View Source Evision.BgSegm.BackgroundSubtractorGMG (Evision v0.2.9)

Summary

Types

t()

Type that represents an BgSegm.BackgroundSubtractorGMG struct.

Functions

Computes a foreground mask.

Computes a foreground mask.

Clears the algorithm state

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

Computes a background image.

Computes a background image.

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

Returns the value of decision threshold.

Returns the learning rate of the algorithm.

Returns total number of distinct colors to maintain in histogram.

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

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

Returns the number of frames used to initialize background model.

Returns the parameter used for quantization of color-space.

Returns the kernel radius used for morphological operations

Returns the status of background model update

Reads algorithm parameters from a file storage

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

Sets the value of decision threshold.

Sets the learning rate of the algorithm.

Sets total number of distinct colors to maintain in histogram.

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

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

Sets the number of frames used to initialize background model.

Sets the parameter used for quantization of color-space

Sets the kernel radius used for morphological operations

Sets the status of background model update

Stores algorithm parameters in a file storage

Types

@type t() :: %Evision.BgSegm.BackgroundSubtractorGMG{ref: reference()}

Type that represents an BgSegm.BackgroundSubtractorGMG struct.

  • ref. reference()

    The underlying erlang resource variable.

Functions

@spec apply(Keyword.t()) :: any() | {:error, String.t()}
@spec apply(t(), Evision.Mat.maybe_mat_in()) :: Evision.Mat.t() | {:error, String.t()}

Computes a foreground mask.

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()

  • image: Evision.Mat.

    Next video frame.

Keyword Arguments
  • learningRate: double.

    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.

Return
  • fgmask: Evision.Mat.t().

    The output foreground mask as an 8-bit binary image.

Python prototype (for reference only):

apply(image[, fgmask[, learningRate]]) -> fgmask
Link to this function

apply(self, image, opts)

View Source
@spec apply(t(), Evision.Mat.maybe_mat_in(), [{:learningRate, term()}] | nil) ::
  Evision.Mat.t() | {:error, String.t()}

Computes a foreground mask.

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()

  • image: Evision.Mat.

    Next video frame.

Keyword Arguments
  • learningRate: double.

    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.

Return
  • fgmask: Evision.Mat.t().

    The output foreground mask as an 8-bit binary image.

Python prototype (for reference only):

apply(image[, fgmask[, learningRate]]) -> fgmask
@spec clear(Keyword.t()) :: any() | {:error, String.t()}
@spec clear(t()) :: t() | {:error, String.t()}

Clears the algorithm state

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()

Python prototype (for reference only):

clear() -> None
@spec empty(Keyword.t()) :: any() | {:error, String.t()}
@spec empty(t()) :: boolean() | {:error, String.t()}

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

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
Return
  • retval: bool

Python prototype (for reference only):

empty() -> retval
Link to this function

getBackgroundImage(named_args)

View Source
@spec getBackgroundImage(Keyword.t()) :: any() | {:error, String.t()}
@spec getBackgroundImage(t()) :: Evision.Mat.t() | {:error, String.t()}

Computes a background image.

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
Return
  • backgroundImage: Evision.Mat.t().

    The output background image.

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

Python prototype (for reference only):

getBackgroundImage([, backgroundImage]) -> backgroundImage
Link to this function

getBackgroundImage(self, opts)

View Source
@spec getBackgroundImage(t(), [{atom(), term()}, ...] | nil) ::
  Evision.Mat.t() | {:error, String.t()}

Computes a background image.

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
Return
  • backgroundImage: Evision.Mat.t().

    The output background image.

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

Python prototype (for reference only):

getBackgroundImage([, backgroundImage]) -> backgroundImage
Link to this function

getBackgroundPrior(named_args)

View Source
@spec getBackgroundPrior(Keyword.t()) :: any() | {:error, String.t()}
@spec getBackgroundPrior(t()) :: number() | {:error, String.t()}

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

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
Return
  • retval: double

Python prototype (for reference only):

getBackgroundPrior() -> retval
Link to this function

getDecisionThreshold(named_args)

View Source
@spec getDecisionThreshold(Keyword.t()) :: any() | {:error, String.t()}
@spec getDecisionThreshold(t()) :: number() | {:error, String.t()}

Returns the value of decision threshold.

