Abstract
The main challenging issues in visual tracking can be listed as follows: significant variation of object’s appearance or background image, illumination changes, serious or even complete occlusion of object, etc. In order to deal with them, two modules are needed: one is an accurate appearance model updating online and the other one is a robust matching method to find the target according to the learned model. In this paper, we propose a novel tracking method in a particle filter framework based on IPCA and sparse representation, in which IPCA is used to model the object appearance adaptively and sparse representation is used in two aspects: first, it helps to formulate a robust updating scheme of the IPCA; second, it strengthens the matching process significantly when the tracker copes with very challenging cases as mentioned in the beginning. In experiments, we select three state-of-the-art tracking methods for comparison and demonstrate the superiority of our method over them on various data.
Similar content being viewed by others
Abbreviations
- \({{TI}_{i}}\) :
-
The \({i}_{th}\) training images.
- \(\bar{TI}\) :
-
Mean value of \(\{{{TI}_{1}},{{TI}_{2}},\ldots ,{{TI}_{n}}\}\).
- A:
-
\(d\times n\) data matrix (\([{{TI}_{1}},{{TI}_{2}},\ldots ,{{TI}_{n}}]\)).
- B:
-
\(d\times m\) data matrix (\([{{TI}_{n+1}},\ldots ,{{TI}_{n+m}}]\)).
- \(U\varSigma {{V}^{\mathrm{T}}}\) :
-
Singular value decomposition.
- \(t_f\) :
-
Fixed target template.
- \({t_d}^{0}\) :
-
Original dynamical target template.
- \(t_d\) :
-
Dynamical target template.
- \(f\) :
-
Forgetting factor.
- \(n\) :
-
Number of frames processed.
- \(m\) :
-
Number of frames newly come.
- \(\bar{V}_m\) :
-
Mean value of the targets in \(m\) frames.
- \(i_i\) :
-
One trivial template.
- \(I\!=\!{[}{i}_{1},{i}_{2},{\ldots },{i}_{l}{]}\) :
-
Identity matrix.
- \(T\!=\!{[}{{t}_{d}},{{t}_{f}}{]}\) :
-
Target template set.
- \(y\) :
-
Tracking result.
- \(a\!=\!{[}{{a}_{1}},{{a}_{2}}{]}^{T}\) :
-
Target coefficient vector.
- \(e\!=\!{{[}{{e}_{1}},\ldots ,{{e}_{l}}{]}^{T}}\) :
-
Trivial coefficient vector.
- \(\varepsilon \) :
-
Error vector.
- \({{e}^{+}}\) :
-
Positive trivial coefficient vector.
- \({{e}^{-}}\) :
-
Negative trivial coefficient vector.
- \(c\) :
-
Nonnegative coefficient vector.
- \(y_0\) :
-
Tracking result in the previous frame.
- \(t\) :
-
Time in particle filter framework.
- \({{X}_{t}}\) :
-
Parameter of affine transformation.
- \(\mu \) :
-
Center of the subspace spanned by \(U\).
- \(d_t\) :
-
Distance to the subspace.
- \(d_w\) :
-
Distance to the subspace center.
References
Ahn, J.H., Choi, S., Oh, J.H.: A new way of PCA: integrated-squared-error and EM algorithms. In: Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP ’04). IEEE International Conference on, vol. 5, pp. V-777–V-780 (2004). doi:10.1109/ICASSP.2004.1327226
Babenko, B., Yang, M.H., Belongie, S.: Visual tracking with online multiple instance learning. In: CVPR 2009. IEEE Conference on, pp. 983–990 (2009). doi:10.1109/CVPR.2009.5206737
Babenko, B., Yang, M.H., Belongie, S.: Robust object tracking with online multiple instance learning. Pattern Anal. Mach. Intell. IEEE Trans. 33(8), 1619–1632 (2011). doi:10.1109/TPAMI.2010.226
Berclaz, J., Fleuret, F., Fua, P.: Robust people tracking with global trajectory optimization. In: Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, vol. 1, pp. 744–750 (2006). doi:10.1109/CVPR.2006.258
Candes, E.J., Romberg, J.K., Tao, T.: Stable signal recovery from incomplete and inaccurate measurements. Commun. Pure Appl. Math. 59(8), 1207–1223 (2006)
Collins, R.: Mean-shift blob tracking through scale space. In: Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on, vol. 2, pp. II-234–II-240 (2003). doi:10.1109/CVPR.2003.1211475
Collins, R., Liu, Y., Leordeanu, M.: Online selection of discriminative tracking features. Pattern Anal. Mach. Intell. IEEE Trans. 27(10), 1631–1643 (2005). doi:10.1109/TPAMI.2005.205
Ferryman, J., Crowley, J.L.: Crowd-pets09. http://www.cvg.cs.rdg.ac.uk/PETS2001/ (2009)
Dagher, I., Nachar, R.: Face recognition using IPCA-ICA algorithm. Pattern Anal. Mach. Intell. IEEE Trans. 28(6), 996–1000 (2006). doi:10.1109/TPAMI.2006.118
Decker, D., Punch, W., Sticklen, J.: IPCA, an architecture for intelligent control. In: Intelligent Control, 1996, Proceedings of the 1996 IEEE International Symposium on, pp. 80–85 (1996). doi:10.1109/ISIC.1996.556181
Everingham, M., Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The Pascal visual object classes (voc) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010). doi:10.1007/s11263-009-0275-4.
