OpenCV  3.4.20-dev
Open Source Computer Vision
Public Member Functions | Static Public Member Functions | Protected Member Functions | Protected Attributes | List of all members
cv::TrackerFeature Class Referenceabstract

Abstract base class for TrackerFeature that represents the feature. More...

#include <opencv2/tracking/tracker.hpp>

Inheritance diagram for cv::TrackerFeature:
cv::TrackerFeatureFeature2d cv::TrackerFeatureHAAR cv::TrackerFeatureHOG cv::TrackerFeatureLBP

Public Member Functions

virtual ~TrackerFeature ()
 
void compute (const std::vector< Mat > &images, Mat &response)
 Compute the features in the images collection. More...
 
String getClassName () const
 Get the name of the specific TrackerFeature. More...
 
virtual void selection (Mat &response, int npoints)=0
 Identify most effective features. More...
 

Static Public Member Functions

static Ptr< TrackerFeaturecreate (const String &trackerFeatureType)
 Create TrackerFeature by tracker feature type. More...
 

Protected Member Functions

virtual bool computeImpl (const std::vector< Mat > &images, Mat &response)=0
 

Protected Attributes

String className
 

Detailed Description

Abstract base class for TrackerFeature that represents the feature.

Constructor & Destructor Documentation

◆ ~TrackerFeature()

virtual cv::TrackerFeature::~TrackerFeature ( )
virtual

Member Function Documentation

◆ compute()

void cv::TrackerFeature::compute ( const std::vector< Mat > &  images,
Mat response 
)

Compute the features in the images collection.

Parameters
imagesThe images
responseThe output response

◆ computeImpl()

virtual bool cv::TrackerFeature::computeImpl ( const std::vector< Mat > &  images,
Mat response 
)
protectedpure virtual

◆ create()

static Ptr<TrackerFeature> cv::TrackerFeature::create ( const String trackerFeatureType)
static

Create TrackerFeature by tracker feature type.

Parameters
trackerFeatureTypeThe TrackerFeature name

The modes available now:

  • "HAAR" – Haar Feature-based

The modes that will be available soon:

  • "HOG" – Histogram of Oriented Gradients features
  • "LBP" – Local Binary Pattern features
  • "FEATURE2D" – All types of Feature2D

◆ getClassName()

String cv::TrackerFeature::getClassName ( ) const

Get the name of the specific TrackerFeature.

◆ selection()

virtual void cv::TrackerFeature::selection ( Mat response,
int  npoints 
)
pure virtual

Identify most effective features.

Parameters
responseCollection of response for the specific TrackerFeature
npointsMax number of features
Note
This method modifies the response parameter

Implemented in cv::TrackerFeatureLBP, cv::TrackerFeatureHAAR, cv::TrackerFeatureHOG, and cv::TrackerFeatureFeature2d.

Member Data Documentation

◆ className

String cv::TrackerFeature::className
protected

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