The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.09 - September (2011 vol.33)
pp: 1860-1876
Yan Li , Microsoft Corporation, Redmond
Leon Gu , WorldQuant LLC, Old Greenwich
Takeo Kanade , Carnegie Mellon University, Pittsburgh
ABSTRACT
Precisely localizing in an image a set of feature points that form a shape of an object, such as car or face, is called alignment. Previous shape alignment methods attempted to fit a whole shape model to the observed data, based on the assumption of Gaussian observation noise and the associated regularization process. However, such an approach, though able to deal with Gaussian noise in feature detection, turns out not to be robust or precise because it is vulnerable to gross feature detection errors or outliers resulting from partial occlusions or spurious features from the background or neighboring objects. We address this problem by adopting a randomized hypothesis-and-test approach. First, a Bayesian inference algorithm is developed to generate a shape-and-pose hypothesis of the object from a partial shape or a subset of feature points. For alignment, a large number of hypotheses are generated by randomly sampling subsets of feature points, and then evaluated to find the one that minimizes the shape prediction error. This method of randomized subset-based matching can effectively handle outliers and recover the correct object shape. We apply this approach on a challenging data set of over 5,000 different-posed car images, spanning a wide variety of car types, lighting, background scenes, and partial occlusions. Experimental results demonstrate favorable improvements over previous methods on both accuracy and robustness.
INDEX TERMS
Shape alignment, RANSAC, ASM.
CITATION
Yan Li, Leon Gu, Takeo Kanade, "Robustly Aligning a Shape Model and Its Application to Car Alignment of Unknown Pose", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.33, no. 9, pp. 1860-1876, September 2011, doi:10.1109/TPAMI.2011.40
REFERENCES
[1] Y. Amit and D. Geman, "Shape Quantization and Recognition with Randomized Trees," Neural Computation, vol. 9, pp. 1545-1588, 1997.
[2] Å. Björck, "Numerical Methods for Least Squares Problems," Proc. SIAM, 1996.
[3] V. Blanz and T. Vetter, "A Morphable Model for the Synthesis of 3D Faces," Proc. ACM SIGGRAPH, pp. 187-194, 1999.
[4] V. Blanz and T. Vetter, "Face Recognition Based on Fitting a 3D Morphable Model," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 9, pp. 1063-1074, Sept. 2003.
[5] L. Breiman, "Bagging Predictors," Machine Learning, vol. 26, no. 2, pp. 123-140, 1996.
[6] L. Breiman, "Random Forests," Machine Learning, vol. 45, pp. 5-32, 2001.
[7] W.L. Buntine, "Learning Classification Trees," Artificial Intelligence Frontiers in Statistics, D.J. Hand, ed., Chapman and Hall, 1991.
[8] T.F. Cootes, G.J. Edwards, and C.J. Taylor, "Active Appearance Models," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 6, pp. 681-685, June 2001.
[9] T.F. Cootes and C.J. Taylor, "A Mixture Model for Representing Shape Variation," Proc. Image and Vision Computing, pp. 110-119, 1997.
[10] T.F. Cootes, C.J. Taylor, D.H. Cooper, and J. Graham, "Active Shape Model—Their Training and Application," Computer Vision and Image Understanding, vol. 61, no. 1, pp. 38-59, Jan. 1995.
[11] T.F. Cootes, K. Walker, and C.J. Taylor, "View-Based Active Appearance Models," Proc. Fourth IEEE Int'l Conf. Automatic Face and Gesture Recognition, 2000.
[12] D. Cristinacce and T. Cootes, "Automatic Feature Localisation with Constrained Local Models," Pattern Recognition, vol. 41, pp. 3054-3067, 2008.
[13] N. Dalal and B. Triggs, "Histograms of Oriented Gradients for Human Detection," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 886-893, 2005.
[14] I. Dryden and K. Mardia, Statistical Shape Analysis. John Wiley & Sons, 1998.
[15] P. Felzenszwalb and J.D. Schwartz, "Hierarchical Matching of Deformable Shapes," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1-8, 2007.
[16] V. Ferrari, F. Jurie, and C. Schmid, "Accurate Object Detection with Deformable Shape Models Learned from Images," Proc. European Conf. Computer Vision, 2008.
[17] M.A. Fischler and R.C. Bolles, "Random Sample Consensus: A Paradigm for Model Fitting with Application to Image Analysis and Automated Cartography," Comm. ACM, vol. 24, no. 6, pp. 381-395, June 1981.
