EXPERIMENTS IN CURVATURE-BASED SEGMENTATION OF RANGE DATA

This paper focuses on the experimental evaluation of a range image seg mentation system which partitions range data into homogeneous surface patches using estimates of the sign of the mean and Gaussian curvature s. We report the results of an extensive testing program aimed at inve stigating the behavior of important experimental parameters such as th e probability of correct classification and the accuracy of curvature estimates, measured over variations of significant segmentation variab les. Evaluation methods in computer vision are often unstructured and subjective: this paper contributes a useful example of extensive exper imental assessment of surface-based range segmentation.