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
Return
  • retval: double

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

Python prototype (for reference only):

getDecisionThreshold() -> retval
Link to this function

getDefaultLearningRate(named_args)

View Source
@spec getDefaultLearningRate(Keyword.t()) :: any() | {:error, String.t()}
@spec getDefaultLearningRate(t()) :: number() | {:error, String.t()}

Returns the learning rate of the algorithm.

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
Return
  • retval: double

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

Python prototype (for reference only):

getDefaultLearningRate() -> retval
Link to this function

getDefaultName(named_args)

View Source
@spec getDefaultName(Keyword.t()) :: any() | {:error, String.t()}
@spec getDefaultName(t()) :: binary() | {:error, String.t()}

getDefaultName

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
Return

Returns the algorithm string identifier. This string is used as top level xml/yml node tag when the object is saved to a file or string.

Python prototype (for reference only):

getDefaultName() -> retval
Link to this function

getMaxFeatures(named_args)

View Source
@spec getMaxFeatures(Keyword.t()) :: any() | {:error, String.t()}
@spec getMaxFeatures(t()) :: integer() | {:error, String.t()}

Returns total number of distinct colors to maintain in histogram.

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
Return
  • retval: integer()

Python prototype (for reference only):

getMaxFeatures() -> retval
@spec getMaxVal(Keyword.t()) :: any() | {:error, String.t()}
@spec getMaxVal(t()) :: number() | {:error, String.t()}

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

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
Return
  • retval: double

Python prototype (for reference only):

getMaxVal() -> retval
@spec getMinVal(Keyword.t()) :: any() | {:error, String.t()}
@spec getMinVal(t()) :: number() | {:error, String.t()}

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

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
Return
  • retval: double

Python prototype (for reference only):

getMinVal() -> retval
Link to this function

getNumFrames(named_args)

View Source
@spec getNumFrames(Keyword.t()) :: any() | {:error, String.t()}
@spec getNumFrames(t()) :: integer() | {:error, String.t()}

Returns the number of frames used to initialize background model.

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
Return
  • retval: integer()

Python prototype (for reference only):

getNumFrames() -> retval
Link to this function

getQuantizationLevels(named_args)

View Source
@spec getQuantizationLevels(Keyword.t()) :: any() | {:error, String.t()}
@spec getQuantizationLevels(t()) :: integer() | {:error, String.t()}

Returns the parameter used for quantization of color-space.

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
Return
  • retval: integer()

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

Python prototype (for reference only):

getQuantizationLevels() -> retval
Link to this function

getSmoothingRadius(named_args)

View Source
@spec getSmoothingRadius(Keyword.t()) :: any() | {:error, String.t()}
@spec getSmoothingRadius(t()) :: integer() | {:error, String.t()}

Returns the kernel radius used for morphological operations

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
Return
  • retval: integer()

Python prototype (for reference only):

getSmoothingRadius() -> retval
Link to this function

getUpdateBackgroundModel(named_args)

View Source
@spec getUpdateBackgroundModel(Keyword.t()) :: any() | {:error, String.t()}
@spec getUpdateBackgroundModel(t()) :: boolean() | {:error, String.t()}

Returns the status of background model update

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
Return
  • retval: bool

Python prototype (for reference only):

getUpdateBackgroundModel() -> retval
@spec read(Keyword.t()) :: any() | {:error, String.t()}
@spec read(t(), Evision.FileNode.t()) :: t() | {:error, String.t()}

Reads algorithm parameters from a file storage

Positional Arguments

Python prototype (for reference only):

read(fn) -> None
@spec save(Keyword.t()) :: any() | {:error, String.t()}
@spec save(t(), binary()) :: t() | {:error, String.t()}

save

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
  • filename: String

Saves the algorithm to a file. In order to make this method work, the derived class must implement Algorithm::write(FileStorage& fs).

Python prototype (for reference only):

save(filename) -> None
Link to this function

setBackgroundPrior(named_args)

View Source
@spec setBackgroundPrior(Keyword.t()) :: any() | {:error, String.t()}
Link to this function

setBackgroundPrior(self, bgprior)

View Source
@spec setBackgroundPrior(t(), number()) :: t() | {:error, String.t()}

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

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
  • bgprior: double

Python prototype (for reference only):

setBackgroundPrior(bgprior) -> None
Link to this function

setDecisionThreshold(named_args)

View Source
@spec setDecisionThreshold(Keyword.t()) :: any() | {:error, String.t()}
Link to this function

setDecisionThreshold(self, thresh)

View Source
@spec setDecisionThreshold(t(), number()) :: t() | {:error, String.t()}

Sets the value of decision threshold.

