Robust Multiple Instance Learning Fast Compressive Tracking

Li Hong Wang, Rui Min Wu, Jin Lin Gao

Abstract


Fast compressive tracking algorithm performs more effective and robust than some other state-of-art tracking algorithm, it crop samples from the current frame, all these samples have the same weighted in learning procedure, in order to integrates the sample importance into the learning procedure, motived by the weighted multiple instance learning algorithm, we present a novel enhanced fast compressive tracking, which integrates the samples importance into learning procedure. Experimental results on various benchmark video sequences demonstrate the superior performance of our algorithm.

Keywords


Object tracking; Fast compressive tracking; Multiple instance learning

Full Text:

PDF

References


S. Avidan, Ensemble Tracking, IEEE Trans. on Pattern Analysis 29 (2) (2008), 261–271.

B. Babenko, M.-H. Yang and S. Belongie, Robust object tracking with online multipleinstance learning, IEEE Trans. on Pattern Analysis 33 (2011), 1619–1632.

E.J. Candes and T. Tao, Decoding by linear programming, IEEE Transactions on Information Theory 51 (12) (2015), 4203–4215.

P. Diaconis and D. Freedman, Asymptotics of graphical projection pursuit, Ann. Stat. 12 (1984), 228–235.

D. Donoho, Compressed sensing, IEEE Trans. Information Teory 52 (4) (2006), 1289–1306.

M. Everingham, L. Gool, C. Williams, J. Winn and A. Zisserman, The pascal visual object class (voc)challenge, International Journal of Computer Vision 88 (2) (2010), 303–338.

H. Grabner, M. Grabner and H. Bischof, Real-time tracking via online boosting, The British Machine Vision Conference (2006), 47–56.

H. Grabner, C. Leistner and H. Bischof, Semi-supervised onlineboosting for robust tracking, The European Conference on Computer Vision (2008), 1–10.

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

X. Mei and H. Ling, Robust visual tracking and vehicle classification via sparse representation, IEEE Trans. on Pattern Analysis 33 (2011), 2259–2272.

D. Ross, J. Lim, R. Lin and M.-H. Yang, Incremental learning for robust visualtracking, International Journal of Computer Vision 77 (2008), 125–141.

P. Viola, J. Platt and C. Zhang, Multiple InstanceBoosting for Object Detection, Advances in Neural Information Processing Systems 18 (2006), 1417–1424.

P. Viola and M. Jones, Rapid object detection using a boosted cascade ofsimple features, IEEE Conference on Computer Vision and Pattern Recognition (2001), 1–9.

Y. Wu, J.W. Lim and M.-H. Yang, Online object tracking: a benchmark, Computer Vision and Pattern Recognition (2013), 2411–2418.

A. Yilmaz, O. Javed and M. Shah, Objecttracking: a survey, ACM Computing Surveys 38 (2006), 1–45.

K. Zhang and H. Song, Real timevisual tracking via online weightedmultiple instance learning, Pattern Recognition 46 (2013), 397–411.

K. Zhang, L. Zhang and M. Yang, Real time compressive tracking, The European Conference on Computer Vision (2012), 866–879.

K. Zhang, L. Zhang and M. Yang, Fast compressive tracking, IEEE Transactions on Pattern Analysis and Machine Intelligence 36 (2014), 2002–2015.




DOI: http://dx.doi.org/10.26713%2Fjims.v8i3.485

eISSN 0975-5748; pISSN 0974-875X