ORB

Objective-C

@interface ORB : Feature2D

Swift

class ORB : Feature2D

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

described in CITE: 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 of Features2d

Methods

  • Declaration

    Objective-C

    - (ScoreType)getScoreType NS_SWIFT_NAME(getScoreType());

    Swift

    func getScoreType() -> ScoreType

  • The ORB constructor

    Declaration

    Objective-C

    + (nonnull ORB *)create:(int)nfeatures
            scaleFactor:(float)scaleFactor
                nlevels:(int)nlevels
          edgeThreshold:(int)edgeThreshold
             firstLevel:(int)firstLevel
                  WTA_K:(int)WTA_K
              scoreType:(ScoreType)scoreType
              patchSize:(int)patchSize
          fastThreshold:(int)fastThreshold;

    Swift

    class func create(nfeatures: Int32, scaleFactor: Float, nlevels: Int32, edgeThreshold: Int32, firstLevel: Int32, WTA_K: Int32, scoreType: ScoreType, patchSize: Int32, fastThreshold: Int32) -> ORB

    Parameters

    nfeatures

    The maximum number of features to retain.
    scaleFactor

    Pyramid 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.
    nlevels

    The number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
    edgeThreshold

    This is size of the border where the features are not detected. It should roughly match the patchSize parameter.
    firstLevel

    The level of pyramid to put source image to. Previous layers are filled with upscaled source image.
    WTA_K

    The 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).
    scoreType

    The 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.
    patchSize

    size 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.
    fastThreshold

    the fast threshold

  • The ORB constructor

    Declaration

    Objective-C

    + (nonnull ORB *)create:(int)nfeatures
            scaleFactor:(float)scaleFactor
                nlevels:(int)nlevels
          edgeThreshold:(int)edgeThreshold
             firstLevel:(int)firstLevel
                  WTA_K:(int)WTA_K
              scoreType:(ScoreType)scoreType
              patchSize:(int)patchSize;

    Swift

    class func create(nfeatures: Int32, scaleFactor: Float, nlevels: Int32, edgeThreshold: Int32, firstLevel: Int32, WTA_K: Int32, scoreType: ScoreType, patchSize: Int32) -> ORB

    Parameters

    nfeatures

    The maximum number of features to retain.
    scaleFactor

    Pyramid 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.
    nlevels

    The number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
    edgeThreshold

    This is size of the border where the features are not detected. It should roughly match the patchSize parameter.
    firstLevel

    The level of pyramid to put source image to. Previous layers are filled with upscaled source image.
    WTA_K

    The 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).
    scoreType

    The 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.
    patchSize

    size 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.

  • The ORB constructor

    Declaration

    Objective-C

    + (nonnull ORB *)create:(int)nfeatures
            scaleFactor:(float)scaleFactor
                nlevels:(int)nlevels
          edgeThreshold:(int)edgeThreshold
             firstLevel:(int)firstLevel
                  WTA_K:(int)WTA_K
              scoreType:(ScoreType)scoreType;

    Swift

    class func create(nfeatures: Int32, scaleFactor: Float, nlevels: Int32, edgeThreshold: Int32, firstLevel: Int32, WTA_K: Int32, scoreType: ScoreType) -> ORB

    Parameters

    nfeatures

    The maximum number of features to retain.
    scaleFactor

    Pyramid 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.
    nlevels

    The number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
    edgeThreshold

    This is size of the border where the features are not detected. It should roughly match the patchSize parameter.
    firstLevel

    The level of pyramid to put source image to. Previous layers are filled with upscaled source image.
    WTA_K

    The 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).
    scoreType

    The 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. pyramid layers the perceived image area covered by a feature will be larger.

