Recent advances in range image segmentation

In this paper we discuss recent advances in range image segmentation concerning two important issues: experimental comparison of segmentation algorithms and the potential of edge-based segmentation approaches. The development of a rigorous framework for experimental comparison of range image segmentation algorithms is of great practical importance. This allows us to assess the state of the art by empirically evaluating range image segmentation algorithms. On the other hand, it help us figure out collective weaknesses of current algorithms, so as to identify requirements of further research. By means of a simple adaptive edge grouping algorithm we show the potential of edge-based segmentation techniques to outperform region-based approaches in terms of both segmentation quality and computation time. The aspect of edge-based complete range image segmentation has not been fully explored so far in the literature and deserves more attention in the future.