3D Registration 三维点云配准 —— 基本概念和ICP算法的C++实现
未完
待读参考:
https://blog.csdn.net/kaspar1992/article/details/54836222
https://www.cnblogs.com/yin52133/archive/2012/07/21/2602562.html
https://blog.csdn.net/u011600592/article/details/70258097
https://blog.csdn.net/Ha_ku/article/details/79755623
https://www.cnblogs.com/21207-iHome/p/6038853.html
https://www.cnblogs.com/sddai/p/6129437.html
论文:方法比较 [Rusinkiewicz et Levoy, 2001], [GRUEN et AKCA, 2005] et [AKCA, 2007]
课堂笔记:
RANSAC算法(RANdom SAmple Consensus随机抽样一致)
ICP算法(Iterative Closest Point迭代最近点)
目的: estimate transform between two dense sets of points
步骤:
1. Assign each point in {Set 1} to its nearest neighbor in {Set 2}
2. Estimate transformation parameters – e.g., least squares or robust least squares
3. Transform the points in {Set 1} using estimated parameters
4. Repeat steps 1-3 until change is very small
可行的预处理:去除离散的噪点。
扩展:PCL云点集