AlignmentParameters Class Reference

Parameters to configure the Align.IcpMatch(PointCloud, PointCloud, AlignmentParameters) algorithm. More...

Public Member Functions
	AlignmentParameters ()
	Default constructor using reasonable default values.

Properties
long	MaxModelPoints [get, set]
	Number of points from the model point cloud to retain and use. More...
long	MaxScenePoints [get, set]
	Number of points from the scene point cloud to retain and use. More...
int	MaxIterations [get, set]
	Maximum number of iterations to execute.
double	Tolerance [get, set]
	Tolerance for stopping criteria. More...
double	MinImprovement [get, set]
	Threshhold for minimum improvement for early stopping criteria. More...
double	CorrespondenceThreshold [get, set]
	Parameter for shape sensitivity. More...
double	ConvergenceRadius [get, set]
	Convergence radius to define when two points are considered as a converged match.
bool	Prealign [get, set]
	True, if pre-alignement of point clouds should be done using the center of gravity.
CorrespondenceType	CorrespondenceMethod [get, set]
	Correspondence type used.

Detailed Description

Parameters to configure the Align.IcpMatch(PointCloud, PointCloud, AlignmentParameters) algorithm.

Property Documentation

CorrespondenceThreshold

double CorrespondenceThreshold

getset

Parameter for shape sensitivity.

It is defined by a value between 0 and 1. A higher value means higher sensitivity.A value of 0 corresponds to the classical ICP without any shape sensitivity.A value between 0.8 and 0.9 is recommended as default value when aligning point clouds.

MaxModelPoints

long MaxModelPoints

getset

Number of points from the model point cloud to retain and use.

Points are selected randomly by the ICP algorithm. Higher numbers tend to lead to much higher processing times. If this value is zero, all points are used.

MaxScenePoints

long MaxScenePoints

getset

Number of points from the scene point cloud to retain and use.

Points are selected randomly by the ICP algorithm. Higher numbers tend to lead to much higher processing times. If this value is zero, all points are used.

MinImprovement

double MinImprovement

getset

Threshhold for minimum improvement for early stopping criteria.

The mean distance between aligned point clouds has to differ more than this value from the results of the previous iteration. Otherwise iteration stops.

Tolerance

double Tolerance

getset

Tolerance for stopping criteria.

Iteration stops if mean distance between aligned point clouds is equal/below this value.