Disjunctive Normal Form of Weak Classifiers for Online Learning based Object Tracking

Zhu Teng, Dong-Joong Kang

2013

Abstract

The use of a strong classifier that is combined by an ensemble of weak classifiers has been prevalent in tracking, classification etc. In the conventional ensemble tracking, one weak classifier selects a 1D feature, and the strong classifier is combined by a number of 1D weak classifiers. In this paper, we present a novel tracking algorithm where weak classifiers are 2D disjunctive normal form (DNF) of these 1D weak classifiers. The final strong classifier is then a linear combination of weak classifiers and 2D DNF cell classifiers. We treat tracking as a binary classification problem, and one full DNF can express any particular Boolean function; therefore 2D DNF classifiers have the capacity to represent more complex distributions than original weak classifiers. This can strengthen any original weak classifier. We implement the algorithm and run the experiments on several video sequences.

References

  1. Avidan S., 2004. Support Vector Tracking. In IEEE Trans. On Pattern Analysis and Machine Intelligence.
  2. Stauffer, C. and E. Grimson, 2000. Learning Patterns of Activity Using Real-Time Tracking. In PAMI, 22(8):747-757.
  3. S. Avidan, 2005. Ensemble tracking. In Proc. CVPR, volume 2, pages 494-501.
  4. H. Grabner and H. Bischof, 2006. On-line boosting and vision. In Proc. CVPR, volume 1, pages 260-267.
  5. H. Grabner, C. Leistner, and H. Bischof, 2008. Semisupervised on-line boosting for robust tracking. In Proc. ECCV.
  6. S. Stalder, H. Grabner, and L. van Gool, 2009. Beyond Semi-Supervised Tracking: Tracking Should Be as Simple as Detection, But Not Simpler than Recognition. In Proc. Workshop Online Learning in Computer Vision.
  7. O. Danielsson, B. Rasolzadeh, and S.Carlsson, 2011. Gated Classifiers: Boosting under High Intra-Class Variation. In Proc. CVPR.
  8. N. Oza and S. Russell, 2001. Online bagging and boosting. In Proc. Artificial Intelligence and Statistics, pages 105-112.
  9. Freund, Y. Schapire, R. E, 1995. A decision-theoretic generalization of on-line learning and an application to boosting. In Computational Learning Theory: Eurocolt 95, pp 23-37.
  10. Comanciu, D., Visvanathan R., Meer. P, 2003. KernelBased Object Tracking. In IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), 25:5, pp 564-575.
  11. Levi, K., Weiss, Y, 2004. Learning Object Detection from a Small Number of Examples: The Importance of Good Features. In IEEE Conf. on Computer Vision and Pattern Recognition.
  12. P. Viola and M. Jones, 2001. Rapid object detection using a boosted cascade of simple features. In Proc. CVPR, volume I, pages 511-518.
  13. Papageorgiou, Oren and Poggio, 1998. A general framework for object detection. In International Conference on Computer Vision.
  14. T. Ahonen, A. Hadid, and M. Pietikäinen, 2004. Face Recognition with Local Binary Patterns. In Proc. Eighth European Conf. Computer Vision, pp. 469-481.
  15. T. Parag, F. Porikli, and A. Elgammal, 2008. Boosting adaptive linear weak classifiers for online learning and tracking. In Proc. CVPR.
  16. K. Tieu and P. Viola, 2000. Boosting image retrieval. In Proc. CVPR, pages 228-235.
  17. Z. Kalal, J. Matas, and K. Mikolajczyk, 2010. P-N Learning: Bootstrapping Binary Classifiers by Structural Constraints. In Proc. CVPR.
  18. Jakob Santner, Christian Leistner, Amir Sa_ari, Thomas Pock, and Horst Bischof, 2010. Prost: Parallel robust online simple tracking. In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, pages 723-730, 13-18.
  19. B. Babenko, M.-H. Yang, and S. Belongie, 2009. Visual Tracking with Online Multiple Instance Learning. In CVPR.
  20. Klein, Cremers, 2011. Boosting Scalable Gradient Features for Adaptive Real-Time Tracking. In Int. Conf. on Robotics and Automation (ICRA).
  21. A. Adam, E. Rivlin, and I. Shimshoni, 2006. Robust fragments based tracking using the integral histogram. In CVPR.
  22. R. Collins, Y. Liu, and M. Leordeanu, 2005. Online selection of discriminative tracking features. In PAMI, 27(10):1631-1643.
  23. M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, 2009. The Pascal Visual Object Classes (VOC) Challenge. In Int. J. Comput. Vision, 88(2):303-308.
Download


Paper Citation


in Harvard Style

Teng Z. and Kang D. (2013). Disjunctive Normal Form of Weak Classifiers for Online Learning based Object Tracking . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-48-8, pages 138-146. DOI: 10.5220/0004240501380146


in Bibtex Style

@conference{visapp13,
author={Zhu Teng and Dong-Joong Kang},
title={Disjunctive Normal Form of Weak Classifiers for Online Learning based Object Tracking},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={138-146},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004240501380146},
isbn={978-989-8565-48-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)
TI - Disjunctive Normal Form of Weak Classifiers for Online Learning based Object Tracking
SN - 978-989-8565-48-8
AU - Teng Z.
AU - Kang D.
PY - 2013
SP - 138
EP - 146
DO - 10.5220/0004240501380146