Fast Video Object Tracking using Affine Invariant Normalization

  • Paraskevi Tzouveli
  • Yannis Avrithis
  • Stefanos Kollias
Conference paper
Part of the IFIP International Federation for Information Processing book series (IFIPAICT, volume 204)


One of the most common problems in computer vision and image processing applications is the localization of object boundaries in a video frame and its tracking in the next frames. In this paper, a fully automatic method for fast tracking of video objects in a video sequence using affine invariant normalization is proposed. Initially, the detection of a video object is achieved using a GVF snake. Next, a vector of the affine parameters of each contour of the extracted video object in two successive frames is computed using affine-invariant normalization. Under the hypothesis that these contours are similar, the affine transformation between the two contours is computed in a very fast way. Using this transformation to predict the position of the contour in the next frame allows initialization of the GVF snake very close to the real position. Applying this technique to the following frames, a very fast tracking technique is achieved. Moreover, this technique can be applied on sequences with very fast moving objects where traditional trackers usually fail. Results on synthetic sequences are presented which illustrate the theoretical developments.


Video Sequence Active Contour Object Boundary Affine Transformation Active Contour Model 
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.


  1. 1.
    J. Guo, J. Kim, and C. Kuo, “An interactive object segmentation system for MPEG video,” IEEE Proceedings of International Conference on Image Processing, Kobe, Japan, 1999.Google Scholar
  2. 2.
    C. Gu and M. Lee, “Semiautomatic segmentation and tracking of semantic video objects,” IEEE Trans. Circuits and Systems for Video Technology, Vol. 8, No. 5, pp.574–584, September, 1998.Google Scholar
  3. 3.
    M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active Contour models,” Int’l J. Computer Vision, vol. 1, pp. 312–333, 1988.Google Scholar
  4. 4.
    H. S. Ip and S. Dinggang, “An Affine-Invariant Active Contour Model (Al-Snake) for Model-Based Segmentation,” Image and Vision Computing, 16(2), pp. 135–146, 1998.CrossRefGoogle Scholar
  5. 5.
    C. Xu and J.L. Prince, “Gradient Vector Flow: A New External Force for Snakes” IEEE Proceedings Conference on Computer Vision and Pattern Recognition, pp 66–71, 1997Google Scholar
  6. 6.
    Y. Avrithis, Y. Xirouhakis, S. Kollias, “Affine-invariant curve normalization for object shape representation, classification, and retrieval,” Machine Vision and Applications, 13, pp. 80–94, 2001.CrossRefGoogle Scholar
  7. 7.
    Y.S. Abu-Mostafa and D. Psaltis, “Image Normalization by Complex Moments,” IEEE Trans. Pattern Analysis and Machine Intelligence vol. 7, pp. 46–55, Jan. 1985.CrossRefGoogle Scholar
  8. 8.
    F. Leymarie and M. D. Levine, “Tracking deformable objects in the plane using an active contour model,” IEEE Trans. Pattern Anal. Machine Intell., vol. 15, pp. 617–634, 1993CrossRefGoogle Scholar
  9. 9.
    A. Blake, M. Isard and D. Reynard, “Learning to track the visual motion of contours”, Journal of Artificial Intelligence, vol. 10, pp. 323–380, 1997Google Scholar
  10. 10.
    C. Tomasi T. Kanade “Shape and Motion from Image Streams; a Factorization Method”, Full Report on the Orthographic Case, March 1992, Cornell TR 92-1270 and Carnegie Mellon CMU-CS-92-104A.Google Scholar
  11. 11.
    J. Shi and C. Tomasi, “Good features to track”, IEEE Proceedings Conference on Computer Vision and Pattern Recognition, pp 593–600, 1994.Google Scholar
  12. 12.
    Y. Avrithis, Y. Xirouhakis and S. Kollias, “Affine-Invariant Curve Normalization for Shape-Based Retrieval,” in Proc. of 15th International Conference on Pattern Recognition (ICPR’ 00), Barcelona, Spain, September 2000, pp. 1015–1018.Google Scholar
  13. 13.
    Y. Xirouhakis, Y. Avrithis and S. Kollias, “Image Retrieval and Classification Using Affine Invariant B-Spline Representation and Neural Networks,” in Proc. of IEE Colloquium on Neural Nets and Multimedia, London, UK, October 1998, pp. 4/1–4/4.Google Scholar

Copyright information

© International Federation for Information Processing 2006

Authors and Affiliations

  • Paraskevi Tzouveli
    • 1
  • Yannis Avrithis
    • 1
  • Stefanos Kollias
    • 1
  1. 1.Electrical and Computer Engineering DepartmentNational Technical University of AthensAthensGreece

Personalised recommendations