Skip to main content
SpringerLink
Log in
Book cover

Mustererkennung 2000 pp 476–487Cite as

Variational Image Motion Computation: Theoretical Framework, Problems and Perspectives

  • Conference paper

Part of the book series: Informatik aktuell ((INFORMAT))

Abstract

Many differential methods for the recovery of the optic flow field from an image sequence can be expressed in terms of a variational problem where the optic flow minimizes some energy. Typically, these energy functionals consist of two terms: a data term, which requires e.g. that a brightness constancy assumption holds, and a regularizer that encourages global or piecewise smoothness of the flow field. In this paper we present a systematic Classification of rotation invariant convex regularizers by exploring their connection to diffusion filters for multichannel images. This taxonomy provides a unifying framework for data-driven and flow-driven, isotropic and anisotropic, as well as spatial and spatiotemporal regularizers. While some of these techniques are classic methods from the literature, others are derived here for the first time. We conclude by pointing out some important research issues related to variational optic flow computation.

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

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   54.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   69.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. L. Alvarez, J. Esclarin, M. Lefebure and J. Sanchez, A PDE model for Computing the optical flow, Proc. XVI Congreso de Ecuaciones Diferenciales y Aplicaciones (C.E.D.Y.A. XVI, Las Palmas de Gran Canaria, Sept. 21-24, 1999), 1349-1356, 1999.

    Google Scholar 

  2. L. Alvarez, J. Weickert, J. Sanchez, Reliable estimation of dense optical flow fields with large displacements, To appear in International Journal of Computer Vision.

    Google Scholar 

  3. G. Aubert, R. Deriche, P. Kornprobst, Computing optical flow via variational techniques, SIAMJ. Appl. Math, Vol. 60, 156–182, 1999.

    Article  MathSciNet  MATH  Google Scholar 

  4. J.L. Barron, D.J. Fleet, S.S. Beauchemin, Performance of optical flow techniques, Int. J. Comput. Vision, Vol. 12, 43–77, 1994.

    Article  Google Scholar 

  5. M.J. Black, P. Anandan, The robust estimation of multiple motions: Parametric and piecewise smooth flow fields,Computer Vision and Image Understanding, Vol. 63, 75–104, 1996.

    Article  Google Scholar 

  6. A. Blake, A. Zisserman, Visual reconstruction, MIT Press, Cambridge (Mass.), 1987.

    Google Scholar 

  7. L. Blanc-Feraud, M. Barlaud, T. Gaidon, Motion estimation involving discontinuities in a multiresolution scheme, Optical Engineering, Vol. 32, No. 7, 1475–1482, 1993.

    Article  Google Scholar 

  8. I. Cohen, Nonlinear varia,tional method for optical flow computation, Proc. Eighth Scandinavian Conf. on Image Analysis (SCIA ’93, Troms0, May 25-28, 1993), Vol. 1, 523-530, 1993.

    Google Scholar 

  9. R.Deriche, P. Kornprobst, G. Aubert, Optical-flow estimation while preserving its discontinuities: A variational approach, Proc. Second Asian Conf. Computer Vision (ACCV ’95, Singapore, December 5-8, 1995), Vol. 2, 290–295, 1995.

    Google Scholar 

  10. S. Di Zenzo, A note on the gradient of a multi-image, Computer Vision, Graphics, and Image Processing, Vol. 33, 116–125, 1986.

    Article  Google Scholar 

  11. D.J. Fleet, A.D. Jepson, Computation of component image velocity from local phase information, Int. J. Comput. Vision, Vol. 5, 77–104, 1990.

    Article  Google Scholar 

  12. W. Förstner, E. Gülch, A fast operator for detection and precise location of distinct points, corners and centres of circular features, Proc. ISPRS Intercommission Conf. on Fast Processing of Photogrammetric Data (Interlaken, June 2-4, 1987), 281-305, 1987.

    Google Scholar 

  13. M.X. Goemans, D.P. Williamson. Improved approximation algorithms for maximum cut and satisfiability problems using semidefinite programming. J. ACM, Vol. 42:1115–1145, 1995.

    Article  MathSciNet  MATH  Google Scholar 

  14. B. ter Haar Romeny, L. Florack, J. Koenderink, M. Viergever (Eds.), Scale-space theory in Computer vision, Lecture Notes in Computer Science, Vol. 1252, Springer, Berlin, 1997.

