Extraction of Object Representations from Stereo Image Sequences Utilizing Statistical and Deterministic Regularities in Visual Data

  • Norbert Krüger
  • Thomas Jäger
  • Christian Perwass
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2525)


The human visual system is a highly interconnected machinery that acquires its stability through integration of information across modalities and time frames. This integration becomes possible by utilizing regularities in visual data, most importantly motion (especially rigid body motion) and statistical regularities reflected in Gestalt principles such as collinearity.

In this paper we describe an artificial vision system which extracts 3D- information from stereo sequences. This system uses deterministic and statistical regularities to aquire stable representations from unreliable sub-modalities such as stereo or edge detection. To make use of the above mentioned regularities we have to work within a complex machinery containing sub-modules such as stereo, pose estimation and an accumulation scheme. The interaction of these modules allows to use the statistical and deterministic regularities for feature disambiguation within a process of recurrent predictions.


Object Representation Rigid Body Motion Consecutive Frame Accumulation Scheme Semantic Parameter 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    J. Aloimonos and D. Shulman. Integration of Visual Modules—An extension of the Marr Paradigm. Academic Press, London, 1989.Google Scholar
  2. [2]
    A. Cozzi and F. Wörgötter. Comvis: A communication framework for computer vision. International Journal of Computer Vision, 41:183–194, 2001.CrossRefzbMATHGoogle Scholar
  3. [3]
    A. Desolneux, L. Moisan, and J.M. Morel. Edge detection by the Helmholtzprinciple. JMIV, 14(3):271–284, 2001.CrossRefzbMATHGoogle Scholar
  4. [4]
    O.D. Faugeras. Three-Dimensional Computer Vision. MIT Press, 1993.Google Scholar
  5. [5]
    M. Felsberg and G. Sommer. The monogenic signal. IEEE Transactions on Signal Processing, 41(12), 2001.Google Scholar
  6. [6]
    O. Granert. Poseschaetzung kinematischer Ketten. Diploma Thesis,Universität Kiel, 2002.Google Scholar
  7. [7]
    D.D. Hoffman, editor. Visual Intelligence: How we create what we see. W.W. Norton and Company, 1980.Google Scholar
  8. [8]
    Thomas Jäger. Interaktion verschiedener visueller Modalitäten zur stabilen Extraktion von Objektrepräsentationen. Diploma thesis (University of Kiel), 2002.Google Scholar
  9. [9]
    B. Jähne. Digital Image Processing—Concepts,Algorithms,and Scientific Applications. Springer, 1997.Google Scholar
  10. [10]
    R. Klette, K. Schlüns, and A. Koschan. Computer Vision—Three-Dimensional Data from Images. Springer, 1998.Google Scholar
  11. [11]
    P. Kovesi. Image features from phase congruency. Videre: Journal of Computer Vision Research, 1(3):1–26, 1999.Google Scholar
  12. [12]
    N. Krüger, M. Ackermann, and G. Sommer. Accumulation of object representations utilizing interaction of robot action and perception. Knowledge Based Systems, 13(2):111–118, 2002.CrossRefGoogle Scholar
  13. [13] N. Krüger, M. Felsberg, C. Gebken, and M. Pörksen. An explicit and compact coding of geometric and structural information applied to stereo processing. Proceedings of the workshop ‘Vision, Modeling and Visualization 2002’ 2002.Google Scholar
  14. [14]
    N. Krüger and F. Wörgötter. Different degree of genetical prestructuring in the ontogenesis of visual abilities based on deterministic and statistical regularities. Proceedings of the Workshop On Growing up Artifacts that Live SAB 2002, 2002.Google Scholar
  15. [15]
    N. Krüger and F. Wörgötter. Multi modal estimation of collinearity and parallelism in natural image sequences. To appear in Network: Computation in Neural Systems, 2002.Google Scholar
  16. [16]
    H.-H. Nagel. On the estimation of optic flow: Relations between different approaches and some new results. Artificial Intelligence, 33:299–324, 1987.CrossRefGoogle Scholar
  17. [17]
    T.Q. Phong, R. Haraud, A. Yassine, and P.T. Tao. Object pose from 2-d to 3-d Point and line correspondences. International Journal of Computer Vision, 15:225–243, 1995.CrossRefGoogle Scholar
  18. [18]
    B. Rosenhahn, N. Krüger, T. Rabsch, and G. Sommer. Automatic tracking with a novel pose estimation algorithm. Robot Vision 2001, 2001.Google Scholar
  19. [19]
    S. Sarkar and K.L. Boyer. Computing Perceptual Organization in Computer Vision. World Scientific, 1994.Google Scholar
  20. [20]
    C. Zetzsche and E. Barth. Fundamental limits of linear filters in the visual processing of two dimensional signals. Vision Research, 30, 1990.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Norbert Krüger
    • 1
  • Thomas Jäger
    • 2
  • Christian Perwass
    • 2
  1. 1.University of StirlingScotland
  2. 2.University of KielGermany

Personalised recommendations