Advertisement

Pattern Recognition and Image Analysis

, Volume 28, Issue 1, pp 79–86 | Cite as

An Improved Spatiogram Similarity Measure for Object Tracking

  • Shuqiang Guo
  • Xuenan Shi
Representation, Processing, Analysis, and Understanding of Images
  • 40 Downloads

Abstract

Spatiogram is a generalization of the histogram. It adds high-order spatial information so that the target can be described more precisely. It is important to choose a suitable method of measuring the similarity between two spatiograms when Spatiogram is applied to the target tracking field. However, the original similarity measure based on spatiogram has the limitation of the insufficient discriminative power. Therefore, in this paper, we propose a new spatiogram similarity measure method called BJSD (Bhattacharyya coefficient and Jensen-Shannon divergence). The similarity of the color feature and the similarity of the spatial distribution are calculated by the Bhattacharyya coefficient (BC) and Jensen-Shannon divergence (JSD). Experiments show that the improved similarity measure has better discriminative than the Conaire’s method and the tracking results are more stable and accurate than the traditional mean shift tracking method.

Keywords

spatiogram Jensen-Shannon divergence (JSD) Bhattacharyya coefficient (BC) object tracking mean-shift 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    D. Comaniciu, V. Ramesh, and P. Meer, “Kernelbased object tracking,” IEEE Trans. Pattern Anal. Mach. Intellig. 25 (5), 564–575 (2003).CrossRefGoogle Scholar
  2. 2.
    R. T. Collins, “Mean-shift blob tracking through scale space,” in Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition (Madison, WI, 2003), Vol. 2, no. II-234-40.Google Scholar
  3. 3.
    Nie, Yi, B. Yang, and W. Liao, “An improved mean shift algorithm for target tracking,” Comput. Inf. Technol. (2015).Google Scholar
  4. 4.
    H. Van Trees and K. Bell, A Tutorial on Particle Filters for Online Nonlinear/NonGaussian Bayesian Tracking (Wiley-IEEE Press, 2007).Google Scholar
  5. 5.
    Z. Tao and L. Wang, “Tracking algorithm based on color correlation histogram using particle filter,” in Proc. IEEE Control and Decision Conf. (Qingdao, 2015).Google Scholar
  6. 6.
    P. Dunne and B. Matuszewski, “Choice of similarity measure, likelihood function and parameters for histogram based particle filter tracking in CCTV grey scale video,” Image Vision Comput. 29.2, 178–189 (2011).CrossRefGoogle Scholar
  7. 7.
    A. M. Nagy, A. Ahmed, and H. H. Zayed, “Particle filter based on joint color texture histogram for object tracking,” in Proc. IEEE Image Processing, Applications, and Systems Conf. (Sfax, 2015), pp. 1–6.Google Scholar
  8. 8.
    A. Elgammal, R. Duraiswami, and L. S. Davis, “Probabilistic tracking in joint feature-spatial spaces,” in Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition (Madison, WI, 2003), Vol. 1, pp. I-781–I-788.Google Scholar
  9. 9.
    S. T. Birchfield and S. Rangarajan, “Spatiograms versus histograms for region-based tracking,” in Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, CVPR 2005 (San Diego, 2005), Vol. 2, pp. 1158–1163.Google Scholar
  10. 10.
    C. Ó. Conaire, N. E. O’Connor, and A. Smeaton, “Thermo-visual feature fusion for object tracking using multiple spatiogram trackers,” Machine Vision Appl. 19.5-6, 483–494 (2008).CrossRefGoogle Scholar
  11. 11.
    S. T. Birchfield and S. Rangarajan, “Spatial histograms for region-based tracking,” ETRI J. 29.5, 697–699 (2007).CrossRefGoogle Scholar
  12. 12.
    C. Ó. Conaire, N. E. O’Connor, and A. F. Smeaton, “Organising a daily visual diary using multifeature clustering,” Proc. SPIE—Int. Soc. Opt. Eng. 2007, 65060C–65060C-11 (2007).Google Scholar
  13. 13.
    S. Zeng, et al., “Image retrieval using spatiograms of colors quantized by Gaussian mixture models,” Neurocomputing 171, 673–684 (2016).CrossRefGoogle Scholar
  14. 14.
    A. Ulges, C. H. Lampert, and D. Keysers, “Spatiogram- based shot distances for video retrieval,” in Proc. TRECVID Workshop (2008).Google Scholar
  15. 15.
    C. Yang, R. Duraiswami, and L. Davis, “Efficient mean-shift tracking via a new similarity measure,” in Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition (IEEE Computer Society, 2005), pp. 176–183.Google Scholar
  16. 16.
    J.-S. Hu, C.-W. Juan, and J.-J. Wang, “A spatial-color mean-shift object tracking algorithm with scale and orientation estimation,” Pattern. Recogn. Lett. 29 (16), 2165–2173 (2008).CrossRefGoogle Scholar
  17. 17.
    C. O. Conaire, N. E. O’Connor, and A. F. Smeaton, “An improved spatiogram similarity measure for robust object localization,” in Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing (Honolulu, HI, 2007), pp. I-1069–I-1072.Google Scholar
  18. 18.
    J. R. Hershey and P. A. Olsen, “Approximating the kullback Leibler divergence between Gaussian mixture models,” in Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing (Honolulu, HI, 2007), pp. IV- 317–IV-320.Google Scholar
  19. 19.
    N. Vasconcelos, “On the efficient evaluation of probabilistic similarity functions for image retrieval,” IEEE Trans. Inf. Theory 50.7, 1482–1496 (2004).MathSciNetCrossRefMATHGoogle Scholar

Copyright information

© Pleiades Publishing, Ltd. 2018

Authors and Affiliations

  1. 1.School of Information EngineeringNortheast Electric Power UniversityJilinChina

Personalised recommendations