Efficient compressive sensing tracking via mixed classifier decision

Abstract

Recent years have witnessed successful use of tracking-by-detection methods, with a number of promising results being achieved. Most of these algorithms use a sliding window to collect samples and then employ these samples to train and update the classifiers. They also use an updated classifier to establish the appearance model and they take the maximum response value of the classifier as the location of the target within a fixed radius. Compressive Tracking (CT) is a novel tracking-by-detection algorithm that updates the appearance model in a compressed domain. However, the conventional CT algorithm uses a single classifier to detect the target, and if the selected region drifts, the classifier may become inaccurate. Furthermore, the CT algorithm updates the classifier parameters with a constant learning rate. Therefore, if the target is completely occluded for an extended period, the classifier will instead learn the features of the covered object and the target will ultimately be lost. To overcome these problems, we present a compressive sensing tracking algorithm using mixed classifier decision. The main improvements in our algorithm are that it adopts mixed classifiers to locate the target and it applies a dynamic learning rate to update the appearance model. An experimental comparison with state-of-the-art algorithms on eight benchmark video sequences in complicated situations shows that the proposed algorithm achieves the best performance with 12 pixels on the average center location error and 66.82% on the average overlap score.

This is a preview of subscription content, access via your institution.

References

  1. 1

    Cannons K. A Review of Visual Tracking. Technical Report CSE-2008-07. 2008

    Google Scholar 

  2. 2

    Yilmaz A, Javed O, Shah M. Object tracking: a survey. ACM Comput Surv, 2006, 38: 1–35

    Article  Google Scholar 

  3. 3

    Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking. Pattern Anal Mach Intell, 2003, 25: 564–577

    Article  Google Scholar 

  4. 4

    Ross D, Lim J, Lin R-S, et al. Incremental learning for robust visual tracking. Int J Comput Vision, 2008, 77: 125–141

    Article  Google Scholar 

  5. 5

    Mei X, Ling H. Robust visual tracking using l1 minimization. In: Proceedings of IEEE International Conference on Computer Vision, Nice, 2009. 1436–1443

    Google Scholar 

  6. 6

    Fan J, Shen X, Wu Y. Scribble tracker: a matting-based approach for robust tracking. Pattern Anal Mach Intell, 2012, 34: 1633–1644

    Article  Google Scholar 

  7. 7

    Wu Y, Huang T S. Robust visual tracking by integrating multiple cues based on co-inference learning. Int J Comput Vision, 2004, 58: 55–71

    Article  Google Scholar 

  8. 8

    Kwon J, Lee K M. Visual tracking decomposition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, 2010. 1269–1276

    Google Scholar 

  9. 9

    Adam A, Rivlin E, Shimshoni I. Robust fragments-based tracking using the integral histogram. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, New York, 2006. 798–805

    Google Scholar 

  10. 10

    Mei X, Ling H. Robust visual tracking and vehicle classification via sparse rep-resentation. Pattern Anal Mach Intell, 2011, 33: 2259–2272

    Article  Google Scholar 

  11. 11

    Li H, Shen C, Shi Q. Real-time visual tracking using compressive sensing. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence, 2011. 1305–1312

    Google Scholar 

  12. 12

    Liu B Y, Huang J Z, Yang L, et al. Robust tracking using local sparse appearance model and k-selection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence, 2011. 1313–1320

    Google Scholar 

  13. 13

    Jia X, Lu H, Yang M-H. Visual tracking via adaptive structural local sparse appearance model. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence, 2012. 1822–1829

    Google Scholar 

  14. 14

    Zhang T, Ghanem B, Liu S, et al. Robust visual tracking via structured multi-task sparse learning. Int J Comput Vision, 2013, 101: 367–383

    MathSciNet  Article  Google Scholar 

  15. 15

    Collins R, Liu Y, Leordeanu M. Online selection of discriminativetracking features. Pattern Anal Mach Intell, 2005, 27: 1631–1643

    Article  Google Scholar 

  16. 16

    Babenko B, Yang M-H, Belongie S. Visual tracking with online multiple instance learning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Miami, 2009. 983–990

    Google Scholar 

  17. 17

    Babenko B, Yang M-H, Belongie S. Robust object tracking with online multiple instance learning. Pattern Anal Mach Intell, 2011, 33: 1619–1632

    Article  Google Scholar 

  18. 18

    Kalal Z, Matas J, Mikolajczyk K. P-N learning: bootstrapping binary classifier by structural constraints. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, 2010. 49–56

    Google Scholar 

  19. 19

    Zhang Y, Du B, Zhang L. A sparse Representation-Based binary hypothesis model for target detection in hyperspectral images. IEEE Trans Geosci Remote Sens, 2015, 53: 1346–1354

    Article  Google Scholar 

  20. 20

    Tao D, Cheng J, Song M, et al. Manifold ranking-based matrix factorization for saliency detection. IEEE Trans Neural Netw Lear Syst, in press. doi: 10.1109/TNNLS.2015.2461554

  21. 21

    Tao D, Lin X, Jin L, et al. Principal component 2-dimensional long short-term memory for font recognition on single Chinese characters. IEEE Trans Cybernetics, in press. doi: 10.1109/TCYB.2015.2414920

  22. 22

    Tao D C, Tang X O, Li X L, et al. Asymmetric bagging and random subspace for support vector machines-based relevance feedback in image retrieval. IEEE Trans Pattern Anal Mach Intell, 2006, 28: 1088–1099

    Article  Google Scholar 

  23. 23

    Tao D C, Li X L, Wu X D, et al. General tensor discriminant analysis and gabor features for gait recognition. IEEE Trans Pattern Anal Mach Intell, 2007, 29: 1700–1715

    Article  Google Scholar 

  24. 24

    Xu C, Tao D C, Xu C. Multi-view intact space learning. IEEE Trans Pattern Anal Mach Intell, 2015, 37: 2531–2544

    Article  Google Scholar 

  25. 25

    Liu T L, Tao D C. Classification with noisy labels by importance reweighting. IEEE Trans Pattern Anal Mach Intell, in press. doi: 10.1109/TPAMI.2015.2456899

  26. 26

    Zhang K, Zhang L, Yang M-H. Real-time compressive tracking. In: Proceedings of European Conference on Computer Vision, Florence, 2012. 864–877

    Google Scholar 

  27. 27

    Avidan S. Support vector tracking. IEEE Trans Pattern Anal Mach Intell, 2004, 26: 1064–1072

    Article  Google Scholar 

  28. 28

    Collins R, Liu Y, Leordeanu M. Online selection of discriminative tracking features. IEEE Trans Pattern Anal Mach Intell, 2005, 27: 1631–1643

    Article  Google Scholar 

  29. 29

    Avidan S. Ensemble tracking. IEEE Trans Pattern Anal Mach Intell, 2007, 29: 261–271

    Article  Google Scholar 

  30. 30

    Grabner H, Leistner C, Bischof H. Semi-supervised on-line boosting for robust tracking. In: Proceedings of European Conference on Computer Vision, Prague, 2008. 234–247

    Google Scholar 

  31. 31

    Zhou Q, Lu H, Yang M H. Online multiple support instance tracking. In: Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition, Ljubljana, 2011. 545–552

    Google Scholar 

  32. 32

    Hare S, Saffari A, Torr P. Struck: structured output tracking with kernels. In: Proceedings of IEEE International Conference on Computer Vision, Barcelona, 2011. 263–270

    Google Scholar 

  33. 33

    Henriques F, Caseiro R, Martins P, et al. Exploiting the circulant structure of tracking-by-detection with kernels. In: Proceedings of European Conference on Computer Vision, Florence, 2012. 702–715

    Google Scholar 

  34. 34

    Grabner H, Grabner M, Bischof H. Real-time tracking via online boosting. In: Proceedings of British Machine Vision Conference, Edinburgh, 2006. 47–56

    Google Scholar 

  35. 35

    Kalal Z, Mikolajczyk K, Matas J. Tracking-learning-detection. IEEE Trans Pattern Anal Mach Intell, 2011, 34: 1409–1422

    Article  Google Scholar 

  36. 36

    Wu Y, Lim J, Yang M H. Online object tracking: a benchmark. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Portland, 2013. 2411–2418

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding authors

Correspondence to Jing Li or Jun Chang.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Sun, H., Li, J., Chang, J. et al. Efficient compressive sensing tracking via mixed classifier decision. Sci. China Inf. Sci. 59, 072102 (2016). https://doi.org/10.1007/s11432-015-5424-5

Download citation

Keywords

  • compressive sensing
  • object tracking
  • mixed classifier decision
  • dynamic learning rate
  • appearance model update