This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
3-D Shape Recovery Using Distributed Aspect Matching
February 1992 (vol. 14 no. 2)
pp. 174-198

An approach to the recovery of 3-D volumetric primitives from a single 2-D image is presented. The approach first takes a set of 3-D volumetric modeling primitives and generates a hierarchical aspect representation based on the projected surfaces of the primitives; conditional probabilities capture the ambiguity of mappings between levels of the hierarchy. From a region segmentation of the input image, the authors present a formulation of the recovery problem based on the grouping of the regions into aspects. No domain-independent heuristics are used; only the probabilities inherent in the aspect hierarchy are exploited. Once the aspects are recovered, the aspect hierarchy is used to infer a set of volumetric primitives and their connectivity. As a front end to an object recognition system, the approach provides the indexing power of complex 3-D object-centered primitives while exploiting the convenience of 2-D viewer-centered aspect matching; aspects are used to represent a finite vocabulary of 3-D parts from which objects can be constructed.

[1] G.J. Agin and T. O. Binford, "Computer description of curved objects,"IEEE Trans. Comput., vol. C-25, no. 4, pp. 439-449, Apr. 1976.
[2] R. Bergevin and M. D. Levine, "Recognition of 3-D objects in 2-D line drawings: An approach based on geons," Tech. Rep. TR-CIM-88-24, McGill Res. Cent. Intell. Machines, McGill Univ., Nov. 1988.
[3] R. Bergevin and M. D. Levine, "Hierarchical decomposition of objects in line drawings," Tech. Rep. TR-CIM-88-25, McGill Res. Cent. Intell. Machines, McGill Univ., Nov. 1988.
[4] R. Bergevin and M. D. Levine, "Generic object recognition: Building coarse 3D descriptions from line drawings," inProc. IEEE Workshop Interpretation of 3D Scenes, Nov. 1989, pp. 68-74.
[5] F. Berman, D. Johnson, T. Leighton, P. W. Shor and L. Snyder, "Generalized planar matching,"J. Algorithms, vol. 11, no. 2, pp. 153-184, June 1990.
[6] P. J. Besl and R. C. Jain, "Three-dimensional object recognition,"ACM Comput. Surveys, vol. 17, no. 1, pp. 75-145, Mar. 1985.
[7] P. J. Besl and R. C. Jain, "Segmentation through variable-order surface fitting,"IEEE Trans. Patt. Anal. Machine Intell., vol. 10, no. 2, pp. 167-192, Mar. 1988.
[8] I. Biederman, "Human image understanding: Recent research and a theory,"Comput. Vision Graphics Image Processing, vol. 32, pp. 29-73, 1985.
[9] T. O. Binford, "Visual perception by computer," inProc. IEEE Conf. Syst. Contr.(Miami, FL), 1971.
[10] T. O. Binford, "Survey of model-based image analysis systems," Int. J. Robotics Res., vol. 1, no. 1, pp. 18-64, Spring 1982.
[11] R. A. Brooks, "Model-based 3-D interpretations of 2-D images,"IEEE Trans. Patt. Anal. Machine Intell., vol. 5, no. 2, pp. 140-150, Mar. 1983.
[12] J. F. Canny, "A computational approach to edge detection,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-8, pp. 679-697, 1986.
[13] I. Chakravarty and H. Freeman, "Characteristic views as a basis for three-dimensional object recognition," inProc. SPIE Conf. Robot Vision(Arlington, VA), May 6-7, 1982, pp. 37-45.
[14] R.T. Chin and C. R. Dyer, "Model-based recognition in robot vision,"ACM Comput. Surveys, vol. 18, no. 1, pp. 67-108, Mar. 1986.
[15] S. J. Dickinson, A. P. Pentland, and A. Rosenfeld, "A representation for qualitative 3-D object recognition integrating object-centered and viewer-centered models," inVision: A Convergence of Disciplines(K.N. Leibovic, Ed.). New York: Springer Verlag, 1990.
[16] S. J. Dickinson, A. P. Pentland, and A. Rosenfeld, "Qualitative 3-D shape recovery using distributed aspect matching," Tech. Rep. CAR-TR-453, Cent. Automat. Res., Univ. Maryland, June 1990.
[17] S. J. Dickinson, A. P. Pentland, and A. Rosenfeld, "From volumes to views: An approach to 3-D object recognition," inProc. IEEE Workshop CAD-Based Vision(Maui, HI), June 1991.
