Advertisement

Object tracking with collaborative extreme learning machines

  • Haipeng KuangEmail author
  • Liang Xun
Article
  • 27 Downloads

Abstract

We propose a novel collaborative discriminative model based on extreme learning machine (ELM) for object tracking in this paper. In order to represent the object more precisely, we first propose a new collaborative discriminative representation model, which includes both a global discriminative sub-model and a local discriminative sub-model. Different from traditional local representation models, in particular, our local sub-model integrates several classifiers which have structural relations to improve the expression. The global discriminative model represents the appearance comprehensively while the local discriminative sub-model can effectively address occlusions and assist the update. Second, to have better combination of these sub-models, we propose a novel collaboration strategy based on the Kullback-Leibler (KL) distance. The novel strategy can determine the weights of the sub-models adaptively by measuring their KL distances reciprocally. Third, we introduce ELM into tracking and adopt it to build both the global and the local discriminative sub-models simultaneously. Since ELM has a good generalization performance and is robust to the imbalance of the training samples, it is suitable to be used for tracking. Experimental results demonstrate that our method can achieve comparable performance to many state-of-the-art tracking approaches.

Keywords

Object tracking Collaborative model Extreme learning machine Kullback-Laibler distance 

Notes

References

  1. 1.
    Adam A, Rivlin E, Shimshoni I (2006) In: Proceedings of the IEEE conference computer vision and pattern recognition (CVPR), vol 1, pp 798–805Google Scholar
  2. 2.
    Avidan S (2004) IEEE Trans Pattern Anal Mach Intell 26(8):1064CrossRefGoogle Scholar
  3. 3.
    Avidan S (2007) IEEE Trans Pattern Anal Mach Intell 29 (2):261.  https://doi.org/10.1109/TPAMI.2007.35 CrossRefGoogle Scholar
  4. 4.
    Babenko B, Yang MH, Belongie S (2011) IEEE Trans Pattern Anal Mach Intell 33(8):1619.  https://doi.org/10.1109/TPAMI.2010.226 CrossRefGoogle Scholar
  5. 5.
    Bai Q, Wu Z, Sclaroff S, Betke M, Monnier C To appear in ICCV2013Google Scholar
  6. 6.
    Baojie Fan YT, Cong Y (2017) J Electron Imaging 26:26.  https://doi.org/10.1117/1.JEI.26.1.013007 CrossRefGoogle Scholar
  7. 7.
    Chang X, Ma Z, Lin M, Yang Y, Hauptmann AG (2017) IEEE Trans Image Process 26(8):3911MathSciNetCrossRefGoogle Scholar
  8. 8.
    Chang X, Yu YL, Yang Y, Xing EP (2017) IEEE Trans Pattern Anal Mach Intell 39(8):1617CrossRefGoogle Scholar
  9. 9.
    Chen D, Yuan Z, Wu Y, Zhang G, Zheng N To appear in ICCV2013Google Scholar
  10. 10.
    Danelljan M, Bhat G, Khan FS, Felsberg M (2017). In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 6931–6939Google Scholar
  11. 11.
    Dinh TB, Vo N, Medioni G (2011) In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 1177–1184, DOI  https://doi.org/10.1109/CVPR.2011.5995733, (to appear in print)
  12. 12.
    Grabner H, Grabner M, Bischof H (2006) In: Proceedings of the British machine vision conference, vol 1, pp 47–56Google Scholar
  13. 13.
    Hare S, Saffari A, Torr PHS (2011) In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 263–270Google Scholar
  14. 14.
    Henriques JF, Caseiro R, Martins P, Batista J (2015) IEEE Trans Pattern Anal Mach Intell 37(3):583CrossRefGoogle Scholar
  15. 15.
    Huang GB, Zhu QY, Siew CK (2006) Neurocomputing 70(1):489CrossRefGoogle Scholar
  16. 16.
    Huang GB, Zhou H, Ding X, Zhang R (2012) IEEE Trans Syst Man Cybern B Cybern 42(2):513CrossRefGoogle Scholar
  17. 17.
    Jia X, Lu H, Yang MH (2012) In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 1822–1829Google Scholar
  18. 18.
    Kalal Z, Mikolajczyk K, Matas J (2012) IEEE Trans Pattern Anal Mach Intell 34(7):1409CrossRefGoogle Scholar
  19. 19.
    Kwon J, Lee KM (2010) In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 1269–1276, DOI  https://doi.org/10.1109/CVPR.2010.5539821, (to appear in print)
  20. 20.
    Kwon J, Lee KM (2011) In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 1195–1202Google Scholar
  21. 21.
    Li H, Shen C, Shi Q (2011) In: Proceedings of the IEEE conference computer vision and pattern recognition (CVPR).  https://doi.org/10.1109/CVPR.2011.5995483, pp 1305–1312
  22. 22.
    Li X, Dick A, Shen C, van den Hengel A, Wang H IEEE Transactions on Pattern Analysis & Machine Intelligence (to be published). Early AccessGoogle Scholar
  23. 23.
