HandEyeCalibrationAlgorithm Class Reference

#include <ImFusion/Vision/HandEyeCalibrationAlgorithm.h>

Performs hand-eye calibration between two tracking sequences. More...

Inheritance diagram for HandEyeCalibrationAlgorithm:

Detailed Description

Performs hand-eye calibration between two tracking sequences.

A typical use case is to calibrate a camera mounted on a robot end effector (EyeInHand) or a camera mounted on a tripod (EyeOnBase) to the robot coordinate system by the use of a calibration target.

Public Types
enum	CalibrationMethod { TsaiLenz = 0 , GlobalMLSL = 1 }
	Method to be used for calibration. More...
enum	StreamInfo { CalibToCam , CamToCalib , HandToBase , BaseToHand }
	Information about the transformation direction of the tracking sequences.
enum class	CalibrationType { EyeInHand , EyeOnBase }
Public Types inherited from Algorithm
enum	Status {   Unknown = -1 , Success = 0 , Error = 1 , InvalidInput ,   IncompleteInput , OutOfMemoryHost , OutOfMemoryGPU , UnsupportedGPU ,   UnknownAction , AbortedByUser , User = 1000 }
	Status codes. More...

Public Member Functions
	HandEyeCalibrationAlgorithm (TrackingSequence &ts1, TrackingSequence &ts2)
	Construct hand-eye calibration from two tracking sequences.
void	compute () override
	Execute the algorithm.
OwningDataList	takeOutput () override
	Return any new Data that was created by the Algorithm during the last call to compute().
mat4	movingToHand () const
	Returns the transformation between the moving and the hand coordinate systems, where the moving object is the one rigidly attached to the (robot) hand, being either the camera (in the case of EyeInHand calibration) or the calibration object (in the case of EyeOnBase calibration).
mat4	fixedToBase () const
	Returns the transformation between the fixed coordinate system and the base coordinate system, where the fixed coordinate system is the one of the object positioned in a fixed location in the scene, being either the calibration object (in the case of EyeInHand calibration) or the camera (in the case of EyeOnBase calibration).
std::vector< vec2i >	finalPairs () const
	Returns the pairs of indices of the samples from the first and second tracking sequences that were used for calibration.
void	setCalibrationOptimizer (CalibrationOptimizer *fcn)
	Set an optimizer, to be used during the non-linear refinement phase.
const TrackingSequence *	tsMovingToFixed () const
	First tracking sequence as it was passed to alignment with non-corresponding samples removed, either CamToCalib (when EyeInHand) or CalibToCam (when EyeOnBase), with applied registration (Fixed to Base)
const TrackingSequence *	tsHandToBase () const
	Second tracking sequence as it was passed to alignment with non-corresponding samples removed with applied calibration (Moving to Hand)
Public Member Functions inherited from Algorithm
	Algorithm ()
	Default constructor will registers a single "compute" action that calls compute() and returns status().
virtual void	setProgress (Progress *progress)
	Sets a Progress interface the algorithm can use to notify observers about its computing progress.
Progress *	progress () const
	Returns the progress interface if set.
virtual int	status () const
	Indicates the status of the last call to compute().
virtual bool	survivesDataDeletion (const Data *) const
	Indicates whether the algorithm can handle (partial) deletion of the specified data, by default this checks whether the data is in the input list.
const FactoryInfo &	factoryInfo () const
	Returns the record describing how this Algorithm was instantiated by the AlgorithmFactory.
void	setFactoryInfo (const FactoryInfo &value)
	Sets the record describing how this Algorithm was instantiated by the AlgorithmFactory.
Status	runAction (const std::string &id)
	Run the action with name id if it exists.
const std::vector< Action > &	actions ()
	Get a mapping from Action id to Action as registered in this algorithm.
Public Member Functions inherited from Configurable
virtual void	configure (const Properties *p)
	Configure this object instance by de-serializing the given Properties.
virtual void	configuration (Properties *p) const
	Serialize the current object configuration into the given Properties object.
virtual void	configureDefaults ()
	Retrieve the properties of this object, replaces values with their defaults and sets it again.
void	registerParameter (ParameterBase *param)
	Register the given Parameter or SubProperty, so that it will be configured during configure()/configuration().
void	unregisterParameter (const ParameterBase *param)
	Remove the given Parameter or SubProperty from the list of registered parameters.
	Configurable (const Configurable &rhs)
	Configurable (Configurable &&rhs) noexcept
Configurable &	operator= (const Configurable &)
Configurable &	operator= (Configurable &&) noexcept

Static Public Member Functions
static bool	createCompatible (const DataList &data, Algorithm **a=nullptr)
Static Public Member Functions inherited from Algorithm
static bool	createCompatible (const DataList &data, Algorithm **a=nullptr)
	Factory function to check algorithm compatibility with input data and optionally instantiate it.

