View Source Evision.StereoSGBM (Evision v0.2.9)
Summary
Functions
Clears the algorithm state
Computes disparity map for the specified stereo pair
Computes disparity map for the specified stereo pair
Creates StereoSGBM object
Creates StereoSGBM object
Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read
getBlockSize
getDefaultName
getDisp12MaxDiff
getMinDisparity
getMode
getNumDisparities
getP1
getP2
getPreFilterCap
getSpeckleRange
getSpeckleWindowSize
getUniquenessRatio
Reads algorithm parameters from a file storage
save
setBlockSize
setDisp12MaxDiff
setMinDisparity
setMode
setNumDisparities
setP1
setP2
setPreFilterCap
setSpeckleRange
setSpeckleWindowSize
setUniquenessRatio
Stores algorithm parameters in a file storage
write
Enumerator
Types
Functions
@spec clear(Keyword.t()) :: any() | {:error, String.t()}
@spec clear(t()) :: t() | {:error, String.t()}
Clears the algorithm state
Positional Arguments
- self:
Evision.StereoSGBM.t()
Python prototype (for reference only):
clear() -> None
@spec compute(t(), Evision.Mat.maybe_mat_in(), Evision.Mat.maybe_mat_in()) :: Evision.Mat.t() | {:error, String.t()}
Computes disparity map for the specified stereo pair
Positional Arguments
self:
Evision.StereoSGBM.t()
left:
Evision.Mat
.Left 8-bit single-channel image.
right:
Evision.Mat
.Right image of the same size and the same type as the left one.
Return
disparity:
Evision.Mat.t()
.Output disparity map. It has the same size as the input images. Some algorithms, like StereoBM or StereoSGBM compute 16-bit fixed-point disparity map (where each disparity value has 4 fractional bits), whereas other algorithms output 32-bit floating-point disparity map.
Python prototype (for reference only):
compute(left, right[, disparity]) -> disparity
@spec compute( t(), Evision.Mat.maybe_mat_in(), Evision.Mat.maybe_mat_in(), [{atom(), term()}, ...] | nil ) :: Evision.Mat.t() | {:error, String.t()}
Computes disparity map for the specified stereo pair
Positional Arguments
self:
Evision.StereoSGBM.t()
left:
Evision.Mat
.Left 8-bit single-channel image.
right:
Evision.Mat
.Right image of the same size and the same type as the left one.
Return
disparity:
Evision.Mat.t()
.Output disparity map. It has the same size as the input images. Some algorithms, like StereoBM or StereoSGBM compute 16-bit fixed-point disparity map (where each disparity value has 4 fractional bits), whereas other algorithms output 32-bit floating-point disparity map.
Python prototype (for reference only):
compute(left, right[, disparity]) -> disparity
Creates StereoSGBM object
Keyword Arguments
minDisparity:
integer()
.Minimum possible disparity value. Normally, it is zero but sometimes rectification algorithms can shift images, so this parameter needs to be adjusted accordingly.
numDisparities:
integer()
.Maximum disparity minus minimum disparity. The value is always greater than zero. In the current implementation, this parameter must be divisible by 16.
blockSize:
integer()
.Matched block size. It must be an odd number >=1 . Normally, it should be somewhere in the 3..11 range.
p1:
integer()
.The first parameter controlling the disparity smoothness. See below.
p2:
integer()
.The second parameter controlling the disparity smoothness. The larger the values are, the smoother the disparity is. P1 is the penalty on the disparity change by plus or minus 1 between neighbor pixels. P2 is the penalty on the disparity change by more than 1 between neighbor pixels. The algorithm requires P2 > P1 . See stereo_match.cpp sample where some reasonably good P1 and P2 values are shown (like 8*number_of_image_channels*blockSize*blockSize and 32*number_of_image_channels*blockSize*blockSize , respectively).
disp12MaxDiff:
integer()
.Maximum allowed difference (in integer pixel units) in the left-right disparity check. Set it to a non-positive value to disable the check.
