Relaxing Symmetric Multiple Windows Stereo Using Markov Random Fields

This paper introduces R-SMW, a new algorithm for stereo matching. The main aspect is the introduction of a Markov Random Field (MRF) model in the Symmetric Multiple Windows (SMW) stereo algorithm in order to obtain a non-deterministic relaxation. The SMW algorithm is an adaptive, multiple window scheme using left-right consistency to compute disparity. The MRF approach allows to combine in a single functional the disparity values coming from different windows, the left-right consistency constraint and regularization hypotheses. The optimal estimate of the disparity is obtained by minimizing an energy functional with simulated annealing. Results with both synthetic and real stereo pairs demonstrate the improvement over the original SMW algorithm, which was already proven to perform better than state-of-the-art algorithms.

[1]  A. Verri,et al.  A compact algorithm for rectification of stereo pairs , 2000 .

[2]  Antonio Ortega,et al.  Stereo image compression with disparity compensation using the MRF model , 1996, Other Conferences.

[3]  Donald Geman,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[4]  Ingemar J. Cox,et al.  A Maximum Likelihood Stereo Algorithm , 1996, Comput. Vis. Image Underst..

[5]  T. Poggio,et al.  Visual Integration and Detection of Discontinuities: The Key Role of Intensity Edges , 1987 .

[6]  Jake K. Aggarwal,et al.  Structure from stereo-a review , 1989, IEEE Trans. Syst. Man Cybern..

[7]  Eric Dubois,et al.  Bayesian Estimation of Motion Vector Fields , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Amitabha Das,et al.  A new MRF model for robust estimate of occlusion and motion vector fields , 1997, Proceedings of International Conference on Image Processing.

[10]  Emanuele Trucco,et al.  Symmetric Stereo with Multiple Windowing , 2000, Int. J. Pattern Recognit. Artif. Intell..

[11]  Haluk Derin,et al.  Modeling and Segmentation of Noisy and Textured Images Using Gibbs Random Fields , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[13]  Vittorio Murino,et al.  A Probabilistic Approach to the Coupled Reconstruction and Restoration of Underwater Acoustic Images , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Takeo Kanade,et al.  A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Emanuele Trucco,et al.  Efficient stereo with multiple windowing , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[16]  Pascal Fua,et al.  Combining Stereo and Monocular Information to Compute Dense Depth Maps that Preserve Depth Discontinuities , 1991, IJCAI.

[17]  Ramin Zabih,et al.  Non-parametric Local Transforms for Computing Visual Correspondence , 1994, ECCV.

[18]  Laurent Moll,et al.  Real time correlation-based stereo: algorithm, implementations and applications , 1993 .

[19]  Aaron F. Bobick,et al.  Disparity-Space Images and Large Occlusion Stereo , 1994, ECCV.

[20]  José L. Marroquín,et al.  Probabilistic solution of inverse problems , 1985 .