A novel approach for segment-based stereo matching problem is presented, based on a modified plane-sweeping strategy. The space is initially divided into planes that are located at different depth levels via plane sweeping by the help of region-wise planarity assumption for the scene. Over-segmented homogenous color regions are utilized for defining planar segment boundaries and plane equations are determined by angle sweeping at different planes. The robustness of depth map estimates is improved by warping segments into the other image via the resulting homographies. In order to refine the reconstruction quality and update segment depths, as well as plane normals, with smoothness and visibility constraints, a greedy search algorithm is applied. Based on the simulation results, the proposed algorithm handles large un-textured regions, depth discontinuities at object boundaries and slanted surfaces. Moreover, the algorithm could be easily upgraded from stereo to multi-view case, since 3D plane equations are already determined.