This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
On Recognizing and Positioning Curved 3-D Objects from Image Contours
December 1990 (vol. 12 no. 12)
pp. 1127-1137

An approach for explicitly relating the shape of image contours to models of curved three-dimensional objects is presented. This relationship is used for object recognition and positioning. Object models consist of collections of parametric surface patches and their intersection curves; this includes nearly all representations used in computer-aided geometric design and computer vision. The image contours considered are the projections of surface discontinuities and occluding contours. Elimination theory provides a method for constructing the implicit equation of these contours for an object observed under orthographic or perspective projection. This equation is parameterized by the object's position and orientation with respect to the observer. Determining these parameters is reduced to a fitting problem between the theoretical contour and the observed data points. The proposed approach readily extends to parameterized models. It has been implemented for a simple world composed of various surfaces of revolution and tested on several real images.

[1] R. Bajcsy and F. Solina, "Three-dimensional object representation revisited," inProc. Int. Conf. Comput. Vision, London, England, June 1987, pp. 231-240.
[2] A. Barr, "Superquadrics and angle preserving transformations,"IEEE Comput. Graphics Appl., vol. 1, pp. 11-23, Jan. 1981.
[3] H. Barrow and J. Tenenbaum, "Interpreting line drawings of three-dimensional surfaces,"Artificial Intell., vol. 17, no. 1-3, pp. 75-116, 1981.
[4] P. J. Besl, "Geometric modeling and computer vision,"Proc. IEEE, vol. 76, no. 8, pp. 936-958, Aug. 1988.
[5] P. J. Besl and R. C. Jain, "Three-dimensional object recognition,"ACM Comput. Surveys, vol. 17, no. 1, pp. 75-145, Mar. 1985.
[6] R. Bolles, P. Horaud, and M. Hannah, "3DPO: A three-dimensional part orientation system," in J. Brady and R. Paul, Eds.,Proc. 1st Int. Symp. Robot. Res.Cambridge, MA: M.I.T. Press, 1984, pp. 413-424.
[7] J. Brady and A. Yuille, "An extremum principle for shape from contour,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-6, pp. 288-301, 1984.
[8] R. Brooks, "Symbolic reasoning among 3-D models and 2-D images,"Artificial Intell., vol. 17, pp. 285-348, 1981.
[9] B. Buchberger, "Applications of Gröbner bases in non-linear computational geometry," in R. Janssen, Ed.,Trends in Comput. Algebra: Int. Symp.New York: Springer-Verlag, 1987, pp. 52-80.
[10] J. Callahan and R. Weiss, "A model for describing surface shape," inProc. IEEE Conf. Comput. Vision Pattern Recognition, 1985, pp. 240-245.
[11] J. F. Canny, "Finding lines and edges in images," Artificial Intell. Lab., Massachusetts Inst. Technol., Tech. Rep. TM-720, 1983.
[12] J. F. Canny,The Complexity of Robot Motion Planning. Cambridge, MA: MIT Press, 1988.
[13] M. Clowes, "On seeing things,"Artificial Intell., vol. 2, no. 1, pp. 79-116, 1971.
[14] D. Cyrluk, D. Kapur, and J. Mundy, "Algebraic reasoning in view consistency and parameterized model matching problems," inProc. Image Understanding Workshop, Boston, MA, Apr. 1988, pp. 731-739.
[15] A. Dixon, "The eliminant of three quantics in two independent variables,"Proc. London Math. Soc., ser. 2, vol. 7, 1908.
[16] D. Eggert and K. Bowyer, "Computing the orthographic projection aspect graph of solids of revolution," inProc. IEEE Workshop Interpretation of 3D Scenes, Nov. 1989, pp. 102-108.
[17] T. J. Fan, G. Medioni, and R. Nevatia, "Matching 3-D objects using surface descriptions," inProc. Int. Conf. Robotics Automat., Apr. 1988, pp. 1400-1406.
[18] R.T. Farouki, "Trimmed-Surface Algorithms for the Evaluation and Interrogation of Solid Boundary Representations,"IBM J. of Research and Development, Vol. 31, 1987, pp. 314-333.
[19] 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.
[20] Z. Gigus, J.F. Canny, and R. Seidel, "Efficiently computing and representing aspect graphs of polyhedral objects," inProc. Second Int. Conf. Computer Vision, IEEE, New York, Dec. 1988, pp. 30-39.
[21] R. N. Goldman and T.W. Sederberg, "Some applications of resultants to problems in computational geometry,"Visual Comput., vol. 1, pp. 101-107, 1985.
[22] W. Grimson, "On the recognition of curved objects,"IEEE Trans. Pattern Anal. Machine Intell., vol. 11, pp. 632-643, June 1989.
[23] W. E. L. Grimson and T. Lozano-Perez, "Localizing overlapping parts by searching the interpretation tree,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-9, no. 4, July 1987.
[24] 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.
[25] M. Hebert and T. Kanade, "The 3D profile method for object recognition," inProc. IEEE Conf. Comput. Vision Pattern Recognition, San Francisco, CA, June 1985.
