Skip to content

Latest commit

 

History

History

RoPSMatcher

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
RoPS Toolbox2
RoPS Toolbox2
 
 
CalRoPSFun.m
CalRoPSFun.m
 
 
RPoS.m
RPoS.m
 
 
RoPSMatchFun.m
RoPSMatchFun.m
 
 
data.mat
data.mat
 
 
main.asv
main.asv
 
 
main.m
main.m
 
 
pcNormals.m
pcNormals.m
 
 
readme.txt
readme.txt
 
 

readme.txt

README
================================================================================================
Version 1.0, 16-Jan-2018

The code has been tested with MATLAB 2017a/b on a PC with 64-bit windows 7/10.

================================================================================================

Use of this code is free for research purposes only.

================================================================================================
For two 3D point cloud, sometimes we need align them coarsely by hand or feature matching. Rotational projection statistics(RoPS)[1] is a robust 3D feature for point cloud just like SIFT feature for image.
The "RoPS Toolbox2" is written by Prof. Yulan Guo, including RoPS calculation and RoPS feature matching. 
I add the rotation/translation calculation in RoPSMatchFun.m.
It should be noted that though RoPS feature calculation had been implemented in PCL 1.8.0, the feature matching and rotation/translation calculation are not added in PCL. 

[1] Guo, Yulan, et al. "Rotational Projection Statistics for 3D Local Surface Description and Object Recognition." International Journal of Computer Vision 105.1(2013):63-86.