Abstract
Discriminative dictionary learning (DDL) provides an appealing paradigm for appearance modeling in visual tracking due to its superior discrimination power. However, most existing DDL based trackers usually cannot handle the drastic appearance changes, especially for scenarios with background cluster and/or similar object interference. One reason is that they often encounter loss of subtle visual information that is critical to distinguish the object from the distracters. In this paper, we propose a robust tracker via jointly learning a multi-class discriminative dictionary. Our DDL method exploits concurrently the intra-class visual information and inter-class visual correlations to learn the shared dictionary and the class-specific dictionaries. By imposing several discrimination constraints into the objective function, the learnt dictionary is reconstructive, compressive and discriminative, thus can achieve better discriminate the object from the background. Tracking is carried out within a Bayesian inference framework where the joint decision measure is used to construct the observation model. Evaluations on the benchmark dataset demonstrate that the proposed algorithm achieves substantially better overall performance against the state-of-the-art trackers.
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
Similar content being viewed by others
Notes
- 1.
The cardinality \(\varTheta (\mathbf {X}_{P})\) denotes the number of samples in the sample pool.
References
Arora, S., Ge, R., Moitra, A.: New algorithms for learning incoherent and overcomplete dictionaries. arXiv preprint arXiv:1308.6273 (2013)
Bai, Q., Wu, Z., Sclaroff, S., Betke, M., Monnier, C.: Randomized ensemble tracking. In: ICCV, pp. 2040–2047 (2013)
Bao, C., Wu, Y., Ling, H., Ji, H.: Real time robust l1 tracker using accelerated proximal gradient approach. In: CVPR, pp. 1830–1837. IEEE (2012)
Barchiesi, D., Plumbley, M.D.: Learning incoherent dictionaries for sparse approximation using iterative projections and rotations. TSP 61(8), 2055–2065 (2013)
Candes, E., Romberg, J.: Sparsity and incoherence in compressive sampling. Inverse Probl. 23(3), 969 (2007)
Danelljan, M., Shahbaz Khan, F., Felsberg, M., Van de Weijer, J.: Adaptive color attributes for real-time visual tracking. In: CVPR. IEEE (2014)
Hare, S., Saffari, A., Torr, P.H.: Struck: Structured output tracking with kernels. In: ICCV, pp. 263–270 (2011)
He, Y., Pei, M., Yang, M., Wu, Y., Jia, Y.: Online visual tracking by integrating spatio-temporal cues. IET Comput. Vis. 9(1), 124–137 (2015)
Jia, X., Lu, H., Yang, M.: Visual tracking via adaptive structural local sparse appearance model. In: CVPR, pp. 1822–1829 (2012)
Jiang, Z., Lin, Z., Davis, L.S.: Label consistent K-SVD: learning a discriminative dictionary for recognition. TPAMI 35(11), 2651–2664 (2013)
Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. TPAMI 34(7), 1409–1422 (2012)
Kwon, J., Lee, K.: Visual tracking decomposition. In: CVPR, pp. 1269–1276 (2010)
Liu, B., Huang, J., Yang, L., Kulikowsk, C.: Robust tracking using local sparse appearance model and k-selection. In: CVPR, pp. 1313–1320 (2011)
Ma, C., Huang, J.B., Yang, X., Yang, M.H.: Hierarchical convolutional features for visual tracking. In: ICCV, pp. 3074–3082 (2015)
Mei, X., Ling, H.: Robust visual tracking using \(\ell 1\) minimization. In: ICCV, pp. 1–8 (2009)
Mei, X., Ling, H., Wu, Y., Blasch, E., Bai, L.: Minimum error bounded efficient \(\ell 1\) tracker with occlusion detection. In: CVPR, pp. 1257–1264. IEEE (2011)
Ross, D., Lim, J., Lin, R., Yang, M.: Incremental learning for robust visual tracking. IJCV 77(1), 125–141 (2008)
Wang, D., Lu, H., Yang, M.H.: Least soft-threshold squares tracking. In: CVPR, pp. 2371–2378 (2013)
Wang, L., Ouyang, W., Wang, X., Lu, H.: Visual tracking with fully convolutional networks. In: ICCV, pp. 3119–3127 (2015)
Wang, N., Wang, J., Yeung, D.Y.: Online robust non-negative dictionary learning for visual tracking. In: ICCV, pp. 657–664. IEEE (2013)
Wang, Q., Chen, F., Xu, W., Yang, M.: Online discriminative object tracking with local sparse representation. In: WACV, pp. 425–432 (2012)
Wang, Q., Chen, F., Xu, W., Yang, M.H.: Object tracking with joint optimization of representation and classification. IEEE Trans. Circ. Syst. Video Technol. 25(4), 638–650 (2015)
Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: CVPR, pp. 2411–2418. IEEE (2013)
Wu, Y., Ma, B., Yang, M., Jia, Y., Zhang, J.: Metric learning based structural appearance model for robust visual tracking. TCSVT 24(5), 865–877 (2014)
Wu, Y., Pei, M., Yang, M., Yuan, J., Jia, Y.: Robust discriminative tracking via landmark-based label propagation. TIP 24(5), 1510–1523 (2015)
Yang, F., Jiang, Z., Davis, L.S.: Online discriminative dictionary learning for visual tracking. In: WACV (2014)
Yang, M., Pei, M., Wu, Y., Jia, Y.: Learning online structural appearance model for robust object tracking. Sci. Chin. Inf. Sci. 58(3), 1–14 (2015)
Yao, R., Shi, Q., Shen, C., Zhang, Y., van den Hengel, A.: Part-based visual tracking with online latent structural learning. In: CVPR, pp. 2363–2370 (2013)
Zhang, K., Zhang, L., Yang, M.-H.: Real-time compressive tracking. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 864–877. Springer, Heidelberg (2012). doi:10.1007/978-3-642-33712-3_62
Zhang, L., Lu, H., Du, D., Liu, L.: Sparse hashing tracking. TIP 25(2), 840–849 (2016)
Zhong, W., Lu, H., Yang, M.: Robust object tracking via sparsity-based collaborative model. TIP 23(5), 2356–2368 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Liu, Z., Pei, M., Zhang, C., Zhu, M. (2016). Jointly Learning a Multi-class Discriminative Dictionary for Robust Visual Tracking. In: Chen, E., Gong, Y., Tie, Y. (eds) Advances in Multimedia Information Processing - PCM 2016. PCM 2016. Lecture Notes in Computer Science(), vol 9917. Springer, Cham. https://doi.org/10.1007/978-3-319-48896-7_54
Download citation
DOI: https://doi.org/10.1007/978-3-319-48896-7_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-48895-0
Online ISBN: 978-3-319-48896-7
eBook Packages: Computer ScienceComputer Science (R0)