Advertisement

Discrete-time rigidity-constrained optical flow

  • Jeffrey Mendelsohn
  • Eero Simoncelli
  • Ruzena Bajcsy
Structure from Motion
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1296)

Abstract

An algorithm for optical flow estimation is presented for the case of discrete-time motion of an uncalibrated camera through a rigid world. Unlike traditional optical flow approaches that impose smoothness constraints on the flow field, this algorithm assumes smoothness on the inverse depth map. The computation is based on differential measurements and estimates are computed within a multi-scale decomposition. Thus, the method is able to operate properly with large displacements (i.e., large velocities or low frame rates. Results are shown for a synthetic and a real sequence.

Keywords

Optical Flow Real Sequence Angular Error Discrete Motion Optical Flow Field 
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.
    P. P. Anandan. A Computational Framework and an Algorithm for the Measurement of Visual Motion. IJCV, 2, 283–310, 1989.CrossRefGoogle Scholar
  2. 2.
    J. L. Barron, D. J. Fleet, and S. S. Beauchemin. Performance of Optical Flow Techniques. IJCV, 1992.Google Scholar
  3. 3.
    P. J. Burt. Fast filter transforms for image processing. Computer Graphics and Image Processing, 16, 20–51, 1981.CrossRefGoogle Scholar
  4. 4.
    J.R. Bergen, P. Anandan, K.J. Hanna, and R. Hingorani. Hierarchical ModelBased Motion Estimation. Proc. ECCV, 237–252, Springer-Verlag, Santa Margherita Ligure, Italy, 1992.Google Scholar
  5. 5.
    W. Eukelmann and H. Nagel. Investigation of Multigrid Algorithms for Estimation of Optical Flow Fields in Image Sequences. Computer Vision Graphics Image Processing, 43, 150–177, 1988.CrossRefGoogle Scholar
  6. 6.
    R. Hartley. Projective Reconstruction from Line Correspondences. Proc. IEEE CVPR, 1994.Google Scholar
  7. 7.
    R. Hartley, R. Gupta, and T. Chang. Stereo from Uncalibrated Cameras. Proc. IEEE CVPR, 1992.Google Scholar
  8. 8.
    B.K.P. Horn. Robot Vision. MIT Press, Cambridge, MA, 1986.Google Scholar
  9. 9.
    M. Leuttgen, W. Karl, and A. Willsky. Efficient Multiscale Regularization with Applications to the Computation of Optical Flow. IEEE Trans. Im. Proc., 1992.Google Scholar
  10. 10.
    H. C. Longuet-Higgins and K. Prazdny. The interpretation of a moving retinal image. Proc. Royal Society of London B, 208, 385–397, 1980.Google Scholar
  11. 11.
    Q.T. Luong and T. Vieville. Canonic Representation for the Geometry of Multiple Projective Views. Proc. ECCV, Stockholm, 1994.Google Scholar
  12. 12.
    Q.T. Luong and O. Faugeras. The Fundamental Matrix: Theory, Algorithms, and Stability Analysis. IJCV, 43–76, 1996.Google Scholar
  13. 13.
    J. Mendelsohn, E. Simoncelli, and R. Bajcsy. Discrete-Time Rigid Motion Constrained Optical Flow Assuming Planar Structure. Univ. of PA GRASP Laboratory Technical Report #410, 1997.Google Scholar
  14. 14.
    A. Shashua and N. Navab. Relative Affine Structure: Theory and Application to 3D Reconstruction from Perspective Views. Proc. IEEE CVPR, Seattle, June 1994.Google Scholar
  15. 15.
    E. P. Simoncelli, E. H. Adelson, and D. J. Heeger. Probability Distributions of Optical Flow. Proc. IEEE CVPR, Maui, June 1991.Google Scholar
  16. 16.
    T. Vieville and O. D. Faugeras. The First Order Expansion of Motion Equations in the Uncalibrated Case. Computer Vision and Image Understanding, 128–146, July 1996.Google Scholar
  17. 17.
    T. Vieville, C. Zeller, and L. Robert. Using Collineations to Compute Motion and Structure in an Uncalibrated Image Sequence. IJCV, 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Jeffrey Mendelsohn
    • 1
  • Eero Simoncelli
    • 2
  • Ruzena Bajcsy
    • 1
  1. 1.University of PennsylvaniaPhiladelphiaUSA
  2. 2.New York UniversityNew YorkUSA

Personalised recommendations