cv::TrackerStateEstimator Class Reference

Abstract base class for TrackerStateEstimator that estimates the most likely target state. More...

#include <opencv2/tracking/tracker.hpp>

Inheritance diagram for cv::TrackerStateEstimator:

Public Member Functions
virtual	~TrackerStateEstimator ()
Ptr< TrackerTargetState >	estimate (const std::vector< ConfidenceMap > &confidenceMaps)
	Estimate the most likely target state, return the estimated state. More...
String	getClassName () const
	Get the name of the specific TrackerStateEstimator. More...
void	update (std::vector< ConfidenceMap > &confidenceMaps)
	Update the ConfidenceMap with the scores. More...

Static Public Member Functions
static Ptr< TrackerStateEstimator >	create (const String &trackeStateEstimatorType)
	Create TrackerStateEstimator by tracker state estimator type. More...

Protected Member Functions
virtual Ptr< TrackerTargetState >	estimateImpl (const std::vector< ConfidenceMap > &confidenceMaps)=0
virtual void	updateImpl (std::vector< ConfidenceMap > &confidenceMaps)=0

Protected Attributes
String	className

Detailed Description

Abstract base class for TrackerStateEstimator that estimates the most likely target state.

See [187] State estimator

See [126] Statistical modeling (Fig. 3), Table III (generative) - IV (discriminative) - V (hybrid)

Constructor & Destructor Documentation

~TrackerStateEstimator()

virtual cv::TrackerStateEstimator::~TrackerStateEstimator ( )

virtual

Member Function Documentation

create()

static Ptr<TrackerStateEstimator> cv::TrackerStateEstimator::create ( const String &  trackeStateEstimatorType )

static

Create TrackerStateEstimator by tracker state estimator type.

Parameters

trackeStateEstimatorType

The TrackerStateEstimator name

The modes available now:

• "BOOSTING" – Boosting-based discriminative appearance models. See [126] section 4.4

The modes available soon:

• "SVM" – SVM-based discriminative appearance models. See [126] section 4.5

estimate()

Ptr<TrackerTargetState> cv::TrackerStateEstimator::estimate

(

const std::vector< ConfidenceMap > &

confidenceMaps

)

Estimate the most likely target state, return the estimated state.

Parameters

confidenceMaps

The overall appearance model as a list of :cConfidenceMap

estimateImpl()

virtual Ptr<TrackerTargetState> cv::TrackerStateEstimator::estimateImpl ( const std::vector< ConfidenceMap > &  confidenceMaps )

protectedpure virtual

Implemented in cv::TrackerStateEstimatorSVM, cv::TrackerStateEstimatorAdaBoosting, and cv::TrackerStateEstimatorMILBoosting.

getClassName()

String cv::TrackerStateEstimator::getClassName

(

)

const

Get the name of the specific TrackerStateEstimator.

update()

void cv::TrackerStateEstimator::update

(

std::vector< ConfidenceMap > &

confidenceMaps

)

Update the ConfidenceMap with the scores.

Parameters

confidenceMaps

The overall appearance model as a list of :cConfidenceMap

updateImpl()

virtual void cv::TrackerStateEstimator::updateImpl ( std::vector< ConfidenceMap > &  confidenceMaps )

protectedpure virtual

Implemented in cv::TrackerStateEstimatorSVM, cv::TrackerStateEstimatorAdaBoosting, and cv::TrackerStateEstimatorMILBoosting.

Member Data Documentation

className

String cv::TrackerStateEstimator::className

protected

---

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

• opencv2/tracking/tracker.hpp