Visual motion estimation from image contour tracking

  • Włodzimierz Kasprzak
  • Heinrich Niemann
Part of the Lecture Notes in Computer Science book series (LNCS, volume 719)


An approach to visual motion estimation and its stabilization suitable for longitudinal camera motion is proposed. Closed contours with their image pair-like displacements in a short image sequence are detected. The contour length change rate is estimated allowing the first stabilization step — a weighted averaging of displacements. Two further steps follow — the grouping of similarly moving neighbour contours and an adaptive motion estimation in a long image sequence.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Enkelmann W., Kories R., Nagel H.-H., Zimmermann G.: An Experimental Investigation of Estimation Approaches for Optical Flow Fields. In: [Martin W.N., Aggarwal J.K.: Motion Understanding. Robot and Human Vision, Kluwer Academic Publ., Boston etc., 1988], 189–226.Google Scholar
  2. [2]
    Salari V., Sethi I.K.: Feature Point Correspondence in the Presence of Occlusion; IEEE Trans. Patt Anal Mach Intell, 12 (1990), No.1, 87–91.Google Scholar
  3. [3]
    Jain R.: Dynamic Vision. Proceedings of the ICPR-88 (Rome, Italy, September 1988), 226–235.Google Scholar
  4. [4]
    Karmann K.-P., von Brandt A.: Moving Object Recognition Using an Adaptive Background Memory. In: Cappellini V. (ed.): Time-Varying Image Processing and Moving Object Recognition Vol. 2., Elsevier Science Publ., 1990, 289–296.Google Scholar
  5. [5]
    Dickmanns E.D., Graefe V., Applications of Dynamic Monocular Machine Vision, Machine Vision and Applications, 1988, No. 1, 241–261.Google Scholar
  6. [6]
    Kirchner H.: Blockmatching with Column and Row Oriented Optimization, In: Cappellini V. (Ed.): Proc. 3rd Int. Workshop on Time-Varying Image Processing and Moving Object Recognition, 1989, 280–288.Google Scholar
  7. [7]
    Niemann H.: Pattern Analysis and Understanding. Springer, Berlin etc., 1990.Google Scholar
  8. [8]
    Kasprzak W.: Translational Motion or Depth from Segmentation in Image-Time space, In: Pavesic N., Niemann H., Paulus D.: Image Processing and Stereo Analysis, University of Erlangen-Nuremberg, IMMD-Research Reports, Vol. 26(1993), No.1, pp. 73–97.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1993

Authors and Affiliations

  • Włodzimierz Kasprzak
    • 1
  • Heinrich Niemann
    • 1
  1. 1.Bavarian Research Center for Knowledge-Based Systems (FORWISS)Erlangen

Personalised recommendations