Structure Restriction for Tracking Through Multiple Views and Occlusions

  • B. Martínez
  • A. Pérez
  • L. Ferraz
  • X. Binefa
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4477)


The last advances on multiple kernel tracking consider the kernels as estimators of target features. The state space of the target is defined by the individual state space of these features.

The aim of this work is to construct an algorithm robust against three dimensional rotations and partial occlusions. For this purpose, we take as the state space the two dimensional position of the features and an indicator of occlusions. We extract the three dimensional structure of the target from the first tracked frames and estimate the projection of this structure on each frame. By using this information, we are able to predict the position of a feature even when the kernel provides a wrong estimation, for example during an occlusion. The experimental results showed a good performance correcting errors and in presence of partial occlusions.


Dimensional Structure Tracking Algorithm Multiple View Projective Transformation Partial Occlusion 
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.
    Collins, R.: Mean-Shift Blob Tracking Through Scale Space. In: Computer Vision and Pattern Recognition (CVPR’03), pp. 234–240 (2003)Google Scholar
  2. 2.
    Comaniciu, D., Ramesh, V., Meer, P.: Real-Time Tracking of Non-Rigid Objects Using Mean Shift. In: Computer Vision and Pattern Recognition (CVPR’00), pp. 142–151 (2000)Google Scholar
  3. 3.
    Fan, Z., Wu, Y., Yang, M.: Multiple Collaborative Kernel Tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 502–509 (2005)Google Scholar
  4. 4.
    Hager, G., Dewan, M., Stewart, C.: Multiple Kernel Tracking with ssd. In: Computer Vision and Pattern Recognition (CVPR’04), pp. 790–797 (2004)Google Scholar
  5. 5.
    Jacobs, D.W.: Linear Fitting with Missing Data for Structure-from-Motion. Computer Vision and Image Understanding 82(1), 57–81 (2001)zbMATHCrossRefGoogle Scholar
  6. 6.
    Martínez, B., Ferraz, L., Binefa, X.: Multiple Kernel Two-Step Tracking-. In: International Conference on Image Processing (2006)Google Scholar
  7. 7.
    Ramesh, V., Comaniciu, V., Meer, P.: Kernel-Based Object Tracking. Transactions on Pattern Analysis and Machine Intelligence 25(5), 564–577 (2003)CrossRefGoogle Scholar
  8. 8.
    Wu, Y., Hua, G., Yu, T.: Tracking Articulated Body by Dynamic Markov network. In: International Conference on Computer Vision, pp. 1094–1101 (2003)Google Scholar
  9. 9.
    Zhang, H., Huang, Z., Huang, W., Li, L.: Kernel-Based Method for Tracking Objects with Rotation and Translation. In: International Conference on Pattern Recognition, vol. 2, pp. 728–731 (2004)Google Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • B. Martínez
    • 1
  • A. Pérez
    • 1
  • L. Ferraz
    • 1
  • X. Binefa
    • 1
  1. 1.Universitat Autónoma de Barcelona, Computer Science Department, 08193 Bellaterra, BarcelonaSpain

Personalised recommendations