preFilterCap:
integer()
.Truncation value for the prefiltered image pixels. The algorithm first computes x-derivative at each pixel and clips its value by [-preFilterCap, preFilterCap] interval. The result values are passed to the Birchfield-Tomasi pixel cost function.
uniquenessRatio:
integer()
.Margin in percentage by which the best (minimum) computed cost function value should "win" the second best value to consider the found match correct. Normally, a value within the 5-15 range is good enough.
speckleWindowSize:
integer()
.Maximum size of smooth disparity regions to consider their noise speckles and invalidate. Set it to 0 to disable speckle filtering. Otherwise, set it somewhere in the 50-200 range.
speckleRange:
integer()
.Maximum disparity variation within each connected component. If you do speckle filtering, set the parameter to a positive value, it will be implicitly multiplied by 16. Normally, 1 or 2 is good enough.
mode:
integer()
.Set it to StereoSGBM::MODE_HH to run the full-scale two-pass dynamic programming algorithm. It will consume O(W*H*numDisparities) bytes, which is large for 640x480 stereo and huge for HD-size pictures. By default, it is set to false .
Return
- retval:
Evision.StereoSGBM.t()
The first constructor initializes StereoSGBM with all the default parameters. So, you only have to set StereoSGBM::numDisparities at minimum. The second constructor enables you to set each parameter to a custom value.
Python prototype (for reference only):
create([, minDisparity[, numDisparities[, blockSize[, P1[, P2[, disp12MaxDiff[, preFilterCap[, uniquenessRatio[, speckleWindowSize[, speckleRange[, mode]]]]]]]]]]]) -> retval
@spec create(Keyword.t()) :: any() | {:error, String.t()}
@spec create( [ blockSize: term(), disp12MaxDiff: term(), minDisparity: term(), mode: term(), numDisparities: term(), p1: term(), p2: term(), preFilterCap: term(), speckleRange: term(), speckleWindowSize: term(), uniquenessRatio: term() ] | nil ) :: t() | {:error, String.t()}
Creates StereoSGBM object
Keyword Arguments
minDisparity:
integer()
.Minimum possible disparity value. Normally, it is zero but sometimes rectification algorithms can shift images, so this parameter needs to be adjusted accordingly.
numDisparities:
integer()
.Maximum disparity minus minimum disparity. The value is always greater than zero. In the current implementation, this parameter must be divisible by 16.
blockSize:
integer()
.Matched block size. It must be an odd number >=1 . Normally, it should be somewhere in the 3..11 range.
p1:
integer()
.The first parameter controlling the disparity smoothness. See below.
p2:
integer()
.The second parameter controlling the disparity smoothness. The larger the values are, the smoother the disparity is. P1 is the penalty on the disparity change by plus or minus 1 between neighbor pixels. P2 is the penalty on the disparity change by more than 1 between neighbor pixels. The algorithm requires P2 > P1 . See stereo_match.cpp sample where some reasonably good P1 and P2 values are shown (like 8*number_of_image_channels*blockSize*blockSize and 32*number_of_image_channels*blockSize*blockSize , respectively).
disp12MaxDiff:
integer()
.Maximum allowed difference (in integer pixel units) in the left-right disparity check. Set it to a non-positive value to disable the check.
preFilterCap:
integer()
.Truncation value for the prefiltered image pixels. The algorithm first computes x-derivative at each pixel and clips its value by [-preFilterCap, preFilterCap] interval. The result values are passed to the Birchfield-Tomasi pixel cost function.
uniquenessRatio:
integer()
.Margin in percentage by which the best (minimum) computed cost function value should "win" the second best value to consider the found match correct. Normally, a value within the 5-15 range is good enough.
speckleWindowSize:
integer()
.Maximum size of smooth disparity regions to consider their noise speckles and invalidate. Set it to 0 to disable speckle filtering. Otherwise, set it somewhere in the 50-200 range.
speckleRange:
integer()
.Maximum disparity variation within each connected component. If you do speckle filtering, set the parameter to a positive value, it will be implicitly multiplied by 16. Normally, 1 or 2 is good enough.
mode:
integer()
.Set it to StereoSGBM::MODE_HH to run the full-scale two-pass dynamic programming algorithm. It will consume O(W*H*numDisparities) bytes, which is large for 640x480 stereo and huge for HD-size pictures. By default, it is set to false .
