#include <vpFeatureLuminanceMapping.h>

Inheritance diagram for vpLuminanceDCT:

Classes
class	vpMatrixZigZagIndex

Public Member Functions
	vpLuminanceDCT (const unsigned int k)
void	init (const unsigned int k)
	vpLuminanceDCT (const vpLuminanceDCT &other)
vpLuminanceDCT &	operator= (const vpLuminanceDCT &)=default
void	map (const vpImage< unsigned char > &I, vpColVector &s) VP_OVERRIDE
void	inverse (const vpColVector &s, vpImage< unsigned char > &I) VP_OVERRIDE
void	interaction (const vpImage< unsigned char > &I, const vpMatrix &LI, const vpColVector &s, vpMatrix &L) VP_OVERRIDE
unsigned int	getProjectionSize () const
unsigned int	getBorder () const
void	setBorder (unsigned border)

Static Public Member Functions
static void	imageAsVector (const vpImage< unsigned char > &I, vpColVector &Ivec, unsigned border)
static void	imageAsMatrix (const vpImage< unsigned char > &I, vpMatrix &Imat, unsigned border)

Protected Attributes
unsigned int	m_Ih
unsigned int	m_Iw
vpMatrix	m_Imat
vpMatrix	m_dct
vpMatrix	m_Dcols
vpMatrix	m_Drows
std::array< vpMatrix, 6 >	m_dIdrPlanes
vpLuminanceDCT::vpMatrixZigZagIndex	m_zigzag
unsigned	m_mappingSize
unsigned	m_border

Detailed Description

Implementation of [38].

Computes the Discrete Cosine Transform (DCT) representation of the image. Only the K first components are preserved and stored into a vector when calling map. These components correspond to the lowest frequencies of the input image.

Examples: catchLuminanceMapping.cpp, and photometricMappingVisualServoing.cpp.

Definition at line 286 of file vpFeatureLuminanceMapping.h.

Constructor & Destructor Documentation

◆ vpLuminanceDCT() [1/2]

vpLuminanceDCT::vpLuminanceDCT ( const unsigned int k )

inline

Build a new DCT object.

Parameters

k	the number of components to keep from the DCT matrix and use as servoing features

Definition at line 335 of file vpFeatureLuminanceMapping.h.

References init(), and vpLuminanceMapping::vpLuminanceMapping().

Referenced by operator=(), and vpLuminanceDCT().

◆ vpLuminanceDCT() [2/2]

vpLuminanceDCT::vpLuminanceDCT ( const vpLuminanceDCT & other )

Copy constructor.

Definition at line 426 of file vpFeatureLuminanceMapping.cpp.

References vpLuminanceMapping::getProjectionSize(), vpLuminanceDCT(), and vpLuminanceMapping::vpLuminanceMapping().

Member Function Documentation

◆ getBorder()

unsigned int vpLuminanceMapping::getBorder ( ) const

inlineinherited

Returns the number of pixels that are removed by the photometric VS computation.

Returns: space size

Examples: catchLuminanceMapping.cpp.

Definition at line 114 of file vpFeatureLuminanceMapping.h.

References m_border.

◆ getProjectionSize()

unsigned int vpLuminanceMapping::getProjectionSize ( ) const

inlineinherited

Returns the size of the space to which an image is mapped to.

Returns: space size

Examples: catchLuminanceMapping.cpp.

Definition at line 107 of file vpFeatureLuminanceMapping.h.

References m_mappingSize.

Referenced by vpLuminanceDCT::vpLuminanceDCT().

◆ imageAsMatrix()

void vpLuminanceMapping::imageAsMatrix	(	const vpImage< unsigned char > &	I,
		vpMatrix &	Imat,
		unsigned	border )

staticinherited

Definition at line 59 of file vpFeatureLuminanceMapping.cpp.

References vpException::dimensionError, and vpArray2D< Type >::resize().

Referenced by vpLuminanceDCT::map().

◆ imageAsVector()

BEGIN_VISP_NAMESPACE void vpLuminanceMapping::imageAsVector	(	const vpImage< unsigned char > &	I,
		vpColVector &	Ivec,
		unsigned	border )

staticinherited

Definition at line 43 of file vpFeatureLuminanceMapping.cpp.

References vpException::dimensionError, and vpColVector::resize().

Referenced by vpLuminancePCA::map().

