Skip to main content

Better Flow Estimation from Color Images


One of the difficulties in estimating optical flow is bias. Correcting the bias using the classical techniques is very difficult. The reason is that knowledge of the error statistics is required, which usually cannot be obtained because of lack of data. In this paper, we present an approach which utilizes color information. Color images do not provide more geometric information than monochromatic images to the estimation of optic flow. They do, however, contain additional statistical information. By utilizing the technique of instrumental variables, bias from multiple noise sources can be robustly corrected without computing the parameters of the noise distribution. Experiments on synthesized and real data demonstrate the efficiency of the algorithm.


  1. Horn BKP, Schunck BG: Determining optical flow. Artificial Intelligence 1981,17(1–3):185-203.

    Article  Google Scholar 

  2. Barron JL, Fleet DJ, Beauchemin SS: Performance of optical flow techniques. International Journal of Computer Vision 1994,12(1):43-77. 10.1007/BF01420984

    Article  Google Scholar 

  3. Nagel H-H: Optical flow estimation and the interaction between measurement errors at adjacent pixel positions. International Journal of Computer Vision 1995,15(3):271-288. 10.1007/BF01451744

    Article  MathSciNet  Google Scholar 

  4. Fermüller C, Shulman D, Aloimonos Y: The statistics of optical flow. Computer Vision and Image Understanding 2001,82(1):1-32. 10.1006/cviu.2000.0900

    Article  Google Scholar 

  5. Kanatani K: Statistical Optimization for Geometric Computation: Theory and Practice. Elsevier Science, Oxford, UK; 1996.

    MATH  Google Scholar 

  6. Bride J, Meer P: Registration via direct methods: a statistical approach. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR '01), December 2001, Kauai, Hawaii, USA 1: 984–989.

    Google Scholar 

  7. Andrews RJ, Lovell BC: Color optical flow. Proceedings of the Workshop on Digital Image Computing, February 2003, Brisbane, Australia 1: 135–139.

    Google Scholar 

  8. Golland P, Bruckstein AM: Motion from Color. Computer Vision and Image Understanding 1997,68(3):346-362. 10.1006/cviu.1997.0553

    Article  Google Scholar 

  9. Fuller WA: Measurement Error Models. John Wiley & Sons, New York, NY, USA; 1987.

    Book  Google Scholar 

  10. Van Huffel S, Vandewalle J: The Total Least Squares Problem: Computational Aspects and Analysis, Frontiers in Applied Mathematics Series. Volume 9. SIAM, Philadelphia, Pa, USA; 1991.

    Book  Google Scholar 

  11. Carroll RJ, Ruppert D: The use and misuse of orthogonal regression estimation in linear errors-in-variables models. Department of Statistics, University of Texas A&M, College Station, Tex, USA; 1994.

    Google Scholar 

  12. Ng L, Solo V: Errors-in-variables modeling in optical flow estimation. IEEE Transactions on Image Processing 2001,10(10):1528-1540. 10.1109/83.951538

    Article  Google Scholar 

  13. Lucas BD, Kanade T: An iterative image registration technique with an application to stereo vision. Proceedings of the 7th International Joint Conference on Artificial Intelligence (IJCAI '81), August 1981, Vancouver, BC, Canada 674–679.

    Google Scholar 

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to Hui Ji.

Rights and permissions

Open Access This article is distributed under the terms of the Creative Commons Attribution 2.0 International License (, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Reprints and permissions

About this article

Cite this article

Ji, H., Fermüller, C. Better Flow Estimation from Color Images. EURASIP J. Adv. Signal Process. 2007, 053912 (2007).

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: