#include <vpMe.h>

Public Types
enum	vpLikelihoodThresholdType { OLD_THRESHOLD = 0 , NORMALIZED_THRESHOLD = 1 }

Public Member Functions
	vpMe ()
	vpMe (const vpMe &me)
virtual	~vpMe ()
vpMe &	operator= (const vpMe &me)
vpMe &	operator= (const vpMe &&me)
void	checkSamplestep (double &sample_step)
unsigned int	getAngleStep () const
int	getInitRange () const
vpMatrix *	getMask () const
unsigned int	getMaskNumber () const
int	getMaskSign () const
unsigned int	getMaskSize () const
double	getMinSampleStep () const
double	getMu1 () const
double	getMu2 () const
int	getNbTotalSample () const
int	getPointsToTrack () const
unsigned int	getRange () const
double	getSampleStep () const
int	getStrip () const
double	getThreshold () const
double	getThresholdMarginRatio () const
double	getMinThreshold () const
bool	getUseAutomaticThreshold () const
vpLikelihoodThresholdType	getLikelihoodThresholdType () const
void	initMask ()
void	print ()
void	setAngleStep (const unsigned int &anglestep)
void	setInitRange (const int &initRange)
void	setMaskNumber (const unsigned int &mask_number)
void	setMaskSign (const int &mask_sign)
void	setMaskSize (const unsigned int &mask_size)
void	setMinSampleStep (const double &min_samplestep)
void	setMu1 (const double &mu_1)
void	setMu2 (const double &mu_2)
void	setNbTotalSample (const int &ntotal_sample)
void	setPointsToTrack (const int &points_to_track)
void	setRange (const unsigned int &range)
void	setSampleStep (const double &sample_step)
void	setStrip (const int &strip)
void	setThreshold (const double &threshold)
void	setThresholdMarginRatio (const double &thresholdMarginRatio)
void	setMinThreshold (const double &minThreshold)
void	setLikelihoodThresholdType (const vpLikelihoodThresholdType likelihood_threshold_type)

Friends
void	to_json (nlohmann::json &j, const vpMe &me)
void	from_json (const nlohmann::json &j, vpMe &me)

Detailed Description

This class defines predetermined masks for moving-edges (ME) sites and holds moving edges tracking parameters.

To know more about moving-edges and their usage for object tracking, follow Tutorial: Moving-edges tracking.

JSON serialization

Since ViSP 3.6.0, if ViSP is build with JSON for modern C++ 3rd-party we introduce JSON serialization capabilities for vpMe. The following sample code shows how to save moving-edges settings in a file named me.json and reload the values from this JSON file.

#include <visp3/me/vpMe.h>
 
#ifdef ENABLE_VISP_NAMESPACE
using namespace VISP_NAMESPACE_NAME;
#endif
 
int main()
{
#if defined(VISP_HAVE_NLOHMANN_JSON)
  std::string filename = "me.json";
  {
    vpMe me;
    me.setLikelihoodThresholdType(vpMe::NORMALIZED_THRESHOLD);
    me.setThreshold(20);    // Value in range [0 ; 255]
    me.setThresholdMarginRatio(-1.); // Deactivate automatic thresholding
    me.setMinThreshold(-1.); // Deactivate automatic thresholding
    me.setMaskNumber(180);
    me.setMaskSign(0);
    me.setMu1(0.5);
    me.setMu2(0.5);
    me.setNbTotalSample(0);
    me.setPointsToTrack(200);
    me.setRange(5);
    me.setStrip(2);
 
    std::ofstream file(filename);
    const nlohmann::json j = me;
    file << j;
    file.close();
  }
  {
    std::ifstream file(filename);
    const nlohmann::json j = nlohmann::json::parse(file);
    vpMe me;
    me = j;
    file.close();
    std::cout << "Read moving-edges settings from " << filename << ":" << std::endl;
    me.print();
  }
#endif
}

If you build and execute the sample code, it will produce the following output:

Read moving-edges settings from me.json:
 
Moving edges settings
 
 Size of the convolution masks....5x5 pixels
 Number of masks..................180
 Query range +/- J................5 pixels
 Likelihood threshold type........normalized
 Likelihood threshold.............20
 Likelihood margin ratio..........unused
 Minimum likelihood threshold.....unused
 Contrast tolerance +/-...........50% and 50%
 Sample step......................10 pixels
 Strip............................2 pixels
 Min sample step..................4 pixels

The content of the me.json file is the following:

$ cat me.json
{"maskSign":0,"maskSize":5,"minSampleStep":4.0,"mu":[0.5,0.5],"nMask":180,"ntotalSample":0,"pointsToTrack":200,
 "range":5,"sampleStep":10.0,"strip":2,"threshold":20.0,"thresholdMarginRatio":-1.0,"minThreshold":-1.0,"thresholdType":"normalized"}

Tutorials & Examples

Tutorials
If you are interested in using a ME tracker in your application, you may have a look at:

Tutorial: Moving-edges tracking

Examples: catchGenericTrackerDeterminist.cpp, mbtEdgeKltTracking.cpp, mbtEdgeTracking.cpp, mbtGenericTracking.cpp, mbtGenericTracking2.cpp, mbtGenericTrackingDepth.cpp, perfGenericTracker.cpp, servoAfma62DhalfCamVelocity.cpp, servoAfma6Cylinder2DCamVelocity.cpp, servoAfma6Cylinder2DCamVelocitySecondaryTask.cpp, servoAfma6Line2DCamVelocity.cpp, servoAfma6SquareLines2DCamVelocity.cpp, servoAfma6TwoLines2DCamVelocity.cpp, testGenericTracker.cpp, testKeyPoint-2.cpp, testKeyPoint-4.cpp, testMbtXmlGenericParser.cpp, trackMeCircle.cpp, trackMeEllipse.cpp, trackMeLine.cpp, trackMeNurbs.cpp, tutorial-detection-object-mbt-deprecated.cpp, tutorial-detection-object-mbt.cpp, tutorial-detection-object-mbt2-deprecated.cpp, tutorial-detection-object-mbt2.cpp, tutorial-mb-edge-tracker.cpp, tutorial-mb-generic-tracker-apriltag-rs2.cpp, tutorial-mb-generic-tracker-apriltag-webcam.cpp, tutorial-mb-generic-tracker-full.cpp, tutorial-mb-generic-tracker-live.cpp, tutorial-mb-generic-tracker-rgbd.cpp, tutorial-mb-generic-tracker-stereo-mono.cpp, tutorial-mb-generic-tracker.cpp, tutorial-mb-hybrid-tracker.cpp, tutorial-mb-tracker-full.cpp, tutorial-mb-tracker.cpp, tutorial-me-ellipse-tracker.cpp, and tutorial-me-line-tracker.cpp.

Definition at line 142 of file vpMe.h.

Member Enumeration Documentation

◆ vpLikelihoodThresholdType

enum vpMe::vpLikelihoodThresholdType

Type of likelihood threshold to use.

Enumerator
OLD_THRESHOLD	Old likelihood ratio threshold (to be avoided).
NORMALIZED_THRESHOLD	Easy-to-use normalized likelihood threshold corresponding to the minimal luminance contrast to consider with values in [0 ; 255].

Definition at line 148 of file vpMe.h.

Constructor & Destructor Documentation

◆ vpMe() [1/2]

vpMe::vpMe ( )

Default constructor.

Definition at line 433 of file vpMe.cpp.

References initMask(), and OLD_THRESHOLD.

Referenced by from_json, operator=(), operator=(), to_json, and vpMe().

◆ vpMe() [2/2]

vpMe::vpMe ( const vpMe & me )

Copy constructor.

Definition at line 461 of file vpMe.cpp.

References OLD_THRESHOLD, and vpMe().

◆ ~vpMe()

vpMe::~vpMe ( )

virtual

Destructor.

Definition at line 547 of file vpMe.cpp.

Member Function Documentation

◆ checkSamplestep()

void vpMe::checkSamplestep ( double & sample_step )

inline

Check sample step wrt min value.

Parameters

[in,out] sample_step : When this value is lower than the min sample step value, it is modified to the min sample step value.

Definition at line 190 of file vpMe.h.

◆ getAngleStep()

unsigned int vpMe::getAngleStep ( ) const

inline

Return the angle step.

Returns: Value of angle step.

Definition at line 202 of file vpMe.h.

Referenced by vpMeSite::computeMaskIndex().

◆ getInitRange()

int vpMe::getInitRange ( ) const

inline

Return the range used during the initialization step. A negative value means that the default value is used by the different ME primitives.

Definition at line 208 of file vpMe.h.

Referenced by from_json, and to_json.

◆ getLikelihoodThresholdType()

vpLikelihoodThresholdType vpMe::getLikelihoodThresholdType ( ) const

inline

Return the selected choice for the likelihood threshold.

Returns: The likelihood threshold type to consider.

See also: setLikelihoodThresholdType(), setThreshold(), getThreshold()

Examples: testMbtXmlGenericParser.cpp.

Definition at line 342 of file vpMe.h.

Referenced by vpMeSite::computeFinalThreshold(), from_json, and to_json.

◆ getMask()

vpMatrix * vpMe::getMask ( ) const

inline

Get the matrix of the mask.

Returns: the value of mask.

Definition at line 215 of file vpMe.h.

Referenced by vpMeSite::convolution(), and vpMeSite::convolution().

◆ getMaskNumber()

unsigned int vpMe::getMaskNumber ( ) const

inline

Return the number of mask applied to determine the object contour. The number of mask determines the precision of the normal of the edge for every sample. If precision is 2deg, then there are 360/2 = 180 masks.

Returns: the current number of mask.

Examples: testMbtXmlGenericParser.cpp.

Definition at line 224 of file vpMe.h.

Referenced by to_json.

◆ getMaskSign()

int vpMe::getMaskSign ( ) const

inline

Return the mask sign.

Returns: Value of mask_sign.

Definition at line 231 of file vpMe.h.

Referenced by from_json, and to_json.

◆ getMaskSize()

unsigned int vpMe::getMaskSize ( ) const

inline

Return the actual mask size (in pixel) used to compute the image gradient and determine the object contour. The mask size defines the size of the convolution mask used to detect an edge.

Returns: the current mask size.

Examples: testMbtXmlGenericParser.cpp.

Definition at line 240 of file vpMe.h.

Referenced by vpMeSite::computeFinalThreshold(), vpMeSite::convolution(), vpMeSite::convolution(), from_json, and to_json.

◆ getMinSampleStep()

double vpMe::getMinSampleStep ( ) const

inline

Get the minimum allowed sample step. Useful to specify a lower bound when the sample step is changed.

Returns: Value of min sample step.

Definition at line 248 of file vpMe.h.

Referenced by from_json, and to_json.

◆ getMinThreshold()

double vpMe::getMinThreshold ( ) const

inline

Return the minimum contrast threshold of the vpMeSite that can be used when using the automatic threshold computation.

Returns: Value of the minimum contrast threshold.

See also: setThresholdMarginRatio(), getThresholdMarginRatio(), setMinThreshold(), getLikelihoodThresholdType(), setLikelihoodThresholdType()

Definition at line 325 of file vpMe.h.

Referenced by from_json, vpMeSite::setContrastThreshold(), and to_json.

◆ getMu1()

double vpMe::getMu1 ( ) const

inline

Get the minimum image contrast allowed to detect a contour.

Returns: Value of mu1.

Examples: testMbtXmlGenericParser.cpp.

Definition at line 255 of file vpMe.h.

Referenced by to_json, vpMeSite::track(), and vpMeSite::trackMultipleHypotheses().

◆ getMu2()

double vpMe::getMu2 ( ) const

inline

Get the maximum image contrast allowed to detect a contour.

Returns: Value of mu2.

Examples: testMbtXmlGenericParser.cpp.

Definition at line 262 of file vpMe.h.

Referenced by to_json, vpMeSite::track(), and vpMeSite::trackMultipleHypotheses().

◆ getNbTotalSample()

int vpMe::getNbTotalSample ( ) const

inline

Get how many discretized points are used to track the feature.

Returns: Value of ntotal_sample.

Definition at line 269 of file vpMe.h.

Referenced by from_json, and to_json.

◆ getPointsToTrack()

int vpMe::getPointsToTrack ( ) const

inline

Return the number of points to track.

Returns: Value of points_to_track.

Definition at line 276 of file vpMe.h.

Referenced by from_json, and to_json.

◆ getRange()

unsigned int vpMe::getRange ( ) const

inline

Return the seek range on both sides of the reference pixel.

Returns: Value of range.

Examples: testMbtXmlGenericParser.cpp, trackMeEllipse.cpp, and trackMeLine.cpp.

Definition at line 283 of file vpMe.h.

Referenced by from_json, to_json, vpMeSite::track(), and vpMeSite::trackMultipleHypotheses().

◆ getSampleStep()

double vpMe::getSampleStep ( ) const

inline

Get the minimum distance in pixel between two discretized points.

Returns: Value of sample_step.

Examples: testMbtXmlGenericParser.cpp, trackMeCircle.cpp, trackMeEllipse.cpp, and trackMeLine.cpp.

Definition at line 290 of file vpMe.h.

Referenced by from_json, and to_json.

◆ getStrip()

int vpMe::getStrip ( ) const

inline

Get the number of pixels that are ignored around the image borders.

Returns: the value of strip.

Definition at line 297 of file vpMe.h.

Referenced by vpMeSite::convolution(), vpMeSite::convolution(), from_json, and to_json.

◆ getThreshold()

double vpMe::getThreshold ( ) const

inline

Return the likelihood threshold used to determine if the moving edge is valid or not.

Returns: Value of the likelihood threshold.

See also: setThreshold(), getLikelihoodThresholdType(), setLikelihoodThresholdType()

Examples: testMbtXmlGenericParser.cpp, trackMeEllipse.cpp, and trackMeLine.cpp.

Definition at line 306 of file vpMe.h.

Referenced by from_json, vpMeSite::setContrastThreshold(), and to_json.

◆ getThresholdMarginRatio()

double vpMe::getThresholdMarginRatio ( ) const

inline

Return the ratio of the initial contrast to use to initialize the contrast threshold of the vpMeSite.

Returns: Value of the likelihood threshold ratio, between 0 and 1. A negative value means it is not activated.

See also: setThresholdMarginRatio(), setMinThreshold(), getMinThreshold(), getLikelihoodThresholdType(), setLikelihoodThresholdType()

Definition at line 315 of file vpMe.h.

Referenced by from_json, and to_json.

◆ getUseAutomaticThreshold()

bool vpMe::getUseAutomaticThreshold ( ) const

inline

Indicates if the contrast threshold of the vpMeSite is automatically computed.

Returns: true The contrast threshold of the vpMeSite is automatically computed.; false The vpMe::m_threshold is used as a global threshold.

Definition at line 333 of file vpMe.h.

Referenced by vpMeSite::setContrastThreshold().

◆ initMask()

BEGIN_VISP_NAMESPACE void vpMe::initMask ( )

Initialise the array of matrices with the defined size and the number of matrices to create.

Definition at line 383 of file vpMe.cpp.

Referenced by from_json, operator=(), operator=(), setMaskNumber(), setMaskSize(), and vpMe().

◆ operator=() [1/2]

vpMe & vpMe::operator= ( const vpMe && me )

Move operator.

Definition at line 517 of file vpMe.cpp.

References initMask(), and vpMe().

◆ operator=() [2/2]

vpMe & vpMe::operator= ( const vpMe & me )

Copy operator.

Definition at line 486 of file vpMe.cpp.

References initMask(), and vpMe().

◆ print()

void vpMe::print ( )

Print using std::cout moving edges settings.

Examples: tutorial-mb-generic-tracker.cpp, tutorial-me-ellipse-tracker.cpp, and tutorial-me-line-tracker.cpp.

Definition at line 404 of file vpMe.cpp.

References NORMALIZED_THRESHOLD.

◆ setAngleStep()

void vpMe::setAngleStep ( const unsigned int & anglestep )

inline

Set the angle step.

Parameters

anglestep : New angle step value.

Definition at line 360 of file vpMe.h.

Referenced by from_json.

◆ setInitRange()

void vpMe::setInitRange ( const int & initRange )

inline

Set the range used during the initialization step. A negative value means that the default value is used by the different ME primitives.

Parameters

initRange : New range, or a negative value to use the default ranges.

Examples: tutorial-mb-generic-tracker-full.cpp.

Definition at line 368 of file vpMe.h.

Referenced by from_json.

◆ setLikelihoodThresholdType()

void vpMe::setLikelihoodThresholdType ( const vpLikelihoodThresholdType likelihood_threshold_type )

inline

Set the likelihood threshold type used to determine if the moving edge is valid or not.

Parameters

likelihood_threshold_type : Likelihood threshold type. It is recommended to use NORMALIZED_THRESHOLD and set the threshold using setThreshold() with a value corresponding to the minimal luminance contrast to consider that can handle values in range [0 ; 255].

See also: setThreshold()

Examples: catchGenericTrackerDeterminist.cpp, mbtEdgeKltTracking.cpp, mbtEdgeTracking.cpp, mbtGenericTracking.cpp, mbtGenericTracking2.cpp, mbtGenericTrackingDepth.cpp, perfGenericTracker.cpp, servoAfma62DhalfCamVelocity.cpp, servoAfma6Cylinder2DCamVelocity.cpp, servoAfma6Cylinder2DCamVelocitySecondaryTask.cpp, servoAfma6Line2DCamVelocity.cpp, servoAfma6SquareLines2DCamVelocity.cpp, servoAfma6TwoLines2DCamVelocity.cpp, testGenericTracker.cpp, testKeyPoint-2.cpp, testKeyPoint-4.cpp, testMbtXmlGenericParser.cpp, trackMeCircle.cpp, trackMeEllipse.cpp, trackMeLine.cpp, trackMeNurbs.cpp, tutorial-detection-object-mbt-deprecated.cpp, tutorial-detection-object-mbt.cpp, tutorial-detection-object-mbt2-deprecated.cpp, tutorial-detection-object-mbt2.cpp, tutorial-mb-edge-tracker.cpp, tutorial-mb-generic-tracker-apriltag-rs2.cpp, tutorial-mb-generic-tracker-apriltag-webcam.cpp, tutorial-mb-generic-tracker-full.cpp, tutorial-mb-generic-tracker-live.cpp, tutorial-mb-generic-tracker-rgbd.cpp, tutorial-mb-generic-tracker-stereo-mono.cpp, tutorial-mb-generic-tracker.cpp, tutorial-mb-hybrid-tracker.cpp, tutorial-mb-tracker-full.cpp, tutorial-mb-tracker.cpp, tutorial-me-ellipse-tracker.cpp, and tutorial-me-line-tracker.cpp.

Definition at line 531 of file vpMe.h.

Referenced by from_json.

◆ setMaskNumber()

void vpMe::setMaskNumber ( const unsigned int & mask_number )

Set the number of mask applied to determine the object contour. The number of mask determines the precision of the normal of the edge for every sample. If precision is 2deg, then there are 360/2 = 180 masks.

Parameters

mask_number : The number of mask.

Examples: catchGenericTrackerDeterminist.cpp, mbtEdgeKltTracking.cpp, mbtEdgeTracking.cpp, mbtGenericTracking.cpp, mbtGenericTracking2.cpp, mbtGenericTrackingDepth.cpp, perfGenericTracker.cpp, testGenericTracker.cpp, testKeyPoint-2.cpp, testKeyPoint-4.cpp, testMbtXmlGenericParser.cpp, tutorial-detection-object-mbt-deprecated.cpp, tutorial-detection-object-mbt.cpp, tutorial-detection-object-mbt2-deprecated.cpp, tutorial-detection-object-mbt2.cpp, tutorial-mb-edge-tracker.cpp, tutorial-mb-generic-tracker-apriltag-rs2.cpp, tutorial-mb-generic-tracker-apriltag-webcam.cpp, tutorial-mb-generic-tracker-full.cpp, tutorial-mb-generic-tracker-live.cpp, tutorial-mb-generic-tracker-rgbd.cpp, tutorial-mb-generic-tracker-stereo-mono.cpp, tutorial-mb-generic-tracker.cpp, tutorial-mb-hybrid-tracker.cpp, tutorial-mb-tracker-full.cpp, and tutorial-mb-tracker.cpp.

Definition at line 555 of file vpMe.cpp.

References initMask().

Referenced by from_json.

◆ setMaskSign()

void vpMe::setMaskSign ( const int & mask_sign )

inline

Set the mask sign.

Parameters

mask_sign : New mask sign.

Definition at line 384 of file vpMe.h.

Referenced by from_json.

◆ setMaskSize()

void vpMe::setMaskSize ( const unsigned int & mask_size )

Set the mask size (in pixel) used to compute the image gradient and determine the object contour. The mask size defines the size of the convolution mask used to detect an edge.

Parameters

mask_size : New mask size.

Examples: catchGenericTrackerDeterminist.cpp, mbtEdgeKltTracking.cpp, mbtEdgeTracking.cpp, mbtGenericTracking.cpp, mbtGenericTracking2.cpp, mbtGenericTrackingDepth.cpp, perfGenericTracker.cpp, testGenericTracker.cpp, testKeyPoint-2.cpp, testKeyPoint-4.cpp, testMbtXmlGenericParser.cpp, tutorial-detection-object-mbt-deprecated.cpp, tutorial-detection-object-mbt.cpp, tutorial-detection-object-mbt2-deprecated.cpp, tutorial-detection-object-mbt2.cpp, tutorial-mb-edge-tracker.cpp, tutorial-mb-generic-tracker-apriltag-rs2.cpp, tutorial-mb-generic-tracker-apriltag-webcam.cpp, tutorial-mb-generic-tracker-full.cpp, tutorial-mb-generic-tracker-live.cpp, tutorial-mb-generic-tracker-rgbd.cpp, tutorial-mb-generic-tracker-stereo-mono.cpp, tutorial-mb-generic-tracker.cpp, tutorial-mb-hybrid-tracker.cpp, tutorial-mb-tracker-full.cpp, and tutorial-mb-tracker.cpp.

Definition at line 563 of file vpMe.cpp.

References initMask().

Referenced by from_json.

◆ setMinSampleStep()

void vpMe::setMinSampleStep ( const double & min_samplestep )

inline

Set the minimum allowed sample step. Useful to specify a lower bound when the sample step is changed.

Parameters

min_samplestep : New minimum sample step.

Definition at line 401 of file vpMe.h.

Referenced by from_json.

◆ setMinThreshold()

void vpMe::setMinThreshold ( const double & minThreshold )

inline

Set the minimum value of the contrast threshold of the vpMeSite.

Parameters

minThreshold Minimum value of the contrast threshold. A negative value means that automatic thresholding is not activated.

See also: getMinThreshold(), setThresholdMarginRatio(), getThresholdMarginRatio(), getLikelihoodThresholdType(), setLikelihoodThresholdType()

Examples: tutorial-mb-generic-tracker-full.cpp.

Definition at line 517 of file vpMe.h.

Referenced by from_json.

◆ setMu1()

void vpMe::setMu1 ( const double & mu_1 )

inline

Set the minimum image contrast allowed to detect a contour.

Parameters

mu_1	: new mu1.

Examples: catchGenericTrackerDeterminist.cpp, mbtEdgeKltTracking.cpp, mbtEdgeTracking.cpp, mbtGenericTracking.cpp, mbtGenericTracking2.cpp, mbtGenericTrackingDepth.cpp, perfGenericTracker.cpp, testGenericTracker.cpp, testKeyPoint-2.cpp, testKeyPoint-4.cpp, testMbtXmlGenericParser.cpp, tutorial-detection-object-mbt-deprecated.cpp, tutorial-detection-object-mbt.cpp, tutorial-detection-object-mbt2-deprecated.cpp, tutorial-detection-object-mbt2.cpp, tutorial-mb-edge-tracker.cpp, tutorial-mb-generic-tracker-apriltag-rs2.cpp, tutorial-mb-generic-tracker-apriltag-webcam.cpp, tutorial-mb-generic-tracker-full.cpp, tutorial-mb-generic-tracker-live.cpp, tutorial-mb-generic-tracker-rgbd.cpp, tutorial-mb-generic-tracker-stereo-mono.cpp, tutorial-mb-generic-tracker.cpp, tutorial-mb-hybrid-tracker.cpp, tutorial-mb-tracker-full.cpp, and tutorial-mb-tracker.cpp.

Definition at line 408 of file vpMe.h.

Referenced by from_json.

◆ setMu2()

void vpMe::setMu2 ( const double & mu_2 )

inline

Set the maximum image contrast allowed to detect a contour.

Parameters

mu_2	: New mu2.

Examples: catchGenericTrackerDeterminist.cpp, mbtEdgeKltTracking.cpp, mbtEdgeTracking.cpp, mbtGenericTracking.cpp, mbtGenericTracking2.cpp, mbtGenericTrackingDepth.cpp, perfGenericTracker.cpp, testGenericTracker.cpp, testKeyPoint-2.cpp, testKeyPoint-4.cpp, testMbtXmlGenericParser.cpp, tutorial-detection-object-mbt-deprecated.cpp, tutorial-detection-object-mbt.cpp, tutorial-detection-object-mbt2-deprecated.cpp, tutorial-detection-object-mbt2.cpp, tutorial-mb-edge-tracker.cpp, tutorial-mb-generic-tracker-apriltag-rs2.cpp, tutorial-mb-generic-tracker-apriltag-webcam.cpp, tutorial-mb-generic-tracker-full.cpp, tutorial-mb-generic-tracker-live.cpp, tutorial-mb-generic-tracker-rgbd.cpp, tutorial-mb-generic-tracker-stereo-mono.cpp, tutorial-mb-generic-tracker.cpp, tutorial-mb-hybrid-tracker.cpp, tutorial-mb-tracker-full.cpp, and tutorial-mb-tracker.cpp.

Definition at line 415 of file vpMe.h.

Referenced by from_json.

◆ setNbTotalSample()

void vpMe::setNbTotalSample ( const int & ntotal_sample )

inline

Set how many discretized points are used to track the feature.

Parameters

ntotal_sample : New total number of sample.

Examples: testKeyPoint-2.cpp, testKeyPoint-4.cpp, tutorial-detection-object-mbt-deprecated.cpp, tutorial-detection-object-mbt.cpp, tutorial-detection-object-mbt2-deprecated.cpp, and tutorial-detection-object-mbt2.cpp.

Definition at line 422 of file vpMe.h.

Referenced by from_json.

◆ setPointsToTrack()

void vpMe::setPointsToTrack ( const int & points_to_track )

inline

Set the number of points to track.

Parameters

points_to_track : New number of points to track.

Warning: This method is useful only for the vpMeNurbsTracker.

Examples: servoAfma62DhalfCamVelocity.cpp, servoAfma6Cylinder2DCamVelocity.cpp, servoAfma6Cylinder2DCamVelocitySecondaryTask.cpp, servoAfma6Line2DCamVelocity.cpp, servoAfma6SquareLines2DCamVelocity.cpp, servoAfma6TwoLines2DCamVelocity.cpp, and trackMeNurbs.cpp.

Definition at line 431 of file vpMe.h.

Referenced by from_json.

◆ setRange()

void vpMe::setRange ( const unsigned int & range )

inline

Set the seek range on both sides of the reference pixel.

Parameters

range : New range.

Examples: catchGenericTrackerDeterminist.cpp, mbtEdgeKltTracking.cpp, mbtEdgeTracking.cpp, mbtGenericTracking.cpp, mbtGenericTracking2.cpp, mbtGenericTrackingDepth.cpp, perfGenericTracker.cpp, servoAfma62DhalfCamVelocity.cpp, servoAfma6Cylinder2DCamVelocity.cpp, servoAfma6Cylinder2DCamVelocitySecondaryTask.cpp, servoAfma6Line2DCamVelocity.cpp, servoAfma6SquareLines2DCamVelocity.cpp, servoAfma6TwoLines2DCamVelocity.cpp, testGenericTracker.cpp, testKeyPoint-2.cpp, testKeyPoint-4.cpp, testMbtXmlGenericParser.cpp, trackMeCircle.cpp, trackMeEllipse.cpp, trackMeLine.cpp, trackMeNurbs.cpp, tutorial-detection-object-mbt-deprecated.cpp, tutorial-detection-object-mbt.cpp, tutorial-detection-object-mbt2-deprecated.cpp, tutorial-detection-object-mbt2.cpp, tutorial-mb-edge-tracker.cpp, tutorial-mb-generic-tracker-apriltag-rs2.cpp, tutorial-mb-generic-tracker-apriltag-webcam.cpp, tutorial-mb-generic-tracker-full.cpp, tutorial-mb-generic-tracker-live.cpp, tutorial-mb-generic-tracker-rgbd.cpp, tutorial-mb-generic-tracker-stereo-mono.cpp, tutorial-mb-generic-tracker.cpp, tutorial-mb-hybrid-tracker.cpp, tutorial-mb-tracker-full.cpp, tutorial-mb-tracker.cpp, tutorial-me-ellipse-tracker.cpp, and tutorial-me-line-tracker.cpp.

Definition at line 438 of file vpMe.h.

Referenced by from_json.

◆ setSampleStep()

void vpMe::setSampleStep ( const double & sample_step )

inline

Set the minimum distance in pixel between two discretized points.

Parameters

sample_step : New sample_step.

Examples: catchGenericTrackerDeterminist.cpp, mbtEdgeKltTracking.cpp, mbtEdgeTracking.cpp, mbtGenericTracking.cpp, mbtGenericTracking2.cpp, mbtGenericTrackingDepth.cpp, perfGenericTracker.cpp, servoAfma62DhalfCamVelocity.cpp, servoAfma6Cylinder2DCamVelocity.cpp, servoAfma6Cylinder2DCamVelocitySecondaryTask.cpp, servoAfma6Line2DCamVelocity.cpp, servoAfma6SquareLines2DCamVelocity.cpp, servoAfma6TwoLines2DCamVelocity.cpp, testGenericTracker.cpp, testKeyPoint-2.cpp, testKeyPoint-4.cpp, testMbtXmlGenericParser.cpp, trackMeCircle.cpp, trackMeEllipse.cpp, trackMeLine.cpp, trackMeNurbs.cpp, tutorial-detection-object-mbt-deprecated.cpp, tutorial-detection-object-mbt.cpp, tutorial-detection-object-mbt2-deprecated.cpp, tutorial-detection-object-mbt2.cpp, tutorial-mb-edge-tracker.cpp, tutorial-mb-generic-tracker-apriltag-rs2.cpp, tutorial-mb-generic-tracker-apriltag-webcam.cpp, tutorial-mb-generic-tracker-full.cpp, tutorial-mb-generic-tracker-live.cpp, tutorial-mb-generic-tracker-rgbd.cpp, tutorial-mb-generic-tracker-stereo-mono.cpp, tutorial-mb-generic-tracker.cpp, tutorial-mb-hybrid-tracker.cpp, tutorial-mb-tracker-full.cpp, tutorial-mb-tracker.cpp, tutorial-me-ellipse-tracker.cpp, and tutorial-me-line-tracker.cpp.

Definition at line 445 of file vpMe.h.

Referenced by from_json.

◆ setStrip()

void vpMe::setStrip ( const int & strip )

inline

Set the number of pixels that are ignored around the image borders.

Parameters

strip : New strip.

Definition at line 452 of file vpMe.h.

Referenced by from_json.

◆ setThreshold()

void vpMe::setThreshold ( const double & threshold )

inline

Set the likelihood threshold used to determined if the moving edge is valid or not.

Parameters

threshold : Threshold to consider. Two different cases need to be considered depending on the likelihood threshold type that can be set using setLikelihoodThresholdType() or get using getLikelihoodThresholdType(). The default likelihood threshold type is set to OLD_THRESHOLD to keep compatibility with ViSP previous releases, but it is recommended to use rather the NORMALIZED_THRESHOLD type like in the following sample code. When doing so, the threshold is more easy to set since it corresponds to the minimal luminance contrast to consider with values in range [0 ; 255].

vpMe me;
me.setLikelihoodThresholdType(NORMALIZED_THRESHOLD);
me.setThreshold(20); // Value in range [0 ; 255]
me.setThresholdMarginRatio(-1.); // Deactivate automatic thresholding
me.setMinThreshold(-1.); // Deactivate automatic thresholding

When the likelihood threshold type is set by default to OLD_THRESHOLD like in the next example, values of the likelihood threshold depends on the minimal luminance contrast to consider and the mask size that can be set using setMaskSize() and retrieved using getMaskSize().

vpMe me;                // By default the constructor set the threshold type to OLD_THRESHOLD
me.setThreshold(10000); // Value that depends on the minimal luminance contrast to consider and the mask size.
me.setThresholdMarginRatio(-1.); // Deactivate automatic thresholding
me.setMinThreshold(-1.); // Deactivate automatic thresholding

The previous sample code is similar to the next one:

vpMe me;
me.setLikelihoodThresholdType(OLD_THRESHOLD);
me.setThreshold(10000); // Value that depends on the minimal luminance contrast to consider and the mask size.
me.setThresholdMarginRatio(-1.); // Deactivate automatic thresholding
me.setMinThreshold(-1.); // Deactivate automatic thresholding

See also: getThreshold(), getLikelihoodThresholdType()

Examples: catchGenericTrackerDeterminist.cpp, mbtEdgeKltTracking.cpp, mbtEdgeTracking.cpp, mbtGenericTracking.cpp, mbtGenericTracking2.cpp, mbtGenericTrackingDepth.cpp, perfGenericTracker.cpp, servoAfma62DhalfCamVelocity.cpp, servoAfma6Cylinder2DCamVelocity.cpp, servoAfma6Cylinder2DCamVelocitySecondaryTask.cpp, servoAfma6Line2DCamVelocity.cpp, servoAfma6SquareLines2DCamVelocity.cpp, servoAfma6TwoLines2DCamVelocity.cpp, testGenericTracker.cpp, testKeyPoint-2.cpp, testKeyPoint-4.cpp, testMbtXmlGenericParser.cpp, trackMeCircle.cpp, trackMeEllipse.cpp, trackMeLine.cpp, trackMeNurbs.cpp, tutorial-detection-object-mbt-deprecated.cpp, tutorial-detection-object-mbt.cpp, tutorial-detection-object-mbt2-deprecated.cpp, tutorial-detection-object-mbt2.cpp, tutorial-mb-edge-tracker.cpp, tutorial-mb-generic-tracker-apriltag-rs2.cpp, tutorial-mb-generic-tracker-apriltag-webcam.cpp, tutorial-mb-generic-tracker-full.cpp, tutorial-mb-generic-tracker-live.cpp, tutorial-mb-generic-tracker-rgbd.cpp, tutorial-mb-generic-tracker-stereo-mono.cpp, tutorial-mb-generic-tracker.cpp, tutorial-mb-hybrid-tracker.cpp, tutorial-mb-tracker-full.cpp, tutorial-mb-tracker.cpp, tutorial-me-ellipse-tracker.cpp, and tutorial-me-line-tracker.cpp.

Definition at line 489 of file vpMe.h.

Referenced by from_json.

◆ setThresholdMarginRatio()

void vpMe::setThresholdMarginRatio ( const double & thresholdMarginRatio )

inline

Set the the ratio of the initial contrast to use to initialize the contrast threshold of the vpMeSite.

