A colour correlation-based stereo matching based on 1D windows

In this paper, we propose an original approach to colour correlation-based stereo matching with mono-dimensional windows. The result of the algorithm is a quasi-dense disparity map associated with its confidence map. For each pixel, correlation indices are computed for several widths of windows and several positions of the current pixel. Three criteria, extracted from each correlation curve, are combined by a fuzzy filter to define a confidence measure. A basic decision rule computes the disparity value and its associated confidence for the most of the image pixels. A first study shows results obtained on grey level images with our 1D method and a classical 2D method. Here, the 1D approach presents better results. Moreover, our method is applied to the RGB colour space. A disparity map is computed with each of the three colour components. A fusion step allows to compute the disparity values based on these three disparity maps. The method is validated on the Tsukuba image pair. In the first time, we show that our method presents lower error rates with the RGB colour space than with the grey level image and this, for identical density rates. In a second time, our results (with the colour way) are compared in terms of errors and density rate with those obtained using similar colour 2D methods (presented on the Middlebury website). Our algorithm is ranked in the first places for each area of the image.