[18] J. Gower and G. Dijksterhuis, Procrustes Problems. Oxford Univ. Press, 2004.
[19] L. Gu and T. Kanade, "3D Alignment of Face in a Single Image," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 1305-1312, 2006.
[20] F. Jiao, S. Li, H.-Y. Shum, and D. Schuurmans, "Face Alignment Using Statistical Models and Wavelet Features," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. I-321-I-327, 2003.
[21] M. Kass, A. Witkin, and D. Terzopoulos, "Snakes: Active Contour Models," Int'l. J. Computer Vision, vol. 1, no. 4, pp. 321-331, 1988.
[22] V. Lepetit, P. Lagger, and P. Fua, "Randomized Trees for Real-Time Keypoint Recognition," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 775-781, 2005.
[23] Y. Li, "Models for Object Detection, Recognition, and Shape Alignment," PhD thesis, Carnegie Mellon Univ, 2009.
[24] L. Liang, F. Wen, Y.-Q. Xu, X. Tang, and H.-Y. Shum, "Accurate Face Alignment Using Shape Constrained Markov Network," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 1313-1319, 2006.
[25] L. Liang, R. Xiao, F. Wen, and J. Sun, "Face Alignment Via Component-Based Discriminative Search," Proc. 10th European Conf. Computer Vision, 2008.
[26] C. Liu, H. Shum, and C. Zhang, "Hierarchical Shape Modeling for Automatic Face Localization," Proc. Seventh European Conf. Computer Vision, 2002.
[27] R. Marée, P. Guerts, J. Piater, and L. Wehenkel, "Random Subwindows for Robust Image Classification," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 34-40, 2005.
[28] F. Moosmann, D. Larlus, and F. Jurie, "Learning Saliency Maps for Object Categorization," Proc. ECCV Workshop the Representation and Use of Prior Knowledge in Vision, 2006.
[29] F. Moosmann, B. Triggs, and F. Jurie, "Fast Discriminative Visual Codebooks Using Randomized Clustering Forests," Proc. Neural Information Processing Systems, 2006.
[30] J.R. Quinlan, "Inductive Knowledge Acquisition: A Case Study," Proc. Applications of Expert Systems, 1987.
[31] S. Ravishankar, A. Jain, and A. Mittal, "Multi-Stage Contour Based Detection of Deformable Objects," Proc. 10th European Conf. Computer Vision: Part I, 2008.
[32] M. Rogers and J. Graham, "Robust Active Shape Model Search," Proc. European Conf. Computer Vision, 2002.
[33] S. Romdhani, S. Gong, and A. Psarrou, "A Multi-View Nonlinear Active Shape Model Using Kernel PCA," Proc. British Machine Vision Conf., 1999.
[34] P.J. Rousseeuw, Robust Regression and Outlier Detection. Wiley, 1987.
[35] C. Steward, "Robust Parameter Estimation in Computer Vision," SIAM Rev., vol. 41, no. 3, pp. 513-537, 1999.
[36] M.E. Tipping and C.M. Bishop, "Probabilistic Principal Component Analysis," J. Royal Statistical Soc., Series B, vol. 61, pp. 611-622, 1999.
[37] J. Tu, Z. Zhang, Z. Zeng, and T. Huang, "Face Localization via Hierarchical Condensation with Fisher Boosting Feature Selection," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2004.
[38] Y. Wang, S. Lucey, and J. Cohn, "Enforcing Convexity for Improved Alignment with Constrained Local Models," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[39] S. Yan, M. Li, H. Zhang, and Q. Cheng, "Ranking Prior Likelihood Distributions for Bayesian Shape Localization Framework," Proc. Ninth IEEE Int'l Conf. Computer Vision, 2003.
[40] Z. Zhang, "Parameter Estimation Techniques: A Tutorial with Application to Conic Fitting," Image and Vision Computing J., vol. 15, no. 1, pp. 59-76, 1997.
[41] Y. Zhou, L. Gu, and H.J. Zhang, "Bayesian Tangent Shape Model: Estimating Shape and Pose Parameters via Bayesian Inference," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2003.
[42] Y. Zhou, W. Zhang, X. Tang, and H. Shum, "A Bayesian Mixture Model for Multi-View Face Alignment," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 741-746, 2005.
[43] F. Zuo and H.d. With, "Fast Facial Feature Extraction Using a Deformable Shape Model with Haar-Wavelet Based Local Texture Attributes," Proc. Int'l Conf. Image Processing, 2004.
16 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool