This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
An Information Fusion Framework for Robust Shape Tracking
January 2005 (vol. 27 no. 1)
pp. 115-129
Existing methods for incorporating subspace model constraints in shape tracking use only partial information from the measurements and model distribution. We propose a unified framework for robust shape tracking, optimally fusing heteroscedastic uncertainties or noise from measurement, system dynamics, and a subspace model. The resulting nonorthogonal subspace projection and fusion are natural extensions of the traditional model constraint using orthogonal projection. We present two motion measurement algorithms and introduce alternative solutions for measurement uncertainty estimation. We build shape models offline from training data and exploit information from the ground truth initialization online through a strong model adaptation. Our framework is applied for tracking in echocardiograms where the motion estimation errors are heteroscedastic in nature, each heart has a distinct shape, and the relative motions of epicardial and endocardial borders reveal crucial diagnostic features. The proposed method significantly outperforms the existing shape-space-constrained tracking algorithm. Due to the complete treatment of heteroscedastic uncertainties, the strong model adaptation, and the coupled tracking of double-contours, robust performance is observed even on the most challenging cases.

[1] Y. Akgul and C. Kambhamettu, “A Coarse-to-Fine Deformable Contour Optimization Framework,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 2, pp. 174-186, Feb. 2003.
[2] P. Anandan, “A Computational Framework and an Algorithm for the Measurement of Visual Motion,” Int'l J. Computer Vision, vol. 2, pp. 283-310, 1989.
[3] B. Anderson and J. Moore, Optimal Filtering. Prentice Hall, 1979.
[4] Y. Bar-Shalom and L. Campo, “The Effect of the Common Process Noise on the Two-Sensor Fused Track,” IEEE Trans. Aerospace and Electronic Systems, vol. 22, pp. 803-805, 1986.
[5] Y. Bar-Shalom and T. Fortmann, Tracking and Data Association. Academic Press, 1988.
[6] P. Batchelor and J. Fitzpatrick, “A Study of the Anisotropically Weighted Procrustes Problem,” Proc. IEEE Workshop Math. Methods in Biomedical Image Analysis, pp. 212-218, 2000.
[7] M. Black and P. Ananadan, “The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields,” Computer Vision and Image Understanding, vol. 63, no. 1, pp. 75-104, 1996.
[8] M. Black and A. Jepson, “Eigentracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation,” Proc. European Conf. Computer Vision, pp. 610-619, 1996.
[9] A. Blake and M. Isard, Active Contours. Springer Verlag, 1998.
[10] M. Brand and R. Bhotika, “Flexible Flow for 3D Nonrigid Object Tracking and Shape Recovery,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. I, pp. 315-322, 2001.
[11] C. Bregler, A. Hertzmann, and H. Biermann, “Recovering Non-Rigid 3D Shape from Image Streams,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. II, pp. 690-696, 2000.
[12] C. B. Burckhardt, “Speckle in Ultrasound b-Mode Scans,” IEEE Trans. Sonics and Ultrasonics, vol. 25, no. 1, pp. 1-6, 1978.
[13] P. Clarysse, D. Friboulet, and I.E. Magnin, “Tracking Geometrical Descriptors on 3-D Deformable Surfaces: Application to the Left-Ventricular Surface of the Heart,” IEEE Trans. Medical Imaging, vol. 16, no. 4, pp. 392-404, 1997.
[14] D. Comaniciu, “Bayesian Kernel Tracking,” Proc. Ann. Conf. German Soc. for Pattern Recognition, pp. 438-445, 2002.
[15] D. Comaniciu, “An Algorithm for Data-Driven Bandwidth Selection,” IEEE Trans. Pattern Analysis Machine Intelligence, vol. 25, no. 2, pp. 281-288, Feb. 2003.
[16] D. Comaniciu, “Nonparametric Information Fusion for Motion Estimation,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. I, pp. 59-66, 2003.
[17] D. Comaniciu and P. Meer, “Mean Shift: A Robust Approach toward Feature Space Analysis,” IEEE Trans. Pattern Analysis and and Machine Intelligence, vol. 24, no. 5, pp. 603-619, May 2002.
