jafar::fdetect::STARDetector Class Reference

This class binds OpenCV2 STARDetector to fdetect STAR detector is a modified version of CenSurE features detector. More...

---

Detailed Description

This class binds OpenCV2 STARDetector to fdetect STAR detector is a modified version of CenSurE features detector.

STAR claims to be runtime complient while outperforming HARRIS for robustness. It is very important to note that the descriptors are computed using SURF algorithm.

Definition at line 29 of file STARDetector.hpp.

#include <STARDetector.hpp>

Inheritance diagram for jafar::fdetect::STARDetector:

List of all members.

Public Member Functions
	STARDetector (int _maxSize, int _responseThreshold, int _lineThresholdProjected, int _lineThresholdBinarized, int _suppressNonmaxSize)
	Constructor.
	STARDetector ()
	Constructor with default parameters if you don't know what to put.
virtual fdetect::DetectionResult	detectIn (jafar::image::Image const &image)
void	setMaxSize (int _maxSize)
void	setResponseThreshold (int _responseThreshold)
void	setLineThresholdProjected (int _lineThresholdProjected)
void	setLineThresholdBinarized (int _lineThresholdBinarized)
void	setSuppressNonmaxSize (int _suppressNonmaxSize)
int	maxSize () const
int	responseThreshold () const
int	lineThresholdProjected () const
int	lineThresholdBinarized () const
int	suppressNonmaxSize () const
Private Member Functions
template<class Archive >
void	serialize (Archive &ar, const unsigned int)
Private Attributes
cv::StarDetector	cv_star
	OpenCV STAR features extractor.
std::vector< cv::KeyPoint >	cv_keypoints
	OpenCV detected key points.
std::vector< float >	cv_descriptors
	OpenCV computed descriptors.
Friends
class	boost::serialization::access
	!! nizar 20100912 : serialization stuff

---

Constructor & Destructor Documentation

jafar::fdetect::STARDetector::STARDetector	(	int	_maxSize,
		int	_responseThreshold,
		int	_lineThresholdProjected,
		int	_lineThresholdBinarized,
		int	_suppressNonmaxSize
	)		[inline]

Constructor.

Parameters:

maxSize,:	maximum size of the features. The following values of the parameter are supported: 4, 6, 8, 11, 12, 16, 22, 23, 32, 45, 46, 64, 90, 128
responseThreshold,:	threshold for the approximated laplacian, used to eliminate weak features. The larger it is, the less features will be retrieved
lineThresholdProjected,:	another threshold for the laplacian to eliminate edges
lineThresholdBinarized,:	another threshold for the feature size to eliminate edges. The larger the 2 threshold, the more points you get.

Definition at line 63 of file STARDetector.hpp.

---

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

• modules/fdetect/include/fdetect/STARDetector.hpp