Skip to main content
SpringerLink
Log in

Optical flow estimation and the interaction between measurement errors at adjacent pixel positions

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

Abstract

In order to estimate both components of optical flow as well as their first spatio-temporal derivatives, it is postulated that the Optical Flow Constraint Equation (OFCE) is valid in a spatio-temporal neighborhood of pixels. So far, it has been tacitly assumed that the partial derivatives of the gray value distribution—which are required for this approach at the pixel positions involved—are independent from each other. It is shown how dropping this assumption affects the estimation procedure, based on well established approaches of estimation theory. The insight gained thereby is used to develop an approach towards merging image regions based on the compatibility of optical flow estimates obtained within the regions considered for merger.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  • Barron, J.L., Fleet, D.J., Beauchemin, S.S., and Burkitt, T.A. 1992. Performance of Optical Flow Techniques. InProc. IEEE Conference on Computer Vision and Pattern Recognition CVPR'92, Champaign, IL, pp. 236–242.

  • Bergen, J.R., Burt, P.J., Hanna, K., Hingorani, R., Jeanne, P., and Peleg, S. 1991. Dynamic Multiple-Motion Computation. InArtificial Intelligence and Computer Vision, Y.A. Feldman and A. Bruckstein (eds.), Elsevier Science Publishers B.V. (North Holland): Amsterdam, The Netherlands, pp. 147–156.

    Google Scholar 

  • Bouthemy, P. and Santillana Rivero, J. 1987. A Hierarchical Likelihood Approach for Region Segmentation According to Motion-Based Criteria. InProc. First Intern. Conference on Computer Vision ICCV'87, London, UK, pp. 463–467.

  • Bouthemy, P. and Francois, E. 1993. Motion Segmentation and Qualitative Scene Analysis from an Image Sequence.Int. Journal of Computer Vision, 10(2):157–182.

    Google Scholar 

  • 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. InProc. IEEE Workshop on Visual Motion, Irvine, CA, pp. 2–12.

  • Burt, P.J., Hingorani, R.J., and Kolczynski, R. 1991. Mechanisms for Isolating Component Patterns in the Sequential Analysis of Multiple Motion. InProc. IEEE Workshop on Visual Motion, Princeton, NJ, pp. 187–193.

  • Campani, M. and Verri, A. 1990. Computing Optical Flow from an Overconstrained System of Linear Algebraic Equations. InProc. Third Intern. Conference on Computer Vision ICCV '90, Osaka, Japan, pp. 22–26.

  • Campani, M. and Verri, A. 1992. Motion Analysis from First Order Properties of Optical Flow.CVGIP: Image Understanding, 56(1):90–107.

    Google Scholar 

  • Chou, W.-S. and Chen, Y.-C. 1993. Estimation of the Velocity Field of Two-Dimensional Deformable Motion.Pattern Recognition 26(2):351–364.

    Google Scholar 

  • De Micheli, E., Torre, V., and Uras, S. 1993. The Accuracy of the Computation of Optical Flow and of the Recovery of Motion Parameters.IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI, 15(5):434–447.

    Google Scholar 

  • Etoh, M. and Shirai, Y. 1993. Segmentation and 2D Motion Estimation by Region Fragments. InProc. Fourth Intern. Conference on Computer Vision ICCV'93, Berlin, Germany, pp. 192–199.

  • Fleet, D.J. 1992.Measurement of Image Velocity. Kluwer Academic Publishers: Boston, MA; London, UK; Dordrecht, NL.

    Google Scholar 

  • Gu, H., Asada, M., and Shirai, Y. 1993. The Optimal Partition of Moving Edge Segments. InProc. IEEE Conference on Computer Vision and Pattern Recognition CVPR'93, New York City, NY, pp. 367–372.

  • Haralick, R.M. 1980. Edge and Region Analysis for Digital Image Data.Computer Graphics and Image Processing, 12(1):60–73.

    Google Scholar 

  • Heeger, D.J. 1988. Optical Flow Using Spatiotemporal Filters.Int. Journal of Computer Vision, 1(4):279–302.

    Google Scholar 

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

    Google Scholar 

  • Horn, B.K.P. and Schunck, B.G. 1981. Determining Optical Flow.Artificial Intelligence Journal, 17:185–203.

    Google Scholar 

  • Hsu, Y.Z., Nagel, H.-H., and Rekers, G. 1984. New Likelihood Test Methods for Change Detection in Image Sequences.Computer Vision, Graphics, and Image Processing, 26(1):73–106.

    Google Scholar 

  • Irani, M., Rousso, B., and Peleg, S. 1992. Detecting and Tracking Multiple Moving Objects Using Temporal Integration. InProc. Second European Conference on Computer Vision ECCV'92, Santa Margherita Ligure, Italy, Lecture Notes in Computer Science 588, G. Sandini (ed.), Springer-Verlag: Berlin Heidelberg New York and others, pp. 282–287.