[18] 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.
[19] T. J. Fan, G. Medioni, and R. Nevatia, "Recognizing 3-D objects using surface descriptions," presented at the 2nd Int. Conf. Computer Vision, Dec. 5-8, 1988.
[20] M.A. Fischler and R. C. Bolles, "Perceptual organization and curve partitioning,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-8, no. 1, pp. 100-105, 1986.
[21] M. Gardiner, "The superellipse: A curve that lies between the ellipse and the rectangle,"Sci. Amer., vol. 213, pp. 222-234, Sept. 1965.
[22] M. R. Garey and D. S. Johnson,Computers and Intractability: A Guide to Theory of NP-Completeness. San Francisco, CA: Freeman, 1979.
[23] Z. Gigus and J. Malik, "Computing the aspect graph for line drawings of polyhedral objects," Tech. Rep. UCB/CSD 88/402, Comput. Sci. Div. (EECS), Univ. of California, Berkeley, Feb. 1988.
[24] Z. Gigus, J. Canny, and R. Seidel, "Efficiently computing and representing aspect graphs of polyhedral objects," Tech. Rep. UCB/CSD 88/432, Comput. Sci. Div. (EECS), Univ. of California, Berkeley, Aug. 1988.
[25] R. M. Haralick and L. Shapiro, "Image segmentation techniques,"Comput. Vision Graphics Image Processing, vol. 29, pp. 100-132, 1985.
[26] D. P. Huttenlocher and S. Ullman, "Object recognition using alignment," inProc. First Int. Conf. Comput. Vision(London, UK), 1987, pp. 102-111.
[27] K. Ikeuchi and T. Kanade, "Automatic generation of object recognition programs,"Proc. IEEE, vol. 76, no. 8, pp. 1016-1035, Aug. 1988.
[28] D. G. Kirpatrick and P. Hell, "On the complexity of a generalized matching problem," inProc. 10th Ann. ACM Symp. Theory Comput., 1978, pp. 240-245.
[29] J. J. Koenderink and A. J. van Doom, "The internal representation of solid shape with respect to vision,"Biol. Cybern., vol. 32, pp. 211-216, 1979.
[30] Y. Lamdan, J. T. Schwartz, and H. J. Wolfson, "On recognition of 3-D objects from 2-D images," inProc. IEEE Int. Conf. Robotics Automat., Apr. 1988.
[31] Y. Liao, "A two-stage method of fitting conic arcs and straight-line segments to digitized contours," inProc. Patt. Recogn. Image Processing Conf.(Dallas, TX), 1981, pp. 224-229.
[32] D. Lowe, Perceptual Organization And Visual Recognition. Boston: Kluwer, 1985.
[33] P. Meer, D. Mintz, and A. Rosenfeld, "Least median of squares based robust analysis of image structure," inProc. DARPA Image Understanding Workshop(Pittsburgh, PA), 1990.
[34] R. Mohan and R. Nevatia, "Perceptual organization for segmentation and description," inProc. DARPA Image Understanding Workshop(Palo Alto, CA), 1989, pp. 415-424.
[35] P. G. Mulgaonkar, L. G Shapiro, and R. M. Haralick, "Matching 'sticks, plates and blobs' objects using geometric and relational constraints,"Image Vision Comput., vol. 2, no. 2, pp. 85-98, May 1984.
[36] R. Nevatia and T. O. Binford, "Description and recognition of curved objects,"Artificial Intell., vol. 8, pp. 77-98, 1977.
[37] N. Nilsson,Principles of Artificial Intelligence. Palo Alto, CA: Tioga, 1980.
[38] A. P. Pentland, "Perceptual organization and the representation of natural form,"Artificial Intell., vol. 28, no. 3, pp. 293-331, 1986.
[39] A.P. Pentland, "Recognition by parts," inProc. First Int. Conf. Comput. Vision(London, UK), 1987, pp. 612-620.
[40] A.P. Pentland, "Toward an ideal 3-D CAD system," inProc. SPIE Conf. Machine Vision Man-Machine Interface(San Diego, CA), 1987.
[41] A. Pentland and J. Williams, "Good vibrations: Modal dynamics for graphics and animation,"Comput. Graphics, vol. 23, no. 4, pp. 215-222, 1989.