    Google Scholar 

  15. W. Hackbusch, editor. Multigrid Methods V: Proc. Fifth European Multigrid Conference, Stuttgart, Oct. 1-4 1998. Springer.

    Google Scholar 

  16. F. Heitz, P. Bouthemy, Multimodal estimation of discontinuous optical flow using Markov random fields, IEEE Trans. Pattern Anal. Mach. Intell., Vol. 15, 1217–1232, 1993.

    Article  Google Scholar 

  17. W. Hinterberger, Generierung eines Films zwischen zwei Bildern mit Hilfe des optischen Flusses, M.Sc. thesis, Industrial Mathematics Institute, University of Linz, Austria, 1999.

    Google Scholar 

  18. B. Horn, B. Schunck, Determining optical flow, Artificial Intelligence, Vol. 17, 185— 203, 1981.

    Article  Google Scholar 

  19. E. Kreyszig, Differential geometry, University of Toronto Press, Toronto, 1959.

    MATH  Google Scholar 

  20. A. Kumar, A.R. Tannenbaum, G.J. Balas, Optic flow: a curve evolution approach, IEEE Trans. Image Proc., Vol. 5, 598–610, 1996.

    Article  Google Scholar 

  21. P.J.M. van Laarhoven, E.H.L. Aarts, Simulated annealing: theory and applications, Reidel, Dordrecht, 1988.

    Google Scholar 

  22. L. Loväsz, A. Schrijver. Cones of matrices and set-functions and 0-1 optimization. SIAMJ. Optimization, Vol. 1, No. 2:166–190, 1991.

    Article  Google Scholar 

  23. E. Memin, P. Perez, Dense estimation and object-based segmentation of the optical flow with robust techniques,IEEE Trans. Image Proc, Vol. 7, 703–719, 1998.

    Article  Google Scholar 

  24. A. Mitiche, P. Bouthemy, Computation and analysis of image motion: a synopsis of current problems and methods,Int. J. Comput. Vision, Vol. 19, 29–55, 1996.

    Article  Google Scholar 

  25. D.W. Murray, B.F. Buxton, Scene segmentation from visual motion using global optimization, IEEE Trans. Pattern Anal. Mach. Intell., Vol. 9, 220–228, 1987.

    Article  Google Scholar 

  26. H.-H. Nagel, Constraints for the estimation of displacement vector fields from image sequences, Proc. Eighth Int. Joint Conf. on Artificial Intelligence (IJCAI ’83, Karlsruhe, August 8-12, 1983), 945-951, 1983.

    Google Scholar 

  27. H.-H. Nagel, Extending the ’oriented smoothness constraint’ into the temporal domain and the estimation of derivatives of optical flow, O. Faugeras (Ed.), Computer vision - ECCV ’90, Lecture Notes in Computer Science, Vol. 427, Springer, Berlin, 139-148, 1990.

    Google Scholar 

  28. H.-H. Nagel, W. Enkelmann, An investigation of smoothness constraints for the estimation of displacement vector fields from images sequences,IEEE Trans. Pattern Anal. Mach. Intell., Vol. 8, 565–593, 1986.

    Article  Google Scholar 

  29. P. Nesi, Variational approach to optical flow estimation managing discontinuities, Image and Vision Computing, Vol. 11, 419–439, 1993.

    Article  Google Scholar 

  30. M. Nielsen, P. Johansen, O.F. Olsen, J. Weickert (Eds.), Scale-space theories in Computer vision, Lecture Notes in Computer Science, Springer, Berlin, Vol. 1682, 1999.

    Google Scholar 

  31. M. Proesmans, L. Van Gool, E. Pauwels, A. Oosterlinck, Determination of optical flow and its discontinuities using non-linear diffusion, J.-O. Eklundh (Ed.), Computer vision - ECCV ’94, Lecture Notes in Computer Science, Vol. 801, Springer, Berlin, 295-304, 1994.

    Google Scholar 

  32. C. Schnörr, Determming optical flow for irregulär domams by minimizing quadratic functionals of a certain class, Int. J. Comput. Vision, Vol. 6, 25–38, 1991.

    Article  Google Scholar 

  33. C. Schnörr, On functionals with greyvalue-controlled smoothness terms for determming optical flow, IEEE Trans. Pattern Anal. Mach. Intell., Vol. 15, 1074–1079, 1993.

