This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Elastically Adaptive Deformable Models
October 2002 (vol. 24 no. 10)
pp. 1310-1321

Abstract—We present a novel technique for the automatic adaptation of a deformable model's elastic parameters within a Kalman filter framework for shape estimation applications. The novelty of the technique is that the model's elastic parameters are not constant, but spatio-temporally varying. The variation of the elastic parameters depends on the distance of the model from the data and the rate of change of this distance. Each pass of the algorithm uses physics-based modeling techniques to iteratively adjust both the geometric and the elastic degrees of freedom of the model in response to forces that are computed from the discrepancy between the model and the data. By augmenting the state equations of an extended Kalman filter to incorporate these additional variables, we are able to significantly improve the quality of the shape estimation. Therefore, the model's elastic parameters are always initialized to the same value and they are subsequently modified depending on the data and the noise distribution. We present results demonstrating the effectiveness of our method for both two-dimensional and three-dimensional data.

[1] A. Blake and M. Isard, ”Three-Dimensional Position and Shape Input Using Video Tracking of Hands and Lips,” Proc. SIGGRAPH '94, pp. 185-192, 1994.
[2] A. Blake and A. Zisserman, Visual Reconstruction. MIT Press, 1987.
[3] R.M. Bolle and B.C. Vemuri, "On Three-Dimensional Surface Reconstruction Methods," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 1, Jan. 1991.
[4] T.J. Broida and R. Chellappa, "Estimation of Object Motion Parameters From Noisy Images," IEEE Trans. Pattern Analysis and Machine Intelligence, 1986, pp. 90-99.
[5] A. Chakraborty, M. Worring, and J.S. Duncan, "On Multi-Feature Integration for Deformable Boundary Finding," Proc. IEEE ICCV-95, pp. 846-861, 1995.
[6] L. D. Cohen,“On active contour models and balloons,” Computer Vision, Graphics, and Image Processing, vol. 53, No. 2, pp. 211-218, March 1991.
[7] H. Delingette, "Simplex Meshes: A General Representation for 3d Shape Reconstruction," Proc. Int'l Conf. Computer Vision and Pattern Recognition (CVPR '94),Seattle, Wash., 1994.
[8] E.D. Dickmanns and V. Graefe, “Applications of Dynamic Monocular Machine Vision,” Machine Vision and Applications, vol. 1, pp. 241-261, 1988.
[9] P. Fua and C. Brechbuhler, “Imposing Hard Constraints on Deformable Models through Optimization in Orthogonal Subspaces,” Computer Vision and Image Understanding, vol. 65, no. 2, pp. 148-162, Feb. 1997.
[10] A. Gelb, Applied Optimal Estimation. MIT Press, 1974.
[11] M.S. Grewal and A.P. Andrews,Kalman Filtering : Theory and Practice, Prentice Hall, 1993.
[12] W.C. Huang and D.B. Goldgof, “Adaptive-Size Meshes for Rigid and Nonrigid Shape Analysis and Synthesis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 6, pp. 611-616, June 1993.
[13] I.A. Kakadiaris, “Motion-Based Part Segmentation, Shape and Motion Estimation of Multi-Part Objects: Application to Human Body Tracking,” PhD dissertation, Dept. of Computer Science, Univ. of Pennsylvania, Philadelphia, Penn., Oct. 1996.
[14] I.A. Kakadiaris and D. Metaxas, “3D Human Body Model Acquisition from Multiple Views,” Proc. Int'l Conf. Computer Vision, pp. 618-623, June 1995.
[15] I.A. Kakadiaris and D. Metaxas, “3D Human Body Model Acquisition from Multiple Views,” Int'l J. Computer Vision, vol. 30, no. 3, pp. 191–218, 1998.
[16] I.A. Kakadiaris and D. Metaxas, “Model-Based Estimation of 3D Human Motion,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 12, pp. 1453-1459, 2000.
[17] I.A. Kakadiaris, D. Metaxas, and R. Bajcsy, “Inferring 2D Object Structure from the Deformation of Apparent Contours,” Computer Vision and Image Understanding, vol. 65, no. 2, pp. 129-147, 1997.
