Signal, Image and Video Processing

, Volume 8, Supplement 1, pp 103–112 | Cite as

Improved mean shift target tracking based on self-organizing maps

  • Xiaohui ChenEmail author
  • Mengjiao Zhang
  • Kai Ruan
  • Guangzhu Xu
  • Shuifa Sun
  • Canfeng Gong
  • Jiangbo Min
  • Bangjun Lei
Original Paper


Thanks to its simplicity and real-time processing possibility, mean shift has been widely used for video tracking. However, it often fails when the background is similar to the intended object or when the object is partially or completely occluded. To address these two problems, in this paper we propose a novel algorithm based on mean shift by exploring simultaneously the temporal and spatial information of the tracked object. A cascade classification method based on nearest neighbor and self-organizing maps is employed as a confirmation step to eliminate spurious objects through the structure information of the object. The forward and backward tracking results are further combined to improve the localization accuracy and tolerate at the same time scale variation. Experiments have shown clearly the superior performance of the proposed system in terms of accuracy, stability and robustness.


Video object tracking Mean shift Topology preservation Self-organizing maps Forward–backward tracking 



This project is supported by 2012 Natural Science Foundation of Hubei Province (2012FFC09701) and the National Natural Science Foundation of China (61102155).


  1. 1.
    Xia, J., Rao, W., Huang, W., Lu, Z.: Automatic multi-vehicle tracking using video cameras: an improved CAMShift approach. KSCE J. Civil. Eng. 17(6), 1462–1470 (2013)CrossRefGoogle Scholar
  2. 2.
    Park, M. W., Brilakis, I.: Enhancement of construction equipment detection in video frames by combining with tracking. In: Proceedings of the 2012 ASCE International Conference on Computing in Civil Engineering, pp. 421–428 (2012)Google Scholar
  3. 3.
    Ye, Y., Mu, Q., Zhang, C.: Tunnel construction multivariate information forewarning and safety management system research. Chin. J. Rock. Mech. Eng. 5, 009 (2009)Google Scholar
  4. 4.
    Li, X., Hu W., Shen, C., Zhang, Z., Dick, A., Van den Hengel, A.: A survey of appearance models in visual object tracking. ACM Trans. Intell. Syst. Technol. 4(4), 58 ( 2013)Google Scholar
  5. 5.
    Ross, D.A., Lim, J., Lin, R.S., Yang, M.H.: Incremental learning for robust visual tracking. Int. J. Comput. Vis. 77(1–3), 125–141 (2008)CrossRefGoogle Scholar
  6. 6.
    Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift. Comput. Vis. Pattern. Recognit. 2, 142–149 (2000)Google Scholar
  7. 7.
    Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. Pattern. Anal. Mach. Intell. IEEE Trans. 25(5), 564–577 (2003)CrossRefGoogle Scholar
  8. 8.
    Zhang, S., Yao, H., Sun, X., Lu, X.: Sparse coding based visual tracking: review and experimental comparison. Pattern. Recognit. 46(7), 1772–1788 (2013)CrossRefGoogle Scholar
  9. 9.
    Zhang, S., Yao, H., Zhou, H., Sun, X., Liu, S.: Robust visual tracking based on online learning sparse representation. Neurocomputing 100, 31–40 (2013)CrossRefGoogle Scholar
  10. 10.
    Zhang, S., Yao, H., Sun, X., Liu, S.: Robust visual tracking using an effective appearance model based on sparse coding. ACM Trans. Intell. Syst. Technol. 3(3), 43 (2012)Google Scholar
  11. 11.
    Avidan, S.: Support vector tracking. Pattern. Anal. Mach. Intell. IEEE Trans. 26(8), 1064–1072 (2004)CrossRefGoogle Scholar
  12. 12.
    Grabner, H., Grabner, M., Bischof, H.: Real-time tracking via on-line boosting. BMVC 1(5), 6 (2006)Google Scholar
  13. 13.
    Grabner, H., Leistner, C., Bischof, H.: Semi-supervised on-line boosting for robust tracking. Computer Vision-ECCV 2008. Springer, Berlin Heidelberg (2008)Google Scholar
  14. 14.
    Babenko, B., Yang, M.H., Belongie, S.: Robust object tracking with online multiple instance learning. Pattern. Anal. Mach. Intell. IEEE Trans. 33(8), 1619–1632 (2011)CrossRefGoogle Scholar
  15. 15.
    Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. Pattern. Anal. Mach. Intell. IEEE Trans. 34(7), 1409–1422 (2012)CrossRefGoogle Scholar
  16. 16.
    Hare, S., Saffari, A., Torr, P. H.: Struck: structured output tracking with kernels. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 263–270 (2011)Google Scholar
  17. 17.
    Zhang, K., Zhang, L., Yang, M.H.: Real-time compressive tracking. Computer Vision-ECCV 2012. Springer, Berlin Heidelberg (2012)Google Scholar
  18. 18.
    Birchfield, S. T., Rangarajan, S.: Spatiograms versus histograms for region-based tracking. Comput. Vis. Pattern. Recognit. CVPR 2005. IEEE computer society conference on. IEEE, Vol. 2, 1158–1163 (2005)Google Scholar
  19. 19.