[42] A. Pentland, "Automatic extraction of deformable part models,"Int. J. Comput. Vision, vol. 4, pp. 107-126, 1990.
[43] A. Pentland and S. Sclaroff, "Closed-form solutions for physically based shape modeling and recognition," to be published inIEEE Trans. Patt. Anal. Machine Intell..
[44] A. Pentland and B. Horowitz, "Recovery of nonrigid motion and structure,"IEEE Trans. Patt. Anal. Machine Intell., vol. 13, no. 7, pp. 730-742, July 1991.
[45] U. Ramer, "An iterative procedure for the polygonal approximation of plane curves,"Comput. Graphics Image Processing, vol. 1, pp. 244-256, 1972.
[46] L. G. Roberts, "Machine perception of three-dimensional solids," inOptical and Electro-Optical Information Processing(J.T. Tippettet al., Eds.). Cambridge, MA: MIT Press, 1965, pp. 159-197.
[47] A. Rosenfeld, "Recognizing unexpected objects: A proposed approach," inProc. DARPA Image Understanding Workshop(Los Angeles, CA), 1987, pp. 620-627.
[48] P. Saint-Marc and G. Medioni, "Adaptive smoothing for feature extraction," inProc. 1988 DARPA Image Understanding Workshop(Cambridge, MA), 1988, pp. 1100-1113.
[49] L. G. Shapiro and H. Lu, "Accumulator-based inexact matching using relational summaries,"Machine Vision and Applications, vol. 3, pp. 143-158, 1990.
[50] F. Solina, "Shape recovery and segmentation with deformable part models," Tech. Rep. MS-CIS-87-111, Univ. of Pennsylvania, Philadelphia, PA, Dec. 1987.
[51] T. Sripradisvarakul and R. Jain, "Generating aspect graphs for curved objects," inProc. IEEE Workshop Interpretation of 3D Scenes, Nov. 1989, pp. 109-115.
[52] L. Stark, D. Eggert, and K. Bowyer, "Aspect graphs and nonlinear optimization in 3-D object recognition," inProc. IEEE Second Int. Conf. Comput. Vision(Tampa, FL), 1988, pp. 501-507.
[53] J. Stewman and K. Bowyer, "Creating the perspective projection aspect graph of polyhedral objects," inProc. Second Int. Conf. Computer Vision, IEEE, New York, Dec. 1988, pp. 494-500.
[54] J. Stewman and K. Bowyer, "Direct construction of the perspective projection aspect graph of convex polyhedra,"Comput. Vision Graphics Image Processing, vol. 51, pp. 20-37, 1990.
[55] D. Terzopoulos, A. Witkin, and M. Kass, "Symmetry-seeking models and 3D object recovery,"Int. J. Comput. Vision, vol. 1, pp. 211-221, 1987.
[56] D. Terzopoulos, A. Witkin, and M. Kass, "Constraints on deformable models: Recovering 3D shape and nonrigid motion,"Artificial Intell., vol. 36, pp. 91-123, 1988.
[57] D. Terzopoulos and D. Metaxas, "Dynamic 3D models with local and global deformations: Deformable superquadrics,"IEEE Trans. Patt. Anal. Machine Intell., vol. 13, no. 7, pp. 703-714, July 1991.
[58] D. W. Thompson and J. L. Mundy, "Model-directed object recognition on the connection machine," inProc. DARPA Image Understanding Workshop(Los Angeles, CA), 1987, pp. 93-106.
[59] S. Ullman and R. Basri, "Recognition by linear combinations of models," A.I. Memo 1152, Artificial Intell. Lab., Mass. Inst. Technol., Aug. 1989.
[60] A. P. Witkin and J. M. Tenenbaum, "On the role of structure in vision," inHuman and Machine Vision(J. Becket al., Eds.). New York: Academic, 1983, pp. 481-543.

Index Terms:
3D shape recovery; pattern recognition; 3D volumetric primitives; picture processing; projected primitive surfaces; distributed aspect matching; hierarchical aspect representation; conditional probabilities; region segmentation; probabilities; connectivity; vocabulary; pattern recognition; picture processing; probability
Citation:
S.J. Dickinson, A.P. Pentland, A. Rosenfeld, "3-D Shape Recovery Using Distributed Aspect Matching," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 174-198, Feb. 1992, doi:10.1109/34.121788
Usage of this product signifies your acceptance of the Terms of Use.