[18] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active Contour Models,” Proc. Int'l Conf. Computer Vision, pp. 259-268, June 1987.
[19] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active Contour Models,” Int'l J. Computer Vision, vol. 1, no. 4, pp. 321-331, 1988.
[20] O.V. Larsen, P. Radeva, and E. Marti, “Bounds on the Optimal Elasticity Parameters for a Snake,” Proc. Eighth Int'l Conf. Image Analysis and Processing, ICIAP '95, pp. 37-44, 1995.
[21] O.V. Larsen, P. Radeva, and E. Marti, “Guidelines for Choosing Optimal Parameters of Elasticity for Snakes,” Proc. Sixth Int'l Conf. Computer Analysis of Images and Patterns, pp. 106-113, 1995.
[22] D. Lee and T. Pavlidis,“One-dimensional regularization with discontinuities,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 10, pp. 822-829, 1986.
[23] C. Mandal, B.C. Vemuri, and H. Qin, “A New-Dynamic Fem-Based Subdivision Surface Model for Shape Recovery and Tracking in Medical Images,” Proc. Medical Image Computing and Computer-Assisted Intervention-MICCAI '98, pp. 753-760, 1998.
[24] C. Mandal, B.C. Vemuri, and H. Qin, “Shape Recovery Using Dynamic Subdivision Surfaces,” Proc. Int'l Conf. Computer Vision, pp. 805-810, Jan. 1998.
[25] L. Matthies, T. Kanade, and R. Szeliski, “Kalman Filter-Based Algorithms for Estimating Depth from Image Sequences,” Int'l J. Computer Vision, vol. 3, no. 3, pp. 209-238, Sept. 1989.
[26] T. McInerney and D. Terzopoulos, “A Dynamic Finite Element Surface Model for Segmentation and Tracking in Multidimensional Medical Images with Application to Cardiac 4D Image Analysis,” Computerized Medical Imaging and Graphics, vol. 19, no. 1, pp. 69-83, Jan. 1995.
[27] D. Metaxas, "Physics-based modeling of nonrigid objects for vision and graphics," PhD thesis, Dept. of Computer Science, Univ. of Toronto, 1992.
[28] D. Metaxas, Physics-Based Deformable Models: Applications to Computer Vision, Graphics and Medical Imaging. Kluwer-Academic, Nov. 1996.
[29] D. Metaxas and I.A. Kakadiaris, “Elastically Adaptive Deformable Models,” Proc. Fourth European Conf. Computer Vision (ECCV), vol. II, pp. 550-559, Apr. 1996.
[30] D. Metaxas, E. Koh, and N. Badler, “Multi-Level Shape Representation Using Global Deformations and Locally Adaptive Finite Elements,” Int'l J. Computer Vision, vol. 25, no. 1, pp. 42-46, Oct. 1997.
[31] D. Metaxas and D. Terzopoulos, “Shape and Non-Rigid Motion Estimation through Physics-Based Synthesis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 6, pp. 580-591, June 1993.
[32] J. Montagnat and H. Delingette, “Globally Constrained Deformable Models for 3D Object Reconstruction,” Signal Processing, vol. 71, no. 2, pp. 173-186, 1998.
[33] A. Pentland and B. Horowitz, “Recovery of Non-Rigid Motion and Structure,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 7, pp. 730-742, July 1991.
[34] A. Pentland and S. Sclaroff, "Closed-Form Solutions for Physically-Based Shape Modeling and Recognition," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 7, pp. 715-729, July 1991.
[35] R. Samadani, “Adaptive Snakes: Control of Damping and Material Parameters,” Proc. SPIE Geometric Methods in Computer Vision, no. 1570, 1991.
[36] S. Sclaroff and L. Liu, “Deformable Shape Detection and Description via Model-Based Region Grouping,” Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 5, pp. 475-489, May 2001.
[37] D. Shen and C. Davatzikos, “An Adaptive-Focus Deformable Model Using Statistical and Geometric Information,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 906-913, Aug. 2000.
