View Source Evision.Saliency.ObjectnessBING (Evision v0.1.28)

Link to this section Summary

Types

t()

Type that represents an Saliency.ObjectnessBING struct.

Functions

create

getBase

getNSS

Return the list of the rectangles' objectness value,

getW

read

This is a utility function that allows to set an arbitrary path in which the algorithm will save the optional results

This is a utility function that allows to set the correct path from which the algorithm will load the trained model.

write

Link to this section Types

@type t() :: %Evision.Saliency.ObjectnessBING{ref: reference()}

Type that represents an Saliency.ObjectnessBING struct.

  • ref. reference()

    The underlying erlang resource variable.

Link to this section Functions

Link to this function

computeSaliency(self, image)

View Source
@spec computeSaliency(t(), Evision.Mat.maybe_mat_in()) ::
  Evision.Mat.t() | false | {:error, String.t()}

computeSaliency

Positional Arguments
  • self: Evision.Saliency.ObjectnessBING.t()
  • image: Evision.Mat.t()
Return
  • retval: bool
  • saliencyMap: Evision.Mat.t().

Python prototype (for reference only):

computeSaliency(image[, saliencyMap]) -> retval, saliencyMap
Link to this function

computeSaliency(self, image, opts)

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

computeSaliency

Positional Arguments
  • self: Evision.Saliency.ObjectnessBING.t()
  • image: Evision.Mat.t()
Return
  • retval: bool
  • saliencyMap: Evision.Mat.t().

Python prototype (for reference only):

computeSaliency(image[, saliencyMap]) -> retval, saliencyMap
@spec create() :: t() | {:error, String.t()}

create

Return
  • retval: ObjectnessBING

Python prototype (for reference only):

create() -> retval
@spec getBase(t()) :: number() | {:error, String.t()}

getBase

Positional Arguments
  • self: Evision.Saliency.ObjectnessBING.t()
Return
  • retval: double

Python prototype (for reference only):

getBase() -> retval
@spec getNSS(t()) :: integer() | {:error, String.t()}

getNSS

Positional Arguments
  • self: Evision.Saliency.ObjectnessBING.t()
Return
  • retval: int

Python prototype (for reference only):

getNSS() -> retval
Link to this function

getobjectnessValues(self)

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

Return the list of the rectangles' objectness value,

Positional Arguments
  • self: Evision.Saliency.ObjectnessBING.t()
Return
  • retval: [float]

in the same order as the vector\<Vec4i> objectnessBoundingBox returned by the algorithm (in computeSaliencyImpl function). The bigger value these scores are, it is more likely to be an object window.

Python prototype (for reference only):

getobjectnessValues() -> retval
@spec getW(t()) :: integer() | {:error, String.t()}

getW

Positional Arguments
  • self: Evision.Saliency.ObjectnessBING.t()
Return
  • retval: int

Python prototype (for reference only):

getW() -> retval
@spec read(t()) :: t() | {:error, String.t()}

read

Positional Arguments
  • self: Evision.Saliency.ObjectnessBING.t()

Python prototype (for reference only):

read() -> None
@spec setBase(t(), number()) :: t() | {:error, String.t()}

setBase

Positional Arguments
  • self: Evision.Saliency.ObjectnessBING.t()
  • val: double

Python prototype (for reference only):

setBase(val) -> None
Link to this function

setBBResDir(self, resultsDir)

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

This is a utility function that allows to set an arbitrary path in which the algorithm will save the optional results

Positional Arguments
  • self: Evision.Saliency.ObjectnessBING.t()

  • resultsDir: String.

    results' folder path

(ie writing on file the total number and the list of rectangles returned by objectess, one for each row).

Python prototype (for reference only):

setBBResDir(resultsDir) -> None
@spec setNSS(t(), integer()) :: t() | {:error, String.t()}

setNSS

Positional Arguments
  • self: Evision.Saliency.ObjectnessBING.t()
  • val: int

Python prototype (for reference only):

setNSS(val) -> None
Link to this function

setTrainingPath(self, trainingPath)

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

This is a utility function that allows to set the correct path from which the algorithm will load the trained model.

Positional Arguments
  • self: Evision.Saliency.ObjectnessBING.t()

  • trainingPath: String.

    trained model path

Python prototype (for reference only):

setTrainingPath(trainingPath) -> None
@spec setW(t(), integer()) :: t() | {:error, String.t()}

setW

Positional Arguments
  • self: Evision.Saliency.ObjectnessBING.t()
  • val: int

Python prototype (for reference only):

setW(val) -> None
@spec write(t()) :: t() | {:error, String.t()}

write

Positional Arguments
  • self: Evision.Saliency.ObjectnessBING.t()

Python prototype (for reference only):

write() -> None