A Robust Matching Algorithm Based on Global Motion Smoothness Criterion

  • Mikhail Mozerov
  • Vitaly Kober
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3773)

Abstract

A new robust matching algorithm for motion detection and computation of precise estimates of motion vectors of moving objects in a sequence of images is presented. Common matching algorithms of dynamic image analysis usually utilize local smoothness constraints. The proposed method exploits global motion smoothness. The suggested matching algorithm is robust to motion discontinuity as well as to noise degradation of a signal. Computer simulation and experimental results demonstrate an excellent performance of the method in terms of dynamic motion analysis.

Keywords

Optical Flow Motion Vector Smoothness Constraint Dissimilarity Function Motion Vector 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.

References

  1. 1.
    Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artificial Intelligence 17, 185–204 (1981)CrossRefGoogle Scholar
  2. 2.
    Watson, A.B., Ahumada, A.J.: Motion: Perception and Representation. In: Tsotsos, J.K. (ed.), pp. 1–10 (1983)Google Scholar
  3. 3.
    Ohta, Y., Kanade, T.: Stereo by intra- and inter-scanline search using dynamic programming. IEEE Trans. Pattern Anal. Machine Intell. 7, 139–154 (1985)CrossRefGoogle Scholar
  4. 4.
    Anandan, P.: Measuring Visual Motion from Image Sequences. PhD thesis, Univ. of Massachusetts, Amherst (1987)Google Scholar
  5. 5.
    Heitz, F., Bouthemy, P.: Multimodal estimation of discontinuous optical flow using Markov random fields. IEEE Transactions on Pattern Analysis and Machine Intelligence 15, 1213–1232 (1993)CrossRefGoogle Scholar
  6. 6.
    Kanade, T., Okutomi, M.: A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment. IEEE Trans. Pattern Analysis and Machine Intelligence 16, 920–932 (1994)CrossRefGoogle Scholar
  7. 7.
    Cedaras, C., Shah, M.: Motion based recognition: A survey. Image and Vision Computing 13, 129–154 (1995)CrossRefGoogle Scholar
  8. 8.
    Anthony, Y.K.H., Pong, T.C.: Cooperative fusion of stereo and motion. Pattern Recognition 28, 553–562 (1995)CrossRefGoogle Scholar
  9. 9.
    Chung, H.Y., Yung, N.H.C., Cheung, P.Y.S.: Fast motion estimation with search-center prediction. Optical Engineering 40, 952–963 (2001)CrossRefGoogle Scholar
  10. 10.
    Petrakis, E.G.M., Diplaros, A., Milios, E.: Matching and retrieval of distorted and occluded shapes using dynamic programming. IEEE Trans. Pattern Anal. Machine Intell. 24, 1501–1516 (2002)CrossRefGoogle Scholar
  11. 11.
    Mozerov, M., Kober, V., Tchernykh, A., Choi, T.S.: Motion estimation with a modified dynamic programming. Optical Engineering 41, 2592–2598 (2002)CrossRefGoogle Scholar
  12. 12.
    Mozerov, M., Kober, V.: Motion Estimation Based on Hidden Segmentation. IEICE Transaction on Fund. E88-A, 376–381 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Mikhail Mozerov
    • 1
  • Vitaly Kober
    • 2
  1. 1.Institute for Information Transmission Problems of RASMoscowRussia
  2. 2.Department of Computer ScienceDivision of Applied Physics, CICESEEnsenadaMéxico

Personalised recommendations