[18] T. Cootes and C. Taylor, “Active Shape Models-'Smart Snakes',” Proc. British Machine Vision Conf., pp. 266-275, 1992.
[19] T. Cootes and C. Taylor, “Statistical Models for Appearance for Computer Vision,” unpublished manuscript, http://www.wiau.man.ac.uk/Modelsapp_model.ps.gz , 2001.
[20] I.L. Dryden and K.V. Mardia, Statistical Shape Analysis. John Wiley & Sons, Ltd., 1998.
[21] R. Goldenberg, R. Kimmel, E. Rivlin, and M. Rudzsky, “Cortex Segmentation: A Fast Variational Geometric Approach,” IEEE Trans. Medical Imaging, vol. 21, no. 2, pp. 1544-1551, Dec. 2002.
[22] P. Hall, D. Marshall, and R. Martin, “Merging and Splitting Eigenspace ZModels,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22. no. 9, pp. 1042-1048, Sept. 2000.
[23] B. Han, D. Comaniciu, and L. Davis, “Sequential Kernel Density Approximation through Mode Propagation: Applications to Background Modeling,” Proc. Asian Conf. Computer Vision, 2004.
[24] A. Hoerl and R. Kennard, “Ridge Regression: Biased Estimation for Nonorthogonal Problems,” Technometrics, vol. 12, no. 1, pp. 55-67, 1970.
[25] B. Horn and B. Schunck, “Determining the Optical Flow,” Artificial Intelligence, vol. 17, pp. 185-203, 1981.
[26] P. J. Huber, Robust Statistics. Wiley, 1981.
[27] M. Irani, “Multi-Frame Optical Flow Estimation Using Subspace Constraints,” Proc. Int'l Conf. Computer Vision, pp. 626-633, Sept. 1999.
[28] M. Irani and P. Anandan, “Factorization with Uncertainty,” Proc. Sixth European Conf. Computer Vision, pp. 539-553, 2000.
[29] G. Jacob, J. Noble, C. Behrenbruch, A. Kelion, and A. Banning, “A Shape-Space-Based Approach to Tracking Myocardial Borders and Quantifying Regional Left-Ventricular Function Applied in Echocardiography,” IEEE Trans. Medical Imaging, vol. 21, no. 3, pp. 226-238, 2002.
[30] S. Julier and J. Uhlmannn, “A Non-Divergent Estimation Algorithm in the Presence of Unknown Correlations,” Proc. Am. Control Conf., 1997.
[31] Y. Kanazawa and K. Kanatani, “Do We Really Have to Consider Covariance Matrices for Image Features?” Proc. Int'l Conf. Computer Vision, vol. II, pp. 586-591, 2001.
[32] D.G. Kendall, D. Barden, T.K. Carne, and H. Le, Shape and Shape Theory. John Wiley & Sons, Ltd., 1999.
[33] Y. Leedan and P. Meer, “Heteroscedastic Regression in Computer Vision: Problems with Bilinear Constraint,” Int'l J. Computer Vision, vol. 37, no. 2, pp. 127-150, 2000.
[34] X. Li, Y. Zhu, and C. Han, “Unified Optimal Linear Estimation Fusion-Part I: Unified Models and Fusion Rules,” Proc. Third Int'l Conf. Information Fusion, pp. MoC2-10-MoC2-17, 2000.
[35] B. Lucas and T. Kanade, “An Iterative Image Registration Technique with an Application to Stereo Vision,” Proc. DARPA Imaging and Understanding Workshop, pp. 121-130, 1981.
[36] G.E. Mailloux, F. Langlois, P.Y. Simard, and M. Bertrand, “Restoration of the Velocity Field of the Heart from Two-Dimensional Echocardiograms,” IEEE Trans. Medical Imaging, vol. 8, no. 2, pp. 143-153, 1989.
[37] J. McEachen and J. Duncan, “Shape-Based Tracking of Left Ventricular Wall Motion,” IEEE Trans. Medical Imaging, vol. 16, pp. 270-283, 1997.
[38] I. Mikic, S. Krucinski, and J.D. Thomas, “Segmentation and Tracking in Echocardiographic Sequences: Active Contours Guided by Optical Flow Estimates,” IEEE Trans. Medical Imaging, vol. 17, no. 2, pp. 274-284, 1998.
