boofcv.alg.feature.orientation.impl

Class ImplOrientationImageAverageIntegral<T extends boofcv.struct.image.ImageSingleBand,G extends boofcv.struct.sparse.GradientValue>

java.lang.Object

boofcv.alg.feature.orientation.OrientationIntegralBase<T,G>

boofcv.alg.feature.orientation.impl.ImplOrientationImageAverageIntegral<T,G>

All Implemented Interfaces:

OrientationIntegral<T>, RegionOrientation

public class ImplOrientationImageAverageIntegral<T extends boofcv.struct.image.ImageSingleBand,G extends boofcv.struct.sparse.GradientValue>
extends OrientationIntegralBase<T,G>

Estimates the orientation of a region using a "derivative free" method. Points are sampled using an integral image.

Field Summary

Fields

Modifier and Type	Field and Description
protected boofcv.struct.convolve.Kernel2D_F64	kerCosine
protected boofcv.struct.convolve.Kernel2D_F64	kerSine

Fields inherited from class boofcv.alg.feature.orientation.OrientationIntegralBase

g, ii, period, radius, sampleWidth, scale, weights, width

Constructor Summary

Constructors

Constructor and Description
ImplOrientationImageAverageIntegral(int radius, double period, int sampleWidth, double weightSigma, java.lang.Class<T> imageType)

Method Summary

Methods

Modifier and Type	Method and Description
double	compute(double c_x, double c_y) Computes the orientation of a region about its center.
protected double	computeUnweighted(double tl_x, double tl_y, double samplePeriod)
protected double	computeWeighted(double tl_x, double tl_y, double samplePeriod)
void	setImage(T integralImage) Specifies input image data for estimating orientation.
void	setScale(double scale) Specifies scale at which the orientation is estimated.

Methods inherited from class boofcv.alg.feature.orientation.OrientationIntegralBase

getImageType

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

kerCosine

protected boofcv.struct.convolve.Kernel2D_F64 kerCosine

kerSine

protected boofcv.struct.convolve.Kernel2D_F64 kerSine

Constructor Detail

ImplOrientationImageAverageIntegral

public ImplOrientationImageAverageIntegral(int radius,
                                   double period,
                                   int sampleWidth,
                                   double weightSigma,
                                   java.lang.Class<T> imageType)

Parameters:

radius - Radius of the region being considered in terms of Wavelet samples. Typically 6.

weightSigma - Sigma for weighting distribution. Zero for unweighted.

Method Detail

setImage

public void setImage(T integralImage)

Description copied from interface: OrientationIntegral

Specifies input image data for estimating orientation.

Specified by:

setImage in interface OrientationIntegral<T extends boofcv.struct.image.ImageSingleBand>

Overrides:

setImage in class OrientationIntegralBase<T extends boofcv.struct.image.ImageSingleBand,G extends boofcv.struct.sparse.GradientValue>

Parameters:

integralImage - Input image transformed into an integral image.

setScale

public void setScale(double scale)

Description copied from interface: RegionOrientation

Specifies scale at which the orientation is estimated.

Specified by:

setScale in interface RegionOrientation

Overrides:

setScale in class OrientationIntegralBase<T extends boofcv.struct.image.ImageSingleBand,G extends boofcv.struct.sparse.GradientValue>

Parameters:

scale - Scale of the orientation region.

compute

public double compute(double c_x,
             double c_y)

Description copied from interface: RegionOrientation

Computes the orientation of a region about its center.

Parameters:

c_x - Center of the region in image pixels.

c_y - Center of the region in image pixels.

Returns:

Orientation in radians. Angle zero points along x-axis and pi/2 along y-axis.

computeUnweighted

protected double computeUnweighted(double tl_x,
                       double tl_y,
                       double samplePeriod)

computeWeighted

protected double computeWeighted(double tl_x,
                     double tl_y,
                     double samplePeriod)