Package org.opencv.bgsegm

Class BackgroundSubtractorGMG

  • public class BackgroundSubtractorGMG
extends BackgroundSubtractor
    Background Subtractor module based on the algorithm given in CITE: Gold2012 . 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.

    • Constructor Summary

      Constructors 
      Modifier Constructor Description
      protected BackgroundSubtractorGMG​(long addr)  

    • Method Summary

      All Methods Static Methods Instance Methods Concrete Methods 
      Modifier and Type Method Description
      static BackgroundSubtractorGMG __fromPtr__​(long addr)  
      void apply​(Mat image, Mat fgmask)
      Computes a foreground mask.
      void apply​(Mat image, Mat fgmask, double learningRate)
      Computes a foreground mask.
      void apply​(Mat image, Mat knownForegroundMask, Mat fgmask)
      Computes a foreground mask with known foreground mask input.
      void apply​(Mat image, Mat knownForegroundMask, Mat fgmask, double learningRate)
      Computes a foreground mask with known foreground mask input.
      void getBackgroundImage​(Mat backgroundImage)
      Computes a background image.
      double getBackgroundPrior()
      Returns the prior probability that each individual pixel is a background pixel.
      double getDecisionThreshold()
      Returns the value of decision threshold.
      double getDefaultLearningRate()
      Returns the learning rate of the algorithm.
      int getMaxFeatures()
      Returns total number of distinct colors to maintain in histogram.
      double getMaxVal()
      Returns the maximum value taken on by pixels in image sequence.
      double getMinVal()
      Returns the minimum value taken on by pixels in image sequence.
      int getNumFrames()
      Returns the number of frames used to initialize background model.
      int getQuantizationLevels()
      Returns the parameter used for quantization of color-space.
      int getSmoothingRadius()
      Returns the kernel radius used for morphological operations
      boolean getUpdateBackgroundModel()
      Returns the status of background model update
      void setBackgroundPrior​(double bgprior)
      Sets the prior probability that each individual pixel is a background pixel.
      void setDecisionThreshold​(double thresh)
      Sets the value of decision threshold.
      void setDefaultLearningRate​(double lr)
      Sets the learning rate of the algorithm.
      void setMaxFeatures​(int maxFeatures)
      Sets total number of distinct colors to maintain in histogram.
      void setMaxVal​(double val)
      Sets the maximum value taken on by pixels in image sequence.
      void setMinVal​(double val)
      Sets the minimum value taken on by pixels in image sequence.
      void setNumFrames​(int nframes)
      Sets the number of frames used to initialize background model.
      void setQuantizationLevels​(int nlevels)
      Sets the parameter used for quantization of color-space
      void setSmoothingRadius​(int radius)
      Sets the kernel radius used for morphological operations
      void setUpdateBackgroundModel​(boolean update)
      Sets the status of background model update

      • Methods inherited from class java.lang.Object

        clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

    • Constructor Detail

      • BackgroundSubtractorGMG

        protected BackgroundSubtractorGMG​(long addr)

    • Method Detail

      • apply

        public void apply​(Mat image,
                  Mat fgmask,
                  double learningRate)
        Computes a foreground mask.
        Overrides:
        apply in class BackgroundSubtractor
        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.

      • apply

        public void apply​(Mat image,
                  Mat fgmask)
        Computes a foreground mask.
        Overrides:
        apply in class BackgroundSubtractor
        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. 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.

      • apply

        public void apply​(Mat image,
                  Mat knownForegroundMask,
                  Mat fgmask,
                  double learningRate)
        Computes a foreground mask with known foreground mask input.
        Overrides:
        apply in class BackgroundSubtractor
        Parameters:
        image - Next video frame.
        fgmask - The output foreground mask as an 8-bit binary image.
        knownForegroundMask - The mask for inputting already known foreground.
        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. Note: This method has a default virtual implementation that throws a "not implemented" error. Foreground masking may not be supported by all background subtractors.

      • apply

        public void apply​(Mat image,
                  Mat knownForegroundMask,
                  Mat fgmask)
        Computes a foreground mask with known foreground mask input.
        Overrides:
        apply in class BackgroundSubtractor
        Parameters:
        image - Next video frame.
        fgmask - The output foreground mask as an 8-bit binary image.
        knownForegroundMask - The mask for inputting already known foreground. 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. Note: This method has a default virtual implementation that throws a "not implemented" error. Foreground masking may not be supported by all background subtractors.

      • getBackgroundImage

        public void getBackgroundImage​(Mat backgroundImage)
        Description copied from class: BackgroundSubtractor
        Computes a background image.
        Overrides:
        getBackgroundImage in class BackgroundSubtractor
        Parameters:
        backgroundImage - The output background image. Note: Sometimes the background image can be very blurry, as it contain the average background statistics.

      • getMaxFeatures

        public int getMaxFeatures()
        Returns total number of distinct colors to maintain in histogram.
        Returns:
        automatically generated

      • setMaxFeatures

        public void setMaxFeatures​(int maxFeatures)
        Sets total number of distinct colors to maintain in histogram.
        Parameters:
        maxFeatures - automatically generated

      • getDefaultLearningRate

        public double getDefaultLearningRate()
        Returns the learning rate of the algorithm. It lies between 0.0 and 1.0. It determines how quickly features are "forgotten" from histograms.
        Returns:
        automatically generated

      • setDefaultLearningRate

        public void setDefaultLearningRate​(double lr)
        Sets the learning rate of the algorithm.
        Parameters:
        lr - automatically generated

      • getNumFrames

        public int getNumFrames()
        Returns the number of frames used to initialize background model.
        Returns:
        automatically generated

      • setNumFrames

        public void setNumFrames​(int nframes)
        Sets the number of frames used to initialize background model.
        Parameters:
        nframes - automatically generated

      • getQuantizationLevels

        public int getQuantizationLevels()
        Returns the parameter used for quantization of color-space. It is the number of discrete levels in each channel to be used in histograms.
        Returns:
        automatically generated

      • setQuantizationLevels

        public void setQuantizationLevels​(int nlevels)
        Sets the parameter used for quantization of color-space
        Parameters:
        nlevels - automatically generated

      • getBackgroundPrior

        public double getBackgroundPrior()
        Returns the prior probability that each individual pixel is a background pixel.
        Returns:
        automatically generated

      • setBackgroundPrior

        public void setBackgroundPrior​(double bgprior)
        Sets the prior probability that each individual pixel is a background pixel.
        Parameters:
        bgprior - automatically generated

      • getSmoothingRadius

        public int getSmoothingRadius()
        Returns the kernel radius used for morphological operations
        Returns:
        automatically generated

      • setSmoothingRadius

        public void setSmoothingRadius​(int radius)
        Sets the kernel radius used for morphological operations
        Parameters:
        radius - automatically generated

      • getDecisionThreshold

        public double getDecisionThreshold()
        Returns the value of decision threshold. Decision value is the value above which pixel is determined to be FG.
        Returns:
        automatically generated

      • setDecisionThreshold

        public void setDecisionThreshold​(double thresh)
        Sets the value of decision threshold.
        Parameters:
        thresh - automatically generated

      • getUpdateBackgroundModel

        public boolean getUpdateBackgroundModel()
        Returns the status of background model update
        Returns:
        automatically generated

      • setUpdateBackgroundModel

        public void setUpdateBackgroundModel​(boolean update)
        Sets the status of background model update
        Parameters:
        update - automatically generated

      • getMinVal

        public double getMinVal()
        Returns the minimum value taken on by pixels in image sequence. Usually 0.
        Returns:
        automatically generated

      • setMinVal

        public void setMinVal​(double val)
        Sets the minimum value taken on by pixels in image sequence.
        Parameters:
        val - automatically generated

      • getMaxVal

        public double getMaxVal()
        Returns the maximum value taken on by pixels in image sequence. e.g. 1.0 or 255.
        Returns:
        automatically generated

      • setMaxVal

        public void setMaxVal​(double val)
        Sets the maximum value taken on by pixels in image sequence.
        Parameters:
        val - automatically generated