A Bayesian segmentation of stereo pairs
Georgios A. Triantafyllidis, Dimitrios K. Tzovaras, Michael Gerassimos Strintzis · 2002
A Bayesian scheme is proposed for the identification of the occlusion and visible background and foreground areas in a noisy stereoscopic image pair. Three hypotheses are used for the formulation of Bayes decision rules: the first describes the visible foreground areas, the second describes the visible background areas and the last describes the occlusion areas. Experimental results illustrating the performance of the proposed technique are presented and evaluated.