Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

Exploiting Discontinuities in Optical Flow

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

Abstract

Most optical flow estimation techniques have substantial difficulties dealing with flow discontinuities. Methods which simultaneously detect flow boundaries and use the detected boundaries to aid in flow estimation can produce significantly improved results. Current approaches to implementing these methods still have important limitations, however. We demonstrate three such problems: errors due to the mixture of image properties across boundaries, an intrinsic ambiguity in boundary location when only short sequences are considered, and difficulties insuring that the motion of a boundary aids in flow estimation for the surface to which it is attached without corrupting the flow estimates for the occluded surface on the other side. The first problem can be fixed by basing flow estimation only on image changes at edges. The second requires an analysis of longer time intervals. The third can be aided by using a boundary detection mechanism which classifies the sides of boundaries as occluding and occluded at the same time as the boundaries are detected.

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

  • Adelson, E.H. and Bergen, J.R. 1986. The extracton of spatiotemporal energy in human and machine vision. In Proc.Workshop on Motion: Representation and Analysis, pages 151-155.

  • Anandan, P. 1989. A computational framework and an algorithm for the measurement of visual motion. International Journal of Computer Vision, pages 283-310.

  • Barnard, S.T. and Thompson, W.B. 1980. Disparity analysis of images. IEEE Trans. on Pattern Analysis and Machine Intelligence, PAMI-2:333-340.

    Google Scholar 

  • Barron, J.L., Fleet, D.J. and Beauchemin, S.S. 1994. Performance of optical flow techniques. International Journal of Computer Vision, pages 43-77.

  • Bergen, J.R., Burt, P.J., Hingorani, R. and Peleg, S. 1990. Computing two motions from three frames. In Proc. Third International Conference on Computer Vision, pages 27-32.

  • Black, M.J. and Anandan, P. 1990. A model for the detection of motion over time. In Proc. Third International Conference on Computer Vision, pages 33-37.

  • Blake, A. and Zisserman, A. 1987. Visual Reconstruction. MIT Press, Cambridge, MA.

    Google Scholar 

  • Fennema, C.L. and Thompson, W.B. 1979. Velocity determination in scenes containing several moving objects. Computer Graphics and Image Processing, 9:301-315.

    Google Scholar 

  • Fleet, D.J. and Jepson, A.D. 1990. Computation of component image velocity from local phase information. International Journal of Computer Vision, pages 77-104.

  • Gamble, E. and Poggio, T. 1987. Visual integration and detection of discontinuities: The key role of intensity edges. AI Memo 970, MIT.

  • Geman, S. and Geman, D. 1984. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Trans. on Pattern Analysis and Machine Intelligence, PAMI-6:721-741.

    Google Scholar 

  • Heeger, D.J. 1988. Optical flow estimation using spatiotemporal filters. International Journal of Computer Vision, pages 279-302.

  • Heitz, F. and Bouthemy, P. 1993. Multimodal estimation of discontinuous optical flow using markov random fields. IEEE Trans. on Pattern Analysis and Machine Intelligence, 15:1217-1232.

    Article  Google Scholar 

  • Hildreth, E.C. 1983. The Measurement of Visual Motion. MIT Press, Cambridge, MA.

    Google Scholar 

  • Horn, B.K.P. and Schunck, B. 1981. Determining optical flow. Artificial Intelligence, 17:185-203.

    Article  Google Scholar 

  • Hutchinson, J., Koch, C., Luo, J. and Mead, C. 1988. Computing motion using analog and binary resistive networks. Computer, 21:52-63.

    Article  Google Scholar 

  • Kanade, T. and Okutomi, M. 1994. A stereo matching algorithm with an adaptive window: Theory and experiment. IEEE Trans. on Pattern Analysis and Machine Intelligence, 16(9):920-932.

    Article  Google Scholar 

  • Kaplan, G.A. 1969. Kinetic disruption of optical texture: The perception of depth at an edge. Perception & Psychophysics, 6(4):193-198.

    Google Scholar 

  • Kearney, J.K., Thompson, W.B. and Boley, D.L. 1987. Optical flow estimation: An error analysis of gradient-based methods with local optimization. IEEE Trans. on Pattern Analysis and Machine Intelligence, PAMI-9:229-244.

