Range Image Segmentation by Randomized Region Growing and Bayesian Edge Regularization

Abstract

We presented and evaluated a new Bayesian method for range image segmentation. The method proceeds in to stages. First, an initial segmentation was produced by a randomized region growing technique. The produced segmentation was considered as a degraded version of the ideal segmentation, which should be then refined. In the second stage, image pixels not labeled in the first stage were labeled by using a Bayesian estimation, based on some prior assumptions on the regions in the image. Image priors were modeled by a new Markov Random Field (MRF) model. Contrary to most of the authors in range image segmentation, who use only surface smoothness MRF models, our MRF model takes into account also the smoothness of region boundaries. Tests performed with real images from the ABW database show the great potential of the proposed method for significantly improving the segmentation results.