org.bytedeco.opencv.opencv_video

Class DISOpticalFlow

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.opencv.opencv_core.Algorithm

org.bytedeco.opencv.opencv_video.DenseOpticalFlow

org.bytedeco.opencv.opencv_video.DISOpticalFlow

All Implemented Interfaces:

AutoCloseable

@Namespace(value="cv")
 @Properties(inherit=opencv_video.class)
public class DISOpticalFlow
extends DenseOpticalFlow

\brief DIS optical flow algorithm.

This class implements the Dense Inverse Search (DIS) optical flow algorithm. More details about the algorithm can be found at \cite Kroeger2016 . Includes three presets with preselected parameters to provide reasonable trade-off between speed and quality. However, even the slowest preset is still relatively fast, use DeepFlow if you need better quality and don't care about speed.

This implementation includes several additional features compared to the algorithm described in the paper, including spatial propagation of flow vectors (\ref getUseSpatialPropagation), as well as an option to utilize an initial flow approximation passed to \ref calc (which is, essentially, temporal propagation, if the previous frame's flow field is passed).

Nested Class Summary

Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer

Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter

Field Summary

Fields

Modifier and Type	Field and Description
static int	PRESET_FAST enum cv::DISOpticalFlow::
static int	PRESET_MEDIUM enum cv::DISOpticalFlow::
static int	PRESET_ULTRAFAST enum cv::DISOpticalFlow::

Fields inherited from class org.bytedeco.javacpp.Pointer

address, capacity, limit, position

Constructor Summary

Constructors

Constructor and Description
DISOpticalFlow(Pointer p) Pointer cast constructor.

Method Summary

Modifier and Type	Method and Description
static DISOpticalFlow	create()
static DISOpticalFlow	create(int preset) \brief Creates an instance of DISOpticalFlow
int	getFinestScale() \brief Finest level of the Gaussian pyramid on which the flow is computed (zero level corresponds to the original image resolution).
int	getGradientDescentIterations() \brief Maximum number of gradient descent iterations in the patch inverse search stage.
int	getPatchSize() \brief Size of an image patch for matching (in pixels).
int	getPatchStride() \brief Stride between neighbor patches.
boolean	getUseMeanNormalization() \brief Whether to use mean-normalization of patches when computing patch distance.
boolean	getUseSpatialPropagation() \brief Whether to use spatial propagation of good optical flow vectors.
float	getVariationalRefinementAlpha() \brief Weight of the smoothness term
float	getVariationalRefinementDelta() \brief Weight of the color constancy term
float	getVariationalRefinementGamma() \brief Weight of the gradient constancy term
int	getVariationalRefinementIterations() \brief Number of fixed point iterations of variational refinement per scale.
void	setFinestScale(int val) \copybrief getFinestScale @see getFinestScale
void	setGradientDescentIterations(int val) \copybrief getGradientDescentIterations @see getGradientDescentIterations
void	setPatchSize(int val) \copybrief getPatchSize @see getPatchSize
void	setPatchStride(int val) \copybrief getPatchStride @see getPatchStride
void	setUseMeanNormalization(boolean val) \copybrief getUseMeanNormalization @see getUseMeanNormalization
void	setUseSpatialPropagation(boolean val) \copybrief getUseSpatialPropagation @see getUseSpatialPropagation
void	setVariationalRefinementAlpha(float val) \copybrief getVariationalRefinementAlpha @see getVariationalRefinementAlpha
void	setVariationalRefinementDelta(float val) \copybrief getVariationalRefinementDelta @see getVariationalRefinementDelta
void	setVariationalRefinementGamma(float val) \copybrief getVariationalRefinementGamma @see getVariationalRefinementGamma
void	setVariationalRefinementIterations(int val) \copybrief getGradientDescentIterations @see getGradientDescentIterations

Methods inherited from class org.bytedeco.opencv.opencv_video.DenseOpticalFlow

calc, calc, calc, collectGarbage

Methods inherited from class org.bytedeco.opencv.opencv_core.Algorithm

clear, empty, getDefaultName, position, read, save, save, write, write, write

Methods inherited from class org.bytedeco.javacpp.Pointer

address, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, hashCode, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetof, parseBytes, physicalBytes, position, put, realloc, referenceCount, releaseReference, retainReference, setNull, sizeof, toString, totalBytes, totalPhysicalBytes, withDeallocator, zero

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Field Detail

PRESET_ULTRAFAST

public static final int PRESET_ULTRAFAST

enum cv::DISOpticalFlow::

See Also:

Constant Field Values

PRESET_FAST

public static final int PRESET_FAST

enum cv::DISOpticalFlow::

See Also:

Constant Field Values

PRESET_MEDIUM

public static final int PRESET_MEDIUM

enum cv::DISOpticalFlow::

See Also:

Constant Field Values

Constructor Detail

DISOpticalFlow

public DISOpticalFlow(Pointer p)

Pointer cast constructor. Invokes Pointer.Pointer(Pointer).

Method Detail

getFinestScale

public int getFinestScale()

\brief 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 Also:

setFinestScale

setFinestScale

public void setFinestScale(int val)

\copybrief getFinestScale @see getFinestScale

getPatchSize

public int getPatchSize()

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

See Also:

setPatchSize

setPatchSize

public void setPatchSize(int val)

\copybrief getPatchSize @see getPatchSize

getPatchStride

public int getPatchStride()

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

See Also:

setPatchStride

setPatchStride

public void setPatchStride(int val)

\copybrief getPatchStride @see getPatchStride

getGradientDescentIterations

public int getGradientDescentIterations()

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

See Also:

setGradientDescentIterations

setGradientDescentIterations

public void setGradientDescentIterations(int val)

\copybrief getGradientDescentIterations @see getGradientDescentIterations

getVariationalRefinementIterations

public int getVariationalRefinementIterations()

\brief 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 Also:

setGradientDescentIterations

setVariationalRefinementIterations

public void setVariationalRefinementIterations(int val)

\copybrief getGradientDescentIterations @see getGradientDescentIterations

getVariationalRefinementAlpha

public float getVariationalRefinementAlpha()

\brief Weight of the smoothness term

See Also:

setVariationalRefinementAlpha

setVariationalRefinementAlpha

public void setVariationalRefinementAlpha(float val)

\copybrief getVariationalRefinementAlpha @see getVariationalRefinementAlpha

getVariationalRefinementDelta

public float getVariationalRefinementDelta()

\brief Weight of the color constancy term

See Also:

setVariationalRefinementDelta

setVariationalRefinementDelta

public void setVariationalRefinementDelta(float val)

\copybrief getVariationalRefinementDelta @see getVariationalRefinementDelta

getVariationalRefinementGamma

public float getVariationalRefinementGamma()

\brief Weight of the gradient constancy term

See Also:

setVariationalRefinementGamma

setVariationalRefinementGamma

public void setVariationalRefinementGamma(float val)

\copybrief getVariationalRefinementGamma @see getVariationalRefinementGamma

getUseMeanNormalization

@Cast(value="bool")
public boolean getUseMeanNormalization()

\brief 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 Also:

setUseMeanNormalization

setUseMeanNormalization

public void setUseMeanNormalization(@Cast(value="bool")
                                    boolean val)

\copybrief getUseMeanNormalization @see getUseMeanNormalization

getUseSpatialPropagation

@Cast(value="bool")
public boolean getUseSpatialPropagation()

\brief 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 Also:

setUseSpatialPropagation

setUseSpatialPropagation

public void setUseSpatialPropagation(@Cast(value="bool")
                                     boolean val)

\copybrief getUseSpatialPropagation @see getUseSpatialPropagation

create

@opencv_core.Ptr
public static DISOpticalFlow create(int preset)

\brief Creates an instance of DISOpticalFlow

Parameters:

preset - one of PRESET_ULTRAFAST, PRESET_FAST and PRESET_MEDIUM

create

@opencv_core.Ptr
public static DISOpticalFlow create()