点击次数：

论文类型：期刊论文

发表时间：2015-01-01

发表刊物：ICIC Express Letters

收录刊物：EI、Scopus

卷号：9

期号：5

页面范围：1399-1404

ISSN号：1881803X

摘要：The detection of feature point plays an important role in spatial information extraction from point cloud. Among the reported methods the Difference of Normal (DoN) operator had been proved to be a promising algorithm for segmentation of large 3D point cloud into scale-salient clusters. However, when more details for each cluster are requested the mentioned operator does not work again. In this paper, a variant of DoN (VoDoN) operator is proposed, which is much more suitable for feature point detection from unorganized noisy point cloud. Comparison had been done between DoN and VoDoN and the results show that the proposed method is efficient and robust for feature point detection. ? ICIC International