Abstract
Visual tracking plays a fundamental role in video surveillance, robot vision and many other computer vision applications. In this paper, a robust visual tracking method that is motivated by the regularized \(\ell\)1 tracker is proposed. We focus on investigating the case that the object target is occluded. Generally, occlusion can be treated as some kind of contiguous outlier with the target object as background. However, the penalty function of the \(\ell\)1 tracker is not robust for relatively dense error distributed in the contiguous regions. Thus, we exploit a nonconvex penalty function and MRFs for outlier modeling, which is more probable to detect the contiguous occluded regions and recover the target appearance. For long-term tracking, a particle filter framework along with a dynamic model update mechanism is developed. Both qualitative and quantitative evaluations demonstrate a robust and precise performance.
Similar content being viewed by others
References
Grabner, H., Grabner, M., Bischof, H.: Real-time tracking via on-line boosting. In: BMVC, p. 6 (2006)
Ross, D.A., Lim, J., Lin, R.-S., Yang, M.-H.: Incremental learning for robust visual tracking. Int. J. Comput. Vis. 77, 125–141 (2008)
Babenko, B., Yang, M.-H., Belongie, S.: Robust object tracking with online multiple instance learning. Pattern Anal. Mach. Intell. IEEE Trans. 33, 1619–1632 (2011)
Hare, S., Saffari, A., Torr, P.H.: Struck: Structured output tracking with kernels. In: Computer vision (ICCV), 2011 IEEE international conference on IEEE, pp. 263–270 (2011)
Mei, X., Ling, H.: Robust visual tracking and vehicle classification via sparse representation. Pattern Anal. Mach. Intell. IEEE Trans. 33, 2259–2272 (2011)
Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. Pattern Anal. Mach. Intell. IEEE Trans. 34, 1409–1422 (2012)
Wu, Y., Lim, J., Yang, M.-H.: Online object tracking: a benchmark. In: Computer vision and pattern recognition (CVPR), 2013 IEEE conference on IEEE, pp. 2411–2418 (2013)
Chandrasekaran, V., Sanghavi, S., Parrilo, P.A., Willsky, A.S.: Sparse and low-rank matrix decompositions. In: Communication, control, and computing, 2009. Allerton 2009. 47th Annual Allerton conference on IEEE, pp. 962–967 (2009)
Candes, E.J., Tao, T.: Near optimal signal recovery from random projections: universal encoding strategies? Inf. Theory IEEE Trans. 52, 5406–5425 (2004)
Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: Robust face recognition via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell. 31, 210–227 (2009)
Zhou, X., Yang, C., Yu, W.: Moving object detection by detecting contiguous outliers in the low-rank representation. Pattern Anal. Mach. Intell. IEEE Trans. 35, 597–610 (2013)
Li, H., Shen, C., Shi, Q.: Real-time visual tracking using compressive sensing. In: Computer vision and pattern recognition (CVPR), 2011 IEEE conference, pp. 1305–1312 (2011)
Mei, X., Ling, H., Wu, Y., Blasch, E., Bai, L.: Minimum error bounded efficient ℓ1 tracker with occlusion detection. In: Computer vision and pattern recognition (CVPR), 2011 IEEE Conference (2011)
Bao, C., Wu, Y., Ling, H., Ji, H.: Real time robust ℓ1 tracker using accelerated proximal gradient approach. In: Proceedings/CVPR, IEEE computer society conference on computer vision and pattern recognition, pp. 1830–1837 (2012)
Kim, S.-J., Koh, K., Lustig, M., Boyd, S., Gorinevsky, D.: An interior-point method for large-scale ℓ1-regularized least squares. Sel. Topics Signal Process. IEEE J. 1, 606–617 (2007)
Goldstein, T., Osher, S.: The split bregman method for ℓ1-regularized problems. Siam J. Imaging Sci. 2, 323–343 (2009)
Zhang, T., Liu, S., Ahuja, N., Yang, M.H., Ghanem, B.: Robust visual tracking via consistent low-rank sparse learning. Int. J. Comput. Vis. 111, 171–190 (2014)
Li, S.Z.: Markov random field modeling in image analysis. Markov random field modeling in image analysis: advances in pattern recognition. ISBN 978-1-84800-279-1. Springer-Verlag, London, pp. xxiv + 357 (2009)
Tseng, P., Tseng, P.: On accelerated proximal gradient methods for convex-concave optimization. Siam J. Optim. (2008)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. In: Computer vision. The Proceedings of the Seventh IEEE International Conference, vol. 371, pp. 377–384 (1999)
Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts. In: IEEE transactions on pattern analysis and machine intelligence, pp. 65–81 (2004)
Wang, D., Lu, H.: Visual tracking via probability continuous outlier model. In: Computer vision and pattern recognition (CVPR), 2014 IEEE conference on IEEE, pp. 3478–3485 (2014)
Kong, X., Chen, Q., Xu, F., Gu, G., Ren, K., Qian, W.: Motion object tracking based on the low-rank matrix representation. Opt. Rev. 22, 786–801 (2015)
Model, I.: Sequential monte carlo methods in practice. Factored Dyn. Syst. 93, 209–250 (2001)
Hartley, R., Zisserman, A.: Multiple view geometry in computer vision, Cambridge University Press (2003)
Lu, H.: Huchuan Lu’s Homepage. http://ice.dlut.edu.cn/lu/index.html
Visual Tracker Benchmark. http://cvlab.hanyang.ac.kr/tracker_benchmark/
Acknowledgments
This research is supported by Jiangsu Province High-level Talents in Six Industries (2012-DZXX-037), Program for New Century Excellent Talents in University (NCET-12-0630), and the Natural Science Foundation of Jiangsu Province of China (BK20130769).
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
The APG algorithm is originally designed for solving the following unconstrained program
where F(x) is a differentiable convex function with Lipschitz continuous gradient and G(x) is a non-smooth but convex function. Equation (7) is a nonlinear problem with nonnegativity constraint, which can be reformulated as
where the additional term \({\mathbf{1}}_{{{\mathbb{R}} + }} ({\mathbf{a}})\) is defined as
Then, Eq. (7) can be decomposed as
The gradient of F(a) is Lipschitz continuous because for any \({\mathbf{x}}_{1} ,{\mathbf{x}}_{2} \in {\mathbb{R}}^{\text{n}}\),
where the matrix \({\mathbf{A}} = \mathcal{P}_{{{\hat{\mathbf{S}}}^{ \bot } }} ({\mathbf{T}})\) and \({\mathbf{b}} = \mathcal{P}_{{{\hat{\mathbf{S}}}^{ \bot } }} ({\mathbf{y}})\). Thus, \(L = \left\| \mathcal{P}_{\hat{{\mathbf{S}}}^{\bot}} ({\mathbf{T}})^{\text{T}} \mathcal{P}_{\hat{{\mathbf{S}}}^{\bot}} ({\mathbf{T}}) \right\|_{2}\).
In the generic APG algorithm, we need to solve the following optimization
For the G(a) defined in Eq. (19), the function is equivalent to
The optimization is a truncated quadratic problem and has a closed-form solution
Rights and permissions
About this article
Cite this article
Wang, P., Qian, W. & Chen, Q. Robust visual tracking with contiguous occlusion constraint. Opt Rev 23, 40–52 (2016). https://doi.org/10.1007/s10043-015-0152-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10043-015-0152-z