Abstract
This letter presents a novel prediction scheme employed for fast visual tracking. The proposed multilinear predictor is formulated as a higher order tensor, instead of the existing vector representations. This predictor is based on emploing the Canonical/Parallel factors (CP) decomposition to decompose a tensor as a sum of rank one tensors. In that way, the proposed scheme efficiently retains the underlying structural information of the input data, while reduces at the same time the computational complexity by employing separable filter operations applied at different directions. The efficiency of the proposed scheme is demonstrated in the conducted experiments.
Similar content being viewed by others
References
S. Baker and I. Mathhews. Locas-Kanade 20 years on: an unifying framework. International Journal of Computer Vision, 56(2004)3, 221–255.
N. Dowson and R. Bowden. Mutual information for Lucas-Kanade tracking (MILK): an inverse compositional formulation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(2008)1, 180–185.
S. Avidan. Support vector tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(2004)8, 1064–1072.
X. Li, W. Hu, Z. Zhang, et al. Robust visual tracking based on incremental tensor subspace learning. IEEE International Conference on Computer Vision, Rio de Janeiro, Brazil, October 14–20, 2007, 1–8.
R. Urtasun, D. J. Fleet, and P. Fua. 3D people tracking with Gaussian process dynamical models. IEEE Conference on Computer Vision and Pattern Recognition, New York, USA, 2006, 238–245.
M. H. Nguyen and F. D. la Torre. Metric learning for image alignment. International Journal of Computer Vision, 88(2010)1, 69–84.
H. Grabner, M. Grabner, and H. Bischof. Real-time tracking via on-line boosting. British Machine Vision Conference, Edinburgh, UK, September 2006, 47–56.
B. Babenko, M. Yang, and S. Belongie. Visual tracking with online multiple instance learning. IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, June 2009, 983–990.
L. Ellis, N. Dowson, J. Matas, et al. Linear predictors for fast simultaneous modeling and tracking. IEEE Internatinal Conference on Computer Vision, Rio de Janeiro, Brazil, October 2007, 1–8.
S. Holzer, S. Ilic, and N. Navab. Adaptive linear predictors for real-time tracking. IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, USA, June 2010, 1807–1814.
K. Zimmermann, J. Matas, and T. Svoboda. Tracking by an optimal sequence of linear predictors. IEEE Transcations on Pattern Analysis and Machine Intelligence, 31(2009)4, 677–692.
O. Williams, A. Blake, and R. Cipolla. Sparse baysian learning for efficient visual tracking. IEEE Transcations on Pattern Analysis and Machine Intelligence, 27(2005)8, 1292–1304.
H. Pirsiavash, D. Ramanan, and C. Fowlkes. Bilinear classifiers for visual recognition. Neural Information Processing Systems, Vancouver, B.C., Canada, December, 2009, 1482–1490.
D. Tao. X. Li, X. Wu, et al. Supervised tensor learning. Knowledge and Information Systems, 13(2007)1, 1–42.
L. Wolf, H. Jhuang, and T. Hazan. Modeling appearances with low-rank SVM. IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA, June 2007, 1–6.
H. Lu, K. N. Plataniotis, and A. N. Venetsanopoulos. MPCA: Multilinear principal component analysis of tensor objects. IEEE Transcations on Neural Networks, 19(2008)1, 18–39.
X. He, D. Cai, and P. Niyogi. Tensor subspace analysis. Neural Information Processing Systems, Vancouver, B.C., Canada, December 2006.
S. Yan, D. Xu, Q. Yang, et al. Multilinear discriminant analysis for face recognition. IEEE Transcations on Image Processing, 16(2007)1, 212–220.
T. Kolda and B. Bader. Tensor decompositions and applications. SIAM Review, 51(2009)3, 455–500.
I. Patras, and E. R. Hancock. Coupled prediction classification for robust visual tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(2010)9, 1553–1567.
J. Lim, D. Ross, R. Lin, et al. Incremental learning for visual tracking. Neural Information Processing Systems, Vancouver, B.C., Canada, December 2005, 793–800.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communication author: Guo Weiwei, born in 1983, male, Ph.D..
About this article
Cite this article
Guo, W., Yu, W. A novel multilinear predictor for fast visual tracking. J. Electron.(China) 29, 158–165 (2012). https://doi.org/10.1007/s11767-012-0755-5
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11767-012-0755-5