View Source Evision.Saliency.StaticSaliency (Evision v0.2.9)
Summary
Functions
This function perform a binary map of given saliency map. This is obtained in this way
This function perform a binary map of given saliency map. This is obtained in this way
Types
@type t() :: %Evision.Saliency.StaticSaliency{ref: reference()}
Type that represents an Saliency.StaticSaliency struct.
ref.
reference()The underlying erlang resource variable.
Functions
@spec computeBinaryMap(t(), Evision.Mat.maybe_mat_in()) :: Evision.Mat.t() | false | {:error, String.t()}
This function perform a binary map of given saliency map. This is obtained in this way:
Positional Arguments
self:
Evision.Saliency.StaticSaliency.t()saliencyMap:
Evision.Mat.the saliency map obtained through one of the specialized algorithms
Return
retval:
boolbinaryMap:
Evision.Mat.t().the binary map
In a first step, to improve the definition of interest areas and facilitate identification of targets, a segmentation by clustering is performed, using K-means algorithm. Then, to gain a binary representation of clustered saliency map, since values of the map can vary according to the characteristics of frame under analysis, it is not convenient to use a fixed threshold. So, Otsu's algorithm* is used, which assumes that the image to be thresholded contains two classes of pixels or bi-modal histograms (e.g. foreground and back-ground pixels); later on, the algorithm calculates the optimal threshold separating those two classes, so that their intra-class variance is minimal.
Python prototype (for reference only):
computeBinaryMap(_saliencyMap[, _binaryMap]) -> retval, _binaryMap@spec computeBinaryMap(t(), Evision.Mat.maybe_mat_in(), [{atom(), term()}, ...] | nil) :: Evision.Mat.t() | false | {:error, String.t()}
This function perform a binary map of given saliency map. This is obtained in this way:
Positional Arguments
self:
Evision.Saliency.StaticSaliency.t()saliencyMap:
Evision.Mat.the saliency map obtained through one of the specialized algorithms
Return
retval:
boolbinaryMap:
Evision.Mat.t().the binary map
In a first step, to improve the definition of interest areas and facilitate identification of targets, a segmentation by clustering is performed, using K-means algorithm. Then, to gain a binary representation of clustered saliency map, since values of the map can vary according to the characteristics of frame under analysis, it is not convenient to use a fixed threshold. So, Otsu's algorithm* is used, which assumes that the image to be thresholded contains two classes of pixels or bi-modal histograms (e.g. foreground and back-ground pixels); later on, the algorithm calculates the optimal threshold separating those two classes, so that their intra-class variance is minimal.
Python prototype (for reference only):
computeBinaryMap(_saliencyMap[, _binaryMap]) -> retval, _binaryMap