  • The ORB constructor

    Declaration

    Objective-C

    + (nonnull ORB *)create:(int)nfeatures
            scaleFactor:(float)scaleFactor
                nlevels:(int)nlevels
          edgeThreshold:(int)edgeThreshold
             firstLevel:(int)firstLevel
                  WTA_K:(int)WTA_K;

    Swift

    class func create(nfeatures: Int32, scaleFactor: Float, nlevels: Int32, edgeThreshold: Int32, firstLevel: Int32, WTA_K: Int32) -> ORB

    Parameters

    nfeatures

    The maximum number of features to retain.
    scaleFactor

    Pyramid 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.
    nlevels

    The number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
    edgeThreshold

    This is size of the border where the features are not detected. It should roughly match the patchSize parameter.
    firstLevel

    The level of pyramid to put source image to. Previous layers are filled with upscaled source image.
    WTA_K

    The 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). (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. pyramid layers the perceived image area covered by a feature will be larger.

  • The ORB constructor

    Declaration

    Objective-C

    + (nonnull ORB *)create:(int)nfeatures
            scaleFactor:(float)scaleFactor
                nlevels:(int)nlevels
          edgeThreshold:(int)edgeThreshold
             firstLevel:(int)firstLevel;

    Swift

    class func create(nfeatures: Int32, scaleFactor: Float, nlevels: Int32, edgeThreshold: Int32, firstLevel: Int32) -> ORB

    Parameters

    nfeatures

    The maximum number of features to retain.
    scaleFactor

    Pyramid 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.
    nlevels

    The number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
    edgeThreshold

    This is size of the border where the features are not detected. It should roughly match the patchSize parameter.
    firstLevel

    The level of pyramid to put source image to. Previous layers are filled with upscaled source image. 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). (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. pyramid layers the perceived image area covered by a feature will be larger.

  • The ORB constructor

    Declaration

    Objective-C

    + (nonnull ORB *)create:(int)nfeatures
            scaleFactor:(float)scaleFactor
                nlevels:(int)nlevels
          edgeThreshold:(int)edgeThreshold;

    Swift

    class func create(nfeatures: Int32, scaleFactor: Float, nlevels: Int32, edgeThreshold: Int32) -> ORB

    Parameters

    nfeatures

    The maximum number of features to retain.
    scaleFactor

    Pyramid 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.
    nlevels

    The number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
    edgeThreshold

    This is size of the border where the features are not detected. It should roughly match the patchSize parameter. with upscaled source image. 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). (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. pyramid layers the perceived image area covered by a feature will be larger.

  • The ORB constructor

    Declaration

    Objective-C

    + (nonnull ORB *)create:(int)nfeatures
            scaleFactor:(float)scaleFactor
                nlevels:(int)nlevels;

    Swift

    class func create(nfeatures: Int32, scaleFactor: Float, nlevels: Int32) -> ORB

    Parameters

    nfeatures

    The maximum number of features to retain.
    scaleFactor

    Pyramid 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.
    nlevels

    The number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel). roughly match the patchSize parameter. with upscaled source image. 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). (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. pyramid layers the perceived image area covered by a feature will be larger.

  • The ORB constructor

    Declaration

    Objective-C

    + (nonnull ORB *)create:(int)nfeatures scaleFactor:(float)scaleFactor;

    Swift

    class func create(nfeatures: Int32, scaleFactor: Float) -> ORB

    Parameters

    nfeatures

    The maximum number of features to retain.
    scaleFactor

    Pyramid 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. input_image_linear_size/pow(scaleFactor, nlevels - firstLevel). roughly match the patchSize parameter. with upscaled source image. 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). (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. pyramid layers the perceived image area covered by a feature will be larger.

  • The ORB constructor

    Declaration

    Objective-C

    + (nonnull ORB *)create:(int)nfeatures;

    Swift

    class func create(nfeatures: Int32) -> ORB

    Parameters

    nfeatures

    The maximum number of features to retain. 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. input_image_linear_size/pow(scaleFactor, nlevels - firstLevel). roughly match the patchSize parameter. with upscaled source image. 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). (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. pyramid layers the perceived image area covered by a feature will be larger.

