摘要
针对传统点云匹配算法的局限性造成的点云匹配时间、效率低的问题,本文对传统算法在点云配准中进行了研究,有效改进了传统算法的局限性。本文搭建了双目视觉平台,并对其进行了参数校正以获取更高精度的点云数据,采用了八叉树算法对获取的数据进行了拓扑关系的建立,然后利用八叉树改进的ICP配准算法进行精确配准,并使用测得的数据进行了验证实例,结果表明,此方法能够有效提高精度和效率。
Aiming at the problem of point cloud matching time and low efficiency caused by the limitations of traditional point cloud matching algorithm,this paper studies the traditional algorithm in point cloud registration,which effectively improves the limitations of traditional algorithms.This paper builds a binocular vision platform,and performs parameter correction to obtain higher precision point cloud data.The octree algorithm is used to establish the topological relationship of the acquired data,and then improved by octree.The ICP registration algorithm performs accurate registration and uses the measured data to verify the example.The results show that this method can effectively improve the accuracy and efficiency.
作者
唐瑞尹
王长伟
张敬
范乃德
Tang Ruiyin;Wang Changwei;Zhang Jing;Fan Naide(College of Electrical Engineering,North China University of Science and Technology,Tangshan,Heibei 063210,China;College of Civil and Architectural Engineering,North China University of Science and Technology,Tangshan,Hebei 063210,China)
出处
《应用激光》
CSCD
北大核心
2020年第2期349-353,共5页
Applied Laser
基金
国家青年自然科学基金(项目编号:51105273)
华北理工大学创新项目(项目编号:2019S20)。
关键词
双目视觉
系统标定
八叉树算法
ICP配准
binocular vision
system calibration
octree algorithm
ICP registration
