华东师范大学学报(自然科学版) ›› 2023, Vol. 2023 ›› Issue (2): 95-105.doi: 10.3969/j.issn.1000-5641.2023.02.011

• 计算机科学 • 上一篇    下一篇

基于高重叠度视角的锁销点云模型的快速建立

金志伟, 黄昶*(), 祝瑞红   

  1. 华东师范大学 通信与电子工程学院, 上海 200241
  • 收稿日期:2021-10-09 出版日期:2023-03-25 发布日期:2023-03-23
  • 通讯作者: 黄昶 E-mail:chuang@ee.ecnu.edu.cn

Fast establishment of a point cloud model for a lock pin based onhigh overlapping views

Zhiwei JIN, Chang HUANG*(), Ruihong ZHU   

  1. School of Communication and Electronic Engineering, East China Normal University, Shanghai 200241, China
  • Received:2021-10-09 Online:2023-03-25 Published:2023-03-23
  • Contact: Chang HUANG E-mail:chuang@ee.ecnu.edu.cn

摘要:

基于高重叠度视角, 提出了一种在集装箱码头针对锁销模型快速建立的三维点云拼接方法. 实验使用Azure Kinect深度相机采集场景点云, 并对点云进行预处理, 得到目标点云. 对于视角略微不同的锁销, 在采用采样一致性初始配准算法 (sample consensus initial algorithm, SAC-IA) 的基础上, 利用经典的迭代最近点 (iterative closest point, ICP)算法进行配准, 确定2片点云的重叠位置关系. 在总体拼接过程中, 用锁销在相机z方向投影的包围盒面积的相对大小, 来估计锁销的大体形状; 然后通过对比相邻视角该面积的差值, 选取数量合适的、重叠度较大的点云视角, 保证配准的正确率并减少耗时. 实验结果表明, 该方法对锁销的配准误差较低, 可以较快速地建立适用于类型匹配的工件模型.

关键词: 三维点云, 采样一致性初始配准算法, 迭代最近点算法

Abstract:

In this paper, we propose a method for fast splicing of three-dimensional point clouds based on the lock pin model on a container terminal using high overlapping views. This experiment first uses an Azure Kinect depth camera to collect scene point clouds, and subsequently preprocesses the point cloud. The target point cloud is thus obtained. For lock pins with slightly different views, the sample consensus initial algorithm (SAC-IA) is used on the basis of the classic iterative closest point (ICP) algorithm to determine the overlapping position relationship of the two point clouds. In the overall splicing process, the relative size of the bounding box area projected by the lock pin in the z-direction of the camera is adopted to estimate the general shape of the lock pin; the relative size of the bounding box area is also used to select an appropriate number of point cloud views with high overlap in order to ensure the accuracy of registration and reduce processing time by comparing the difference between the area of adjacent views. The experimental results show that the proposed method has a lower relative registration error for the lock pin, and can quickly establish a workpiece model suitable for type matching.

Key words: 3D point cloud, sample consensus initial algorithm (SAC-IA), iterative closest point (ICP) algorithm

中图分类号: