Point Cloud Library (PCL)  1.7.0
Public Types | Public Member Functions
pcl::PCA< PointT > Class Template Reference

Principal Component analysis (PCA) class. More...

#include <pcl/common/pca.h>

+ Inheritance diagram for pcl::PCA< PointT >:

List of all members.

Public Types

enum  FLAG { increase, preserve }
 Updating method flag. More...
typedef pcl::PCLBase< PointTBase
typedef Base::PointCloud PointCloud
typedef Base::PointCloudPtr PointCloudPtr
typedef Base::PointCloudConstPtr PointCloudConstPtr
typedef Base::PointIndicesPtr PointIndicesPtr
typedef Base::PointIndicesConstPtr PointIndicesConstPtr

Public Member Functions

 PCA (bool basis_only=false)
 Default Constructor.
 PCL_DEPRECATED (PCA(const pcl::PointCloud< PointT > &X, bool basis_only=false),"Use PCA (bool basis_only); setInputCloud (X.makeShared ()); instead")
 Constructor with direct computation X input m*n matrix (ie n vectors of R(m)) basis_only flag to compute only the PCA basis.
 PCA (PCA const &pca)
 Copy Constructor.
PCAoperator= (PCA const &pca)
 Assignment operator.
void setInputCloud (const PointCloudConstPtr &cloud)
 Provide a pointer to the input dataset.
Eigen::Vector4f & getMean ()
 Mean accessor.
Eigen::Matrix3f & getEigenVectors ()
 Eigen Vectors accessor.
Eigen::Vector3f & getEigenValues ()
 Eigen Values accessor.
Eigen::MatrixXf & getCoefficients ()
 Coefficients accessor.
void update (const PointT &input, FLAG flag=preserve)
 update PCA with a new point
void project (const PointT &input, PointT &projection)
 Project point on the eigenspace.
void project (const PointCloud &input, PointCloud &projection)
 Project cloud on the eigenspace.
void reconstruct (const PointT &projection, PointT &input)
 Reconstruct point from its projection.
void reconstruct (const PointCloud &projection, PointCloud &input)
 Reconstruct cloud from its projection.

Detailed Description

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

Principal Component analysis (PCA) class.


Principal components are extracted by singular values decomposition on the covariance matrix of the centered input cloud. Available data after pca computation are the mean of the input data, the eigenvalues (in descending order) and corresponding eigenvectors.
Other methods allow projection in the eigenspace, reconstruction from eigenspace and update of the eigenspace with a new datum (according Matej Artec, Matjaz Jogan and Ales Leonardis: "Incremental PCA for On-line Visual Learning and Recognition").

Author:
Nizar Sallem

Definition at line 60 of file pca.h.


Member Typedef Documentation

template<typename PointT >
typedef pcl::PCLBase<PointT> pcl::PCA< PointT >::Base

Definition at line 63 of file pca.h.

template<typename PointT >
typedef Base::PointCloud pcl::PCA< PointT >::PointCloud

Reimplemented from pcl::PCLBase< PointT >.

Definition at line 64 of file pca.h.

template<typename PointT >
typedef Base::PointCloudConstPtr pcl::PCA< PointT >::PointCloudConstPtr

Reimplemented from pcl::PCLBase< PointT >.

Definition at line 66 of file pca.h.

template<typename PointT >
typedef Base::PointCloudPtr pcl::PCA< PointT >::PointCloudPtr

Reimplemented from pcl::PCLBase< PointT >.

Definition at line 65 of file pca.h.

template<typename PointT >
typedef Base::PointIndicesConstPtr pcl::PCA< PointT >::PointIndicesConstPtr

Reimplemented from pcl::PCLBase< PointT >.

Definition at line 68 of file pca.h.

template<typename PointT >
typedef Base::PointIndicesPtr pcl::PCA< PointT >::PointIndicesPtr

Reimplemented from pcl::PCLBase< PointT >.

Definition at line 67 of file pca.h.


Member Enumeration Documentation

template<typename PointT >
enum pcl::PCA::FLAG

Updating method flag.

Enumerator:
increase 

keep the new basis vectors if possible

preserve 

preserve subspace dimension

Definition at line 76 of file pca.h.


Constructor & Destructor Documentation

template<typename PointT >
pcl::PCA< PointT >::PCA ( bool  basis_only = false) [inline]

Default Constructor.

