OpenCV for Unity  2.6.3
Enox Software / Please refer to OpenCV official document ( http://docs.opencv.org/4.10.0/index.html ) for the details of the argument of the method.
Public Member Functions | Static Public Member Functions | Public Attributes | Protected Member Functions | List of all members
OpenCVForUnity.Features2dModule.ORB Class Reference

Class implementing the ORB (oriented BRIEF) keypoint detector and descriptor extractor. More...

Inheritance diagram for OpenCVForUnity.Features2dModule.ORB:
OpenCVForUnity.Features2dModule.Feature2D OpenCVForUnity.CoreModule.Algorithm OpenCVForUnity.DisposableOpenCVObject OpenCVForUnity.DisposableObject

Public Member Functions

void setMaxFeatures (int maxFeatures)
 
int getMaxFeatures ()
 
void setScaleFactor (double scaleFactor)
 
double getScaleFactor ()
 
void setNLevels (int nlevels)
 
int getNLevels ()
 
void setEdgeThreshold (int edgeThreshold)
 
int getEdgeThreshold ()
 
void setFirstLevel (int firstLevel)
 
int getFirstLevel ()
 
void setWTA_K (int wta_k)
 
int getWTA_K ()
 
void setScoreType (int scoreType)
 
int getScoreType ()
 
void setPatchSize (int patchSize)
 
int getPatchSize ()
 
void setFastThreshold (int fastThreshold)
 
int getFastThreshold ()
 
override string getDefaultName ()
 
- Public Member Functions inherited from OpenCVForUnity.Features2dModule.Feature2D
void detect (Mat image, MatOfKeyPoint keypoints, Mat mask)
 Detects keypoints in an image (first variant) or image set (second variant). More...
 
void detect (Mat image, MatOfKeyPoint keypoints)
 Detects keypoints in an image (first variant) or image set (second variant). More...
 
void detect (List< Mat > images, List< MatOfKeyPoint > keypoints, List< Mat > masks)
 
void detect (List< Mat > images, List< MatOfKeyPoint > keypoints)
 
void compute (Mat image, MatOfKeyPoint keypoints, Mat descriptors)
 Computes the descriptors for a set of keypoints detected in an image (first variant) or image set (second variant). More...
 
void compute (List< Mat > images, List< MatOfKeyPoint > keypoints, List< Mat > descriptors)
 
void detectAndCompute (Mat image, Mat mask, MatOfKeyPoint keypoints, Mat descriptors, bool useProvidedKeypoints)
 
void detectAndCompute (Mat image, Mat mask, MatOfKeyPoint keypoints, Mat descriptors)
 
int descriptorSize ()
 
int descriptorType ()
 
int defaultNorm ()
 
void write (string fileName)
 
void read (string fileName)
 
override bool empty ()
 Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read. More...
 
- Public Member Functions inherited from OpenCVForUnity.CoreModule.Algorithm
IntPtr getNativeObjAddr ()
 
virtual void clear ()
 Clears the algorithm state. More...
 
void save (string filename)
 
- Public Member Functions inherited from OpenCVForUnity.DisposableObject
void Dispose ()
 
void ThrowIfDisposed ()
 

Static Public Member Functions

static new ORB __fromPtr__ (IntPtr addr)
 
static ORB create (int nfeatures, float scaleFactor, int nlevels, int edgeThreshold, int firstLevel, int WTA_K, int scoreType, int patchSize, int fastThreshold)
 The ORB constructor. More...
 
static ORB create (int nfeatures, float scaleFactor, int nlevels, int edgeThreshold, int firstLevel, int WTA_K, int scoreType, int patchSize)
 The ORB constructor. More...
 
static ORB create (int nfeatures, float scaleFactor, int nlevels, int edgeThreshold, int firstLevel, int WTA_K, int scoreType)
 The ORB constructor. More...
 
static ORB create (int nfeatures, float scaleFactor, int nlevels, int edgeThreshold, int firstLevel, int WTA_K)
 The ORB constructor. More...
 
static ORB create (int nfeatures, float scaleFactor, int nlevels, int edgeThreshold, int firstLevel)
 The ORB constructor. More...
 
static ORB create (int nfeatures, float scaleFactor, int nlevels, int edgeThreshold)
 The ORB constructor. More...
 
static ORB create (int nfeatures, float scaleFactor, int nlevels)
 The ORB constructor. More...
 
static ORB create (int nfeatures, float scaleFactor)
 The ORB constructor. More...
 
static ORB create (int nfeatures)
 The ORB constructor. More...
 
static ORB create ()
 The ORB constructor. More...
 
- Static Public Member Functions inherited from OpenCVForUnity.Features2dModule.Feature2D
static new Feature2D __fromPtr__ (IntPtr addr)
 
- Static Public Member Functions inherited from OpenCVForUnity.CoreModule.Algorithm
static Algorithm __fromPtr__ (IntPtr addr)
 
- Static Public Member Functions inherited from OpenCVForUnity.DisposableObject
static IntPtr ThrowIfNullIntPtr (IntPtr ptr)
 

Public Attributes

const int HARRIS_SCORE = 0
 
const int FAST_SCORE = 1
 

Protected Member Functions

override void Dispose (bool disposing)
 
- Protected Member Functions inherited from OpenCVForUnity.DisposableOpenCVObject
 DisposableOpenCVObject ()
 
 DisposableOpenCVObject (IntPtr ptr)
 
 DisposableOpenCVObject (bool isEnabledDispose)
 
 DisposableOpenCVObject (IntPtr ptr, bool isEnabledDispose)
 
- Protected Member Functions inherited from OpenCVForUnity.DisposableObject
 DisposableObject ()
 
 DisposableObject (bool isEnabledDispose)
 

Additional Inherited Members

- Properties inherited from OpenCVForUnity.DisposableObject
bool IsDisposed [get, protected set]
 
bool IsEnabledDispose [get, set]
 

Detailed Description

Class implementing the ORB (oriented BRIEF) keypoint detector and descriptor extractor.

described in [RRKB11] . The algorithm uses FAST in pyramids to detect stable keypoints, selects the strongest features using FAST or Harris response, finds their orientation using first-order moments and computes the descriptors using BRIEF (where the coordinates of random point pairs (or k-tuples) are rotated according to the measured orientation).

Member Function Documentation

◆ __fromPtr__()

static new ORB OpenCVForUnity.Features2dModule.ORB.__fromPtr__ ( IntPtr  addr)
static

◆ create() [1/10]

static ORB OpenCVForUnity.Features2dModule.ORB.create ( int  nfeatures,
float  scaleFactor,
int  nlevels,
int  edgeThreshold,
int  firstLevel,
int  WTA_K,
int  scoreType,
int  patchSize,
int  fastThreshold 
)
static

The ORB constructor.

Parameters
nfeaturesThe maximum number of features to retain.
scaleFactorPyramid decimation ratio, greater than 1. scaleFactor==2 means the classical pyramid, where each next level has 4x less pixels than the previous, but such a big scale factor will degrade feature matching scores dramatically. On the other hand, too close to 1 scale factor will mean that to cover certain scale range you will need more pyramid levels and so the speed will suffer.
nlevelsThe number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
edgeThresholdThis is size of the border where the features are not detected. It should roughly match the patchSize parameter.
firstLevelThe level of pyramid to put source image to. Previous layers are filled with upscaled source image.
WTA_KThe number of points that produce each element of the oriented BRIEF descriptor. The default value 2 means the BRIEF where we take a random point pair and compare their brightnesses, so we get 0/1 response. Other possible values are 3 and 4. For example, 3 means that we take 3 random points (of course, those point coordinates are random, but they are generated from the pre-defined seed, so each element of BRIEF descriptor is computed deterministically from the pixel rectangle), find point of maximum brightness and output index of the winner (0, 1 or 2). Such output will occupy 2 bits, and therefore it will need a special variant of Hamming distance, denoted as NORM_HAMMING2 (2 bits per bin). When WTA_K=4, we take 4 random points to compute each bin (that will also occupy 2 bits with possible values 0, 1, 2 or 3).
scoreTypeThe default HARRIS_SCORE means that Harris algorithm is used to rank features (the score is written to KeyPoint::score and is used to retain best nfeatures features); FAST_SCORE is alternative value of the parameter that produces slightly less stable keypoints, but it is a little faster to compute.
patchSizesize of the patch used by the oriented BRIEF descriptor. Of course, on smaller pyramid layers the perceived image area covered by a feature will be larger.
fastThresholdthe fast threshold

◆ create() [2/10]

static ORB OpenCVForUnity.Features2dModule.ORB.create ( int  nfeatures,
float  scaleFactor,
int  nlevels,
int  edgeThreshold,
int  firstLevel,
int  WTA_K,
int  scoreType,
int  patchSize 
)
static

The ORB constructor.

