Motion Vector Prediction Using Frequency Sensitive Competitive Learning

  • HyungJun Kim
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4233)


We propose a search region prediction method using a Frequency Sensitive Competitive Learning(FSCL) algorithm for the adaptive vector quantization of the motion vector. We train the motion vector codebook using the first two successive images of a sequence of images and utilize it for search region prediction. The proposed method can reduce computation time by using a smaller number of search points compared to other methods, and also decreases the bits required to represent motion vectors. The experimental results show that it provides competitive PSNR values compared to other block matching algorithms.


Motion Vector Motion Estimation Vector Quantization Search Point Full Search 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Li, B., Li, W., Tu, Y.: A fast block-matching algorithm using smooth motion vector field adaptive search technique. Journal of Computer Science and Technology 18(1), 14–21 (2003)MATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Yao, W., Wenger, S., Jiantao, W., Katsaggelos, A.K.: Error resilient video coding techniques. IEEE Signal Processing Magazine 17(4), 61–82 (2000)CrossRefGoogle Scholar
  3. 3.
    Oh, H.S., Lee, H.K.: Block-matching algorithm based on an adaptive reduction of the search area for motion estimation. Real-Time Imaging 6, 407–414 (2000)MATHCrossRefGoogle Scholar
  4. 4.
    Iinuma, K., Koga, T., Niwa, K., Iijima, Y.: A motion-compensated interframe codec. In: Proc. Image Coding, SPIE, vol. 594, pp. 194–201 (1985)Google Scholar
  5. 5.
    Lee, Y.Y., Woods, J.W.: Motion vector quantization for video coding. IEEE Trans. Image Processing 4(3) (March 1995)Google Scholar
  6. 6.
    Gersho, A., Gray, R.M.: Vector Quantization and Signal Compression. Kluwer Academic Publishers, Dordrecht (1991)Google Scholar
  7. 7.
    Al Sayeed, C., Ishteak Hossain, A.: Image compression using frequency-sensitive competitive neural network. In: Proceedings of the SPIE, vol. 5637, pp. 611–618 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • HyungJun Kim
    • 1
  1. 1.Division of Information TechnologyHansei UniversityKorea

Personalised recommendations