This Article 
 Bibliographic References 
 Add to: 
A Constraint Learning Feedback Dynamic Model for Stereopsis
November 1995 (vol. 17 no. 11)
pp. 1095-1100

Abstract—This paper presents a stereo matcher inspired by the earlier work of Marr and Poggio [7]. Two major extensions are introduced: the algorithm is extended to gray-level images, and the inhibitory/excitatory weights of the model are learned rather than set a priori according to “uniqueness” and “continuity” constraints. Gray level stereo pairs of real scenes with known disparity maps are used to train the model. The trained system is successfully tested on other gray level stereo pairs of real scenes as well as a set of random dot stereograms (RDS). Performance is compared to a recent stereo matching algorithm.

[1] S. Barnard and M. Fischler, “Computational Stereo,” ACM Computing Surveys, vol. 14, no. 4, pp. 553–572, 1982.
[2] U. Dhond and J.K. Aggarwal, "Structure From Stereo—A Review," IEEE Trans. Systems, Man, and Cybernetics, vol. 19, no. 6, pp. 1,489-1,510, Nov. 1989.
[3] W. Hoff and N. Ahuja, "Surfaces From Stereo: Integrating Feature Matching, Disparity Estimation, and Contour Detection," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 2, pp. 121-136, Feb. 1989.
[4] Y.C. Hsieh,D.M. Mckeown, Jr.,, and F.P. Perlant,“Performance evaluation of scene registration and stereo matching for cartographic feature extraction,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 2, Feb. 1992.
[5] J. Hu and P. Siy,“Stereo correspondence through multiple constraint neural networks,” Proc. IEEE Int’l Conf. Neural Networks, pp. 126-131,San Francisco, Mar. 1993.
[6] A. Khotanzad,A. Bokil,, and Y.W. Lee,“Stereopsis by constraint learning feed-forward neural networks,” IEEE Trans. Neural Networks, vol. 4, no. 2, pp. 332-342, Mar. 1993.
[7] D. Marr and T. Poggio,“Cooperative computation of stereo disparity,” Science, vol. 194, pp. 283-287, Oct. 1976.
[8] N.M. Nasrabadi and C.Y. Choo,“Hopfield network for stereo vision correspondence,” IEEE Trans. Neural Networks, vol. 3, no. 1, Jan. 1992.
[9] Y. Ohta and T. Kanade,“Stereo by two-level dynamic programming,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 7, no. 2, pp. 139-154, Apr. 1985.
[10] A.J. O’Toole and T. Nguyen,“Neural network simulations of distributed versus interval disparity cell codings,” J. Biological Systems, in press.
[11] F.J. Pineda,“Generalization of back-propagation to recurrent neural networks,” Physical Review Letters, vol. 59, pp. 2,229-2,232, 1987.
[12] N. Qian and T.J. Sejnowski,“Learning to solve random-dot stereograms of dense and transparent surfaces with recurrent backpropagation,” Proc. 1988 Connectionist Models, pp. 435-443, Summer School, Carnegie Mellon Univ., June17-26, 1988.
[13] W.J. Orlikowski and D.C. Gash, "Technological Frames: Making Sense of Information Technology in Organizations," ACM Trans. Information Systems, vol. 12, no. 2, pp. 174-207, Apr. 1994.

Index Terms:
Computational binocular stereo, learning stereo constraints, learning correspondence problem, generalized Marr-Poggio algorithm, dynamic feedback model.
Amol Bokil, Alireza Khotanzad, "A Constraint Learning Feedback Dynamic Model for Stereopsis," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 11, pp. 1095-1100, Nov. 1995, doi:10.1109/34.473237
Usage of this product signifies your acceptance of the Terms of Use.