Parameters
nfeaturesThe maximum number of features to retain.
scaleFactorPyramid decimation ratio, greater than 1. scaleFactor==2 means the classical pyramid, where each next level has 4x less pixels than the previous, but such a big scale factor will degrade feature matching scores dramatically. On the other hand, too close to 1 scale factor will mean that to cover certain scale range you will need more pyramid levels and so the speed will suffer.
nlevelsThe number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
edgeThresholdThis is size of the border where the features are not detected. It should roughly match the patchSize parameter.
firstLevelThe level of pyramid to put source image to. Previous layers are filled with upscaled source image.
WTA_KThe number of points that produce each element of the oriented BRIEF descriptor. The default value 2 means the BRIEF where we take a random point pair and compare their brightnesses, so we get 0/1 response. Other possible values are 3 and 4. For example, 3 means that we take 3 random points (of course, those point coordinates are random, but they are generated from the pre-defined seed, so each element of BRIEF descriptor is computed deterministically from the pixel rectangle), find point of maximum brightness and output index of the winner (0, 1 or 2). Such output will occupy 2 bits, and therefore it will need a special variant of Hamming distance, denoted as NORM_HAMMING2 (2 bits per bin). When WTA_K=4, we take 4 random points to compute each bin (that will also occupy 2 bits with possible values 0, 1, 2 or 3).
scoreTypeThe default HARRIS_SCORE means that Harris algorithm is used to rank features (the score is written to KeyPoint::score and is used to retain best nfeatures features); FAST_SCORE is alternative value of the parameter that produces slightly less stable keypoints, but it is a little faster to compute.
patchSizesize of the patch used by the oriented BRIEF descriptor. Of course, on smaller pyramid layers the perceived image area covered by a feature will be larger.
fastThresholdthe fast threshold

◆ create() [3/10]

static ORB OpenCVForUnity.Features2dModule.ORB.create ( int  nfeatures,
float  scaleFactor,
int  nlevels,
int  edgeThreshold,
int  firstLevel,
int  WTA_K,
int  scoreType 
)
static

The ORB constructor.

Parameters
nfeaturesThe maximum number of features to retain.
scaleFactorPyramid decimation ratio, greater than 1. scaleFactor==2 means the classical pyramid, where each next level has 4x less pixels than the previous, but such a big scale factor will degrade feature matching scores dramatically. On the other hand, too close to 1 scale factor will mean that to cover certain scale range you will need more pyramid levels and so the speed will suffer.
nlevelsThe number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
edgeThresholdThis is size of the border where the features are not detected. It should roughly match the patchSize parameter.
firstLevelThe level of pyramid to put source image to. Previous layers are filled with upscaled source image.
WTA_KThe number of points that produce each element of the oriented BRIEF descriptor. The default value 2 means the BRIEF where we take a random point pair and compare their brightnesses, so we get 0/1 response. Other possible values are 3 and 4. For example, 3 means that we take 3 random points (of course, those point coordinates are random, but they are generated from the pre-defined seed, so each element of BRIEF descriptor is computed deterministically from the pixel rectangle), find point of maximum brightness and output index of the winner (0, 1 or 2). Such output will occupy 2 bits, and therefore it will need a special variant of Hamming distance, denoted as NORM_HAMMING2 (2 bits per bin). When WTA_K=4, we take 4 random points to compute each bin (that will also occupy 2 bits with possible values 0, 1, 2 or 3).
scoreTypeThe default HARRIS_SCORE means that Harris algorithm is used to rank features (the score is written to KeyPoint::score and is used to retain best nfeatures features); FAST_SCORE is alternative value of the parameter that produces slightly less stable keypoints, but it is a little faster to compute.
patchSizesize of the patch used by the oriented BRIEF descriptor. Of course, on smaller pyramid layers the perceived image area covered by a feature will be larger.
fastThresholdthe fast threshold

◆ create() [4/10]

static ORB OpenCVForUnity.Features2dModule.ORB.create ( int  nfeatures,
float  scaleFactor,
int  nlevels,
int  edgeThreshold,
int  firstLevel,
int  WTA_K 
)
static

The ORB constructor.