    Google Scholar 

  • Letang, J.M., Rebuffel, V., and Bouthemy, P. 1993. Motion Detection Robust to Perturbations: A Statistical Regularization and Temporal Integration Framework. InProc. Fourth Intern. Conference on Computer Vision ICCV'93, Berlin, Germany, pp. 21–30.

  • Lucas, B.D. and Kanade, T. 1981. An Iterative Image Registration Technique with an Application to Stereo Vision. InProc. Image Understanding Workshop, Washington, DC, pp. 121–130.

  • Nagel, H.-H. 1992. Direct Estimation of Optical Flow and of Its Derivatives. InArtificial and Biological Vision Systems, G. Orban and H.-H. Nagel (eds.). Springer-Verlag: Berlin Heidelberg New York and others, pp. 193–224.

    Google Scholar 

  • Nagel, H.-H., Socher, G., Kollnig, H., and Otte, M. 1994. Motion Boundary Detection in Image Sequences by Local Stochastic Tests.Proc. Third European Conference on Computer Vision ECCV'94, Stockholm/Sweden, J.-O. Eklundh (ed.), Lecture Notes in Computer Science Vol. 801, Springer-Verlag, Berlin Heidelberg New York/NY, pp. 305–315.

    Google Scholar 

  • Negahdaripour, S. and Lee, S. 1992. Motion Recovery from Image Sequences Using Only First Order Optical Flow Information.Int. Journal of Computer Vision, 9(3):163–184.

    Google Scholar 

  • Negahdaripour, S. and Yu, C.-H. 1993. A Generalized Brightness Change Model for Computing Optical Flow. InProc. Fourth Intern. Conference on Computer Vision ICCV'93, Berlin, Germany, pp. 2–11.

  • Peleg, S. and Rom, H. 1990. Motion Based Segmentation. In Proc. Tenth Intern. Conference on Pattern Recognition, Atlantic City, NJ,Vol. 1, pp. 109–113.

    Google Scholar 

  • Simoncelli, E.P., Adelson, E.H., and Heeger, D.J. 1991. Probability Distributions of Optical Flow. InProc. IEEE Conference on Computer Vision and Pattern Recognition, Lahaina, Maui, Hawaii, pp. 310–315.

  • Socher, G. 1993. Test zur Beurteilung der Güte optischer Flußvektoren und Entwicklung eines Verfahrens zur Segmentierung von optischen Flußfeldern. Diplomarbeit, Fakultät für Informatik der Universität Karlsruhe (TH).

  • Spoerri, A. and Ullman, S. 1987. The Early Detection of Motion Boundaries. InProc. First Intern. Conference on Computer Vision ICCV'87, London, UK, pp. 209–218.

  • Szeliski, R. 1989.Bayesian Modeling of Uncertainty in Low-level Vision. Kluwer Academic Publishers: Boston, MA; Dordrecht, NL; London, UK.

    Google Scholar 

  • Szeliski, R. 1990. Bayesian Modeling of Uncertainty in Low-Level Vision.Int. Journal of Computer Vision, 5(3):271–301.

    Google Scholar 

  • Thompson, W.B. and Pong, T.-C. 1990. Detecting Moving Objects.Intern. Journal of Computer Vision, 4(1):39–57.

    Google Scholar 

  • Torr, P.H.S. and Murray, D.W. 1992. Statistical Detection of Independent Movement from a Moving Camera. InProc. British Machine Vision Conference, Leeds, UK, D. Hogg and R. Boyle (eds.), Springer-Verlag: London Berlin Heidelberg and others, pp. 79–88. See, too, Image and Vision Computing, 11(4):180–187, 1993.

    Google Scholar 

  • Wang, J.Y.A. and Adelson, E.H. 1993. Layered Representation for Motion Analysis. InProc. IEEE Conference on Computer Vision and Pattern Recognition CVPR'93, New York City, NY, pp. 361–366.

  • Weber, J. and Malik, J. 1993. Robust Computation of Optical Flow in a Multiscale Differential Framework. InProc. Fourth Intern. Conference on Computer Vision ICCV'93, Berlin, Germany, pp. 12–20.

Download references

Author information

Authors and Affiliations

  1. Institut für Algorithmen und Kognitive Systeme, Fakultät für Informatik der Universität Karlsruhe (TH) and Fraunhofer-Institut für Informations- und Datenverarbeitung IITB, Fraunhoferstr. 1, D-76131, Karlsruhe

    Hans-Hellmut Nagel

Authors
  1. Hans-Hellmut Nagel
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

This contribution is dedicated to Dr. h.c. Lothar Späth who throughout many years furthered the Fakultät für Informatik der Universität Karlsruhe (TH) and substantially helped to provide a much-needed new building in which to teach and to do research has been and continues to be a source of pleasure.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Nagel, HH. Optical flow estimation and the interaction between measurement errors at adjacent pixel positions. Int J Comput Vision 15, 271–288 (1995). https://doi.org/10.1007/BF01451744

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01451744

Keywords

Search

Navigation