boofcv.alg.shapes.edge

Class ScoreLineSegmentEdge<T extends boofcv.struct.image.ImageGray>

java.lang.Object

boofcv.alg.shapes.edge.BaseIntegralEdge<T>

boofcv.alg.shapes.edge.ScoreLineSegmentEdge<T>

public class ScoreLineSegmentEdge<T extends boofcv.struct.image.ImageGray>
extends BaseIntegralEdge<T>

Looks at the difference in pixel values along the edge of a polygon and decides if its a false positive or not. The average difference along the polygons edge is the score. Note that the abs is only taken after the sum is finished, so objects which are entirely dark/light along the edge will have an advantage.

Field Summary

Fields inherited from class boofcv.alg.shapes.edge.BaseIntegralEdge

integral, integralImage

Constructor Summary

Constructors

Constructor and Description
ScoreLineSegmentEdge(int numSamples, java.lang.Class<T> imageType) Constructor which configures scoring.

Method Summary

Modifier and Type	Method and Description
double	computeAverageDerivative(georegression.struct.point.Point2D_F64 a, georegression.struct.point.Point2D_F64 b, double tanX, double tanY) Returns average tangential derivative along the line segment.
double	getAverageDown()
double	getAverageUp()
int	getNumSamples()
int	getSamplesInside()
void	setImage(T image) Sets the image which is going to be processed.
void	setNumSamples(int numSamples)
void	setTransform(boofcv.struct.distort.PixelTransform_F32 undistToDist) Used to specify a transform that is applied to pixel coordinates to bring them back into original input image coordinates.

Methods inherited from class java.lang.Object

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

Constructor Detail

ScoreLineSegmentEdge

public ScoreLineSegmentEdge(int numSamples,
                            java.lang.Class<T> imageType)

Constructor which configures scoring.

Parameters:

numSamples - Number of points it will sample along an edge

imageType - Type of image it will process

Method Detail

setTransform

public void setTransform(boofcv.struct.distort.PixelTransform_F32 undistToDist)

Used to specify a transform that is applied to pixel coordinates to bring them back into original input image coordinates. For example if the input image has lens distortion but the edge were found in undistorted coordinates this code needs to know how to go from undistorted back into distorted image coordinates in order to read the pixel's value.

Overrides:

setTransform in class BaseIntegralEdge<T extends boofcv.struct.image.ImageGray>

Parameters:

undistToDist - Pixel transformation from undistorted pixels into the actual distorted input image..

setImage

public void setImage(T image)

Sets the image which is going to be processed.

Overrides:

setImage in class BaseIntegralEdge<T extends boofcv.struct.image.ImageGray>

computeAverageDerivative

public double computeAverageDerivative(georegression.struct.point.Point2D_F64 a,
                                       georegression.struct.point.Point2D_F64 b,
                                       double tanX,
                                       double tanY)

Returns average tangential derivative along the line segment. Derivative is computed in direction of tangent. A positive step in the tangent direction will have a positive value. If all samples go outside the image then zero is returned.

Parameters:

a - start point

b - end point

tanX - unit tangent x-axis. determines length of line integral

tanY - unit tangent y-axis determines length of line integral

Returns:

average derivative

getSamplesInside

public int getSamplesInside()

getNumSamples

public int getNumSamples()

setNumSamples

public void setNumSamples(int numSamples)

getAverageUp

public double getAverageUp()

getAverageDown

public double getAverageDown()