Return
- retval:
Evision.StereoSGBM.t()
The first constructor initializes StereoSGBM with all the default parameters. So, you only have to set StereoSGBM::numDisparities at minimum. The second constructor enables you to set each parameter to a custom value.
Python prototype (for reference only):
create([, minDisparity[, numDisparities[, blockSize[, P1[, P2[, disp12MaxDiff[, preFilterCap[, uniquenessRatio[, speckleWindowSize[, speckleRange[, mode]]]]]]]]]]]) -> retval
@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.StereoSGBM.t()
Return
- retval:
bool
Python prototype (for reference only):
empty() -> retval
@spec getBlockSize(Keyword.t()) :: any() | {:error, String.t()}
@spec getBlockSize(t()) :: integer() | {:error, String.t()}
getBlockSize
Positional Arguments
- self:
Evision.StereoSGBM.t()
Return
- retval:
integer()
Python prototype (for reference only):
getBlockSize() -> retval
@spec getDefaultName(Keyword.t()) :: any() | {:error, String.t()}
@spec getDefaultName(t()) :: binary() | {:error, String.t()}
getDefaultName
Positional Arguments
- self:
Evision.StereoSGBM.t()
Return
- retval:
String
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
@spec getDisp12MaxDiff(Keyword.t()) :: any() | {:error, String.t()}
@spec getDisp12MaxDiff(t()) :: integer() | {:error, String.t()}
getDisp12MaxDiff
Positional Arguments
- self:
Evision.StereoSGBM.t()
Return
- retval:
integer()
Python prototype (for reference only):
getDisp12MaxDiff() -> retval
@spec getMinDisparity(Keyword.t()) :: any() | {:error, String.t()}
@spec getMinDisparity(t()) :: integer() | {:error, String.t()}
getMinDisparity
Positional Arguments
- self:
Evision.StereoSGBM.t()
Return
- retval:
integer()
Python prototype (for reference only):
getMinDisparity() -> retval
@spec getMode(Keyword.t()) :: any() | {:error, String.t()}
@spec getMode(t()) :: integer() | {:error, String.t()}
getMode
Positional Arguments
- self:
Evision.StereoSGBM.t()
Return
- retval:
integer()
Python prototype (for reference only):
getMode() -> retval
@spec getNumDisparities(Keyword.t()) :: any() | {:error, String.t()}
@spec getNumDisparities(t()) :: integer() | {:error, String.t()}
getNumDisparities
Positional Arguments
- self:
Evision.StereoSGBM.t()
Return
- retval:
integer()
Python prototype (for reference only):
getNumDisparities() -> retval
@spec getP1(Keyword.t()) :: any() | {:error, String.t()}
@spec getP1(t()) :: integer() | {:error, String.t()}
getP1
Positional Arguments
- self:
Evision.StereoSGBM.t()
Return
- retval:
integer()
Python prototype (for reference only):
getP1() -> retval
@spec getP2(Keyword.t()) :: any() | {:error, String.t()}
@spec getP2(t()) :: integer() | {:error, String.t()}
getP2
Positional Arguments
- self:
Evision.StereoSGBM.t()
Return
- retval:
integer()
Python prototype (for reference only):
getP2() -> retval
@spec getPreFilterCap(Keyword.t()) :: any() | {:error, String.t()}
@spec getPreFilterCap(t()) :: integer() | {:error, String.t()}
getPreFilterCap
Positional Arguments
- self:
Evision.StereoSGBM.t()
Return
- retval:
integer()
Python prototype (for reference only):
getPreFilterCap() -> retval
@spec getSpeckleRange(Keyword.t()) :: any() | {:error, String.t()}
@spec getSpeckleRange(t()) :: integer() | {:error, String.t()}
getSpeckleRange
Positional Arguments
- self:
Evision.StereoSGBM.t()
Return
- retval:
integer()
