GRT::ThresholdDetection Class Reference

#include <ThresholdDetection.h>

Inheritance diagram for GRT::ThresholdDetection:

Public Member Functions
	ThresholdDetection (UINT bufferLength=100, UINT numDimensions=1, double alpha=4.0, double beta=1.2)
	ThresholdDetection (const ThresholdDetection &rhs)
virtual	~ThresholdDetection ()
ThresholdDetection &	operator= (const ThresholdDetection &rhs)
virtual bool	deepCopyFrom (const FeatureExtraction *featureExtraction)
virtual bool	computeFeatures (const VectorDouble &inputVector)
virtual bool	reset ()
virtual bool	saveModelToFile (string filename) const
virtual bool	loadModelFromFile (string filename)
virtual bool	saveModelToFile (fstream &file) const
virtual bool	loadModelFromFile (fstream &file)
bool	init (UINT bufferLength, UINT numDimensions, double alpha, double beta)
VectorDouble	update (double x)
VectorDouble	update (const VectorDouble &x)
CircularBuffer< VectorDouble >	getBufferData ()
const CircularBuffer< VectorDouble > &	getBufferData () const

Protected Attributes
UINT	bufferLength
CircularBuffer< VectorDouble >	dataBuffer
double	alpha
double	beta
bool	inNoise

Static Protected Attributes
static RegisterFeatureExtractionModule< ThresholdDetection >	registerModule

Constructor & Destructor Documentation

GRT::ThresholdDetection::ThresholdDetection	(	UINT	bufferLength = 100,
		UINT	numDimensions = 1,
		double	alpha = 4.0,
		double	beta = 1.2
	)

GRT::ThresholdDetection::ThresholdDetection

(

const ThresholdDetection &

rhs

)

Copy constructor, copies the ThresholdDetection from the rhs instance to this instance.

Parameters

const

ThresholdDetection &rhs: another instance of the ThresholdDetection class from which the data will be copied to this instance

GRT::ThresholdDetection::~ThresholdDetection ( )

virtual

Default Destructor

Member Function Documentation

bool GRT::ThresholdDetection::computeFeatures ( const VectorDouble &  inputVector )

virtual

Sets the FeatureExtraction computeFeatures function, overwriting the base FeatureExtraction function. This function is called by the GestureRecognitionPipeline when any new input data needs to be processed (during the prediction phase for example). This function calls the ThresholdDetection's update function.

Parameters

const

VectorDouble &inputVector: the inputVector that should be processed. Must have the same dimensionality as the FeatureExtraction module

Returns

returns true if the data was processed, false otherwise

bool GRT::ThresholdDetection::deepCopyFrom ( const FeatureExtraction *  featureExtraction )

virtual

Sets the FeatureExtraction deepCopyFrom function, overwriting the base FeatureExtraction function. This function is used to deep copy the values from the input pointer to this instance of the FeatureExtraction module. This function is called by the GestureRecognitionPipeline when the user adds a new FeatureExtraction module to the pipeline.

Parameters

FeatureExtraction

*featureExtraction: a pointer to another instance of a ThresholdDetection, the values of that instance will be cloned to this instance

Returns

returns true if the deep copy was successful, false otherwise

CircularBuffer< VectorDouble > GRT::ThresholdDetection::getBufferData

(

)

Get the circular buffer.

Returns

a copy of the circular buffer

const CircularBuffer< VectorDouble > & GRT::ThresholdDetection::getBufferData

(

)

const

Gets a reference to the circular buffer.

Returns

a reference to the circular buffer

bool GRT::ThresholdDetection::init	(	UINT	bufferLength,
		UINT	numDimensions,
		double	alpha,
		double	beta
	)

Initializes the MovementTrajectoryFeatures

bool GRT::ThresholdDetection::loadModelFromFile ( string  filename )

virtual

This saves the feature extraction settings to a file.

Parameters

fstream

&file: a reference to the file to save the settings to

Returns

returns true if the settings were saved successfully, false otherwise

bool GRT::ThresholdDetection::loadModelFromFile ( fstream &  file )

virtual

This loads the feature extraction settings from a file. This overrides the loadSettingsFromFile function in the FeatureExtraction base class.

Parameters

fstream

&file: a reference to the file to load the settings from

Returns

returns true if the settings were loaded successfully, false otherwise

ThresholdDetection & GRT::ThresholdDetection::operator=

(

const ThresholdDetection &

rhs

)

Sets the equals operator, copies the data from the rhs instance to this instance.

Parameters

const

ThresholdDetection &rhs: another instance of the ThresholdDetection class from which the data will be copied to this instance

Returns

a reference to this instance of ThresholdDetection

bool GRT::ThresholdDetection::reset ( )

virtual

Sets the FeatureExtraction reset function, overwriting the base FeatureExtraction function. This function is called by the GestureRecognitionPipeline when the pipelines main reset() function is called. This function resets the feature extraction by re-initiliazing the instance.

Returns

true if the filter was reset, false otherwise

bool GRT::ThresholdDetection::saveModelToFile ( string  filename ) const

virtual

This saves the feature extraction settings to a file.

Parameters

const

string filename: the filename to save the settings to

Returns

returns true if the settings were saved successfully, false otherwise

bool GRT::ThresholdDetection::saveModelToFile ( fstream &  file ) const

virtual

This saves the feature extraction settings to a file. This overrides the saveSettingsToFile function in the FeatureExtraction base class.

Parameters

fstream

&file: a reference to the file to save the settings to

Returns

returns true if the settings were saved successfully, false otherwise

VectorDouble GRT::ThresholdDetection::update

(

double

x

)

Computes the features from the input, this should only be called if the dimensionality of this instance was set to 1.

Parameters

double

x: the value to compute features from, this should only be called if the dimensionality of the filter was set to 1

Returns

a vector containing the features, an empty vector will be returned if the features were not computed

VectorDouble GRT::ThresholdDetection::update

(

const VectorDouble &

x

)

Computes the features from the input, the dimensionality of x should match that of this instance.

Parameters

const

vector<double> &x: a vector containing the values to be processed, must be the same size as the numInputDimensions

Returns

a vector containing the features, an empty vector will be returned if the features were not computed

Member Data Documentation

double GRT::ThresholdDetection::alpha

protected

double GRT::ThresholdDetection::beta

protected

UINT GRT::ThresholdDetection::bufferLength

protected

CircularBuffer< VectorDouble > GRT::ThresholdDetection::dataBuffer

protected

bool GRT::ThresholdDetection::inNoise

protected

RegisterFeatureExtractionModule< ThresholdDetection > GRT::ThresholdDetection::registerModule

staticprotected

---

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

• src/ThresholdDetection.h
• src/ThresholdDetection.cpp