基于多尺度特征及点距离约束的点云配  

Point Cloud Registration Based on Multi-Scale Feature and Point Distance Constraint

作　　者：张旭春 周洪军[2] 郑津津[1] 金一[1] Zhang Xuchun;Zhou Hongjun;Zheng Jinjin;Jin Yi(Department of Precision Machinery and Precision Inustrumentation,University of Science and Technology of China,Hefei,Anhui 230026,China;National Symchrotron Radiation Laboratory,University of Science and Technology of China,Hefei,Anhui 230027,China)

机构地区：[1]中国科学技术大学精密机械与精密仪器系,安徽合肥230026 [2]中国科学技术大学国家同步辐射实验室,安徽合肥230027

出　　处：《激光与光电子学进展》2021年第24期325-333,共9页Laser & Optoelectronics Progress

基　　金：国家自然科学基金联合基金(U1713206);国家自然科学基金重大科研仪器研制项目(61727809)。

摘　　要：已有匹配算法对低重叠度点云的配准精度较低,且对不同尺度的点云比较敏感,为了达到较好的配准效果,需要对点云进行预处理或调节较多参数。快速点特征直方图(FPFH)的复杂度较低,且能保留点云的大部分特征,因此,基于点云的FPFH提出了一种改进的配准算法。首先,基于FPFH提取多尺度特征的关键点,以适应不同规模的点云数据集,同时降低需要调节的参数量。然后,对经过FPFH匹配初步筛选的对应点关系进行精确提取,增加点云内的距离约束条件,降低算法对重叠度的敏感性,获取配准的初步变换矩阵。最后,经过迭代最近点算法进行微调,达到精确配准的目的。实验结果表明,该算法在不同重叠度以及不同规模的点云数据集上均具有较好的配准精度。The existing matching algorithm has a low registration accuracy of point clouds with low overlap, and is more sensitive to different scales. In order to achieve a better registration effect, it is necessary to preprocess or adjust more parameters to the point cloud. Fast point feature histogram(FPFH) has a low complexity, and retains most of the features of the point cloud. Therefore, we propose an improved registration algorithm based on FPFH of the point cloud. First, extracting key points with multi-scale features based on FPFH to adapt to different scales point cloud datasets, while reducing the number of parameters that require adjustment. Then, the corresponding point relationship after the initial screening of FPFH matching is accurately extracted, the distance constraint condition in the point cloud is added, which reduces sensitivity of the algorithm to overlap and the preliminary transformation matrix of registration is obtained. Finally, the iterative closest point algorithm is subjected to fine-tuning to achieve the purpose of accurate registration. The experimental results show that the algorithm has good registration accuracy on different overlap and different scales of point cloud datasets.

关 键 词：机器视觉 点云配准 快速点特征直方图 迭代最近点 欧氏距离 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]