Parameters

thresholdMarginRatio Value of the likelihood threshold ratio, between 0 and 1. A negative value means that this the automatic thresholding is not activated. The threshold of a vpMeSite is computed from the convolution value computed when initializing the vpMeTracker multiplied by this ratio.

See also: getThresholdMarginRatio(), setMinThreshold(), getMinThreshold(), getLikelihoodThresholdType(), setLikelihoodThresholdType()

Examples: tutorial-mb-generic-tracker-full.cpp.

Definition at line 500 of file vpMe.h.

References vpException::badValue.

Referenced by from_json.

◆ from_json

void from_json	(	const nlohmann::json &	j,
		vpMe &	me )

friend

Retrieve a vpMe object from a JSON representation.

JSON content (key: type):

thresholdType: either "old" or "normalized", vpMe::getLikelihoodThresholdType()
threshold: double, vpMe::setThreshold()
thresholdMarginRatio: double, vpMe::setThresholdMarginRatio()
minThreshold: double, vpMe::setMinThreshold()
mu : [double, double], vpMe::setMu1, vpMe::setMu2()
minSampleStep: double, vpMe::setMinSampleStep()
angleStep: double, vpMe::setAngleStep()
sampleStep: double, vpMe::setSampleStep()
range: int, vpMe::setRange()
ntotal_sample: int, vpMe::setNbTotalSample()
pointsToTrack: int, vpMe::setPointsToTrack()
maskSize: int, vpMe::setMaskSize()
nMask: int, vpMe::setMaskNumber()
maskSign: int, vpMe::setMaskSign()
strip: int, vpMe::setStrip()

Example:

{
 "angleStep": 1,
  "maskSign": 0,
  "maskSize": 5,
  "minSampleStep": 4.0,
  "mu": [
      0.5,
      0.5
  ],
  "nMask": 180,
  "ntotal_sample": 0,
  "pointsToTrack": 500,
  "range": 7,
  "sampleStep": 4.0,
  "strip": 2,
  "thresholdType": "normalized",
  "threshold": 20.0,
  "thresholdMarginRatio": 0.75,
  "minThreshold": 20.0,
}

Parameters

j	JSON representation to convert
me	converted object

Definition at line 658 of file vpMe.h.

References from_json, getInitRange(), getLikelihoodThresholdType(), getMaskSign(), getMaskSize(), getMinSampleStep(), getMinThreshold(), getNbTotalSample(), getPointsToTrack(), getRange(), getSampleStep(), getStrip(), getThreshold(), getThresholdMarginRatio(), initMask(), setAngleStep(), setInitRange(), setLikelihoodThresholdType(), setMaskNumber(), setMaskSign(), setMaskSize(), setMinSampleStep(), setMinThreshold(), setMu1(), setMu2(), setNbTotalSample(), setPointsToTrack(), setRange(), setSampleStep(), setStrip(), setThreshold(), setThresholdMarginRatio(), and vpMe().

Referenced by from_json.

◆ to_json

void to_json	(	nlohmann::json &	j,
		const vpMe &	me )

friend

Convert a vpMe object to a JSON representation.

Parameters

j	: Resulting json object.
me	: The object to convert.

Definition at line 637 of file vpMe.h.

References getInitRange(), getLikelihoodThresholdType(), getMaskNumber(), getMaskSign(), getMaskSize(), getMinSampleStep(), getMinThreshold(), getMu1(), getMu2(), getNbTotalSample(), getPointsToTrack(), getRange(), getSampleStep(), getStrip(), getThreshold(), getThresholdMarginRatio(), to_json, and vpMe().

Referenced by to_json.

Public Types

Public Member Functions

Friends

Detailed Description

Tutorials & Examples

Member Enumeration Documentation

◆ vpLikelihoodThresholdType

Constructor & Destructor Documentation

◆ vpMe() [1/2]

◆ vpMe() [2/2]

◆ ~vpMe()

Member Function Documentation

◆ checkSamplestep()

◆ getAngleStep()

◆ getInitRange()

◆ getLikelihoodThresholdType()

◆ getMask()

◆ getMaskNumber()

◆ getMaskSign()

◆ getMaskSize()

◆ getMinSampleStep()

◆ getMinThreshold()

◆ getMu1()

◆ getMu2()

◆ getNbTotalSample()

◆ getPointsToTrack()

◆ getRange()

◆ getSampleStep()

◆ getStrip()

◆ getThreshold()

◆ getThresholdMarginRatio()

◆ getUseAutomaticThreshold()

◆ initMask()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ print()

◆ setAngleStep()

◆ setInitRange()

◆ setLikelihoodThresholdType()

◆ setMaskNumber()

◆ setMaskSign()

◆ setMaskSize()

◆ setMinSampleStep()

◆ setMinThreshold()

◆ setMu1()

◆ setMu2()

◆ setNbTotalSample()

◆ setPointsToTrack()

◆ setRange()

◆ setSampleStep()

◆ setStrip()

◆ setThreshold()

◆ setThresholdMarginRatio()

Friends And Related Symbol Documentation

◆ from_json

◆ to_json