OpenCV  4.10.0-dev
Open Source Computer Vision
Loading...
Searching...
No Matches
cv::optflow::DualTVL1OpticalFlow Class Referenceabstract

"Dual TV L1" Optical Flow Algorithm. More...

#include <opencv2/optflow.hpp>

Collaboration diagram for cv::optflow::DualTVL1OpticalFlow:

Public Member Functions

virtual double getEpsilon () const =0
 Stopping criterion threshold used in the numerical scheme, which is a trade-off between precision and running time.
 
virtual double getGamma () const =0
 coefficient for additional illumination variation term
 
virtual int getInnerIterations () const =0
 Inner iterations (between outlier filtering) used in the numerical scheme.
 
virtual double getLambda () const =0
 Weight parameter for the data term, attachment parameter.
 
virtual int getMedianFiltering () const =0
 Median filter kernel size (1 = no filter) (3 or 5)
 
virtual int getOuterIterations () const =0
 Outer iterations (number of inner loops) used in the numerical scheme.
 
virtual int getScalesNumber () const =0
 Number of scales used to create the pyramid of images.
 
virtual double getScaleStep () const =0
 Step between scales (<1)
 
virtual double getTau () const =0
 Time step of the numerical scheme.
 
virtual double getTheta () const =0
 Weight parameter for (u - v)^2, tightness parameter.
 
virtual bool getUseInitialFlow () const =0
 Use initial flow.
 
virtual int getWarpingsNumber () const =0
 Number of warpings per scale.
 
virtual void setEpsilon (double val)=0
 Stopping criterion threshold used in the numerical scheme, which is a trade-off between precision and running time.
 
virtual void setGamma (double val)=0
 coefficient for additional illumination variation term
 
virtual void setInnerIterations (int val)=0
 Inner iterations (between outlier filtering) used in the numerical scheme.
 
virtual void setLambda (double val)=0
 Weight parameter for the data term, attachment parameter.
 
virtual void setMedianFiltering (int val)=0
 Median filter kernel size (1 = no filter) (3 or 5)
 
virtual void setOuterIterations (int val)=0
 Outer iterations (number of inner loops) used in the numerical scheme.
 
virtual void setScalesNumber (int val)=0
 Number of scales used to create the pyramid of images.
 
virtual void setScaleStep (double val)=0
 Step between scales (<1)
 
virtual void setTau (double val)=0
 Time step of the numerical scheme.
 
virtual void setTheta (double val)=0
 Weight parameter for (u - v)^2, tightness parameter.
 
virtual void setUseInitialFlow (bool val)=0
 Use initial flow.
 
virtual void setWarpingsNumber (int val)=0
 Number of warpings per scale.
 
- Public Member Functions inherited from cv::DenseOpticalFlow
virtual void calc (InputArray I0, InputArray I1, InputOutputArray flow)=0
 Calculates an optical flow.
 
virtual void collectGarbage ()=0
 Releases all inner buffers.
 
- Public Member Functions inherited from cv::Algorithm
 Algorithm ()
 
virtual ~Algorithm ()
 
virtual void clear ()
 Clears the algorithm state.
 
virtual bool empty () const
 Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read.
 
virtual String getDefaultName () const
 
virtual void read (const FileNode &fn)
 Reads algorithm parameters from a file storage.
 
virtual void save (const String &filename) const
 
void write (const Ptr< FileStorage > &fs, const String &name=String()) const
 
virtual void write (FileStorage &fs) const
 Stores algorithm parameters in a file storage.
 
void write (FileStorage &fs, const String &name) const
 

Static Public Member Functions

static Ptr< DualTVL1OpticalFlowcreate (double tau=0.25, double lambda=0.15, double theta=0.3, int nscales=5, int warps=5, double epsilon=0.01, int innnerIterations=30, int outerIterations=10, double scaleStep=0.8, double gamma=0.0, int medianFiltering=5, bool useInitialFlow=false)
 Creates instance of cv::DualTVL1OpticalFlow.
 
- Static Public Member Functions inherited from cv::Algorithm
template<typename _Tp >
static Ptr< _Tpload (const String &filename, const String &objname=String())
 Loads algorithm from the file.
 
template<typename _Tp >
static Ptr< _TploadFromString (const String &strModel, const String &objname=String())
 Loads algorithm from a String.
 
template<typename _Tp >
static Ptr< _Tpread (const FileNode &fn)
 Reads algorithm from the file node.
 

