Advertisement

Extending the ‘Oriented smoothness constraint’ into the temporal domain and the estimation of derivatives of optical flow

  • Hans-Hellmut Nagel
Optical Flow
Part of the Lecture Notes in Computer Science book series (LNCS, volume 427)

Abstract

Recent experimental results by Schnörr 89 with an approach based on a simplified ‘oriented smoothness constraint’ show considerable improvement at expected discontinuities of the optical flow field. It thus appears justified to study whether the local gray value variation can be exploited in the temporal as well as in the spatial domain in order to achieve further improvements at discontinuities in the optical flow field associated with the image areas of moving objects in image sequences. An extension of the oriented smoothness constraint into the temporal domain is presented. In this context, a local estimation approach for the spatio-temporal partial derivatives of optical flow has been developed. This, in turn, is used to compare two approaches for the definition of optical flow.

Keywords

Partial Derivative Optical Flow Flow Line Local Coordinate System Temporal Domain 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. F. Girosi, A. Verri, and V. Torre, ”Constraints for the Estimation of Optical Flow”, Proc. Workshop on Visual Motion, March 20–22, 1989, Irvine/CA, pp. 116–124Google Scholar
  2. B.K.P. Horn and B.G. Schunck, ”Determining Optical Flow”, Artificial Intelligence 17 (1981) 185–203Google Scholar
  3. J.J. Koenderink, private communication, September 29–30, 1989Google Scholar
  4. T. Krämer, ”Direkte Berechnung von Bewegungsparametern und einer Tiefenkarte durch Auswertung monokularer Grauwertbildfolgen”, Dissertation, Fakultät für Informatik der Universität Karlsruhe (TH), Karlsruhe/Bundesrepublik Deutschland, Mai 1989Google Scholar
  5. H.-H. Nagel, ”Displacement Vectors Derived from Second Order Intensity Variations in Image Sequences”. Computer Vision, Graphics, and Image Processing 21 (1983) 85–117Google Scholar
  6. H.-H. Nagel, ”On the Estimation of Optical Flow: Relations between Different Approaches and Some New Results”, Artificial Intelligence 33 (1987) 299–324Google Scholar
  7. C. Schnörr, ”Zur Schätzung von Geschwindigkeitsvektorfeldern in Bildfolgen mit einer richtungsabhängigen Glattheitsforderung”, 11. DAGM-Symposium Mustererkennung 1989, 2.–4. Oktober 1989, Informatik-Fachberichte 219, H. Burkhardt, K.H. Höhne, B. Neumann (Hrsg.), Springer-Verlag Berlin Heidelberg New York 1989, pp. 294–301Google Scholar
  8. M.A. Snyder, ”On the Mathematical Foundations of Smoothness Constraints for the Determination of Optical Flow and for Surface Reconstruction”, Proc. Workshop on Visual Motion, March 20–22, 1989, Irvine/CA, pp. 107–115Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1990

Authors and Affiliations

  • Hans-Hellmut Nagel
    • 1
    • 2
  1. 1.Fraunhofer-Institut für Informations- und Datenverarbeitung (IITB)Karlsruhe 1Federal Republic of Germany
  2. 2.Fakultät für Informatik der Universität Karlsruhe (TH)Germany

Personalised recommendations