Python prototype (for reference only):
getSpeckleRange() -> retval
@spec getSpeckleWindowSize(Keyword.t()) :: any() | {:error, String.t()}
@spec getSpeckleWindowSize(t()) :: integer() | {:error, String.t()}
getSpeckleWindowSize
Positional Arguments
- self:
Evision.StereoSGBM.t()
Return
- retval:
integer()
Python prototype (for reference only):
getSpeckleWindowSize() -> retval
@spec getUniquenessRatio(Keyword.t()) :: any() | {:error, String.t()}
@spec getUniquenessRatio(t()) :: integer() | {:error, String.t()}
getUniquenessRatio
Positional Arguments
- self:
Evision.StereoSGBM.t()
Return
- retval:
integer()
Python prototype (for reference only):
getUniquenessRatio() -> retval
@spec read(t(), Evision.FileNode.t()) :: t() | {:error, String.t()}
Reads algorithm parameters from a file storage
Positional Arguments
- self:
Evision.StereoSGBM.t()
- func:
Evision.FileNode
Python prototype (for reference only):
read(fn) -> None
save
Positional Arguments
- self:
Evision.StereoSGBM.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
setBlockSize
Positional Arguments
- self:
Evision.StereoSGBM.t()
- blockSize:
integer()
Python prototype (for reference only):
setBlockSize(blockSize) -> None
setDisp12MaxDiff
Positional Arguments
- self:
Evision.StereoSGBM.t()
- disp12MaxDiff:
integer()
Python prototype (for reference only):
setDisp12MaxDiff(disp12MaxDiff) -> None
setMinDisparity
Positional Arguments
- self:
Evision.StereoSGBM.t()
- minDisparity:
integer()
Python prototype (for reference only):
setMinDisparity(minDisparity) -> None
setMode
Positional Arguments
- self:
Evision.StereoSGBM.t()
- mode:
integer()
Python prototype (for reference only):
setMode(mode) -> None
setNumDisparities
Positional Arguments
- self:
Evision.StereoSGBM.t()
- numDisparities:
integer()
Python prototype (for reference only):
setNumDisparities(numDisparities) -> None
setP1
Positional Arguments
- self:
Evision.StereoSGBM.t()
- p1:
integer()
Python prototype (for reference only):
setP1(P1) -> None
setP2
Positional Arguments
- self:
Evision.StereoSGBM.t()
- p2:
integer()
Python prototype (for reference only):
setP2(P2) -> None
setPreFilterCap
Positional Arguments
- self:
Evision.StereoSGBM.t()
- preFilterCap:
integer()
Python prototype (for reference only):
setPreFilterCap(preFilterCap) -> None
setSpeckleRange
Positional Arguments
- self:
Evision.StereoSGBM.t()
- speckleRange:
integer()
Python prototype (for reference only):
setSpeckleRange(speckleRange) -> None
setSpeckleWindowSize
Positional Arguments
- self:
Evision.StereoSGBM.t()
- speckleWindowSize:
integer()
Python prototype (for reference only):
setSpeckleWindowSize(speckleWindowSize) -> None
setUniquenessRatio
Positional Arguments
- self:
Evision.StereoSGBM.t()
- uniquenessRatio:
integer()
Python prototype (for reference only):
setUniquenessRatio(uniquenessRatio) -> None
@spec write(t(), Evision.FileStorage.t()) :: t() | {:error, String.t()}
Stores algorithm parameters in a file storage
Positional Arguments
- self:
Evision.StereoSGBM.t()
- fs:
Evision.FileStorage
Python prototype (for reference only):
write(fs) -> None
@spec write(t(), Evision.FileStorage.t(), binary()) :: t() | {:error, String.t()}
write
Positional Arguments
- self:
Evision.StereoSGBM.t()
- fs:
Evision.FileStorage
- name:
String
Has overloading in C++
Python prototype (for reference only):
write(fs, name) -> None