    Collins, R.T., Liu, Y., Leordeanu, M.: Online selection of discriminative tracking features. Pattern. Anal. Mach. Intell. IEEE Trans. 27(10), 1631–1643 (2005)CrossRefGoogle Scholar
  20. 20.
    Zivkovic, Z., Krose, B.: An EM-like algorithm for color- histogram-based object tracking. Computer vision and pattern recognition, 2004. Proc. IEEE Comput. Soc. Conf. Vol. 1, I-798– I-803 (2004)Google Scholar
  21. 21.
    Jeyakar, J., Babu, R.V., Ramakrishnan, K.R.: Robust object tracking with background-weighted local kernels. Comput. Vis. Image Underst. 112(3), 296–309 (2008)CrossRefGoogle Scholar
  22. 22.
    Phadke, G., Velmurugan, R.: Improved mean shift for multi-target tracking. In Performance evaluation of tracking and surveillance (PETS), 2013 IEEE International Workshop on. IEEE, 37–44, (2013)Google Scholar
  23. 23.
    Collins, R. T.: Mean-shift blob tracking through scale space. Computer vision and pattern recognition, 2003. Proc. IEEE Comput. Soc. Conf. IEEE, Vol. 2, II-234–240 (2003)Google Scholar
  24. 24.
    Vojir, T., Noskova, J., Matas, J.: Robust scale-adaptive mean-shift for tracking: in image analysis. Springer, Berlin Heidelberg (2013)Google Scholar
  25. 25.
    Ning, J., Zhang, L., Zhang, D., Wu, C.: Scale and orientation adaptive mean shift tracking. Comput. Vis. IET 6(1), 52–61 (2012)CrossRefMathSciNetGoogle Scholar
  26. 26.
    Ning, J., Zhang, L., Zhang, D., Wu, C.: Robust object tracking using joint color-texture histogram. Int. J. Pattern. Recognit. Artif. Intell. 23(07), 1245–1263 (2009)CrossRefGoogle Scholar
  27. 27.
    Xiaorong, P., Zhihu, Z.: A more robust mean shift tracker on joint color-CLTP histogram. Int. J. Image Gr. Signal. Process. 4(12), 34–42 (2012)CrossRefGoogle Scholar
  28. 28.
    Liu, B., Huang, J., Yang, L., Kulikowsk, C.: Robust tracking using local sparse appearance model and k-selection. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1313–1320 (2011)Google Scholar
  29. 29.
    Yang, Y., Jia, Y.X., Rong, C.Z., Zhu, Y., Wang, Y., Yue, Z.J., Gao, Z.X.: Object tracking based on corrected background-weighted histogram mean shift and kalman filter. Adv. Mate. Res. 765, 720–725 (2013)Google Scholar
  30. 30.
    Khan, Z.H., Gu, I.Y.H., Backhouse, A.G.: Robust visual object tracking using multi-mode anisotropic mean shift and particle filters. Circuits. Syst. Video Technol. IEEE Trans. 21(1), 74–87 (2011)CrossRefGoogle Scholar
  31. 31.
    Yao, A., Lin, X., Wang, G., Yu, S.: A compact association of particle filtering and kernel based object tracking. Pattern. Recognit. 45(7), 2584–2597 (2012) Google Scholar
  32. 32.
    Wang, L., Yan, H., Wu, H. Y., Pan, C.: Forward–backward mean-shift for visual tracking with local-background-weighted histogram. IEEE Trans. Intell. Transp. Syst. 14(3), 1480–1489 (2013)Google Scholar
  33. 33.
    Cheng, Y.: Mean shift, mode seeking, and clustering. Pattern. Anal. Mach. Intell. IEEE Trans. 17(8), 790–799 (1995)CrossRefGoogle Scholar
  34. 34.
    Kalal, Z., Mikolajczyk, K., Matas, J.: Forward–backward error: automatic detection of tracking failures. Pattern. Recognit. (ICPR), 2010 20th international conference on. IEEE, 2756–2759 (2010)Google Scholar
  35. 35.
    Kohonen, T.: Essentials of the self-organizing map. Neural Netw. 37, 52–65 (2013)CrossRefGoogle Scholar
  36. 36.
    Wu, Y., Lim, J., Yang, M. H.: Online object tracking: a benchmark. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2411–2418 (2013)Google Scholar
  37. 37.
    Wang, F., Yu, S., Yang, J.: Robust and efficient fragments-based tracking using mean shift. AEU Int. J. Electron. Commun. 64(7), 614–623 (2010)CrossRefGoogle Scholar
  38. 38.
    Ning, J., Zhang, L., Zhang, D., Wu, C.: Robust mean-shift tracking with corrected background-weighted histogram. Comput. Vis. IET 6(1), 62–69 (2012)CrossRefMathSciNetGoogle Scholar
  39. 39.
    Zhang, K., Zhang, L., Yang, M.: Real-time object tracking via online discriminative feature selection. IEEE Trans. Image Process. 22(12), 4664–4677 (2013)Google Scholar
  40. 40.
    Wang, N., Yeung, D. Y.: Learning a deep compact image representation for visual tracking. In: 27th Annual Conference on Neural Information Processing Systems, NIPS 2013, pp. 809–817 (2013)Google Scholar

Copyright information

© Springer-Verlag London 2014

Authors and Affiliations

  • Xiaohui Chen
    • 1
    • 2
    Email author
  • Mengjiao Zhang
    • 1
  • Kai Ruan
    • 1
  • Guangzhu Xu
    • 1
    • 2
  • Shuifa Sun
    • 1
    • 2
  • Canfeng Gong
    • 1
  • Jiangbo Min
    • 1
  • Bangjun Lei
    • 1
    • 2
  1. 1.College of Computer and Information TechnologyChina Three Gorges UniversityYichangPeople’s Republic of China
  2. 2.Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric EngineeringChina Three Gorges UniversityYichangPeople’s Republic of China

Personalised recommendations