opentl::core::cvdata::Pose3dProjective Class Reference

Sets 3d projection matrix from parameter vector. ATTENTION: direct transformation from body to screen space (extrinsic+intrinsic!) y=H(p)x. More...

Inherits opentl::core::cvdata::Pose.

List of all members.

Public Member Functions
virtual Pose3dProjective *	clone () const
virtual int	initFromPoints (const math::Matrix &bodyPoints, const math::Matrix &screenPoints, const math::SquareMatrix &intrinsicMat, const math::Vector *linkIdx=NULL)
	Compute LSE pose (world T matrix) from N object-screen point correspondences (also called "PnP problem").
virtual int	initFromPointsAndLines (const math::Matrix &bodyPoints, const math::Matrix &screenPoints, const math::Matrix &bodyLines, const math::Matrix &screenLines, const math::SquareMatrix &intrinsicMat, const math::Vector *linkIdxForPoint=NULL, const math::Vector *linkIdxForLine=NULL)
	Compute LSE pose (world T matrix) from N1 object-screen point correspondences and N2 line correspondences.
virtual void	initLieAlgGen ()
	Initialize Lie algebra generators for this pose type.
virtual Pose3dProjective &	operator= (const Pose3dProjective &value)
	Pose3dProjective (const Pose3dProjective &value)
	Constructor. Initialize object with existing value object.
	Pose3dProjective (opentl::core::cvdata::Pose::T_UPDATEMODE updateMode, std::vector< math::Vector2 > *poseLimits=NULL)
	Default constructor.
void	setDataFromVal (double v0, double v1, double v2, double v3, double v4, double v5, double v6, double v7, double v8, double v9, double v10, double v11)
	Set pose data one by one.
virtual void	updateDataFromLocalT ()
	Set pose by homog. transformation matrix.
virtual void	updateWorldTFromData ()
	Function to get the pose as homog. transformation matrix T.
virtual	~Pose3dProjective ()
	Destructor.

---

Detailed Description

Sets 3d projection matrix from parameter vector. ATTENTION: direct transformation from body to screen space (extrinsic+intrinsic!) y=H(p)x.

In order to be compatible to x in 3d homogeneous coordinates H is 4x4 matrix

|p11+1 p12 p13 p14| P = |p21 p22+1 p23 p24| |p31 p32 p33 1| |0 0 0 1|

Vector[0] = p11 Vector[1] = p21 Vector[2] = p31 Vector[3] = p12 Vector[4] = p22 Vector[5] = p32 Vector[6] = p13 Vector[7] = p23 Vector[8] = p33 Vector[9] = p14 Vector[10] = p24

---

Constructor & Destructor Documentation

opentl::core::cvdata::Pose3dProjective::Pose3dProjective	(	opentl::core::cvdata::Pose::T_UPDATEMODE	updateMode,
		std::vector< math::Vector2 > *	poseLimits = NULL
	)

Default constructor.

opentl::core::cvdata::Pose3dProjective::Pose3dProjective

(

const Pose3dProjective &

value

)

Constructor. Initialize object with existing value object.

virtual opentl::core::cvdata::Pose3dProjective::~Pose3dProjective

(

)

[inline, virtual]

Destructor.

---

Member Function Documentation

virtual Pose3dProjective* opentl::core::cvdata::Pose3dProjective::clone

(

)

const [virtual]

Implements opentl::core::cvdata::Pose.

virtual int opentl::core::cvdata::Pose3dProjective::initFromPoints	(	const math::Matrix &	bodyPoints,
		const math::Matrix &	screenPoints,
		const math::SquareMatrix &	intrinsicMat,
		const math::Vector *	linkIdx = NULL
	)			[inline, virtual]

Compute LSE pose (world T matrix) from N object-screen point correspondences (also called "PnP problem").

Parameters:

	bodyPoints	Input points in object space (3xN) or (2xN)
	screenPoints	Input corresponding points in image space (2xN)
	intrinsicMat	Input camera calibration matrix (3x3)
	linkIdx	Input Link ID of each point (for articulated Poses only)

Returns:

Error condition (0 = OK)

Implements opentl::core::cvdata::Pose.

virtual int opentl::core::cvdata::Pose3dProjective::initFromPointsAndLines	(	const math::Matrix &	bodyPoints,
		const math::Matrix &	screenPoints,
		const math::Matrix &	bodyLines,
		const math::Matrix &	screenLines,
		const math::SquareMatrix &	intrinsicMat,
		const math::Vector *	linkIdxForPoint = NULL,
		const math::Vector *	linkIdxForLine = NULL
	)			[inline, virtual]

Compute LSE pose (world T matrix) from N1 object-screen point correspondences and N2 line correspondences.

Parameters:

	bodyPoints	Input points in object space (3xN1) or (2xN1)
	screenPoints	Input corresponding points in image space (2xN1)
	bodyLines	Input line segments in object space (3x2*N2)
	screenLines	Input corresponding lines in image space (3xN2 for 2D represantation)
	intrinsicMat	Input camera calibration matrix (3x3)
	linkIdxForPoint	Input Link ID of each point (for articulated Poses only)
	linkIdxForLine	Input Link ID of each line (for articulated Poses only)

Returns:

Error condition (0 = OK)

Implements opentl::core::cvdata::Pose.

virtual void opentl::core::cvdata::Pose3dProjective::initLieAlgGen

(

)

[virtual]

Initialize Lie algebra generators for this pose type.

Implements opentl::core::cvdata::Pose.

virtual Pose3dProjective& opentl::core::cvdata::Pose3dProjective::operator=

(

const Pose3dProjective &

value

)

[inline, virtual]

void opentl::core::cvdata::Pose3dProjective::setDataFromVal	(	double	v0,
		double	v1,
		double	v2,
		double	v3,
		double	v4,
		double	v5,
		double	v6,
		double	v7,
		double	v8,
		double	v9,
		double	v10,
		double	v11
	)

Set pose data one by one.

virtual void opentl::core::cvdata::Pose3dProjective::updateDataFromLocalT

(

)

[inline, virtual]

Set pose by homog. transformation matrix.

Parameters:

matT

Implements opentl::core::cvdata::Pose.

virtual void opentl::core::cvdata::Pose3dProjective::updateWorldTFromData

(

)

[virtual]

Function to get the pose as homog. transformation matrix T.

Returns:

transformation matrix T

Implements opentl::core::cvdata::Pose.