    Article  Google Scholar 

  34. C. Schnörr, Segmentation of Visual motion by minimizing convex non-quadratic functionals, Proc. 12th Int. Conf. Pattern Recognition (ICPR 12, Jerusalem, Oct. 9-13, 1994), Vol. A, IEEE Computer Society Press, Los Alamitos, 661-663, 1994.

    Google Scholar 

  35. C. Schnörr, R. Sprengel, B. Neumann, A variational approach to the design of early vision algorithms,Computing, Suppl. 11, 149–165, 1996.

    Article  Google Scholar 

  36. E.P. Simoncelli. Bayesian multiscale differential optical flow. In B. Jähne, H. Haußecker, and P. Geißler, editors, Handbook: of Computer Vision and Applications, volume 2, chapter 14, pages 297–422. Academic Press, San Diego, 1999.

    Google Scholar 

  37. M.A. Snyder, On the mathernatical foundations of smoothness constraints for the determination of optical flow arid for surface reconstruction, IEEE Trans. Pattern Anal. Mach. Intell, Vol. 13, 1105–1114, 1991.

    Article  Google Scholar 

  38. J. Sporring, M. Nielsen, L. Florack, P. Johansen (Eds.), Gaussian scale-space theory, Kluwer, Dordrecht, 1997.

    Google Scholar 

  39. C. Stiller, J. Konrad, Estimating motion in image sequences,IEEE Signal Proc. Magazine, Vol. 16, 70–91, 1999.

    Article  Google Scholar 

  40. J. Weber, J. Malik, Robust computation of optical flow in a multi-scale differential framework, Int. J. Comput. Vision, Vol. 14, 67–81, 1995.

    Article  Google Scholar 

  41. J. Weickert, Anisotropie diffusion in image processing, Teubner, Stuttgart, 1998.

    Google Scholar 

  42. J. Weickert, On discontmuity-preserving optic flow, S. Orphanoudakis, P. TYahanias, J. Crowley, N. Katevas (Eds.), Proc. Computer Vision and Mobile Robotics Workshop (CVMR ’98, Santorini, Sept. 17-18, 1998), 115-122, 1998.

    Google Scholar 

  43. J. Weickert, Coherence-enhancing diffusion of colour images,Image and Vision Computing, Vol. 17, 199-210 , 1999.

    Article  Google Scholar 

  44. J . Weickert , B. ter Haar Romeny, M.A. Viergever. Efficient and reliable schemes for nonlinear diffusion filtering. IEEE T .-Image Proc., Vol. 7, No. 3:398–410, 1998.

    Google Scholar 

  45. J . Weickert, C. Schnorr, Riiumlich- zeitliche Berechnung des optischen Fluss es mit ni chtl in earen fluftabhiingig en GlattheitsteTmen , W. Forstner , J .M. Buhmann, A. Fab er , P. Fab er (Eds .), Mustcrerkennung 1999, Springer, Berlin, 317–324, 1999.

    Google Scholar 

  46. J . Weickert, .1 . Heers , C. Schnorr , K.-.1 . Zuiderveld , O. Scherzer. and H.-S. Stiehl. Fast parallel algorithms for a broad class of nonlinear variational diffusion ap proaches. Real-Time Imaging , 2000. In press.

    Google Scholar 

  47. J . Weickert, C. Schnorr. A th eoret ical framework for convex regu larizers in PD Ebased computation of image motion . Computer Science Series 13/2000, Dept. Math. and CompoScience, University of Mannheim, Germany, J une 2000. Submitted.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computer Vision, Graphics, and Pattern Recognition Group, Dept. of Math, and Comp. Science, University of Mannheim, 68131, Mannheim, Germany

    Christoph Schnörr & Joachim Weickert

Authors
  1. Christoph Schnörr
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Joachim Weickert
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Institut für Informatik und Praktische Mathematik, Christian-Albrechts Universität Kiel, Preußerstr. 1-9, 24105, Kiel, Deutschland

    Gerald Sommer , Norbert Krüger  & Christian Perwass ,  & 

Rights and permissions

Reprints and permissions

Copyright information

© 2000 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Schnörr, C., Weickert, J. (2000). Variational Image Motion Computation: Theoretical Framework, Problems and Perspectives. In: Sommer, G., Krüger, N., Perwass, C. (eds) Mustererkennung 2000. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-59802-9_60

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-59802-9_60

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-67886-1

  • Online ISBN: 978-3-642-59802-9

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation