View Source Evision.DISOpticalFlow (Evision v0.1.8)

Link to this section Summary

cv

Creates an instance of DISOpticalFlow

Creates an instance of DISOpticalFlow

Finest level of the Gaussian pyramid on which the flow is computed (zero level corresponds to the original image resolution). The final flow is obtained by bilinear upscaling.

Maximum number of gradient descent iterations in the patch inverse search stage. Higher values may improve quality in some cases.

Size of an image patch for matching (in pixels). Normally, default 8x8 patches work well enough in most cases.

Stride between neighbor patches. Must be less than patch size. Lower values correspond to higher flow quality.

Whether to use mean-normalization of patches when computing patch distance. It is turned on by default as it typically provides a noticeable quality boost because of increased robustness to illumination variations. Turn it off if you are certain that your sequence doesn't contain any changes in illumination.

Whether to use spatial propagation of good optical flow vectors. This option is turned on by default, as it tends to work better on average and can sometimes help recover from major errors introduced by the coarse-to-fine scheme employed by the DIS optical flow algorithm. Turning this option off can make the output flow field a bit smoother, however.

Weight of the smoothness term

Weight of the color constancy term

Weight of the gradient constancy term

Number of fixed point iterations of variational refinement per scale. Set to zero to disable variational refinement completely. Higher values will typically result in more smooth and high-quality flow.

Positional Arguments
  • val: int

@copybrief getFinestScale @see getFinestScale

Positional Arguments
  • val: int

@copybrief getGradientDescentIterations @see getGradientDescentIterations

Positional Arguments
  • val: int

@copybrief getPatchSize @see getPatchSize

Positional Arguments
  • val: int

@copybrief getPatchStride @see getPatchStride

Positional Arguments
  • val: bool

@copybrief getUseMeanNormalization @see getUseMeanNormalization

Positional Arguments
  • val: bool

@copybrief getUseSpatialPropagation @see getUseSpatialPropagation

Positional Arguments
  • val: float

@copybrief getVariationalRefinementAlpha @see getVariationalRefinementAlpha

Positional Arguments
  • val: float

@copybrief getVariationalRefinementDelta @see getVariationalRefinementDelta

Positional Arguments
  • val: float

@copybrief getVariationalRefinementGamma @see getVariationalRefinementGamma

Positional Arguments
  • val: int

@copybrief getGradientDescentIterations @see getGradientDescentIterations

Functions

Raising version of create/0.

Raising version of create/1.

Raising version of getPatchSize/1.

Link to this section cv

Creates an instance of DISOpticalFlow

Keyword Arguments
  • preset: int.

    one of PRESET_ULTRAFAST, PRESET_FAST and PRESET_MEDIUM

Python prototype (for reference):

create([, preset]) -> retval

Creates an instance of DISOpticalFlow

Keyword Arguments
  • preset: int.

    one of PRESET_ULTRAFAST, PRESET_FAST and PRESET_MEDIUM

Python prototype (for reference):

create([, preset]) -> retval

Finest level of the Gaussian pyramid on which the flow is computed (zero level corresponds to the original image resolution). The final flow is obtained by bilinear upscaling.

@see setFinestScale

Python prototype (for reference):

getFinestScale() -> retval
Link to this function

getGradientDescentIterations(self)

View Source

Maximum number of gradient descent iterations in the patch inverse search stage. Higher values may improve quality in some cases.

@see setGradientDescentIterations

Python prototype (for reference):

getGradientDescentIterations() -> retval

Size of an image patch for matching (in pixels). Normally, default 8x8 patches work well enough in most cases.

@see setPatchSize

Python prototype (for reference):

getPatchSize() -> retval

Stride between neighbor patches. Must be less than patch size. Lower values correspond to higher flow quality.

@see setPatchStride

Python prototype (for reference):

getPatchStride() -> retval
Link to this function

getUseMeanNormalization(self)

View Source

Whether to use mean-normalization of patches when computing patch distance. It is turned on by default as it typically provides a noticeable quality boost because of increased robustness to illumination variations. Turn it off if you are certain that your sequence doesn't contain any changes in illumination.

@see setUseMeanNormalization

Python prototype (for reference):

getUseMeanNormalization() -> retval
Link to this function

getUseSpatialPropagation(self)

View Source

Whether to use spatial propagation of good optical flow vectors. This option is turned on by default, as it tends to work better on average and can sometimes help recover from major errors introduced by the coarse-to-fine scheme employed by the DIS optical flow algorithm. Turning this option off can make the output flow field a bit smoother, however.

@see setUseSpatialPropagation

Python prototype (for reference):

getUseSpatialPropagation() -> retval
Link to this function

getVariationalRefinementAlpha(self)

View Source

Weight of the smoothness term

@see setVariationalRefinementAlpha

Python prototype (for reference):

getVariationalRefinementAlpha() -> retval
Link to this function

getVariationalRefinementDelta(self)

View Source

Weight of the color constancy term

@see setVariationalRefinementDelta

Python prototype (for reference):

getVariationalRefinementDelta() -> retval
Link to this function

getVariationalRefinementGamma(self)

View Source

Weight of the gradient constancy term

@see setVariationalRefinementGamma

Python prototype (for reference):

getVariationalRefinementGamma() -> retval
Link to this function

getVariationalRefinementIterations(self)

View Source

Number of fixed point iterations of variational refinement per scale. Set to zero to disable variational refinement completely. Higher values will typically result in more smooth and high-quality flow.

