lti::gaussian< T > Class Template Reference

This function evaluates a multivariate gaussian with the form:

. More...

#include <ltiGaussian.h>

Inheritance diagram for lti::gaussian< T >:

[legend]

Collaboration diagram for lti::gaussian< T >:

[legend]

List of all members.

Classes
class	parameters
	the parameters for the class gaussian More...
Public Member Functions
	gaussian ()
	gaussian (const T mean, const T variance)
	gaussian (const vector< T > &mean, const matrix< T > &covar)
	gaussian (const gaussian< T > &other)
virtual	~gaussian ()
virtual const char *	getTypeName () const
bool	apply (const vector< T > &src, T &dest) const
T	operator() (const vector< T > &vct)
bool	apply (const T src, T &dest) const
T	operator() (const T x)
void	setMeanAndCovariance (const vector< T > &mean, const matrix< T > &covar)
void	setMeanAndVariance (const T mean, const T variance)
gaussian &	copy (const gaussian &other)
gaussian &	operator= (const gaussian &other)
virtual functor *	clone () const
const parameters &	getParameters () const
virtual bool	updateParameters ()
Protected Attributes
matrix< T >	invCovariance
vector< T >	meanVct
T	norm
T	invVarianceH
T	mean

---

Detailed Description

template<class T>
class lti::gaussian< T >

This function evaluates a multivariate gaussian with the form:

.

The template value T is the type of the container elements (double or float).

---

Constructor & Destructor Documentation

template<class T>

lti::gaussian< T >::gaussian

(

)

default constructor

template<class T>

lti::gaussian< T >::gaussian	(	const T	mean,
		const T	variance
	)

Construct a 1D gaussian with the given mean and variance.

Note that the second parameter is the variance and not the standard deviation.

template<class T>

lti::gaussian< T >::gaussian	(	const vector< T > &	mean,
		const matrix< T > &	covar
	)

construct a n-dimensional gaussian with the given mean vector and covariance matrix.

template<class T>

lti::gaussian< T >::gaussian

(

const gaussian< T > &

other

)

copy constructor

Parameters:

other

the object to be copied

template<class T>

virtual lti::gaussian< T >::~gaussian

(

)

[virtual]

destructor

---

Member Function Documentation

template<class T>

bool lti::gaussian< T >::apply	(	const T	src,
		T &	dest
	)			const

Computes the gaussian for the given scalar, and leave the result in the dest parameter.

This is a shortcut for the 1D case. If the mean and covariance given in the parameters have more the one dimension, the result will not be valid.

Parameters:

	src	input scalar
	dest	function value

Returns:

true if apply successful or false otherwise.

template<class T>

bool lti::gaussian< T >::apply	(	const vector< T > &	src,
		T &	dest
	)			const

computes the gaussian for the given vector, and leave the result in the dest parameter.

Parameters:

	src	vector<T> with the source data.
	dest	function value

Returns:

true if apply successful or false otherwise.

template<class T>

virtual functor* lti::gaussian< T >::clone

(

)

const [virtual]

returns a pointer to a clone of this functor.

Reimplemented from lti::mathFunction.

template<class T>

gaussian& lti::gaussian< T >::copy

(

const gaussian< T > &

other

)

copy data of "other" functor.

Parameters:

other

the functor to be copied

Returns:

a reference to this functor object

Reimplemented from lti::mathFunction.

template<class T>

const parameters& lti::gaussian< T >::getParameters

(

)

const

returns used parameters

Reimplemented from lti::mathFunction.

template<class T>

virtual const char* lti::gaussian< T >::getTypeName

(

)

const [virtual]

returns the name of this type ("gaussian")

Reimplemented from lti::mathFunction.

template<class T>

T lti::gaussian< T >::operator()

(

const T

x

)

Alias for apply.

Parameters:

x

input scalar

Returns:

function value

template<class T>

T lti::gaussian< T >::operator()

(

const vector< T > &

vct

)

alias for apply

Parameters:

vct

vector<T> with the source data.

Returns:

function value or negative if error occurred

template<class T>

gaussian& lti::gaussian< T >::operator=

(

const gaussian< T > &

other

)

alias for copy member

Parameters:

other

the functor to be copied

Returns:

a reference to this functor object

Reimplemented from lti::mathFunction.

template<class T>

void lti::gaussian< T >::setMeanAndCovariance	(	const vector< T > &	mean,
		const matrix< T > &	covar
	)

Shortcut to set the mean vector and covariance matrix.

template<class T>

void lti::gaussian< T >::setMeanAndVariance	(	const T	mean,
		const T	variance
	)

Shortcut to set a one dimensional gaussian with the mean value and the variance.

template<class T>

virtual bool lti::gaussian< T >::updateParameters

(

)

[virtual]

set functor's parameters.

This member makes a copy of theParam: the functor will keep its own copy of the parameters!

Returns:

true if successful, false otherwise

Reimplemented from lti::functor.

---

Member Data Documentation

template<class T>

matrix<T> lti::gaussian< T >::invCovariance [protected]

inverse of covariance matrix

template<class T>

T lti::gaussian< T >::invVarianceH [protected]

inverse of -2 times the variance for the 1D case

template<class T>

T lti::gaussian< T >::mean [protected]

mean value for the 1D case

template<class T>

vector<T> lti::gaussian< T >::meanVct [protected]

mean vector

template<class T>

T lti::gaussian< T >::norm [protected]

determinant of the covariance matrix

---

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

• ltiGaussian.h