This class is used for storing, analyzing and manipulating votes obtained from ISM algorithm. More...

#include <pcl/recognition/implicit_shape_model.h>

Collaboration diagram for pcl::features::ISMVoteList< PointT >:

Public Types
using	Ptr = shared_ptr<ISMVoteList<PointT> >
using	ConstPtr = shared_ptr<const ISMVoteList<PointT>>

Public Member Functions
	ISMVoteList ()
	Empty constructor with member variables initialization.
virtual	~ISMVoteList ()
	virtual descriptor.
void	addVote (pcl::InterestPoint &in_vote, const PointT &vote_origin, int in_class)
	This method simply adds another vote to the list.
pcl::PointCloud< pcl::PointXYZRGB >::Ptr	getColoredCloud (typename pcl::PointCloud< PointT >::Ptr cloud=0)
	Returns the colored cloud that consists of votes for center (blue points) and initial point cloud (if it was passed).
void	findStrongestPeaks (std::vector< ISMPeak, Eigen::aligned_allocator< ISMPeak > > &out_peaks, int in_class_id, double in_non_maxima_radius, double in_sigma)
	This method finds the strongest peaks (points were density has most higher values).
double	getDensityAtPoint (const PointT &point, double sigma_dist)
	Returns the density at the specified point.
unsigned int	getNumberOfVotes ()
	This method simply returns the number of votes.

Protected Member Functions
void	validateTree ()
	this method is simply setting up the search tree.
Eigen::Vector3f	shiftMean (const Eigen::Vector3f &snapPt, const double in_dSigmaDist)

Protected Attributes
pcl::PointCloud< pcl::InterestPoint >::Ptr	votes_ {new pcl::PointCloud<pcl::InterestPoint>}
	Stores all votes.
bool	tree_is_valid_ {false}
	Signalizes if the tree is valid.
pcl::PointCloud< PointT >::Ptr	votes_origins_ {new pcl::PointCloud<PointT>}
	Stores the origins of the votes.
std::vector< int >	votes_class_ {}
	Stores classes for which every single vote was cast.
pcl::KdTreeFLANN< pcl::InterestPoint >::Ptr	tree_ {nullptr}
	Stores the search tree.
pcl::Indices	k_ind_ {}
	Stores neighbours indices.
std::vector< float >	k_sqr_dist_ {}
	Stores square distances to the corresponding neighbours.

Detailed Description

template<typename PointT>
class pcl::features::ISMVoteList< PointT >

This class is used for storing, analyzing and manipulating votes obtained from ISM algorithm.

Definition at line 70 of file implicit_shape_model.h.

Member Typedef Documentation

◆ ConstPtr

template<typename PointT>

using pcl::features::ISMVoteList< PointT >::ConstPtr = shared_ptr<const ISMVoteList<PointT>>

Definition at line 75 of file implicit_shape_model.h.

◆ Ptr

template<typename PointT>

using pcl::features::ISMVoteList< PointT >::Ptr = shared_ptr<ISMVoteList<PointT> >

Definition at line 74 of file implicit_shape_model.h.

Constructor & Destructor Documentation

◆ ISMVoteList()

template<typename PointT>

pcl::features::ISMVoteList< PointT >::ISMVoteList ( )

default

Empty constructor with member variables initialization.

References addVote(), findStrongestPeaks(), getColoredCloud(), getDensityAtPoint(), getNumberOfVotes(), ISMVoteList(), shiftMean(), and validateTree().

Referenced by ISMVoteList().

◆ ~ISMVoteList()

template<typename PointT>

pcl::features::ISMVoteList< PointT >::~ISMVoteList ( )

virtual

virtual descriptor.

Definition at line 56 of file implicit_shape_model.hpp.

References k_ind_, k_sqr_dist_, tree_, votes_, votes_class_, and votes_origins_.

Member Function Documentation

◆ addVote()

template<typename PointT>

void pcl::features::ISMVoteList< PointT >::addVote	(	pcl::InterestPoint &	in_vote,
		const PointT &	vote_origin,
		int	in_class )

This method simply adds another vote to the list.

Parameters

[in]	in_vote	vote to add
[in]	vote_origin	origin of the added vote
[in]	in_class	class for which this vote is cast

Definition at line 68 of file implicit_shape_model.hpp.

References tree_is_valid_, votes_, votes_class_, and votes_origins_.

Referenced by pcl::ism::ImplicitShapeModelEstimation< FeatureSize, PointT, NormalT >::findObjects(), and ISMVoteList().

◆ findStrongestPeaks()

template<typename PointT>

void pcl::features::ISMVoteList< PointT >::findStrongestPeaks	(	std::vector< ISMPeak, Eigen::aligned_allocator< ISMPeak > > &	out_peaks,
		int	in_class_id,
		double	in_non_maxima_radius,
		double	in_sigma )

This method finds the strongest peaks (points were density has most higher values).

It is based on the non maxima suppression principles.

Parameters

[out]	out_peaks	it will contain the strongest peaks
[in]	in_class_id	class of interest for which peaks are evaluated
[in]	in_non_maxima_radius	non maxima suppression radius. The shapes radius is recommended for this value.
	in_sigma

Definition at line 119 of file implicit_shape_model.hpp.

References pcl::ISMPeak::class_id, pcl::ISMPeak::density, getDensityAtPoint(), shiftMean(), validateTree(), votes_, and votes_class_.

Referenced by ISMVoteList().

◆ getColoredCloud()

template<typename PointT>

pcl::PointCloud< pcl::PointXYZRGB >::Ptr pcl::features::ISMVoteList< PointT >::getColoredCloud ( typename pcl::PointCloud< PointT >::Ptr cloud = 0 )