This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Sparse Bayesian Learning for Efficient Visual Tracking
August 2005 (vol. 27 no. 8)
pp. 1292-1304
This paper extends the use of statistical learning algorithms for object localization. It has been shown that object recognizers using kernel-SVMs can be elegantly adapted to localization by means of spatial perturbation of the SVM. While this SVM applies to each frame of a video independently of other frames, the benefits of temporal fusion of data are well-known. This is addressed here by using a fully probabilistic Relevance Vector Machine (RVM) to generate observations with Gaussian distributions that can be fused over time. Rather than adapting a recognizer, we build a displacement expert which directly estimates displacement from the target region. An object detector is used in tandem, for object verification, providing the capability for automatic initialization and recovery. This approach is demonstrated in real-time tracking systems where the sparsity of the RVM means that only a fraction of CPU time is required to track at frame rate. An experimental evaluation compares this approach to the state of the art showing it to be a viable method for long-term region tracking.

[1] S. Avidan, “Support Vector Tracking,” Proc. Conf. Computer Vision and Pattern Recognition, 2001.
[2] M.J. Black and A.D. Jepson, “Eigentracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation,” Proc. European Conf. Computer Vision, vol. 1, pp. 329-342, 1996.
[3] A. Blake and M. Isard, “3D Position, Attitude and Shape Input Using Video Tracking of Hands and Lips,” Proc. Siggraph, pp. 185-192, 1994.
[4] A. Blake and M. Isard, Active Contours. Springer, 1998.
[5] Computer Vision for Human-Machine Interaction, R. Cipolla and A. Pentland, eds. Cambridge Univ. Press, 1998.
[6] D. Comaniciu, V. Ramesh, and P. Meer, “Real-Time Tracking of Non-Rigid Objects Using Mean Shift,” Proc. Conf. Computer Vision and Pattern Recognition, 2000.
[7] T.F. Cootes, G.J. Edwards, and C.J. Taylor, “Active Appearance Models,” Proc. European Conf. Computer Vision, pp. 484-498, 1998.
[8] W. Freeman and E. Adelson, “The Design and Use of Steerable Filters,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 9, pp. 891-906, Sept. 1991.
[9] Applied Optimal Estimation, A. Gelb, ed. Cambridge, Mass.: MIT Press, 1974.
[10] G.D. Hager and P.N. Belhumeur, “Efficient Region Tracking with Parametric Models of Geometry and Illumination,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 10, pp. 1025-1039, Oct. 1998.
[11] M. Isard and A. Blake, “Contour Tracking by Stochasitc Propagation of Conditional Density,” Proc. European Conf. Computer Vision, pp. 343-356, 1996.
[12] A.K. Jain, Fundamentals of Digital Image Processing. Prentice-Hall, 1989.
[13] T. Jebara and A. Pentland, “Parametrized Structure from Motion for 3D Adaptive Feedback Tracking of Faces,” Proc. Conf. Computer Vision and Pattern Recognition, 1997.
[14] A.D. Jepson, D.J. Fleet, and T.F. El-Maraghi, “Robust On-Line Appearance Models for Visual Tracking,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 415-422, 2001.
[15] F. Jurie and M. Dhome, “Hyperplane Approximation for Template Matching,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 7, pp. 996-1000, July 2002.
[16] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active Contour Models,” Proc. Int'l Conf. Computer Vision, pp. 259-268, 1987.
[17] J.P. Lewis, “Fast Normalized Cross-Correlation,” Vision Interface, 1995.
[18] S.Z. Li, L. Zhu, Z.Q. Zhang, A. Blake, H.J. Zhang, and H. Shum, “Statistical Learning of Multi-View Face Detection,” Proc. European Conf. Computer Vision, 2002.
[19] D.G. Lowe, “Robust Model-Based Motion Tracking through the Integration of Search and Estimation,” Int'l J. Computer Vision, vol. 8, no. 2, pp. 113-122, 1992.
[20] E. Osuna, R. Freund, and F. Girosi, “Training Support Vector Machines: An Application to Face Detection,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 130-136, 1997.
[21] S. Romdhani, P. Torr, B. Scholköpf, and A. Blake, “Computationally Efficient Face Detection,” Proc. Int'l Conf. Computer Vision, vol. 2, pp. 524-531, 2001.
[22] B. Scholköpf, C. Burges, and A. Smola, Advances in Kernel Methods: Support Vector Machines. Cambridge, Mass.: MIT Press, Dec. 1998.
[23] M.E. Tipping and A.C. Faul, “Fast Marginal Likelihood Maximisation for Sparse Bayesian Models,” Proc. Ninth Int'l Workshop on Artificial Intelligence and Statistics, C.M. Bishop and B.J. Frey, eds., Jan. 2003.
[24] M.E. Tipping, “The Relevance Vector Machine,” Advances in Neural Information Processing Systems, S.A. Solla, T.K. Leen, and K.R. Müller, eds., vol. 12, pp. 652-658, 2000.
[25] M.E. Tipping, “Sparse Bayesian Learning and the Relevance Vector Machine,” J. Machine Learning Research, vol. 1, pp. 211-244, 2001.
[26] L. Vacchetti, V. Lepetit, and P. Fua, “Stable 3D Tracking in Real-Time Using Integrated Context Information,” Proc. Conf. Computer Vision and Pattern Recognition, 2003.
[27] V. Vapnik, The Nature of Statistical Learning Theory. New York: Springer Verlag, 1995.
[28] P. Viola and M. Jones, “Rapid Object Detection Using a Boosted Cascade of Simple Features,” Proc. Conf. Computer Vision and Pattern Recognition, 2001.
[29] P Viola, M.J. Jones, and D. Snow, “Detecting Pedestrians Using Patterns of Motion and Appearance,” Proc. Int'l Conf. Computer Vision, pp. 734-741, Oct. 2003.
[30] A.L. Yuille and P. Hallinan, “Deformable Templates,” Active Vision, A. Blake and A.L. Yuille, eds. pp. 20-38, MIT, 1992.

Index Terms:
Index Terms- Probabilistic algorithms, robust regression, tracking, object recognition.
Citation:
Oliver Williams, Andrew Blake, Roberto Cipolla, "Sparse Bayesian Learning for Efficient Visual Tracking," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 8, pp. 1292-1304, Aug. 2005, doi:10.1109/TPAMI.2005.167
Usage of this product signifies your acceptance of the Terms of Use.