◆ init()

void vpLuminanceDCT::init ( const unsigned int k )

inline

Initialize the DCT object with the number of required components.

Definition at line 343 of file vpFeatureLuminanceMapping.h.

References vpFeatureLuminance::DEFAULT_BORDER, vpLuminanceMapping::m_border, m_Ih, m_Iw, and vpLuminanceMapping::m_mappingSize.

Referenced by vpLuminanceDCT().

◆ interaction()

void vpLuminanceDCT::interaction	(	const vpImage< unsigned char > &	I,
		const vpMatrix &	LI,
		const vpColVector &	s,
		vpMatrix &	L )

virtual

Compute the interaction matrix associated with the representation s.

Parameters

I	input image used to compute s
LI	Photometric interaction matrix associated to `I` (see vpFeatureLuminance)
s	the already computed representation
L	The output interaction matrix, of dimensions getProjectionSize() x 6

Implements vpLuminanceMapping.

Definition at line 478 of file vpFeatureLuminanceMapping.cpp.

References m_Dcols, m_dIdrPlanes, m_Drows, m_Ih, m_Iw, vpLuminanceMapping::m_mappingSize, m_zigzag, vpArray2D< Type >::resize(), and vpMatrix::t().

Referenced by operator=().

◆ inverse()

void vpLuminanceDCT::inverse	(	const vpColVector &	s,
		vpImage< unsigned char > &	I )

virtual

Reconstruct I from a representation s.

Parameters

s	the representation
I	Output lossy reconstruction

Implements vpLuminanceMapping.

Definition at line 465 of file vpFeatureLuminanceMapping.cpp.

References vpArray2D< Type >::getCols(), vpArray2D< Type >::getRows(), m_Dcols, m_dct, m_Drows, and m_zigzag.

Referenced by operator=().

◆ map()

void vpLuminanceDCT::map	(	const vpImage< unsigned char > &	I,
		vpColVector &	s )

virtual

Map an image I to a representation s. This representation s has getProjectionSize() rows.

Note that when combined with vpFeatureLuminanceMapping, The image I does not have the same size as the image input of vpFeatureLuminanceMapping::build. I is the center crop of this image.

Parameters

I	The input image
s	The resulting representation that will serve as visual servoing features.

Implements vpLuminanceMapping.

Definition at line 431 of file vpFeatureLuminanceMapping.cpp.

References vpLuminanceMapping::imageAsMatrix(), vpLuminanceMapping::m_border, m_Dcols, m_dct, m_Drows, m_Ih, m_Imat, m_Iw, vpLuminanceMapping::m_mappingSize, and m_zigzag.

Referenced by operator=().

◆ operator=()

vpLuminanceDCT & vpLuminanceDCT::operator= ( const vpLuminanceDCT & )

default

References interaction(), inverse(), map(), and vpLuminanceDCT().

◆ setBorder()

void vpLuminanceMapping::setBorder ( unsigned border )

inlineinherited

Set the number of pixels that are removed by the photometric VS computation This function should be called by vpFeatureLuminanceMapping.

Parameters

border

Examples: catchLuminanceMapping.cpp.

Definition at line 122 of file vpFeatureLuminanceMapping.h.

References m_border.

Member Data Documentation

◆ m_border

unsigned vpLuminanceMapping::m_border

protectedinherited

Final vector size.

Definition at line 129 of file vpFeatureLuminanceMapping.h.

Referenced by getBorder(), vpLuminanceDCT::init(), vpLuminancePCA::init(), vpLuminanceDCT::map(), vpLuminancePCA::map(), vpLuminancePCA::operator=(), and setBorder().

◆ m_Dcols

vpMatrix vpLuminanceDCT::m_Dcols

protected

DCT representation of the image.

Definition at line 369 of file vpFeatureLuminanceMapping.h.

Referenced by interaction(), inverse(), and map().

◆ m_dct

vpMatrix vpLuminanceDCT::m_dct

protected

Image as a matrix.

Definition at line 368 of file vpFeatureLuminanceMapping.h.

Referenced by inverse(), and map().

◆ m_dIdrPlanes

std::array<vpMatrix, 6> vpLuminanceDCT::m_dIdrPlanes

protected

the computed DCT matrices. The separable property of DCt is used so that a 1D DCT is computed on rows and another on columns of the result of the first dct;

Definition at line 370 of file vpFeatureLuminanceMapping.h.

Referenced by interaction().