Additional Inherited Members

- Protected Member Functions inherited from cv::Algorithm
void writeFormat (FileStorage &fs) const
 

Detailed Description

"Dual TV L1" Optical Flow Algorithm.

The class implements the "Dual TV L1" optical flow algorithm described in [314] and [234] . Here are important members of the class that control the algorithm, which you can set after constructing the class instance:

  • member double tau Time step of the numerical scheme.
  • member double lambda Weight parameter for the data term, attachment parameter. This is the most relevant parameter, which determines the smoothness of the output. The smaller this parameter is, the smoother the solutions we obtain. It depends on the range of motions of the images, so its value should be adapted to each image sequence.
  • member double theta Weight parameter for (u - v)\^2, tightness parameter. It serves as a link between the attachment and the regularization terms. In theory, it should have a small value in order to maintain both parts in correspondence. The method is stable for a large range of values of this parameter.
  • member int nscales Number of scales used to create the pyramid of images.
  • member int warps Number of warpings per scale. Represents the number of times that I1(x+u0) and grad( I1(x+u0) ) are computed per scale. This is a parameter that assures the stability of the method. It also affects the running time, so it is a compromise between speed and accuracy.
  • member double epsilon Stopping criterion threshold used in the numerical scheme, which is a trade-off between precision and running time. A small value will yield more accurate solutions at the expense of a slower convergence.
  • member int iterations Stopping criterion iterations number used in the numerical scheme.

C. Zach, T. Pock and H. Bischof, "A Duality Based Approach for Realtime TV-L1 Optical Flow". Javier Sanchez, Enric Meinhardt-Llopis and Gabriele Facciolo. "TV-L1 Optical Flow Estimation".

Member Function Documentation

◆ create()

static Ptr< DualTVL1OpticalFlow > cv::optflow::DualTVL1OpticalFlow::create ( double tau = 0.25,
double lambda = 0.15,
double theta = 0.3,
int nscales = 5,
int warps = 5,
double epsilon = 0.01,
int innnerIterations = 30,
int outerIterations = 10,
double scaleStep = 0.8,
double gamma = 0.0,
int medianFiltering = 5,
bool useInitialFlow = false )
static
Python:
cv.optflow.DualTVL1OpticalFlow.create([, tau[, lambda_[, theta[, nscales[, warps[, epsilon[, innnerIterations[, outerIterations[, scaleStep[, gamma[, medianFiltering[, useInitialFlow]]]]]]]]]]]]) -> retval
cv.optflow.DualTVL1OpticalFlow_create([, tau[, lambda_[, theta[, nscales[, warps[, epsilon[, innnerIterations[, outerIterations[, scaleStep[, gamma[, medianFiltering[, useInitialFlow]]]]]]]]]]]]) -> retval

Creates instance of cv::DualTVL1OpticalFlow.

◆ getEpsilon()

virtual double cv::optflow::DualTVL1OpticalFlow::getEpsilon ( ) const
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.getEpsilon() -> retval

Stopping criterion threshold used in the numerical scheme, which is a trade-off between precision and running time.

See also
setEpsilon

◆ getGamma()

virtual double cv::optflow::DualTVL1OpticalFlow::getGamma ( ) const
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.getGamma() -> retval

coefficient for additional illumination variation term

See also
setGamma

◆ getInnerIterations()

virtual int cv::optflow::DualTVL1OpticalFlow::getInnerIterations ( ) const
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.getInnerIterations() -> retval

Inner iterations (between outlier filtering) used in the numerical scheme.

See also
setInnerIterations

◆ getLambda()

virtual double cv::optflow::DualTVL1OpticalFlow::getLambda ( ) const
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.getLambda() -> retval

Weight parameter for the data term, attachment parameter.

See also
setLambda

◆ getMedianFiltering()

virtual int cv::optflow::DualTVL1OpticalFlow::getMedianFiltering ( ) const
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.getMedianFiltering() -> retval

Median filter kernel size (1 = no filter) (3 or 5)

See also
setMedianFiltering

◆ getOuterIterations()

virtual int cv::optflow::DualTVL1OpticalFlow::getOuterIterations ( ) const
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.getOuterIterations() -> retval

Outer iterations (number of inner loops) used in the numerical scheme.