Parameters
nfeaturesThe maximum number of features to retain.
scaleFactorPyramid decimation ratio, greater than 1. scaleFactor==2 means the classical pyramid, where each next level has 4x less pixels than the previous, but such a big scale factor will degrade feature matching scores dramatically. On the other hand, too close to 1 scale factor will mean that to cover certain scale range you will need more pyramid levels and so the speed will suffer.
nlevelsThe number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
edgeThresholdThis is size of the border where the features are not detected. It should roughly match the patchSize parameter.
firstLevelThe level of pyramid to put source image to. Previous layers are filled with upscaled source image.
WTA_KThe number of points that produce each element of the oriented BRIEF descriptor. The default value 2 means the BRIEF where we take a random point pair and compare their brightnesses, so we get 0/1 response. Other possible values are 3 and 4. For example, 3 means that we take 3 random points (of course, those point coordinates are random, but they are generated from the pre-defined seed, so each element of BRIEF descriptor is computed deterministically from the pixel rectangle), find point of maximum brightness and output index of the winner (0, 1 or 2). Such output will occupy 2 bits, and therefore it will need a special variant of Hamming distance, denoted as NORM_HAMMING2 (2 bits per bin). When WTA_K=4, we take 4 random points to compute each bin (that will also occupy 2 bits with possible values 0, 1, 2 or 3).
scoreTypeThe default HARRIS_SCORE means that Harris algorithm is used to rank features (the score is written to KeyPoint::score and is used to retain best nfeatures features); FAST_SCORE is alternative value of the parameter that produces slightly less stable keypoints, but it is a little faster to compute.
patchSizesize of the patch used by the oriented BRIEF descriptor. Of course, on smaller pyramid layers the perceived image area covered by a feature will be larger.
fastThresholdthe fast threshold

◆ create() [5/10]

static ORB OpenCVForUnity.Features2dModule.ORB.create ( int  nfeatures,
float  scaleFactor,
int  nlevels,
int  edgeThreshold,
int  firstLevel 
)
static

The ORB constructor.

Parameters
nfeaturesThe maximum number of features to retain.
scaleFactorPyramid decimation ratio, greater than 1. scaleFactor==2 means the classical pyramid, where each next level has 4x less pixels than the previous, but such a big scale factor will degrade feature matching scores dramatically. On the other hand, too close to 1 scale factor will mean that to cover certain scale range you will need more pyramid levels and so the speed will suffer.
nlevelsThe number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
edgeThresholdThis is size of the border where the features are not detected. It should roughly match the patchSize parameter.
firstLevelThe level of pyramid to put source image to. Previous layers are filled with upscaled source image.
WTA_KThe number of points that produce each element of the oriented BRIEF descriptor. The default value 2 means the BRIEF where we take a random point pair and compare their brightnesses, so we get 0/1 response. Other possible values are 3 and 4. For example, 3 means that we take 3 random points (of course, those point coordinates are random, but they are generated from the pre-defined seed, so each element of BRIEF descriptor is computed deterministically from the pixel rectangle), find point of maximum brightness and output index of the winner (0, 1 or 2). Such output will occupy 2 bits, and therefore it will need a special variant of Hamming distance, denoted as NORM_HAMMING2 (2 bits per bin). When WTA_K=4, we take 4 random points to compute each bin (that will also occupy 2 bits with possible values 0, 1, 2 or 3).
scoreTypeThe default HARRIS_SCORE means that Harris algorithm is used to rank features (the score is written to KeyPoint::score and is used to retain best nfeatures features); FAST_SCORE is alternative value of the parameter that produces slightly less stable keypoints, but it is a little faster to compute.
patchSizesize of the patch used by the oriented BRIEF descriptor. Of course, on smaller pyramid layers the perceived image area covered by a feature will be larger.
fastThresholdthe fast threshold

◆ create() [6/10]

static ORB OpenCVForUnity.Features2dModule.ORB.create ( int  nfeatures,
float  scaleFactor,
int  nlevels,
int  edgeThreshold 
)
static

The ORB constructor.