@see setGradientDescentIterations

Python prototype (for reference):

getVariationalRefinementIterations() -> retval
Link to this function

setFinestScale(self, val)

View Source
Positional Arguments
  • val: int

@copybrief getFinestScale @see getFinestScale

Python prototype (for reference):

setFinestScale(val) -> None
Link to this function

setGradientDescentIterations(self, val)

View Source
Positional Arguments
  • val: int

@copybrief getGradientDescentIterations @see getGradientDescentIterations

Python prototype (for reference):

setGradientDescentIterations(val) -> None
Positional Arguments
  • val: int

@copybrief getPatchSize @see getPatchSize

Python prototype (for reference):

setPatchSize(val) -> None
Link to this function

setPatchStride(self, val)

View Source
Positional Arguments
  • val: int

@copybrief getPatchStride @see getPatchStride

Python prototype (for reference):

setPatchStride(val) -> None
Link to this function

setUseMeanNormalization(self, val)

View Source
Positional Arguments
  • val: bool

@copybrief getUseMeanNormalization @see getUseMeanNormalization

Python prototype (for reference):

setUseMeanNormalization(val) -> None
Link to this function

setUseSpatialPropagation(self, val)

View Source
Positional Arguments
  • val: bool

@copybrief getUseSpatialPropagation @see getUseSpatialPropagation

Python prototype (for reference):

setUseSpatialPropagation(val) -> None
Link to this function

setVariationalRefinementAlpha(self, val)

View Source
Positional Arguments
  • val: float

@copybrief getVariationalRefinementAlpha @see getVariationalRefinementAlpha

Python prototype (for reference):

setVariationalRefinementAlpha(val) -> None
Link to this function

setVariationalRefinementDelta(self, val)

View Source
Positional Arguments
  • val: float

@copybrief getVariationalRefinementDelta @see getVariationalRefinementDelta

Python prototype (for reference):

setVariationalRefinementDelta(val) -> None
Link to this function

setVariationalRefinementGamma(self, val)

View Source
Positional Arguments
  • val: float

@copybrief getVariationalRefinementGamma @see getVariationalRefinementGamma

Python prototype (for reference):

setVariationalRefinementGamma(val) -> None
Link to this function

setVariationalRefinementIterations(self, val)

View Source
Positional Arguments
  • val: int

@copybrief getGradientDescentIterations @see getGradientDescentIterations

Python prototype (for reference):

setVariationalRefinementIterations(val) -> None

Link to this section Functions

Raising version of create/0.

Raising version of create/1.

Raising version of getFinestScale/1.

Link to this function

getGradientDescentIterations!(self)

View Source

Raising version of getGradientDescentIterations/1.

Raising version of getPatchSize/1.

Raising version of getPatchStride/1.

Link to this function

getUseMeanNormalization!(self)

View Source

Raising version of getUseMeanNormalization/1.

Link to this function

getUseSpatialPropagation!(self)

View Source

Raising version of getUseSpatialPropagation/1.

Link to this function

getVariationalRefinementAlpha!(self)

View Source

Raising version of getVariationalRefinementAlpha/1.

Link to this function

getVariationalRefinementDelta!(self)

View Source

Raising version of getVariationalRefinementDelta/1.

Link to this function

getVariationalRefinementGamma!(self)

View Source

Raising version of getVariationalRefinementGamma/1.

Link to this function

getVariationalRefinementIterations!(self)

View Source

Raising version of getVariationalRefinementIterations/1.

Link to this function

setFinestScale!(self, val)

View Source

Raising version of setFinestScale/2.

Link to this function

setGradientDescentIterations!(self, val)

View Source

Raising version of setGradientDescentIterations/2.

Link to this function

setPatchSize!(self, val)

View Source

Raising version of setPatchSize/2.

Link to this function

setPatchStride!(self, val)

View Source

Raising version of setPatchStride/2.

Link to this function

setUseMeanNormalization!(self, val)

View Source

Raising version of setUseMeanNormalization/2.

Link to this function

setUseSpatialPropagation!(self, val)

View Source

Raising version of setUseSpatialPropagation/2.

Link to this function

setVariationalRefinementAlpha!(self, val)

View Source

Raising version of setVariationalRefinementAlpha/2.

Link to this function

setVariationalRefinementDelta!(self, val)

View Source

Raising version of setVariationalRefinementDelta/2.

Link to this function

setVariationalRefinementGamma!(self, val)

View Source

Raising version of setVariationalRefinementGamma/2.

Link to this function

setVariationalRefinementIterations!(self, val)

View Source

Raising version of setVariationalRefinementIterations/2.