This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
COSMOS-A Representation Scheme for 3D Free-Form Objects
October 1997 (vol. 19 no. 10)
pp. 1115-1130

Abstract—We address the problem of representing and recognizing 3D free-form objects when 1) the object viewpoint is arbitrary, 2) the objects may vary in shape and complexity, and 3) no restrictive assumptions are made about the types of surfaces on the object. We assume that a range image of a scene is available, containing a view of a rigid 3D object without occlusion. We propose a new and general surface representation scheme for recognizing objects with free-form (sculpted) surfaces. In this scheme, an object is described concisely in terms of maximal surface patches of constant shape index. The maximal patches that represent the object are mapped onto the unit sphere via their orientations, and aggregated via shape spectral functions. Properties such as surface area, curvedness, and connectivity, which are required to capture local and global information, are also built into the representation. The scheme yields a meaningful and rich description useful for object recognition. A novel concept, the shape spectrum of an object is also introduced within the framework of COSMOS for object view grouping and matching. We demonstrate the generality and the effectiveness of our scheme using real range images of complex objects.

[1] 3D Object Recognition Systems. A.K. Jain and P.J. Flynn, eds., Amsterdam: Elsevier Science Publishers B.V., 1993.
[2] P.J. Besl, "The Free-Form Surface Matching Problem," Machine Vision for Three-Dimensional Scenes, H. Freeman, ed., pp. 25-71. Academic Press, 1990.
[3] R.S. Millman and G.D. Parker, Elements of Differential Geometry. Prentice-Hall, 1977.
[4] C. Dorai and A.K. Jain, "COSMOS—A Representation Scheme for Free-Form Surfaces," Proc. Fifth Int'l Conf. Computer Vision, pp. 1,024-1,029,Boston, June 1995.
[5] J.J. Koenderink and A.J. van Doorn, "Surface Shape and Curvature Scales," Image and Vision Computing, vol. 10, pp. 557-565, Oct. 1992.
[6] P.J. Besl and R. Jain, "Three-Dimensional Object Recognition," Computing Surveys, vol. 17, pp. 75-145, 1985.
[7] P. Suetens, P. Fua, and A.J. Hanson, "Computational Strategies for Object Recognition," ACM Computing Surveys, vol. 24, pp. 5-61, Mar. 1992.
[8] F. Arman and J.K. Aggarwal, "Model-Based Object Recognition in Dense Range Images-A Review," ACM Computing Surveys, vol. 25, no. 1, pp. 5-43, 1993.
[9] P.J. Flynn and A.K. Jain, "Three-Dimensional Object Recognition," Handbook of Pattern Recognition and Image Processing, T.Y. Young, ed., vol. 2, chapter 14, pp. 497-541. Academic Press, 1994.
[10] B.K.P. Horn, "Extended Gaussian Image," Proc. IEEE, vol. 72, pp. 1,671-1,686, 1984.
[11] V.S. Nalwa, "Representing Oriented Piecewise$C^2$Surfaces," Int'l J. Computer Vision, vol. 3, pp. 131-153, 1989.
[12] S. Kang and K. Ikeuchi, "The Complex EGI: New Representation for 3-D Pose Determination," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 7, pp. 707-721, 1997.
[13] P. Liang and C.H. Taubes, “Orientation-Based Differential Geometric Representations for Computer Vision Applications,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 3, pp. 249-258, Mar. 1994.
[14] H. Matsuo and A. Iwata, "3-D Object Recognition Using MEGI Model from Range Data," Proc. 12th Int'l Conf. Pattern Recognition, pp. 843-846,Jerusalem, Israel, Oct. 1994.
[15] 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 Analysis and Machine Intelligence, vol. 13, no. 11, pp. 1115-1137, Nov. 1991.
[16] D. Keren,D. Cooper,, and J. Subrahmonia,“Describing complicated objects by implicit polynomials,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 1, pp. 38-53, 1994.
[17] J. Ponce, D.J. Kriegman, S. Petitjean, S. Sullivan, G. Taubin, and B. Vijayakumar, "Representations and Algorithms for 3D Curved Object Recognition," Three-Dimensional Object Recognition Systems, A.K. Jain and P.J. Flynn, eds., pp. 17-56.Amsterdam: Elsevier Science Publishers B.V., 1993.
