access icon free Adaptive earth movers distance-based Bayesian multi-target tracking

This study describes a complete system for multiple-target tracking in image sequences. The target appearance is represented as a set of weighted clusters in colour space. This is in contrast to the more typical use of colour histograms to model target appearance. The use of clusters allows a more flexible and accurate representation of the target, which demonstrates the benefits for tracking. However, it also introduces a number of computational difficulties, as calculating and matching cluster signatures are both computationally intensive tasks. To overcome this, the authors introduce a new formulation of incremental medoid-shift clustering that operates faster than mean shift in multi-target tracking scenarios. This matching scheme is integrated into a Bayesian tracking framework. Particle filters, a special case of Bayesian filters where the state variables are non-linear and non-Gaussian, are used in this study. An adaptive model update procedure is proposed for the cluster signature representation to handle target changes with time. The model update procedure is demonstrated to work successfully on a synthetic dataset and then on real datasets. Successful tracking results are shown on public datasets. Both qualitative and quantitative evaluations have been carried out to demonstrate the improved performance of the proposed multi-target tracking system. A higher tracking accuracy in long image sequences has been achieved compared to other standard tracking methods.

Inspec keywords: image matching; target tracking; image representation; tracking filters; particle filtering (numerical methods); image colour analysis; image sequences

Other keywords: tracking accuracy; mean shift; Bayesian filters; adaptive earth mover distance-based Bayesian multitarget tracking; cluster signature representation; nonlinear state variables; adaptive model update procedure; image sequences; colour histograms; incremental medoid-shift clustering; cluster signature matching; nonGaussian state variables; weighted clusters; target appearance representation; colour space; synthetic dataset; particle filters

Subjects: Computer vision and image processing techniques; Filtering methods in signal processing; Image recognition

