This Article 
 Bibliographic References 
 Add to: 
Fitting Parameterized Three-Dimensional Models to Images
May 1991 (vol. 13 no. 5)
pp. 441-450

Model-based recognition and motion tracking depend upon the ability to solve for projection and model parameters that will best fit a 3-D model to matching 2-D image features. The author extends current methods of parameter solving to handle objects with arbitrary curved surfaces and with any number of internal parameters representing articulation, variable dimensions, or surface deformations. Numerical stabilization methods are developed that take account of inherent inaccuracies in the image measurements and allow useful solutions to be determined even when there are fewer matches than unknown parameters. The Levenberg-Marquardt method is used to always ensure convergence of the solution. These techniques allow model-based vision to be used for a much wider class of problems than was possible with previous methods. Their application is demonstrated for tracking the motion of curved, parameterized objects.

[1] T. O. Binford, "Visual perception by computer," presented at IEEE Systems Sci. and Cybern. Conf., Miami, FL, 1971.
[2] A. J. Bray, "Tracking objects using image disparities,"Image Vision Comput., vol. 8, no. 1, pp. 4-9, 1990.
[3] R. A. Brooks, "Symbolic reasoning among 3-D models and 2-D images,"Artificial Intell., vol. 17, pp. 285-348, 1981.
[4] M. Dhome, M. Richetin, J. T. Lapresté, and G. Rives, "Determination of the attitude of 3-D objects from a single perspective view,"IEEE Trans. Pattern Anal. Machine Intell., vol. 11, no. 12, pp. 1265-1278, 1989.
[5] 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.
[6] M. A. Fischler and R. C. Bolles, "Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography,"Commun. ACM, vol. 24, no. 6, pp. 381-395, 1981.
[7] C. Goad, "Special purpose automatic programming for 3D model-based vision," inFrom Pixels to Predicates, A. Pentland, Ed. Norwood, NJ: Ablex, 1986, pp. 371-391.
[8] R. R. Goldberg and D. G. Lowe, "Verification of 3-D parametric models in 2-D image data," inProc. IEEE Workshop Computer Vision, Miami, FL, Nov. 1987, pp. 255-257.
[9] G. H. Golub and C. F. Van Loan,Matrix Computations, 2nd ed. Baltimore, MD: Johns Hopkins Press, 1989.
[10] E. Grimson and T. Lozano-Pérez, "Model-based recognition and localization from sparse range or tactile data,"Int. J. Robotics Res., vol. 3, pp. 3-35, 1984.
[11] R. M. Haralick,et al., "Pose estimation from corresponding point data,"IEEE Trans. Syst., Man, Cybern., vol. 19, no. 6, pp. 1426-1446, 1989.
[12] R. Horaud, B. Conio, O. Leboulleux, and B. Lacolle, "An analytic solution for the perspective 4-point problem," inProc. Conf. Computer Vision and Pattern Recognition, San Diego, CA, June 1989, pp. 500-507.
[13] D. P. Huttenlocher and S. Ullman, "Object recognition using alignment," inProc. Int. Conf. Computer Vision, London, June 1987, pp. 102-111.
[14] M. Ishii, S. Sakane, M. Kakikura, and Y. Mikami, "A 3-D sensor system for teaching robot paths and environments,"Int. J. Robotics Res., vol. 6, no. 2, pp. 45-59, 1987.
[15] R. Kumar, "Determination of camera location and orientation," inProc. DARPA Image Understanding Workshop, Palo Alto, CA, 1989, pp. 870-879.
[16] C. L. Lawson and R. J. Hanson,Solving Least Squares Problems. Englewood Cliffs, NJ: Prentice-Hall, 1974.
[17] K. Levenberg, "A method for the solution of certain non-linear problems in least squares,"Quart. Appl. Math., vol. 2, pp. 164-168, 1944.
[18] Y. Liu, T. S. Huang, and O. D. Faugeras, "Determination of camera location from 2-D to 3-D line and point correspondences,"IEEE Trans. Pattern Anal. Machine Intell., vol. 12, no. 1, pp. 28-37, 1990.
[19] D. G. Lowe, "Solving for the parameters of object models from image descriptions," inProc. ARPA Image Understanding Workshop, College Park, MD, Apr. 1980, pp. 121-127.
[20] D. Lowe, Perceptual Organization And Visual Recognition. Boston: Kluwer, 1985.
[21] D. G. Lowe, "Three-dimensional object recognition from single two-dimensional images,"Artificial Intell., vol. 31, 1987.
[22] D. G. Lowe, "The viewpoint consistency constraint,"Int. J. Computer Vision, vol. 1, no. 1, pp. 57-72, 1987.
[23] D. G. Lowe, "Organization of smooth image curves at multiple scales,"Int. J. Computer Vision, vol. 3, no. 2, pp. 119-130, June 1989.
[24] D. W. Marquardt, "An algorithm for least-squares estimation of nonlinear parameters,"J. Soc. Indust. Applied Math., vol. 11, no. 2, pp. 431-441, 1963.
[25] D. Marr and E. Hildreth, "Theory of edge detection,"Proc. Roy. Soc. London B, vol. 207, pp. 187-217, 1980.
[26] A. M. McIvor, "An analysis of Lowe's model-based vision system," inProc. 4th Alvey Vision Conf., Univ. Manchester, U.K., Aug. 1988, pp. 73-78.
[27] A. P. Pentland, "Perceptual organization and the representation of natural form,"Artificial Intell., vol. 28, no. 3, pp. 293-331, 1986.
[28] T. Poggio, V. Torre, and C. Koch, "Computational vision and regularization theory,"Nature, vol. 317, pp. 314-319, 1985.
[29] J. Ponce and D. J. Kriegman, "On recognizing and positioning curved 3D objects from image contours," inProc. DARPA Image Understanding Workshop, Palo Alto, CA, 1989, pp. 461-470.
[30] L. G. Roberts, "Machine perception of three-dimensional solids," inOptical and Electro-optical Information Processing, J. Tippetet al. Eds. Cambridge, MA: MIT Press, 1965, pp. 159-197.
[31] I. Rock,The Logic of Perception. Cambridge, MA: MIT Press, 1983.
[32] D. W. Thompson and J. L. Mundy, "Model-based motion analysis: Motion from motion," inRobotics Research: 4th Int. Symp., R. Bolles and B. Roth, Eds. Cambridge, MA: MIT Press, 1988, pp. 299-309.
[33] A. N. Tikhonov and V.Y. Arsenin,Solutions of Ill-Posed Problems. Washington, DC: W. H. Winston, 1977.
[34] A. D. Worrall, K. D. Baker, and G. D. Sullivan, "Model based perspective inversion,"Image and Vision Computing, vol. 7, no. 1, pp. 17-23, 1989.

Index Terms:
3D model; 2D image matching; model based pattern recognition; picture processing; motion tracking; arbitrary curved surfaces; Levenberg-Marquardt method; curve fitting; pattern recognition; picture processing
D.G. Lowe, "Fitting Parameterized Three-Dimensional Models to Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 5, pp. 441-450, May 1991, doi:10.1109/34.134043
Usage of this product signifies your acceptance of the Terms of Use.