[18] F. Stein and G. Medioni, “Structural Indexing: Efficient 3-D Object Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 125–145, 1992.
[19] H. Delingette, M. Hebert, and K. Ikeuchi, "A Spherical Representation for the Recognition of Curved Objects," Proc. Int'l Conf. Computer Vision '93,Berlin, 1993.
[20] P.J. Besl and N.D. McKay, "A Method for Registration of 3D Shapes," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 239-256, Feb. 1992.
[21] S. Lavallee and R. Szeliski, "Recovering the Position and Orientation of Free-Form Objects From Image Contours Using 3D Distance Maps," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 4, pp. 378-390, 1995.
[22] J.-L. Chen and G.C. Stockman, "Determining Pose of 3D Objects with Curved Surfaces," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 1, pp. 52-56, Jan. 1996.
[23] P.J. Besl, "Triangles as a Primary Representation," Object Representation in Computer Vision, M. Hebert, J. Ponce, T. Boult, and A. Gross, eds., pp. 191-206.Berlin: Springer-Verlag, 1995.
[24] T. Joshi, J. Ponce, B. Vijayakumar, and D.J. Kriegman, "HOT Curves for Modelling and Recognition of Smooth Curved 3D Objects," Proc. IEEE Conf. Computer Vision and Pattern Recognition,Seattle, Wash., pp. 876-880, June 1994.
[25] A.K. Jain and R. Hoffman, "Evidence-Based Recognition of 3D Objects," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 10, no. 6, pp. 783-802, June 1988.
[26] J. Subrahmonia, D.B. Cooper, and D. Keren, “Practical, Reliable, Bayesian Recognition of 2D and 3D Objects Using Implicit Polynomials and Algebraic Invariants,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 5, pp. 505-519, May 1996.
[27] H. Delingette, M. Hebert, and K. Ikeuchi, "Shape Representation and Image Segmentation Using Deformable Surfaces," Image and Vision Computing, vol. 10, no. 3, pp. 132-144, 1992.
[28] P.J. Besl, Surfaces in Range Image Understanding. Springer Series in Perception Engineering, Springer-Verlag, 1988.
[29] J.J. Koenderink, Solid Shape. MIT Press, 1990.
[30] P.J. Besl, "Geometric Signal Processing," Analysis and Interpretation of Range Images, R.C. Jain and A.K. Jain, eds., chapter 3, pp. 141-205. Springer-Verlag, 1990.
[31] R.S. Strichartz, A Guide to Distribution Theory and Fourier Transforms.Boca Raton, Fla.: CRC Press, 1994.
[32] C. Dorai and A.K. Jain, "View Organization and Matching of Free-Form Objects," Proc. IEEE Int'l Symp. Computer Vision,Coral Gables, Fla., pp. 25-30, Nov. 1995.
[33] A.A.G. Requicha, "Representations for Rigid Solids: Theory, Methods, and Systems," Computing Surveys, vol. 12, pp. 437-464, Dec. 1980.
[34] Y. Li and R.J. Woodham, "Orientation-Based Representations of 3-D Shape," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 182-187,Seattle, Wash., June 1994.
[35] P.J. Flynn, "CAD-Based Computer Vision: Modeling and Recognition Strategies," PhD thesis, Michigan State Univ., Dept. of Computer Science, East Lansing, 1990.
[36] F.P. Ferrie, S. Mathur, and G. Soucy, "Feature Extraction for 3-D Model Building and Object Recognition," Three-Dimensional Object Recognition Systems, A.K. Jain and P.J. Flynn, eds., pp. 57-88.Amsterdam: Elsevier Science Publishers B.V., 1993.
[37] C. Dorai and A.K. Jain, "Recognition of 3D Free-Form Objects," Proc. 13th Int'l Conf. Pattern Recognition, vol. I, pp. 697-701,Vienna, Aug. 1996, under review, Int'l J. Computer Vision.
[38] C. Dorai, "COSMOS: A Framework for Representation and Recognition of 3D Free-Form Objects," PhD thesis, Dept. Computer Science, Michigan State Univ., East Lansing, May 1996.

Index Terms:
Free-form objects, sculpted surfaces, arbitrarily curved objects, 3D object representation, shape index, spherical map, shape spectrum, view matching, object recognition.
Citation:
Chitra Dorai, Anil K. Jain, "COSMOS-A Representation Scheme for 3D Free-Form Objects," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 10, pp. 1115-1130, Oct. 1997, doi:10.1109/34.625113
Usage of this product signifies your acceptance of the Terms of Use.