Public Attributes
Parameter< CalibrationType >	p_calibrationType
	Calibration type, either EyeInHand or EyeOnBase.
Parameter< StreamInfo >	p_si1
	Direction of the transformation of the first tracking sequence.
Parameter< StreamInfo >	p_si2
	Direction of the transformation of the second tracking sequence.
Parameter< CalibrationMethod >	p_method = {"method", CalibrationMethod::TsaiLenz, this}
	Calibration method to be used.
Parameter< bool >	p_resetMatricesBeforeComputing
	Reset the matrices of the input streams before starting the computation.
Parameter< double >	p_minRelativeAngleSampleSelection
	Minimum angle in degrees between current sample and a previously selected sample for the current sample to be selected.
Parameter< double >	p_minRelativeTranslationSampleSelection
	Minimum trnaslation between current sample and a previously selected sample for the current sample to be selected.
Parameter< double >	p_minRelativeAngle
	Minimum angle in degrees between pose pairs selected for optimization.
Parameter< double >	p_poseInlierThreshold = {"poseInlierThreshold", 5, this}
	Inlier threshold for pose pair errors.
Parameter< bool >	p_useRansac
	Use RANSAC scheme: select 3 random pairs of poses and compute the calibration, repeat number of iterations and select the best result.
Parameter< int >	p_ransacIterations = {"ransacIterations", 1000, this}
	Number of RANSAC iterations.
Parameter< bool >	p_refineNonLinear = {"refineNonLinear", false, this}
	Refine Tsai-Lenz output using the non-linear optimizer.
Public Attributes inherited from Algorithm
Signal	signalOutputChanged
	Signal should be emitted by Algorithms when their output/result has changed.
Signal	signalParametersChanged
	Signal should be emitted by Algorithms when their parameter configuration has changed.
Public Attributes inherited from Configurable
Signal	signalParametersChanged
	Emitted whenever one of the registered Parameters' or SubPropertys' signalValueChanged signal was emitted.

Additional Inherited Members
Protected Member Functions inherited from Algorithm
void	loadDefaults ()
void	registerAction (const std::string &id, const std::string &guiName, const std::function< Algorithm::Status(void)> &action)
	Register an action to be run via runAction.
template<typename D>
void	registerAction (const std::string &id, const std::string &guiName, Algorithm::Status(D::*action)(void))
	Template version of runAction that can be used with a pointer to a member function.
void	registerAction (const Action &action)
	Register an action.
Protected Attributes inherited from Algorithm
std::string	m_name
	Algorithm name.
Progress *	m_progress = nullptr
	Non-owing pointer to a progress interface. May be a nullptr.
FactoryInfo	m_factoryInfo = {}
	Record describing how this algorithm was instantiated by the AlgorithmFactory.
int	m_status = Status::Unknown
	Algorithm status after last call to compute()
std::vector< Action >	m_actions
	Map of key given by the id of the action, of the available actions of this algorithm.
Protected Attributes inherited from Configurable
std::vector< Param >	m_params
	List of all registered Parameter and SubProperty instances.

Member Enumeration Documentation

CalibrationMethod

enum CalibrationMethod

Method to be used for calibration.

Enumerator
TsaiLenz	Tsai-Lenz.
GlobalMLSL	NLopt, MLSL algorithm.

CalibrationType

enum class CalibrationType

strong

Enumerator
EyeInHand	The camera is mounted on the robot end effector (moving object is the camera, fixed object is the calibration target)
EyeOnBase	The camera is mounted e.g. on a tripod or on the ceiling (moving object is the calibration target, fixed object is the camera)

Constructor & Destructor Documentation

HandEyeCalibrationAlgorithm()

HandEyeCalibrationAlgorithm	(	TrackingSequence &	ts1,
		TrackingSequence &	ts2 )

Construct hand-eye calibration from two tracking sequences.

Position-wise correspondence between the tracking sequences is assumed. Timestamps are NOT used for matching.

Member Function Documentation

compute()

void compute ( )

overridevirtual

Execute the algorithm.

Implements Algorithm.

takeOutput()

OwningDataList takeOutput ( )

overridevirtual

Return any new Data that was created by the Algorithm during the last call to compute().

The default implementation will return an empty list.

Note

Since ownership of the data is transferred, you can call this method only once between calls to compute().

Reimplemented from Algorithm.

setCalibrationOptimizer()

void setCalibrationOptimizer ( CalibrationOptimizer * fcn )

inline

Set an optimizer, to be used during the non-linear refinement phase.

If not set, a default pose optimizer will be used minimizing the HregInv * m_Hg[i] * Hcg * m_Hc[i]

Member Data Documentation

p_calibrationType

Parameter<CalibrationType> p_calibrationType

Initial value:

= {"calibrationType",
                                                        CalibrationType::EyeInHand,
                                                        this}

Calibration type, either EyeInHand or EyeOnBase.

p_si1

Parameter<StreamInfo> p_si1

Initial value:

= {"stream1",
                                       StreamInfo::CamToCalib,
                                       this}

Direction of the transformation of the first tracking sequence.

p_si2

Parameter<StreamInfo> p_si2

Initial value:

= {"stream2",
                                       StreamInfo::HandToBase,
                                       this}

Direction of the transformation of the second tracking sequence.

p_resetMatricesBeforeComputing

Parameter<bool> p_resetMatricesBeforeComputing

Initial value:

= {"resetMatricesBefore",
                                                          false,
                                                          this}

Reset the matrices of the input streams before starting the computation.

p_minRelativeAngleSampleSelection

Parameter<double> p_minRelativeAngleSampleSelection

Initial value:

= {
            "minRelativeAngleSampleSelection",
            0,
            this}

Minimum angle in degrees between current sample and a previously selected sample for the current sample to be selected.

p_minRelativeTranslationSampleSelection

Parameter<double> p_minRelativeTranslationSampleSelection

Initial value:

= {
            "minRelativeTranslationSampleSelection",
            0,
            this}

Minimum trnaslation between current sample and a previously selected sample for the current sample to be selected.

p_minRelativeAngle

Parameter<double> p_minRelativeAngle

Initial value:

= {"minRelativeAngle",
                                                20,
                                                this}

Minimum angle in degrees between pose pairs selected for optimization.

p_useRansac

Parameter<bool> p_useRansac

Initial value:

= {
            "useRansac",
            false,
            this}

Use RANSAC scheme: select 3 random pairs of poses and compute the calibration, repeat number of iterations and select the best result.

---

The documentation for this class was generated from the following file:

• ImFusion/Vision/HandEyeCalibrationAlgorithm.h