access icon free Optimal colour-based mean shift algorithm for tracking objects

The mean-shift method is widely used to locate a target object quickly in sequential images. The mean-shift algorithm takes advantage of a colour distribution with a uniform quantisation. However, the quantisation method ignores the close relationship of colour statistics. The uniform distribution also results in a colour histogram with many empty bins, which introduces additional computation cost in the tracking procedure. To reduce the number of these redundant, empty bins, the authors present a new optimal colour-based, mean-shift algorithm for tracking objects. In the proposed method, the optimal colours are extracted by a histogram agglomeration, which clusters three-dimensional (3D) colour histogram bins with the frequency ratios of 3D colour values. After obtaining optimal colours in a RGB colour histogram, the target image is represented by the indices of the optimal colours. The mean-shift algorithm thus creates a confidence map in a candidate image based on the optimal colour histogram in the target image. It then finds the peak of the confidence map near the previous position of an object area. Comparative experiments with the conventional mean-shift method showed that our method has the advantages of decreased processing time and improved tracking accuracy.

Inspec keywords: computer vision; feature extraction; quantisation (signal); object tracking; image sequences; image representation; image colour analysis; statistical distributions

Other keywords: colour distribution; computation cost; uniform quantisation method; confidence map; object target localization; computer vision; optimal colour-based mean shift algorithm; colour statistics; object tracking; uniform distribution; sequential images; 3D colour histogram bins; histogram agglomeration extraction; target image representation; RGB colour histogram

Subjects: Computer vision and image processing techniques; Other topics in statistics; Other topics in statistics; Image recognition

