Advertisement

Fast Local Estimation of Optical Flow Using Variational and Wavelet Methods

  • Kai Neckeis
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2124)

Abstract

We present a framework for fast (linear time) local estimation of optical flow in image sequences. Starting from the commonly used brightness constancy assumption, a simple differential technique is derived in a first step. Afterwards, this approach will be extended by the application of a nonlinear diffusion process to the flow field in order to reduce smoothing at motion boundaries. Due to the ill-posedness of the determination of optical flow from the related differential equations, a Wavelet-Galerkin projection method is applied to regularize and linearize the problem.

Keywords

optical flow estimation wavelet methods variational methods 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Alvarez, L., Weickert, J., Sánchez, J.: Reliable Estimation of Dense Optical Flow Fields with Large Displacements. International Journal of Computer Vision 1 (2000) 205–206Google Scholar
  2. [2]
    Barron, J.L., Fleet, D.J., Beauchemin, S.S.: Performance of Optical Flow Techniques. Int. Journal of Computer Vision 12 (1994) 43–77CrossRefGoogle Scholar
  3. [3]
    Bernard, C.: Fast Optic Flow with Wavelets. Proceedings Wavelets and Applications Workshop (WAW’ 98) (1998)Google Scholar
  4. [4]
    Black, M.J., Anandan, P.: The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields. Computer Vision and Image Understanding 63(1) (1996) 75–104CrossRefGoogle Scholar
  5. [5]
    Charbonnier, P., Blanc-Féraud, L., Aubert, G., Barlaud, M.: Deterministic Edge-Preserving Regularization in Computing Imaging. IEEE Transactions on Image Processing 6(2) (1997) 298–311CrossRefGoogle Scholar
  6. [6]
    Daubechies, I.: Ten Lectures on Wavelets. CBMS-NSF Regional Conference Series in Applied Mathematics 61. SIAM Publishing, Philadelphia (1992)Google Scholar
  7. [7]
    Fleet, D.J., Langley, K.: Recursive Filters for Optical Flow. IEEE Trans. Pattern Analysis and Machine Intelligence 17(1) (1995) 61–67CrossRefGoogle Scholar
  8. [8]
    Haußecker, H., Jähne, B.: A Tensor Approach for Local Structure Analysis in Multi-Dimensional Images. In: Girod, B., Niemann, H., Seidel, H.-P. (eds.): Proceedings 3D Image Analysis and Synthesis’ 96. Proceedings in Artifical Intelligence 3 (1996) 171–178Google Scholar
  9. [9]
    Horn, B., Schunck, B.: Determining Optical Flow. Artifical Intelligence 17 (1981) 185–203CrossRefGoogle Scholar
  10. [10]
    Latto, A., Resnikoff, H.L., Tenenbaum, E.: The Evaluation of Connection Coefficients of Compactly Supported Wavelets. In: Maday, Y. (ed.): Proceedings of the French-USA Workshop on Wavelets and Turbulence. Springer Verlag, New York (1996)Google Scholar
  11. [11]
    Maaß, P.: Wavelet-projection Methods for Inverse Problems. Beiträge zur angewandten Analysis und Informatik. Shaker Verlag, Aachen (1994) 213–224Google Scholar
  12. [12]
    Mitchie, A., Bouthemy, P.: Computation and Analysis of Image Motion: A Synopsis of Current Problems and Methods. International Journal of Computer Vision 19(1) (1996) 29–55CrossRefGoogle Scholar
  13. [13]
    Nagel, H.-H., Enkelmann, W.: An Investigation of Smoothness Constraints for the Estimation of Displacement Vector Fields from Image Sequences. IEEE Transactions on Pattern Analysis and Machine Intelligence 8 (1986) 565–593CrossRefGoogle Scholar
  14. [14]
    Neckels, K.: Wavelet Filter Design via Linear Independent Basic Filters. In: Sommer, G., Zeevi, Y.Y. (eds.): Algebraic Frames for the Perception Action Cycle 2000. Springer Verlag, Berlin (2000) 251–258CrossRefGoogle Scholar
  15. [15]
    Neckels, K.: Wavelet Connection Coefficients in Higher Dimensions. Paper draft, Cognitive Systems, CAU Kiel (2000)Google Scholar
  16. [16]
    Nordström, K.N.: Biased Anisotropic Diffusion — A Unified Regularization and Diffusion Approach to Edge Detection. Technical Report. University of California, Berkeley (1989) 89–514Google Scholar
  17. [17]
    Perona, P., Malik, J.: Scale Space and Edge Detection Using Anisotropic Diffusion. IEEE Trans. Pattern Analysis and Machine Intelligence 12 (1990) 629–639CrossRefGoogle Scholar
  18. [18]
    Resnikoff, H.L., Wells, R.O., Jr.: Wavelet Analysis —The Scalable Structure of Information. Springer Verlag, Berlin — Heidelberg — New York (1998)zbMATHGoogle Scholar
  19. [19]
    Schar, H., Körkel, S., Jähne, B.: Numerische Isotropieoptimierung von FIR-Filtern mittels Querglättung. In: Wahl, F., Paulus, E. (eds.): Proceedings Mustererkennung 1997. Springer Verlag, Berlin (1997)Google Scholar
  20. [20]
    Weber, J., Malik, J.: Robust Computation of Optical Flow in a Multi-Scale Differential Framework. International Journal of Computer Vision 2 (1994) 5–19Google Scholar
  21. [21]
    Weickert, J.: Anisotropic Diffusion in Image Processing. B.G. Teubner, Stuttgart (1998)zbMATHGoogle Scholar
  22. [22]
    Weickert, J., ter Haar Romeny, B.M., Viergever, M.A.: Efficient and Reliable Schemes for Nonlinear Diffusion Filtering. IEEE Transactions on Image Processing 7(3) (1998) 398–410CrossRefGoogle Scholar
  23. [23]
    Weickert, J., Schnörr, C.: Räumlich-zeitliche Berechnung des optischen Flusses mit nichtlinearen flußabhängigen Glattheitstermen. In: Förstner, W., Buhmann, J.M., Faber, A., Faber, P. (eds.): Mustererkennung 1999. Springer Verlag, Berlin (1999) 317–324Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Kai Neckeis
    • 1
  1. 1.Institut für Informatik und Praktische MathematikChristian-Albrecht-Universität KielKielGermany

Personalised recommendations