Abstract

A cooperative method is proposed in which image intensity (brightness) and optical-flow information are integrated into a single stereo technique by modeling the input data as coupled Markov random fields (MRF’s). The Bayesian probabilistic estimation method and the MRF–Gibbs equivalence theory are used to integrate the optical flow and the gray-level intensity information to obtain an energy function that will explicitly represent the depth discontinuity and occlusion constraints on the solution. This energy function involves the similarity in intensity (or edge orientation) and the optical flow between corresponding sites of the left and right images as well as the smoothness constraint on the disparity solution. If a simple MRF is used to model the data, the energy function will yield a poor disparity by smoothing across object boundaries, particularly when occluding objects are present. We use optical-flow information to indicate object boundaries (depth discontinuities) and occluded regions, in order to improve the disparity solution in occluded regions. A stochastic relaxation algorithm (simulated annealing) is used to find a favorable disparity solution by minimization of the energy equation.

© 1989 Optical Society of America

Full Article  |  PDF Article
OSA Recommended Articles
Cooperative integration of stereopsis and optic flow computation

G. Sudhir, Subhashis Banerjee, K. K. Biswas, and R. Bahl
J. Opt. Soc. Am. A 12(12) 2564-2572 (1995)

Disparity-selective stereo matching using correlation confidence measure

Sijung Kim, Jinbeum Jang, Jaeseung Lim, Joonki Paik, and Sangkeun Lee
J. Opt. Soc. Am. A 35(9) 1653-1662 (2018)

Integration of depth modules: stereo and shading

Heinrich H. Bülthoff and Hanspeter A. Mallot
J. Opt. Soc. Am. A 5(10) 1749-1758 (1988)

References

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access OSA Member Subscription

Cited By

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access OSA Member Subscription

Figures (7)

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access OSA Member Subscription

Equations (24)

You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access OSA Member Subscription

Metrics

You do not have subscription access to this journal. Article level metrics are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access OSA Member Subscription