Advertisement

Optical flow estimation: Advances and comparisons

  • M. Otte
  • H. -H. Nagel
Optical Flow and Motion Fields
Part of the Lecture Notes in Computer Science book series (LNCS, volume 800)

Abstract

This contribution investigates local differential techniques for estimating optical flow and its derivatives based on the brightness change constraint. By using the tensor calculus representation we build the Taylor expansion of the gray-value derivatives as well as of the optical flow in a spatiotemporal neighborhood. Such a formulation simplifies a unifying framework for all existing local differential approaches and allows to derive new systems of equations to estimate the optical flow and its derivatives. We also tested various optical flow estimation approaches on real image sequences recorded by a calibrated camera fixed on the arm of a robot. By moving the arm of the robot along a precisely defined trajectory we can determine the true displacement rate of scene surface elements projected into the image plane and compare it quantitatively with the results of different optical flow estimators.

Keywords

Optical Flow Difference Vector Angular Error Rigorous Condition Optical Flow Estimator 
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. [Aisbett 89]
    J. Aisbett, Optical Flow with an Intensity-Weighted Smoothing, IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-11 (1989) 512–522.Google Scholar
  2. [Baraldi et al. 89]
    P. Baraldi, E. De Micheli, S. Uras, Motion and Depth from Optical Flow, Proc. Fifth Alvey Vision Conference, University of Reading, Reading/UK, September 25–28, 1989, pp. 205–208.Google Scholar
  3. [Barron et al. 92]
    J.L. Barron, D. J. Fleet, S. S. Beauchemin, Performance of Optical Flow Techniques, Technical Report RPL-TR-9107, Dept. of Computing Science, Queen's University, Kingston, Ontario, July 1992. (Revised July 1993).Google Scholar
  4. [Campani & Verri 90]
    M. Campani, A. Verri, Computing Optical Flow from an Over-constrained System of Linear Algebraic Equations, Proc. Third Int. Conf. on Computer Vision ICCV'90, Osaka, Japan, Dec. 4–7, 1990, pp. 22–26.Google Scholar
  5. [Chen et al. 93]
    H.-J. Chen, Y. Shirai, M. Asada, Obtaining Optical Flow with Multi-Orientation Filters, Proc. IEEE Conf. Computer Vision and Pattern Recognition CVPR'93, New York City, NY, June 15–17, 1993, pp. 736–737.Google Scholar
  6. [Cipolla & Blake 92]
    R. Cipolla, A. Blake, Surface Orientation and Time to Contact from Image Divergence and Deformation, Proc. Second European Conference on Computer Vision ECCV'92, S. Margherita, Italy, May 19–22, 1992, G. Sandini (ed.), Lecture Notes in Computer Science 588, Springer-Verlag, Berlin etc., pp. 187–202.Google Scholar
  7. [Girosi et al. 89]
    F. Girosi, A. Verri, V. Torre, Constraints for the Computation of Optical Flow, Proc. IEEE Workshop on Visual Motion, Irvine, CA, March 20–22, 1989, pp. 116–124.Google Scholar
  8. [Horn & Schunck 81]
    B.K.P. Horn, B.G. Schunck, Determining Optical Flow, Artificial Intelligence 17 (1981) 185–203.Google Scholar
  9. [Kearney et al. 87]
    J.K. Kearney, W.B. Thompson, D.L. Boley, Optical Flow Estimation: An Error Analysis of Gradient-Based Methods with Local Optimization, IEEE Trans. Pattern Analysis and Machine Intelligence PAMI 9 (1987) 229–244.Google Scholar
  10. [Koenderink & van Doorn 76]
    J.J. Koenderink, A.J. van Doorn, Local Structure of Movement Parallax of the Plane, Journal of the Optical Society of America 66 (1976) 717–723.Google Scholar
  11. [Nagel 85]
    H.-H. Nagel, Analyse und Interpretation von Bildfolgen, Informatik-Spektrum 8 (1985) 178–200 und 312–327.Google Scholar
  12. [Nagel 87]
    H.-H. Nagel, On the Estimation of Optical Flow: Relations between Different Approaches and Some New Results, Artificial Intelligence 33 (1987) 299–324.Google Scholar
  13. [Nagel 92]
    H.H. Nagel, Direct Estimation of Optical Flow and its Derivatives, in Artificial and Biological Vision Systems, G.A Orban and H.-H. Nagel (eds.), Springer-Verlag Berlin etc., 1992, pp. 193–224.Google Scholar
  14. [Negahdaripour & Lee 92]
    S. Negahdaripour, S. Lee, Motion Recovery from Image Sequences Using Only First Order Optical Flow Information, International Journal of Computer Vision 9 (1992) 163–184.Google Scholar
  15. [Negahdaripour & Yu 93]
    S. Negahdaripour, C.-H. Yu, A Generalized Brightness Change Model for Computing Optical Flow, Proc. Fourth Int. Conf. on Computer Vision ICCV'93, Berlin, Germany, May 11–14, 1993, pp. 2–11.Google Scholar
  16. [Nelson & Aloimonos 88]
    R.C. Nelson, J. Aloimonos, Using Flow Field Divergence for Obstacle Avoidance: Towards Qualitative Vision, Proc. Second Int. Conf. on Computer Vision ICCV'88, Tampa, FL, Dec. 5–8, 1988, pp. 188–196.Google Scholar
  17. [Otte 94]
    M. Otte, Extraktion von linienförmigen Merkmalen und Ermittlung des optischen Flusses mit seinen Ableitungen aus Voll-und Halbbildfolgen, eingereichte Dissertation, Institut für Algorithmen und Kognitive Systeme, Fakultät für Informatik der Universität Karlsruhe (TH), Karlsruhe, Deutschland, Januar 1994.Google Scholar
  18. [Schunck 84]
    B.G. Schunck, The Motion Constraint Equation for Optical Flow, Proc. Int. Conf. on Pattern Recognition ICPR'84, Montréal, Canada, July 30–Aug. 2, 1984, pp. 20–22.Google Scholar
  19. [Srinivasan 90]
    M.V. Srinivasan, Generalized Gradient Schemes for the Measurement of Two-Dimensional Image Motion, Biological Cybernetics 63 (1990) 421–431.Google Scholar
  20. [Subbarao 90]
    M. Subbarao, Bounds on Time-to-Collision and Rotational Component from First-Order Derivatives of Image Flow, Computer Vision, Graphics, and Image Processing 50 (1990) 329–341.Google Scholar
  21. [Verri & Poggio 89]
    A. Verri, T. Poggio, Motion Field and Optical Flow: Qualitative Properties, IEEE Trans. Pattern Analysis and Machine Intelligence PAMI-11 (1989) 490–498.Google Scholar
  22. [Weber & Malik 93]
    J. Weber, J. Malik, Robust Computation of Optical Flow in a Multi-Scale Differential Framework, Proc. Fourth Int. Conf. on Computer Vision ICCV'93, Berlin, Germany, May 11–14, 1993, pp. 12–20.Google Scholar
  23. [Werkhoven & Koenderink 90]
    P. Werkhoven, J.J. Koenderink, Extraction of Motion Parallax Structure in the Visual System, Biological Cybernetics 63 (1990) 185–199.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • M. Otte
    • 1
  • H. -H. Nagel
    • 1
    • 2
  1. 1.Institut für Algorithmen und Kognitive SystemeFakultät für Informatik der Universität Karlsruhe (TH)KarlsruheGermany
  2. 2.Fraunhofer - Institut für Informations- und Datenverarbeitung (IITB)Karlsruhe

Personalised recommendations