References

    1. 1)
    2. 2)
      • 24. http://www.cvg.cs.rdg.ac.uk/PETS2001/pets2001-dataset.html, accessed May 2012.
    3. 3)
    4. 4)
    5. 5)
    6. 6)
    7. 7)
    8. 8)
    9. 9)
    10. 10)
    11. 11)
    12. 12)
    13. 13)
    14. 14)
    15. 15)
      • 24. http://www.cvg.cs.rdg.ac.uk/PETS2001/pets2001-dataset.html, accessedMay 2012.
    16. 16)
      • 19. Selim, S.Z., Ismail, M.A.: ‘K-means-type algorithms: a generalized convergence theorem and characterization of local optimality’, IEEE Trans. Pattern Anal. Mach. Intell., 1984, 6, (1), pp. 8187 (doi: 10.1109/TPAMI.1984.4767478).
    17. 17)
      • 23. Comaniciu, D., Ramesh, V., Meer, P.: ‘Kernel-based object tracking’, IEEE Trans. Pattern Anal. Mach. Intell., 2003, 25, (5), pp. 564575 (doi: 10.1109/TPAMI.2003.1195991).
    18. 18)
      • 11. Fang, J., Yang, J., Liu, H.: ‘Efficient and robust fragments-based multiple Kernels tracking’, AEU-Int. J. Electron. Commun., 2011, 65, (11), pp. 915923 (doi: 10.1016/j.aeue.2011.02.013).
    19. 19)
      • 18. Wada, T., Hamatsuka, T., Kato, T.: ‘K-means tracking: a robust target tracking against background involution’, MIRU, 2004, 2, pp. 712.
    20. 20)
      • 22. Camapum, J., Fisher, M.: ‘Spatial-feature parametric clustering applied to motion-based segmentation in Camouflage’, Comput. Vis. Image Underst., 2002, 85, (2), pp. 144157 (doi: 10.1006/cviu.2001.0944).
    21. 21)
      • 13. Isard, M., Blake, A.: ‘Contour tracking by stochastic propagation of conditional density’. European Conf. on Computer Vision-ECCV, 1996, pp. 343356.
    22. 22)
      • 5. Isard, M., Blake, A.: ‘Condensation-conditional density propagation for visual tracking’, Int. J. Comput. Vis., 1998, 29, (1), pp. 528 (doi: 10.1023/A:1008078328650).
    23. 23)
      • 17. Hartigan, J.A., Wong, M.A.: ‘Algorithm AS136: a K-means clustering algorithm’, J. R. Stat. Soc.. Series C (Applied Statistics), 1979, 28, (1), pp. 100108.
    24. 24)
      • 9. Comaniciu, D., Meer, P.: ‘Mean shift: a robust approach toward feature space analysis’, IEEE Trans. Pattern Anal. Mach. Intell., 2002, 24, (5), pp. 603619 (doi: 10.1109/34.1000236).
    25. 25)
      • 6. Yao, A., Lin, X., Wang, G., Yu, S.: ‘A compact association of particle filtering and Kernel based object tracking’, Pattern Recognit., 2012, 45, (7), pp. 25842597 (doi: 10.1016/j.patcog.2012.01.016).
    26. 26)
      • 20. Koontz, G., Narendra, M., Fukunaga, K.: ‘A graph-theoretic approach to non-parametric clustering’, IEEE Trans. Comput., 1976, 25, (9), pp. 936944 (doi: 10.1109/TC.1976.1674719).
    27. 27)
      • 2. Steger, C., Ulrich, M., Wiedemann, C.: ‘Machine vision algorithms and applications’ (Wiley-VCH, 2007, 1st edn.).
    28. 28)
      • 15. Zhao, Q., Yang, Z., Tao, H.: ‘Differential earth mover's distance with its applications to visual tracking’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 32, (2), pp. 274287 (doi: 10.1109/TPAMI.2008.299).
    29. 29)
      • 10. Shen, C., Brooks, M.: ‘Fast global Kernel density mode seeking: applications to localization and tracking’. Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 2005, vol. 16, no. 5, pp. 15161523.
    30. 30)
      • 12. Zhao, Q., Tao, H.: ‘Object tracking using colour correlogram’. Proc. Joint IEEE Int. Workshop on VS-PETS, 2005, pp. 263270.
    31. 31)
      • 4. Odobez, J.M., Perez, D.G., Ba, S.O.: ‘Embedding motion in model-based stochastic tracking’, IEEE Trans. Image Process., 2006, 15, (11), pp. 35143530 (doi: 10.1109/TIP.2006.877497).
    32. 32)
      • 21. Matas, J., Kittler, J.: ‘Spatial and feature space clustering: applications in image analysis’. Proc. Sixth Int. Conf. on Computer Analysis and Patterns, 1995.
    33. 33)
      • 16. Karavasilis, V., Nikou, C., Likas, A.: ‘Visual tracking using the earth mover's distance between Gaussian mixtures and Kalman filtering’, Image Vis. Comput., 2011, 29, (5), pp. 295305 (doi: 10.1016/j.imavis.2010.12.002).
    34. 34)
      • 8. Yang, C., Duraiswami, R., Davis, L.: ‘Efficient mean-shift tracking via a new similarity measure’. Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 2005, vol. 1, pp. 176183.
    35. 35)
      • 14. Roh, M., Kim, T., Park, J., Lee, S.: ‘Accurate object contour tracking based on boundary edge selection’, Pattern Recognit., 2007, 40, (3), pp. 931943 (doi: 10.1016/j.patcog.2006.06.014).
    36. 36)
      • 7. Collins, R.T.: ‘Mean-shift blob tracking through scale space’. Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 2003, vol. 2, pp. 234241.
    37. 37)
      • 3. Yilmaz, A., Javed, O., Shah, M.: ‘Object Tracking: a survey’, ACM Computer Surveys, 2006, 38, (4), pp. 145 (doi: 10.1145/1177352.1177355).
    38. 38)
      • 1. Baird, H.S.: ‘Model-based image matching using location’ (MIT Press, 1985).
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2013.0004
Loading

Related content

content/journals/10.1049/iet-cvi.2013.0004
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading