Abstract
The appearance model, which is required to be adaptive to the non-stationary environment, is the essential step in object tracking but normally suffers from imbalance between effectiveness and efficiency. In this paper, a novel method named as sequential binary code selection (SBC) is proposed to learn a set of compact binary codes for image patch representation. Using the sparse projections, the high dimensional feature can be speedily embedded into the compact binary codes with preserving both the label information and geometrical distance. By the sequential learning, the latter learned binary code which corrects the errors made by the previous codes is more discriminative to the present environment. Furthermore, though binary code selection, the most compact and least redundant hash codes from the candidate pool will be selected and kept. Experimental results illustrate the effectiveness of the SBC, as well as the state-of-the-art tracking performance of the proposed approach.
Similar content being viewed by others
Notes
It is worth to point out that the index |Φt− 1| is less than the index t − 1 because the most discriminative binary codes are selected and kept by a step which is introduced in Section 3.2.
References
Achlioptas D (2003) Database-friendly random projections: Johnson-lindenstrauss with binary coins. Journal of Computer and System Sciences (66):671–687
Avidan S (2007) Ensemble tracking. IEEE Trans PAMI 29(2):261–271
Babenko B, Yang MH, Belongie S (2011) Robust object tracking with online multiple instance learning. IEEE Trans PAMI 33(8):1619–1632
Belkin M, Niyogi P (2003) Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput 15:1373–1396
Chen K, Tao W, Han S (2017) Visual object tracking via enhanced structural correlation filter. Inf Sci 394:232–245
Collins RT, Liu Y, Leordeanu M (2005) Online selection of discriminative tracking features. IEEE Trans PAMI 27(10):1631–1643
Gao J, Xing J, Hu W, Maybank S (2013) Discriminant tracking using tensor representation with semi-supervised improvement. In: Proceedings of the ICCV
Gionis A, Indyky P, Motwani R (1999) Similarity search in high dimensions via hashing. In: Proceedings of the International Conference on Very Large Datadases
Grabner H, Bischof H (2006) On-line boosting and vision. In: Proceedings of the CVPR
He J, Radhakrishnan R, Chang SF, Bauer C (2011) Compact hashing with joint optimization of search accuracy and time. In: Proceedings of the CVPR
Henriques JF, Caseiro R, Martins P, Batista J (2012) Exploiting the circulant structure of tracking-by-detection with kernels. In: Proceedings of the ECCV
Heo J P, Lee Y, He J, Chang S F, Yoon SE (2012) Spherical hashing. In: Proceedings of the CVPR
Jin Z, Hu Y, Lin Y, Zhang D, Lin S, Cai D, Xuelong (2013) Complementary projection hashing. In: Proceedings of the ICCV
Johnson WB, Lindenstrauss J (1982) Extensions of lipschitz mappings into a hilbert space. In: Conference in modern analysis and probability
Kulis B, Jain P, Grauman K (2009) Fast similarity search for learned metrics. IEEE Tansactions on TPAMI
Kwon J, Lee KM (2010) Visual tracking decomposition. In: Proceedings of the CVPR
Kwon J, Lee KM (2011) Tracking by sampling trackers. In: Proceedings of the ICCV
Li H, Li Y, Porikli F (2016) Deeptrack: learning discriminative feature representations online for robust visual tracking. IEEE Trans Image Process 25 (4):1834–1848
Li P, Hastie TJ, Church KW (2006) Very sparse random projections. In: Proceedings of the KDD, pp 287–296
Li X, Shen C, Dick A, Van den Hengel A (2013) Learning compact binary codes for visual tracking. In: Proceedings of the CVPR
Lin G, Shen C, Suter D, Van den Hengel A (2013) A general two-step approach to learning-based hashing. In: Proceedings of the ICCV
Liu H, Yan S (2010) Robust graph mode seeking by graph shift. In: Proceedings of the ICML
Luenberger DG, Ye Y (2008) Linear and nonlinear programming, international series in operations research & management science, vol 116. Springer, Berlin. ISBN 978-0-387-74503-9
Mei X, Ling H (2009) Robust visual tracking using l1 minimization. In: Proceedings of the ICCV
Mu Y, Chen X, Liu X, Chua TS, Yan S (2012) Multimedia semantics-aware query-adaptive hashing with bits reconfigurability. Int J Multimed Info Retr 1:59–70
Oron S, Bar-Hillel A, Levi D, Avidan S (2012) Locally orderless tracking. In: Proceedings of the CVPR
Pavan M, Pelillo M (2007) Dominant sets and pairwise clustering. IEEE Trans TPAMI 29(1)
Ross DA, Lim J, Lin RS, Yang MH (2008) Incremental learning for robust visual tracking. IJCV 77(3):125–141
Wang J, Kumar S, Chang SF (2010) Sequential projection learning for hashing with compact codes. In: Proceedings of the ICML
Wang J, Kumar S, Chang SF (2012) Semi-supervised hashing for large scale search. IEEE Tansactions on TPAMI
Weibull JW (1997) Evolutionary game theory. MIT Press, Cambridge
Weiss Y, Torralba A, Fergus R (2008) Spectral hashing. In: Proceedings of the NIPS
Wu Y, Lim J, Yang MH (2013) Online object tracking: a benchmark. In: Proceedings of the CVPR
Yi S, Jiang N, Feng B, Wang X, Liu W (2016) Online similarity learning for visual tracking. Inf Sci 364–365:33–50
Zhang K, Zhang L, Yang MH (2012) Real-time compressive tracking. In: Proceedings of the ECCV
Zhang T, Ghanem B, Liu S, Ahuja N (2012) Robust visual tracking via multi-task sparse learning. In: Proceedings of the CVPR
Zhang T, Ghanem B, Liu S, Xu C, Ahuja N (2016) Robust visual tracking via exclusive context modeling. IEEE Trans Cybernetics 46(1):51–63
Zhong W, Lu H, Yang MH (2012) Robust object tracking via sparsity-based collaborative model. In: Proceedings of the CVPR
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interests
We, the authors of “Sequential Binary Code Selection for Robust Object Tracking”, have no conflict of interest to declare.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Guo, X., Xiao, N. & Zhang, L. Sequential binary code selection for robust object tracking. Multimed Tools Appl 79, 6951–6963 (2020). https://doi.org/10.1007/s11042-019-08258-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-08258-w