Pattern Analysis and Applications

, Volume 7, Issue 2, pp 144–150 | Cite as

Improving the selection of feature points for tracking

  • Zoran ŽivkovićEmail author
  • Ferdinand van der Heijden
Theoretical Advances


The problem considered in this paper is how to select the feature points (in practice, small image patches are used) in an image from an image sequence, such that they can be tracked adequately further through the sequence. Usually, the tracking is performed by some sort of local search method looking for a similar patch in the next image in the sequence. Therefore, it would be useful if we could estimate “the size of the convergence region” for each image patch. There is a smaller chance of error when calculating the displacement for an image patch with a large convergence region than for an image patch with a small convergence region. Consequently, the size of the convergence region can be used as a proper goodness measure for a feature point. For the standard Kanade-Lucas-Tomasi (KLT) tracking method, we propose a simple and fast way to approximate the convergence region for an image patch. In the experimental part, we test our hypothesis on a large set of real data.


Feature (interest) point selection Motion estimation Visual tracking Optical flow Convergence region Robustness 


  1. 1.
    Azarbayejani A, Pentland A (1995) Recursive estimation of motion, structure, and focal length. IEEE T Pattern Anal 17(6):562–575CrossRefGoogle Scholar
  2. 2.
    Beauchemin SS, Barron JL (1995) The computation of optical flow. ACM Comput Surv 27(3):433–467Google Scholar
  3. 3.
    Beymer D, McLauchlan P, Coifman B, Malik J (1997) A real-time computer vision system for measuring traffic parameters. In: Proceedings of the IEEE conference on computer vision and pattern recognition, San Juan, Puerto Rico, June 1997, pp 495–501Google Scholar
  4. 4.
    Bradley AP (1997) The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recogn 30(7):1145–1159CrossRefGoogle Scholar
  5. 5.
    Fletcher R (1987) Practical methods of optimization. John Wiley and Sons, New YorkGoogle Scholar
  6. 6.
    Fusiello A, Trucco E, Tommasini T, Roberto V (1999) Improving feature tracking with robust statistics. Pattern Anal Appl 2(4):312–320CrossRefGoogle Scholar
  7. 7.
    Hager GD, Belhumeur PN (1998) Efficient region tracking with parametric models of geometry and illumination. IEEE T Pattern Anal 20(10):1025–1039CrossRefGoogle Scholar
  8. 8.
    Harris C, Stephens M (1988) A combined corner and edge detector. In: Proceedings of the 4th Alvey vision conference, Manchester, England, August/September 1998, pp 147–151Google Scholar
  9. 9.
    Hartley R, Zisserman A (2000) Multiple view geometry in computer vision. Cambridge University Press, CambridgeGoogle Scholar
  10. 10.
    Horn BKP, Schunck BG (1993) Determining optical flow: A retrospective. Artif Intell 59(1–2):81–87Google Scholar
  11. 11.
    Jin H, Favaro P, Soatto S (2001) Real-time feature tracking and outlier rejection with changes in illumination. In: Proceedings of the 8th IEEE international conference on computer vision, Vancouver, Canada, July 2001, pp 684–689Google Scholar
  12. 12.
    Kuijper A, Florack LMJ (2002) Understanding and modeling the evolution of critical points under Gaussian blurring. In: Proceedings of the 7th European conference on computer vision, Copenhagen, Denmark, May/June 2002, pp 143–157Google Scholar
  13. 13.
    Lindeberg T (1984) Feature detection with automatic scale selection. Int J Computer Vision 30(2):77–116Google Scholar
  14. 14.
    Lucas BD (1984) Generalized image matching by the method of differences. PhD thesis, Dept. of Computer Science, Carnegie-Mellon UniversityGoogle Scholar
  15. 15.
    Lucas BD, Kanade T (1981) An iterative image registration technique with an application to stereo vision. In: Proceedings of the international joint conference on artificial intelligence, Vancouver, Canada, August 1981, pp 674–679Google Scholar
  16. 16.
    Otte M, Nagel HH (1995) Estimation of optical flow based on higher-order spatiotemporal derivatives in interlaced and non-interlaced image sequences. Artif Intell 78(1/2):5–43Google Scholar
  17. 17.
    Schmid C, Mohr R, Bauckhage C (2000) Evaluation of interest point detectors. Int J Computer Vision 37(2):151–172Google Scholar
  18. 18.
    Shi J, Tomasi C (1994) Good features to track. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Seattle, Washington, June 1994, pp 593–600Google Scholar
  19. 19.
    Smith SM, Brady JM (1997) SUSAN – A new approach to low level image processing. Int J Computer Vision 23(1):45–78Google Scholar
  20. 20.
    Song Y, Concalves L, Perona P (2003) Unsupervised learning of human motion. IEEE T Pattern Anal 25(7):814–827CrossRefGoogle Scholar
  21. 21.
    Tomasi C, Kanade T (1991) Detection and tracking of point features. Carnegie Mellon University Technical Report CMU-CS-91–132Google Scholar
  22. 22.
    Tomasi C, Kanade T (1992) Shape and motion from image streams under orthography: A factorization approach. Int J Computer Vision 9(2):137–154Google Scholar
  23. 23.
    Trajkovic M, Hedley M (1998) Fast corner detection. Image Vision Comput 16:75–87Google Scholar
  24. 24.
    Vidyasagar M (1993) Nonlinear systems analysis. Prentice Hall, Upper Saddle River, New JerseyGoogle Scholar
  25. 25.
    Zivkovic Z, van der Heijden F (2002) Better features to track by estimating the tracking convergence region. In: Proceedings of the international conference on pattern recognition, Quebec, Canada, August 2002Google Scholar

Copyright information

© Springer-Verlag London Limited 2004

Authors and Affiliations

  1. 1.Laboratory for Measurement and InstrumentationUniversity of TwenteEnschedeThe Netherlands
  2. 2.University of AmsterdamAmsterdamThe Netherlands

Personalised recommendations