[39] W. Mio, A. Srivastava, and X. Liu, “Learning and Bayesian Shape Extraction for Object Recognition,” Proc. European Conf. Computer Vision, 2004.
[40] K. Nickels and S. Hutchinson, “Estimating Uncertainty in SSD-Based Feature Tracking,” Image and Vision Computing, vol. 20, pp. 47-58, 2002.
[41] J.K. Oh, J.B. Seward, and A.J. Tajik, The Echo Manual. Philadelphia: Lippincott Williams & Wilkins, 1999.
[42] N. Paragios, “A Variational Approach for the Segmentation of the Left Ventricle in MR Cardiac Images,” Proc. IEEE Workshop Variational and Level Set Methods, 2001.
[43] J. Rehg and T. Kanade, “Visual Tracking of High DoF Articulated Structures: An Application to Human Hand Tracking,” Proc. European Conf. Computer Vision, pp. 35-46, 1994.
[44] M. Rogers and J. Graham, “Robust Active Shape Model Search,” Proc. European Conf. Computer Vision, pp. 517-530, 2002.
[45] L.L. Scharf, Statistical Signal Processing. Reading, Mass.: Addison Wesley, 1991.
[46] C. Schmid, R. Mohr, and C. Bauckhage, “Evaluation of Interest Point Detectors,” Int'l J. Computer Vision, vol. 37, no. 2, pp. 151-172, 2000.
[47] P.H. Schonemann, “A Generalized Solution of the Orthogonal Procrustes Problem,” Psychometrika, vol. 31, pp. 1-10, 1966.
[48] J. Shi and C. Tomasi, “Good Features to Track,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 593-600, June 1994.
[49] E. Simoncelli, E. Adelson, and D. Heeger, “Probability Distributions of Optical Flow,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 310-315, June 1991.
[50] A. Singh, Optical Flow Computation: A Unified Perpective. Los Alamitos, Calif.: IEEE CS Press, 1992.
[51] A. Singh and P. Allen, “Image-Flow Computation: An Estimation-Theoretic Framework and a Unified Perspective,” CVGIP: Image Undestanding, vol. 56, no. 2, pp. 152-177, 1992.
[52] M. Suhling, M. Arigovindan, P. Hunziker, and M. Unser, “Motion Analysis of Echocardiograms Using a Local-Affine, Spatio-Temporal Model,” Proc. IEEE Int'l Symp. Biomedical Imaging: Macro to Nano, pp. 573-576, 2002.
[53] E. Trucco and A. Verri, Introductory Techniques for 3-D Computer Vision. Prentice Hall, 1998.
[54] M.A. Turk and A.P. Pentland, “Face Recognition Using Eigen-Face,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 586-591, 1991.
[55] S. Wang, X. Ji, and Z.-P. Liang, “Landmark-Based Shape Deformation with Topology-Preserving Constraints,” Proc. Int'l Conf. Computer Vision, 2003.
[56] B. Xie, D. Comaniciu, V. Ramesh, M. Simon, and T. Boult, “Component Fusion for Face Detection in the Presence of Heteroscedastic Noise,” Proc. Ann. Conf. German Soc. for Pattern Recognition, pp. 434-441, 2003.
[57] X.S. Zhou, D. Comaniciu, and S. Krishnan, “An Information Fusion Framework for Robust Shape Tracking,” Proc. Int'l Workshop Statistical and Computational Theories of Vision, 2003.
[58] X.S. Zhou, D. Comaniciu, and S. Krishnan, “Coupled-Contour Tracking through Non-Orthogonal Projections and Fusion for Echocardiography,” Proc. European Conf. Computer Vision, 2004.

Index Terms:
Shape tracking, subspace constraint, motion estimation with uncertainty, heteroscedastic noise, active shape model, model adaptation.
Citation:
Xiang Sean Zhou, Dorin Comaniciu, Alok Gupta, "An Information Fusion Framework for Robust Shape Tracking," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 1, pp. 115-129, Jan. 2005, doi:10.1109/TPAMI.2005.3
Usage of this product signifies your acceptance of the Terms of Use.