Weighted Update and Comparison for Channel-Based Distribution Field Tracking

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8926)

Abstract

There are three major issues for visual object trackers: model representation, search and model update. In this paper we address the last two issues for a specific model representation, grid based distribution models by means of channel-based distribution fields. Particularly we address the comparison part of searching. Previous work in the area has used standard methods for comparison and update, not exploiting all the possibilities of the representation. In this work we propose two comparison schemes and one update scheme adapted to the distribution model. The proposed schemes significantly improve the accuracy and robustness on the Visual Object Tracking (VOT) 2014 Challenge dataset.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

Supplementary material (MP4 19,618 KB)

References

  1. 1.
    Bigün, J., Granlund, G.H.: Optimal orientation detection of linear symmetry. In: Proceedings of the IEEE First International Conference on Computer Vision, London, Great Britain, pp. 433–438, June 1987Google Scholar
  2. 2.
    Felsberg, M., Forssén, P.E., Scharr, H.: Channel smoothing: Efficient robust smoothing of low-level signal features. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(2), 209–222 (2006)CrossRefGoogle Scholar
  3. 3.
    Felsberg, M., Larsson, F., Wiklund, J., Wadströmer, N., Ahlberg, J.: Online learning of correspondences between images. IEEE Transactions on Pattern Analysis and Machine Intelligence (2013)Google Scholar
  4. 4.
    Felsberg, M.: Enhanced distribution field tracking using channel representations. In: IEEE ICCV Workshop on Visual Object Tracking Challenge (2013)Google Scholar
  5. 5.
    Forssén, P.E.: Low and Medium Level Vision using Channel Representations. Ph.D. thesis, Linköping University, Sweden (2004)Google Scholar
  6. 6.
    Granlund, G.H.: An Associative Perception-Action Structure Using a Localized Space Variant Information Representation. In: Proceedings of Algebraic Frames for the Perception-Action Cycle (AFPAC), Germany, September 2000Google Scholar
  7. 7.
    Johansson, B., Elfving, T., Kozlov, V., Censor, Y., Forssén, P.E., Granlund, G.: The application of an oblique-projected landweber method to a model of supervised learning. Mathematical and Computer Modelling 43, 892–909 (2006)CrossRefMATHMathSciNetGoogle Scholar
  8. 8.
    Kass, M., Solomon, J.: Smoothed local histogram filters. In: ACM SIGGRAPH 2010 papers, SIGGRAPH 2010, pp. 100:1–100:10. ACM, New York (2010). http://doi.acm.org/10.1145/1833349.1778837
  9. 9.
    Kristan, M., Čehovin, L., Vojir, T., Nebehay, G.: Visual object tracking challenge 2014 evaluation kit. http://votchallenge.net/vot2014/download/vot2014-guidelines.pdf
  10. 10.
    Pouget, A., Dayan, P., Zemel, R.S.: Inference and computation with population codes. Annu. Rev. Neurosci. 26, 381–410 (2003)CrossRefGoogle Scholar
  11. 11.
    Rényi, A.: On measures of entropy and information. In: Proceedings of the Fourth Berkeley Symposium on Mathematical Statistics and Probability, pp. 547–561. University of California Press, Berkeley (1961)Google Scholar
  12. 12.
    Scott, D.W.: Averaged shifted histograms: Effective nonparametric density estimators in several dimensions. Annals of Statistics 13(3), 1024–1040 (1985)CrossRefMATHMathSciNetGoogle Scholar
  13. 13.
    Sevilla-Lara, L., Learned-Miller, E.: Distribution fields for tracking. In: IEEE Computer Vision and Pattern Recognition (2012)Google Scholar
  14. 14.
    Zemel, R.S., Dayan, P., Pouget, A.: Probabilistic interpretation of population codes. Neural Computation 10(2), 403–430 (1998)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Computer Vision Laboratory Department of Electrical EngineeringLinköping UniversityLinköpingSweden

Personalised recommendations