摘要
针对目前常用配准算法不能满足生产制造行业中高精度工艺要求的问题,本文基于三维点云提出一种改进三维形状上下文(3DSC)点云配准的有效解决方案。首先,通过改进的降采样方式设定阈值采集轮廓点云,对采集的点云依次进行三维网格划分形成形状上下文。然后,进行改进的3DSC初始配准,进而采用迭代最近点(ICP)精确配准,实现了源点云与目标点云之间的旋转平移变换。为验证改进算法的有效性,采用FPFH-ICP、PFH-ICP、传统3DSC和本文改进算法进行配准实验对比。实验结果表明,对于bunny点云和flowerpot点云,本文改进算法精度分别可达2.25355e-05 m和9.96902e-06 m,明显优于其他算法的配准精度。与传统3DSC配准算法相比,改进的3DSC配准算法可节省75%~85%的配准时间。改进的3DSC点云配准方法有利于提高配准精度且能优化配准时间,提高了配准效率。
In view of the problem that the commonly used registration algorithms cannot meet the highprecision process requirements in the manufacturing industry,this paper proposes an improved 3DSC point cloud registration based on the 3D point cloud.Firstly,the threshold value is set to collect the contour point cloud by the improved down-sampling method,and the collected point cloud is divided into 3D mesh in turn to form a 3D shape context.Then,the improved 3DSC coarse registration is performed,and the ICP fine registration is used to realize the rotation and translation transformation between the source point cloud and the target point cloud.In order to verify the effectiveness of the improved algorithm,the traditional 3DSC,FPFH-ICP,PFH-ICP and the improved algorithm in this paper are used to compare the registration experiments.The experiment results show that the accuracy of the improved algorithm can reach 2.25355e-05 m and 9.96902e-06 m respectively for the bunny point cloud and the flowerpot point cloud,which is obviously better than the registration accuracy of other algorithms.Compared with the traditional 3DSC registration algorithm,the improved 3DSC registration algorithm can save 75%~85%of the registration time.The improved 3DSC point cloud registration method is beneficial to improve the registration accuracy,optimize the registration time,and improve the registration efficiency.
作者
赵云涛
齐佳祥
李维刚
甘镭
ZHAO Yun-tao;QI Jia-xiang;LI Wei-gang;GAN Lei(Engineering Research Center for Metallurgical Automation and Detecting Technology of Ministry of Education,Wuhan University of Science and Technology,Wuhan 430081,China;College of Information Science and Engineering,Wuhan University of Science and Technology,Wuhan 430081,China)
出处
《液晶与显示》
CAS
CSCD
北大核心
2022年第12期1590-1597,共8页
Chinese Journal of Liquid Crystals and Displays
基金
国家自然科学基金(No.51774219)。
关键词
点云配准
三维形状上下文
迭代最近点
三维视觉
point cloud registration
3D shape context
iterative closest point
3D vision
