lti::probabilityMapBase::parameters Class Reference

the parameters for the class probabilityMapBase More...

#include <ltiProbabilityMapBase.h>

Inheritance diagram for lti::probabilityMapBase::parameters:

[legend]

Collaboration diagram for lti::probabilityMapBase::parameters:

[legend]

List of all members.

Public Member Functions
	parameters ()
	parameters (const parameters &other)
	~parameters ()
const char *	getTypeName () const
parameters &	copy (const parameters &other)
parameters &	copyAllButHistograms (const parameters &other)
parameters &	operator= (const parameters &other)
virtual bool	write (ioHandler &handler, const bool complete=true) const
virtual bool	read (ioHandler &handler, const bool complete=true)
void	setObjectColorModel (const thistogram< double > &objModel)
const thistogram< double > &	getObjectColorModel () const
virtual bool	isObjectColorModelValid () const =0
void	setNonObjectColorModel (const thistogram< double > &nonObjModel)
const thistogram< double > &	getNonObjectColorModel () const
virtual bool	isNonObjectColorModelValid () const =0
Public Attributes
float	objectProbability
int	iterations
bool	gaussian
int	windowSize
double	variance
Protected Attributes
bool	ownModels
const thistogram< double > *	nonObjectColorModel
const thistogram< double > *	objectColorModel

Detailed Description

the parameters for the class probabilityMapBase

Constructor & Destructor Documentation

lti::probabilityMapBase::parameters::parameters ( )

default constructor

Reimplemented from lti::transform::parameters.

Reimplemented in lti::probabilityMap::parameters, lti::probabilityMap2D::parameters, and lti::skinProbabilityMap::parameters.

lti::probabilityMapBase::parameters::parameters ( const parameters & other )

copy constructor

Parameters:

other

the parameters object to be copied

Reimplemented from lti::transform::parameters.

Reimplemented in lti::probabilityMap::parameters, lti::probabilityMap2D::parameters, and lti::skinProbabilityMap::parameters.

lti::probabilityMapBase::parameters::~parameters ( ) [virtual]

destructor

Reimplemented from lti::functor::parameters.

Reimplemented in lti::probabilityMap::parameters, lti::probabilityMap2D::parameters, and lti::skinProbabilityMap::parameters.

Member Function Documentation

parameters& lti::probabilityMapBase::parameters::copy ( const parameters & other )

copy the contents of a parameters object

Parameters:

other

the parameters object to be copied

Returns:: a reference to this parameters object

Reimplemented from lti::transform::parameters.

Reimplemented in lti::probabilityMap::parameters, lti::probabilityMap2D::parameters, and lti::skinProbabilityMap::parameters.

parameters& lti::probabilityMapBase::parameters::copyAllButHistograms ( const parameters & other )

copy the contents of a parameters object, except the histograms.

Parameters:

other

the parameters object to be copied

Returns:: a reference to this parameters object

const thistogram<double>& lti::probabilityMapBase::parameters::getNonObjectColorModel ( ) const

returns a reference to the non-object color model

const thistogram<double>& lti::probabilityMapBase::parameters::getObjectColorModel ( ) const

returns a reference to the object color model

const char* lti::probabilityMapBase::parameters::getTypeName ( ) const [virtual]

returns name of this type

Reimplemented from lti::transform::parameters.

Reimplemented in lti::probabilityMap::parameters, lti::probabilityMap2D::parameters, and lti::skinProbabilityMap::parameters.

virtual bool lti::probabilityMapBase::parameters::isNonObjectColorModelValid ( ) const [pure virtual]

check if the non-object color model is valid

Valid means that the model has already been set (with setObjectColorModel) and that the dimensionality of the model fits with the dimension which the derived class requires.

Returns:: true if valid, false otherwise.

Implemented in lti::probabilityMap::parameters, and lti::probabilityMap2D::parameters.

virtual bool lti::probabilityMapBase::parameters::isObjectColorModelValid ( ) const [pure virtual]

check if the object color model is valid.

Valid means that the model has already been set (with setObjectColorModel) and that the dimensionality of the model fits with the dimension which the derived class requires.

Returns:: true if valid, false otherwise.

Implemented in lti::probabilityMap::parameters, and lti::probabilityMap2D::parameters.

parameters& lti::probabilityMapBase::parameters::operator= ( const parameters & other )

copy the contents of a parameters object

Parameters:

other

the parameters object to be copied

Returns:: a reference to this parameters object

Reimplemented in lti::probabilityMap::parameters, lti::probabilityMap2D::parameters, and lti::skinProbabilityMap::parameters.

virtual bool lti::probabilityMapBase::parameters::read	(	ioHandler &	handler,
		const bool	complete = `true`
	)			`[virtual]`

write the parameters in the given ioHandler

Parameters:

	handler	the ioHandler to be used
	complete	if true (the default) the enclosing begin/end will be also written, otherwise only the data block will be written.

Returns:: true if write was successful

Reimplemented from lti::functor::parameters.

Reimplemented in lti::skinProbabilityMap::parameters.

void lti::probabilityMapBase::parameters::setNonObjectColorModel ( const thistogram< double > & nonObjModel )

set non-object color model

A copy of the object will be done.

void lti::probabilityMapBase::parameters::setObjectColorModel ( const thistogram< double > & objModel )

set object color model.

A copy of the object will be done.

virtual bool lti::probabilityMapBase::parameters::write	(	ioHandler &	handler,
		const bool	complete = `true`
	)			const `[virtual]`

write the parameters in the given ioHandler

Parameters:

	handler	the ioHandler to be used
	complete	if true (the default) the enclosing begin/end will be also written, otherwise only the data block will be written.

Returns:: true if write was successful

Reimplemented from lti::functor::parameters.

Reimplemented in lti::skinProbabilityMap::parameters.

Member Data Documentation

bool lti::probabilityMapBase::parameters::gaussian

If true, a gaussian averaging filter will be used.

If false, a square filter will be used.

Default value: false (use a square kernel)

int lti::probabilityMapBase::parameters::iterations

Number of Iterations.

Default value: 1

This member should be always greater than 1. If zero or negative values are given, then 1 will be assumed. At this time, the functor requires BOTH models (object AND non-object) to compute more than one iteration.

The first iteration will always compute the probability map, assuming that for all pixels in the color image the a priori probability for it to be part of the object is given by the objectProbability.

Each following iteration will compute the a priori for each pixel as some averaging of the probabilities in the neighbourhood of pixel computed in the previous iteration. The available averaging operators are gaussian filters or square filters. The size of the neighbourhood will be specified by the windowSize attribute.