Signal, Image and Video Processing

, Volume 13, Issue 1, pp 61–67 | Cite as

Using spatial overlap ratio of independent classifiers for likelihood map fusion in mean-shift tracking

  • Ibrahim Saygin TopkayaEmail author
  • Hakan Erdogan
Original Paper


We combine the outputs of independent classifiers for mean-shift tracking within the likelihood map fusion framework and introduce a novel likelihood fusion technique that directly employs the tracking confidences of likelihood maps which are generated by different binary classifiers. Our proposed measure tries to compensate drifting that may be caused by each likelihood map using their independent tracking results. We present results obtained with the proposed fusion approach using two different classifiers, where one models the tracked object and one models the background. The results show superior performance of the proposed fusion technique as compared to the others. We further discuss how the proposed likelihood map fusion approach can be generalized to any number and any kind of likelihood maps.


Mean shift Camshift Object tracking Classifier combination Background modeling 


  1. 1.
    Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662), vol. 2, pp. 142–149 (2000)Google Scholar
  2. 2.
    Bradski, G.R.: Computer vision face tracking for use in a perceptual user interface. Intel Technol. J. 2(2), 13–27 (1998)Google Scholar
  3. 3.
    Avidan, S.: Ensemble tracking. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, pp. 494–501 (2005)Google Scholar
  4. 4.
    Chang, W.C., Cho, C.W.: Online boosting for vehicle detection. IEEE Trans. Syst. Man Cybern. Part B (Cybernetics) 40(3), 892–902 (2010)CrossRefGoogle Scholar
  5. 5.
    Collins, R., Liu, Y., Leordeanu, M.: On-line selection of discriminative tracking features. IEEE Trans. Pattern Anal. Mach. Intell. 27(1), 1631–1643 (2005)CrossRefGoogle Scholar
  6. 6.
    Liang, D., Huang, Q., Gao, W., Yao, H.: Online selection of discriminative features using bayes error rate for visual tracking. Adv. Multimed. Inf. Process. PCM 2006, 547–555 (2006)Google Scholar
  7. 7.
    Yeh, Y.J., Hsu, C.T.: Online selection of tracking features using adaboost. IEEE Trans. Circuits Syst. Video Technol. 19(3), 442–446 (2009)CrossRefGoogle Scholar
  8. 8.
    Yin, Z., Porikli, F., Collins, R.T.: Likelihood map fusion for visual object tracking. In: 2008 IEEE Workshop on Applications of Computer Vision, pp. 1–7 (2008)Google Scholar
  9. 9.
    Stauffer, C., Grimson, E.: Adaptive background mixture models for real-time tracking. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1999 (2002)Google Scholar
  10. 10.
    Aherne, F.J., Thacker, N.A., Rockett, P.: The Bhattacharyya metric as an absolute similarity measure for frequency coded data. Kybernetika 34(4), 363–368 (1998)MathSciNetzbMATHGoogle Scholar
  11. 11.
    Fisher, R.A.: The use of multiple measurements in taxonomic problems. Ann. Eugen. 7(7), 179–188 (1936)CrossRefGoogle Scholar
  12. 12.
    Chen, H.-T., Liu, T.-L., Fuh, C.-S.: Probabilistic tracking with adaptive feature selection. In: Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004. vol. 2, pp. 736–739 (2004)Google Scholar
  13. 13.
    Kullback, S., Leibler, R.A.: On information and sufficiency. Ann. Math. Stat. 22(1), 79–86 (1951)MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Grabner, H., Grabner, M., Bischof, H.: Real-time tracking via on-line boosting. In: BMVC (2006)Google Scholar
  15. 15.
    Grabner, H., Sochman, J., Bischof, H., Matas, J.: Training sequential on-line boosting classifier for visual tracking. In: 19th International Conference on Pattern Recognition, 2008, pp. 1–4 (2008)Google Scholar
  16. 16.
    Tian, M., Zhang, W., Liu, F.: On-line ensemble svm for robust object tracking. In: Proceedings of the 8th Asian conference on Computer vision—Volume Part I, ACCV’07, pp. 355–364. Springer, Berlin (2007)Google Scholar
  17. 17.
    Medouakh, S., Boumehraz, M., Terki, N.: Improved object tracking via joint color-lpq texture histogram based mean shift algorithm. Signal Image Video Process. 12(3), 583–590 (2018)CrossRefGoogle Scholar
  18. 18.
    Chen, X., Zhang, M., Ruan, K., Guangzhu, X., Sun, S., Gong, C., Min, J., Lei, B.: Improved mean shift target tracking based on self-organizing maps. Signal Image Video Process. 8(1), 103–112 (2014)CrossRefGoogle Scholar
  19. 19.
    Phadke, G., Velmurugan, R.: Mean lbp and modified fuzzy c-means weighted hybrid feature for illumination invariant mean-shift tracking. Signal Image Video Process. 11(4), 665–672 (2017)CrossRefGoogle Scholar
  20. 20.
    Supreeth, H.S.G., Patil, C.M.: Efficient multiple moving object detection and tracking using combined background subtraction and clustering. Signal Image Video Process. (2018).
  21. 21.
    Kasturi, R., Goldgof, D., Soundararajan, P., Manohar, V., Garofolo, J., Bowers, R., Boonstra, M., Korzhova, V., Zhang, J.: Framework for performance evaluation of face, text, and vehicle detection and tracking in video: data, metrics, and protocol. IEEE Trans. Pattern Anal. Mach. Intell. 31(2), 319–336 (2009)CrossRefGoogle Scholar
  22. 22.
    Second IEEE International Workshop on Performance Evaluation of Tracking and Surveillance. Accessed 21 July 2003
  23. 23.
    Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. Ann. Stat. 28(2), 337–407 (2000)MathSciNetCrossRefzbMATHGoogle Scholar
  24. 24.
    Zivkovic, Zoran, van der Heijden, Ferdinand: Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recognit. Lett. 27(7), 773–780 (2006)CrossRefGoogle Scholar
  25. 25.
    Emgucv software library. (2008). Accessed 27 May 2012
  26. 26.
    Bradski, G.: The OpenCV Library. Dr. Dobb’s J. Softw. Tools (2000)Google Scholar
  27. 27.
    McDonald, R.A., Hand, D.J., Eckley, I.A.: An empirical comparison of three boosting algorithms on real data sets with artificial class noise. In: Fourth International Workshop on Multiple Classifier Systems, pp. 35–44. Springer (2003)Google Scholar
  28. 28.
    Freund, Y., Schapire, R.E.: A short introduction to boosting. J. Jpn. Soc. Artif. Intell. 14, 771–780 (1999)Google Scholar
  29. 29.
    Turdu, D., Erdogan, H.: Improving gaussian mixture model based adaptive background modeling using hysteresis thresholding. In: Signal Processing and Communications Applications, 2007. SIU 2007, IEEE 15th, pp. 1 –4 (2007)Google Scholar
  30. 30.
    Wolpert, D.H., Macready, W.G.: No free lunch theorems for optimization. IEEE Trans. Evol. Comput. 1(1), 67–82 (1997)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2018

Authors and Affiliations

  1. 1.VPALABSabanci UniversityIstanbulTurkey

Personalised recommendations