ShiTomasiFeatureDetector Class Reference

#include <ImFusion/Vision/FeatureDetection.h>

Implementation of the Shi-Tomasi corner detection algorithm. More...

Inheritance diagram for ShiTomasiFeatureDetector:

Detailed Description

Implementation of the Shi-Tomasi corner detection algorithm.

Public Member Functions
	ShiTomasiFeatureDetector ()
	Default constructor.
	~ShiTomasiFeatureDetector ()
	Destructor.
std::string	name () const override
	Return name of detector.
std::vector< Keypoint >	detect (SharedImage &img) override
	Detect keypoints from a SharedImage.
std::vector< Keypoint >	extract (const TypedImage< unsigned char > &img)
	Detect keypoints from a TypedImage.
std::vector< Keypoint >	extract (const TypedImage< unsigned char > &img, const std::vector< Keypoint > &keypointsAlreadyExtracted)
	Detect keypoints from a TypedImage with already extracted keypoints.
std::vector< Keypoint >	extract (const TypedImage< unsigned char > &img, const TypedImage< unsigned char > &mask)
	Detect keypoints from a TypedImage with additional mask.
std::vector< Keypoint >	extract (const TypedImage< unsigned char > &img, const std::vector< Keypoint > &keypointsAlreadyExtracted, const TypedImage< unsigned char > &mask)
	Detect keypoints from a TypedImage with already extracted keypoints and mask.
std::vector< Keypoint >	applyMask (const std::vector< Keypoint > &keypoints, const TypedImage< unsigned char > &mask)
	Filter out the keypoints inside the surfical tool mask.
Public Member Functions inherited from Configurable
virtual void	configure (const Properties *p)
	Configure this object instance by de-serializing the given Properties.
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< int >	p_nFeatures = {"Max features", 1024, this}
	Maximum number of features.
Parameter< int >	p_blockSize = {"Block size", 3, this}
	Block size for corner detection.
Parameter< int >	p_gradientSize = {"Gradient size", 3, this}
	Gradient size.
Parameter< double >	p_qualityLevel = {"Quality level", 0.01, this}
	Quality level parameter.
Parameter< double >	p_minDist = {"Min distance", 10, this}
	Minimum distance between keypoints.
Parameter< double >	p_k = {"Harris detector free param", 0.04, this}
	Harris detector parameter.
Parameter< bool >	p_useHarrisDetector = {"Use Harris detector", false, this}
	Use Harris detector flag.
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

name()

std::string name ( ) const

inlineoverridevirtual

Return name of detector.

Implements FeatureDetector.

detect()

std::vector< Keypoint > detect ( SharedImage & img )

overridevirtual

Detect keypoints from a SharedImage.

Parameters

img	SharedImage to detect features in.

Returns

Vector of detected keypoints.

Implements FeatureDetector.

extract() [1/4]

std::vector< Keypoint > extract

(

const TypedImage< unsigned char > &

img

)

Detect keypoints from a TypedImage.

Parameters

img	Input image.

Returns

Vector of detected keypoints.

extract() [2/4]

std::vector< Keypoint > extract	(	const TypedImage< unsigned char > &	img,
		const std::vector< Keypoint > &	keypointsAlreadyExtracted )

Detect keypoints from a TypedImage with already extracted keypoints.

After detection, the old keypoints remain and new keypoints won't be too close to the old ones.

Parameters

img	Input image.
keypointsAlreadyExtracted	Existing keypoints.

Returns

Vector of detected keypoints.

extract() [3/4]

std::vector< Keypoint > extract	(	const TypedImage< unsigned char > &	img,
		const TypedImage< unsigned char > &	mask )

Detect keypoints from a TypedImage with additional mask.

Parameters

img	Input image.
mask	Mask image.

Returns

Vector of detected keypoints.

extract() [4/4]

std::vector< Keypoint > extract	(	const TypedImage< unsigned char > &	img,
		const std::vector< Keypoint > &	keypointsAlreadyExtracted,
		const TypedImage< unsigned char > &	mask )

Detect keypoints from a TypedImage with already extracted keypoints and mask.

Parameters

img	Input image.
keypointsAlreadyExtracted	Existing keypoints.
mask	Mask image.

Returns

Vector of detected keypoints.

applyMask()

std::vector< Keypoint > applyMask	(	const std::vector< Keypoint > &	keypoints,
		const TypedImage< unsigned char > &	mask )

Filter out the keypoints inside the surfical tool mask.

Parameters

keypoints	Input keypoints.
mask	Mask image.

Returns

Filtered keypoints.

---

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

• ImFusion/Vision/FeatureDetection.h