Background Subtractor module based on the algorithm given in [106] . More...

#include <opencv2/bgsegm.hpp>

Collaboration diagram for cv::bgsegm::BackgroundSubtractorGMG:

Public Member Functions
virtual void	apply (InputArray image, OutputArray fgmask, double learningRate=-1) CV_OVERRIDE=0
	Computes a foreground mask.

virtual void	getBackgroundImage (OutputArray backgroundImage) const CV_OVERRIDE=0
	Computes a background image.

virtual double	getBackgroundPrior () const =0
	Returns the prior probability that each individual pixel is a background pixel.

virtual double	getDecisionThreshold () const =0
	Returns the value of decision threshold.

virtual double	getDefaultLearningRate () const =0
	Returns the learning rate of the algorithm.

virtual int	getMaxFeatures () const =0
	Returns total number of distinct colors to maintain in histogram.

virtual double	getMaxVal () const =0
	Returns the maximum value taken on by pixels in image sequence. e.g. 1.0 or 255.

virtual double	getMinVal () const =0
	Returns the minimum value taken on by pixels in image sequence. Usually 0.

virtual int	getNumFrames () const =0
	Returns the number of frames used to initialize background model.

virtual int	getQuantizationLevels () const =0
	Returns the parameter used for quantization of color-space.

virtual int	getSmoothingRadius () const =0
	Returns the kernel radius used for morphological operations.

virtual bool	getUpdateBackgroundModel () const =0
	Returns the status of background model update.

virtual void	setBackgroundPrior (double bgprior)=0
	Sets the prior probability that each individual pixel is a background pixel.

virtual void	setDecisionThreshold (double thresh)=0
	Sets the value of decision threshold.

virtual void	setDefaultLearningRate (double lr)=0
	Sets the learning rate of the algorithm.

virtual void	setMaxFeatures (int maxFeatures)=0
	Sets total number of distinct colors to maintain in histogram.

virtual void	setMaxVal (double val)=0
	Sets the maximum value taken on by pixels in image sequence.

virtual void	setMinVal (double val)=0
	Sets the minimum value taken on by pixels in image sequence.

virtual void	setNumFrames (int nframes)=0
	Sets the number of frames used to initialize background model.

virtual void	setQuantizationLevels (int nlevels)=0
	Sets the parameter used for quantization of color-space.

virtual void	setSmoothingRadius (int radius)=0
	Sets the kernel radius used for morphological operations.

virtual void	setUpdateBackgroundModel (bool update)=0
	Sets the status of background model update.

Public Member Functions inherited from cv::BackgroundSubtractor
Public Member Functions inherited from cv::Algorithm
	Algorithm ()

virtual	~Algorithm ()

virtual void	clear ()
	Clears the algorithm state.

virtual bool	empty () const
	Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read.

virtual String	getDefaultName () const

virtual void	read (const FileNode &fn)
	Reads algorithm parameters from a file storage.

virtual void	save (const String &filename) const

void	write (const Ptr< FileStorage > &fs, const String &name=String()) const

virtual void	write (FileStorage &fs) const
	Stores algorithm parameters in a file storage.

void	write (FileStorage &fs, const String &name) const

Additional Inherited Members
Static Public Member Functions inherited from cv::Algorithm
template<typename _Tp >
static Ptr< _Tp >	load (const String &filename, const String &objname=String())
	Loads algorithm from the file.

template<typename _Tp >
static Ptr< _Tp >	loadFromString (const String &strModel, const String &objname=String())
	Loads algorithm from a String.

template<typename _Tp >
static Ptr< _Tp >	read (const FileNode &fn)
	Reads algorithm from the file node.

Protected Member Functions inherited from cv::Algorithm
void	writeFormat (FileStorage &fs) const

Detailed Description

Background Subtractor module based on the algorithm given in [106] .

Takes a series of images and returns a sequence of mask (8UC1) images of the same size, where 255 indicates Foreground and 0 represents Background. This class implements an algorithm described in "Visual Tracking of Human Visitors under Variable-Lighting Conditions for a Responsive Audio Art Installation," A. Godbehere, A. Matsukawa, K. Goldberg, American Control Conference, Montreal, June 2012.

Member Function Documentation

◆ apply()

virtual void cv::bgsegm::BackgroundSubtractorGMG::apply	(	InputArray	image,
		OutputArray	fgmask,
		double	learningRate = -1 )

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.apply(	image[, fgmask[, learningRate]]	) ->	fgmask

Computes a foreground mask.

Parameters

image	Next video frame of type CV_8UC(n),CV_8SC(n),CV_16UC(n),CV_16SC(n),CV_32SC(n),CV_32FC(n),CV_64FC(n), where n is 1,2,3,4.
fgmask	The output foreground mask as an 8-bit binary image.
learningRate	The value between 0 and 1 that indicates how fast the background model is learnt. Negative parameter value makes the algorithm to use some automatically chosen learning rate. 0 means that the background model is not updated at all, 1 means that the background model is completely reinitialized from the last frame.

Implements cv::BackgroundSubtractor.

◆ getBackgroundImage()

virtual void cv::bgsegm::BackgroundSubtractorGMG::getBackgroundImage ( OutputArray backgroundImage ) const

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.getBackgroundImage(	[, backgroundImage]	) ->	backgroundImage

Computes a background image.

Parameters

backgroundImage The output background image.

Note: Sometimes the background image can be very blurry, as it contain the average background statistics.

Implements cv::BackgroundSubtractor.

◆ getBackgroundPrior()

virtual double cv::bgsegm::BackgroundSubtractorGMG::getBackgroundPrior ( ) const

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.getBackgroundPrior(		) ->	retval

Returns the prior probability that each individual pixel is a background pixel.

