Robust Model-Based Algorithm for Range Image Segmentation

his paper presents a novel range image segmentation algorithm based on a newly proposed obust estimator: Adaptive Scale Sample Consensus (ASSC) [28]. The proposed algorithm is a odel-based top-down technique and directly extracts the required primitives (models) from the aw images. Compared with current popular methods (region-based and edge-based methods), the lgorithm is very robust to noisy or occluded data due to the adoption of the novel robust stimator ASSC. Using a hierarchical implementation, the proposed method is computationally fficient. Experimental results on real range images show that the proposed algorithm is attractive hen compared with other state-of-the-art segmentation methods.