OpenCV  3.3.0-dev
Open Source Computer Vision
Public Member Functions | Static Public Member Functions | List of all members
cv::cuda::OpticalFlowDual_TVL1 Class Referenceabstract

Implementation of the Zach, Pock and Bischof Dual TV-L1 Optical Flow method. More...

#include "cudaoptflow.hpp"

Inheritance diagram for cv::cuda::OpticalFlowDual_TVL1:
cv::cuda::DenseOpticalFlow cv::Algorithm

Public Member Functions

virtual double getEpsilon () const =0
 
virtual double getGamma () const =0
 
virtual double getLambda () const =0
 
virtual int getNumIterations () const =0
 
virtual int getNumScales () const =0
 
virtual int getNumWarps () const =0
 
virtual double getScaleStep () const =0
 
virtual double getTau () const =0
 
virtual double getTheta () const =0
 
virtual bool getUseInitialFlow () const =0
 
virtual void setEpsilon (double epsilon)=0
 
virtual void setGamma (double gamma)=0
 
virtual void setLambda (double lambda)=0
 
virtual void setNumIterations (int iterations)=0
 
virtual void setNumScales (int nscales)=0
 
virtual void setNumWarps (int warps)=0
 
virtual void setScaleStep (double scaleStep)=0
 
virtual void setTau (double tau)=0
 
virtual void setTheta (double theta)=0
 
virtual void setUseInitialFlow (bool useInitialFlow)=0
 
- Public Member Functions inherited from cv::cuda::DenseOpticalFlow
virtual void calc (InputArray I0, InputArray I1, InputOutputArray flow, Stream &stream=Stream::Null())=0
 Calculates a dense optical flow. More...
 
- Public Member Functions inherited from cv::Algorithm
 Algorithm ()
 
virtual ~Algorithm ()
 
virtual void clear ()
 Clears the algorithm state. More...
 
virtual bool empty () const
 Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read. More...
 
virtual String getDefaultName () const
 
virtual void read (const FileNode &fn)
 Reads algorithm parameters from a file storage. More...
 
virtual void save (const String &filename) const
 
virtual void write (FileStorage &fs) const
 Stores algorithm parameters in a file storage. More...
 

Static Public Member Functions

static Ptr< OpticalFlowDual_TVL1create (double tau=0.25, double lambda=0.15, double theta=0.3, int nscales=5, int warps=5, double epsilon=0.01, int iterations=300, double scaleStep=0.8, double gamma=0.0, bool useInitialFlow=false)
 
- Static Public Member Functions inherited from cv::Algorithm
template<typename _Tp >
static Ptr< _Tp > load (const String &filename, const String &objname=String())
 Loads algorithm from the file. More...
 
template<typename _Tp >
static Ptr< _Tp > loadFromString (const String &strModel, const String &objname=String())
 Loads algorithm from a String. More...
 
template<typename _Tp >
static Ptr< _Tp > read (const FileNode &fn)
 Reads algorithm from the file node. More...
 

Additional Inherited Members

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

Detailed Description

Implementation of the Zach, Pock and Bischof Dual TV-L1 Optical Flow method.

See also
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<OpticalFlowDual_TVL1> cv::cuda::OpticalFlowDual_TVL1::create ( double  tau = 0.25,
double  lambda = 0.15,
double  theta = 0.3,
int  nscales = 5,
int  warps = 5,
double  epsilon = 0.01,
int  iterations = 300,
double  scaleStep = 0.8,
double  gamma = 0.0,
bool  useInitialFlow = false 
)
static

◆ getEpsilon()

virtual double cv::cuda::OpticalFlowDual_TVL1::getEpsilon ( ) const
pure virtual

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.

◆ getGamma()

virtual double cv::cuda::OpticalFlowDual_TVL1::getGamma ( ) const
pure virtual

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.

◆ getLambda()

virtual double cv::cuda::OpticalFlowDual_TVL1::getLambda ( ) const
pure virtual

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.

◆ getNumIterations()

virtual int cv::cuda::OpticalFlowDual_TVL1::getNumIterations ( ) const
pure virtual

Stopping criterion iterations number used in the numerical scheme.

◆ getNumScales()

virtual int cv::cuda::OpticalFlowDual_TVL1::getNumScales ( ) const
pure virtual

Number of scales used to create the pyramid of images.

◆ getNumWarps()

virtual int cv::cuda::OpticalFlowDual_TVL1::getNumWarps ( ) const
pure virtual

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.

◆ getScaleStep()

virtual double cv::cuda::OpticalFlowDual_TVL1::getScaleStep ( ) const
pure virtual

◆ getTau()

virtual double cv::cuda::OpticalFlowDual_TVL1::getTau ( ) const
pure virtual

Time step of the numerical scheme.

◆ getTheta()

virtual double cv::cuda::OpticalFlowDual_TVL1::getTheta ( ) const
pure virtual

parameter used for motion estimation. It adds a variable allowing for illumination variations Set this parameter to 1. if you have varying illumination. See: Chambolle et al, A First-Order Primal-Dual Algorithm for Convex Problems with Applications to Imaging Journal of Mathematical imaging and vision, may 2011 Vol 40 issue 1, pp 120-145

◆ getUseInitialFlow()

virtual bool cv::cuda::OpticalFlowDual_TVL1::getUseInitialFlow ( ) const
pure virtual

◆ setEpsilon()

virtual void cv::cuda::OpticalFlowDual_TVL1::setEpsilon ( double  epsilon)
pure virtual

◆ setGamma()

virtual void cv::cuda::OpticalFlowDual_TVL1::setGamma ( double  gamma)
pure virtual

◆ setLambda()

virtual void cv::cuda::OpticalFlowDual_TVL1::setLambda ( double  lambda)
pure virtual

◆ setNumIterations()

virtual void cv::cuda::OpticalFlowDual_TVL1::setNumIterations ( int  iterations)
pure virtual

◆ setNumScales()

virtual void cv::cuda::OpticalFlowDual_TVL1::setNumScales ( int  nscales)
pure virtual

◆ setNumWarps()

virtual void cv::cuda::OpticalFlowDual_TVL1::setNumWarps ( int  warps)
pure virtual

◆ setScaleStep()

virtual void cv::cuda::OpticalFlowDual_TVL1::setScaleStep ( double  scaleStep)
pure virtual

◆ setTau()

virtual void cv::cuda::OpticalFlowDual_TVL1::setTau ( double  tau)
pure virtual

◆ setTheta()

virtual void cv::cuda::OpticalFlowDual_TVL1::setTheta ( double  theta)
pure virtual

◆ setUseInitialFlow()

virtual void cv::cuda::OpticalFlowDual_TVL1::setUseInitialFlow ( bool  useInitialFlow)
pure virtual

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