Gu, S., Zheng, Y., Tomasi, C.: Linear time offline tracking and lower envelope algorithms. In: Computer Vision (ICCV), 2011 IEEE International Conference on, pp. 1840–1846 (2011). doi:10.1109/ICCV.2011.6126451
Hargrave, P.: A tutorial introduction to Kalman filtering. In: Kalman Filters: Introduction, Applications and Future Developments, IEE Colloquium on, pp. 1/1–1/6 (1989)
Herman, M., Strohmer, T.: General deviants: an analysis of perturbations in compressed sensing. Sel. Top. Signal Process. IEEE J. 4(2), 342–349 (2010). doi:10.1109/JSTSP.2009.2039170
Kalal, Z., Matas, J., Mikolajczyk, K.: Online learning of robust object detectors during unstable tracking. In: Computer Vision Workshops (ICCV Workshops), 2009 IEEE 12th International Conference on, pp. 1417–1424 (2009). doi:10.1109/ICCVW.2009.5457446
Kalal, Z., Matas, J., Mikolajczyk, K.: P-n learning: Bootstrapping binary classifiers by structural constraints. In: Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, pp. 49–56 (2010). doi:10.1109/CVPR.2010.5540231
Kim, S.J., Koh, K., Lustig, M., Boyd, S., Gorinevsky, D.: An interior-point method for large-scale l1-regularized least squares. Sel. Top. Signal Process. IEEE J. 1(4), 606–617 (2007). doi:10.1109/JSTSP.2007.910971
Leibe, B., Schindler, K., Van Gool, L.: Coupled detection and trajectory estimation for multi-object tracking. In: Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on, pp. 1–8 (2007). doi:10.1109/ICCV.2007.4408936
Levy, A., Lindenbaum, M.: Sequential karhunen-loeve basis extraction and its application to images. In: Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on, vol. 2, pp. 456–460 (1998). doi:10.1109/ICIP.1998.723422
Liu, B., Ji, C., Zhang, Y., Hao, C., Wong, K.K.: Multi-target tracking in clutter with sequential monte carlo methods. IET Radar, Sonar Navig. 4(5), 662–672 (2010). doi:10.1049/iet-rsn.2009.0051
Liu, L., Fieguth, P.: Texture classification from random features. Pattern Anal. Mach. Intell. IEEE Trans. 34(3), 574–586 (2012). doi:10.1109/TPAMI.2011.145
Mei, X., Ling, H.: Robust visual tracking and vehicle classification via sparse representation. Pattern Anal. Mach. Intell. IEEE Trans. 33(11), 2259–2272 (2011). doi:10.1109/TPAMI.2011.66
Ross, D.A., Lim, J., Lin, R.S., Yang, M.H.: Incremental learning for robust visual tracking. Int. J. Comput. Vis. 77(1–3), 125–141 (2008). doi:10.1007/s11263-007-0075-7.
Wright, J., Yang, A., Ganesh, A., Sastry, S., Ma, Y.: Robust face recognition via sparse representation. Pattern Anal. Mach. Intell., IEEE Trans. 31(2), 210–227 (2009). doi:10.1109/TPAMI.2008.79
Yang, C., Duraiswami, R., Davis, L.: Efficient mean-shift tracking via a new similarity measure. In: Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, vol. 1, pp. 176–183 (2005). doi:10.1109/CVPR.2005.139
Zhang, D., Van Gool, L., Oosterlinck, A.: Generalized predictive control of a vision-based tracking system using kalman filtering technique. In: Control and Applications, 1989. Proceedings. ICCON ’89. IEEE International Conference on, pp. 731–733 (1989). doi:10.1109/ICCON.1989.770616
Zhou, H., Yuan, Y., Shi, C.: Object tracking using sift features and mean shift. Comput. Vis. Image Underst. 113(3), 345–352 (2009). doi:10.1016/j.cviu.2008.08.006
Zhou, S.K., Chellappa, R., Moghaddam, B.: Visual tracking and recognition using appearance-adaptive models in particle filters. Image Process. IEEE Trans. 13(11), 1491–1506 (2004). doi:10.1109/TIP.2004.836152
Acknowledgments
This work was supported by National Key Basic Research Project of China (973Program) 2011CB302400 and National Nature Science Foundation of China (NSFC Grant No. 61071156).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Shan, D., Zhang, C. Visual tracking using IPCA and sparse representation. SIViP 9, 913–921 (2015). https://doi.org/10.1007/s11760-013-0525-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-013-0525-3