This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Curvature-Based Algorithms for Nonrigid Motion and Correspondence Estimation
October 2003 (vol. 25 no. 10)
pp. 1349-1354

Abstract—We present a novel technique for utilizing the Gaussian curvature information in 3D nonrigid motion estimation in the absence of known correspondence. Differential-geometric constraints derived in the paper allow one to estimate parameters of the local affine motion model given the values of Gaussian curvature before and after motion. These constraints can be further combined with the previously known constraints based on the unit normals before and after motion. Our experiments demonstrate that the resulting hybrid algorithm is more accurate than each of its constituents and more accurate than the classical ICP algorithm. We also present a technique for curvilinear orthogonalization of quadratic Monge patches that is essential in our derivation and useful in other applications.

[1] J.K. Aggarwal, Q. Cai, W. Liao, and B. Sabata, Articulated and Elastic Non-Rigid Motion: A Review Proc. IEEE Computer Soc. Workshop Motion of Non-Rigid and Articulated Objects, pp. 16-22, 1994.
[2] A.A. Amini and J.S. Duncan, Bending and Stretching Models for LV Wall Motion Analysis from Curves and Surfaces Image and Vision Computing, vol. 10, no. 6, pp. 418-430, 1992.
[3] A.A. Amini and J.S. Duncan, Differential Geometry for Characterizing 3D Shape Change Proc. SPIE: Math. Methods in Medical Imaging, vol. 1786, pp. 170-181, 1992.
[4] A.A. Amini, R.L. Owen, P. Anandan, and J.S. Duncan, Non-Rigid Motion Models for Tracking the Left-Ventricular Wall Proc. Int'l Conf. Information Processing in Medical Imaging, pp. 343-357, 1991.
[5] E. Angelopoulou and L.B. Wolff, “Sign of Gaussian Curvature from Curve Orientation in Photometric Space,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 10, pp. 1,056-1,066, Oct.. 1998.
[6] P.J. Besl and R.C. Jain, Invariant Suarace Characteristics for 3-D Object Recognition in Range Images Computer Vision, Graphics, and Image Processing: Image Understanding, pp. 33-80, 1986.
[7] P.J. Besl and N.D. McKay, "A Method for Registration of 3D Shapes," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 239-256, Feb. 1992.
[8] S.S. Chen and M. Penna, Motion Analysis of Deformable Objects Advances in Computer Vision and Image Processing, T.S. Huang, ed., vol. 3, pp. 179-220, JAI Press, 1988.
[9] Y. Chen and G. Medioni, Object Modeling by Registration of Multiple Range Images Int'l J. Computer Vision, vol. 10, no. 3, pp. 145-155, 1992.
[10] I. Cohen, N. Ayache, and P. Sulger, Tracking Points on Deformable Objects Using Curvature Information Proc. European Conf. Computer Vision, pp. 458-466, 1992.
[11] R. Courant and F. John, Introduction to Calculus and Analysis. John Wiley and Sons 1974.
[12] D. DeCarlo and D. Metaxas, Adjusting Shape Parameters Using Model-Based Optical Flow Residuals IEEE Trans. Pattern Analysis and Machine Intelligence, pp. 814-823, 2002.
[13] F. Devernay and O.D. Faugeras, "Computing Differential Properties of 3D Shapes from Stereoscopic Images Without 3D Models," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 208-213, 1994.
[14] M.P. DoCarmo, Differential Geometry of Curves and Surfaces. Prentice-Hall, 1976.
[15] I. Douros and B. Buxton, Three-Dimensional Surface Curvature Estimation Using Quadric Surface Patches Scanning 2002, 2002, in press.
[16] J. Feldmar and N. Ayache, Rigid, Affine and Locally Affine Registration of Free-Form Surfaces Technical Report 2200, INRIA, 1994.
[17] J. Feldmar and N. Ayache, Rigid, Affine and Locally Affine Registration of Free-Form Surfaces Int'l J. Computer Vision, vol. 18, no. 2, May 1996.
[18] P.J. Flynn and A.K. Jain, On Reliable Curvature Estimation Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 110-116, 1989.
[19] D.B. Goldgof, H. Lee, and T.S. Huang, Motion Analysis of Non-Rigid Surfaces Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 375-380, 1988.
[20] T.S. Huang, Modeling, Analysis and Visualization of Nonrigid Object Motion Proc. Int'l Conf. Pattern Recognition, pp. 361-364, 1990.
[21] C. Kambhamettu and D.B. Goldgof, Towards Finding Point Correspondences in Non-Rigid Motion Proc. Scandinavian Conf. Image Analysis, pp. 1126-1133, 1991.
[22] C. Kambhamettu and D.B. Goldgof, Point Correspondence Recovery in Non-Rigid Motion Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 222-227, 1992.