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
  • thresh: double

Python prototype (for reference only):

setDecisionThreshold(thresh) -> None
Link to this function

setDefaultLearningRate(named_args)

View Source
@spec setDefaultLearningRate(Keyword.t()) :: any() | {:error, String.t()}
Link to this function

setDefaultLearningRate(self, lr)

View Source
@spec setDefaultLearningRate(t(), number()) :: t() | {:error, String.t()}

Sets the learning rate of the algorithm.

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
  • lr: double

Python prototype (for reference only):

setDefaultLearningRate(lr) -> None
Link to this function

setMaxFeatures(named_args)

View Source
@spec setMaxFeatures(Keyword.t()) :: any() | {:error, String.t()}
Link to this function

setMaxFeatures(self, maxFeatures)

View Source
@spec setMaxFeatures(t(), integer()) :: t() | {:error, String.t()}

Sets total number of distinct colors to maintain in histogram.

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
  • maxFeatures: integer()

Python prototype (for reference only):

setMaxFeatures(maxFeatures) -> None
@spec setMaxVal(Keyword.t()) :: any() | {:error, String.t()}
@spec setMaxVal(t(), number()) :: t() | {:error, String.t()}

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

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
  • val: double

Python prototype (for reference only):

setMaxVal(val) -> None
@spec setMinVal(Keyword.t()) :: any() | {:error, String.t()}
@spec setMinVal(t(), number()) :: t() | {:error, String.t()}

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

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
  • val: double

Python prototype (for reference only):

setMinVal(val) -> None
Link to this function

setNumFrames(named_args)

View Source
@spec setNumFrames(Keyword.t()) :: any() | {:error, String.t()}
Link to this function

setNumFrames(self, nframes)

View Source
@spec setNumFrames(t(), integer()) :: t() | {:error, String.t()}

Sets the number of frames used to initialize background model.

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
  • nframes: integer()

Python prototype (for reference only):

setNumFrames(nframes) -> None
Link to this function

setQuantizationLevels(named_args)

View Source
@spec setQuantizationLevels(Keyword.t()) :: any() | {:error, String.t()}
Link to this function

setQuantizationLevels(self, nlevels)

View Source
@spec setQuantizationLevels(t(), integer()) :: t() | {:error, String.t()}

Sets the parameter used for quantization of color-space

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
  • nlevels: integer()

Python prototype (for reference only):

setQuantizationLevels(nlevels) -> None
Link to this function

setSmoothingRadius(named_args)

View Source
@spec setSmoothingRadius(Keyword.t()) :: any() | {:error, String.t()}
Link to this function

setSmoothingRadius(self, radius)

View Source
@spec setSmoothingRadius(t(), integer()) :: t() | {:error, String.t()}

Sets the kernel radius used for morphological operations

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
  • radius: integer()

Python prototype (for reference only):

setSmoothingRadius(radius) -> None
Link to this function

setUpdateBackgroundModel(named_args)

View Source
@spec setUpdateBackgroundModel(Keyword.t()) :: any() | {:error, String.t()}
Link to this function

setUpdateBackgroundModel(self, update)

View Source
@spec setUpdateBackgroundModel(t(), boolean()) :: t() | {:error, String.t()}

Sets the status of background model update

Positional Arguments
  • self: Evision.BgSegm.BackgroundSubtractorGMG.t()
  • update: bool

Python prototype (for reference only):

setUpdateBackgroundModel(update) -> None
@spec write(Keyword.t()) :: any() | {:error, String.t()}
@spec write(t(), Evision.FileStorage.t()) :: t() | {:error, String.t()}

Stores algorithm parameters in a file storage

Positional Arguments

Python prototype (for reference only):

write(fs) -> None
@spec write(t(), Evision.FileStorage.t(), binary()) :: t() | {:error, String.t()}

write

Positional Arguments

Has overloading in C++

Python prototype (for reference only):

write(fs, name) -> None