See also
setOuterIterations

◆ getScalesNumber()

virtual int cv::optflow::DualTVL1OpticalFlow::getScalesNumber ( ) const
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.getScalesNumber() -> retval

Number of scales used to create the pyramid of images.

See also
setScalesNumber

◆ getScaleStep()

virtual double cv::optflow::DualTVL1OpticalFlow::getScaleStep ( ) const
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.getScaleStep() -> retval

Step between scales (<1)

See also
setScaleStep

◆ getTau()

virtual double cv::optflow::DualTVL1OpticalFlow::getTau ( ) const
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.getTau() -> retval

Time step of the numerical scheme.

See also
setTau

◆ getTheta()

virtual double cv::optflow::DualTVL1OpticalFlow::getTheta ( ) const
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.getTheta() -> retval

Weight parameter for (u - v)^2, tightness parameter.

See also
setTheta

◆ getUseInitialFlow()

virtual bool cv::optflow::DualTVL1OpticalFlow::getUseInitialFlow ( ) const
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.getUseInitialFlow() -> retval

Use initial flow.

See also
setUseInitialFlow

◆ getWarpingsNumber()

virtual int cv::optflow::DualTVL1OpticalFlow::getWarpingsNumber ( ) const
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.getWarpingsNumber() -> retval

Number of warpings per scale.

See also
setWarpingsNumber

◆ setEpsilon()

virtual void cv::optflow::DualTVL1OpticalFlow::setEpsilon ( double val)
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.setEpsilon(val) -> None

Stopping criterion threshold used in the numerical scheme, which is a trade-off between precision and running time.

See also
getEpsilon

◆ setGamma()

virtual void cv::optflow::DualTVL1OpticalFlow::setGamma ( double val)
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.setGamma(val) -> None

coefficient for additional illumination variation term

See also
getGamma

◆ setInnerIterations()

virtual void cv::optflow::DualTVL1OpticalFlow::setInnerIterations ( int val)
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.setInnerIterations(val) -> None

Inner iterations (between outlier filtering) used in the numerical scheme.

See also
getInnerIterations

◆ setLambda()

virtual void cv::optflow::DualTVL1OpticalFlow::setLambda ( double val)
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.setLambda(val) -> None

Weight parameter for the data term, attachment parameter.

See also
getLambda

◆ setMedianFiltering()

virtual void cv::optflow::DualTVL1OpticalFlow::setMedianFiltering ( int val)
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.setMedianFiltering(val) -> None

Median filter kernel size (1 = no filter) (3 or 5)

See also
getMedianFiltering

◆ setOuterIterations()

virtual void cv::optflow::DualTVL1OpticalFlow::setOuterIterations ( int val)
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.setOuterIterations(val) -> None

Outer iterations (number of inner loops) used in the numerical scheme.

See also
getOuterIterations

◆ setScalesNumber()

virtual void cv::optflow::DualTVL1OpticalFlow::setScalesNumber ( int val)
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.setScalesNumber(val) -> None

Number of scales used to create the pyramid of images.

See also
getScalesNumber

◆ setScaleStep()

virtual void cv::optflow::DualTVL1OpticalFlow::setScaleStep ( double val)
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.setScaleStep(val) -> None

Step between scales (<1)

See also
getScaleStep

◆ setTau()

virtual void cv::optflow::DualTVL1OpticalFlow::setTau ( double val)
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.setTau(val) -> None

Time step of the numerical scheme.

See also
getTau

◆ setTheta()

virtual void cv::optflow::DualTVL1OpticalFlow::setTheta ( double val)
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.setTheta(val) -> None

Weight parameter for (u - v)^2, tightness parameter.

See also
getTheta

◆ setUseInitialFlow()

virtual void cv::optflow::DualTVL1OpticalFlow::setUseInitialFlow ( bool val)
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.setUseInitialFlow(val) -> None

Use initial flow.

See also
getUseInitialFlow

◆ setWarpingsNumber()

virtual void cv::optflow::DualTVL1OpticalFlow::setWarpingsNumber ( int val)
pure virtual
Python:
cv.optflow.DualTVL1OpticalFlow.setWarpingsNumber(val) -> None

Number of warpings per scale.

See also
getWarpingsNumber

The documentation for this class was generated from the following file: