OpenCV  4.1.0
Open Source Computer Vision
Public Member Functions | List of all members
cv::BackgroundSubtractorKNN Class Referenceabstract

K-nearest neighbours - based Background/Foreground Segmentation Algorithm. More...

#include <opencv2/video/background_segm.hpp>

Inheritance diagram for cv::BackgroundSubtractorKNN:
cv::BackgroundSubtractor cv::Algorithm

Public Member Functions

virtual bool getDetectShadows () const =0
 Returns the shadow detection flag.
 
virtual double getDist2Threshold () const =0
 Returns the threshold on the squared distance between the pixel and the sample.
 
virtual int getHistory () const =0
 Returns the number of last frames that affect the background model.
 
virtual int getkNNSamples () const =0
 Returns the number of neighbours, the k in the kNN.
 
virtual int getNSamples () const =0
 Returns the number of data samples in the background model.
 
virtual double getShadowThreshold () const =0
 Returns the shadow threshold.
 
virtual int getShadowValue () const =0
 Returns the shadow value.
 
virtual void setDetectShadows (bool detectShadows)=0
 Enables or disables shadow detection.
 
virtual void setDist2Threshold (double _dist2Threshold)=0
 Sets the threshold on the squared distance.
 
virtual void setHistory (int history)=0
 Sets the number of last frames that affect the background model.
 
virtual void setkNNSamples (int _nkNN)=0
 Sets the k in the kNN. How many nearest neighbours need to match.
 
virtual void setNSamples (int _nN)=0
 Sets the number of data samples in the background model.
 
virtual void setShadowThreshold (double threshold)=0
 Sets the shadow threshold.
 
virtual void setShadowValue (int value)=0
 Sets the shadow value.
 
- Public Member Functions inherited from cv::BackgroundSubtractor
virtual void apply (InputArray image, OutputArray fgmask, double learningRate=-1)=0
 Computes a foreground mask.
 
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
 
virtual void write (FileStorage &fs) const
 Stores algorithm parameters in a file storage.
 
void write (const Ptr< FileStorage > &fs, const String &name=String()) const
 simplified API for language bindingsThis is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.
 

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

K-nearest neighbours - based Background/Foreground Segmentation Algorithm.

The class implements the K-nearest neighbours background subtraction described inZivkovic2006 . Very efficient if number of foreground pixels is low.

Member Function Documentation

virtual bool cv::BackgroundSubtractorKNN::getDetectShadows ( ) const
pure virtual
Python:
retval=cv.BackgroundSubtractorKNN.getDetectShadows()

Returns the shadow detection flag.

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

virtual double cv::BackgroundSubtractorKNN::getDist2Threshold ( ) const
pure virtual
Python:
retval=cv.BackgroundSubtractorKNN.getDist2Threshold()

Returns the threshold on the squared distance between the pixel and the sample.

The threshold on the squared distance between the pixel and the sample to decide whether a pixel is close to a data sample.

virtual int cv::BackgroundSubtractorKNN::getHistory ( ) const
pure virtual
Python:
retval=cv.BackgroundSubtractorKNN.getHistory()

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

virtual int cv::BackgroundSubtractorKNN::getkNNSamples ( ) const
pure virtual
Python:
retval=cv.BackgroundSubtractorKNN.getkNNSamples()

Returns the number of neighbours, the k in the kNN.

K is the number of samples that need to be within dist2Threshold in order to decide that that pixel is matching the kNN background model.

virtual int cv::BackgroundSubtractorKNN::getNSamples ( ) const
pure virtual
Python:
retval=cv.BackgroundSubtractorKNN.getNSamples()

Returns the number of data samples in the background model.

virtual double cv::BackgroundSubtractorKNN::getShadowThreshold ( ) const
pure virtual
Python:
retval=cv.BackgroundSubtractorKNN.getShadowThreshold()

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.

virtual int cv::BackgroundSubtractorKNN::getShadowValue ( ) const
pure virtual
Python:
retval=cv.BackgroundSubtractorKNN.getShadowValue()

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.

virtual void cv::BackgroundSubtractorKNN::setDetectShadows ( bool  detectShadows)
pure virtual
Python:
None=cv.BackgroundSubtractorKNN.setDetectShadows(detectShadows)

Enables or disables shadow detection.

virtual void cv::BackgroundSubtractorKNN::setDist2Threshold ( double  _dist2Threshold)
pure virtual
Python:
None=cv.BackgroundSubtractorKNN.setDist2Threshold(_dist2Threshold)

Sets the threshold on the squared distance.

virtual void cv::BackgroundSubtractorKNN::setHistory ( int  history)
pure virtual
Python:
None=cv.BackgroundSubtractorKNN.setHistory(history)

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

virtual void cv::BackgroundSubtractorKNN::setkNNSamples ( int  _nkNN)
pure virtual
Python:
None=cv.BackgroundSubtractorKNN.setkNNSamples(_nkNN)

Sets the k in the kNN. How many nearest neighbours need to match.

virtual void cv::BackgroundSubtractorKNN::setNSamples ( int  _nN)
pure virtual
Python:
None=cv.BackgroundSubtractorKNN.setNSamples(_nN)

Sets the number of data samples in the background model.

The model needs to be reinitalized to reserve memory.

virtual void cv::BackgroundSubtractorKNN::setShadowThreshold ( double  threshold)
pure virtual
Python:
None=cv.BackgroundSubtractorKNN.setShadowThreshold(threshold)

Sets the shadow threshold.

virtual void cv::BackgroundSubtractorKNN::setShadowValue ( int  value)
pure virtual
Python:
None=cv.BackgroundSubtractorKNN.setShadowValue(value)

Sets the shadow value.


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