TY  - JOUR
AU  - Mikhail Mozerov
AU  - Joost Van de Weijer
PY  - 2019//
TI  - One-view occlusion detection for stereo matching with a fully connected CRF model
T2  - TIP
JO  - IEEE Transactions on Image Processing
SP  - 2936
EP  - 2947
VL  - 28
IS  - 6
KW  - Stereo matching
KW  - energy minimization
KW  - fully connected MRF model
KW  - geodesic distance filter
N2  - In this paper, we extend the standard belief propagation (BP) sequential technique proposed in the tree-reweighted sequential method [15] to the fully connected CRF models with the geodesic distance affinity. The proposed method has been applied to the stereo matching problem. Also a new approach to the BP marginal solution is proposed that we call one-view occlusion detection (OVOD). In contrast to the standard winner takes all (WTA) estimation, the proposed OVOD solution allows to find occluded regions in the disparity map and simultaneously improve the matching result. As a result we can perform onlyone energy minimization process and avoid the cost calculation for the second view and the left-right check procedure. We show that the OVOD approach considerably improves results for cost augmentation and energy minimization techniques in comparison with the standard one-view affinity space implementation. We apply our method to the Middlebury data set and reach state-ofthe-art especially for median, average and mean squared error metrics.
L1  - http://refbase.cvc.uab.es/files/MoW2019.pdf
UR  - http://dx.doi.org/10.1109/TIP.2019.2892668
N1  - LAMP; 600.098; 600.109; 602.133; 600.120
ID  - Mikhail Mozerov2019
ER  -