View Source Evision.StereoSGBM (Evision v0.1.9)

Link to this section Summary

cv

Computes disparity map for the specified stereo pair

Computes disparity map for the specified stereo pair

Creates StereoSGBM object

Creates StereoSGBM object

Python prototype (for reference):

Python prototype (for reference):

Python prototype (for reference):

Python prototype (for reference):

Python prototype (for reference):

Python prototype (for reference):

Python prototype (for reference):

Python prototype (for reference):

Python prototype (for reference):

Python prototype (for reference):

Python prototype (for reference):

Positional Arguments
  • blockSize: int

Python prototype (for reference):

Positional Arguments
  • disp12MaxDiff: int

Python prototype (for reference):

Positional Arguments
  • minDisparity: int

Python prototype (for reference):

Positional Arguments
  • mode: int

Python prototype (for reference):

Positional Arguments
  • numDisparities: int

Python prototype (for reference):

Positional Arguments
  • p1: int

Python prototype (for reference):

Positional Arguments
  • p2: int

Python prototype (for reference):

Positional Arguments
  • preFilterCap: int

Python prototype (for reference):

Positional Arguments
  • speckleRange: int

Python prototype (for reference):

Positional Arguments
  • speckleWindowSize: int

Python prototype (for reference):

Positional Arguments
  • uniquenessRatio: int

Python prototype (for reference):

Functions

Raising version of create/0.

Raising version of create/1.

Raising version of getBlockSize/1.

Raising version of getMode/1.

Raising version of getP1/1.

Raising version of getP2/1.

Raising version of setMode/2.

Raising version of setP1/2.

Raising version of setP2/2.

Link to this section cv

Link to this function

compute(self, left, right)

View Source

Computes disparity map for the specified stereo pair

Positional Arguments
  • 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.

    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):

compute(left, right[, disparity]) -> disparity
Link to this function

compute(self, left, right, opts)

View Source

Computes disparity map for the specified stereo pair

Positional Arguments
  • 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.

    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):

compute(left, right[, disparity]) -> disparity

Creates StereoSGBM object

Keyword Arguments
  • minDisparity: int.

    Minimum possible disparity value. Normally, it is zero but sometimes rectification algorithms can shift images, so this parameter needs to be adjusted accordingly.

  • numDisparities: int.

    Maximum disparity minus minimum disparity. The value is always greater than zero. In the current implementation, this parameter must be divisible by 16.

  • blockSize: int.

    Matched block size. It must be an odd number >=1 . Normally, it should be somewhere in the 3..11 range.

  • p1: int.

    The first parameter controlling the disparity smoothness. See below.

  • p2: int.

    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: int.

    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: int.

    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: int.

    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: int.

    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: int.

    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: int.

    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 .

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):

create([, minDisparity[, numDisparities[, blockSize[, P1[, P2[, disp12MaxDiff[, preFilterCap[, uniquenessRatio[, speckleWindowSize[, speckleRange[, mode]]]]]]]]]]]) -> retval

Creates StereoSGBM object

Keyword Arguments
  • minDisparity: int.

    Minimum possible disparity value. Normally, it is zero but sometimes rectification algorithms can shift images, so this parameter needs to be adjusted accordingly.

  • numDisparities: int.

    Maximum disparity minus minimum disparity. The value is always greater than zero. In the current implementation, this parameter must be divisible by 16.

  • blockSize: int.

    Matched block size. It must be an odd number >=1 . Normally, it should be somewhere in the 3..11 range.

  • p1: int.

    The first parameter controlling the disparity smoothness. See below.

  • p2: int.

    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: int.

    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: int.

    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: int.

    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: int.

    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: int.

    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: int.

    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 .

