Class cv::detail::tracking::TrackerContribFeatureSet#

Class that manages the extraction and selection of features. View details

#include <opencv2/tracking/tracking_internals.hpp>

Collaboration diagram for cv::detail::tracking::TrackerContribFeatureSet:

Detailed Description#

Class that manages the extraction and selection of features.

AAM Feature Extraction and Feature Set Refinement (Feature Processing and Feature Selection). See table I and section III C AMVOT Appearance modelling -> Visual representation (Table II, section 3.1 - 3.2)

TrackerContribFeatureSet is an aggregation of TrackerContribFeature

Constructor & Destructor Documentation#

TrackerContribFeatureSet()#

cv::detail::tracking::TrackerContribFeatureSet::TrackerContribFeatureSet()

~TrackerContribFeatureSet()#

cv::detail::tracking::TrackerContribFeatureSet::~TrackerContribFeatureSet()

Member Function Documentation#

addTrackerFeature()#

bool cv::detail::tracking::TrackerContribFeatureSet::addTrackerFeature(Ptr< TrackerContribFeature > & feature)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

feature — The TrackerContribFeature class

addTrackerFeature()#

bool cv::detail::tracking::TrackerContribFeatureSet::addTrackerFeature(String trackerFeatureType)

Add TrackerContribFeature in the collection. Return true if TrackerContribFeature is added, false otherwise.

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

Example TrackerContribFeatureSet::addTrackerFeature : :

//sample usage:

Ptr<TrackerContribFeature> trackerFeature = ...;
featureSet->addTrackerFeature( trackerFeature );

//or add CSC sampler with default parameters
//featureSet->addTrackerFeature( "HAAR" );

Note

If you use the second method, you must initialize the TrackerContribFeature

Parameters

trackerFeatureType — The TrackerContribFeature name

extraction()#

void cv::detail::tracking::TrackerContribFeatureSet::extraction(const std::vector< Mat > & images)

Extract features from the images collection.

Parameters

images — The input images

getResponses()#

const std::vector< Mat > & cv::detail::tracking::TrackerContribFeatureSet::getResponses()

Get the responses.

Note

Be sure to call extraction before getResponses Example TrackerContribFeatureSet::getResponses : :

getTrackerFeature()#

const std::vector< std::pair< String, Ptr< TrackerContribFeature > > > & cv::detail::tracking::TrackerContribFeatureSet::getTrackerFeature()

Get the TrackerContribFeature collection (TrackerContribFeature name, TrackerContribFeature pointer)

removeOutliers()#

void cv::detail::tracking::TrackerContribFeatureSet::removeOutliers()

Remove outliers for all feature types (optional)

selection()#

void cv::detail::tracking::TrackerContribFeatureSet::selection()

Identify most effective features for all feature types (optional)

clearResponses()#

void cv::detail::tracking::TrackerContribFeatureSet::clearResponses()

Member Data Documentation#

blockAddTrackerFeature#

bool cv::detail::tracking::TrackerContribFeatureSet::blockAddTrackerFeature

features#

std::vector< std::pair< String, Ptr< TrackerContribFeature > > > cv::detail::tracking::TrackerContribFeatureSet::features

responses#

std::vector< Mat > cv::detail::tracking::TrackerContribFeatureSet::responses

Source file#

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

opencv2/tracking/tracking_internals.hpp