[38] A. Singh, D. Goldgof, and D. Terzopoulos, Deformable Models in Medical Image Analysis. Los Alamitos, Calif.: IEEE CS, 1998.
[39] F. Solina and R. Bajcsy,“Recovery of parametric models from range images: The case for superquadrics with global deformations,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, pp. 131-147, Feb. 1990.
[40] G. Sparr, “A Common Framework for Kinetic Depth, Reconstruction and Motion for Deformable Objects,” Proc. Third European Conf. Computer Vision, pp. 471-482, May 1994.
[41] L.H. Staib and J.S. Duncan, “Boundary Finding with Parametrically Deformable Models,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 11, pp. 1,061-1,075, Nov. 1992.
[42] D. Terzopoulos, "The Computation of Visible Surface Representations," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 10, no. 4, pp. 417-438, Apr. 1988.
[43] D. Terzopoulos, "Regularization of Inverse Visual Problems Involving Discontinuities," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, no. 4, pp. 413-424, 1986.
[44] D. Terzopoulos and D. Metaxas, “Dynamic 3D Models with Local and Global Deformations: Deformable Superquadrics,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 7, pp. 703-714, July 1991.
[45] D. Terzopoulos, A. Witkin, and M. Kass, “Symmetry-Seeking Models and 3D Object Reconstruction,” Int'l J. Computer Vision, vol. 1, no. 3, pp. 211-221, 1987.
[46] D. Terzopolous, A. Witkin, and M. Kass, "Constraints on deformable models: Recovering 3D shape and nonrigid motion, AI, no. 36, pp. 91-123, 1988.
[47] M. Vasilescu and D. Terzopoulos, “Adaptive Meshes and Shells: Irregular Triangulation, Discontinuities and Hierarchical Subdivision,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 829-832, June 1992.
[48] B.C. Vemuri and Y. Guo, “Pedal Snakes: Geometric Models with Physics-Based Control,” Proc. IEEE Int'l Conf. Computer Vision, pp. 427-432, Jan. 1998.
[49] B.C. Vemuri, Y. Guo, S.H. Lai, and C.M. Leonard, “Fast Numerical Algorithms for Fitting Hybrid Shape Models to Brain MRI,” Medical Image Analysis, vol. 1, no. 4 pp. 343-362, 1997.
[50] B. C. Vemuri and R. Malladi,“Constructing intrinsic parameters with active models for invariant surface reconstruction,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 15, No. 7, pp. 668-681, July 1993.
[51] B.C. Vemuri and A. Radisavljevic, “Multiresolution Stochastic Hybrid Shape Models with Fractal Priors,” ACM Trans. Graphics, vol. 13, no. 2, pp. 177-207, Apr. 1994.
[52] G. Wahba, Spline Models for Observational Data. SIAM, 1990.
[53] Y.F. Wang and J.-F. Wang, "Surface reconstruction using deformable models with interior and boundary constraints," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 5, pp. 572-579, 1992.
[54] R. Whitaker, “Algorithms for Implicit Deformable Models,” Proc. Fifth Int'l Conf. Computer Vision, pp. 822-827, June 1995.
[55] G. Whitten, "Scale Space Tracking and Deformable Sheet Models for Computational Vision," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 7, pp. 697-706, July 1993.
[56] C. Xu and J.L. Prince, “Generalized Gradient Vector Flow External Forces for Active Contours,” Signal Processing, pp. 131-139, Dec. 1998.
[57] L. Zhou and C. Kambhamettu, “Extending Superquadrics with Exponent Functions: Modeling and Reconstruction,” Graphical Models and Image Processing, vol. 63, no. 1, pp. 1-20, 2001.
[58] O. Zienkiewicz, The Finite Element Method. McGraw-Hill, 1977.

Index Terms:
Adaptive elastic parameters, deformable models, shape estimation, physics-based modeling, Kalman filter.
Citation:
Dimitris N. Metaxas, Ioannis A. Kakadiaris, "Elastically Adaptive Deformable Models," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 10, pp. 1310-1321, Oct. 2002, doi:10.1109/TPAMI.2002.1039203
Usage of this product signifies your acceptance of the Terms of Use.