One-view occlusion detection for stereo matching with a fully connected CRF model
This addresses the problem of occlusion detection in stereo vision for computer vision applications, offering an incremental improvement by reducing computational costs while enhancing accuracy.
The paper tackles stereo matching by introducing a one-view occlusion detection (OVOD) method that identifies occluded regions and improves disparity maps without needing a second view or left-right checks. The approach achieves state-of-the-art results on the Middlebury dataset, with improvements in median, average, and mean squared error metrics.
In this paper, we extend the standard belief propagation (BP) sequential technique proposed in the tree-reweighted sequential method 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 only one 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-of-the-art especially for median, average and mean squared error metrics.