An Improved Real-Time Contour Tracking Algorithm Using Fast Level Set Method

  • Myo Thida
  • Kap Luk Chan
  • How-Lung Eng
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4319)


Human contour provides important information in high level vision tasks such as activity recognition and human computer interaction where detailed analysis of shape deformation is required. In this paper, a real time region-based contour tracking algorithm is presented. The main advantage of our algorithm is the ability of tracking nonrigid objects such as human using an adaptive external speed function with fast level set method. The weighting parameter, λ i is adjusted to accommodate the situations in which the object being tracked and the background have similar intensity. Experimental results show the better performance of the proposed algorithm with adaptive weights.


Active Contour Active Contour Model Subsequent Frame Speed Function Geodesic Active Contour 
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.
    Yilmaz, A., Li, X., Shah, M.: Contour-based tracking with occlusion handling in video acquired using mobile cameras. IEEE Trans. on Pattern Analysis and Machine Intelligence 26(11) (November 2004)Google Scholar
  2. 2.
    Besson, S., Barlaund, M., Aubert, G.: Detection and trackign of moving objects using a new level set based method. In: Proc. International Conference on Pattern Recognition, September 2000, vol. 3, pp. 1100–1105 (2000)Google Scholar
  3. 3.
    Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: IEEE Comptuer Society Conference on Computer Vision and Pattern Recognition, vol. 2 (1999)Google Scholar
  4. 4.
    Chan, T., Vese, L.: Active contours without edges. IEEE Trans. on Image Processing 10(2), 266–277 (2001)CrossRefMATHGoogle Scholar
  5. 5.
    Cremers, D.: Dynamical statistical shape priors for level set based tracking. IEEE Trans. on Pattern Analysis and Machine Intelligence (2006)Google Scholar
  6. 6.
  7. 7.
    Kass, M., Witkin, A., Terzopolous, D.: Snakes: Active contour models. International Journal of Computer Vision 1, 321–331 (1987)CrossRefGoogle Scholar
  8. 8.
    Mansouri, A.: Region tracking via level set pdes without motion computation. IEEE Trans. Pattern Analysis and Machine Intelligence 24, 947–961 (2002)CrossRefGoogle Scholar
  9. 9.
    Paragios, N., Deriche, R.: Unifying boundary and region-based information for geodesic active tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, Colorado, USA (1999)Google Scholar
  10. 10.
    Paragios, N., Deriche, R.: Geodesic active contours and level sets for the detection and tracking of moving objects. IEEE Trans. on Pattern Analysis and Machine Intelligence 22(3), 266–280 (2000)CrossRefGoogle Scholar
  11. 11.
    Shi, Y., Clem Karl, W: Real-time tracking using level sets. Computer Vision and Pattern Recognition (June 2005)Google Scholar
  12. 12.
    Osher, S., Sethian, J.A.: Fronts propagating with curvature dependent speed: Algorithms based on hamiton-jacobi formulations. Journal of Computational Physics 79, 12–49 (1988)CrossRefMathSciNetMATHGoogle Scholar
  13. 13.
    Zhu, S., Yuille, A.: Region competition: Unifying snake/ballon, region growing, and bayes/mdl/energy for multi-band image segmentation. IEEE Trans. on Pattern Analysis and Machine Intelligence 18(9), 884–900 (1996)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Myo Thida
    • 1
  • Kap Luk Chan
    • 1
  • How-Lung Eng
    • 2
  1. 1.Center for Signal Processing, Division of Information Engineering, School of Electrical and Electronic EngineeringNanyang Technological UniversitySingapore
  2. 2.Institute for Infocomm ResearchSingapore

Personalised recommendations