This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Shape Evolution With Structural and Topological Changes Using Blending
November 1998 (vol. 20 no. 11)
pp. 1186-1205

Abstract—This paper describes a framework for the estimation of shape from sparse or incomplete range data. It uses a shape representation called blending, which allows for the geometric combination of shapes into a unified model—selected regions of the component shapes are cut-out and glued together. Estimation of shape using this representation is realized using a physics-based framework, and also includes a process for deciding how to adapt the structure and topology of the model to improve the fit. The blending representation helps avoid abrupt changes in model geometry during fitting by allowing the smooth evolution of the shape, which improves the robustness of the technique. We demonstrate this framework with a series of experiments showing its ability to automatically extract structured representations from range data given both structurally and topologically complex objects.

[1] 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.
[2] D. Metaxas, Physics-Based Deformable Models: Applications to Computer Vision, Graphics, and Medical Imaging. Kluwer Academic Publishers, 1996.
[3] T. Binford, "Visual Perception by Computer," IEEE Conf. Systems and Control, Dec. 1971.
[4] D. Marr and K. Nishihara, "Representation and Recognition of the Spatial Organization of Three-Dimensional Shapes," Proc. Royal Soc. London, vol. 200, pp. 269-294, 1978.
[5] T. O'Donnell, T. Boult, X. Fang, and A. Gupta, "The Extruded Generalized Cylinder: A Deformable Model for Object Recovery," Computer Vision and Pattern Recognition '94, pp. 174-181, 1994.
[6] I. Biederman, "Recognition-by-Components: A Theory of Human Image Understanding," Psychological Rev., vol. 94, pp. 115-147, Apr. 1987.
[7] A. Pentland, "Perceptual Organization and the Representation of Natural Form," Artificial Intelligence, vol. 28, pp. 293-331, 1986.
[8] 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.
[9] A.J. Hanson, "Hyperquadrics: Smoothly Deformable Shapes With Convex Polyhedral Bounds," Computer Vision, Graphics and Image Processing, vol. 44, pp. 191-210, 1988.
[10] S. Han, D.B. Goldgof, and K.W. Bowyer, “Using Hyperquadrics for Shape Recovery from Range Data,” IEEE Proc. Third Int'l Conf. Computer Vision, pp. 492-496, 1993.
[11] G. Taubin, "An improved algorithm for algebraic curve and surface fitting," Proc. Fourth Int'l Conf. Computer Vision, pp. 658-665,Berlin, Germany, May 1993.
[12] 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.
[13] H. Hoppe, T. DeRose, T. Duchamp, J. McDonald, and W. Stuetzle, "Surface Reconstruction From Unorganized Points," SIGGRAPH '92, vol. 26, pp. 71-78, July 1992.
[14] C. Liao and G. Medioni, "Surface Approximation of Complex Multipart Objects," IEEE Workshop on Physics-Based Modeling in Computer Vision, pp. 2-8, 1995.
[15] T. McInerney and D. Terzopoulos, "Topology Adaptive Snakes," Medical Image Analysis, to appear.
[16] D. Terzopoulos, A. Witkin, and M. Kass, "Constraints on Deformable Models: Recovering 3D Shape and Nonrigid Motion," Artificial Intelligence, vol. 36, no. 1, pp. 91-123, 1988.
[17] R. Malladi, J. Sethian, and B.C. Vemuri, "Shape Modeling with Front Propagation: A Level Set Approach," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, pp. 158-175, 1995.
[18] R. Whitaker, “Algorithms for Implicit Deformable Models,” Proc. Fifth Int'l Conf. Computer Vision, pp. 822-827, June 1995.
[19] R. Szeliski, D. Tonnesen, and D. Terzopoulos, "Modeling Surfaces of Arbitrary Topology with Dynamic Particles," Proc. IEEE Computer Vision and Pattern Recognition, pp. 82-85,New York, NY, June 1993.
[20] D. DeCarlo and D. Metaxas, "Blended Deformable Models," Computer Vision and Pattern Recognition '94, pp. 566-572, 1994.
[21] D. DeCarlo and D. Metaxas, “Blended Deformable Models,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, pp. 443-448, 1996.
[22] D. DeCarlo and D. Metaxas, "Adaptive Shape Evolution Using Blending," IEEE Proc. Int'l Conf. Computer Vision, pp. 834-839, 1995.
