This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Structural Stereopsis for 3-D Vision
March 1988 (vol. 10 no. 2)
pp. 144-166

A novel approach to solving the stereo correspondence problem in computer vision is described. Structural descriptions of two two-dimensional views of a scene are extracted by one of possibly several available low-level processes, and a new theory of inexact matching for such structures is derived. An entropy-based figure of merit for attribute selection and ordering is defined. Experimental results applying these techniques to real image pairs are presented. Some manipulation experiments are briefly presented.

[1] N. Abramson,Information Theory and Coding. New York: Mc-Graw-Hill, 1963.
[2] R. D. Arnold, "Local context in matching edges for stereo vision," inProc. Image Understanding Workshop, 1978, pp. 65-12.
[3] H. H. Baker and T. O. Binford, "Depth from edge and intensity based stereo," inProc. 7th IJCAI, Tokyo, 1979, pp. 631-636.
[4] S. T. Barnard and W. B. Thompson, "Disparity analysis of images,"IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-2, pp. 333-340, 1981.
[5] S. T. Barnard and M. A. Fischler, "Computational stereo,"Comput. Surveys, vol. 14, no. 4, pp. 553-572, 1982.
[6] K. L. Boyer, R. J. Safranek, and A. C. Kak, "A knowledge based robotic vision system," inProc. 1st IEEE Conf. Artif. Intell. Appl., 1984, pp. 45-50.
[7] K. L. Boyer and A. C. Kak, "Symbolic stereo from structural descriptions," School Elec. Eng., Purdue Univ., West Lafayette, IN, Tech. Rep. TR-EE 86-12, Mar. 1986.
[8] D. J. Burr and R. T. Chien, "A system for stereo computer vision with geometric models," inProc. 5th IJCAI, Cambridge, MA, 1977, pp. 583.
[9] L. S. Dreschler and H. H. Nagel, "On the selection of critical points and local curvature extrema of region boundaries for interframe matching," inImage Sequence Processing and Dynamic Scene Analysis, T. S. Huang, Ed. Berlin, West Germany: Springer-Verlag, 1983.
[10] O. D. Faugeras and K. E. Price, "Semantic description of aerial images using stochastic labeling,"IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-3, pp. 633-642, Nov. 1981.
[11] W. E. L. Grimson,From Images to Surfaces: A Computational Study of the Human Early visual System. Cambridge, MA: MIT Press, 1981.
[12] W. E. L. Grimson, "Computational experiments with a feature based stereo algorithm," M.I.T., Cambridge, MA, AI Memo 762, Jan. 1984.
[13] R. M. Haralick and L. G. Shapiro, "The consistent labeling problem: Part I,"IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-1, pp. 173-184, Apr. 1979.
[14] R. M. Haralick, "Decision making in context,"IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-5, pp. 417-428, July 1983.
[15] A. C. Kak, "Depth perception for robots," inHandbook of Industrial Robotics, S. Nof, Ed. New York: Wiley, 1986, pp. 272-319.
[16] A. C. Kak, K. L. Boyer, R. J. Safranek, and H. S. Yang, "Knowledge-based stereo and structured light for 3-D robot vision," inTechniques for 3-D Machine Perception, A. Rosenfeld, Ed. Amsterdam, The Netherlands: Elsevier Science, 1986, pp. 185-218.
[17] D. T. Lawton, "Motion analysis via local translational processing," inProc. Workshop Comput. Vision: Rep. Contr., Rindge, NH, 1982, pp. 59-72.
[18] H. S. Lee and N. V. Thakor, "Shape matching by correlating relational models," inProc. 7th Int. Conf. Pattern Recognition, 1984, pp. 1178-1181.
[19] J. E. W. Mayhew and J. P. Frisby, "Psychological and computational studies towards a theory of human stereopsis,"Artif Intell., vol. 17, pp. 349-385, 1981.
[20] D. Marr,VISION: A Computational Investigation into the Human Representation and Processing of Visual Information. San Francisco, CA: W. H. Freeman, 1981.
[21] G. G. Medioni and R. Nevatia, "Matching images using linear features,"IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-6, pp. 675-685, Nov. 1984.
[22] H. P. Moravec, "Rover visual obstacle avoidance," inProc. 7th IJCAI, Vancouver, B.C., 1981, pp. 785-790.
[23] T. Sakai, M. Nagao, and H. Matsushima, "Extraction of invariant picture sub-structures by computer,"CGIP, vol. 1, pp. 81-96, 1972.
[24] A. Sanfeliu and K. S. Fu, "A distance measure between attributed relational graphs for pattern recognition,"IEEE Trans. Syst., Man, Cybernet., vol. SMC-13, pp. 353-362, May/June 1983.
[25] C. E. Shannon, "A mathematical theory of communications,"Bell. Syst. Tech. J., vol. 27, pp. 379-423, 623-656, July-Oct. 1948.
[26] L. G. Shapiro and R. M. Haralick, "Structural descriptions and inexact matching,"IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI- 3, pp. 504-519, 1981.
[27] L. G. Shapiro and R. M. Haralick, "A metric for comparing relational descriptions,"IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-7, pp. 90-94, Jan. 1985.
[28] M. Shneier, "A compact relational structure representation," inProc. 6th IJCAI, Tokyo, 1979, pp. 818-826.
[29] H. Shvayster and S. Peleg, "A new approach to the consistent labeling problem," inProc. CVPR-85, San Francisco, CA, pp. 320-327.
[30] H. L. Van Trees,Detection, Estimation, and Modulation Theory, Vol. I. New York: Wiley, 1968.
[31] T. D. Williams and F. Glazer, "Comparison of feature operators for use in matching pairs,"Image Sequence Processing and Dynamic Scene Analysis, T. S. Huang, Ed. Berlin, West Germany: Springer-Verlag, 1983.
[32] A. K. C. Wong and D. E. Ghahraman, "Random graphs: structural-contextual dichotomy,"IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-2, pp. 341-348, July 1980.
[33] A. K. C. Wong and M. You, "Entropy and distance of random graphs with application to structural pattern recognition,"IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-7, pp. 599-609, Sept. 1985.
[34] Y. Yakimovsky and R. Cunningham, "A system for extracting three-dimensional measurements from a stereo pair of TV cameras,"CGIP, vol. 7, pp. 195-210, 1978.
[35] K. L. Boyer, A. J. Vayda, and A. C. Kak, "Robotic manipulation experiments using structural stereopsis for 3D vision,"IEEE Expert, vol. 1, no. 3, pp. 73-94, Fall 1986.

Index Terms:
3D comput vision; computerised pattern recognition; robot vision; structural stereopsis; 2D views; stereo correspondence; inexact matching; entropy-based figure of merit; image pairs; computer vision; computerised pattern recognition; statistical analysis
Citation:
K.L. Boyer, A.C. Kak, "Structural Stereopsis for 3-D Vision," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 10, no. 2, pp. 144-166, March 1988, doi:10.1109/34.3880
Usage of this product signifies your acceptance of the Terms of Use.