boofcv.alg.feature.detect.chess

Class DetectChessCalibrationPoints<T extends boofcv.struct.image.ImageSingleBand,D extends boofcv.struct.image.ImageSingleBand>

java.lang.Object

boofcv.alg.feature.detect.chess.DetectChessCalibrationPoints<T,D>

public class DetectChessCalibrationPoints<T extends boofcv.struct.image.ImageSingleBand,D extends boofcv.struct.image.ImageSingleBand>
extends java.lang.Object

Detects calibration points inside a chessboard calibration target. A crude approximation of the chess board is found by thresholding the image dynamically. Once found corner points are detected and pruned. The remaining points are computed to sub-pixel accuracy by fitting a 2D quadratic to feature intensity in a 3x3 region.

The found control points are ensured to be returned in a row-major format with the correct number of rows and columns, with a counter clockwise ordering. Note that when viewed on the monitor this will appear to be clockwise because the y-axis points down.

Constructor Summary

Constructors

Constructor and Description
DetectChessCalibrationPoints(int numCols, int numRows, int radius, double relativeSizeThreshold, java.lang.Class<T> imageType) Configures detection parameters

Method Summary

Methods

Modifier and Type	Method and Description
boofcv.struct.image.ImageUInt8	getBinary()
DetectChessSquaresBinary	getFindBound()
OrderChessboardQuadBlobs	getOrderAlg()
java.util.List<georegression.struct.point.Point2D_F64>	getPoints()
double	getUserAdaptiveBias()
int	getUserAdaptiveRadius()
double	getUserBinaryThreshold()
boolean	isFoundBound()
boolean	process(T gray)
void	renderIntensity(boofcv.struct.image.ImageFloat32 wholeImage) Only part of the image is processed when detecting features.
void	reset() Forgets any past history and resets the detector
void	setUserAdaptiveBias(double userAdaptiveBias)
void	setUserAdaptiveRadius(int userAdaptiveRadius)
void	setUserBinaryThreshold(double userBinaryThreshold)

Methods inherited from class java.lang.Object

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

Constructor Detail

DetectChessCalibrationPoints

public DetectChessCalibrationPoints(int numCols,
                            int numRows,
                            int radius,
                            double relativeSizeThreshold,
                            java.lang.Class<T> imageType)

Configures detection parameters

Parameters:

numCols - Number of columns in the grid. Target dependent.

numRows - Number of rows in the grid. Target dependent.

radius - Side of interest point detection region. Typically 5

relativeSizeThreshold - Increases or decreases the minimum allowed blob size. Try 1.0

imageType - Type of image being processed

Method Detail

reset

public void reset()

Forgets any past history and resets the detector

process

public boolean process(T gray)

renderIntensity

public void renderIntensity(boofcv.struct.image.ImageFloat32 wholeImage)

Only part of the image is processed when detecting features. This copies the detected part into the provided image

Parameters:

wholeImage - Image being written to

getOrderAlg

public OrderChessboardQuadBlobs getOrderAlg()

getFindBound

public DetectChessSquaresBinary getFindBound()

getPoints

public java.util.List<georegression.struct.point.Point2D_F64> getPoints()

getBinary

public boofcv.struct.image.ImageUInt8 getBinary()

setUserBinaryThreshold

public void setUserBinaryThreshold(double userBinaryThreshold)

getUserBinaryThreshold

public double getUserBinaryThreshold()

getUserAdaptiveRadius

public int getUserAdaptiveRadius()

setUserAdaptiveRadius

public void setUserAdaptiveRadius(int userAdaptiveRadius)

getUserAdaptiveBias

public double getUserAdaptiveBias()

setUserAdaptiveBias

public void setUserAdaptiveBias(double userAdaptiveBias)

isFoundBound

public boolean isFoundBound()