Algorithm of object-tracking based on collaborative representation

doi:10.7523/j.issn.2095-6134.2016.01.020

Abstract

Abstract:

A new algorithm of object-tracking based on collaborative representation is proposed. Within Bayes framework,the robust tracker is presented using the observation likelihood model based on the error reconstruction and the updating scheme accounting for occlusion. The error reconstruction is modelled by the l₁ norm to tolerate the outlier, and the code coefficients are regularized by collaborative representation. Experimental results show that the proposed algorithm solves the problems of occlusion, scale changing, varying illumination, and cluttered background with high accuracy and robustness.

Key words: object tracking, collaborative representation, l₁ norm, observation likelihood function

CLC Number:

TP391

WANG Haijun, ZHANG Shengyan. Algorithm of object-tracking based on collaborative representation[J]. , 2016, 33(1): 135-143.

References

[1] Wang D, Lu H C. On-line learning parts-based representation via incremental orthogonal projective non-negative matrix factorization[J]. Signal Processing, 2013,93: 1 608-1 623.
[2] Wang D, Lu H C. Incremental orthogonal projective non-negative matrix factorization and its applications [C]// IEEE International Conference on Image Processing. Brussels, Belgium. 2011: 2 117-2 120.
[3] Zhang K, Zhang L, Yang M. Fast compressive tracking[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2014, 36(10): 2 002-2 015.
[4] Wright J, Yang A Y, Ganesh A. Robust representation for face recognition via sparse representation[J]. IEEE Trans Pattern and Machine Intell, 2009,31(2):210-227.
[5] Mei X, Ling H B. Robust visual tracking using L1 minimization [C]// IEEE international Conference on Computer Vision. Kyoto, Japan. 2009: 1 436-1 443.
[6] Bao C, Wu Y, Ling H, et al. Real time robust L1 tracker using accelerated proximal gradient approach [C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Providenc, RI, USA. 2012:1 830-1 837.
[7] Zhong W, Lu H C, Yang M H. Robust object tracking via sparse collaborative appearance model[J]. IEEE Transaction on Image Processing, 2014, 23(5): 2 356-2 368.
[8] Jia X, Lu H C, Yang M H. Visual tracking via adaptive structural local sparse appearance model [C]// International Conference on Computer Visioan and Pattern Recognition, Providenc, Ri, USA. 2012:1 822-1 829.
[9] Wang D, Lu H C, Yang M H. Least Soft-threshold Squares Tracking [C]// International Conference on Computer Vision and Pattern Recognition. Portland, Orego, 2013:2 371-2 378.
[10] Zhang L, Yang M, Feng X, et al. Collaborative representation based classification for face recognition [R]. arXiv: 1204.2358.
[11] Ross D, Lim J, Lin R S, et al. Incremental learning for robust visual tracking[J]. International Journal of Computer Vision, 2008,77(3):125-141.
[12] Kalal J, Matas J, Mikolajczyk K. P-N learning:bootstrapping binary classifiers by structural constraints [C]//IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, California, 2010:49-56.
[13] Kwon J, Lee K M. Visual tracking decomposition [C]// IEEE Conference on Computer Vision and Pattern Recognition. Francisco, California, 2010:1 269-1 276.
[14] Babenko B, Yang M H, Belongle S. Visual tracking with online multiple instance learning [C]//IEEE Conference on Computer Vision and Pattern Recognition. Florida, 2009: 983-990.
[15] Adam A, Riviin E, Shimshoni I. Robust fragments-based tracking using the integral histogram [C]// IEEE Conference on Computer Vision and Pattern Recognition. New York. 2006: 798-805.