Parameters
nfeaturesThe maximum number of features to retain.
scaleFactorPyramid decimation ratio, greater than 1. scaleFactor==2 means the classical pyramid, where each next level has 4x less pixels than the previous, but such a big scale factor will degrade feature matching scores dramatically. On the other hand, too close to 1 scale factor will mean that to cover certain scale range you will need more pyramid levels and so the speed will suffer.
nlevelsThe number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
edgeThresholdThis is size of the border where the features are not detected. It should roughly match the patchSize parameter.
firstLevelThe level of pyramid to put source image to. Previous layers are filled with upscaled source image.
WTA_KThe number of points that produce each element of the oriented BRIEF descriptor. The default value 2 means the BRIEF where we take a random point pair and compare their brightnesses, so we get 0/1 response. Other possible values are 3 and 4. For example, 3 means that we take 3 random points (of course, those point coordinates are random, but they are generated from the pre-defined seed, so each element of BRIEF descriptor is computed deterministically from the pixel rectangle), find point of maximum brightness and output index of the winner (0, 1 or 2). Such output will occupy 2 bits, and therefore it will need a special variant of Hamming distance, denoted as NORM_HAMMING2 (2 bits per bin). When WTA_K=4, we take 4 random points to compute each bin (that will also occupy 2 bits with possible values 0, 1, 2 or 3).
scoreTypeThe default HARRIS_SCORE means that Harris algorithm is used to rank features (the score is written to KeyPoint::score and is used to retain best nfeatures features); FAST_SCORE is alternative value of the parameter that produces slightly less stable keypoints, but it is a little faster to compute.
patchSizesize of the patch used by the oriented BRIEF descriptor. Of course, on smaller pyramid layers the perceived image area covered by a feature will be larger.
fastThresholdthe fast threshold

◆ create() [7/10]

static ORB OpenCVForUnity.Features2dModule.ORB.create ( int  nfeatures,
float  scaleFactor,
int  nlevels 
)
static

The ORB constructor.

Parameters
nfeaturesThe maximum number of features to retain.
scaleFactorPyramid decimation ratio, greater than 1. scaleFactor==2 means the classical pyramid, where each next level has 4x less pixels than the previous, but such a big scale factor will degrade feature matching scores dramatically. On the other hand, too close to 1 scale factor will mean that to cover certain scale range you will need more pyramid levels and so the speed will suffer.
nlevelsThe number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
edgeThresholdThis is size of the border where the features are not detected. It should roughly match the patchSize parameter.
firstLevelThe level of pyramid to put source image to. Previous layers are filled with upscaled source image.
WTA_KThe number of points that produce each element of the oriented BRIEF descriptor. The default value 2 means the BRIEF where we take a random point pair and compare their brightnesses, so we get 0/1 response. Other possible values are 3 and 4. For example, 3 means that we take 3 random points (of course, those point coordinates are random, but they are generated from the pre-defined seed, so each element of BRIEF descriptor is computed deterministically from the pixel rectangle), find point of maximum brightness and output index of the winner (0, 1 or 2). Such output will occupy 2 bits, and therefore it will need a special variant of Hamming distance, denoted as NORM_HAMMING2 (2 bits per bin). When WTA_K=4, we take 4 random points to compute each bin (that will also occupy 2 bits with possible values 0, 1, 2 or 3).
scoreTypeThe default HARRIS_SCORE means that Harris algorithm is used to rank features (the score is written to KeyPoint::score and is used to retain best nfeatures features); FAST_SCORE is alternative value of the parameter that produces slightly less stable keypoints, but it is a little faster to compute.
patchSizesize of the patch used by the oriented BRIEF descriptor. Of course, on smaller pyramid layers the perceived image area covered by a feature will be larger.
fastThresholdthe fast threshold

◆ create() [8/10]

static ORB OpenCVForUnity.Features2dModule.ORB.create ( int  nfeatures,
float  scaleFactor 
)
static

The ORB constructor.

