Stereo matching is one of the most important topics in computer vision and aims at generating precise depth maps for various applications. The major challenge of stereo matching is to suppress inevitable errors occurring in smooth, occluded, and discontinuous regions. In this paper, the proposed stereo matching system uses segment-based superpixels and matching cost. After determination of edge and smooth regions and selection of matching cost, we suggest the segment-based adaptive support weights in cost aggregation instead of color similarity and spatial proximity only. The proposed dual-path depth refinements use the cross-based support region by referring texture features to correct the inaccurate disparities with iterative procedures to improve the depth maps for shape reserving. Specially for leftmost and rightmost regions, the segment-based refinement can greatly improve the mismatched disparity holes. The experimental results show that the proposed system can achieve higher accurate depth maps than the conventional methods.

No abstract

No abstract

In this paper, we analyze the limitation of ρ-domain based rate-quantization (R-Q) model. We find out that a characteristic-based R-Q model can be derived from ρ-domain to q-domain. Experimental data show that such a characteristic-based R-Q model can provide a more accurate estimation of the actual bitrate than existing models for both frame-level and macroblock(MB)-level. In addition, a simple analysis of computational complexity of our quantizationfree characteristics extraction framework shows that our model is faster than existing variance and ρ-domain based R-Q models.

No abstract