Package org.opencv.ximgproc
Class DisparityWLSFilter
java.lang.Object
org.opencv.core.Algorithm
org.opencv.ximgproc.DisparityFilter
org.opencv.ximgproc.DisparityWLSFilter
Disparity map filter based on Weighted Least Squares filter (in form of Fast Global Smoother that
is a lot faster than traditional Weighted Least Squares filter implementations) and optional use of
left-right-consistency-based confidence to refine the results in half-occlusions and uniform areas.
-
Field Summary
-
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionstatic DisparityWLSFilter
__fromPtr__
(long addr) protected void
finalize()
Get the confidence map that was used in the last filter call.int
DepthDiscontinuityRadius is a parameter used in confidence computation.double
Lambda is a parameter defining the amount of regularization during filtering.int
LRCthresh is a threshold of disparity difference used in left-right-consistency check during confidence map computation.getROI()
Get the ROI used in the last filter calldouble
SigmaColor is a parameter defining how sensitive the filtering process is to source image edges.void
setDepthDiscontinuityRadius
(int _disc_radius) SEE: getDepthDiscontinuityRadiusvoid
setLambda
(double _lambda) SEE: getLambdavoid
setLRCthresh
(int _LRC_thresh) SEE: getLRCthreshvoid
setSigmaColor
(double _sigma_color) SEE: getSigmaColorMethods inherited from class org.opencv.ximgproc.DisparityFilter
filter, filter, filter, filter
Methods inherited from class org.opencv.core.Algorithm
clear, empty, getDefaultName, getNativeObjAddr, save
-
Constructor Details
-
DisparityWLSFilter
protected DisparityWLSFilter(long addr)
-
-
Method Details
-
__fromPtr__
-
getLambda
public double getLambda()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.- Returns:
- automatically generated
-
setLambda
public void setLambda(double _lambda) SEE: getLambda- Parameters:
_lambda
- automatically generated
-
getSigmaColor
public double getSigmaColor()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.- Returns:
- automatically generated
-
setSigmaColor
public void setSigmaColor(double _sigma_color) SEE: getSigmaColor- Parameters:
_sigma_color
- automatically generated
-
getLRCthresh
public int getLRCthresh()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.- Returns:
- automatically generated
-
setLRCthresh
public void setLRCthresh(int _LRC_thresh) SEE: getLRCthresh- Parameters:
_LRC_thresh
- automatically generated
-
getDepthDiscontinuityRadius
public int getDepthDiscontinuityRadius()DepthDiscontinuityRadius is a parameter used in confidence computation. It defines the size of low-confidence regions around depth discontinuities.- Returns:
- automatically generated
-
setDepthDiscontinuityRadius
public void setDepthDiscontinuityRadius(int _disc_radius) SEE: getDepthDiscontinuityRadius- Parameters:
_disc_radius
- automatically generated
-
getConfidenceMap
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).- Returns:
- automatically generated
-
getROI
Get the ROI used in the last filter call- Returns:
- automatically generated
-
finalize
- Overrides:
finalize
in classDisparityFilter
- Throws:
Throwable
-