Advertisement

Video Object Segmentation Using Graphs

  • Salvador B. López Mármol
  • Nicole M. Artner
  • Adrian Ion
  • Walter G. Kropatsch
  • Csaba Beleznai
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5197)

Abstract

This paper presents an approach for video object segmentation. The main idea of our approach is to generate a planar, triangulated, and labeled graph that describes the scene, foreground objects and background. With the help of the Kanade-Lucas-Tomasi Tracker, corner points are tracked within a video sequence. Then the movement of the points adaptively generates a planar triangulation. The triangles are labeled as rigid, articulated, and separating depending on the variation of the length of their edges.

Keywords

Video object segmentation adaptive triangulation articulated objects 

References

  1. 1.
    Celasun, I., Tekalp, A.M., Gokcetekin, M.H., Harmanci, D.M.: 2-d mesh-based video object segmentation and tracking with occlusion resolution. Signal Processing: Image Communication 16(10), 949–962 (2001)Google Scholar
  2. 2.
    Alatan, A.A., Onural, L., Wollborn, M., Mech, R., Tuncel, E., Sikora, T.: Image sequence analysis for emerging interactive multimedia services. IEEE Transactions on Circuits and Systems for Video Technology 8(7), 802–813 (1998)CrossRefGoogle Scholar
  3. 3.
    Altunbasak, Y., Eren, P.E., Tekalp, A.M.: Region-based parametric motion segmentation using color information. Graphical Models and Image Processing 60(1), 13–23 (1998)CrossRefGoogle Scholar
  4. 4.
    Castagno, R., Ebrahimi, T., Kunt, M.: Video segmentation based on multiple features for interactive multimedia applications. IEEE Transactions on Circuits and Systems for Video Technology 8(5), 562–571 (1998)CrossRefGoogle Scholar
  5. 5.
    Chen, H.T., Liu, T.L., Fuh, C.S.: Segmenting highly articulated video objects with weak-prior random forests. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 373–385. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  6. 6.
    Celasun, I., Tekalp, A.: Optimal 2-d hierarchical content-based mesh design and update for object-based video. IEEE Transactions on Circuits and Systems for Video Technology 10(7), 1135–1153 (2000)CrossRefGoogle Scholar
  7. 7.
    Li, H., Lin, W., Tye, B., Ong, E., Ko, C.: Object segmentation with affine motion similarity measure. In: IEEE International Conference on Multimedia and Expo, 2001, August 22-25. ICME 2001, pp. 841–844 (2001)Google Scholar
  8. 8.
    Tekalp, A., Van Beek, P., Toklu, C., Gunsel, B.: Two-dimensional mesh-based visual-object representation for interactive synthetic/natural digital video. Proceedings of the IEEE 86(6), 1029–1051 (1998)CrossRefGoogle Scholar
  9. 9.
    Artner, N., López Mármol, S.B., Beleznai, C., Kropatsch, W.G.: Kernel-based tracking using spatial structure. In: 32nd annual workshop of the Austrian Association for Pattern Recognition, Austria, pp. 103–114 (2008)Google Scholar
  10. 10.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. Image and Vision Computing 22(10), 761–767 (2004)CrossRefGoogle Scholar
  11. 11.
    Birchfeld, S.: Klt: An implementation of the kanade-lucas-tomasi feature tracker (March 2008), http://www.ces.clemson.edu/~stb/klt/
  12. 12.
    Moss, S., Wilson, R.C., Hancock, E.R.: A mixture model for pose clustering. Pattern Recognition Letters 20(11–13), 1093–1101 (1999)CrossRefGoogle Scholar
  13. 13.
    Klette, R., Rosenfeld, A.: Digital Geometry. Morgan Kaufmann, San Francisco (2004)zbMATHGoogle Scholar
  14. 14.
    Shi, J., Tomasi, C.: Good features to track. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 593–600. IEEE Computer Society Press, Los Alamitos (June 1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Salvador B. López Mármol
    • 1
    • 3
  • Nicole M. Artner
    • 2
  • Adrian Ion
    • 1
  • Walter G. Kropatsch
    • 1
  • Csaba Beleznai
    • 2
  1. 1.PRIPVienna University of TechnologyAustria
  2. 2.Austrian Research Centers GmbH - ARC, Smart Systems DivisionViennaAustria
  3. 3.Andalusian Research Group FQM-296: “Computational Topology and Applied Mathematics”Spain

Personalised recommendations