一种基于特征点的地面激光点云全局配准方法  

A Global Registration Method of Terrestrial Laser Point Cloud Based on Feature Points

作　　者：杨志华 张云生[1] YANG Zhihua;ZHANG Yunsheng(School of Geoseienees and Info-Physics, Central South University, Changsha 410083, China)

机构地区：[1]中南大学地球科学与信息物理学院,湖南长沙410083

出　　处：《测绘与空间地理信息》2018年第4期66-68,71,共4页Geomatics & Spatial Information Technology

基　　金：卫星测绘技术与应用国家测绘地理信息局重点实验室开放基金(KLSMTA-201505);国家重点基础研究发展计划资助项目(973计划)(2012CB719903);国家自然科学基金(41201472);水能资源利用关键技术湖南省重点实验室开放基金(PKLHD201310)资助

摘　　要：针对当前地面激光扫描(TLS)点云配准自动化程度低且耗时的问题,本文提出一种基于特征点和改进FGR(fast global registration)算法的TLS点云全局配准方法。该方法一共分为三步:首先对点云进行粗差剔除和降采样;然后提取Do G(Difference-of-Gaussian)特征点和进行FPFH(fast point feature histogram)描述,进而进行双向一致性匹配;最后使用FGR算法进行优化获得点云之间初始参数,结合标准ICP算法实现TLS点云的高精度配准。利用7站地面激光点云数据进行实验,结果表明本方法可以在保证配准精度的前提下获得较高的配准效率。Aiming at the problem of low degree of automatic and time consuming to align pair-wise of TLS point cloud,a global registration method based on feature point and FGR（ fast global registration） algorithm is proposed. The method consists of three steps： at first,the outlier is removed and down-sampling is carried out; After that,the Do G（ Difference-of-Gaussian） feature is extracted and the FPFH（ fast point feature histogram） is described,then matching based on FPFH is performed; Finally,FGR algorithm is used to obtain the initial parameters and standard ICP algorithm is used to optimize the transformation parameters on original point cloud. Seven stations of TLS data are employed to perform the experiment,the results reveal that the method can improve the registration efficiency ensuring the registration accuracy.

关 键 词：点云配准 特征点提取 FGR算法 ICP 

分 类 号：P225[天文地球—大地测量学与测量工程]