基于相移的三维扫描数据自动配准方法研究  

Research on Automatic Registration Method of 3D Scanning Data Based on Phase Shift

作　　者：刘颖[1] 刘宝华 LIU Ying;LIU Bao-hua(Xi'an Eurasia University,Xi'an 710065 China)

机构地区：[1]西安欧亚学院,陕西西安710065

出　　处：《自动化技术与应用》2024年第1期39-43,共5页Techniques of Automation and Applications

基　　金：陕西省科技厅(2018GY-059)。

摘　　要：在三维扫描过程中,常因受到设备自身因素与点云丢失的限制而难以一次性完成数据采集。为准确实现物体三维模型重构,提出基于相移的三维扫描数据自动配准方法。首先设置旋转台,利用非接触式结构光方法获得转动轴的有关信息,从而采集目标点云数据。在此基础上,结合任意一点与其周围点曲率信息建立曲率图,对全部顶点做曲率运算,将数据划分为连续子块,计算每个子块中平均值和方差,从而提取关键特征点。然后获取两幅具有部分重叠关系图像的相对位移,采用交叉功率谱的傅里叶变换完成位移估计,再通过构造与组合点对、粗略与精确配准去除噪声点,实现三维扫描数据自动配准。仿真实验表明,该方法能够在确保配准精度的同时提高配准方法的运行效率,可靠性和实用性较强。In the process of 3D scanning,it is often difficult to complete the data collection at one time due to the limitations of equipment and point cloud loss.In order to reconstruct the 3D model accurately,an automatic registration method of 3D scan data based on phase shift is proposed.First,a rotary table is set,and the information about the rotation axis is obtained by using the non-contact structural light method,so as to collect the target point cloud data.On this basis,the curvature graph is established by combining the curvature information of any point and its surrounding points,and the curvature operation is performed on all vertices.The data is divided into continuous sub-blocks,and the mean value and variance in each sub-block are calculated,so as to extract key feature points.Then,the relative displacements of two images with partial overlapping relationship are obtained,the displacement is estimated by using the Fourier transform of the cross power spectrum,and the noise points are removed by constructing and combining point pairs,rough and accurate registration,so as to realize the automatic registration of 3D scanning data.The simulation results show that this method can improve the operation efficiency,reliability and practicability of the registration method while ensuring the registration accuracy.

关 键 词：相移 三维扫描数据 数据配准 非接触采集 傅里叶变换 曲率图 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]