Coupled-Contour Tracking through Non-orthogonal Projections and Fusion for Echocardiography

  • Xiang Sean Zhou
  • Dorin Comaniciu
  • Sriram Krishnan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3021)


Existing methods for incorporating subspace model constraints in contour tracking use only partial information from the measurements and model distribution. We propose a complete fusion formulation for robust contour tracking, optimally resolving uncertainties from heteroscedastic measurement noise, system dynamics, and a subspace model. The resulting non-orthogonal subspace projection is a natural extension of the traditional model constraint using orthogonal projection. We build models for coupled double-contours, and exploit information from the ground truth initialization through a strong model adaptation. Our framework is applied for tracking in echocardiograms where the noise is heteroscedastic, each heart has distinct shape, and the relative motions of epi- and endocardial borders reveal crucial diagnostic features. The proposed method significantly outperforms the traditional shape-space-constrained tracking algorithm. Due to the joint fusion of heteroscedastic uncertainties, the strong model adaptation, and the coupled tracking of double-contours, robust performance is observed even on the most challenging cases.


Motion Estimation Information Fusion Initial Contour Endocardial Border Tracking Framework 
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.
    Cootes, T., Taylor, C.: Active shape models-’smart snakes’. In: Proc. British Machine Vision Conference, pp. 266–275 (1992)Google Scholar
  2. 2.
    Turk, M.A., Pentland, A.P.: Face recognition using eigen-face. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Hawaii, pp. 586–591 (1991)Google Scholar
  3. 3.
    Leedan, Y., Meer, P.: Heteroscedastic regression in computer vision: Problems with bilinear constraint. Intl. J. of Computer Vision 37, 127–150 (2000)zbMATHCrossRefGoogle Scholar
  4. 4.
    Kanazawa, Y., Kanatani, K.: Do we really have to consider covariance matrices for image features? In: Proc. Intl. Conf. on Computer Vision, Vancouver, Canada, Vol. II, pp. 586–591 (2001)Google Scholar
  5. 5.
    Irani, M., Anandan, P.: Factorization with uncertainty. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 539–553. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  6. 6.
    Oh, J.K., Seward, J.B., Tajik, A.J.: The Echo Manual. Lippincott Williams & Wilkins, Philadelphia (1999)Google Scholar
  7. 7.
    Blake, A., Isard, M.: Active contours. Springer, Heidelberg (1998)Google Scholar
  8. 8.
    Jacob, G., Noble, A., Blake, A.: Robust contour tracking in echocardiographic sequence. In: Proc. Intl. Conf. on Computer Vision, Bombay, India, pp. 408–413 (1998)Google Scholar
  9. 9.
    Paragios, N.: A variational approach for the segmentation of the left ventricle in cardiac images. In: Proc. IEEE Workshop onVariational and Level Set Methods in Computer Vision, Vancouver, Canada (2001)Google Scholar
  10. 10.
    Goldenberg, R., Kimmel, R., Rivlin, E., Rudzsky, M.: Cortex segmentation:A fast variational geometric approach. IEEE Trans. Medical Imaging 21, 1544–1551 (2002)CrossRefGoogle Scholar
  11. 11.
    Wang, S., Ji, X., Liang, Z.P.: Landmark-based shape deformation with topology-preserving constraints. In: Proc. Intl. Conf. on Computer Vision, Nice, France (2003)Google Scholar
  12. 12.
    Black, M., Jepson, A.: Eigentracking: Robust matching and tracking of articulated objects using a view-based representation. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1065, pp. 610–619. Springer, Heidelberg (1996)Google Scholar
  13. 13.
    Comaniciu, D.: Nonparametric information fusion for motion estimation. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Madison, Wisconsin, Vol. I, 59–66 (2003)Google Scholar
  14. 14.
    Scharf, L.L.: Statistical Signal Processing. Addison Wesley, Reading (1991)zbMATHGoogle Scholar
  15. 15.
    Bar-Shalom, Y., Campo, L.: The effect of the common process noise on the two-sensor fused track covariance. IEEE Trans. Aero. Elect. Syst. AES-22, 803–805 (1986)CrossRefGoogle Scholar
  16. 16.
    Li, X., Zhu, Y., Han, C.: Unified optimal linear estimation fusion - part i: Unified models and fusion rules. In: Proc. of 3rd Intl. Conf. on Information Fusion, Paris, France, MoC2–10–MoC2–17 (2000)Google Scholar
  17. 17.
    Anderson, B., Moore, J.: Optimal filtering. Prentice-Hall, Englewood Cliffs (1979)zbMATHGoogle Scholar
  18. 18.
    Hall, P., Marshall, D., Martin, R.: Merging and splitting eigenspace models. IEEE Trans. Pattern Anal. Machine Intell. 22, 1042–1048 (2000)CrossRefGoogle Scholar
  19. 19.
    Julier, S., Uhlmannn, J.: A non-divergent estimation algorithm in the presence of unknown correlations. In: Proc. American Control Conf., Alberqueque, NM (1997)Google Scholar
  20. 20.
    Cootes, T., Taylor, C.: Statistical models for appearance for computer vision (2001) (unpublished manuscript), Available at
  21. 21.
    Comaniciu, D.: An algorithm for data-driven bandwidth selection. IEEE Trans. Pattern Anal. Machine Intell. 25, 281–288 (2003)CrossRefGoogle Scholar
  22. 22.
    Akgul, Y., Kambhamettu, C.: A coarse-to-fine deformable contour optimization framework. IEEE Trans. Pattern Anal. Machine Intell. 25, 174–186 (2003)CrossRefGoogle Scholar
  23. 23.
    Mikić, I., Krucinski, S., Thomas, J.D.: Segmentation and tracking in echocardiographic sequences: Active contours guided by optical flow estimates. IEEE Trans. Medical Imaging 17, 274–284 (1998)CrossRefGoogle Scholar
  24. 24.
    Brand, M., Bhotika, R.: Flexible flow for 3D nonrigid object tracking and shape recovery. In: Proc. IEEE Conf. on ComputerVision and Pattern Recognition, Hawaii, Vol. I, pp. 315–322 (2001)Google Scholar
  25. 25.
    Irani, M.: Multi-frame optical flow estimation using subspace constraints. In: Proc. Intl. Conf. on Computer Vision, Kerkyra, Greece, pp. 626–633 (1999)Google Scholar
  26. 26.
    Bregler, C., Hertzmann, A., Biermann, H.: Recovering non-rigid 3d shape from image streams. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Hilton Head, SC. Vol. II, pp. 690–696 (2000)Google Scholar
  27. 27.
    Cremers, D., Kohlberger, T., Schnorr, C.: Nonlinear shape statistics in mumford-shah based segmentation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2351, pp. 93–108. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  28. 28.
    Black, M., Ananadan, P.: The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields. Computer Vision and Image Understanding 63, 75–104 (1996)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Xiang Sean Zhou
    • 1
  • Dorin Comaniciu
    • 1
  • Sriram Krishnan
    • 2
  1. 1.Siemens Corporate ResearchPrincetonUSA
  2. 2.Siemens Medical SolutionsMalvernUSA

Personalised recommendations