W3cubDocs

/PointCloudLibrary

MEstimatorSampleConsensus represents an implementation of the MSAC (M-estimator SAmple Consensus) algorithm, as described in: "MLESAC: A new robust estimator with application to estimating image geometry", P.H.S. More...

#include <pcl/sample_consensus/msac.h>

Public Types

using Ptr = shared_ptr< MEstimatorSampleConsensus< PointT > >
using ConstPtr = shared_ptr< const MEstimatorSampleConsensus< PointT > >
- Public Types inherited from pcl::SampleConsensus< PointT >
using Ptr = shared_ptr< SampleConsensus< PointT > >
using ConstPtr = shared_ptr< const SampleConsensus< PointT > >

Public Member Functions

MEstimatorSampleConsensus (const SampleConsensusModelPtr &model)
MSAC (M-estimator SAmple Consensus) main constructor. More...
MEstimatorSampleConsensus (const SampleConsensusModelPtr &model, double threshold)
MSAC (M-estimator SAmple Consensus) main constructor. More...
bool computeModel (int debug_verbosity_level=0) override
Compute the actual model and find the inliers. More...
- Public Member Functions inherited from pcl::SampleConsensus< PointT >
SampleConsensus (const SampleConsensusModelPtr &model, bool random=false)
Constructor for base SAC. More...
SampleConsensus (const SampleConsensusModelPtr &model, double threshold, bool random=false)
Constructor for base SAC. More...
void setSampleConsensusModel (const SampleConsensusModelPtr &model)
Set the Sample Consensus model to use. More...
SampleConsensusModelPtr getSampleConsensusModel () const
Get the Sample Consensus model used. More...
virtual ~SampleConsensus ()
Destructor for base SAC. More...
void setDistanceThreshold (double threshold)
Set the distance to model threshold. More...
double getDistanceThreshold () const
Get the distance to model threshold, as set by the user. More...
void setMaxIterations (int max_iterations)
Set the maximum number of iterations. More...
int getMaxIterations () const
Get the maximum number of iterations, as set by the user. More...
void setProbability (double probability)
Set the desired probability of choosing at least one sample free from outliers. More...
double getProbability () const
Obtain the probability of choosing at least one sample free from outliers, as set by the user. More...
void setNumberOfThreads (const int nr_threads=-1)
Set the number of threads to use or turn off parallelization. More...
int getNumberOfThreads () const
Get the number of threads, as set by the user. More...
virtual bool refineModel (const double sigma=3.0, const unsigned int max_iterations=1000)
Refine the model found. More...
void getRandomSamples (const IndicesPtr &indices, std::size_t nr_samples, std::set< index_t > &indices_subset)
Get a set of randomly selected indices. More...
void getModel (Indices &model) const
Return the best model found so far. More...
void getInliers (Indices &inliers) const
Return the best set of inliers found so far for this model. More...
void getModelCoefficients (Eigen::VectorXf &model_coefficients) const
Return the model coefficients of the best model found so far. More...

Additional Inherited Members

- Protected Member Functions inherited from pcl::SampleConsensus< PointT >
double rnd ()
Boost-based random number generator. More...
- Protected Attributes inherited from pcl::SampleConsensus< PointT >
SampleConsensusModelPtr sac_model_
The underlying data model used (i.e. More...
Indices model_
The model found after the last computeModel () as point cloud indices. More...
Indices inliers_
The indices of the points that were chosen as inliers after the last computeModel () call. More...
Eigen::VectorXf model_coefficients_
The coefficients of our model computed directly from the model found. More...
double probability_
Desired probability of choosing at least one sample free from outliers. More...
int iterations_
Total number of internal loop iterations that we've done so far. More...
double threshold_
Distance to model threshold. More...
int max_iterations_
Maximum number of iterations before giving up. More...
int threads_
The number of threads the scheduler should use, or a negative number if no parallelization is wanted. More...
boost::mt19937 rng_alg_
Boost-based random number generator algorithm. More...
std::shared_ptr< boost::uniform_01< boost::mt19937 > > rng_
Boost-based random number generator distribution. More...

Detailed Description

template<typename PointT>
class pcl::MEstimatorSampleConsensus< PointT >

MEstimatorSampleConsensus represents an implementation of the MSAC (M-estimator SAmple Consensus) algorithm, as described in: "MLESAC: A new robust estimator with application to estimating image geometry", P.H.S.

Torr and A. Zisserman, Computer Vision and Image Understanding, vol 78, 2000. The difference to RANSAC is how the quality of a model is computed: RANSAC counts the number of inliers, given a threshold. The more inliers, the better the model is - it does not matter how close the inliers actually are to the model, as long as they are within the threshold. MSAC changes this by using the sum of all point-model distances as the quality measure, however outliers only add the threshold instead of their true distance. This method can lead to better results compared to RANSAC.

Author
Radu B. Rusu

Definition at line 60 of file msac.h.

Member Typedef Documentation

ConstPtr

template<typename PointT >
using pcl::MEstimatorSampleConsensus< PointT >::ConstPtr = shared_ptr<const MEstimatorSampleConsensus<PointT> >

Definition at line 66 of file msac.h.

Ptr

template<typename PointT >
using pcl::MEstimatorSampleConsensus< PointT >::Ptr = shared_ptr<MEstimatorSampleConsensus<PointT> >

Definition at line 65 of file msac.h.

Constructor & Destructor Documentation

MEstimatorSampleConsensus() [1/2]

template<typename PointT >
pcl::MEstimatorSampleConsensus< PointT >::MEstimatorSampleConsensus ( const SampleConsensusModelPtr & model )
inline

MSAC (M-estimator SAmple Consensus) main constructor.

Parameters
[in] model a Sample Consensus model

Definition at line 80 of file msac.h.

References pcl::SampleConsensus< PointT >::max_iterations_.

MEstimatorSampleConsensus() [2/2]

template<typename PointT >
pcl::MEstimatorSampleConsensus< PointT >::MEstimatorSampleConsensus ( const SampleConsensusModelPtr & model,
double threshold
)
inline

MSAC (M-estimator SAmple Consensus) main constructor.

Parameters
[in] model a Sample Consensus model
[in] threshold distance to model threshold

Definition at line 91 of file msac.h.

References pcl::SampleConsensus< PointT >::max_iterations_.

Member Function Documentation

computeModel()

template<typename PointT >
bool pcl::MEstimatorSampleConsensus< PointT >::computeModel ( int debug_verbosity_level = 0 )
overridevirtual

Compute the actual model and find the inliers.

Parameters
[in] debug_verbosity_level enable/disable on-screen debug information and set the verbosity level

Implements pcl::SampleConsensus< PointT >.

Definition at line 48 of file msac.hpp.

References pcl::geometry::distance().


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

© 2009–2012, Willow Garage, Inc.
© 2012–, Open Perception, Inc.
Licensed under the BSD License.
https://pointclouds.org/documentation/classpcl_1_1_m_estimator_sample_consensus.html