首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于特征点提取改进的ICP算法
引用本文:刘冬秋,景凤宣,谢晓尧.基于特征点提取改进的ICP算法[J].贵州师范大学学报(自然科学版),2013(6):106-110.
作者姓名:刘冬秋  景凤宣  谢晓尧
作者单位:贵州师范大学贵州省信息与计算科学重点实验室,贵州贵阳550001
基金项目:基于数字图形介质理论的高速公路及高边坡稳定状态快速评价技术研究及应用(黔科合GZ字[2012]3017)贵州师范大学,2012.06-2014.12.
摘    要:点云数据在逆向工程,可视化技术,虚拟现实技术,机器视觉等领域具有十分广泛的应用。提出了基于特征点提取的改进ICP算法,在曲率特征和管理点云数据的索引方法 K-D tree的基础上对改进的ICP算法进行了详细的分析,将该算法应用到对雕像数据进行精确配准,实验表明该算法在一定程度上提高了配准的精度和效率。

关 键 词:点云数据  ICP  四元数法  曲率特征  K-D  tree

Improved ICP algorithm based on feature points extraction
LIU Dong-qiu,JING Feng-xuan,XIE Xiao-yao.Improved ICP algorithm based on feature points extraction[J].Journal of Guizhou Normal University(Natural Sciences),2013(6):106-110.
Authors:LIU Dong-qiu  JING Feng-xuan  XIE Xiao-yao
Institution:( Key Laboratory of Information and Computing Science of Guizhou Province, Guizhou Normal University, Guiyang, Guizhou 550001, China)
Abstract:Point cloud data have very extensive application in reverse engineering visualization technol- ogy, virtual reality technology, machine vision and other fields. The improved ICP algorithm is proposed in this paper basing on the original ICP algorithm. This paper introduces the unit four element method and has carried on the detailed analysis in the improved ICP algorithm which based on curvature fea- tures and K - D tree. The improved ICP algorithm is applied to the statue data for accurate registration and the experimental result show that the algorithm can improve the precision and efficiency of registra- tion to some extent.
Keywords:point cloud data  ICP  four element method  curvature features  K - D tree
本文献已被 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号