Advertisement

Optical Flow in Log-mapped Image Plane

A New Approach
  • Mohammed Yeasin
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1998)

Abstract

In this article we propose a novel approach to compute the optical flow directly on log-mapped images. We propose the use of a generalized dynamic image model (GDIM) based method for computing the optical flow as opposed to the brightness constancy model (BCM) based method. We introduce a new notion of “variable window” and use the space-variant form of gradient operator while computing the spatiotemporal gradient in log-mapped images for a better accuracy and to ensure that the local neighborhood is preserved. We emphasize that the proposed method must be numerically accurate, provides a consistent interpretation and is capable of computing the peripheral motion. Experimental results on both the synthetic and real images have been presented to show the efficacy of the proposed method.

Keywords

Optical Flow Image Motion Angular Error Average Relative Error Variable Window 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    K. Daniilidis, C. Krauss, M. Hansen, G. Sommer: Real-time tracking with moving objects with an active camera. J. of Real-time Imaging, Academic Press, (1997). 252, 254Google Scholar
  2. 2.
    M. Tistarelli, G. Sandini: On the advantage of log-polar mapping for estimation of time to impact from the optical flow. IEEE Trans. on Patt. Analysis and Mach. Intl., 15 (1993) 401–410. 252CrossRefGoogle Scholar
  3. 3.
    K. Daniilidis, V. Krüger: Optical flow computation in the log-polar plane. Technical report, CAIP, (1995). 252Google Scholar
  4. 4.
    K. Daniilidis: Computation of 3d-motion parameters using the log-polar transform. Technical report, CAIP, (1995). 252Google Scholar
  5. 5.
    B. Fischl, A. Cohen, E. L. Schwartz: Rapid anisotropic diffusion using space-variant vision. Internat. J. of Comp. Vision, 28 (1998) 199–212. 253CrossRefGoogle Scholar
  6. 6.
    S. Negadharipour: Revised definition of optical flow: Integration of radio-metric and geometric cues for dynamic scene analysis. IEEE Trans. on Pat. Analysis and Mach. Intl., 20 (1998) 961–979. 253, 255CrossRefGoogle Scholar
  7. 7.
    R. J. Woodham: Multiple light source optical flow. In: the Proceed. of Internat. Conf. on Computer Vision, Osaka, Japan, (Dec. 1990).Google Scholar
  8. 8.
    B. K. P. Horn, B. G. Schunk: Determining optical flow. Artificial Intelligence, 17 (1981) 185–203. 254CrossRefGoogle Scholar
  9. 9.
    J. K. Kearney, W. R. Thompson, D.L. Bolly: Optical flow estimation, an error analysis of gradient based methods with local optimization. IEEE Trans. on Pattern Anal. and Mach. Intell., 14 (1987) 229–244.CrossRefGoogle Scholar
  10. 10.
    B. Horn, B. Schunck: Determining optical flow, Artificial Intelligence, 17 (1981) 185–204. 253CrossRefGoogle Scholar
  11. 11.
    P. Anandan: Measuring visual motion from image sequences, PhD thesis, University of Massachussetts, Amherst, MA, (1987). 253Google Scholar
  12. 12.
    A. B. Watson, A. J. Ahumada: A look at motion in the frequency domain. In: Motion: perception and representation, J. K. Tsotsos (ed.), (1983) 1–10. 253Google Scholar
  13. 13.
    J. L. Barron, D. J. Fleet, S. S. Beauchemin: Performance of optical flow techniques. Internat. J. of Computer Vision, 12 (1994) 43–77. 253CrossRefGoogle Scholar
  14. 14.
    E. L. Schwartz: Computational studies of spatial architecture of primate visual cortex. Vol 10, Chap. 9, Plenum, New York, (1994) 359–411. 253Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Mohammed Yeasin
    • 1
  1. 1.Dept. of Computer Science and Engg.The Pennsylvania State UniversityPA

Personalised recommendations