View Source Evision.XImgProc.DisparityWLSFilter (Evision v0.2.9)
Summary
Functions
Get the confidence map that was used in the last filter call. It is a CV_32F one-channel image with values ranging from 0.0 (totally untrusted regions of the raw disparity map) to 255.0 (regions containing correct disparity values with a high degree of confidence).
DepthDiscontinuityRadius is a parameter used in confidence computation. It defines the size of low-confidence regions around depth discontinuities.
Lambda is a parameter defining the amount of regularization during filtering. Larger values force filtered disparity map edges to adhere more to source image edges. Typical value is 8000.
LRCthresh is a threshold of disparity difference used in left-right-consistency check during confidence map computation. The default value of 24 (1.5 pixels) is virtually always good enough.
Get the ROI used in the last filter call
SigmaColor is a parameter defining how sensitive the filtering process is to source image edges. Large values can lead to disparity leakage through low-contrast edges. Small values can make the filter too sensitive to noise and textures in the source image. Typical values range from 0.8 to 2.0.
setDepthDiscontinuityRadius
setLambda
setLRCthresh
setSigmaColor
Types
@type t() :: %Evision.XImgProc.DisparityWLSFilter{ref: reference()}
Type that represents an XImgProc.DisparityWLSFilter
struct.
ref.
reference()
The underlying erlang resource variable.
Functions
@spec getConfidenceMap(Keyword.t()) :: any() | {:error, String.t()}
@spec getConfidenceMap(t()) :: Evision.Mat.t() | {:error, String.t()}
Get the confidence map that was used in the last filter call. It is a CV_32F one-channel image with values ranging from 0.0 (totally untrusted regions of the raw disparity map) to 255.0 (regions containing correct disparity values with a high degree of confidence).
Positional Arguments
- self:
Evision.XImgProc.DisparityWLSFilter.t()
Return
- retval:
Evision.Mat.t()
Python prototype (for reference only):
getConfidenceMap() -> retval
@spec getDepthDiscontinuityRadius(Keyword.t()) :: any() | {:error, String.t()}
@spec getDepthDiscontinuityRadius(t()) :: integer() | {:error, String.t()}
DepthDiscontinuityRadius is a parameter used in confidence computation. It defines the size of low-confidence regions around depth discontinuities.
Positional Arguments
- self:
Evision.XImgProc.DisparityWLSFilter.t()
Return
- retval:
integer()
Python prototype (for reference only):
getDepthDiscontinuityRadius() -> retval
@spec getLambda(Keyword.t()) :: any() | {:error, String.t()}
@spec getLambda(t()) :: number() | {:error, String.t()}
Lambda is a parameter defining the amount of regularization during filtering. Larger values force filtered disparity map edges to adhere more to source image edges. Typical value is 8000.
Positional Arguments
- self:
Evision.XImgProc.DisparityWLSFilter.t()
Return
- retval:
double
Python prototype (for reference only):
getLambda() -> retval
@spec getLRCthresh(Keyword.t()) :: any() | {:error, String.t()}
@spec getLRCthresh(t()) :: integer() | {:error, String.t()}
LRCthresh is a threshold of disparity difference used in left-right-consistency check during confidence map computation. The default value of 24 (1.5 pixels) is virtually always good enough.
Positional Arguments
- self:
Evision.XImgProc.DisparityWLSFilter.t()
Return
- retval:
integer()
Python prototype (for reference only):
getLRCthresh() -> retval
@spec getROI(Keyword.t()) :: any() | {:error, String.t()}
@spec getROI(t()) :: {number(), number(), number(), number()} | {:error, String.t()}
Get the ROI used in the last filter call
Positional Arguments
- self:
Evision.XImgProc.DisparityWLSFilter.t()
Return
- retval:
Rect
Python prototype (for reference only):
getROI() -> retval
@spec getSigmaColor(Keyword.t()) :: any() | {:error, String.t()}
@spec getSigmaColor(t()) :: number() | {:error, String.t()}
SigmaColor is a parameter defining how sensitive the filtering process is to source image edges. Large values can lead to disparity leakage through low-contrast edges. Small values can make the filter too sensitive to noise and textures in the source image. Typical values range from 0.8 to 2.0.
Positional Arguments
- self:
Evision.XImgProc.DisparityWLSFilter.t()
Return
- retval:
double
Python prototype (for reference only):
getSigmaColor() -> retval
setDepthDiscontinuityRadius
Positional Arguments
- self:
Evision.XImgProc.DisparityWLSFilter.t()
- disc_radius:
integer()
@see getDepthDiscontinuityRadius
Python prototype (for reference only):
setDepthDiscontinuityRadius(_disc_radius) -> None
setLambda
Positional Arguments
- self:
Evision.XImgProc.DisparityWLSFilter.t()
- lambda:
double
@see getLambda
Python prototype (for reference only):
setLambda(_lambda) -> None
setLRCthresh
Positional Arguments
- self:
Evision.XImgProc.DisparityWLSFilter.t()
- lRC_thresh:
integer()
@see getLRCthresh
Python prototype (for reference only):
setLRCthresh(_LRC_thresh) -> None
setSigmaColor
Positional Arguments
- self:
Evision.XImgProc.DisparityWLSFilter.t()
- sigma_color:
double
@see getSigmaColor
Python prototype (for reference only):
setSigmaColor(_sigma_color) -> None