    Liu R, Cheng J, Lu H (2009) In: 2009 IEEE 12th international conference on computer vision, IEEE, pp 1459–1466Google Scholar
  24. 24.
    Liu B, Huang J, Kulikowski C, Yang L (2013) IEEE Trans Pattern Anal Mach Intell 35(12):2968CrossRefGoogle Scholar
  25. 25.
    Lu H, Zhou Q, Wang D, Xiang R (2011) In: 2011 IEEE international conference on automatic face & gesture recognition and workshops (FG 2011), IEEE, pp 539–544Google Scholar
  26. 26.
    Luka C, Matej K, Ales L Technical report 10-2013Google Scholar
  27. 27.
    Mei X, Ling H (2009) In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 1436 –1443.  https://doi.org/10.1109/ICCV.2009.5459292
  28. 28.
    Mei X, Ling H (2011) IEEE Trans Pattern Anal Mach Intell 33(11):2259.  https://doi.org/10.1109/TPAMI.2011.66 CrossRefGoogle Scholar
  29. 29.
    Mueller M, Smith N, Ghanem B (2017) In: Proceedings of the IEEE conference on computer vision pattern recognition (CVPR), pp 1396–1404Google Scholar
  30. 30.
    Nam H, Han B (2016) In: The IEEE conference on computer vision and pattern recognition (CVPR), pp 4293–4302Google Scholar
  31. 31.
    Peng X, Schmid C (2016) In: European conference on computer vision (Springer), pp 744–759Google Scholar
  32. 32.
    Ross D, Lim J, Lin R, Yang M (2008) Int J Comput Vis 77(1):125CrossRefGoogle Scholar
  33. 33.
    Saffari A, Leistner C, Santner J, Godec M, Bischof H (2009) In: 2009 IEEE 12th international conference on computer vision workshops (ICCV workshops), IEEE, pp 1393–1400Google Scholar
  34. 34.
    Santner J, Leistner C, Saffari A, Pock T, Bischof H (2010) In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).  https://doi.org/10.1109/CVPR.2010.5540145  https://doi.org/10.1109/CVPR.2010.5540145, pp 723–730
  35. 35.
    Sun L, Liu G (2011) IEEE Trans Circuits Syst Video Technol 21(4):408.  https://doi.org/10.1109/TCSVT.2010.2087815 CrossRefGoogle Scholar
  36. 36.
    Tang F, Brennan S, Zhao Q, Tao H (2007) In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 1–8.  https://doi.org/10.1109/ICCV.2007.4408954
  37. 37.
    Wang Y, Luo X, Ding L, Hu S (2018) Multimed Tools Appl 77(23):31447.  https://doi.org/10.1007/s11042-018-6198-8 CrossRefGoogle Scholar
  38. 38.
    Wu Y, Lim J, Yang M (2013) In: IEEE conference on computer vision and pattern recognition (CVPR), IEEE, pp 2411–2418Google Scholar
  39. 39.
    Yang H, Shao L, Zheng F, Wang L, Song Z (2011) Neurocomputing 74(18):3823CrossRefGoogle Scholar
  40. 40.
    Yang J, Zhang S, Zhang L (2016) J Electron Imaging 25(5):053006CrossRefGoogle Scholar
  41. 41.
    Yang H, Zhong D, Liu C, Song K, Yin Z (2018) J Electron Imaging 27:27.  https://doi.org/10.1117/1.JEI.27.2.023008 CrossRefGoogle Scholar
  42. 42.
    Yao R, Shi Q, Shen C, Zhang Y, van den Hengel A (2013) In: IEEE conference on computer vision and pattern recognition (CVPR)Google Scholar
  43. 43.
    Yilmaz A, Javed O, Shah M (2006) Acm Computing Surveys (CSUR) 38 (4):13CrossRefGoogle Scholar
  44. 44.
    Yu Q, Dinh T, Medioni G (2008) Comput Vis–ECCV 2008:678–691Google Scholar
  45. 45.
    Yun S, Choi J, Yoo Y, Yun K, Choi JY (2017) In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 1349–1358Google Scholar
  46. 46.
    Zhang L, van der Maaten L (2013) In: 2013 IEEE conference on computer vision and pattern recognition (CVPR), IEEE, pp 1838–1845Google Scholar
  47. 47.
    Zhang T, Ghanem B, Liu S, Ahuja N (2012) In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 2042–2049Google Scholar
  48. 48.
    Zhang G, Liu J, Li H, Chen YQ, Davis LS (2017) IEEE Signal Process Lett 24(11):1666CrossRefGoogle Scholar
  49. 49.
    Zhang S, Lu W, Xing W, Zhang L (2018) IEEE transactions on cybernetics. Early acccess 1:14.  https://doi.org/10.1109/TCYB.2018.2868782
  50. 50.
    Zhang S, Lu W, Xing W, Zhang L (2018) Pattern Recogn 84:112CrossRefGoogle Scholar
  51. 51.
    Zhang S, Sui Y, Yu X, Zhao S, Zhang L (2015) Pattern Recogn 48 (8):2474CrossRefGoogle Scholar
  52. 52.
    Zhang S, Zhao S, Sui Y, Zhang L (2015) IEEE Trans Image Process 24(12):5723MathSciNetCrossRefGoogle Scholar
  53. 53.
    Zhao J, Zhang W, Cao F (2018) Multimed Tools Appl 77(23):30969.  https://doi.org/10.1007/s11042-018-6132-0 CrossRefGoogle Scholar
  54. 54.
    Zhong W, Lu H, Yang MH (2012) In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 1838–1845Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Key Laboratory of Airborne Optical Imaging and MeasurementChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of SciencesChangchunChina
  2. 2.Beijing Topmoo Technologies Co., LtdResearch and Development PlazaBeijingChina

Personalised recommendations