View Source Evision.DISOpticalFlow (Evision v0.1.13)
Link to this section Summary
Types
Type that represents an Evision.DISOpticalFlow
struct.
Functions
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.
Link to this section Types
@type t() :: %Evision.DISOpticalFlow{ref: reference()}
Type that represents an Evision.DISOpticalFlow
struct.
ref.
reference()
The underlying erlang resource variable.
Link to this section Functions
Creates an instance of DISOpticalFlow
Keyword Arguments
preset:
int
.one of PRESET_ULTRAFAST, PRESET_FAST and PRESET_MEDIUM
Return
- retval:
Evision.DISOpticalFlow
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
Return
- retval:
Evision.DISOpticalFlow
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.
Return
- retval:
int
@see setFinestScale/2
Python prototype (for reference):
getFinestScale() -> retval
Maximum number of gradient descent iterations in the patch inverse search stage. Higher values may improve quality in some cases.
Return
- retval:
int
@see setGradientDescentIterations/2
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.
Return
- retval:
int
@see setPatchSize/2
Python prototype (for reference):
getPatchSize() -> retval
Stride between neighbor patches. Must be less than patch size. Lower values correspond to higher flow quality.
Return
- retval:
int
@see setPatchStride/2
Python prototype (for reference):
getPatchStride() -> retval
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.
Return
- retval:
bool
@see setUseMeanNormalization/2
Python prototype (for reference):
getUseMeanNormalization() -> retval
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.
Return
- retval:
bool
@see setUseSpatialPropagation/2
Python prototype (for reference):
getUseSpatialPropagation() -> retval
Weight of the smoothness term
Return
- retval:
float
@see setVariationalRefinementAlpha/2
Python prototype (for reference):
getVariationalRefinementAlpha() -> retval
Weight of the color constancy term
Return
- retval:
float
@see setVariationalRefinementDelta/2
Python prototype (for reference):
getVariationalRefinementDelta() -> retval
Weight of the gradient constancy term
Return
- retval:
float
@see setVariationalRefinementGamma/2
Python prototype (for reference):
getVariationalRefinementGamma() -> retval
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.
Return
- retval:
int
@see setGradientDescentIterations/2
Python prototype (for reference):
getVariationalRefinementIterations() -> retval
Positional Arguments
- val:
int
@see getFinestScale/1
Python prototype (for reference):
setFinestScale(val) -> None
Positional Arguments
- val:
int
@see getGradientDescentIterations/1
Python prototype (for reference):
setGradientDescentIterations(val) -> None
Positional Arguments
- val:
int
@see getPatchSize/1
Python prototype (for reference):
setPatchSize(val) -> None
Positional Arguments
- val:
int
@see getPatchStride/1
Python prototype (for reference):
setPatchStride(val) -> None
Positional Arguments
- val:
bool
@see getUseMeanNormalization/1
Python prototype (for reference):
setUseMeanNormalization(val) -> None
Positional Arguments
- val:
bool
@see getUseSpatialPropagation/1
Python prototype (for reference):
setUseSpatialPropagation(val) -> None
Positional Arguments
- val:
float
@see getVariationalRefinementAlpha/1
Python prototype (for reference):
setVariationalRefinementAlpha(val) -> None
Positional Arguments
- val:
float
@see getVariationalRefinementDelta/1
Python prototype (for reference):
setVariationalRefinementDelta(val) -> None
Positional Arguments
- val:
float
@see getVariationalRefinementGamma/1
Python prototype (for reference):
setVariationalRefinementGamma(val) -> None
Positional Arguments
- val:
int
@see getGradientDescentIterations/1
Python prototype (for reference):
setVariationalRefinementIterations(val) -> None