OpenCV  4.10.0-dev
Open Source Computer Vision
Loading...
Searching...
No Matches
Public Member Functions | List of all members
cv::BackgroundSubtractorMOG2 Class Referenceabstract

Gaussian Mixture-based Background/Foreground Segmentation Algorithm. More...

#include <opencv2/video/background_segm.hpp>

Collaboration diagram for cv::BackgroundSubtractorMOG2:

Public Member Functions

virtual void apply (InputArray image, OutputArray fgmask, double learningRate=-1) CV_OVERRIDE=0
 Computes a foreground mask.
 
virtual double getBackgroundRatio () const =0
 Returns the "background ratio" parameter of the algorithm.
 
virtual double getComplexityReductionThreshold () const =0
 Returns the complexity reduction threshold.
 
virtual bool getDetectShadows () const =0
 Returns the shadow detection flag.
 
virtual int getHistory () const =0
 Returns the number of last frames that affect the background model.
 
virtual int getNMixtures () const =0
 Returns the number of gaussian components in the background model.
 
virtual double getShadowThreshold () const =0
 Returns the shadow threshold.
 
virtual int getShadowValue () const =0
 Returns the shadow value.
 
virtual double getVarInit () const =0
 Returns the initial variance of each gaussian component.
 
virtual double getVarMax () const =0
 
virtual double getVarMin () const =0
 
virtual double getVarThreshold () const =0
 Returns the variance threshold for the pixel-model match.
 
virtual double getVarThresholdGen () const =0
 Returns the variance threshold for the pixel-model match used for new mixture component generation.
 
virtual void setBackgroundRatio (double ratio)=0
 Sets the "background ratio" parameter of the algorithm.
 
virtual void setComplexityReductionThreshold (double ct)=0
 Sets the complexity reduction threshold.
 
virtual void setDetectShadows (bool detectShadows)=0
 Enables or disables shadow detection.
 
virtual void setHistory (int history)=0
 Sets the number of last frames that affect the background model.
 
virtual void setNMixtures (int nmixtures)=0
 Sets the number of gaussian components in the background model.
 
virtual void setShadowThreshold (double threshold)=0
 Sets the shadow threshold.
 
virtual void setShadowValue (int value)=0
 Sets the shadow value.
 
virtual void setVarInit (double varInit)=0
 Sets the initial variance of each gaussian component.
 
virtual void setVarMax (double varMax)=0
 
virtual void setVarMin (double varMin)=0
 
virtual void setVarThreshold (double varThreshold)=0
 Sets the variance threshold for the pixel-model match.
 
virtual void setVarThresholdGen (double varThresholdGen)=0
 Sets the variance threshold for the pixel-model match used for new mixture component generation.
 
- Public Member Functions inherited from cv::BackgroundSubtractor
virtual void getBackgroundImage (OutputArray backgroundImage) const =0
 Computes a background image.
 
- 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< _Tpload (const String &filename, const String &objname=String())
 Loads algorithm from the file.
 
template<typename _Tp >
static Ptr< _TploadFromString (const String &strModel, const String &objname=String())
 Loads algorithm from a String.
 
template<typename _Tp >
static Ptr< _Tpread (const FileNode &fn)
 Reads algorithm from the file node.
 
- Protected Member Functions inherited from cv::Algorithm
void writeFormat (FileStorage &fs) const
 

Detailed Description

Gaussian Mixture-based Background/Foreground Segmentation Algorithm.

The class implements the Gaussian mixture model background subtraction described in [325] and [324] .

Member Function Documentation

◆ apply()

virtual void cv::BackgroundSubtractorMOG2::apply ( InputArray  image,
OutputArray  fgmask,
double  learningRate = -1 
)
pure virtual
Python:
cv.BackgroundSubtractorMOG2.apply(image[, fgmask[, learningRate]]) -> fgmask

Computes a foreground mask.

Parameters
imageNext video frame. Floating point frame will be used without scaling and should be in range \([0,255]\).
fgmaskThe output foreground mask as an 8-bit binary image.
learningRateThe 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.

◆ getBackgroundRatio()

virtual double cv::BackgroundSubtractorMOG2::getBackgroundRatio ( ) const
pure virtual
Python:
cv.BackgroundSubtractorMOG2.getBackgroundRatio() -> retval

Returns the "background ratio" parameter of the algorithm.

If a foreground pixel keeps semi-constant value for about backgroundRatio*history frames, it's considered background and added to the model as a center of a new component. It corresponds to TB parameter in the paper.

◆ getComplexityReductionThreshold()

virtual double cv::BackgroundSubtractorMOG2::getComplexityReductionThreshold ( ) const
pure virtual
Python:
cv.BackgroundSubtractorMOG2.getComplexityReductionThreshold() -> retval

Returns the complexity reduction threshold.

This parameter defines the number of samples needed to accept to prove the component exists. CT=0.05 is a default value for all the samples. By setting CT=0 you get an algorithm very similar to the standard Stauffer&Grimson algorithm.

◆ getDetectShadows()

virtual bool cv::BackgroundSubtractorMOG2::getDetectShadows ( ) const
pure virtual
Python:
cv.BackgroundSubtractorMOG2.getDetectShadows() -> retval

Returns the shadow detection flag.

If true, the algorithm detects shadows and marks them. See createBackgroundSubtractorMOG2 for details.

◆ getHistory()

virtual int cv::BackgroundSubtractorMOG2::getHistory ( ) const
pure virtual
Python:
cv.BackgroundSubtractorMOG2.getHistory() -> retval

Returns the number of last frames that affect the background model.

◆ getNMixtures()

virtual int cv::BackgroundSubtractorMOG2::getNMixtures ( ) const
pure virtual
Python:
cv.BackgroundSubtractorMOG2.getNMixtures() -> retval

Returns the number of gaussian components in the background model.

◆ getShadowThreshold()

virtual double cv::BackgroundSubtractorMOG2::getShadowThreshold ( ) const
pure virtual
Python:
cv.BackgroundSubtractorMOG2.getShadowThreshold() -> retval

Returns the shadow threshold.

A shadow is detected if pixel is a darker version of the background. The shadow threshold (Tau in the paper) is a threshold defining how much darker the shadow can be. Tau= 0.5 means that if a pixel is more than twice darker then it is not shadow. See Prati, Mikic, Trivedi and Cucchiara, Detecting Moving Shadows...*, IEEE PAMI,2003.

◆ getShadowValue()

virtual int cv::BackgroundSubtractorMOG2::getShadowValue ( ) const
pure virtual
Python:
cv.BackgroundSubtractorMOG2.getShadowValue() -> retval

Returns the shadow value.

Shadow value is the value used to mark shadows in the foreground mask. Default value is 127. Value 0 in the mask always means background, 255 means foreground.

◆ getVarInit()

virtual double cv::BackgroundSubtractorMOG2::getVarInit ( ) const
pure virtual
Python:
cv.BackgroundSubtractorMOG2.getVarInit() -> retval

Returns the initial variance of each gaussian component.

◆ getVarMax()

virtual double cv::BackgroundSubtractorMOG2::getVarMax ( ) const
pure virtual
Python:
cv.BackgroundSubtractorMOG2.getVarMax() -> retval

◆ getVarMin()

virtual double cv::BackgroundSubtractorMOG2::getVarMin ( ) const
pure virtual
Python:
cv.BackgroundSubtractorMOG2.getVarMin() -> retval

◆ getVarThreshold()

virtual double cv::BackgroundSubtractorMOG2::getVarThreshold ( ) const
pure virtual
Python:
cv.BackgroundSubtractorMOG2.getVarThreshold() -> retval

Returns the variance threshold for the pixel-model match.

The main threshold on the squared Mahalanobis distance to decide if the sample is well described by the background model or not. Related to Cthr from the paper.

◆ getVarThresholdGen()

virtual double cv::BackgroundSubtractorMOG2::getVarThresholdGen ( ) const
pure virtual
Python:
cv.BackgroundSubtractorMOG2.getVarThresholdGen() -> retval

Returns the variance threshold for the pixel-model match used for new mixture component generation.

Threshold for the squared Mahalanobis distance that helps decide when a sample is close to the existing components (corresponds to Tg in the paper). If a pixel is not close to any component, it is considered foreground or added as a new component. 3 sigma => Tg=3*3=9 is default. A smaller Tg value generates more components. A higher Tg value may result in a small number of components but they can grow too large.

◆ setBackgroundRatio()

virtual void cv::BackgroundSubtractorMOG2::setBackgroundRatio ( double  ratio)
pure virtual
Python:
cv.BackgroundSubtractorMOG2.setBackgroundRatio(ratio) -> None

Sets the "background ratio" parameter of the algorithm.

◆ setComplexityReductionThreshold()

virtual void cv::BackgroundSubtractorMOG2::setComplexityReductionThreshold ( double  ct)
pure virtual
Python:
cv.BackgroundSubtractorMOG2.setComplexityReductionThreshold(ct) -> None

Sets the complexity reduction threshold.

◆ setDetectShadows()

virtual void cv::BackgroundSubtractorMOG2::setDetectShadows ( bool  detectShadows)
pure virtual
Python:
cv.BackgroundSubtractorMOG2.setDetectShadows(detectShadows) -> None

Enables or disables shadow detection.

◆ setHistory()

virtual void cv::BackgroundSubtractorMOG2::setHistory ( int  history)
pure virtual
Python:
cv.BackgroundSubtractorMOG2.setHistory(history) -> None

Sets the number of last frames that affect the background model.

◆ setNMixtures()

virtual void cv::BackgroundSubtractorMOG2::setNMixtures ( int  nmixtures)
pure virtual
Python:
cv.BackgroundSubtractorMOG2.setNMixtures(nmixtures) -> None

Sets the number of gaussian components in the background model.

The model needs to be reinitalized to reserve memory.

◆ setShadowThreshold()

virtual void cv::BackgroundSubtractorMOG2::setShadowThreshold ( double  threshold)
pure virtual
Python:
cv.BackgroundSubtractorMOG2.setShadowThreshold(threshold) -> None

Sets the shadow threshold.

◆ setShadowValue()

virtual void cv::BackgroundSubtractorMOG2::setShadowValue ( int  value)
pure virtual
Python:
cv.BackgroundSubtractorMOG2.setShadowValue(value) -> None

Sets the shadow value.

◆ setVarInit()

virtual void cv::BackgroundSubtractorMOG2::setVarInit ( double  varInit)
pure virtual
Python:
cv.BackgroundSubtractorMOG2.setVarInit(varInit) -> None

Sets the initial variance of each gaussian component.

◆ setVarMax()

virtual void cv::BackgroundSubtractorMOG2::setVarMax ( double  varMax)
pure virtual
Python:
cv.BackgroundSubtractorMOG2.setVarMax(varMax) -> None

◆ setVarMin()

virtual void cv::BackgroundSubtractorMOG2::setVarMin ( double  varMin)
pure virtual
Python:
cv.BackgroundSubtractorMOG2.setVarMin(varMin) -> None

◆ setVarThreshold()

virtual void cv::BackgroundSubtractorMOG2::setVarThreshold ( double  varThreshold)
pure virtual
Python:
cv.BackgroundSubtractorMOG2.setVarThreshold(varThreshold) -> None

Sets the variance threshold for the pixel-model match.

◆ setVarThresholdGen()

virtual void cv::BackgroundSubtractorMOG2::setVarThresholdGen ( double  varThresholdGen)
pure virtual
Python:
cv.BackgroundSubtractorMOG2.setVarThresholdGen(varThresholdGen) -> None

Sets the variance threshold for the pixel-model match used for new mixture component generation.


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