A similarity measure under Log-Euclidean metric for stereo matching

Stereo matching has been one of the most active areas in computer vision for decades. Many methods, ranging from similarity measures to local or global matching cost optimization algorithms, have been proposed. In this paper, we propose a novel similarity measure under log-euclidean metric for stereo matching. A generalized structure tensor is applied to describe a point and the similarity is measured by the distance between the associated tensors. Since the structure tensor lies in a Riemannian manifold, the log-euclidean metric is adopted to calculate the distance between the generalized structure tensors. The proposed similarity measure can provide an effective and efficient way to fuse different features and is independent of illumination change and window scaling. Experiments on standard data set prove that the proposed similarity measure outperforms traditional measures such as SSD, SAD and normalized-cross-correlation (NCC).