Sparsity-Constrained and Dynamic Group Structured Sparse Coding for Robust Visual Tracking
YUAN Guang-lin1, XUE Mo-gen2
1. Eleventh Department, Army Officer Academy of PLA, Hefei, Anhui 230031, China;
2. Department of Scientific Research, Army Officer Academy of PLA, Hefei, Anhui 230031, China
L1 tracker is one of the most effective methods in dealing with the occlusions for sparseness of coding coefficients of objects.However, the existing sparse coding algorithms do not use special sparse structure of coding coefficients in L1 tracker.In this paper, we propose a two-stage sparse coding algorithm for visual tracking based on constrained sparsity of target template coefficients and spatial continuity structure of trivial template coefficients with block coordinate optimization theory.At the first stage, the algorithm solves sparsity-constrained coding coefficients on target template set using orthogonal matching pursuit.At the second stage, the algorithm finds sparse coding coefficients with spatial continuity on trivial template set via dynamic group sparse coding.Robust visual tracking is achieved using the proposed sparse coding algorithm in particle filter framework.The experimental results demonstrate that the proposed tracking method has better robustness and higher precision than the state-of-the-art trackers.
[1] Ross D,Lim J,Lin R S,et al.Incremental learning for robust visual tracking[J].International Journal of Computer Vision,2008,77(1-3):125-141.
[2] Kwon J,Lee K M.Visual tracking decomposition[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C].San Francisc:IEEE Computer Society Press,2010.1269-1276.
[3] Babenko B,Yang M H,Belongie S.Robust object tracking with online multiple instance learning[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(8):1619-1632.
[4] D Donoho.Compressed sensing[J].IEEE Transactions Information Theory,2006,52(4):1289-1306.
[5] Wright J,Yang A Y,Ganesh A,et al.Robust face recognition via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):210-227.
[6] Xue Mei,Haibin Ling.Robust visual tracking using L1 minimization[A].Proceedings of IEEE Conference on Computer Vision[C].Kyoto :IEEE Computer Society Press,2009.1436-1443.
[7] Baiyang Liu,Lin Yang,Junzhou Huang,et al.Robust and fast collaborative tracking with two stage sparse optimization[A].Proceedings of Conference on European Conference on Computer Vision[C].Crete :Springer,2010.Part IV:624-637.
[8] Mei X,Ling H B,Wu Y,et al.Minimum error bounded efficient L1 tracker with occlusion detection[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C].Colorado:IEEE Computer Society Press,2011.1257-1264.
[9] Chenglong Bao,Yi Wu,Haibin Ling,et al.Real time robust L1 tracker using accelerated proximal gradient approach[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C].Rhode Island:IEEE Computer Society Press,2012.1830-1837.
[10] Tianzhu Zhang,Bernard Ghanem,Si Liu,et al.Robust visual tracking via multi-task sparse learning[J].International Journal of Computer Vision,2013,101(2):367-383.
[11] Xu Jia,Huchuan Lu,Ming-Hsuan Yang.Visual tracking via adaptive structural local sparse appearance model[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C].Rhode Island:IEEE Computer Society Press,2012.1822-1929.
[12] 姜明新,王洪玉,王洁,等.基于 ML和L2范数的视频目标跟踪算法[J].电子学报,2013,41(11):2307-2313. Jiang Ming-xin,Wang Hong-yu,Wang Jie,et al.Visual object tracking algorithm based on ML and L2 norm[J].Acta Electronica Sinica,2013,41(11):2307-2313.(in Chinese)
[13] Dong Wang,Huchuan Lu,Ming-Hsuan Yang.Least soft-thresold squares tracking[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C].Portland:IEEE Computer Society Press,2013.2371-2378.
[14] Zihan Zhou,Andrew Wagner,Hossein Mobahi,et al.Face recognition with contiguous occlusion using Markov random fields[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C].Kyoto:IEEE Computer Society Press,2009.1050-1057.
[15] Joel A Tropp,Anna C Gilbert.Signal recovery from random measurements via orthogonal matching pursuit[J].IEEE Transactions on information theory,2007,53(12):4655-4666.
[16] Junzhou Huang,Xiaolei Huang,Dimitris Metaxas.Learning with dynamic group sparsity[A].Proceedings of IEEE Conference on Computer Vision[C].Kyoto:IEEE Computer Society Press,2009.64-71.
[17] Paul Tseng,Sangwoon Yun.A block-coordinate gradient descent method for linearly constrained nonsmooth separable optimization[J].Optimization Theory Application,2009,140:513-535.
[18] Yi Wu,Jongwoo Lim,Ming-Hsuan Yang.Online object tracking:a benchmark[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C].Portland:IEEE Computer Society Press,2013.2411-2418.
2015, Vol. 43 
