This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Using Geometric Distance Fits for 3-D Object Modeling and Recognition
December 1994 (vol. 16 no. 12)
pp. 1183-1196

Addresses the problems of automatically constructing algebraic surface models from sets of 2D and 3D images and using these models in pose computation, motion and deformation estimation, and object recognition. We propose using a combination of constrained optimization and nonlinear least-squares estimation techniques to minimize the mean-squared geometric distance between a set of points or rays and a parameterized surface. In modeling tasks, the unknown parameters are the surface coefficients, while in pose and deformation estimation tasks they represent the transformation which maps the observer's coordinate system onto the modeled surface's own coordinate system. We have applied this approach to a variety of real range, computerized tomography and video images.

[1] N. Ahuja and J. Veensra, "Generating octrees from object silhouettes in orthographic views,"IEEE Trans. Pattern Anal. Machine Intell., vol. 11, no. 2, pp. 137-149, 1989.
[2] A. A. Amini and J. Duncan, "Pointwise tracking of left-ventricular motion in 3-D," inProc. IEEE Workshop on Visual Motion, pp. 294-299, 1991.
[3] R. Bajcsy and F. Solina, "Three-dimensional object representation revisited," inProc. Int. Conf. Comp. Vision, London, June 1987, pp. 231-240.
[4] B. G. Baumgart, "Geometric modeling for computer vision," Ph.D. dissertation, Dept. of Computer Science, Stanford Univ., Stanford, CA, Tech Rep. AIM-249, 1974.
[5] L. Brunie, S. Lavallée, and R. Szeliski, "Using force fields derived form 3-D distance maps for infering the attitude of a 3-D rigid object," in G. Sandini, Ed.,Proc. European Conf. Comp. Vision, vol. 588 ofLecture Notes in Computer Science. New York: Springer, 1992, pp. 670-675.
[6] C. W. Chen and T. S. Huang, "'Non-rigid object motion and deformation estimation from three-dimensional data,"Int. J. Imaging Syst. Technol., pp. 385-394, 1990.
[7] C. I. Connolly and J. R. Stenstrom, "3-D scene reconstruction from multiple intensity images," inProc. IEEE Workshop on Interpretation of 3-D Scenes, Austin, TX, Nov. 1989, pp. 124-130.
[8] O. D. Faugeras and M. Hebert, "The representation, recognition, and locating of 3-D objects,"Int. J. Robotics Res., vol. 5, no. 3, Fall 1986, pp. 27-52.
[9] A. D. Gross and T. E. Boult, "Error of fit measures for recovering parametric solids," inProc. 2nd Int. Conf. Comput. vision, Dec. 1988, pp. 690-694.
[10] K. T. Gunnarsson and F. B. Prinz, "CAD model-based localization of parts in manufacturing,"IEEE Comput., vol. 20, no. 8, pp. 66-74, Aug. 1987.
[11] A. Gupta, L. Bologni, and R. Bajcsy, "Quantitative and qualitative measures for the evaluation of the superquadric models," inProc. IEEE Workshop on Interpretation of 3-D Scenes, Austin, TX, Nov. 1989, pp. 162-169.
[12] W. E. Higgins, N. Chung, and E. L. Ritman, "Extraction of left ventricle chamber from 3-D CT images of the heart,"IEEE Trans Medical Imaging, vol. 9, pp. 384-395, 1990.
[13] C. Kambhamettu and D. B. Goldgof, "Point correspondence recovery in nonrigid motion," inProc. IEEE Conf. Computer Vision and Pattern Recognition, Champaign, IL, 1992, pp. 222-227.
[14] D. J. Kriegman and J. Ponce, "On rccognizing and positioning curved 3-D objects from image contours,"IEEE Trans. Pattern Anal. Machine Intell., vol. 12, no. 12, pp. 1127-1137, Dec. 1990.
[15] D. G. Luenberger,Linear and Nonlinear Programming. Addison-Wesley, 1984, second ed.
[16] J. J. Moré, B. S. Garbow, and K. E. Hillstrom, "User guide for MINPACK 1," Argonne National Laboratories, ANL-80-74, 1980.
[17] A. P. Pentland, "Recognition by parts," inProc. Int. Conf. Comp. Vision, pp. 612-620, 1987.
[18] V. Pratt, "Direct least squares fitting of algebraic surfaces,Comput. Graphics, vol. 21, no. 4, pp. 145-152, July 1987.
[19] R. Ritman and L. Harris,Imaging Physiological Functions: Experience with the Dynamic Spatial Reconstructor. Praeger: 1975.
[20] S. Srivastava and N. Ahuja, "Octree generation from object silhouettes in perspective views,"Comput. Vision Graphics Image Processing, vol. 49, No. 1, pp. 68-84, 1990.
[21] G. Strang,Linear Algebra and its Applications. Academic, 1980, second ed.
[22] S. Sullivan, L. Sanford, and J. Ponce, "On using geometric distance fits to estimate 3-D object shape, pose, and deformation from range, CT, and video images," inProc. IEEE Conf. Computer Vision and Pattern Recognition, New York, June 1993, pp. 110-116.
[23] G Taubin, "Estimation of planar curves, surfaces, and nonplanar space curves defined by implicit equations, with applications to edge and range image segmentation,"IEEE Trans. Pattern Anal. Machine Intell., vol. 13, no. 11, pp. 1115-1138, 1991.
[24] G. Taubin, F. Cukierman, S. Sullivan, J. Ponce, and D. J. Kriegman, "Parameterizing and fitting bounded algebraic curves and surfaces," inProc. CVPR, 1992, pp. 103-109.
[25] R.Y. Tsai, "A Versatile Camera Calibration Technique for High-Accuracy 3D Machine Vision Metrology Using Off-the-Shelf TV Cameras and Lenses,"IEEE J. of Robotics and Automation, Vol. RA-3, No. 4, Aug. 1987, pp. 323-344.
[26] N. Yokota, M. Kaneta, and K. Yamamoto, "Recovery of superquadric primitives from a range image using simulated annealing," inProc. IEEE 11th Int. Conf. Pattern Recognition, The Hague, Netherlands, Aug. 1992, pp. 168-172.

Index Terms:
object recognition; solid modelling; algebra; deformation; geometric distance fits; 3D object modeling; 3D object modeling and recognition; algebraic surface models; automatic model construction; pose computation; motion estimation; deformation estimation; constrained optimization; nonlinear least-squares estimation techniques; mean-squared geometric distance minimization; point set; ray set; parameterized surface; unknown parameters; surface coefficients; transformation mapping; coordinate system; range images; computerized tomography images; video images; implicit algebraic surfaces
Citation:
S. Sullivan, L. Sandford, J. Ponce, "Using Geometric Distance Fits for 3-D Object Modeling and Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 12, pp. 1183-1196, Dec. 1994, doi:10.1109/34.387489
Usage of this product signifies your acceptance of the Terms of Use.