This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Closed-Form Solutions for Physically Based Shape Modeling and Recognition
July 1991 (vol. 13 no. 7)
pp. 715-729

The authors present a closed-form, physically based solution for recovering a three-dimensional (3-D) solid model from collections of 3-D surface measurements. Given a sufficient number of independent measurements, the solution is overconstrained and unique except for rotational symmetries. The proposed approach is based on the finite element method (FEM) and parametric solid modeling using implicit functions. This approach provides both the convenience of parametric modeling and the expressiveness of the physically based mesh formulation and, in addition, can provide great accuracy at physical simulation. A physically based object-recognition method that allows simple, closed-form comparisons of recovered 3-D solid models is presented. The performance of these methods is evaluated using both synthetic range data with various signal-to-noise ratios and using laser rangefinder data.

[1] T. Binford, "Visual perception by computer," presented at the IEEE conference on Systems and Control, Dec. 1971.
[2] D. Marr and K. Nishihara, "Representation and recognition of the spatial organization of three-dimensional shapes," inProc. of the Royal Society-London B, 1978.
[3] R. Mohan and R. Nevatia, "Using perceptual organization to extract 3D structures,"IEEE Trans. Patt. Anal. Mach. Intell., vol. 11, no. 11, pp. 1121-1139, Nov. 1989.
[4] A. P. Pentland, "Perceptual organization and the representation of natural form,"Artificial Intell., vol. 28, no. 3, pp. 293-331, 1986.
[5] A. Pentland, "Recognition by parts," inProc. First International Conf. Comput. Vision, (London, England), 1987, pp. 612-620.
[6] F. Solina and R. Bajcsy, "Recovery of parametric models from range images: The case for superquadrics with global deformations,"IEEE Trans. Patt. Anal. Mach. Intell., vol. 12, no. 2, pp. 131-147, 1990.
[7] T. Boult and A. Gross, "Recovery of superquadrics from depth information," inProc. of the AAAI Workshop on Spatial Reasoning and Multi-Sensor Fusion, Oct. 1987, pp. 128-137.
[8] I. Biederman, "Recognition-by-components: A theory of human image understanding,"Psychological Rev., vol. 94, no. 2, pp. 115-147, 1987.
[9] P. Winston, T. Binford, B. Katz, and M. Lowry, "Learning physical description from functional descriptions, examples, and precedents," inProc. of AAAI, 1983, pp. 433-439.
[10] D. Terzopoulos, A. Witkin, and M. Kass, "Symmetry-seeking models for 3-D object reconstruction,"Int. J. Comput. Vision, vol. 1, no. 3, pp. 211-221, 1987.
[11] A. Pentland, "Automatic extraction of deformable part models,"Int. J. Comput. Vision, vol. 4, pp. 107-126, 1990.
[12] A. Pentland and J. Williams, "Good vibrations: Modal dynamics for graphics and animation,"Comput. Graphics, vol. 23, no. 4, pp. 215-222, 1989.
[13] M. Leyton, "Perceptual organization as nested control,"Biological Cybernetics, vol. 51, pp. 141-153, 1984.
[14] D. Hoffman and W. Richards, "Parts of recognition," inFrom Pixels to Predicates(A. Pentland, Ed.), Norwood, NJ: Ablex, 1985.
[15] K. Bathe,Finite Element Procedures in Engineering Analysis, Englewood Cliffs, NJ: Prentice-Hall, 1982.
[16] A. Pentland, I. Essa, M. Freidmann, B. Horowitz, and S. Sclaroff, "The thingworld modeling system: Virtual sculpting by modal forces,"Comput. Graphics, vol. 24, no. 2, pp. 143-144, 1990.
[17] T. Darrell, S. Sclaroff, and A. Pentland, "Segmentation by minimal description," inProc. Third International Conf. Comput. Vision, Dec. 1990.
[18] L. Segerlind,Applied Finite Element Analysis, New York: Wiley, 1984.
[19] I. Essa, "Contact Detection, Collision Forces, and Friction for Physically-Based Virtual World Modeling," M.A. thesis, Dept. of Civil Engineering, M.I.T., 1990.

Index Terms:
shape recognition; picture processing; pattern recognition; shape modeling; 3-D surface; rotational symmetries; finite element method; solid modeling; parametric modeling; object-recognition; finite element analysis; pattern recognition; picture processing; solid modelling
Citation:
A. Pentland, S. Sclaroff, "Closed-Form Solutions for Physically Based Shape Modeling and Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 7, pp. 715-729, July 1991, doi:10.1109/34.85660
Usage of this product signifies your acceptance of the Terms of Use.