  • The ORB constructor

     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.
 input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).
 roughly match the patchSize parameter.
 with upscaled source image.
 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).
 (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.
 pyramid layers the perceived image area covered by a feature will be larger.

    Declaration

    Objective-C

    + (nonnull ORB *)create;

    Swift

    class func create() -> ORB

  • Declaration

    Objective-C

    - (nonnull NSString *)getDefaultName;

    Swift

    func getDefaultName() -> String

  • Declaration

    Objective-C

    - (double)getScaleFactor NS_SWIFT_NAME(getScaleFactor());

    Swift

    func getScaleFactor() -> Double

  • Declaration

    Objective-C

    - (int)getEdgeThreshold NS_SWIFT_NAME(getEdgeThreshold());

    Swift

    func getEdgeThreshold() -> Int32

  • Declaration

    Objective-C

    - (int)getFastThreshold NS_SWIFT_NAME(getFastThreshold());

    Swift

    func getFastThreshold() -> Int32

  • Declaration

    Objective-C

    - (int)getFirstLevel NS_SWIFT_NAME(getFirstLevel());

    Swift

    func getFirstLevel() -> Int32

  • Declaration

    Objective-C

    - (int)getMaxFeatures NS_SWIFT_NAME(getMaxFeatures());

    Swift

    func getMaxFeatures() -> Int32

  • Declaration

    Objective-C

    - (int)getNLevels NS_SWIFT_NAME(getNLevels());

    Swift

    func getNLevels() -> Int32

  • Declaration

    Objective-C

    - (int)getPatchSize NS_SWIFT_NAME(getPatchSize());

    Swift

    func getPatchSize() -> Int32

  • Declaration

    Objective-C

    - (int)getWTA_K NS_SWIFT_NAME(getWTA_K());

    Swift

    func getWTA_K() -> Int32

  • Declaration

    Objective-C

    - (void)setEdgeThreshold:(int)edgeThreshold NS_SWIFT_NAME(setEdgeThreshold(edgeThreshold:));

    Swift

    func setEdgeThreshold(edgeThreshold: Int32)

  • Declaration

    Objective-C

    - (void)setFastThreshold:(int)fastThreshold NS_SWIFT_NAME(setFastThreshold(fastThreshold:));

    Swift

    func setFastThreshold(fastThreshold: Int32)

  • Declaration

    Objective-C

    - (void)setFirstLevel:(int)firstLevel NS_SWIFT_NAME(setFirstLevel(firstLevel:));

    Swift

    func setFirstLevel(firstLevel: Int32)

  • Declaration

    Objective-C

    - (void)setMaxFeatures:(int)maxFeatures NS_SWIFT_NAME(setMaxFeatures(maxFeatures:));

    Swift

    func setMaxFeatures(maxFeatures: Int32)

  • Declaration

    Objective-C

    - (void)setNLevels:(int)nlevels NS_SWIFT_NAME(setNLevels(nlevels:));

    Swift

    func setNLevels(nlevels: Int32)

  • Declaration

    Objective-C

    - (void)setPatchSize:(int)patchSize NS_SWIFT_NAME(setPatchSize(patchSize:));

    Swift

    func setPatchSize(patchSize: Int32)

  • Declaration

    Objective-C

    - (void)setScaleFactor:(double)scaleFactor NS_SWIFT_NAME(setScaleFactor(scaleFactor:));

    Swift

    func setScaleFactor(scaleFactor: Double)

  • Declaration

    Objective-C

    - (void)setScoreType:(ScoreType)scoreType NS_SWIFT_NAME(setScoreType(scoreType:));

    Swift

    func setScoreType(scoreType: ScoreType)

  • Declaration

    Objective-C

    - (void)setWTA_K:(int)wta_k NS_SWIFT_NAME(setWTA_K(wta_k:));

    Swift

    func setWTA_K(wta_k: Int32)