计算机与现代化 ›› 2024, Vol. 0 ›› Issue (02): 1-6.doi: 10.3969/j.issn.1006-2475.2024.02.001

• 算法分析与设计 •    下一篇

基于3D-SIFT与4PCS融合的大数据量点云快速配准方法

  

  1. (1.上海交通大学机械与动力工程学院,上海 200240; 2.绍兴市特种设备检测院,浙江 绍兴 312071)
  • 出版日期:2024-02-19 发布日期:2024-03-19
  • 作者简介: 作者简介:李家乐(1999—),男,河南周口人,硕士研究生,研究方向:金属件视觉定位,E-mail: lijiale@sjtu.edu.cn; 李哲润(1999—),男,福建莆田人,硕士研究生,研究方向:变形零件测量,E-mail: leonard0@sjtu.edu.cn; 赵勇(1984—),男,上海人,副研究员,博士,研究方向:视觉测量,E-mail: default1984@126.com; 通信作者:张杨(1985—),男,上海人,副教授,博士,研究方向:机器人与计算机集成系统,数字化测量技术与装备,E-mail: meyzhang@sjtu.edu.cn。
  • 基金资助:
    上海市自然科学基金资助项目(22ZR1435200)
       

A Fast Registration Method for Massive Point Clouds Based on 3D-SIFT and 4PCS

  1. (1. School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China;
    2. Shaoxing Special Equipment Testing Institute, Shaoxing 312071, China)
  • Online:2024-02-19 Published:2024-03-19

摘要: 摘要:测量点云与模型点云的配准是视觉定位的关键。针对测量点云数据量大且与CAD模型点云重叠率低造成视觉定位精度差、算法效率低的问题,提出一种基于三维尺度不变特征变换(3D-SIFT)与4点快速鲁棒匹配算法(4PCS)融合的测量点云与模型点云配准方法。首先利用深度相机对零件进行点云提取并对提取到的测量点云进行降噪和滤波处理;接着利用3D-SIFT特征点提取算法对测量点云和CAD模型点云进行特征点提取;最后把提取的特征点作为4PCS算法的初始值进行2种点云数据的配准。与常用的4PCS算法、Super-4PCS算法相比,在算法仿真与实际应用实验结果表明,本文算法在保证配准精度的前提下将配准速度提高30%以上。



关键词: 关键词:测量点云, 模型点云, SIFT, 4PCS算法, 点云配准

Abstract: Abstract: The registration of measurement point cloud and model point cloud is the key of visual positioning. Aiming at the problems of poor visual positioning accuracy and low algorithm efficiency caused by large amount of measurement point cloud data and low overlap rate with CAD model point cloud, a registration method of measurement point cloud and model point cloud based on the fusion of 3D scale invariant feature transform (3D-SIFT) and four point fast robust matching algorithm (4PCS) is proposed. Firstly, the depth camera is used to extract the point cloud of the part, and the extracted measurement point cloud is denoised and filtered; Then 3D-SIFT feature point extraction algorithm is used to extract feature points from measurement point cloud and CAD model point cloud; Finally, the extracted feature points are used as the initial values of the 4PCS algorithm to achieve the registration of the two point cloud data. Compared with the commonly used 4PCS algorithm and Super-4PCS algorithm, the algorithm simulation and experimental results show that the proposed algorithm can improve the registration speed by more than 30% on the premise of ensuring the registration accuracy.

Key words: Key words: measurement point cloud, model point cloud, SIFT, 4PCS, point cloud registration

中图分类号: