FeatureDetectorWithAdaptiveThreshold Class Reference

#include <ImFusion/Vision/FeatureDetection.h>

Feature detection with adaptive thresholding to fill image grid with features. More...

Inheritance diagram for FeatureDetectorWithAdaptiveThreshold:

Detailed Description

Feature detection with adaptive thresholding to fill image grid with features.

See class description for algorithm steps.

Classes
struct	KeyPointIterator
	Iterator for traversing keypoints, optionally sorted by response. More...

Public Member Functions
	FeatureDetectorWithAdaptiveThreshold ()
	Default constructor.
std::vector< Keypoint >	detectAdaptive (SharedImage &img)
	Runs the detection by iteratively adapting a max number of features and a threshold.
virtual bool	setMaxFeatures (int v)=0
	Sets the number of maximum features.
virtual int	maxFeatures () const =0
	Gets the maximum number of features.
virtual void	setThreshold (double threshold)=0
	Sets the detection threshold.
virtual double	threshold () const =0
	Gets the detection threshold.
virtual std::unique_ptr< KeyPointIterator >	initKeypointIterator (const std::vector< Keypoint > &keypoints)
	Instantiate keypoint iterator, can be overridden for custom sorting.
void	configure (const Properties *p) override
	Configure parameters from properties.
Public Member Functions inherited from FeatureDetector
virtual std::string	name () const =0
	Return name of feature detector.
virtual std::vector< Keypoint >	detect (SharedImage &img)=0
	Run feature detection on provided image.
Public Member Functions inherited from Configurable
virtual void	configuration (Properties *p) const
	Serialize the current object configuration into the given Properties object.
virtual void	configureDefaults ()
	Retrieve the properties of this object, replaces values with their defaults and sets it again.
void	registerParameter (ParameterBase *param)
	Register the given Parameter or SubProperty, so that it will be configured during configure()/configuration().
void	unregisterParameter (const ParameterBase *param)
	Remove the given Parameter or SubProperty from the list of registered parameters.
	Configurable (const Configurable &rhs)
	Configurable (Configurable &&rhs) noexcept
Configurable &	operator= (const Configurable &)
Configurable &	operator= (Configurable &&) noexcept

Public Attributes
Parameter< bool >	p_adaptThreshold = {"Iteratively adapt threshold", false, this}
	Enable adaptive threshold.
Parameter< int >	p_cellSize = {"Grid cell size", 100, this}
	Size of grid cell for adaptive threshold.
Parameter< double >	p_minThreshold = {"Minimum threshold", 0.0, this}
	Minimum threshold value.
Parameter< double >	p_thresholdStep = {"Threshold step", 0.0, this}
	Step size for threshold adaptation.
Public Attributes inherited from Configurable
Signal	signalParametersChanged
	Emitted whenever one of the registered Parameters' or SubPropertys' signalValueChanged signal was emitted.

Additional Inherited Members
Protected Attributes inherited from Configurable
std::vector< Param >	m_params
	List of all registered Parameter and SubProperty instances.

Member Function Documentation

detectAdaptive()

std::vector< Keypoint > detectAdaptive

(

SharedImage &

img

)

Runs the detection by iteratively adapting a max number of features and a threshold.

Parameters

img	SharedImage to detect features in.

Returns

Vector of detected keypoints.

setMaxFeatures()

virtual bool setMaxFeatures ( int v )

pure virtual

Sets the number of maximum features.

Parameters

v	Maximum number of features.

Returns

False if not supported.

Implemented in ORBFeatureDetector, and SIFTFeatureDetector.

maxFeatures()

virtual int maxFeatures ( ) const

pure virtual

Gets the maximum number of features.

Returns

Maximum number of features.

Implemented in ORBFeatureDetector, and SIFTFeatureDetector.

setThreshold()

virtual void setThreshold ( double threshold )

pure virtual

Sets the detection threshold.

Parameters

threshold

Threshold value.

Implemented in ORBFeatureDetector, and SIFTFeatureDetector.

threshold()

virtual double threshold ( ) const

pure virtual

Gets the detection threshold.

Returns

Threshold value.

Implemented in ORBFeatureDetector, and SIFTFeatureDetector.

initKeypointIterator()

virtual std::unique_ptr< KeyPointIterator > initKeypointIterator ( const std::vector< Keypoint > & keypoints )

inlinevirtual

Instantiate keypoint iterator, can be overridden for custom sorting.

Parameters

keypoints

Keypoints to iterate over.

Returns

Unique pointer to KeyPointIterator.

Reimplemented in ORBFeatureDetector.

configure()

void configure ( const Properties * p )

inlineoverridevirtual

Configure parameters from properties.

Parameters

p	Properties to configure from.

Reimplemented from Configurable.

---

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

• ImFusion/Vision/FeatureDetection.h