Abstract
Symmetric Bi- and Trinocular Stereo: Tradeoffs between Theoretical Foundations and Heuristics. Tradeoffs between theoretical and heuristic sides of ill-posed problems of the intensity-based computational stereo are discussed, as applied to the previously proposed symmetric approach for solving this problem. The heuristics are needed to deal with discontinuities in stereo images due to partial occlusions of observed surface. Basically, it is these discontinuities that cause the ill-posedness of the stereo problems. Theoretical base of the symmetric stereo is refined here by introducing a novel probabilistic model of the surface geometry and by deducing compound Bayesian decision rules to be implemented by dynamic programming techniques, as in the case of simple MAP-decision with the maximum a posteriori probability. Also, several heuristics are proposed to regularize the binocular stereo.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Baker, H. H.: Surfaces from mono and stereo images. Photogrammetria 39, 217–237 (1984).
Barnard, S. T., Fischler, M. A.: Computational stereo. ACM Comput. Surv. 14, 553–572 (1982).
Hannah, M. J.: Digital stereo image matching techniques. Int. Arch. Photogra. Remote Sensing 27, 280–293 (1988).
Gimel’farb, G. L.: Symmetric approach to the problem of automating stereoscopic measurements in photogrammetry. Kibernetika 2, 73–82 (1979) [in Russian; English translation: Cybernetics 8, 311–322 (1979)].
Gimel’farb, G. L.: Gibbs random fields and compound decisions at the lower level of digital image processing. Pattern Rec. Image Anal. Adv. Math. Theory Appl. USSR 1, 39–49 (1991).
Gimel’farb, G. L.: Intensity-based computer binocular stereo vision: signal models and algorithms. Int. J. Imaging Syst. Tech. 3, 189–200 (1991).
Gimel’farb, G. L.: Regularization of low-level binocular stereo vision considering surface smoothness and dissimilarity of superimposed stereo images. In: Proc. of the 2nd Int. Workshop on Visual Form (Capri, Italy, May 30-June 2, 1994), pp. 231–240. Singapore: World Scientific 1994.
Kyreitov, V. R.: Inverse problems of photometry. Novosibirsk: Computing Center (Acad. Sci. USSR, Siberian Branch), 1983. [in Russian]
Marroquin, J., Mitter, S., Poggio, T.: Probabilistic solution of ill-posed problems in computational vision. J. Amer. Stat. Assoc. 82, 76–89 (1987).
Poggio, T., Torre, V., Koch, C.: Computational vision and regularization theory. Nature 317, 314–319 (1985).
Schlesinger, M. L: Mathematical tools for image processing. Kiev: Naukova Dumka, 1989. [in Russian]
Yuille, A. L., Geiger, D., Bulthoff, H.: Stereo integration, mean field theory and psychophysics. In: Lecture Notes in Computer Science 427: Proc. of the First European Conf. on Computer Vision (Antibes, France, April 1990), pp. 73–82. Berlin, Heidelberg, New York, Tokyo: Springer 1990.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Springer-Verlag Wien
About this paper
Cite this paper
Gimel’farb, G.L. (1996). Symmetric Bi- and Trinocular Stereo: Tradeoffs between Theoretical Foundations and Heuristics. In: Kropatsch, W., Klette, R., Solina, F., Albrecht, R. (eds) Theoretical Foundations of Computer Vision. Computing Supplement, vol 11. Springer, Vienna. https://doi.org/10.1007/978-3-7091-6586-7_4
Download citation
DOI: https://doi.org/10.1007/978-3-7091-6586-7_4
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-82730-7
Online ISBN: 978-3-7091-6586-7
eBook Packages: Springer Book Archive