[23] C. Kambhamettu and D.B. Goldgof, Curvature-Based Approach to Point Correspondence Recovery in Conformal Non-Rigid Motion Computer Vision, Graphics and Image Processing: Image Understanding, vol. 60, no. 1, pp. 26-43, 1994.
[24] C. Kambhamettu, D.B. Goldgof, and M. He, Determination of Motion Parameters and Estimation of Point Correspondences in Small Non-Rigid Deformations Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 943-946, 1994.
[25] C. Kambhamettu, D.B. Goldgof, M. He, and P. Laskov, 3D Nonrigid Motion Analysis under Small Deformations Image and Vision Computing J., vol. 21, no. 3, pp. 229-245, Mar. 2003.
[26] C. Kambhamettu, D.B. Goldgof, D. Terzopoulos, and T.S. Huang, Nonrigid Motion Analysis Handbook of Pattern Recognition and Image Processing: Computer Vision, chapter 11, pp. 405-430, Academic Press, 1994.
[27] J.J. Koenderink and A.J. van Doorn, Depth and Shape from Different Perspective in the Presence of Bending Deformations J. Optical Soc. Am., vol. 3, pp. 242-249, Feb. 1986.
[28] P. Laskov, Extensions of Differential-Geometric Algorithms for Estimation of 3D Non-Rigid Motion and Correspondence PhD thesis, Univ. of Delaware, 2001.
[29] P. Laskov and C. Kambhamettu, Comparison of 3D Algorithms for Non-Rigid Motion and Correspondence Estimation Proc. British Machine Vision Conf., pp. 273-282, 2001.
[30] P. Laskov and C. Kambhamettu, Curvature-Based Algorithms for Non-Rigid Motion and Correspondence Estimation Proc. Fifth Asian Conf. Computer Vision, vol. 1, pp. 19-26, Jan. 2002.
[31] H. Lütkepohl, Handbook of Matrices. John Wiley and Sons, 1996.
[32] J.R. Magnus and H. Neudecker, Matrix Differential Calculus with Applications in Statistics and Econometrics. John Wiley and Sons, 1988.
[33] 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.
[34] S.K. Mishra, D.B. Goldgof, T.S. Huang, and C. Kambhamettu, Curvature-Based Non-Rigid Motion Analysis from 3D Point Correspondences Int'l J. Imaging Systems and Technology, vol. 4, pp. 214-225, 1992.
[35] 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.
[36] P. Shi, A.J. Sinusas, R.T. Constable, E. Ritman, and J.S. Duncan, Point-Tracked Quantitative Analysis of Left-Ventricular Surface Motion from 3D Images Sequences IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 1, pp. 36-50, Jan. 2000.
[37] C.K. Tang and G. Medioni, Robust Estimation of Curvature Information from Noisy 3D Data for Shape Description Proc. Int'l Conf. Computer Vision, pp. 426-433, 1999.
[38] H. Tao and T. Huang, Explanation-Based Facial Motion Tracking Using a Piecewise Bezier Volume Deformation Model Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 611-617, 1999, full system presented in Int'l J. Computer Vision, 2002.
[39] H. Tao and T. Huang, Visual Estimation and Compression of Facial Motion Parameters Elements of a 3D Model-Based Video Coding System Int'l J. Computer Vision, no. 2, pp. 111-125, Nov. 2002.
[40] D. Terzopoulos, A. Witkin, and M. Kass, Constraints on Deformable Models: Recovering 3D Shape and Nonrigid Motion Artificial Intelligence, vol. 36, pp. 91-123, Jan. 1988.
[41] E. Trucco and R.B. Fisher, "Experiments in Curvature-Based Segmentation of Range Data," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 2, pp. 177-181, Feb. 1995.
[42] Y. Wang, B.S. Peterson, and L.H. Staib, Shape-Based 3D Surface Correspoondence Using Geodesics and Local Geometry Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 644-651, 2000.
[43] C.E. Weatherburn, Differential Geometry of Three Dimensions. Cambridge Univ. Press, 1927.
[44] H. Yahia, E. Huot, I. Herlin, and I. Cohen, Geodesic Distance Evolution of Surfaces: A New Method for Matching Surfaces Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 663-668, 2000.
[45] L. Zhou and C. Kambhamettu, Hierarchical Structure and Nonrigid Motion Recovery from 2D Monocular Views Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 752-759, 2000.
[46] L. Zhou, C. Kambhamettu, D. Goldgof, K. Palaniappan, and A.F. Hasler, Tracking Nonrigid Motion and Structure from 2D Satellite Cloud Images without Correspondences IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 11, pp. 1330-1336, Nov. 2001.

Index Terms:
Nonrigid motion, correspondence estimation, differential geometry, Gaussian curvature.
Citation:
Pavel Laskov, Chandra Kambhamettu, "Curvature-Based Algorithms for Nonrigid Motion and Correspondence Estimation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 10, pp. 1349-1354, Oct. 2003, doi:10.1109/TPAMI.2003.1233911
Usage of this product signifies your acceptance of the Terms of Use.