Advertisement

Domain Adaptation for Sequential Detection

  • Šimon Fojtů
  • Karel Zimmermann
  • Tomáš Pajdla
  • Václav Hlaváč
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7944)

Abstract

We propose a domain adaptation method for sequential decision-making process. While most of the state-of-the-art approaches focus on SVM detectors, we propose the domain adaptation method for the sequential detector similar to WaldBoost, which is suitable for real-time processing. The work is motivated by applications in surveillance, where detectors must be adapted to new observation conditions. We address the situation, where the new observation is related to the previous observation by a parametric transformation. We propose a learning procedure, which reveals the hidden transformation between the old and new data. The transformation essentially allows to transfer the knowledge from the old data to the new one. We show that our method can achieve a 60% speedup in the training w.r.t. the baseline WaldBoost algorithm while outperforming it in precision.

Keywords

Receiver Operating Characteristic Training Sample Local Binary Pattern Domain Adaptation Single View 
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.

References

  1. 1.
    Huang, C., Ai, H., Li, Y., Lao, S.: High-performance rotation invariant multiview face detection. PAMI 29(4), 671–686 (2007)CrossRefGoogle Scholar
  2. 2.
    Šochman, J., Matas, J.: Waldboost-learning for time constrained sequential detection. In: CVPR (2005)Google Scholar
  3. 3.
    Tommasi, T., Caputo, B.: The more you know, the less you learn: from knowledge transfer to one-shot learning of object categories. In: BMVC, pp. 1–11 (2009)Google Scholar
  4. 4.
    Tommasi, T., Orabona, F., Caputo, B.: Safety in numbers: Learning categories from few examples with multi model knowledge transfer. In: CVPR, pp. 3081–3088 (2010)Google Scholar
  5. 5.
    Jie, L., Tommasi, T., Caputo, B.: Multiclass transfer learning from unconstrained priors. In: ICCV (2011)Google Scholar
  6. 6.
    Aytar, Y., Zisserman, A.: Tabula rasa: Model transfer for object category detection. In: ICCV, pp. 2252–2259 (2011)Google Scholar
  7. 7.
    Cao, X., Wang, Z., Yan, P., Li, X.: Rapid pedestrian detection in unseen scenes. Neurocomputing 74(17), 3343–3350 (2011)CrossRefGoogle Scholar
  8. 8.
    Grabner, H., Šochman, J., Bischof, H., Matas, J.: Training sequential on-line boosting classifier for visual tracking. In: ICPR, pp. 1–4 (2008)Google Scholar
  9. 9.
    Wald, A.: Sequential Analysis. Dover Phoenix Editions. Dover Publications (2004)Google Scholar
  10. 10.
    Visentini, I., Snidaro, L., Foresti, G.L.: Cascaded online boosting. Journal of Real-Time Image Processing 5(4), 245–257 (2010)CrossRefGoogle Scholar
  11. 11.
    Jain, V., Learned-Miller, E.: Online domain adaptation of a pre-trained cascade of classifiers. In: CVPR, pp. 577–584 (2011)Google Scholar
  12. 12.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: CVPR (2001)Google Scholar
  13. 13.
    Freund, Y., Schapire, R.E.: A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. Journal of Computer and System Sciences 55(1), 119–139 (1997)MathSciNetzbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Šimon Fojtů
    • 1
  • Karel Zimmermann
    • 1
  • Tomáš Pajdla
    • 1
  • Václav Hlaváč
    • 1
  1. 1.Center for Machine PerceptionCzech Technical University in PraguePraha 6Czech Republic

Personalised recommendations