Open3D (C++ API)  0.18.0
Public Member Functions | Data Fields
open3d::pipelines::registration::RANSACConvergenceCriteria Class Reference

Class that defines the convergence criteria of RANSAC. More...

#include <Registration.h>

Public Member Functions

 RANSACConvergenceCriteria (int max_iteration=100000, double confidence=0.999)
 Parameterized Constructor. More...
 
 ~RANSACConvergenceCriteria ()
 

Data Fields

int max_iteration_
 Maximum iteration before iteration stops. More...
 
double confidence_
 Desired probability of success. More...
 

Detailed Description

Class that defines the convergence criteria of RANSAC.

RANSAC algorithm stops if the iteration number hits max_iteration_, or the fitness measured during validation suggests that the algorithm can be terminated early with some confidence_. Early termination takes place when the number of iteration reaches k = log(1 - confidence)/log(1 - fitness^{ransac_n}), where ransac_n is the number of points used during a ransac iteration. Use confidence=1.0 to avoid early termination.

Constructor & Destructor Documentation

◆ RANSACConvergenceCriteria()

open3d::pipelines::registration::RANSACConvergenceCriteria::RANSACConvergenceCriteria ( int  max_iteration = 100000,
double  confidence = 0.999 
)
inline

Parameterized Constructor.

Parameters
max_iterationMaximum iteration before iteration stops.
confidenceDesired probability of success. Used for estimating early termination.

◆ ~RANSACConvergenceCriteria()

open3d::pipelines::registration::RANSACConvergenceCriteria::~RANSACConvergenceCriteria ( )
inline

Field Documentation

◆ confidence_

double open3d::pipelines::registration::RANSACConvergenceCriteria::confidence_

Desired probability of success.

◆ max_iteration_

int open3d::pipelines::registration::RANSACConvergenceCriteria::max_iteration_

Maximum iteration before iteration stops.


The documentation for this class was generated from the following file: