This Article 
 Bibliographic References 
 Add to: 
A Neural Network Approach to CSG-Based 3-D Object Recognition
July 1994 (vol. 16 no. 7)
pp. 719-726

Describes the recognition subsystem of a computer vision system based on constructive solid geometry (CSG) representation scheme. Instead of using the conventional CSG trees to represent objects, the proposed system uses an equivalent representation scheme-precedence graphs-for object representation. Each node in the graph represents a primitive volume and each are between two nodes represents the relation between them. Object recognition is achieved by matching the scene precedence graph to the model precedence graph. A constraint satisfaction network is proposed to implement the matching process. The energy function associated with the network is used to enforce the matching constraints including match validity, primitive similarity, precedence graph preservation, and geometric structure preservation. The energy level is at its minimum only when the optimal match is reached. Experimental results on several range images are presented to demonstrate the proposed approach.

[1] P. J. Besl and R. C. Jain, "Three-dimensional object recognition,"ACM Comput. Surveys, vol. 17, no. 1, pp. 75-145, Mar. 1985.
[2] 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.
[3] J. Brady, N. Nandhakumar, and J. Aggarwal, "Recent progress in the recognition of obiects from range data," inProc. 9th Int. Conf. Pattern Recognition, Nov. 1988, pp. 85-92.
[4] D. H. Ballard and C. M. Brown,Computer Vision. Englewood Cliffs, NJ: Prentice-Hall, 1982.
[5] A. A. Requicha, "Representations for rigid solids: Theory, methods, and systems,"Comput. Surveys, vol. 12, no. 4, pp. 437-465, 1980.
[6] P. J. Besl, "Geometric modeling and computer vision,"Proc. IEEE, vol. 76, no. 8, pp. 936-958, Aug. 1988.
[7] Y.-C. Lee and K.-S. Fu, "Machine understanding of CSG: Extraction and unification of manufacturing features,"IEEE Comput. Graphics and Applicat., vol. 7, no. 1, pp. 20-32, Jan. 1987.
[8] S. D. Roth, "Ray casting for modeling solids,"Comput. Graphics and Image Processing, vol. 18, pp. 109-144, 1982.
[9] P. Besl, "Active, optical range imaging sensors,"Machine Vision Applications, vol. 1, pp. 127-152, 1988.
[10] F. Lo, "An effective calibration procedure for structured-light-based range sensors," Masters thesis, Dept. Elec. Eng. Comput. Sci., North-western Univ., Sept. 1988.
[11] A. K. Jain and R. Hoffman, "Evidence-based recognition of 3-D objects,"IEEE Trans. Pattern Anal. Machine Intell., vol. 10, no. 6, pp. 783-802, Nov. 1988.
[12] P. Besl and R. Jain, "Invariant surface characteristics for 3-D object recognition in range images,"Comput. Vision Graphics Image Processing, 1986, pp. 33-80, vol. 33.
[13] D. Forsyth, A. Zisserman, C. Rothwell, C. Coelho, A. Heller, and J. L. Mundy, "Invariant descriptors for 3-D object recognition and pose,"IEEE Trans. Pattern Anal. Machine Intell., vol. 13, no. 10, pp. 971-991, Oct. 1991.
[14] 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.
[15] T.-J. Fan, G. Medioni, and R. Nevatia, "Recognizing 3-D objects using surface descriptions,"IEEE Trans. Pattern Anal. Machine Intell., vol. 11, no. 11, pp. 1140-1157, Nov. 1989.
[16] P. J. Flynn and A. K. Jain, "CAD-based computer vision: From CAD models to relational graphs,"IEEE Trans. Pattern Anal. Machine Intell., vol. 13, no. 2, pp. 114-132, Feb. 1991.
[17] P. J. Flynn and A. K. Jain, "BONSAI: 3-D object recognition using constrained search,"IEEE Trans. Pattern Anal. Machine Intell., vol. 13, no. 10, pp. 1066-1075, Oct. 1991.
[18] M. Seibert and A. M. Waxman, "Adaptive 3-D object recognition from multiple views,"IEEE Trans. Pattern Anal. Machine Intell., vol. 14, no. 2, pp. 107-124, Feb. 1992.
[19] W.-C. Lin and T.-W. Chen, "CSG-based object recognition using range images, " inProc. 9th Int. Conf. Pattern Recognition, Nov. 1988, pp. 99-103.
[20] W.-C. Lin and T.-W. Chen, "Inferring CSG-based object representation from range image," inProc. Vision Interface'90, Halifax, NS, Canada, May 14-18, 1990, pp. 173-180; extended version appeared inPattern Recognition: Architectures, Algorithms, and Applications, R. Plamondon and H. D. Cheng, Eds. New York: World Scientific, 1991, pp. 355-379.
[21] P. J. Besl and R. C. Jain, "Segmentation through variable-order surface fitting,"IEEE Trans. Pattern Anal. Machine Intell., vol. 10, no. 2, pp. 167-192, Mar. 1988.
[22] S. H. Friedberg, A. J. Insel, and L. E. Spence,Linear Algebra. Englewood Cliffs, NJ: Prentice-Hall, 1979, pp. 420-426.
[23] A. Kusiak and W. S. Chow, "Decomposition of manufacturing systems,"IEEE Trans. Robotics Automation, vol. 4, pp. 457-471, 1988.
[24] B. Parvin and G. Medioni, "A constraint satisfaction network for matching 3d obiects," inProc. Int. Conf. Neural Networks(Washington, DC), June 1989, pp. 281-286, volume II.
[25] W. Li and N. M. Nasrabadi, "Object recognition based on graph matching implemented by a Hopfield-style neural network," inProc. IEEE Int. Joint Conf. Neural Netw., Washington DC, vol. II, June 18-22, 1989, pp. 287-290.
[26] W-C. Lin, F-Y. Liao, C-K. Tsao, and T. Lingutla, "A hierarchical multiple-view approach to three-dimensional object recognition,"IEEE Trans. Neural Networks, vol. 2, pp. 84-92, Jan. 1991.
[27] D. E. Van Den Bout and T. K. Miller, III, "Improving the performance of the Hopfield-tank neural network through normalization and annealing,"Biological Cybern., vol. 62, pp. 129-139, 1989.
[28] D. E. Van Den Bout and T. K. Miller, III, "Graph partitioning using annealed neural network,"IEEE Trans. Neural Netw., vol. NN-1, no. 2, pp. 192-203, June 1990.
[29] S. Kirkpatrick, C. Gelatt, and M. Vecchi, "Optimization by simulated annealing,"Science, vol. 220, pp. 671-680, May 13, 1983.
[30] D. D. Hoffman and W. A. Richards, "Parts of recognition,"Cognition, vol. 18, pp. 65-96, 1984.
[31] I. Biederman, "Human image understanding: Recent research,"Comput. Vision, Graphics Image Processing, vol. 32, pp. 29-73, 1985.

Index Terms:
computer vision; solid modelling; neural nets; graph theory; neural network approach; 3-D object recognition; computer vision system; constructive solid geometry; precedence graphs; primitive volume; object recognition; constraint satisfaction network; matching process; energy function; match validity; primitive similarity; geometric structure preservation; range images
T.W. Chen, W.C. Lin, "A Neural Network Approach to CSG-Based 3-D Object Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 7, pp. 719-726, July 1994, doi:10.1109/34.297953
Usage of this product signifies your acceptance of the Terms of Use.