Parameters
nfeaturesThe maximum number of features to retain.
scaleFactorPyramid decimation ratio, greater than 1. scaleFactor==2 means the classical pyramid, where each next level has 4x less pixels than the previous, but such a big scale factor will degrade feature matching scores dramatically. On the other hand, too close to 1 scale factor will mean that to cover certain scale range you will need more pyramid levels and so the speed will suffer.
nlevelsThe number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
edgeThresholdThis is size of the border where the features are not detected. It should roughly match the patchSize parameter.
firstLevelThe level of pyramid to put source image to. Previous layers are filled with upscaled source image.
WTA_KThe number of points that produce each element of the oriented BRIEF descriptor. The default value 2 means the BRIEF where we take a random point pair and compare their brightnesses, so we get 0/1 response. Other possible values are 3 and 4. For example, 3 means that we take 3 random points (of course, those point coordinates are random, but they are generated from the pre-defined seed, so each element of BRIEF descriptor is computed deterministically from the pixel rectangle), find point of maximum brightness and output index of the winner (0, 1 or 2). Such output will occupy 2 bits, and therefore it will need a special variant of Hamming distance, denoted as NORM_HAMMING2 (2 bits per bin). When WTA_K=4, we take 4 random points to compute each bin (that will also occupy 2 bits with possible values 0, 1, 2 or 3).
scoreTypeThe default HARRIS_SCORE means that Harris algorithm is used to rank features (the score is written to KeyPoint::score and is used to retain best nfeatures features); FAST_SCORE is alternative value of the parameter that produces slightly less stable keypoints, but it is a little faster to compute.
patchSizesize of the patch used by the oriented BRIEF descriptor. Of course, on smaller pyramid layers the perceived image area covered by a feature will be larger.
fastThresholdthe fast threshold

◆ create() [9/10]

static ORB OpenCVForUnity.Features2dModule.ORB.create ( int  nfeatures)
static

The ORB constructor.

Parameters
nfeaturesThe maximum number of features to retain.
scaleFactorPyramid decimation ratio, greater than 1. scaleFactor==2 means the classical pyramid, where each next level has 4x less pixels than the previous, but such a big scale factor will degrade feature matching scores dramatically. On the other hand, too close to 1 scale factor will mean that to cover certain scale range you will need more pyramid levels and so the speed will suffer.
nlevelsThe number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
edgeThresholdThis is size of the border where the features are not detected. It should roughly match the patchSize parameter.
firstLevelThe level of pyramid to put source image to. Previous layers are filled with upscaled source image.
WTA_KThe number of points that produce each element of the oriented BRIEF descriptor. The default value 2 means the BRIEF where we take a random point pair and compare their brightnesses, so we get 0/1 response. Other possible values are 3 and 4. For example, 3 means that we take 3 random points (of course, those point coordinates are random, but they are generated from the pre-defined seed, so each element of BRIEF descriptor is computed deterministically from the pixel rectangle), find point of maximum brightness and output index of the winner (0, 1 or 2). Such output will occupy 2 bits, and therefore it will need a special variant of Hamming distance, denoted as NORM_HAMMING2 (2 bits per bin). When WTA_K=4, we take 4 random points to compute each bin (that will also occupy 2 bits with possible values 0, 1, 2 or 3).
scoreTypeThe default HARRIS_SCORE means that Harris algorithm is used to rank features (the score is written to KeyPoint::score and is used to retain best nfeatures features); FAST_SCORE is alternative value of the parameter that produces slightly less stable keypoints, but it is a little faster to compute.
patchSizesize of the patch used by the oriented BRIEF descriptor. Of course, on smaller pyramid layers the perceived image area covered by a feature will be larger.
fastThresholdthe fast threshold

◆ create() [10/10]

static ORB OpenCVForUnity.Features2dModule.ORB.create ( )
static

The ORB constructor.

