利用局部熵和重复度检测特征点  

Feature Point Detection Based on Local Entropy and Repeatability Rate

作　　者：武剑洁[1] 王启付[1] 黄正东[1] 黄运保[1] 

机构地区：[1]华中科技大学国家CAD支撑软件工程技术研究中心,武汉430074

出　　处：《计算机辅助设计与图形学学报》2005年第5期1046-1053,共8页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家"十五"重大科技攻关项目"产品设计CAD"( 2 0 0 1BA2 0 1A0 2 )

摘　　要：以三维散乱点在局部邻域内的熵变化为检测准则,利用局部熵突变发生在曲面形状变化剧烈区域的特性,描述采样点属于某个特征的可能性;同时引入重复度;以反映在不同大小的局部窗口下采样点被检测为特征点的频度,获取特征点集实验结果表明,该算法稳定性较好。Local entropy of data points changing sharply over neighborhood is introduced as a detection criterion to classify points as a feature, where the local surface curvature changes greatly. Repeatability rate is introduced as well to reflect the frequency that a sample point is detected as a feature point during its verification at different sizes of local windows. Experiments show that such a multi-scale feature point detection approach can improve the reliability of the algorithm. Furthermore, non-uniformly sampled point cloud can be dealt with.

关 键 词：特征点检测 散乱点 局部熵 重复度 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]