Fast plane detection in disparity maps

We propose a new method for fast detection of planar patches in disparity maps. We first use a region growing algorithm on random seeds. This approach is similar to the one introduced in [1] for fast line segment detection in images. Then, the parameter-free criterion introduced in [2] is used to keep only the patches that are planar. The main advantage of our method is to be able to estimate the disparity map precision which is usually a critical parameter in other methods. This method is specially well suited to 3D reconstruction of urban environments from low-baseline aerial or satellite stereo pairs where a piecewise-planar model can be applied.