Statistical Patch-Based Observation for Single Object Tracking

  • Mohd Asyraf Zulkifley
  • Bill Moran
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6979)


Statistical patch-based observation (SPBO) is built specifically for obtaining good tracking observation in robust environment. In video analytics applications, the problems of blurring, moderate deformation, low ambient illumination, homogenous texture and illumination change are normally encountered as the foreground objects move. We approach the problems by fusing both feature and template based methods. While we believe that feature based matchings are more distinctive, we consider that object matching is best achieved by means of a collection of points as in template based detectors. Our algorithm starts by building comparison vectors at each detected point of interest between consecutive frames. The vectors are matched to build possible patches based on their respective coordination. Patch matching is done statistically by modelling the histograms of patches as Poisson distributions for both RGB and HSV colour models. Then, maximum likelihood is applied for position smoothing while a Bayesian approach is applied for size smoothing. Our algorithm performs better than SIFT and SURF detectors in a majority of the cases especially in complex video scenes.


Neyman-Pearson Tracking observation Poisson modelling Maximum likelihood 


  1. 1.
    Canny, J.: A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 6, 679–698 (1986)CrossRefGoogle Scholar
  2. 2.
    Duda, R.O., Hart, P.E.: In: Sobel, I., Feldman, G. (eds.) A 3x3 Isotropic Gradient Operator for Image Processing, pp. 271–272 (1973)Google Scholar
  3. 3.
    Roberts, L.G.: Machine perception of three-dimensional solids. PhD thesis, Dept. of Electrical Engineering, Massachusetts Institute of Technology (1963)Google Scholar
  4. 4.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Proceedings of the 4th Alvey Vision Conference, pp. 147–151 (1988)Google Scholar
  5. 5.
    Shi, J., Tomasi, C.: Good features to track. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 593–600 (1994)Google Scholar
  6. 6.
    Ke, Y., Suthankar, R.: Pca-sift: a more distinctive representation for local image descriptors. In: IEEE Computer Society Conference Computer Vision and Pattern Recognition, vol. 2, pp. 506–513 (2004)Google Scholar
  7. 7.
    Burghouts, G.J., Geusebroek, J.M.: Performance evaluation of local colour invariants. Computer Vision and Image Understanding 113, 48–62 (2008)CrossRefGoogle Scholar
  8. 8.
    Geusebroek, J.M., Smeulders, A.W.M., Boomgaarda, R.V.D.: Color invariance. IEEE Transactions on Pattern Analysis and Machine Intelligence 23, 1338–1350 (2001)CrossRefGoogle Scholar
  9. 9.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence 27, 1615–1630 (2005)CrossRefGoogle Scholar
  10. 10.
    Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-up robust features (surf). Computer Vision and Image Understanding 110, 346–359 (2008)CrossRefGoogle Scholar
  11. 11.
    Kay, S.M.: Fundamentals of Statistical Signal Processing, Detection Theory, vol. 2. Prentice Hall, Englewood Cliffs (1998)Google Scholar
  12. 12.
    Evans, C.: Notes on the opensurf library. Technical Report CSTR-09-001, University of Bristol (January 2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Mohd Asyraf Zulkifley
    • 1
  • Bill Moran
    • 1
  1. 1.Department of Electrical and Electronic EngineeringThe University of MelbourneVictoriaAustralia

Personalised recommendations