Base class allowing to estimate gaussian curve parameters from a set of input data (based on Caruanas algorithm) More...

Inheritance diagram for ipsdk::math::BaseGaussianCurveEstimator:

Public Member Functions
Constructors and destructor
	BaseGaussianCurveEstimator (const ipUInt32 curveDomainSize)

virtual	~BaseGaussianCurveEstimator ()=0

Public Member Functions inherited from ipsdk::math::BaseEstimator
bool	isInit () const
	check for object initialization

ipUInt32	getNbMinRequestedData () const
	retrieve minimum data set size to ensure an estimation More...

ipUInt32	getNbEstimParams () const
	retrieve number of estimated parameters More...

ipUInt32	getDataSize () const
	unitary data size into data set collection More...

BoolResult	computeEstimation (const DataSet &dataSet, ParameterType &estimParams)
	method allowing to estimate parameters from a given data set More...

BoolResult	computeResiduals (const DataSet &dataSet, const ParameterType &estimParams, ResidualsSet &residualsSet) const
	method allowing to compute estimation residuals from a given data set and some estimated parameters More...

	BaseEstimator ()

virtual	~BaseEstimator ()=0

Protected Member Functions
BoolResult	processEstimation (const math::DataSet &dataSet, math::ParameterType &estimParams)
	method allowing to compute estimation into derived classes More...

BoolResult	processResiduals (const math::DataSet &dataSet, const math::ParameterType &estimParams, math::ResidualsSet &residualsSet) const
	method allowing to compute residuals into derived classes More...

Protected Member Functions inherited from ipsdk::math::BaseEstimator
void	initBase (const ipUInt32 nbMinRequestedData, const ipUInt32 nbEstimParams, const ipUInt32 dataSize)
	base class initialization More...

BoolResult	checkData (const DataSet &dataSet, const ParameterType &estimParams) const
	method allowing to check input data properties associated to estimation More...

Detailed Description

Base class allowing to estimate gaussian curve parameters from a set of input data (based on Caruanas algorithm)

Fitted gaussian curve is defined as follow :

$\begin{cases} G:\Re^n \rightarrow \Re \\ y = G(X) = Ae^{-\sum_{i=1}^{n}{\frac{(x_i-\mu_i)^2}{2\sigma_i^2}}} \end{cases}$

Input data used for fit are tuple of values such as $(x^j_1, x^j_2, ..., x^j_n, y^j), j \in [1, m]$ .

Note: Note that computed residuals are simplified taking the difference between gaussian curve computed value from and associated value

See also: Two-dimensional Gaussian regression for sub-pixel displacement estimation in particle image velocimetry or particle position estimation in particle tracking velocimetry, H. Nobach Æ M. Honkanen, Experiments in Fluids (2005) 38: 511515; A Simple Algorithm for Fitting a Gaussian Function, Hongwei Guo, IEEE Signal Processing Magazine · September 2011

Member Function Documentation

BoolResult ipsdk::math::BaseGaussianCurveEstimator::processEstimation	(	const math::DataSet &	dataSet,
		math::ParameterType &	estimParams
	)

protectedvirtual

method allowing to compute estimation into derived classes

BoolResult ipsdk::math::BaseGaussianCurveEstimator::processResiduals	(	const math::DataSet &	dataSet,
		const math::ParameterType &	estimParams,
		math::ResidualsSet &	residualsSet
	)		const

protectedvirtual

method allowing to compute residuals into derived classes

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

/media/reactivipdev/Nightly/IPSDK_Patch/IPSDK_4_1/IPSDK_Nightly/include/public/IPSDKMath/Statistics/GaussianCurveEstimator/BaseGaussianCurveEstimator.h