An effective segmentation algorithm to range images

Abstract

In this paper, we try to present an improved effective segmentation algorithm for range images. Our work was partially motivated by the desire to overcome the drawbacks inherent to most of the algorithms known from the literature, which edge detection is mostly criticized for its tendency to produce non-connected boundaries and region-based techniques suffer from a number of problems, such as complex control structures, the selection of initial regions, the actual number of clusters and an over segmentation. It provides edge strength measures that have a straightforward geometric interpretation and supports a classification of edge points into several subtypes. We consider analysis of geometric properties of edge points as the key to solve the problem of image segmentation and propose a geometric model to deduce algorithm template. And we adopt morphological method to boundaries obtained in the edge map as to save much time. Experiments were performed in a popular range image database and the results were compared to five other traditional range image segmentation algorithms, demonstrating that it could achieve more edge information of the object and overcome the shortcoming of non-connected boundaries to a certain extent. It is proved to be correct and effective.