The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.04 - April (2009 vol.31)
pp: 677-692
Karel Zimmermann , Czech Technical University, Prague
Jiří Matas , Czech Technical University, Prague
Thomáš Svoboda , Czech Technical University, Prague
ABSTRACT
We propose a learning approach to tracking explicitly minimizing the computational complexity of the tracking process subject to user-defined probability of failure (loss-of-lock) and precision. The tracker is formed by a Number of Sequences of Learned Linear Predictors (NoSLLiP). Robustness of NoSLLiP is achieved by modeling the object as a collection of local motion predictors - object motion is estimated by the outlier-tolerant Ransac algorithm from local predictions. Efficiency of the NoSLLiP tracker stems from (i) the simplicity of the local predictors and (ii) from the fact that all design decisions - the number of local predictors used by the tracker, their computational complexity (i.e. the number of observations the prediction is based on), locations as well as the number of Ransac iterations are all subject to the optimization (learning) process. All time-consuming operations are performed during the learning stage - tracking is reduced to only a few hundreds integer multiplications in each step. On PC with 1xK8 3200+, a predictor evaluation requires about 30 microseconds. The proposed approach is verified on publicly-available sequences with approximately 12000 frames with ground-truth. Experiments demonstrates, superiority in frame rates and robustness with respect to the SIFT detector, Lucas-Kanade tracker and other trackers.
INDEX TERMS
Image Processing and Computer Vision, Tracking
CITATION
Karel Zimmermann, Jiří Matas, Thomáš Svoboda, "Tracking by an Optimal Sequence of Linear Predictors", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.31, no. 4, pp. 677-692, April 2009, doi:10.1109/TPAMI.2008.119
REFERENCES
[1] B. Lucas and T. Kanade, “An Iterative Image Registration Technique with an Application to Stereo Vision,” Int'l J. Computer Vision and Artificial Intelligence, pp. 674-679, 1981.
[2] S. Baker and I. Matthews, “Lucas-Kanade 20 Years on: A Unifying Framework,” Int'l J. Computer Vision, vol. 56, no. 3, pp. 221-255, 2004.
[3] M. Özuysal, V. Lepetit, F. Fleuret, and P. Fua, “Feature Harvesting for Tracking-by-Detection,” Proc. Ninth European Conf. Computer Vision, pp. 592-605, 2006.
[4] S. Avidan, “Support Vector Tracking,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 8, pp. 1064-1072, Aug. 2004.
[5] H. Grabner and H. Bischof, “On-Line Boosting and Vision,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 260-267, 2006.
[6] F. Jurie and M. Dhome, “Real Time Robust Template Matching,” Proc. British Machine Vision Conf., pp. 123-131, 2002.
[7] T. Cootes, G. Edwards, and C. Taylor, “Active Appearance Models,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 6, pp. 681-685, June 2001.
[8] O. Williams, A. Blake, and R. Cipolla, “Sparse Bayesian Learning for Efficient Visual Tracking,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 8, pp. 1292-1304, Aug. 2005.
[9] H. Bay, T. Tuytelaars, and L. Van Gool, “Surf: Speeded Up Robust Features,” Proc. Ninth European Conf. Computer Vision, May 2006.
[10] L. Vacchetti, V. Lepetit, and P. Fua, “Stable Real-Time 3D Tracking Using Online and Offline Information,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 10, pp. 1385-1391, Oct. 2004.
[11] J. Shi and C. Tomasi, “Good Features to Track,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 593-600, 1994.
[12] T. Cootes, G. Edwards, and C. Taylor, “Active Appearance Models,” Proc. Fifth European Conf. Computer Vision, vol. 2, pp.484-498, 1998.
[13] D. Cristinacce and T. Cootes, “Feature Detection and Tracking with Constrained Local Models,” Proc. 17th British Machine Vision Conf., pp. 929-938, 2006.
[14] M.E. Tipping, “Sparse Bayesian Learning and the Relevance Vector Machine,” J. Machine Learning Research, vol. 1, pp. 211-244, 2001.
[15] A. Agarwal and B. Triggs, “Recovering 3D Human Pose from Monocular Images,” IEEE Trans. Pattern Analysis Machine Intelligence, vol. 28, no. 1, pp. 44-58, Jan. 2006.
[16] H. Drucker, C. Burges, L. Kaufman, A. Smola, and V. Vapnik, “Support Vector Regression Machines,” Advances in Neural Information Processing Systems, vol. 9, pp. 156-161, 1996.
[17] V.N. Vapnik, The Nature of Statistical Learning Theory (Information Science and Statistics). Springer-Verlag, Nov. 1999.
[18] A. Smola and B. Schölkopf, “A Tutorial on Support Vector Regression,” technical report, ESPRIT Working Group in Neural and Computational Learning II, 1998.
[19] S.K. Zhou, B. Georgescu, X.S. Zhou, and D. Comaniciu, “Image Based Regression Using Boosting Method,” Proc. 10th IEEE Int'l Conf. Computer Vision, vol. 1, pp. 541-548, 2005.
[20] A. Bissacco, M. Yang, and S. Soatto, “Fast Human Pose Estimation Using Appearance and Motion via Multi-Dimensional Boosting Regression,” Computer Vision and Pattern Recognition, pp. 1-8, 2007.
[21] K. Zimmermann, “Fast Learnable Methods for Object Tracking,” PhD dissertation, Czech Technical Univ., 2008.
[22] B. Bollobás, Modern Graph Theory. Springer, 1998.
[23] S. Benhimane, A. Ladikos, V. Lepetit, and N. Navab, “Linear and Quadratic Subsets for Template-Based Tracking,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2007.
[24] D. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” Int'l J. Computer Vision, vol. 60, no. 2, pp. 91-110, 2004.
[25] A. Haar, “Zur Theorie der Orthogonalen Funktionensysteme,” Annals of Math., vol. 69, pp. 331-371, 1910.
5 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool