The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.03 - March (2009 vol.31)
pp: 570-576
Ali Shahrokni , University of Oxford, UK
Tom Drummond , University of Cambridge, UK
François Fleuret , IDIAP Research Institute, Switzerland
Pascal Fua , Ecole Polytechnic Fédérale de Lausanne, Switzerland
ABSTRACT
We introduce a classification-based approach to finding occluding texture boundaries. The classifier is composed of a set of weak learners which operate on image intensity discriminative features which are defined on small patches and fast to compute. A database which is designed to simulate digitized occluding contours of textured objects in natural images is used to train the weak learners. The trained classifier score is then used to obtain a probabilistic model for the presence of texture transitions which can readily be used for line search texture boundary detection in the direction normal to an initial boundary estimate. This method is fast and therefore suitable for real-time and interactive applications. It works as a robust estimator which requires a ribbon like search region and can handle complex texture structures without requiring a large number of observations. We demonstrate results both in the context of interactive 2-D delineation and fast 3-D tracking and compare its performance with other existing methods for line search boundary detection.
INDEX TERMS
Texture, Tracking, Pixel classification, Markov random fields, Edge and feature detection
CITATION
Ali Shahrokni, Tom Drummond, François Fleuret, Pascal Fua, "Classification-Based Probabilistic Modeling of Texture Transition for Fast Line Search Tracking and Delineation", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.31, no. 3, pp. 570-576, March 2009, doi:10.1109/TPAMI.2008.236
REFERENCES
[1] C. Harris, Tracking with Rigid Objects. MIT Press, 1992.
[2] T. Drummond and R. Cipolla, “Real-Time Visual Tracking of Complex Structures,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 7, pp. 932-946, July 2002.
[3] A. Blake, C. Rother, M. Brown, P. Perez, and P. Torr, “Interactive Image Segmentation Using an Adaptive Gmmrf Model,” Proc. Eighth European Conf. Computer Vision, vol. 1, pp. 428-441, 2004.
[4] C. Rother, V. Kolmogorov, and A. Blake, ““GrabCut”: Interactive Foreground Extraction Using Iterated Graph Cuts,” ACM Trans. Graphics, vol. 23, no. 3, pp. 309-314, 2004.
[5] A. Shahrokni, T. Drummond, and P. Fua, “Texture Boundary Detection for Real-Time Tracking,” Proc. Eighth European Conf. Computer Vision, vol. II, pp. 566-577, May 2004.
[6] Y. Boykov and M. Jolly, “Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images,” Proc. Eighth Int'l Conf. Computer Vision, vol. I, pp. 105-112, July 2001.
[7] M. Rivera and J.C. Gee, “Two-Level MRF Models for Image Restoration and Segmentation,” Proc. British Machine Vision Conf., pp. 809-818, 2004.
[8] C.H. Lampert, M.B. Blaschko, and T. Hofmann, “Beyond Sliding Windows: Object Localization by Efficient Subwindow Search,” IEEE Trans. Pattern Analysis and Machine Intelligence, to appear.
[9] D. Martin, C. Fowlkes, and J. Malik, “Learning to Detect Natural Image Boundaries Using Local Brightness, Color and Texture Cues,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 5, May 2004.
[10] P. Dollár, Z. Tu, and S. Belongie, “Supervised Learning of Edges and Object Boundaries,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, June 2006.
[11] A. Shahrokni, F. Fleuret, and P. Fua, “Classifier-Based Contour Tracking for Rigid and Deformable Objects,” Proc. British Machine Vision Conf., 2005.
[12] Y. Freund and R.E. Schapire, “Experiments with a New Boosting Algorithm,” Proc. 13th Int'l Conf. Machine Learning, pp. 148-156, 1996.
[13] A. Shahrokni, “Probabilistic Modeling of Texture Transition for Fast Tracking and Delineation,” PhD thesis no. 3377, EPFL, Lausanne, 2005.
[14] P. Simard, L. Bottou, P. Haffner, and Y. LeCun, “A Fast Convolution Algorithm for Neural Networks and Signal Processing,” Advances in Neural Information Processing Systems 11, MIT Press, 1999.
[15] G. Rätsch, T. Onoda, and K.R. Müller, “Regularizing Adaboost,” Neural Information Processing Systems, MIT Press, pp. 564-570, 1998.
[16] P. Langley, W. Iba, and K. Thompson, “An Analysis of Bayesian Classifiers,” Proc. 10th Nat'l Conf. Artificial Intelligence, pp. 223-228, 1992.
[17] R. Kaucic and A. Blake, “Accurate, Real-Time, Unadorned Lip Tracking,” Proc. Sixth Int'l Conf. Computer Vision, pp. 370-375, 1998.
[18] S. Ilić and P. Fua, “Implicit Meshes for Surface Reconstruction,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 2, Feb. 2006.
18 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool