Skip to main content
SpringerLink
Log in

Robust Optic Flow Computation

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

This paper formulates the optic flow problem as a set of over-determined simultaneous linear equations. It then introduces and studies two new robust optic flow methods. The first technique is based on using the Least Median of Squares (LMedS) to detect the outliers. Then, the inlier group is solved using the least square technique. The second method employs a new robust statistical method named the Least Median of Squares Orthogonal Distances (LMSOD) to identify the outliers and then uses total least squares to solve the optic flow problem. The performance of both methods are studied by experiments on synthetic and real image sequences. These methods outperform other published methods both in accuracy and robustness.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Bab-Hadiashar, A. 1996. Least squares and closest point problem in optic flow estimation: The duality or the confusion. Technical Report MECSE 96-2, Monash University, Clayton, 3168, Australia, available at: http://batman.eng.monash.edu.au/ali/.

    Google Scholar 

  • Barron, J.L., Fleet, D.J., and Beauchemin, S.S. 1994. Systems and experiment performance of optical flow techniques. Intern. J. Comput. Vis., 12:43-77.

    Google Scholar 

  • Bergen, J.R., Anandan, P., Hana, K.J., and Hingorani, R. 1992. Hierarchical model-based motion estimation. In Proc. Secd. Europ. Conf. Comp. Vis., ECCV-92, Springer-Verlag, pp. 237-252.

  • Bergen, J.R., Burt, P.J., Hana, K.J., Hingorani, R., Jeanne, P., and Peleg, S. 1991. Dynamic multiple motion estimation. Artif. Inte. Comp. Vis. Proc. Israeli Conf., North Holland, pp. 147-156.

  • Black, M.J. 1994. Recursive non-linear estimation of discontinous flowfield. In Proc. of Third Europ. Conf. on Comp. Vis., ECCV-94, Springer-Verlag, pp. 138-145.

  • Black, M.J. and Anandan, P. 1991. Robust dynamic motion estimation over time. In Proc. of Computer Vision and Pattern Recognition, CVPR-91, Maui, HI, pp. 296-302.

  • Black, M.J. and Anandan, P. 1993. A framework for the robust estimation of optical flow. In Proc. Int. Conf. on Computer Vision, ICCV-93, Berlin, pp. 231-236.

  • Black, M.J. and Anandan, P. 1996. The robust estimation of multiple motion: Parametric and piecewise-smooth flow fields. Computer Vision and Image Understanding, 63(1):75-104.

    Article  Google Scholar 

  • Black, M.J. and Jepson, A.D. 1994. Estimating multiple independent motions in segmented images using parametric models with local deformations. Workshop on Motion of Non-rigid and Articulated Objects, Austin, pp. 220-227.

  • Bober, M. and Kittler, J. 1994a. Estimation of complex multimodal motion: An approach based on robust statistics and hough transform. Image and Vision Computing, 12(10):661-668.

    Article  Google Scholar 

  • Bober, M. and Kittler, J. 1994b. Robust motion analysis. In Proc. of Computer Vision and Pattern Recognition, CVPR-94, Seattle, pp. 947-952.

  • Burt, P.J., Bergen, J.R., Hingorani, R., Kolczynski, R., Lee, W.A., Leung, A., Lubin, J., and Shvaytser, H. 1989. Object tracking with a moving camera: An application of dynamic motion analysis. In Proc. of the Workshop on Visual Motion, Irvin, CA, pp. 2-12.

  • Cafforio, C. and Rocca, F. 1976. Methods for measuring small displacement of television images. IEEE Trans. Inform. Theory, IT-22:573-579.

    Article  Google Scholar 

  • Chaudhuri, S. and Chatterjee, S. 1991. Performance analysis of total least squares method in three-dimensional motion estimation. IEEE Trans. on Robotics and Automation, 7(5):707-714.

    Article  Google Scholar 

  • Chu, C.H. and Delp, E.J. 1989. Estimating displacement vector form an image sequence. J. Opt. Soc. Am. A, 6(6):871-878.

    Google Scholar 

  • Darrell, T. and Pentland, A. 1991. Robust estimation of a multilayered motion representation. IEEE Proc. of Workshop on Visual Motion, Princeton, NJ, pp. 173-178.

  • Edelsbrunner, H. and Souvaine, D.L. 1990. Computing least median of squares regression lines and guided topological sweep. J. of the American Statistical Association, 85(409):115-119.

    Google Scholar 

  • Fennema, C. and Thompson, W. 1979. Velocity determination in scenes containing several moving objects. Comput. Graph. Image Process, 9:301-315.

    Google Scholar 

  • Fleet, D.J. and Jepson, A.D. 1990. Computation of component image velocity from local phase information. Intern. J. Comput. Vis., 5:77-104.

    Google Scholar 

  • Giachetti, A. and Torre, V. 1996. Refinement of optical flow estimation and detection of motion edges. In Proc. of Fourth Europ. Conf. on Comp. Vis., ECCV-96, Springer-Verlag, pp. 151-160.

  • Hampel, F.R., and Ronchetti, E.M., Rousseeuw, P.J., and Stahel, W.A. 1986. Robust Statistics: The Approach Based on Influence Functions. John Wiley: New York.

    Google Scholar 

  • Heeger, D. 1997. Private correspondence.

  • Horn, B.K.P. 1986. Robot Vision. MIT Press: Cambridge.

    Google Scholar 

  • Horn, B.K.P. and Schunck, B.G. 1981. Determining optical flow. Artificial Intelligence, 17:185-204.

    Article  Google Scholar 

  • Iu, S.L. 1995. Robust estimation of motion vector field with discontinuity and occlusion using local outliers rejection. J. of Visual Communication and Image Representation, 6(2):132-141.

