Dense Stereo Matching With Edge-Constrained Penalty Tuning

Dense stereo matching has been an indispensable technique for 3-D exploitation of imagery, in which semiglobal matching (SGM) is one of the outstanding approaches and has numerous variations in the literature. However, generating accurate disparity in depth discontinuity areas remains challenging, since the cost-aggregation step of SGM providing consistency constraints is sensitive to nonoptimal parametrizations of relevant penalty functions. In this letter, we present a gradual SGM cost aggregation that comprises a penalty tuning process and involves edge feature knowledge. To be more specific, we propose an additional penalty parameter and a weighting formula to handle edge pixels with depth variations, acquiring satisfactory depth estimation by preserving sharp geometric edges and maintaining smoothness without raising extra noise. Evaluations on well-known benchmark and real large-scale images are promising, and the latter case yields point clouds with sharp edges and smooth surfaces showing the effectiveness and feasibility of the proposed method.