DIFFERENNTIAL TECHNIQUE FOR MOTION COMPUTATION USING COLOUR INFORMATION

T. Bouden, N. Doghmane

2007

Abstract

Optical flow computation is an important and challenging problem in the motion analysis of images sequence. It is a difficult and computationally expensive task and is an ill-posed problem, which expresses itself as the aperture problem. However, optical flow vectors or motion can be estimated by differential techniques using regularization methods; in which additional constraints functions are introduced. In this work we propose to improve differential methods for optical flow estimation by including colour information as constraints functions in the optimization process using a simple matrix inversion. The proposed technique has shown encouraging results.

References

  1. Arredondo M. A., Lebart K. and Lane D., 2004. Optical flow using texture. In Pattern Recognition letters in Elsevier computer science, Letters25.
  2. Barron J. L., Fleet D. J., Beauchemin S. S. and Burkitt T. A., 1994. Performance of optical flow techniques. In IJCV 12 (1).
  3. Barron J. L. and Klette R., 2002. Quantitative colour optical flow. In Proc. Int. Conf. on Pattern Recognition.
  4. Beauchemin S. S. and Barron J. L., 1995. The Computation of Optical Flow. In ACM Computing Survey, 27(3).
  5. Bruno E. and Pellerin, D., 2000. Robust motion estimation using spatial gabor filters. In X European Conf. Signal Process.
  6. Horn B. K. P. and Schunck, B. G., 1981. Determining optical flow. In A.I.17.
  7. Lucas B. D. and Kanade T., 1981. An iterative image registration technique with an application to stereo vision. In 7th Int. Joint Conf. on Artificial Intelligence.
  8. Markandy V. and Flinchbaugh B. E., 1990. Multispectral constraints for optical flow computation. In Proc. 3rd ICCV, Osaka, Japan.
  9. Ming, Y., Haralick, R. M. and Shapiro, L. G., 2002. Estimating optical flow using a global matching formulation and graduated optimization. In Proc. Int. Conf. on Image Process.
  10. Polina Golland, 1995. Use of colour for optical flow estimation. In master of science in computer science, Israel institute of Technologies, Iyar 5755 Haifa.
  11. Tsai C. J., Galatsanos N. P. and Katsaggelos A. K., 1999. Optical flow estimation from noisy data using differential techniques. In Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Process., vol. 6.
  12. Weickert J. and Schnörr C., 2001. Variational optic flow computation with a spatio-temporal smoothness constraint. In Journal of Mathematical Imaging and Vision.
  13. Weber J., Malik J., 1995. Robust computation of opticalflow in a multiscale differential framework. In IJCV 14 (1).
  14. Zhang D. and Lu G., 2000. An edge and colour oriented optical flow estimation using block matching. In: Proc.5th Int. Conf. on Signal Process.
  15. Robert J. A and Brian C. Lovell, 2003. Color Optical Flow. In Lovell, Brian C. and Maeder, Anthony J, Eds. Proceedings Workshop on Digital Image Computing, pages 135-139, Brisbane.
  16. Joachim W., André B and Christoph S., 2003. Lukas/Kanade Meets Horn/Schunck: Combining Local and Global Optic Flow Methods. PrePrint N°82. In Fachrichtung 6.1- Mathematik Universität des Saarlandes.
  17. Thomax B., André B., Nils P. and Joachim W., 2004. High Accuracy Optical Flow Estimation Based on a theory for warping. In Proc., 8th European Conf. on Computer Vision, Springer LNCS 3024, T. Pajdla and J. Matas (Eds.), vol.4, PP:25-36, Prague, Czech Republic.
  18. André B., Joachim W., Christian F., Timo K. and Christoph S., 2005. Variational optical flow computation in real time. In IEEE Transactions on Image Processing. Volume 14, Num.1.
  19. Volker W., Julian E., Sebastian C. and Edgar K.; 2005.
  20. Probabilistic colour optical flow. In W. Kropatsch, R. Sablatnig, and Hanbury (Eds): DAGM 2005, LNCS 3663; PP:9-16; Springer-Verlag Berlin Heidelberg.
Download


Paper Citation


in Harvard Style

Bouden T. and Doghmane N. (2007). DIFFERENNTIAL TECHNIQUE FOR MOTION COMPUTATION USING COLOUR INFORMATION . In Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 978-972-8865-74-0, pages 531-537. DOI: 10.5220/0002054605310537


in Bibtex Style

@conference{visapp07,
author={T. Bouden and N. Doghmane},
title={DIFFERENNTIAL TECHNIQUE FOR MOTION COMPUTATION USING COLOUR INFORMATION},
booktitle={Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2007},
pages={531-537},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002054605310537},
isbn={978-972-8865-74-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,
TI - DIFFERENNTIAL TECHNIQUE FOR MOTION COMPUTATION USING COLOUR INFORMATION
SN - 978-972-8865-74-0
AU - Bouden T.
AU - Doghmane N.
PY - 2007
SP - 531
EP - 537
DO - 10.5220/0002054605310537