References

    1. 1)
      • 20. Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: ‘Introduction to algorithms’ (The MIT Press, 2009, 3rd edn.).
    2. 2)
      • 19. Tenenbaum, J.B., de Silva, V., Langford, J.C.: ‘A global geometric framework for nonlinear dimensionality reduction’, Science, 2000, 290, (5500), pp. 23192323 (doi: 10.1126/science.290.5500.2319).
    3. 3)
      • 14. Jain, A.K.: ‘Fundamentals of digital image processing’ (Prentice-Hall International, Englewood Cliffs, New Jersey 0732, United States of America, 1989, 1 edn.).
    4. 4)
      • 21. Doucet, A., De Freitas, N., Gordon, N.: ‘Sequential Monte Carlo methods in practice’ (Statistics for Engineering and Information Science, Springer, 2001, 1 edn.).
    5. 5)
      • 15. Kumar, P., Ranganath, S., Huang, W.: ‘Queue based fast background modelling and fast hysteresis thresholding for better foreground segmentation’. The Fourth Pacific Rim Conf. Multimedia. Proc. 2003 Joint Conf. Fourth Int. Conf. Information, Communications and Signal Processing, 2003, vol. 2, pp. 743747.
    6. 6)
      • 1. Dorin, C., Visvanathan, R., Meer, P.: ‘Real-time tracking of non-rigid objects using mean shift’. IEEE Conf. Computer Vision and Pattern Recognition, 2000, Hilton Head Island, SC, USA, 2000, vol. 2, pp. 142149.
    7. 7)
      • 17. Birchfield, S.T., Rangarajan, S.: ‘Spatiograms versus histograms for region-based tracking’. IEEE Conf. Computer Vision and Pattern Recognition, 2005, vol. 2, pp. 11581163.
    8. 8)
      • 16. Cheng, Y.: ‘Mean shift, mode seeking, and clustering’, IEEE Trans. Patt. Anal. Mach. Intell., 1995, 17, (8), pp. 790799 (doi: 10.1109/34.400568).
    9. 9)
      • 2. Arulampalam, S., Maskell, S., Gordon, N., Clapp, T.: ‘A tutorial on particle filters for on-line non-linear/non-Gaussian Bayesian tracking’, IEEE Trans. Signal Process., 2002, 50, (2), pp. 174188 (doi: 10.1109/78.978374).
    10. 10)
      • 8. Ling, H., Okada, K.: ‘An efficient earth mover's distance algorithm for robust histogram comparison’, IEEE Trans. Patt. Anal. Mach. Intell., 2007, 29, (5), pp. 840853 (doi: 10.1109/TPAMI.2007.1058).
    11. 11)
      • 10. Zhao, Q., Brennan, S., Tao, H.: ‘Differential EMD tracking’. IEEE Int. Conf. Computer Vision, 2007, pp. 18.
    12. 12)
      • 4. Comaniciu, D., Visvanathan, R., Meer, P.: ‘Kernel-based object tracking’, IEEE Trans. Patt. Anal. Mach. Intell., 2003, 25, (5), pp. 564577 (doi: 10.1109/TPAMI.2003.1195991).
    13. 13)
      • 3. Rubner, Y., Tomasi, C., Guibas, L.J.: ‘The earth mover's distance as a metric for image retrieval’, Int. J. Comput. Vis., 2000, 40, (2), pp. 99121 (doi: 10.1023/A:1026543900054).
    14. 14)
      • 5. Kumar, P., Brooks, M.J., Dick, A.: ‘Adaptive multiple object tracking using colour and segmentation cues’. Asian Conf. Computer Vision, 2007, vol. 1, pp. 853863.
    15. 15)
      • 18. Birchfield, S.T., Rangarajan, S.: ‘Spatial histograms for region-based tracking’, Electron. Telecommun. Res. Inst. J., 2007, 29, (5), pp. 697699.
    16. 16)
      • 11. Perez, P., Vermaak, J., Blake, A.: ‘Data fusion for visual tracking with particles’, Proc. IEEE, 2004, 92, (3), pp. 495513 (doi: 10.1109/JPROC.2003.823147).
    17. 17)
      • 13. Kaufman, L., Rousseeuw, P.J.: ‘Clustering by means of medoids’, Stat. Data Anal. Based L1 Norm, 1987, 3, pp. 353360.
    18. 18)
      • 24. Gad, A., Majdi, F., Farooq, M.: ‘A comparison of data association techniques for target tracking in clutter’. Proc. Fifth Int. Conf. Information Fusion, 2002, vol. 2, pp. 11261133.
    19. 19)
      • 23. Kumar, P., Dick, A., Brooks, M.J.: ‘Integrated Bayesian multi-cue tracker for objects observed from moving cameras’. 23rd Int. Conf. Image and Vision Computing, New Zealand, 2008, vol. 1, pp. 16.
    20. 20)
      • 25. Zhao, Q., Tao, H.: ‘Differential earth mover's distance and its application in visual tracking’, IEEE Trans. Patt. Anal. Mach. Intell., 2010, 32, (2), pp. 274287 (doi: 10.1109/TPAMI.2008.299).
    21. 21)
      • 9. Shirdhonkar, S., Jacobs, D.: ‘Approximate earth mover's distance in linear time’. IEEE Conf. Computer Vision and Pattern Recognition, June 2008, pp. 18.
    22. 22)
      • 7. Kumar, P., Dick, A., Brooks, M.: ‘Multiple target tracking with an efficient compact colour correlogram’. 10th Int. Conf. Control, Automation, Robotics and Vision, 2008 (ICARCV, 2008), December 2008, pp. 699704.
    23. 23)
      • 22. Kumar, P., Ranganath, S., Sengupta, K., Huang, W.: ‘Cooperative multitarget tracking with efficient split and merge handling’, IEEE Trans. Circuits Syst. Video Technol., 2006, 16, (12), pp. 14771490 (doi: 10.1109/TCSVT.2006.885715).
    24. 24)
      • 6. Nummiaro, K., Koller-Meier, E., Gool, L.J.V.: ‘Object tracking with an adaptive color-based particle filter’. Proc. 24th DAGM Symposium on Pattern Recognition, London, UK, 2002, vol. 21, pp. 353360.
    25. 25)
      • 12. Sheikh, Y., Khan, E., Kanade, T.: ‘Mode-seeking by medoidshifts’. IEEE 11th Int. Conf. Computer Vision, 2007, no. 1, pp. 18.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2011.0223
Loading

Related content

content/journals/10.1049/iet-cvi.2011.0223
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading