Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

Multi-task non-negative matrix factorization for visual object tracking

  • Theoretical advances
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

This paper proposes an online object tracking algorithm in which the object tracking is achieved by using multi-task sparse learning and non-negative matrix factorization under the particle filtering framework. The object appearance is first modeled by subspace learning to reflect the target variations across frames. Combination of non-negative components is learned from examples observed in previous frames. In order to robust tracking an object, group sparsity constraints are included to the non-negativity one. Furthermore, the alternating direction method of multipliers algorithm is employed to compute the model efficiently. Qualitative and quantitative experiments on a variety of challenging sequences show favorable performance of the proposed algorithm against state-of-the-art methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References

  1. Yilmaz A, Javed O, Shah M (2006) Object tracking: a survey. ACM Comput Surv 38(4):13–32

    Article  Google Scholar 

  2. Ross D, Lim J, Lin RS, Yang MH (2008) Incremental learning for robust visual tracking. Int J Comput Vis 77(1):125–141

    Article  Google Scholar 

  3. Mei X, Ling H (2011) Robust visual tracking and vehicle classification via sparse representation. IEEE Trans Pattern Anal Mach Intell 33(11):2259–2272

    Article  Google Scholar 

  4. Zhang T, Ghanem B, Liu S, Ahuja N (2012) Low-rank sparse learning for robust visual tracking. In: ECCV 2012. Springer, Berlin, pp 470–484

    Chapter  Google Scholar 

  5. Zhang T, Ghanem B, Liu S, Ahuja N (2012) Robust visual tracking via multi-task sparse learning. In: IEEE conference on computer vision and pattern recognition, pp 1–8

  6. Zhang K, Zhang L, Yang M-H (2012) Real-time compressive tracking. In: Proceedings of European conference on computer vision, vol 3, Florence, Italy, pp 864–877

    Chapter  Google Scholar 

  7. Bao C, Wu Y, Ling H, Ji H (2012) Real time robust L1 tracker using accelerated proximal gradient approach. In: IEEE conference on computer vision and pattern recognition (CVPR), Rhode Island

  8. Wu Y, Shen B, Ling H (2014) Visual tracking via online non-negative matrix factorization. IEEE Trans Circuits Syst Video Technol 24(3):374–383

    Article  Google Scholar 

  9. Babenko B, Yang M-H, Belongie S (2011) Robust object tracking with online multiple instance learning. IEEE Trans Pattern Anal Mach Intell 33(8):1619–1632

    Article  Google Scholar 

  10. Wang Q, Chen F, Xu W, Yang M-H (2012) Online discriminative object tracking with local sparse representation. In: IEEE workshop on the applications of computer vision, pp 425–432

  11. Li X, Hu W, Shen C, Zhang Z, Dick A, Hengel A (2013) A survey of appearance models in visual object tracking. ACM Trans Intell Syst Technol 4(4):58

    Article  Google Scholar 

  12. Adam A, Rivlin E, Shimshoni I (2006) Robust fragments-based tracking using the integral histogram. CVPR 1:798–805

    Google Scholar 

  13. Kwon J, Lee KM (2010) Visual tracking decomposition. In: CVPR, pp 1269–1276

  14. Wang S, Lu H, Yang F, Yang M-H (2011) Superpixel Tracking. In: IEEE international conference on ICCV, pp 1323–1330

  15. Wang Y, Hu S, Wu S (2015) Visual tracking based on group sparsity learning. Mach Vis Appl 26(1):127–139

    Article  Google Scholar 

  16. Lee DD, Seung HS (1999) Learning the parts of objects by non-negative matrix factorization. Nature 401:788–791

    Article  Google Scholar 

  17. Sun DL, Fevotte C (2014) Alternating direction method of multipliers for non-negative matrix factorization with the beta-divergence. In: 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE

  18. Boyd S, Parikh N, Chu E, Peleato B, Eckstein J (2011) Distributed optimization and statistical learning via the alternating direction method of multipliers. Found Trends Mach Learn 3(1):1–122

    Article  Google Scholar 

  19. Wang Y, Luo X, Hu S (2016) Visual tracking via multi-task non-negative matrix factorization. In: 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE

  20. Zhang K, Song H (2013) Real-time visual tracking via online weighted multiple instance learning. Pattern Recognit 46(1):397–411

    Article  MathSciNet  Google Scholar 

  21. Grabner H, Bischof H (2006) On-line boosting and vision. In: Proceedings of the IEEE CVPR, pp 260–267

  22. Grabner H, Leistner C, Bischof H (2008) Semi-supervised on-line boosting for robust tracking. In: Proceedings of the 10th ECCV, pp 234–247

    Google Scholar 

  23. Hu W, Li X, Zhang X, Shi X, Maybank SJ, Zhang Z (2011) Incremental tensor subspace learning and its applications to foreground segmentation and tracking. Int J Comput Vis 91(3):303–327

    Article  Google Scholar 

  24. Li X, Hu W, Zhang Z, Zhang X, Luo G (2007) Robust visual tracking based on incremental tensor subspace learning. In: Proceedings of the IEEE ICCV, pp 1–8

  25. Mei X, Zhou SK, Porikli F (2007) Probabilistic visual tracking via robust template matching and incremental subspace update. In: Proceedings of the IEEE ICME, pp 1818–1821

  26. Porikli F, Tuzel O, Meer P (2006) Covariance tracking using model update based on lie algebra. In: Proceedings of the IEEE computer society conference CVPR, pp 728–735

  27. Pinho RR, Correia MV (2005) A movement tracking management model with Kalman filtering, global optimization techniques and mahalanobis distance. In: Lecture series on computer and computational sciences, vol 4A. Brill Academic Publishers, pp 463–466

  28. Pinho RR, Tavares JMRS (2009) Tracking features in image sequences with Kalman filtering, global optimization, mahalanobis distance and a management model. CMES 46(1):51–75

    MATH  Google Scholar 

  29. Pinho RR, Tavares JMRS, Correia MV (2006) An improved management model for tracking missing features in computer vision long image sequences. WSEAS Trans Inf Sci Appl 3(11):2165–2170

    Google Scholar 

  30. Tavares JMRS, Padilha A (1995) Matching lines in image sequences with geometric constraints. In: RecPad’95—7th Portuguese conference on pattern recognition

  31. Pinho RR, Tavares JMRS, Correia MFV (2007) Efficient approximation of the mahalanobis distance for tracking with the Kalman filter. Int J Simul Model 6(2):84–92; ISSN: 1726-4529, DAAAM International Vienna

    Article  Google Scholar 

  32. Li H, Shen C, Shi Q (2011) Real-time visual tracking using compressive sensing. In: CVPR

  33. Yuan X-T, Liu X, Yan S (2012) Visual classification with multitask joint sparse representation. TIP 21(10):4349–4360

    MathSciNet  MATH  Google Scholar 

  34. Zhang H, Nasrabadi NM, Zhang Y, Huang TS (2011) Multi-observation visual recognition via joint dynamic sparse representation. In: ICCV

  35. Shekhar S, Patel VM, Nasrabadi NM, Chellappa R (2012) Joint sparsity-based robust multimodal biometrics recognition. In: ECCV

  36. Lin CJ (2007) On the convergence of multiplicative update algorithms for non-negative matrix factorization. IEEE Trans Neural Netw 18(6):1589–1596

    Article  Google Scholar 

  37. Cai D, He X, Han J, Huang TS (2011) Graph regularized non-negative matrix factorization for data representation. IEEE Trans Pattern Anal Mach Intell 33(8):1548–1560

    Article  Google Scholar 

  38. Guan N, Tao D, Luo Z, Yuan B (2012) Online non-negative matrix factorization with robust stochastic approximation. IEEE Trans Neural Netw Learn 23(7):1087–1099

    Article  Google Scholar 

  39. Bucak SS, Gunsel B (2009) Incremental subspace learning via non-negative matrix factorization. Patt Recognit 42(5):788–797

    Article  Google Scholar 

  40. Zhou G, Yang Z, Xie S, Yang J-M (2011) Online blind source separation using incremental non-negative matrix factorization with volume constraint. IEEE Trans Neural Netw 22(4):550–560

    Article  Google Scholar 

  41. Qian YZ, Xu Z (2014) Visual tracking with structural appearance model based on extended incremental non-negative matrix factorization. Neurocomputing 136:327–336

    Article  Google Scholar 

  42. Wang D, Lu HC (2013) On-line learning parts-based representation via incremental orthogonal projective non-negative matrix factorization. Signal Process 93(6):1608–1623

    Article  Google Scholar 

  43. Liu F, Zhou T, Fu K, Gu IYH, Yang J (2016) Robust visual tracking via inverse nonnegative matrix factorization. In: 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 1491–1495

  44. Jalali A, Sanghavi S, Ruan C, Ravikumar PK (2010) A dirty model for multi-task learning. In: Advances in neural information processing systems, pp 964–972

  45. Wang D, Lu H, Yang M-H (2013) Least soft-threshold squares tracking. In: CVPR, pp 2371–2378

  46. Xiao Z, Huchuan L, Wang D (2014) L2-RLS-based object tracking. IEEE Trans Circuits Syst Video Technol 24(8):1301–1309

    Article  Google Scholar 

  47. Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2010) The PASCAL visual object classes challenge 2010 (VOC2010) results

Download references

Acknowledgements

Funding was provided by National Natural Science Foundation of China (CN) (Grant No. 61374161) and China Aviation Science Foundation (Grant No. 20142057006).

Author information

Authors and Affiliations

  1. School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Canada

    Yong Wang

  2. School of Electronic information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China

    Xinbin Luo & Shan Fu

  3. School of Aeronautics and Astronautics, Shanghai Jiao Tong University, Shanghai, China

    Yong Wang, Lu Ding & Shiqiang Hu

Authors
  1. Yong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xinbin Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lu Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shan Fu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Shiqiang Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xinbin Luo.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, Y., Luo, X., Ding, L. et al. Multi-task non-negative matrix factorization for visual object tracking. Pattern Anal Applic 23, 493–507 (2020). https://doi.org/10.1007/s10044-019-00812-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-019-00812-4

Keywords

Search

Navigation