: Superresolved image reconstruction of images taken through the turbulent atmosphere. J. Opt. Soc. Am. A 15(10), 2620–2628 (1998)CrossRefGoogle Scholar
  9. 9.
    Mao, Y., Gilles, J.: Non rigid geometric distortions correction-application to atmospheric turbulence stabilization. Inverse Problems and Imaging 6(3), 531–546 (2012)MathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    Clyde, D., Scott-Fleming, I., Fraser, D., Lambert, A.: Application of optical flow techniques in the restoration of non-uniformly warped images. In: Proc. DICTA, pp. 195–200 (2002)Google Scholar
  11. 11.
    Abdoola, R., Wyk, B., Monacelli, E.: A simple statistical algorithm for the correction of atmospheric turbulence degraded sequences. In: Proc. Annual Symposium of the Pattern Recognition Association of South Africa (2010)Google Scholar
  12. 12.
    Tahtali, M., Lambert, A.J., Fraser, D.: Graphics processing unit restoration of non-uniformly warped images using a typical frame as prototype. In: Proc. SPIE, vol. 7800 (2010)Google Scholar
  13. 13.
    Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  14. 14.
    Liu, C.: Beyond pixels: exploring new representations and applications for motion analysis. Massachusetts Institute of Technology (2009)Google Scholar
  15. 15.
    Pennec, X.: Probabilities and statistics on riemannian manifolds: a geometric approach. Research Report 5093, INRIA (2004)Google Scholar
  16. 16.
    Micheli, M., Lou, Y., Soatto, S., Bertozzi, A.L.: A linear systems approach to imaging through turbulence. Journal of Mathematical Imaging and Vision, 1–17 (2013)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Kalyan Kumar Halder
    • 1
  • Murat Tahtali
    • 1
  • Sreenatha G. Anavatti
    • 1
  1. 1.School of Engineering and Information TechnologyThe University of New South WalesCanberraAustralia

Personalised recommendations