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):

create([, minDisparity[, numDisparities[, blockSize[, P1[, P2[, disp12MaxDiff[, preFilterCap[, uniquenessRatio[, speckleWindowSize[, speckleRange[, mode]]]]]]]]]]]) -> retval

Python prototype (for reference):

getBlockSize() -> retval

Python prototype (for reference):

getDisp12MaxDiff() -> retval

Python prototype (for reference):

getMinDisparity() -> retval

Python prototype (for reference):

getMode() -> retval

Python prototype (for reference):

getNumDisparities() -> retval

Python prototype (for reference):

getP1() -> retval

Python prototype (for reference):

getP2() -> retval

Python prototype (for reference):

getPreFilterCap() -> retval

Python prototype (for reference):

getSpeckleRange() -> retval
Link to this function

getSpeckleWindowSize(self)

View Source

Python prototype (for reference):

getSpeckleWindowSize() -> retval
Link to this function

getUniquenessRatio(self)

View Source

Python prototype (for reference):

getUniquenessRatio() -> retval
Link to this function

setBlockSize(self, blockSize)

View Source
Positional Arguments
  • blockSize: int

Python prototype (for reference):

setBlockSize(blockSize) -> None
Link to this function

setDisp12MaxDiff(self, disp12MaxDiff)

View Source
Positional Arguments
  • disp12MaxDiff: int

Python prototype (for reference):

setDisp12MaxDiff(disp12MaxDiff) -> None
Link to this function

setMinDisparity(self, minDisparity)

View Source
Positional Arguments
  • minDisparity: int

Python prototype (for reference):

setMinDisparity(minDisparity) -> None
Positional Arguments
  • mode: int

Python prototype (for reference):

setMode(mode) -> None
Link to this function

setNumDisparities(self, numDisparities)

View Source
Positional Arguments
  • numDisparities: int

Python prototype (for reference):

setNumDisparities(numDisparities) -> None
Positional Arguments
  • p1: int

Python prototype (for reference):

setP1(P1) -> None
Positional Arguments
  • p2: int

Python prototype (for reference):

setP2(P2) -> None
Link to this function

setPreFilterCap(self, preFilterCap)

View Source
Positional Arguments
  • preFilterCap: int

Python prototype (for reference):

setPreFilterCap(preFilterCap) -> None
Link to this function

setSpeckleRange(self, speckleRange)

View Source
Positional Arguments
  • speckleRange: int

Python prototype (for reference):

setSpeckleRange(speckleRange) -> None
Link to this function

setSpeckleWindowSize(self, speckleWindowSize)

View Source
Positional Arguments
  • speckleWindowSize: int

Python prototype (for reference):

setSpeckleWindowSize(speckleWindowSize) -> None
Link to this function

setUniquenessRatio(self, uniquenessRatio)

View Source
Positional Arguments
  • uniquenessRatio: int

Python prototype (for reference):

setUniquenessRatio(uniquenessRatio) -> None

Link to this section Functions

Link to this function

compute!(self, left, right)

View Source

Raising version of compute/3.

Link to this function

compute!(self, left, right, opts)

View Source

Raising version of compute/4.

Raising version of create/0.

Raising version of create/1.

Raising version of getBlockSize/1.

Raising version of getDisp12MaxDiff/1.

Raising version of getMinDisparity/1.

Raising version of getMode/1.

Link to this function

getNumDisparities!(self)

View Source

Raising version of getNumDisparities/1.

Raising version of getP1/1.

Raising version of getP2/1.

Raising version of getPreFilterCap/1.

Raising version of getSpeckleRange/1.

Link to this function

getSpeckleWindowSize!(self)

View Source

Raising version of getSpeckleWindowSize/1.

Link to this function

getUniquenessRatio!(self)

View Source

Raising version of getUniquenessRatio/1.

Link to this function

setBlockSize!(self, blockSize)

View Source

Raising version of setBlockSize/2.

Link to this function

setDisp12MaxDiff!(self, disp12MaxDiff)

View Source

Raising version of setDisp12MaxDiff/2.

Link to this function

setMinDisparity!(self, minDisparity)

View Source

Raising version of setMinDisparity/2.

Raising version of setMode/2.

Link to this function

setNumDisparities!(self, numDisparities)

View Source

Raising version of setNumDisparities/2.

Raising version of setP1/2.

Raising version of setP2/2.

Link to this function

setPreFilterCap!(self, preFilterCap)

View Source

Raising version of setPreFilterCap/2.

Link to this function

setSpeckleRange!(self, speckleRange)

View Source

Raising version of setSpeckleRange/2.

Link to this function

setSpeckleWindowSize!(self, speckleWindowSize)

View Source

Raising version of setSpeckleWindowSize/2.

Link to this function

setUniquenessRatio!(self, uniquenessRatio)

View Source

Raising version of setUniquenessRatio/2.