Advertisement

Disagreement-Based Multi-system Tracking

  • Quannan Li
  • Xinggang Wang
  • Wei Wang
  • Yuan Jiang
  • Zhi-Hua Zhou
  • Zhuowen Tu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7729)

Abstract

In this paper, we tackle the tracking problem from a fusion angle and propose a disagreement-based approach. While most existing fusion-based tracking algorithms work on different features or parts, our approach can be built on top of nearly any existing tracking systems by exploiting their disagreements. In contrast to assuming multi-view features or different training samples, we utilize existing well-developed tracking algorithms, which themselves demonstrate intrinsic variations due to their design differences. We present encouraging experimental results as well as theoretical justification of our approach. On a set of benchmark videos, large improvements (20% ~40%) over the state-of-the-art techniques have been observed.

Keywords

Tracking Algorithm Time Stamp Unlabeled Data Appearance Model Visual Tracking 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Avidan, S.: Ensemble tracking. In: CVPR (2005)Google Scholar
  2. 2.
    Tang, F., Brennan, S., Zhao, Q., Tao, H.: Co-tracking using semi-supervised support vector machines. In: ICCV (2007)Google Scholar
  3. 3.
    Grabner, H., Leistner, C., Bischof, H.: Semi-supervised On-Line Boosting for Robust Tracking. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 234–247. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  4. 4.
    Lim, J., Ross, D., Lin, R.-S., Yang, M.-H.: Incremental learning for visual tracking. Int’l J. of Comp. Vis. (2008)Google Scholar
  5. 5.
    Babenko, B., Yang, M.-H., Belongie, S.: Visual tracking with online multiple instance learning. In: CVPR (2009)Google Scholar
  6. 6.
    Zhou, Z.-H., Li, M.: Semi-supervised learning by disagreement. Knowledge and Information Systems 24, 415–439 (2010)CrossRefGoogle Scholar
  7. 7.
    Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: COLT, pp. 92–100 (1998)Google Scholar
  8. 8.
    Zhou, Z.-H., Li, M.: Tri-training: Exploiting unlabeled data using three classifiers. IEEE Trans. on Know. and Data Eng. (2005)Google Scholar
  9. 9.
    Dietterich, T.G.: Ensemble Methods in Machine Learning. In: Kittler, J., Roli, F. (eds.) MCS 2000. LNCS, vol. 1857, pp. 1–15. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  10. 10.
    Kuncheva, L.I.: A theoretical study on six classifier fusion strategies. IEEE Tran. on PAMI 24, 281–286 (2002)CrossRefGoogle Scholar
  11. 11.
    Bennett, K.P., Demiriz, A., Maclin, R.: Exploiting Unlabeled Data in Ensemble Methods. In: ACM SIGKDD 2002, Edmonton, Alberta, CA (2002)Google Scholar
  12. 12.
    Wang, W., Zhou, Z.-H.: Analyzing Co-training Style Algorithms. In: Kok, J.N., Koronacki, J., Lopez de Mantaras, R., Matwin, S., Mladenič, D., Skowron, A. (eds.) ECML 2007. LNCS (LNAI), vol. 4701, pp. 454–465. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  13. 13.
    Wu, Y., Huang, T.: Robust visual tracking by integrating multiple cues based on co-inference learning. In’l J. of Comp. Vis. (2004)Google Scholar
  14. 14.
    Siebel, N.T., Maybank, S.: Fusion of Multiple Tracking Algorithms for Robust People Tracking. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part IV. LNCS, vol. 2353, pp. 373–387. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  15. 15.
    Triesch, J., von der Naksvyrg, C.: Democratic integration: Self-organized integration of adaptive visual cues. Neural Computation (2001)Google Scholar
  16. 16.
    Spengler, M., Schiele, B.: Towards robust multi-cue integration of visual tracking. In: MVA (2003)Google Scholar
  17. 17.
    Kwon, J., Lee, K.M.: Visual tracking decomposition. In: CVPR (2010)Google Scholar
  18. 18.
    Leichter, I., Lindenbaum, M., Rivlin, E.: A general framework for combining visual trackers the ’black boxes’ approach. Int’l J. of Comp. Vis. (2006)Google Scholar
  19. 19.
    Zhong, B., Yao, H., Chen, S., Ji, R.-R., Yuan, X., Liu, S., Gao, W.: Visual tracking via weakly supervised learning from multiple imperfect oracles. In: CVPR (2010)Google Scholar
  20. 20.
    Stenger, B., Woodley, T., Cipolla, R.: Learning to track with multiple observers. In: CVPR (2009)Google Scholar
  21. 21.
    Mundy, J.L., Chang, C.F.: Fusion of intensity, texture, and color in video tracking based on mutual information. In: AIPR (2010)Google Scholar
  22. 22.
    Collins, M., Singer, Y.: Unsupervised models for named entity classification. In: EMNLP (1999)Google Scholar
  23. 23.
    Leskes, B., Torenvliet, L.: The value of agreement a new boosting algorithm. J. of Comp. and Sys. Sci. (2008)Google Scholar
  24. 24.
    Dasgupta, S., Littman, M.L., McAllester, D.: Pac generalization bounds for co-training. In: NIPS (1999)Google Scholar
  25. 25.
    Wang, W., Zhou, Z.-H.: A new analysis of co-training. In: ICML, Haifa, Israel, pp. 1135–1142 (2010)Google Scholar
  26. 26.
    Zhou, Y., Goldman, S.: Democratic co-learning. In: Inte’l Conf. on Tools with Art. Intell. (2004)Google Scholar
  27. 27.
    Dasgupta, S.: Coarse sample complexity bounds for active learning. In: NIPS (2005)Google Scholar
  28. 28.
    Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift. In: CVPR (2000)Google Scholar
  29. 29.
    Isard, M., Blake, A.: Condensation - conditional density propagation for visual tracking. Int’l J. on Comp. Vis. (1998)Google Scholar
  30. 30.
    Santner, J., Leistner, C., Saffari, A., Pock, T., Bischof, H.: Prost: Parallel robust online simple tracking. In: CVPR (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Quannan Li
    • 1
  • Xinggang Wang
    • 2
  • Wei Wang
    • 3
  • Yuan Jiang
    • 3
  • Zhi-Hua Zhou
    • 3
  • Zhuowen Tu
    • 1
    • 4
  1. 1.Lab of Neuro ImagingUniversity of CaliforniaLos AngelesUSA
  2. 2.Huazhong University of Science and TechnologyChina
  3. 3.National Key Laboratory for Novel Software TechnologyNanjing UniversityChina
  4. 4.Microsoft Research AsiaChina

Personalised recommendations