Object tracking with sparse representation and annealed particle filter
详细信息 查看全文
- 作者：Xiangyang Wang (1) (2)
Ying Wang (1) (2)
Wanggen Wan (1) (2)
Jenq-Neng Hwang (2) (3) - 关键词：Visual tracking ; Sparse representation ; Annealed particle filter ; $$\ell _{1}$$ ? ; Minimization
- 刊名：Signal, Image and Video Processing
- 出版年：2014
- 出版时间：September 2014
- 年：2014
- 卷：8
- 期：6
- 页码：1059-1068
- 全文大小：5,984 KB
- 参考文献：1. Arulampalam, S., Maskell, S., Gordon, N., Clapp, T.: A tutorial on particle filters for non-linear/non-Gaussian Bayesian tracking. IEEE Trans. Signal Process. 50(2), 174-88 (2002) CrossRef
2. Comaniciu, D., Member, V.R., Meer, P.: Kernel-based object tracking. IEEE Trans Pattern Anal. Mach. Intell. 25(5), 564-75 (2003) CrossRef
3. Mei, X., Ling, H.: Robust visual tracking using L1 minimization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1436-443 (2009)
4. Ross, D., Lim, J., Lin, R.-S., Yang, M.-H.: Incremental learning for robust visual tracking. Int. J. Comput. Vis. 77(1-), 125-41 (2008) CrossRef
5. Li, G., Liang, D., Huang, Q., Jiang, S., Gao, W.: Object tracking using incremental 2D-LDA learning and Bayes inference. In: Proceedings of IEEE International Conference on Image Processing, pp. 1568-571 (2008)
6. Wang, D., Lu, H., Chen, Y.-W.: Incremental MPCA for color object tracking. In: Proceedings of IEEE International Conference on Pattern Recognition, pp. 1751-754 (2010)
7. Hu, W., Li, X., Zhang, X., Shi, X., Maybank, S.J., Zhang, Z.: Incremental tensor subspace learning and its applications to foreground segmentation and tracking. Int. J. Comput. Vis. 91(3), 303-27 (2011) CrossRef
8. Wang, T., Gu, I.Y.H., Shi, P.: Object tracking using incremental 2DPCA learning and ML estimation. In: Proceedings of IEEE International Conference on Acoustics Speech and Signal Processing, pp. 933-36 (2007)
9. Babenko, B., Yang, M.-H., Belongie, S.: Robust object tracking with online multiple instance learning. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 33(8), 1619-632 (2011) CrossRef
10. Viola, P.A., Platt, J.C., Zhang, C.: Multiple Instance boosting for object detection. In: Advances in Neural Information Processing Systems, pp. 1681-688
11. Kalal, Z., Matas, J., Mikolajczyk, K.: P-N learning: bootstrapping binary classifiers by structural constraints. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 49-6 (2010)
12. Adam, A., Rivlin, E., Shimshoni, I.: Robust fragments-based tracking using the integral histogram. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 798-05 (2006)
13. Mei, X., Ling, H.: Robust visual tracking and vehicle classification via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 33(11), 2259-272 (2011)
14. Mei, X., Ling, H., Wu, Y., Blasch, E., Bai, L.: Minimum error bounded efficient L1 tracker with occlusion detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1257-264 (2011)
15. Mei, X., Ling, H., Blasch, E., Bai, L.: Efficient minimum error bounded particle resampling L1 tracker with occlusion detection. IEEE Trans. Image Process. 22(7), 2661-675 (2013) CrossRef
16. 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(1), 210-27 (2009) CrossRef
17. Deutscher, J., Reid, I.: Articulated body motion capture by stochastic search. Int. J. Comput. Vis. 61(2), 185-05 (2005) CrossRef
18. Raskin, L.M., Rudzsky, M., Rivlin, E.: Dimensionality reduction using a Gaussian process annealed particle filter for tracking and classification of articulated body motions. Comput. Vis. Image Underst. 115(4), 503-19 (2011)
19. Isard, M., Blake, A.: CONDENSATION—conditional density propagation for visual tracking. Int. J. Comput. Vis. 29(1), 5-8 (1998)
20. Arulampalam, S., Maskell, S., Gordon, N., Clapp, T.: A tutorial on particle filters for non-linear/non-Gaussian Bayesian tracking. IEEE Trans. Signal Process. 50(2), 174-88 (2002)
21. Yang, C., Duraiswami, R., Davis, L.S.: Fast multiple object tracking via a hierarchical particle filter. In: International Conference on Computer Vision (ICCV), 212-19 (2005)
22. Wang, X., Wan, W., Zhang, X.: Annealed particle filter based on particle swarm optimization for articulated three-dimensional human motion tracking. Opt. Eng. 49(1), 017204-1-17204-11 (2010) CrossRef
23. MacCormick, J.: Probabilistic Models and Stochastic Algorithms for Visual Tracking. PhD thesis, University of Oxford
24. Kim, S.J., Koh, K., Lustig, M., Boyd, S., Gorinevsky, D.: A method for large-scale L1-regularized least squares. IEEE J. Sel. Top. Signal Process. 1(4), 606-17 (2007) CrossRef
25. Matthews, I., Ishikawa, T., Baker, S.: The template update problem. IEEE Trans. Pattern Anal. Mach. Intell. 26(6), 810-15 (2004) CrossRef
26. Porikli, F., Tuzel, O., Meer, P.: Covariance tracking using model update based on lie algebra. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 728-35 (2006)
27. Wang, D., Huchuan, L.: Online object tracking with sparse prototypes. IEEE Trans. Image Process. (TIP) 22(1), 314-25 (2013) CrossRef
28. Kwon, J., Lee, K.M.: Visual tracking decomposition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1269-276 (2010)
29. Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes, Challenge 2010 (VOC2010) Results
30. Zaveri, M.A., Merchant, S.N.: Evolutionary algorithm for data association and IMM-based target tracking in IR image sequences. Signal Image Video Process. 7(1), 27-3 (2013) CrossRef - 作者单位：Xiangyang Wang (1) (2)
Ying Wang (1) (2)
Wanggen Wan (1) (2)
Jenq-Neng Hwang (2) (3)
1. School of Communication and Information Engineering, Shanghai University, Shanghai, China
2. Institute of Smart City, Shanghai University, Shanghai, China
3. Department of Electrical Engineering, University of Washington, Seattle, WA, USA - ISSN：1863-1711
文摘
Recently, the L1 tracker is proposed for robust visual tracking. However, L1 tracker is still in traditional particle filter framework. As we know, particle filters suffer from some problems such as sample impoverishment. In this paper, we propose a new visual tracking algorithm, sparse representation based annealed particle filter, to further improve the performance of L1 tracker. As in L1 tracker, we find the tracking target at a new frame by sparsely representing each target candidate with both target and trivial templates. The sparsity is achieved by solving an \(\ell _{1}\) -regularized least squares problem. The candidate with the largest likelihood is taken as the tracking target. But different from L1 tracker, instead of tracking objects in the common particle filter framework, we solve the sparse representation problem in an annealed particle filter (APF) framework. In the APF framework, the sampling covariance and annealing factors are incorporated into the tracking process. The annealing strategy can achieve “smart sampling-to avoid generating invalid particles corresponding to infeasible targets. Both qualitative and quantitative evaluations on challenging video sequences are implemented to demonstrate the favorable performance in comparison with several other state-of-the-art tracking schemes.