Abstract
This paper proposes an object tracking method, where we first predict target dynamics by harmonic means and particle filter in which we exploit kernel machines to derive a new entropy-based observation likelihood distribution. We then employ online Structured SVMs (Structured SVMs) to model object appearance, where we analyze responses of several kernel functions for various feature descriptors and study how such kernels can be optimally combined to formulate a single joint kernel function. We gain efficiency improvements by (1) exploiting particle filter for sampling the search space instead of commonly adopted dense sampling strategies, and (2) introducing a motion-augmented regularization term during inference to constrain the output search space. We objectively demonstrate that our method strongly competes against state-of-the-art structured object tracking methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arulampalam, M.S., Maskell, S., Gordon, N., Clapp, T.: A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Trans. Signal Process. 50, 174–188 (2002)
Bao, C., Wu, Y., Ling, H., Ji, H.: Real time robust \(l_1\) tracker using accelerated proximal gradient approach. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1830–1837 (2012)
Bordes, A., Bottou, L., Gallinari, P., Weston, J.: Solving multiclass support vector machines with LaRank. In: International Conference on Machine Learning, pp. 89–96 (2007)
Cai, Y., Wang, H., Chen, X., Chen, L.: Multilevel framework to handle object occlusions for real-time tracking. IET Image Process. 10(11), 885–892 (2016)
Doucet, A., Godsill, S., Andrieu, C.: On sequential monte carlo sampling methods for Bayesian filtering. Stat. Comput. 10(3), 197–208 (2000)
Gordon, N., Salmond, D., Smith, A.: Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IET Radar Signal Proc. 140(2), 107–113 (1993)
Hare, S., et al.: Struck: structured output tracking with kernels. IEEE Trans. PAMI 38(10), 2096–2109 (2016)
Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: Exploiting the circulant structure of tracking-by-detection with kernels. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 702–715. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33765-9_50
Hu, W., Gao, J., Xing, J., Zhang, C., Maybank, S.: Semi-supervised tensor-based graph embedding learning and its application to visual discriminant tracking. IEEE Trans. Pattern Anal. Mach. Intell. PP(99), 1 (2016)
Jia, X., Lu, H., Yang, M.H.: Visual tracking via adaptive structural local sparse appearance model. In: IEEE Conference on CVPR, pp. 1822–1829 (2012)
Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. IEEE Trans. Pattern Anal. Mach. Intell. 34(7), 1409–1422 (2012)
Kang, B., Zhu, W., Liang, D.: Robust multi-feature visual tracking via multi-task kernel-based sparse learning. IET Image Process. 11(12), 1172–1178 (2017)
Platt, J.: Fast training of support vector machines using sequential minimal optimization. In: Advances in Kernel Methods-Support Vector Learning, vol. 3 (1999)
Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large margin methods for structured and interdependent output variables. J. Mach. Learn. Res. 6, 1453–1484 (2005)
Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2411–2418 (2013)
Zhong, W., Lu, H., Yang, M.H.: Robust object tracking via sparsity-based collaborative model. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1838–1845 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Ratnayake, K., Amer, M.A. (2019). Motion-Augmented Inference and Joint Kernels in Structured Learning for Object Tracking. In: Karray, F., Campilho, A., Yu, A. (eds) Image Analysis and Recognition. ICIAR 2019. Lecture Notes in Computer Science(), vol 11662. Springer, Cham. https://doi.org/10.1007/978-3-030-27202-9_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-27202-9_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-27201-2
Online ISBN: 978-3-030-27202-9
eBook Packages: Computer ScienceComputer Science (R0)