[23] 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.
[24] 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.
[25] B.C. Vemuri and A. Radisavljevic, “From Global to Local, a Continuum of Shape Models with Fractal Priors,” Proc. Conf. on Computer Vision and Pattern Recognition (CVPR '93), IEEE CS Press, Los Alamitos, Calif., 1993, pp. 307–313.
[26] D.D. Hoffman and W.A. Richards, "Parts of Recognition," Cognition, vol. 18, pp. 65-96, 1985.
[27] D. Marr, Vision, W.H. Freeman, 1982.
[28] A. Gupta and R. Bajcsy, "Volumetric Segmentation of Range Images of 3D Objects Using Superquadric Models," Computer Vision, Graphics and Image Processing, vol. 58, pp. 302-326, 1993.
[29] P.J. Besl and R.C. Jain,“Segmentation through variable-order surface fitting,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 10, no. 2, pp. 167-191, Mar. 1988.
[30] T. Horikoshi and S. Suzuki, "3D Parts Decomposition from Sparse Range Data Using Information Criterion," Proc. 1993 IEEE Conf. Computer Vision and Pattern Recognition, pp. 168-173,New York, June 1993.
[31] A. Leonardis, A. Jaklic, and F. Solina, "Superquadrics for Segmenting and Modeling Range Data," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 11, pp. 1,289-1,295, Nov. 1997.
[32] S. Muraki, "Volumetric Shape Description of Range Data Using 'Blobby Model,'" SIGGRAPH '91, vol. 25, pp. 227-235, July 1991.
[33] Y. Sato, J. Ohya, and K. Ishii, "Recovery of Hierarchical Part Structure of 3D Shape From Range Image," Computer Vision and Pattern Recognition '92, pp. 699-702, 1992.
[34] F.P. Ferrie, J. Lagarde, and P. Whaite, "Darboux Frames, Snakes and Superquadrics: Geometry from the Bottom Up," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 8, pp. 771-784, Aug. 1993.
[35] A. Lejeune and F. Ferrie, "Partioning Range Images Using Curvature and Scale," Proc. 1993 IEEE Conf. Computer Vision and Pattern Recognition, pp. 800-801,New York, June 1993.
[36] K. Siddiqi and B.B. Kimia, “Parts of Visual Form: Computational Aspects,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 3, Mar. 1995.
[37] S. Kumar and D. Goldgof, "Model Based Part Segmentation of Range Data: Hyperquadrics and Dividing Planes," IEEE Workshop on Physics-Based Modeling in Computer Vision, pp. 17-23, 1995.
[38] V. Guillemin and A. Pollack, Differential Topology. Prentice-Hall, 1974.
[39] C. Grimm and J. Hughes, "Modeling Surfaces of Arbitrary Topology Using Manifolds," SIGGRAPH '95, 1995, pp. 359-368.
[40] L.E.J. Brouwer, Collected Works Volume 2: Geometry, Analysis, Topology, and Mechanics. North-HollandPub. Co., 1976.
[41] M. Rutishauser, M. Stricker, and M. Trobina, "Merging Range Images of Arbitrarily Shaped Objects," Proc. IEEE Computer Vision and Pattern Recognition, pp. 573-580, 1994.
[42] W. Massey, Algebraic Topology: An Introduction, 2nd ed. Springer Verlag, 1987.
[43] D. DeCarlo and J. Gallier, "Topological Evolution of Surfaces," Graphics Interface '96, pp. 194-203, 1996.
[44] J.J. Koenderink, Solid Shape. MIT Press, 1990.
[45] A. Barr, "Superquadrics and Angle-Preserving Transformations," IEEE Computer Graphics and Applications, vol. 1, no. 1, pp. 11-23, 1981.
[46] D. Terzopoulos, A. Witkin, and M. Kass, "Symmetry-Seeking Models and 3D Object Reconstruction," IJCV, vol. 1, no. 3, pp. 211-221, 1987.
[47] C. Liao and G. Medioni, "Simulataneous Segmentation and Approximation of Complex Patterns," Computer Vision and Pattern Recognition '94, pp. 617-623, 1994.
[48] G. Lee and G. Stockman, "Obtaining Registered Range and Intensity Images Using the Technical Arts Scanner," Tech. Rep. CPS-91-08, Dept. of Computer Science, Michigan State Univ., 1991.
[49] G. Farin, Curves and Surfaces for Computer Aided Geometric Design. Academic Press, 1993.

Index Terms:
Shape blending, shape estimation from range data, shape evolution, deformable models, shape representation
Citation:
Douglas DeCarlo, Dimitris Metaxas, "Shape Evolution With Structural and Topological Changes Using Blending," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 11, pp. 1186-1205, Nov. 1998, doi:10.1109/34.730554
Usage of this product signifies your acceptance of the Terms of Use.