Integral based approach for determining motion vector fields

  • Atsushi Nomura
Poster Session B: Active Vision, Motion, Shape, Stereo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1310)


This paper describes a method determining a motion vector field from an image sequence. In this method, a couple of a basic constraint equations in integral form and an additional constraint equation of spatio-temporal local constancy of a motion vector field is solved by the over-deterministic approach such as the least squares method. The method is applied to artificially synthesized image sequences and a real image one. As the results, robustness of the proposed method to noisy image sequences is confirmed. In addition, it is confirmed that the method requires less calculation cost than a conventional spatio-temporal optimization method.


  1. 1.
    S. Maybank: Theory of reconstruction from image motion. Springer-Verlag (1993)Google Scholar
  2. 2.
    P. Anandan: Computing optical flow from two frames of an image sequence. COINS Technical Report 86-16 (1986)Google Scholar
  3. 3.
    B. K. P. Horn and B. G. Schunck: Determining optical flow. Artificial Intelligence 17 (1981) 185–203Google Scholar
  4. 4.
    J. K. Kearney, W. B. Thompson and D. L. Boley: Optical flow estimation: an error analysis of gradient-based methods with local optimization. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-9 (1987) 229–244Google Scholar
  5. 5.
    A. Nomura, H. Miike and K. Koga: Field theory approach for determining optical flow. Pattern Recognition Letters 12 (1991) 183–190Google Scholar
  6. 6.
    J. Aisbett: Optical flow with an intensity-weighted smoothing. IEEE Transactions on Pattern Analysis and Machine Intelligence 11 (1989) 512–522Google Scholar
  7. 7.
    A. D. Bimbo, P. Nesi and J. L. C. Sanz: Analysis of optical flow constraints. IEEE Transactions on Image Processing 4 (1995) 460–469Google Scholar
  8. 8.
    N. Mukawa: Estimation of shape, reflection coefficients and illuminant direction from image sequences. Proceedings of the 3rd International Conference on Computer Vision (Osaka, Japan, 1990) 507–512Google Scholar
  9. 9.
    A. Nomura, H. Miike and K. Koga: Determining motion fields under non-uniform illumination. Pattern Recognition Letters 16 (1995) 285–296Google Scholar
  10. 10.
    K. Nakajima, A. Osa, T. Maekawa and H. Miike: Evaluation of body motion by optical flow analysis. Japanese Journal of Applied Physics 36 (1997) 2929–2937Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Atsushi Nomura
    • 1
  1. 1.Department of Cultural and International StudiesYamaguchi Prefectural UniversityYamaguchiJapan

Personalised recommendations