◆ getDecisionThreshold()

virtual double cv::bgsegm::BackgroundSubtractorGMG::getDecisionThreshold ( ) const

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.getDecisionThreshold(		) ->	retval

Returns the value of decision threshold.

Decision value is the value above which pixel is determined to be FG.

◆ getDefaultLearningRate()

virtual double cv::bgsegm::BackgroundSubtractorGMG::getDefaultLearningRate ( ) const

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.getDefaultLearningRate(		) ->	retval

Returns the learning rate of the algorithm.

It lies between 0.0 and 1.0. It determines how quickly features are "forgotten" from histograms.

◆ getMaxFeatures()

virtual int cv::bgsegm::BackgroundSubtractorGMG::getMaxFeatures ( ) const

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.getMaxFeatures(		) ->	retval

Returns total number of distinct colors to maintain in histogram.

◆ getMaxVal()

virtual double cv::bgsegm::BackgroundSubtractorGMG::getMaxVal ( ) const

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.getMaxVal(		) ->	retval

Returns the maximum value taken on by pixels in image sequence. e.g. 1.0 or 255.

◆ getMinVal()

virtual double cv::bgsegm::BackgroundSubtractorGMG::getMinVal ( ) const

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.getMinVal(		) ->	retval

Returns the minimum value taken on by pixels in image sequence. Usually 0.

◆ getNumFrames()

virtual int cv::bgsegm::BackgroundSubtractorGMG::getNumFrames ( ) const

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.getNumFrames(		) ->	retval

Returns the number of frames used to initialize background model.

◆ getQuantizationLevels()

virtual int cv::bgsegm::BackgroundSubtractorGMG::getQuantizationLevels ( ) const

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.getQuantizationLevels(		) ->	retval

Returns the parameter used for quantization of color-space.

It is the number of discrete levels in each channel to be used in histograms.

◆ getSmoothingRadius()

virtual int cv::bgsegm::BackgroundSubtractorGMG::getSmoothingRadius ( ) const

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.getSmoothingRadius(		) ->	retval

Returns the kernel radius used for morphological operations.

◆ getUpdateBackgroundModel()

virtual bool cv::bgsegm::BackgroundSubtractorGMG::getUpdateBackgroundModel ( ) const

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.getUpdateBackgroundModel(		) ->	retval

Returns the status of background model update.

◆ setBackgroundPrior()

virtual void cv::bgsegm::BackgroundSubtractorGMG::setBackgroundPrior ( double bgprior )

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.setBackgroundPrior(	bgprior	) ->	None

Sets the prior probability that each individual pixel is a background pixel.

◆ setDecisionThreshold()

virtual void cv::bgsegm::BackgroundSubtractorGMG::setDecisionThreshold ( double thresh )

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.setDecisionThreshold(	thresh	) ->	None

Sets the value of decision threshold.

◆ setDefaultLearningRate()

virtual void cv::bgsegm::BackgroundSubtractorGMG::setDefaultLearningRate ( double lr )

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.setDefaultLearningRate(	lr	) ->	None

Sets the learning rate of the algorithm.

◆ setMaxFeatures()

virtual void cv::bgsegm::BackgroundSubtractorGMG::setMaxFeatures ( int maxFeatures )

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.setMaxFeatures(	maxFeatures	) ->	None

Sets total number of distinct colors to maintain in histogram.

◆ setMaxVal()

virtual void cv::bgsegm::BackgroundSubtractorGMG::setMaxVal ( double val )

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.setMaxVal(	val	) ->	None

Sets the maximum value taken on by pixels in image sequence.

◆ setMinVal()

virtual void cv::bgsegm::BackgroundSubtractorGMG::setMinVal ( double val )

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.setMinVal(	val	) ->	None

Sets the minimum value taken on by pixels in image sequence.

◆ setNumFrames()

virtual void cv::bgsegm::BackgroundSubtractorGMG::setNumFrames ( int nframes )

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.setNumFrames(	nframes	) ->	None

Sets the number of frames used to initialize background model.

◆ setQuantizationLevels()

virtual void cv::bgsegm::BackgroundSubtractorGMG::setQuantizationLevels ( int nlevels )

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.setQuantizationLevels(	nlevels	) ->	None

Sets the parameter used for quantization of color-space.

◆ setSmoothingRadius()

virtual void cv::bgsegm::BackgroundSubtractorGMG::setSmoothingRadius ( int radius )

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.setSmoothingRadius(	radius	) ->	None

Sets the kernel radius used for morphological operations.

◆ setUpdateBackgroundModel()

virtual void cv::bgsegm::BackgroundSubtractorGMG::setUpdateBackgroundModel ( bool update )

pure virtual

Python:
	cv.bgsegm.BackgroundSubtractorGMG.setUpdateBackgroundModel(	update	) ->	None

Sets the status of background model update.

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

opencv2/bgsegm.hpp

Public Member Functions

Additional Inherited Members

Detailed Description

Member Function Documentation

◆ apply()

◆ getBackgroundImage()

◆ getBackgroundPrior()

◆ getDecisionThreshold()

◆ getDefaultLearningRate()

◆ getMaxFeatures()

◆ getMaxVal()

◆ getMinVal()

◆ getNumFrames()

◆ getQuantizationLevels()

◆ getSmoothingRadius()

◆ getUpdateBackgroundModel()

◆ setBackgroundPrior()

◆ setDecisionThreshold()

◆ setDefaultLearningRate()

◆ setMaxFeatures()

◆ setMaxVal()

◆ setMinVal()

◆ setNumFrames()

◆ setQuantizationLevels()

◆ setSmoothingRadius()

◆ setUpdateBackgroundModel()