Parameters
nfeaturesThe maximum number of features to retain.
scaleFactorPyramid decimation ratio, greater than 1. scaleFactor==2 means the classical pyramid, where each next level has 4x less pixels than the previous, but such a big scale factor will degrade feature matching scores dramatically. On the other hand, too close to 1 scale factor will mean that to cover certain scale range you will need more pyramid levels and so the speed will suffer.
nlevelsThe number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
edgeThresholdThis is size of the border where the features are not detected. It should roughly match the patchSize parameter.
firstLevelThe level of pyramid to put source image to. Previous layers are filled with upscaled source image.
WTA_KThe number of points that produce each element of the oriented BRIEF descriptor. The default value 2 means the BRIEF where we take a random point pair and compare their brightnesses, so we get 0/1 response. Other possible values are 3 and 4. For example, 3 means that we take 3 random points (of course, those point coordinates are random, but they are generated from the pre-defined seed, so each element of BRIEF descriptor is computed deterministically from the pixel rectangle), find point of maximum brightness and output index of the winner (0, 1 or 2). Such output will occupy 2 bits, and therefore it will need a special variant of Hamming distance, denoted as NORM_HAMMING2 (2 bits per bin). When WTA_K=4, we take 4 random points to compute each bin (that will also occupy 2 bits with possible values 0, 1, 2 or 3).
scoreTypeThe default HARRIS_SCORE means that Harris algorithm is used to rank features (the score is written to KeyPoint::score and is used to retain best nfeatures features); FAST_SCORE is alternative value of the parameter that produces slightly less stable keypoints, but it is a little faster to compute.
patchSizesize of the patch used by the oriented BRIEF descriptor. Of course, on smaller pyramid layers the perceived image area covered by a feature will be larger.
fastThresholdthe fast threshold

◆ Dispose()

override void OpenCVForUnity.Features2dModule.ORB.Dispose ( bool  disposing)
protectedvirtual

◆ getDefaultName()

override string OpenCVForUnity.Features2dModule.ORB.getDefaultName ( )
virtual

Returns the algorithm string identifier. This string is used as top level xml/yml node tag when the object is saved to a file or string.

Reimplemented from OpenCVForUnity.Features2dModule.Feature2D.

◆ getEdgeThreshold()

int OpenCVForUnity.Features2dModule.ORB.getEdgeThreshold ( )

◆ getFastThreshold()

int OpenCVForUnity.Features2dModule.ORB.getFastThreshold ( )

◆ getFirstLevel()

int OpenCVForUnity.Features2dModule.ORB.getFirstLevel ( )

◆ getMaxFeatures()

int OpenCVForUnity.Features2dModule.ORB.getMaxFeatures ( )

◆ getNLevels()

int OpenCVForUnity.Features2dModule.ORB.getNLevels ( )

◆ getPatchSize()

int OpenCVForUnity.Features2dModule.ORB.getPatchSize ( )

◆ getScaleFactor()

double OpenCVForUnity.Features2dModule.ORB.getScaleFactor ( )

◆ getScoreType()

int OpenCVForUnity.Features2dModule.ORB.getScoreType ( )

◆ getWTA_K()

int OpenCVForUnity.Features2dModule.ORB.getWTA_K ( )

◆ setEdgeThreshold()

void OpenCVForUnity.Features2dModule.ORB.setEdgeThreshold ( int  edgeThreshold)

◆ setFastThreshold()

void OpenCVForUnity.Features2dModule.ORB.setFastThreshold ( int  fastThreshold)

◆ setFirstLevel()

void OpenCVForUnity.Features2dModule.ORB.setFirstLevel ( int  firstLevel)

◆ setMaxFeatures()

void OpenCVForUnity.Features2dModule.ORB.setMaxFeatures ( int  maxFeatures)

◆ setNLevels()

void OpenCVForUnity.Features2dModule.ORB.setNLevels ( int  nlevels)

◆ setPatchSize()

void OpenCVForUnity.Features2dModule.ORB.setPatchSize ( int  patchSize)

◆ setScaleFactor()

void OpenCVForUnity.Features2dModule.ORB.setScaleFactor ( double  scaleFactor)

◆ setScoreType()

void OpenCVForUnity.Features2dModule.ORB.setScoreType ( int  scoreType)

◆ setWTA_K()

void OpenCVForUnity.Features2dModule.ORB.setWTA_K ( int  wta_k)

Member Data Documentation

◆ FAST_SCORE

const int OpenCVForUnity.Features2dModule.ORB.FAST_SCORE = 1

◆ HARRIS_SCORE

const int OpenCVForUnity.Features2dModule.ORB.HARRIS_SCORE = 0

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