    Google Scholar 

  • Koch, C., Wang, H.T., Mathur, B., Hsu, A., and Suarez, H. 1989. Computing optical flow in resistive networks and in the primate visual system. In Proc. Workshop on Visual Motion, pages 62-69.

  • Konrad, J. and Dubois, E. 1992. Bayesian estimation of motion vector fields. IEEE Trans. on Pattern Analysis and Machine Intelligence, 14:910-927.

    Article  Google Scholar 

  • Marr, D. and Poggio, T. 1979. Cooperative computation of stereo disparity. Science, 194:283-287.

    Google Scholar 

  • Murray, D.W. and Buxton, B.F. 1987. Scene segmentation from visual motion using global optimization. IEEE Trans. on Pattern Analysis and Machine Intelligence, PAMI-9:220-228.

    Google Scholar 

  • Mutch, K.M. and Thompson, W.B. 1983. Hierarchical estimation of spatial properties from motion. In A. Rosenfeld, editor, Multiresolution Image Processing and Analysis, pages 343-354. Springer-Verlag.

  • Mutch, K.M. and Thompson, W.B. 1985. Analysis of accretion and deletion at boundaries in dynamic scenes. IEEE Trans. on Pattern Analysis and Machine Intelligence, PAMI-7:133-138.

    Google Scholar 

  • Nagel, H.H. 1995. Optical flow estimation and the interaction between measurement errors at adjacent pixel positions. International Journal of Computer Vision, 15(3):273-288.

    Google Scholar 

  • Prazdnyk, K. 1985. Detection of binocular disparities. Biological Cybernetics, 52:93-99.

    Google Scholar 

  • Rangarajan, K., Shah, M. and Van Brackle, D. 1988. Optimal corner detection. In Proc. Second International Conference on Computer Vision, pages 90-94.

  • Schunck, B.G. 1989. Image flow segmentation and estimation by constraint line clustering. IEEE Trans. on Pattern Analysis and Machine Intelligence, PAMI-11:1010-1027.

    Article  Google Scholar 

  • Scott, G.L. 1988. Local and Global Interpretation ofMoving Images. Morgan Kauffman, Los Altos.

    Google Scholar 

  • Smitley, D.L. and Bajcsy, R. 1984. Stereo processing of aerial, urban images. In Proc. Seventh Int. Conference on Pattern Recognition, pages 433-435.

  • Thompson, W.B. 1995. Exploiting discontinuities in optical flow. Technical Report UUCS-95-015, Departement of Computer Science, University of Utah.

  • Thompson, W.B. and Barnard, S.T. 1981. Lower-level estimation and interpretation of visual motion. Computer, 14:20-28.

    Google Scholar 

  • Thompson, W.B., Kersten, D. and Knecht, W.R. 1985. Structurefrom-motion based on information at surface boundaries. Biological Cybernetics, pages 327-333, 1992.

  • Thompson, W.B., Mutch, K.M. and Berzins, V.A. 1985. Dynamic occlusion analysis in optical flow fields. IEEE Trans. on Pattern Analysis and Machine Intelligence, PAMI-7:374-383.

    Google Scholar 

  • Thompson, W.B. and Painter, J.S. 1992. Qualitative constraints for structure-from-motion. Computer Vision, Graphics and Image Processing: Image Understanding, pages 69-77.

  • Waxman, A.M., Wu, J. and Bergholm, F. 1988. Convected activation profiles and the measurement of visual motion. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 717-723, Ann Arbor, MI.

  • Yonas, A., Craton, L.G., Thompson, W.B. and Condry, K.F. 1990. Boundary identification and the computation of relative motion: Two processes in kinetic occlusion. Abstracts in Investigative Ophthalmology and Visual Science, 31(4):524.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Utah, Salt Lake City, UT, 84112. E-mail

    William B. Thompson

Authors
  1. William B. Thompson
    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

Thompson, W.B. Exploiting Discontinuities in Optical Flow. International Journal of Computer Vision 30, 163–173 (1998). https://doi.org/10.1023/A:1008026031844

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1008026031844

Search

Navigation