2020-04-22 纸片 09

论文纸片盒子 09

A fast registration algorithm of rock point cloud based on spherical projection and feature extraction

abstract

点云配准是三维重建当中的重要步骤之一。
本文在 iterative closeset point(ICP) 算法的基础上提出了一种快速配置算法。
点云首先通过 球面极坐标 转换为 数字图像。
然后移除边界点并提取图像特征。
通过图像之间的特征配准，实现点云之间的配准。

introduction

related work

coarse registration

粗配准

fine registration

精配准

the registration based on image

图像配准

feature extraction

特征提取

proposed method

basic framework

image

image projection transformation

图像投影变换

image

transformation principle

transformation steps

feature selection

extract feature

remove the boundary point

selection of matching

transform

experimental results and analysis

image

image

image

image

image

experimental data and evaluation standard

the influence of resoluton

comparison of experimental results

summary and future work