cv::KeyPoint Class Reference

Data structure for salient point detectors. More...

#include <opencv2/core/types.hpp>

Inheritance diagram for cv::KeyPoint:

Public Member Functions
	KeyPoint ()
	the default constructor More...
	KeyPoint (Point2f pt, float size, float angle=-1, float response=0, int octave=0, int class_id=-1)
	KeyPoint (float x, float y, float size, float angle=-1, float response=0, int octave=0, int class_id=-1)
size_t	hash () const

Static Public Member Functions
static void	convert (const std::vector< KeyPoint > &keypoints, std::vector< Point2f > &points2f, const std::vector< int > &keypointIndexes=std::vector< int >())
static void	convert (const std::vector< Point2f > &points2f, std::vector< KeyPoint > &keypoints, float size=1, float response=1, int octave=0, int class_id=-1)
static float	overlap (const KeyPoint &kp1, const KeyPoint &kp2)

Public Attributes
float	angle
int	class_id
	object class (if the keypoints need to be clustered by an object they belong to) More...
int	octave
	octave (pyramid layer) from which the keypoint has been extracted More...
Point2f	pt
	coordinates of the keypoints More...
float	response
	the response by which the most strong keypoints have been selected. Can be used for the further sorting or subsampling More...
float	size
	diameter of the meaningful keypoint neighborhood More...

Detailed Description

Data structure for salient point detectors.

The class instance stores a keypoint, i.e. a point feature found by one of many available keypoint detectors, such as Harris corner detector, FAST, StarDetector, SURF, SIFT etc.

The keypoint is characterized by the 2D position, scale (proportional to the diameter of the neighborhood that needs to be taken into account), orientation and some other parameters. The keypoint neighborhood is then analyzed by another algorithm that builds a descriptor (usually represented as a feature vector). The keypoints representing the same object in different images can then be matched using KDTree or another method.

Constructor & Destructor Documentation

KeyPoint() [1/3]

cv::KeyPoint::KeyPoint

(

)

the default constructor

KeyPoint() [2/3]

cv::KeyPoint::KeyPoint	(	Point2f	pt,
		float	size,
		float	angle = -1,
		float	response = 0,
		int	octave = 0,
		int	class_id = -1
	)

Parameters

pt	x & y coordinates of the keypoint
size	keypoint diameter
angle	keypoint orientation
response	keypoint detector response on the keypoint (that is, strength of the keypoint)
octave	pyramid octave in which the keypoint has been detected
class_id	object id

KeyPoint() [3/3]

cv::KeyPoint::KeyPoint	(	float	x,
		float	y,
		float	size,
		float	angle = -1,
		float	response = 0,
		int	octave = 0,
		int	class_id = -1
	)

Parameters

x	x-coordinate of the keypoint
y	y-coordinate of the keypoint
size	keypoint diameter
angle	keypoint orientation
response	keypoint detector response on the keypoint (that is, strength of the keypoint)
octave	pyramid octave in which the keypoint has been detected
class_id	object id

Member Function Documentation

convert() [1/2]

static void cv::KeyPoint::convert ( const std::vector< KeyPoint > &  keypoints, std::vector< Point2f > &  points2f, const std::vector< int > &  keypointIndexes = std::vector< int >()  )

static

Python:
	cv.KeyPoint.convert(	keypoints[, keypointIndexes]	) ->	points2f
	cv.KeyPoint.convert(	points2f[, size[, response[, octave[, class_id]]]]	) ->	keypoints
	cv.KeyPoint_convert(	keypoints[, keypointIndexes]	) ->	points2f
	cv.KeyPoint_convert(	points2f[, size[, response[, octave[, class_id]]]]	) ->	keypoints

This method converts vector of keypoints to vector of points or the reverse, where each keypoint is assigned the same size and the same orientation.

Parameters

keypoints	Keypoints obtained from any feature detection algorithm like SIFT/SURF/ORB
points2f	Array of (x,y) coordinates of each keypoint
keypointIndexes	Array of indexes of keypoints to be converted to points. (Acts like a mask to convert only specified keypoints)

convert() [2/2]

static void cv::KeyPoint::convert ( const std::vector< Point2f > &  points2f, std::vector< KeyPoint > &  keypoints, float  size = 1, float  response = 1, int  octave = 0, int  class_id = -1  )

static

Python:
	cv.KeyPoint.convert(	keypoints[, keypointIndexes]	) ->	points2f
	cv.KeyPoint.convert(	points2f[, size[, response[, octave[, class_id]]]]	) ->	keypoints
	cv.KeyPoint_convert(	keypoints[, keypointIndexes]	) ->	points2f
	cv.KeyPoint_convert(	points2f[, size[, response[, octave[, class_id]]]]	) ->	keypoints

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

points2f	Array of (x,y) coordinates of each keypoint
keypoints	Keypoints obtained from any feature detection algorithm like SIFT/SURF/ORB
size	keypoint diameter
response	keypoint detector response on the keypoint (that is, strength of the keypoint)
octave	pyramid octave in which the keypoint has been detected
class_id	object id

hash()

size_t cv::KeyPoint::hash

(

)

const

overlap()

static float cv::KeyPoint::overlap ( const KeyPoint &  kp1, const KeyPoint &  kp2  )

static

Python:
	cv.KeyPoint.overlap(	kp1, kp2	) ->	retval
	cv.KeyPoint_overlap(	kp1, kp2	) ->	retval

This method computes overlap for pair of keypoints. Overlap is the ratio between area of keypoint regions' intersection and area of keypoint regions' union (considering keypoint region as circle). If they don't overlap, we get zero. If they coincide at same location with same size, we get 1.

Parameters

kp1	First keypoint
kp2	Second keypoint

Member Data Documentation

angle

float cv::KeyPoint::angle

computed orientation of the keypoint (-1 if not applicable); it's in [0,360) degrees and measured relative to image coordinate system, ie in clockwise.

class_id

int cv::KeyPoint::class_id

object class (if the keypoints need to be clustered by an object they belong to)

octave

int cv::KeyPoint::octave

octave (pyramid layer) from which the keypoint has been extracted

pt

Point2f cv::KeyPoint::pt

coordinates of the keypoints

response

float cv::KeyPoint::response

the response by which the most strong keypoints have been selected. Can be used for the further sorting or subsampling

size

float cv::KeyPoint::size

diameter of the meaningful keypoint neighborhood

---

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

• opencv2/core/types.hpp