    Article  Google Scholar 

  • Jähne, B. 1993. Spatio-Temporal Image Processing, Theory and Scientific Applications. Springer-Verlag: New York.

    Google Scholar 

  • Jepson, A.D. and Black, M.J. 1993. Mixture models for optical flow computation. In Proc. of Compu. Vision and Pattern Recognition, CVPR-93, New York, pp. 760-761.

  • Jepson, A.D. and Black, M.J. 1995. Mixture models for optical flow computation. DIMACS Series in Discrete Mathematics and Theoretical Computer Science, vol. 19, pp. 271-286.

    Google Scholar 

  • Ju, S.X., Black, M.J., and Jepson, A.D. 1996. Skin and Bones: Multilayer, locally affine, optical flow and regularaization with transparency. In Proc. of Computer Vision and Pattern Recognition, CVPR-96, San Francisco, pp. 307-314.

  • Kvalseth, T.O. 1985. Cautionary note about R 2. The American Statistician, 39(4):279-285.

    Google Scholar 

  • Limb, J.O. and Murphy, J.A. 1975. Measuring the speed of moving objects from television signals. IEEE Trans. on Communications, 23(4):474-478.

    Article  Google Scholar 

  • Liu, H., Hong, T., Herman, M., and Chellappa, R. 1996. Accuracy vs. efficiency trade-offs in optical flow algorithms. In Proc. of Fourth Europ. Conf. on Comp. Vis., ECCV-96, Springer-Verlag, pp. 174-183.

  • Meer, P., Mintz, D., Rosenfeld, A., and Kim, D.Y. 1991. Robust regression methods for computer vision: A review. Intern. J. Comput. Vis., 6(1):59-70.

    Google Scholar 

  • Mitiche, A. 1994. Computational Analysis of Visual Motion. Plenum: New York.

    Google Scholar 

  • Nagel, H.H. 1987. On the estimation of optical flow. Artificial Intelligence, 33:299-324.

    Article  Google Scholar 

  • Nagel, H.H. 1995. Optical flow estimation and the interaction between measurement errors at adjacent pixel positions. Intern. J. Comput. Vis., 15:271-288.

    Google Scholar 

  • Nesi, P., Del Bimbo, A., and Ben-Tzvi, D. 1995. A robust algorithm for optical flow estimation. Computer Vision and Image Understanding, 62(1):59-68.

    Article  Google Scholar 

  • Odobez, J.M. and Bouthemy, P. 1995. Robust multiresolution estimation of parametric motion models. J. of Visual Communication and Image Representation, 6(4):348-365.

    Article  Google Scholar 

  • Otte, M. and Nagel, H.H. 1994. Optical flow estimation: Advances and comparisons. In Proc. of Third Europ. Conf. on Comp. Vis., ECCV-94, Springer-Verlag, pp. 51-60.

  • Rousseeuw, P.J. 1984. Least median of squares regression. Journal of the American Statistical Association, 79:871-880.

    Google Scholar 

  • Rousseeuw, P.J. and Leroy, A.M. 1987. Robust Regression and Outlier Detection. John Wiley: New York.

    Google Scholar 

  • Schunck, B.G. 1989. Image flow segmentation and estimation by constraint line clustering. IEEE Trans. on Pattern Anal. and Mach. Intell., PAMI, 11(10):1010-1027.

    Google Scholar 

  • Shi, J. and Tomasi, C. 1994. Good features to track. In Proc. of Computer Vision and Pattern Recognition, CVPR-94, Seattle, pp. 593-600.

  • Steele, J.M. and Steiger, W.L. 1986. Algorithms and complexity for least median of squares regression. Discrete. Appl. Math., 14:93-100.

    Article  Google Scholar 

  • Stewart, C. 1996. Bias in robust estimation caused by discontinuities and multiple structures. Technical Report, Department of Computer Science, Rensselaer Polytechnic Institute, Troy, New York TR-12180-3590.

    Google Scholar 

  • Szeliski, R. and Coughlan, J. 1994. Hierarchical spline-based image registration. In Proc. of Computer Vision and Pattern Recognition, CVPR-94, Seattle, pp. 194-201.

  • VanHuffel, S. and Vandewalle, J. 1991. The Total Least Squares Problem: Computational Aspects and Analysis. 1st edition, SIAM: Philadelphia.

    Google Scholar 

  • Van Mieghlem, J.A., Avi-Itzhak, H.I., and Melen, R.D. 1995. Straight line extraction using iterative total least squares method. J. of Visual Communication and Image Representation, 6(1):59-68.

    Article  Google Scholar 

  • Wang, S., Markandey, V., and Reid, A. 1992. Total least squares fitting spatiotemporal derivatives to smooth optical flow field. In Proc. of the SPIE: Signal and Data Processing of Small Targets, vol. 1698, pp. 42-55.

    Google Scholar 

  • Weber, J. and Malik, J. 1993. Robust computation of optical flow in a multi-scale differential framework. In Proc. of Int. Conf. on Computer Vision, ICCV-93, Berlin, pp. 12-20.

  • Weber, J. and Malik, J. 1995. Robust computation of optical flow in a multi-scale differential framework. Intern. J. Comput. Vis., 14:67-81.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Intelligent Robotics Research Centre, Department of Electrical and Computer Systems Engineering, Monash University, Clayton, Vic, 3168, Australia. E-mail

    Alireza Bab-Hadiashar & David Suter

Authors
  1. Alireza Bab-Hadiashar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. David Suter
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Bab-Hadiashar, A., Suter, D. Robust Optic Flow Computation. International Journal of Computer Vision 29, 59–77 (1998). https://doi.org/10.1023/A:1008090730467

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1008090730467

Keywords

Search

Navigation