論文紙片盒子 09
A fast registration algorithm of rock point cloud based on spherical projection and feature extraction
abstract
點云配準是三維重建當中的重要步驟之一。
本文在 iterative closeset point(ICP) 算法的基礎上提出了一種快速配置算法。
點云首先通過 球面極坐標 轉換為 數字圖像。
然后移除邊界點并提取圖像特征。
通過圖像之間的特征配準，實現點云之間的配準。
introduction
related work
coarse registration
粗配準
fine registration
精配準
the registration based on image
圖像配準
feature extraction
特征提取
proposed method
basic framework
image
image projection transformation
圖像投影變換
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