[26] R. Horaud, "New methods for matching 3-D objects with single perspective views,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-9, pp. 401-412, May 1987.
[27] R. Horaud and J. Brady, "On the geometric interpretation of image contours," inProc. Int. Conf. Comput. Vision, London, England, June 1987.
[28] D. Huffman, "Impossible objects as nonsense sentences,"Machine Intell., vol. 6, pp. 295-323, 1971.
[29] D. Huttenlocher and S. Ullman, "Object recognition using alignment," inProc. Int. Conf. Comput. Vision, London, England, June 1987, pp. 102-111.
[30] K. Ikeuchi, "Precompiling a geometrical model into an interpretation tree for object recognition in bin-picking tasks," inProc. Image Understanding Workshop, Los Angeles, CA, Feb. 1987, pp. 321-339.
[31] C. Jerian and R. Jain, "Polynomial algorithms for structure from motion," inProc. 2nd ICCV(Tarpon Springs, FL), 1988.
[32] J. Kajiya, "Ray Tracing Parametric Patches,"Computer Graphics(Proc. SIGGRAPH), Vol. 16, No. 3, July 1982, pp. 245-254.
[33] T. Kanade, "Recovery of the three-dimensional shape of an object from a single view,"Artificial Intell., vol. 17, pp. 409-460, 1981.
[34] J. Koenderink, "What does the occluding contour tell us about solid shape?"Perception, vol. 13, 1984.
[35] J. Koenderink and A. Van Doorn, "The internal representation of solid shape with respect to vision,"Biol. Cybern., vol. 32, pp. 211-216, 1979.
[36] D. Kriegman and T. Binford, "Generic models for robot navigation," inProc. IEEE Int. Conf. Robot. Automation, Philadelphia, PA, Apr. 1988.
[37] D.J. Kriegman and I. Ponce, "Computing exact aspect graphs of curved objects: Solids of revolution," inProc. IEEE Workshop Interpretation of 3D Scenes, IEEE, New York, Nov. 1989, pp. 116-121.
[38] D. G. Lowe, "The viewpoint consistency constraint,"Int. J. Comput. Vision, vol. 1, no. 1, pp. 57-72, 1987.
[39] F. Macaulay,The Algebraic Theory of Modular Systems. Cambridge, England: Cambridge Univ. Press, 1916.
[40] J. Malik, "Interpreting line drawings of curved objects,"Int. J. Comput. Vision, vol. 1, no. 1, pp. 73-103, 1987.
[41] D. Marr,Vision. San Francisco, CA: Freeman, 1982.
[42] V. Nalwa, "Line-drawing interpretation: Bilateral symmetry," inProc. Image Understanding Workshop, Los Angeles, CA, Feb. 1987, pp. 956-967.
[43] R. Nevatia and T. Binford, "Description and recognition of complex curved objects,"Artificial Intell., vol. 8, pp. 77-98, 1977.
[44] A. Pentland, "Recognition by parts," SRI Int., Menlo Park, CA, Tech. Note 406, 1986.
[45] J. Ponce, "On characterizing ribbons and finding skewed symmetries," inProc. IEEE Int. Conf. Robot. Automation, Scottsdale, AZ, May 1989.
[46] J. Ponce and D. Chelberg, "Finding the limbs and cusps of generalized cylinders,"Int. J. Comput. Vision, vol. 1, Oct. 1987.
[47] J. Ponce, D. Chelberg, and W. Mann, "Invariant properties of straight homogeneous generalized cylinders and their contours,"IEEE Trans. Pattern Anal. Machine Intell., vol. 11, pp. 951-966, Sept. 1989.
[48] J. Ponce and D. Kriegman, "Computing exact aspect graphs of curved objects: Parametric patches," inProc. Amer. Ass. Artificial Intell., July 1990.
[49] W. Press, B. Flannery, S. Teukolsky, and W. Vetterling,Numeric Recipes in C-The Art of Scientific Computing.Cambridge, UR: Cambridge University Press, 1988.
[50] J.H. Rieger, "On the classification of views of piecewise smooth objects,"Image Vision Comput., vol. 5, no. 2, pp. 91-97, May 1987.
[51] G. Salmon,Modern Higher Algebra. Dublin, Ireland: Hodges, Smith, 1866.
[52] T. W. Sederberg, D. Anderson, and R. N. Goldman, "Implicit representation of parametric curves and surfaces,"Comput. Vision, Graphics, Image Processing, vol. 28, pp. 72-84, 1984.
[53] S. Shafer,Shadows and Silhouettes in Computer Vision. Kluwer Academic, 1985.
[54] K. Stevens, "The visual interpretation of visual contours,"Artifical Intell., vol. 17, pp. 47-73, Aug. 1981.
[55] K. Sugihara, "An algebraic approach to Shape-from-Image problems,"Artificial Intell., vol. 23, pp. 59-95, 1984.
[56] F. Ulupinar and R. Nevatia, "Using symmetries for analysis of shape from contour," inProc. 2nd ICCV, Tarpon Springs, FL, 1988, pp. 414-426.

Index Terms:
object models; pattern recognition; 3-D objects; image contours; parametric surface patches; intersection curves; computer vision; surface discontinuities; occluding contours; pattern recognition; picture processing
Citation:
D.J. Kriegman, J. Ponce, "On Recognizing and Positioning Curved 3-D Objects from Image Contours," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 12, pp. 1127-1137, Dec. 1990, doi:10.1109/34.62602
Usage of this product signifies your acceptance of the Terms of Use.