boofcv.alg.feature.detect.line

Class HoughTransformLineFootOfNorm

java.lang.Object

boofcv.alg.feature.detect.line.HoughTransformLineFootOfNorm

public class HoughTransformLineFootOfNorm
extends java.lang.Object

Hough transform based line detector. Lines are parameterized based upon the (x,y) coordinate of the closest point to the origin. This parametrization is more convenient since it corresponds directly with the image space. See [1] for more details.

The line's direction is estimated using the gradient at each point flagged as belonging to a line. To minimize error the image center is used as the coordinate system's center. However lines which lie too close to the center can't have their orientation accurately estimated.

[1] Section 9.3 of E.R. Davies, "Machine Vision Theory Algorithms Practicalities," 3rd Ed. 2005

Constructor Summary

Constructors

Constructor and Description
HoughTransformLineFootOfNorm(NonMaxSuppression extractor, int minDistanceFromOrigin) Specifies parameters of transform.

Method Summary

Modifier and Type	Method and Description
org.ddogleg.struct.FastQueue<georegression.struct.line.LineParametric2D_F32>	extractLines() Searches for local maximas and converts into lines.
float[]	getFoundIntensity() Returns the intensity/edge count for each returned line.
boofcv.struct.image.GrayF32	getTransform() Returns the Hough transform image.
void	parameterize(int x, int y, float derivX, float derivY) Takes the detected point along the line and its gradient and converts it into transform space.
<D extends boofcv.struct.image.ImageGray> void	transform(D derivX, D derivY, boofcv.struct.image.GrayU8 binary) Computes the Hough transform using the image gradient and a binary image which flags pixels as being edges or not.

Methods inherited from class java.lang.Object

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

Constructor Detail

HoughTransformLineFootOfNorm

public HoughTransformLineFootOfNorm(NonMaxSuppression extractor,
                                    int minDistanceFromOrigin)

Specifies parameters of transform.

Parameters:

extractor - Extracts local maxima from transform space. A set of candidates is provided, but can be ignored.

minDistanceFromOrigin - Distance from the origin in which lines will not be estimated. In transform space. Try 5.

Method Detail

transform

public <D extends boofcv.struct.image.ImageGray> void transform(D derivX,
                                                                D derivY,
                                                                boofcv.struct.image.GrayU8 binary)

Computes the Hough transform using the image gradient and a binary image which flags pixels as being edges or not.

Parameters:

derivX - Image derivative along x-axis.

derivY - Image derivative along y-axis.

binary - Non-zero pixels are considered to be line pixels.

extractLines

public org.ddogleg.struct.FastQueue<georegression.struct.line.LineParametric2D_F32> extractLines()

Searches for local maximas and converts into lines.

Returns:

Found lines in the image.

parameterize

public void parameterize(int x,
                         int y,
                         float derivX,
                         float derivY)

Takes the detected point along the line and its gradient and converts it into transform space.

Parameters:

x - point in image.

y - point in image.

derivX - gradient of point.

derivY - gradient of point.

getTransform

public boofcv.struct.image.GrayF32 getTransform()

Returns the Hough transform image.

Returns:

Transform image.

getFoundIntensity

public float[] getFoundIntensity()

Returns the intensity/edge count for each returned line. Useful when doing post processing pruning.

Returns:

Array containing line intensities.