This interface provide basic functionalities of the calibration object. More...

Inheritance diagram for ILCalib:

Public Member Functions
LPVErrorCode	AddPoint (double imagePointX, double imagePointY, double worldPointX, double worldPointY)

LPVErrorCode	AddPoints (ILCalibPointPairs *pointPairs)

LPVErrorCode	Calibrate ()

LPVErrorCode	FixImage (ILImage image, ILImage fixedImage)

LPVErrorCode	GenPostTransformMatrix (ILCalibPointPairs *pointPairs)

void	ImageToWorld (double imagePointX, double imagePointY, double worldPointX, double worldPointY)

BOOL	IsCalibrated ()

void	SetImageSize (int w, int h)

void	SetPostTransform (double offsetX, double offsetY, double deltaAngle)

void	SetPostTransformMatrix (ILTransform *tf)

void	SetPostTransformMatrix23 (LMatrix23 *data)

void	SetPostTransformMatrix33 (LMatrix33 *data)

void	WorldToImage (double worldPointX, double worldPointY, double imagePointX, double imagePointY)

Public Member Functions inherited from ILObject
ILObject *	Copy ()

LPVErrorCode	Load (LString filename)

void	Reset ()

LPVErrorCode	Save (LString filename)

BOOL	Valid ()

Properties
double	CalibError `[get]`
	The overall RMS re-projection error for the calibration, calculated based on the distances between the image points and the projected (using the optimized calibration matrices) world points. It's defined as: \( \sqrt{ \frac{1}{n} \sum_{i=0}^{n} distance(p^{image}_i, p^{proj}_i)^2 } \).

LPVFixImageMode	FixImageMode `[get, set]`
	The mode to fix image used in FixImage(). More...

double	FixImageOffsetX `[get, set]`
	The x-coordinate offset (in pixel unit) of the fixed image used in FixImage(), used together with FixImageOffsetY. By default, it's 0, means no offset in x-coordinate. You may change the offset to translate the fixed image, for example move the inspect region to the center of the fixed image.

double	FixImageOffsetY `[get, set]`
	The y-coordinate offset (in pixel unit) of the fixed image used in FixImage(), used together with FixImageOffsetX. By default, it's 0, means no offset in y-coordinate. You may change the offset to translate the fixed image, for example move the inspect region to the center of the fixed image.

double	FixImageScale `[get, set]`
	The scale of the fixed image used in FixImage(). By default, it's 1, means no scale. You may change the scale factor to zoom in/out the fixed image.

LPVInterpolationMethod	InterpolationMethod `[get, set]`
	The interpolation method used in fix the image for undistortion (and untilt). By default, it's LPVInterCubic.

LPVCalibModel	Model `[get]`
	The calibration model.

BOOL	UseCache `[get, set]`
	Whether to make use of cache which is used to speed-up the process of the image undistortion (and untilt), but consume more memory. By default, it's off.

Detailed Description

This interface provide basic functionalities of the calibration object.

This is a base interface for all kinds of calibrations. For different chosen calibration model, the implementation varies.

To use this interface, you should create a calibration object, such as:

ILCalibNPoints, ILCalibPinHole, ILCalibFFD, ILCalibCustom...

Member Function Documentation

◆ AddPoint()

LPVErrorCode AddPoint	(	double	imagePointX,
		double	imagePointY,
		double	worldPointX,
		double	worldPointY
	)

Add a new point pair for calibration.

Parameters

[in]	imagePointX	The x-coordinate of the image point.
[in]	imagePointY	The y-coordinate of the image point.
[in]	worldPointX	The x-coordinate of the world point.
[in]	worldPointY	The y-coordinate of the world point.

Return values

error Return error code if anything is wrong.

◆ AddPoints()

LPVErrorCode AddPoints ( ILCalibPointPairs * pointPairs )

Add a collection of point pairs for calibration, usually you get these point pairs from a calibration board.

Parameters

[in] pointPairs The collection of point pairs.

Return values

error Return error code if anything is wrong.

See also: ILCalibBoard

◆ Calibrate()

LPVErrorCode Calibrate ( )

Do calibration with current configuration and point pairs added.

Return values

error Return error code if anything is wrong.

◆ FixImage()

LPVErrorCode FixImage	(	ILImage *	image,
		ILImage *	fixedImage
	)

Fix the image for undistortion (and untilt).
The rectification works with a calibrated system, if not it returns the LPVErrCalibNotCalib error.

Parameters

[in]	image	The input image.
[out]	fixedImage	Output the fixed result image.

Return values

error Return error code if anything is wrong.

See also: FixImageMode, FixImageScale, FixImageOffsetX, FixImageOffsetY, InterpolationMethod

◆ GenPostTransformMatrix()

LPVErrorCode GenPostTransformMatrix ( ILCalibPointPairs * pointPairs )

Generate and set the post-transform matrix, according to the pairs of some pixel positions in the output fixed image and their expected world positions.

Parameters

[in] pointPairs The collection of point pairs.

