Motion-based identification of deformable templates

  • Christoph Schnörr
  • Wladimir Peckar
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 970)


An algorithm is presented to compute the shape of moving objects in image sequences. We assume that locally the motion fields of both the object and its environment can be represented by affine approximations. Based on hypotheses about these fields, an optimality principle is formulated to compute the shape of an object in terms of deformations of an arbitrary convex polygonal domain. As input data the algorithm merely requires first order derivatives of the image function. Numerical experiments using synthesized and real image data are presented. The results suggest that our approach is suited for tracking tasks within an bottom-up/top-down framework.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    J.Y. Aloimonos and D.P. Tsakiris. On the visual mathematics of tracking. Image and Vis. Comp., 9(4):235–251, 1991.Google Scholar
  2. 2.
    R. Curwen and A. Blake. Dynamic contours: Real-time active splines. In A. Blake and A. Yuille, editors, Active Vision, pages 39–57. MIT Press, 1992.Google Scholar
  3. 3.
    C. Harris. Tracking with rigid models. In A. Blake and A. Yuille, editors, Active Vision, pages 59–73. MIT Press, 1992.Google Scholar
  4. 4.
    B.K.P. Horn and B.G. Schunck. Determining optical flow. Artif. Intell., 17:185–203, 1981.Google Scholar
  5. 5.
    R. Horst. Nichtlineare Optimierung. Carl Hanser Verlag, München, Wien, 1979.Google Scholar
  6. 6.
    M. Irani, B. Rousso, and S. Peleg. Detecting and tracking multiple moving objects using temporal integration. In G. Sandini, editor, Computer Vision — ECCV '92, pages 282–287. Springer Verlag, 1992.Google Scholar
  7. 7.
    F. Leymarie and M.D. Levine. Tracking deformable objects in the plane using an active contour model. IEEE Trans. Patt. Anal. Mach. Intell., 15(6):617–634, 1993.Google Scholar
  8. 8.
    F. Meyer and P. Bouthemy. Region-based tracking in an image sequence. In G. Sandini, editor, Computer Vision — ECCV '92, pages 476–484. Springer Verlag, 1992.Google Scholar
  9. 9.
    M. Mohnhaupt and B. Neumann. Understanding object motion: Recognition, learning and spatiotemporal reasoning. J. of Robotics and Autonom. Systems, 8:65–91, 1991.Google Scholar
  10. 10.
    K. Rohr. Towards model-based recognition of human movements in image sequences. Comp. Vis. Graph. Image Proc: IU, 59(1):94–115, 1994.Google Scholar
  11. 11.
    C. Schnörr. Computation of discontinuous optical flow by domain decomposition and shape optimization. Int. J. of Comp. Vision, 8(2):153–165, 1992.Google Scholar
  12. 12.
    D. Terzopoulos and D. Metaxas. Tracking nonrigid 3d objects. In A. Blake and A. Yuille, editors, Active Vision, pages 75–89. MIT Press, 1992.Google Scholar
  13. 13.
    D. Terzopoulos and R. Szeliski. Tracking with kalman snakes. In A. Blake and A. Yuille, editors, Active Vision, pages 3–20. MIT Press, 1992.Google Scholar
  14. 14.
    A. Yuille and P. Hallinan. Deformable templates. In A. Blake and A. Yuille, editors, Active Vision, pages 21–38. MIT Press, 1992.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Christoph Schnörr
    • 1
  • Wladimir Peckar
    • 2
  1. 1.FB Informatik, AB Kognitive SystemeUniversität HamburgHamburgGermany
  2. 2.Dept. of Computer ScienceTaganrog University of Radio EngineeringTaganrogRussia

Personalised recommendations