Visual tracking based on the sparse representation of the PCA subspace

Abstract

We construct a collaborative model of the sparse representation and the subspace representation. First, we represent the tracking target in the principle component analysis (PCA) subspace, and then we employ an L₁ regularization to restrict the sparsity of the residual term, an L₂ regularization term to restrict the sparsity of the representation coefficients, and an L₂ norm to restrict the distance between the reconstruction and the target. Then we implement the algorithm in the particle filter framework. Furthermore, an iterative method is presented to get the global minimum of the residual and the coefficients. Finally, an alternative template update scheme is adopted to avoid the tracking drift which is caused by the inaccurate update. In the experiment, we test the algorithm on 9 sequences, and compare the results with 5 state-of-art methods. According to the results, we can conclude that our algorithm is more robust than the other methods.

References

[1] Wang D, Yang J, Yang L, Ge H. Journal of Optoelectronics ·Laser. 2016, 27: 1066

[2] Li C, Shi J, Xu L, Wei L. Journal of Optoelectronics ·Laser. 2015, 26: 1381

[3] Yang H, Wu X, He B, Zhu M. Journal of Optoelectronics ·Laser. 2015, 26: 170

[4] Bai T, Li Y. IEEE Trans. on Industrial Electronics. 2014, 10: 538

[5] Ross D A, Lim J, Lin R S, Yang M H. International Journal of Computer Vision. 2008, 77: 125

[6] Turk M A, Pentland A P. J. Cogn. Neurosci.. 2001, 3: 71

[7] Shirazi S, Harandi M, Lovell BC, Sanderson C. Object Tracking via Non-euclidean Geometry: A Grassmann Approach, Proc. IEEE Winter Conf. on Applications of Comput. Vision (WACV). 2014901

[8] Kumar BS, Swamy MNS, Ahmad MO. Weighted Residual Minimization in PCA Subspace for Visual Tracking, IEEE International Symposium on Circuits and Systems. 2016986

[9] Wright J, Yang A, Ganesh A, Sastry S, Ma Y. IEEE Transactions on Pattern Analysis & Machine Intelligence. 2008, 31: 210

[10] Yang J, Wright J, Huang T S, Ma Y. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society. 2010, 19: 2861

[11] Cevher V, Sankaranarayanan A, Duarte M F, Reddy D, Baraniuk R G, Chellappa R. Compressive Sensing for Background Subtraction, European Conference on Computer Vision. 2008155

[12] Mei X, Ling H B, Wu Y, Blasch E, Bai L. Minimum Error Bounded Efficient L1 Tracker with Occlusion Detection. The 24th IEEE Conference on Computer Vision and Pattern Recognition. 20111257

[13] Mei X, Ling H B. Robust Visual Tracking using l1 Minimization. IEEE International Conference on Computer Vision. 20091436

[14] Bao C L, Wu Y, Ling H B, Ji H. Real Time Robust L1 Tracker using Accelerated Proximal Gradient Approach, IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society. 20121830

[15] Zhuang BH, Lu HC, Xiao ZY, Wang D. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society. 2014, 23: 1872

[16] Wang D, Lu HC, Yang MH. Least Soft-threshold Squares Tracking. IEEE Computer Vision and Pattern Recognition. 20132371

[17] Xiao ZY, Lu HC, Wang D. IEEE Transactions on Circuits & Systems for Video Technology. 2014, 24: 1301

[18] Wu Y, Lim J, Yang MH. IEEE Transactions on Pattern Analysis & Machine Intelligence. 2015, 37: 1834

[19] Zhong W, Lu HC, Yang MH. Robust Object Tracking via Sparsity-based Collaborative Model, IEEE Computer Vision and Pattern Recognition. 20121838

[20] Kalal Z, Mikolajczyk K, Matas JR. IEEE Transactions on Pattern Analysis & Machine Intelligence. 2012, 34: 1409

[21] Zhang T, Ghanem B, Liu S. International Journal of Computer Vision. 2013, 101: 367

[22] Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A. International Journal of Computer Vision. 2010, 88: 303