Tracking Aspects of the Foreground against the Background

  • Hieu T. Nguyen
  • Arnold Smeulders
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3022)


In object tracking, change of object aspect is a cause of failure due to significant changes of object appearances. The paper proposes an approach to this problem without a priori learning object views. The object identification relies on a discriminative model using both object and background appearances. The background is represented as a set of texture patterns. The tracking algorithm then maintains a set of discriminant functions each recognizing a pattern in the object region against the background patterns that are currently relevant. Object matching is then performed efficiently by maximization of the sum of the discriminant functions over all object patterns. As a result, the tracker searches for the region that matches the target object and it also avoids background patterns seen before. The results of the experiment show that the proposed tracker is robust to even severe aspect changes when unseen views of the object come into view.


Discriminant Function Tracking Algorithm IEEE Conf Appearance Model Object Region 
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.
    Adiv, G.: Inherent ambiguities in recovering 3-D motion and structures from noisy flow field. IEEE Trans. on PAMI 11(5), 477–489 (1989)Google Scholar
  2. 2.
    Black, M.J., Jepson, A.D.: 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. 329–342. Springer, Heidelberg (1996)CrossRefGoogle Scholar
  3. 3.
    Chomat, O., Crowley, J.L.: Probabilistic recognition of activity using local appearance. In: Proc. IEEE Conf. on Comp. Vision and Pattern Recogn., pp. II:104–109 (1999)Google Scholar
  4. 4.
    Collins, R., Liu, Y.: On-line selection of discriminative tracking features. In: Proc. IEEE Conf. on Computer Vision (2003)Google Scholar
  5. 5.
    Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift. In: CVPR 2000, pp. II:142–149 (2000)Google Scholar
  6. 6.
    Cootes, T.F., Wheeler, G.V., Walker, K.N., Taylor, C.J.: View-based active appearance models. Image and Vision Computing 20(9-10), 657–664 (2002)CrossRefGoogle Scholar
  7. 7.
    Daugman, J.G.: High confidence visual recognition of persons by a test of statistical independence. IEEE Trans. on PAMI 15(11), 1148–1161 (1993)Google Scholar
  8. 8.
    Duda, P.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley, NewYork (2001)zbMATHGoogle Scholar
  9. 9.
    Gong, S., McKenna, S.J., Collins, J.J.: An investigation into face pose distributions. In: Proc. of 2nd Inter. Conf. on Automated Face and Gesture Recognition, Killington, Vermont (1996)Google Scholar
  10. 10.
    Jain, A.K., Farrokhnia, F.: Unsupervised texture segmentation using Gabor filters. Pattern Recognition 24(12), 1167–1186 (1991)CrossRefGoogle Scholar
  11. 11.
    Jepson, A.D., Fleet, D.J., El-Maraghi, T.F.: Robust online appearance models for visual tracking. In: Proc. IEEE Conf. on Computer Vision and Pattern Recogn., CVPR 2001 (2001)Google Scholar
  12. 12.
    Morency, L.P., Rahimi, A., Darrell, T.: Adaptive view-based appearance models. In: Proc. IEEE Conf. on Comp. Vision and Pattern Recogn., pp. I: 803–810 (2003)Google Scholar
  13. 13.
    Nguyen, H.T., Worring, M., van den Boomgaard, R.: Occlusion robust adaptive template tracking. In: Proc. IEEE Conf. on Computer Vision, ICCV 2001, pp. I: 678–683 (2001)Google Scholar
  14. 14.
    Ravela, S., Draper, B.A., Lim, J., Weiss, R.: Tracking object motion across aspect changes for augmented reality. In: ARPA Image Understanding Workshop, pp. 1345–1352 (1996)Google Scholar
  15. 15.
    Vacchetti, L., Lepetit, V., Fua, P.: Fusing online and offline information for stable 3D tracking in real-time. In: Proc. IEEE Conf. on Comp. Vision and Pattern Recogn., pp. II: 241–248 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Hieu T. Nguyen
    • 1
  • Arnold Smeulders
    • 1
  1. 1.Intelligent Sensory Information Systems, Faculty of ScienceUniversity of AmsterdamAmsterdamThe Netherlands

Personalised recommendations