Abstract
We describe a theoretical formulation for stereo in terms of the Markov Random Field and Bayesian approach to vision. This formulation enables us to integrate the depth information from different types of matching primitives, or from different vision modules. We treat the correspondence problem and surface interpolation as different aspects of the same problem and solve them simultaneously, unlike most previous theories. We use techniques from statistical physics to compute properties of our theory and show how it relates to previous work. These techniques also suggest novel algorithms for stereo which are argued to be preferable to standard algorithms on theoretical and experimental grounds. It can be shown (Yuille, Geiger and Bülthoff 1989) that the theory is consistent with some psychophysical experiments which investigate the relative importance of different matching primitives.
Chapter PDF
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Barnard, S. Proc. Image Understanding Workshop, Los Angeles, 1986.
Barnard, S. and Fischler, M.A, “Computational Stereo”. Computing Surveys, 14, No. 4, 1982.
Blake, A. “The least disturbance principle and weak constraints,” Pattern Recognition Letters, 1, 393–399, 1983.
Blake, A. “Comparison of the efficiency of deterministic and stochastic algorithms for visual reconstruction,” PAMI, Vol. 11, No. 1, 2–12, 1989.
Bülthoff, H. and Mallot, H-P. “Interactions of different modules in depth perception”. In Proceedings of the First International Conference on Computer Vision, London, 1987.
Bülthoff, H. and Mallot, H-P. “Integration of depth modules: stereo and shading”. J. Opt. Soc. Am., 5, 1749–1758, 1988.
Bülthoff, H. and Fahle, M. “Disparity Gradients and Depth Scaling”. Artificial Intelligence Memo 1175, Cambridge, M.I.T., 1989.
Burt, P. and Julesz, B. “A disparity gradient limit for binocular fusion”. Science 208, 615–617, 1980.
Clark, J.J. and Yuille, A.L. Data Fusion for Sensory Information Processing Systems., Kluwer Academic Press, 1990.
Dev, P. “Perception of depth surfaces in random-dot stereograms: A neural model”. Int. J. Man-Machine Stud. 7, 511–528, 1975.
Durbin, R., Szeliski, R. and Yuille, A.L. “The elastic net and the travelling salesman problem”. Harvard Robotics Laboratory Technical Report. No. 89–3, 1989.
Durbin, R. and Willshaw, D. “An analog approach to the travelling salesman problem using an elastic net method”. Nature, 326, 689–691, 1987.
Duchon, J. Lecture Notes in Mathematics. 571. (Eds Schempp, W. and Zeller, K.), 85–100 (Berlin, Springer-Verlag, 1979).
Geiger, D. and Girosi, F., ”Parallel and deterministic algorithms from MRFs:integration and surface reconstruction”. Artificial Intelligence Laboratory Memo 1114. Cambridge, M.I.T., June 1989.
Geiger, D. and Yuille, A., ”A common framework for image segmentation”. Harvard Robotics Laboratory Technical Report. No. 89–7, 1989.
Geiger, D. and Yuille, A., “Stereopsis and eye movement”, Proceedings of the First International Conference on Computer Vision. London, pp 306–314, 1987.
Gelb, A. Applied Optimal Estimation. M.I.T. Press. Cambridge, Ma., 1974.
Geman, S. and Geman, D. “Stochastic relaxation, Gibbs distributions and the Bayesian restoration of images”. IEEE Trans. PAMI, 6, 721–741, 1984.
Gennert, M. “A Computational Framework for Understanding Problems in Stereo Vision”. M.I.T. AI Lab PhD. Thesis, 1987.
Grimson, W.E.L. From Images to Surfaces: A computational study of the human early visual system. M.I.T. Press. Cambridge, Ma., 1981.
Hopfield, J.J. and Tank, D.W. “Neural computation of decisions in optimization problems”. Biological Cybernetics, 52, 141–152, 1985.
Jepson, A.D. and Jenkin, M.R.M. “The fast computation of disparity from phase differences”. Proceedings Computer Vision and Pattern Recognition '89. pp 398–403, San Diego, 1989.
Kirkpatrick, S., Gelatt, C.D. Jr. and Vecchi, M.P. “Optimization by simulated annealing”. Science, 220, 671–680, 1983.
Marr, D. and Poggio, T. “Cooperative computation of stereo disparity”. Science, 194, 283–287, 1976.
Marr, D. and Poggio, T. “A computational theory of human stereo vision”. Proc. R. Soc. Lond. B. Vol 204, pp 301–328, 1979.
Marroquin, J. In Proceedings of the First International Conference on Computer Vision. London. 1987.
Metropolis, N. Rosenbluth, A., Rosenbluth, M., Teller, A., and Teller, E. “Equation of state calculations by fast computing machines”. J. Phys. Chem. 21, 1087–1091, 1953.
Mitchison, G.M. ”Planarity and segmentation in stereoscopic matching. Perception, 17, 753–782, 1988.
Mitchison, G.M. and McKee, S. “The resolution of ambiguous stereoscopic matches by interpolation”. Vision Research, Vol 27, no 2. pp 285–294, 1987.
Mumford, D. and Shah, J. “Boundary detection by minimizing functionals, I”, Proc. IEEE Conf. on Computer Vision and Pattern Recognition, San Francisco, 1985.
Parisi, G. Statistical Field Theory. Addison-Wesley, Reading, Mass. 1988.
Pollard, S.B., Mayhew, J.E.W. and Frisby, J.P. “Disparity Gradients and Stereo Correspondences”. Perception, 1987.
Poggio, T. and Torre, V. “Ill-posed problems and regularization analysis in early vision”. M.I.T. A.I. Memo No. 773, 1984.
Prazdny, K. “Detection of Binocular Disparities”. Biological Cybernetics, 52, 93–99, 1985.
Sanger, T. “Stereo disparity computation using Gabor filters,” Biological Cybernetics, 59, 405–418, 1988.
Ullman, S. The Interpretation of Visual Motion. Cambridge, Ma. M.I.T. Press, 1979.
Wasserstrom, E. “Numerical solutions by the continuation method”. SIAM Review,,15, 89–119, 1973.
Yuille, A.L. “Energy Functions for Early Vision and Analog Networks”. Biological Cybernetics, 61, 115–123, 1989a.
Yuille, A.L. Harvard Robotics Laboratory Technical Report 89–12. 1989b.
Yuille, A.L., Geiger, D. and Bülthoff, H. “Stereo Integration, Mean Field Theory and Psychophysics”. Harvard Robotics Laboratory Technical Report 89–11.
Yuille, A.L. and Gennert, M. Preprint. 1988.
Yuille, A.L. and Grzywacz, N.M. “A Computational Theory for the Perception of Coherent Visual Motion”. Nature, 1988a.
Yuille, A.L. and Grzywacz, N.M. “The Motion Coherence Theory”. Proceedings of the Second International Conference on Computer Vision. pp 344–353. Tampa, Florida. 1988b.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yuille, A.L., Geiger, D., Bülthoff, H. (1990). Stereo integration, mean field theory and psychophysics. In: Faugeras, O. (eds) Computer Vision — ECCV 90. ECCV 1990. Lecture Notes in Computer Science, vol 427. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0014852
Download citation
DOI: https://doi.org/10.1007/BFb0014852
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-52522-6
Online ISBN: 978-3-540-47011-3
eBook Packages: Springer Book Archive