Multiresolution phase-based bidirectional stereo matching with provision for discontinuity and occlusion

Stereo image matching is the most robust and domain-independent-way of reco nstructing object surfaces from perspective images. Dense feature space mat ching is desirable because it constructs a disparity field without arbitrar y selection of interest points for individual matching. Multiresolution or coarse-to-fine strategies have been shown to be effective in overcoming the inherent ambiguities of dense feature space matching. We use Gabor phase a s the basis for dense multiresolution matching, as it is a stable, ubiquito us feature of a signal. The use of Gabor-like complex wavelets enables the efficient transformation of images to Gabor-phase-based feature pyramids. D isparity discontinuity and occlusions are the major potential disruptions t o coarse-to-fine image matching. Through perspective geometry, we show that depth discontinuities are the direct cause of the discontinuity of dispari ty field, and bidirectional matching is required to detect disparity discon tinuities (and their dual counterpart, occlusions) in both views. To handle these, a global objective function incorporating feature similarity, dispa rity smoothness, and discontinuity/occlusions is established under the maxi mum a posteriori probability criterion and equivalently transformed into a minimum description length criterion. A general procedure, using stochastic relaxation with special provision for occlusions, is developed for minimis ing the objective function. The result is a disparity field which is regula rised in the continuous regions, while the discontinuities and occlusions a re detected and preserved. Some results from an aerial terrain image pair i ndicate the applicability of this approach. (C) 1998 Academic Press.