点击次数：

论文类型：期刊论文

发表时间：2011-08-01

发表刊物：ICIC Express Letters

收录刊物：EI、Scopus

卷号：5

期号：8 B

页面范围：2741-2746

ISSN号：1881803X

摘要：In this paper, we consider the problem of 3D point cloud classification for ground robots in outdoor environment. This problem is important for various tasks from environment modeling to obstacle avoidance for autonomous mobile robot navigation. In order to improve the description of natural scene, we propose novel features with the consideration of surface condition and environmental characters. By introducing a fuzzy inference system, feature fusion is implemented to produce a high-level feature which represents the inherent fuzziness of natural objects. The classification of 3D point cloud is approached by a fuzzy entropy method in the local area. Experimental results demonstrate the validity of the proposed approaches. ? 2011 ISSN 1881-803X.