Visual tracking using discriminative representation with ℓ₂ regularization

Abstract

In this paper, we propose a novel visual tracking method using a discriminative representation under a Bayesian framework. First, we exploit the histogram of gradient (HOG) to generate the texture features of the target templates and candidates. Second, we introduce a novel discriminative representation and ℓ₂-regularized least squares method to solve the proposed representation model. The proposed model has a closed-form solution and very high computational efficiency. Third, a novel likelihood function and an update scheme considering the occlusion factor are adopted to improve the tracking performance of our proposed method. Both qualitative and quantitative evaluations on 15 challenging video sequences demonstrate that our method can achieve more robust tracking results in terms of the overlap rate and center location error.

Keywords

visual tracking / discriminative representation / Bayesian framework / closed-form solution

References

[1] Li A, Lin M, Wu Y, Yang M H, Yan S C. NUS-PRO: a new visual tracking challenge. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 335–349

[2] Wu Y, Lim J, Yang M H. Object tracking benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1834–1848

[3] Zhang K H, Zhang L, Yang M H. Fast compressive tracking. IEEE Transations on Pattern Analysis and Machine Intelligence, 2014, 36(10): 2002–2015

[4] Li X, Shen C H, Dick A, Hengel A. Learning compact binary codes for visual tracking. In: Proceedings of the 26th IEEE Conference on Computer Vision and Pattern Recognition. 2013, 2419–2426

[5] Zhang K H, Zhang L, Yang M H, Hu Q H. Robust object tracking via active feature selection. IEEE Transactions Circuits and Systems for Video Technology, 2013, 23(11): 1957–1967

[6] Song H H. Robust visual tracking via online informative feature selection. Electronics Letters, 2014, 50(25): 1931–1933.

[7] Babenko B, Yang M H, Belongie S. Visual tracking with online multiple instance learning. In: Proceedings of the 22nd IEEE Conference on Computer Vision and Pattern Recognition. 2009, 983–990

[8] Zhang K H, Liu Q S, Wu Y, Yang M H. Robust visual tracking via convolutional networks without training. IEEE Transations on Image Processing, 2016, 25(4): 1779–1792

[9] Yan J, Chen X, Deng D X, Zhu Q P. Visual object tracking via online sparse instance learning. Journal of Visual Communication and Image Representation, 2015, 26: 231–246

[10] Zhang K H, Zhang L, Yang M H. Real-time object tracking via online discriminative feature selection. IEEE Transactions on Image Processing, 2013, 22(12): 4664–4677

[11] Song H H, Zheng Y H, Zhang K H. Robust visual tracking via selfsimilarity learning. Electronics Letters, 2017, 53(1): 20–22

[12] Yang X, Wang M, Zhang L M, Sun F M, Hong R C, Qi M B. An efficient tracking system by orthogonalized templates. IEEE Transactions on Industrial Electronics, 2016, 63(5): 3187–3197

[13] Wang D, Lu H C, Xiao Z Y, Yang M H. Inverse sparse tracker with a locally weighted distance metric. IEEE Transactions on Image Processing, 2015, 24(9): 2646–2657

[14] Wang D, Lu H C. Online visual tracking via two view sparse representation. IEEE Signal Processing Letters, 2014, 21(9): 1031–1034

[15] Han Y H, Yang Y, Yan Y, Ma Z G, Sebe N, Zhou X F. Semisupervised feature selection via spline regression for video semantic recognition. IEEE Transactions on Neural Networks and Learning Systems, 2015, 26(2): 252–264

[16] Han Y H, Wu F, Tian Q, Zhuang Y T. Image annotation by input-output structural grouping sparsity. IEEE Transactions on Image Processing, 2012, 21(6): 3066–3079

[17] Yang J, Chu D L, Zhang L, Xu Y, Yang J Y. Sparse representation classifier steered discriminative projection with applications to face recognition. IEEE Transactions on Neural Networks and Learning Systems, 2013, 24(7): 1023–1035

[18] Wright J, Yang A Y, Ganesh A, Sastry S, Ma Y. Robust face recognition via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210–227

[19] Zhuang B H, Lu H C, Xiao Z Y, Wang D. Visual tracking via discriminative sparse similarity map. IEEE Transactions on Image Processing, 2014, 23(4): 1872–1881

[20] Hu H W, Ma B, Jia Y D. Multi-task L0 gradient minimization for visual tracking. Neurocomputing, 2015, 154(22): 41–49

[21] Yoon J H, Yang M H, Yoon K J. Interacting multiview tracker. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(5): 903–917

[22] Pan J S, Lim J, Su Z X, Yang M H. L0-regularized object representation for visual tracking. In: Proceedings of the British Machine Vision Conference. 2014, 1–12

[23] Ma B, Shen J B, Liu Y B, Hu H W, Shao L, Li X L. Visual tracking using strong classifier and structural local sparse descriptors. IEEE Transactions on Multimedia, 2015, 17(10): 1818–1828

[24] Mei X, Ling H B. Robust visual tracking using l₁ minimization. In: Proceedings of the 12th IEEE International Conference on Computer Vision. 2009, 1436–1443

[25] Bao C L, Wu Y, Ling H B, Ji H. Real time robust l₁ tracker using accelerated proximal gradient approach. In: Proceedings of the 25th IEEE Conference on Computer Vision and Pattern Recognition. 2012, 1830–1837

[26] Jia X, Lu H C, Yang M H. Visual tracking via coarse and fine structural local sparse appearance models. IEEE Transactions on Image Processing, 2016, 25(10): 4555–4564

[27] Zhong W, Lu H C, Yang M H. Robust object tracking via sparse collaborative appearance model. IEEE Transactions on Image Processing, 2014, 23(5): 2356–2368

[28] Wang D, Lu H C, Yang M H. Least soft-threshold squares tracking. In: Proceedings of the 26th IEEE Conference on Computer Vision and Pattern Recognition. 2013, 2371–2378

[29] Wu Y W, Yuan J S, Tan P Y, Jia Y D, Zhang J. Robust distracterresistive tracker via learning a multi-component discriminative dictionary. IEEE Transactions on Image Processing, submitted.

[30] Wang D, Lu H C, Yang M H. Kernel collaborative face recognition. Pattern Recognition, 2015, 48(10): 3025–3237

[31] Zhang L, Yang M H, Feng X C. Sparse representation or collaborative representation: Which helps face recognition? In: Proceedings of the 13th IEEE International Conference on Computer Vision. 2011, 471–478

[32] Cai S J, Zhang L, Zuo W M, Feng X C. A probabilistic collaborative representation based approach for pattern classification. In: Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition. 2016, 2950–2959

[33] Shi S F, Eriksson A, Hengel A, Shen C H. Is face recognition really a compressive sensing problem? In: Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition. 2011, 553–560

[34] Xiao Z Y, Lu H C, Wang D. L2-RLS based object tracking. IEEE Transaction on Circuits and Systems for Video Technology, 2014, 24(8): 1301–1308

[35] Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: Proceedings of the 18th IEEE Conference on Computer Vision and Pattern Recognition. 2005, 886–893

[36] Henriques J, Caseiro R, Martins P, Batista J. Exploiting the circulant structure of tracking-by-detection with kernels. In: Proceedings of the 12th European Conference on Computer Vision. 2012, 702–715

[37] Xu Y, Zhong Z F, Yang J, You J, Zhang D. A new discriminative sparse representation method for robust face recognition via l₂ regularization. IEEE Transactions on Neural Networks and Learning Systems, 2016, PP(99): 1–10

[38] Jia X, Lu H C, Yang M H. Visual tracking via adaptive structural local sparse appearance model. In: Proceedings of the 25th IEEE Conference on Computer Vision and Pattern Recognition. 2012, 1822–1829

[39] Wang D, Lu H C. On-line learning parts-based representation via incremental orthogonal projective non-negative matrix factorization. Signal Processing, 2013, 93(6): 1608–1623

[40] Wang D, Lu H C, Yang M H. Online object tracking with sparse prototypes. IEEE Transactions on Image Processing, 2013, 22(1): 314–325

[41] Wang D, Lu H C. Visual tracking via probability continuous outlier model. In: Proceedings of the 27th IEEE Conference on Computer Vision and Pattern Recognition. 2014, 3478–3485

[42] Adam A, Rivlin E, Shimshoni I. Robust fragments-based tracking using the integral histogram. In: Proceedings of the 19th IEEE Conference on Computer Vision and Pattern Recognition. 2006, 798–805

[43] Kwon J S, Lee K M. Visual tracking decomposition. In: Proceedings of the 23rd IEEE Conference on Computer Vision and Pattern Recognition. 2010, 1269–1276

RIGHTS & PERMISSIONS

2018 Higher Education Press and Springer-Verlag GmbH Germany, part of Springer Nature