Parameters:
basis_onlyflag to compute only the PCA basis

Definition at line 87 of file pca.h.

template<typename PointT >
pcl::PCA< PointT >::PCA ( PCA< PointT > const &  pca) [inline]

Copy Constructor.

Parameters:
[in]pcaPCA object

Definition at line 107 of file pca.h.


Member Function Documentation

template<typename PointT >
Eigen::MatrixXf& pcl::PCA< PointT >::getCoefficients ( ) [inline]

Coefficients accessor.

Exceptions:
InitFailedException

Definition at line 186 of file pca.h.

template<typename PointT >
Eigen::Vector3f& pcl::PCA< PointT >::getEigenValues ( ) [inline]

Eigen Values accessor.

Exceptions:
InitFailedException

Definition at line 172 of file pca.h.

template<typename PointT >
Eigen::Matrix3f& pcl::PCA< PointT >::getEigenVectors ( ) [inline]

Eigen Vectors accessor.

Exceptions:
InitFailedException

Definition at line 158 of file pca.h.

template<typename PointT >
Eigen::Vector4f& pcl::PCA< PointT >::getMean ( ) [inline]

Mean accessor.

Exceptions:
InitFailedException

Definition at line 144 of file pca.h.

template<typename PointT >
PCA& pcl::PCA< PointT >::operator= ( PCA< PointT > const &  pca) [inline]

Assignment operator.

Parameters:
[in]pcaPCA object

Definition at line 121 of file pca.h.

template<typename PointT >
pcl::PCA< PointT >::PCL_DEPRECATED ( PCA< PointT >(const pcl::PointCloud< PointT > &X, bool basis_only=false)  ,
"Use PCA< PointT > (bool basis_only); setInputCloud (X.makeShared ()); instead"   
)

Constructor with direct computation X input m*n matrix (ie n vectors of R(m)) basis_only flag to compute only the PCA basis.

template<typename PointT >
void pcl::PCA< PointT >::project ( const PointT input,
PointT projection 
) [inline]

Project point on the eigenspace.

Parameters:
[in]inputpoint from original dataset
[out]projectionthe point in eigen vectors space
Exceptions:
InitFailedException

Definition at line 175 of file pca.hpp.

template<typename PointT >
void pcl::PCA< PointT >::project ( const PointCloud input,
PointCloud projection 
) [inline]

Project cloud on the eigenspace.

Parameters:
[in]inputcloud from original dataset
[out]projectionthe cloud in eigen vectors space
Exceptions:
InitFailedException

Definition at line 188 of file pca.hpp.

References pcl::PointCloud< PointT >::is_dense, pcl::PointCloud< PointT >::push_back(), pcl::PointCloud< PointT >::resize(), and pcl::PointCloud< PointT >::size().

template<typename PointT >
void pcl::PCA< PointT >::reconstruct ( const PointT projection,
PointT input 
) [inline]

Reconstruct point from its projection.

Parameters:
[in]projectionpoint from eigenvector space
[out]inputreconstructed point
Exceptions:
InitFailedException

Definition at line 217 of file pca.hpp.

template<typename PointT >
void pcl::PCA< PointT >::reconstruct ( const PointCloud projection,
PointCloud input 
) [inline]

Reconstruct cloud from its projection.

Parameters:
[in]projectioncloud from eigenvector space
[out]inputreconstructed cloud
Exceptions:
InitFailedException

Definition at line 230 of file pca.hpp.

References pcl::PointCloud< PointT >::is_dense, pcl::PointCloud< PointT >::push_back(), pcl::PointCloud< PointT >::resize(), and pcl::PointCloud< PointT >::size().

template<typename PointT >
void pcl::PCA< PointT >::setInputCloud ( const PointCloudConstPtr cloud) [inline, virtual]

Provide a pointer to the input dataset.

Parameters:
cloudthe const boost shared pointer to a PointCloud message

Reimplemented from pcl::PCLBase< PointT >.

Definition at line 134 of file pca.h.

References pcl::PCLBase< PointT >::setInputCloud().

template<typename PointT >
void pcl::PCA< PointT >::update ( const PointT input,
FLAG  flag = preserve 
) [inline]

update PCA with a new point

Parameters:
[in]inputinput point
[in]flagupdate flag
Exceptions:
InitFailedException

Definition at line 105 of file pca.hpp.


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