Return values

error Return error code if anything is wrong.

◆ ImageToWorld()

void ImageToWorld	(	double	imagePointX,
		double	imagePointY,
		double *	worldPointX,
		double *	worldPointY
	)

Map a point from the image coordinates to the world coordinates.
The mapping works with a calibrated system, if not the output world point is the same point as the input image point.

Parameters

[in]	imagePointX	The x-coordinate of the image point.
[in]	imagePointY	The y-coordinate of the image point.
[out]	worldPointX	Return the x-coordinate of the world point.
[out]	worldPointY	Return the y-coordinate of the world point.

◆ IsCalibrated()

BOOL IsCalibrated ( )

Check whether the calibration object is well-calibrated.

Return values

val	Return True if it's calibrated, otherwise, return False.

◆ SetImageSize()

void SetImageSize	(	int	w,
		int	h
	)

Set the image size from camera, use for calibration process without image, such as 9 points calibration.

Parameters

[in]	w	The width of the image.
[in]	h	The height of the image.

◆ SetPostTransform()

void SetPostTransform	(	double	offsetX,
		double	offsetY,
		double	deltaAngle
	)

Set customized post-transform to the world coordinates, based on the transformation of origin point.
It is applied at the end of the image-to-world mapping, and inverted applied at the beginning of the world-to-image mapping.
If both post-transform origin and matrix is configured, the first one is applied firstly then the later one. In the inverted transform, it's done in the reversed order.

Parameters

[in]	offsetX	The x-coordinate of offset to origin point.
[in]	offsetY	The y-coordinate of offset to origin point.
[in]	deltaAngle	The clockwise delta rotation angle of the coordinates.

See also: SetPostTransformMatrix(), SetPostTransformMatrix23(), SetPostTransformMatrix33().

◆ SetPostTransformMatrix()

void SetPostTransformMatrix ( ILTransform * tf )

Set customized post-transform to the world coordinates, using transformation matrix.
It is applied at the end of the image-to-world mapping, and inverted applied at the beginning of the world-to-image mapping.
If both post-transform origin and matrix is configured, the first one is applied firstly then the later one. In the inverted transform, it's done in the reversed order.

Parameters

[in] tf The transformation.

See also: SetPostTransform(), SetPostTransformMatrix23(), SetPostTransformMatrix33().

◆ SetPostTransformMatrix23()

void SetPostTransformMatrix23 ( LMatrix23 * data )

Set customized post-transform to the world coordinates, using \( 2 \times 3 \) transformation matrix, which has rotation, translation and scale DOF.

See also: SetPostTransform(), SetPostTransformMatrix(), SetPostTransformMatrix33().

◆ SetPostTransformMatrix33()

void SetPostTransformMatrix33 ( LMatrix33 * data )

Set customized post-transform to the world coordinates, using \( 3 \times 3 \) transformation matrix, which has rotation, translation, scale and perspective projection DOF.

See also: SetPostTransform(), SetPostTransformMatrix(), SetPostTransformMatrix23().

◆ WorldToImage()

void WorldToImage	(	double	worldPointX,
		double	worldPointY,
		double *	imagePointX,
		double *	imagePointY
	)

Map a point from the world coordinates to the image coordinates.
The mapping works with a calibrated system, if not the output world point is the same point as the input image point.

Parameters

[in]	worldPointX	The x-coordinate of the world point.
[in]	worldPointY	The y-coordinate of the world point.
[out]	imagePointX	Return the x-coordinate of the image point.
[out]	imagePointY	Return the y-coordinate of the image point.

Property Documentation

◆ FixImageMode

LPVFixImageMode FixImageMode

getset

The mode to fix image used in FixImage().

Change the mode will also affect the image-world mapping logic.
LPVFixImageNone (Default) indicate user is using the original image captured by the camera for the subsequent detection or inspection tasks, so the image point in the image-world mapping logic is in the coordinates of the original image. Correspondingly, for LPVFixImageUndistort mode, the image point is in the coordinates of the undistorted image. For LPVFixImageUndistortAndUntilt mode, it's in the coordinates of the undistorted and untilt image. If you want to use different mapping logic at the same time, you may have to duplicate the calibration object via Copy() and set different FixImageMode for them.

Different calibration model support different fix mode, as the table below.

Calibration model	Original	Undistort	Undistort and Untilt
N-Points	Support	-	Only untilt
Pinhole	Support	Support	Support
FFD	Support	Support	Support
Custom	Support	-	-

Public Member Functions

Properties

Detailed Description

Member Function Documentation

◆ AddPoint()

◆ AddPoints()

◆ Calibrate()

◆ FixImage()

◆ GenPostTransformMatrix()

◆ ImageToWorld()

◆ IsCalibrated()

◆ SetImageSize()

◆ SetPostTransform()

◆ SetPostTransformMatrix()

◆ SetPostTransformMatrix23()

◆ SetPostTransformMatrix33()

◆ WorldToImage()

Property Documentation

◆ FixImageMode