Robust Real-Time Visual Tracking Using Pixel-Wise Posteriors

  • Charles Bibby
  • Ian Reid
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5303)


We derive a probabilistic framework for robust, real-time, visual tracking of previously unseen objects from a moving camera. The tracking problem is handled using a bag-of-pixels representation and comprises a rigid registration between frames, a segmentation and online appearance learning. The registration compensates for rigid motion, segmentation models any residual shape deformation and the online appearance learning provides continual refinement of both the object and background appearance models. The key to the success of our method is the use of pixel-wise posteriors, as opposed to likelihoods. We demonstrate the superior performance of our tracker by comparing cost function statistics against those commonly used in the visual tracking literature. Our comparison method provides a way of summarising tracking performance using lots of data from a variety of different sequences.


Visual Tracking Pixel Location Probabilistic Framework Rigid Transformation Motion Blur 
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.

Supplementary material

978-3-540-88688-4_61_MOESM1_ESM.avi (29.3 mb)
Supplementary material (30,044 KB)


  1. 1.
    Osher, S., Paragios, N.: Geometric Level Set Methods in Imaging, Vision and Graphics. Springer, Secaucus, NJ, USA (2003)zbMATHGoogle Scholar
  2. 2.
    Paragios, N., Deriche, R.: Geodesic active contours and level sets for the detection and tracking of moving objects. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(3), 266–280 (2000)CrossRefGoogle Scholar
  3. 3.
    Goldenberg, R., Kimmel, R., Rivlin, E., Rudzsky, M.: Fast geodesic active contours. IEEE Trans. on Image Processing 10(10), 1467–1475 (2001)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Cremers, D.: Dynamical statistical shape priors for level set based tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(8), 1262–1273 (2006)CrossRefGoogle Scholar
  5. 5.
    Cremers, D., Rousson, M., Deriche, R.: A review of statistical approaches to level set segmentation: Integrating color, texture, motion and shape. International Journal of Computer Vision V72(2), 195–215 (2007)CrossRefGoogle Scholar
  6. 6.
    Jebara, T.: Images as bags of pixels. In: Proc. 9th Int’l Conf. on Computer Vision, Nice (2003)Google Scholar
  7. 7.
    Chan, T., Vese, L.: Active contours without edges. IEEE Trans. Image Processing 10(2), 266–277 (2001)CrossRefzbMATHGoogle Scholar
  8. 8.
    Freedman, D., Zhang, T.: Active contours for tracking distributions. IEEE Transactions on Image Processing 13(4), 518–526 (2004)CrossRefGoogle Scholar
  9. 9.
    Zhang, T., Freedman, D.: Improving performance of distribution tracking through background matching. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(2), 282–287 (2005)CrossRefGoogle Scholar
  10. 10.
    Li, C., Xu, C., Gui, C., Fox, M.D.: Level set evolution without re-initialization: A new variational formulation. In: Proc. 22nd IEEE Conf. on Computer Vision and Pattern Recognition, San Diego, California, vol. 1, pp. 430–436. IEEE Computer Society, Los Alamitos (2005)Google Scholar
  11. 11.
    Yilmaz, A.: Object tracking by asymmetric kernel mean shift with automatic scale and orientation selection. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Minneapolis, Minnesota (2007)Google Scholar
  12. 12.
    Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift. In: Proc. 19th IEEE Conf. on Computer Vision and Pattern Recognition, Hilton Head Island, vol. 2, pp. 142–149 (2000)Google Scholar
  13. 13.
    Collins, R.T.: Mean-shift blob tracking through scale space. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 234–240 (2003)Google Scholar
  14. 14.
    Baker, S., Matthews, I.: Lukas-kanade 20 years on: A unifiying framework. International Journal of Computer Vision 69(3), 221–255 (2004)CrossRefGoogle Scholar
  15. 15.
    Rother, C., Kolmogorov, V., Blake, A.: Grabcut: Interactive foreground extraction using iterated graph cuts. In: ACM Transactions on Graphics (SIGGRAPH 2004) (2004)Google Scholar
  16. 16.
    Evans, L.C.: Partial Differential Equations. AMS (2002)Google Scholar
  17. 17.
    Cremers, D., Osher, S.J., Soatto, S.: Kernel density estimation and intrinsic alignment for shape priors in level set segmentation. International Journal of Computer Vision 69(3), 335–351 (2006)CrossRefGoogle Scholar
  18. 18.
    Fisher, R.: CAVIAR Test Case Scenarios, EC Funded IST 2001 37540. Online Book (October 2004)Google Scholar
  19. 19.
    Kadir, T., Brady, M.: Estimating statistics in arbitrary regions of interest. In: Proc. 16th British Machine Vision Conf., Oxford (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Charles Bibby
    • 1
  • Ian Reid
    • 1
  1. 1.Active Vision Lab Department of Engineering ScienceUniversity of OxfordUK

Personalised recommendations