OpenCV  4.2.0
Open Source Computer Vision
Public Member Functions | Static Public Member Functions | Public Attributes | List of all members
cv::optflow::RLOFOpticalFlowParameter Class Reference

This is used store and set up the parameters of the robust local optical flow (RLOF) algoritm. More...

#include <opencv2/optflow/rlofflow.hpp>

Public Member Functions

 RLOFOpticalFlowParameter ()
 
int getCrossSegmentationThreshold () const
 
float getGlobalMotionRansacThreshold () const
 
int getLargeWinSize () const
 
int getMaxIteration () const
 
int getMaxLevel () const
 
float getMinEigenValue () const
 
float getNormSigma0 () const
 
float getNormSigma1 () const
 
int getSmallWinSize () const
 
SolverType getSolverType () const
 
SupportRegionType getSupportRegionType () const
 
bool getUseGlobalMotionPrior () const
 
bool getUseIlluminationModel () const
 
bool getUseInitialFlow () const
 
void setCrossSegmentationThreshold (int val)
 
void setGlobalMotionRansacThreshold (float val)
 
void setLargeWinSize (int val)
 
void setMaxIteration (int val)
 
void setMaxLevel (int val)
 
void setMinEigenValue (float val)
 
void setNormSigma0 (float val)
 
void setNormSigma1 (float val)
 
void setSmallWinSize (int val)
 
void setSolverType (SolverType val)
 
void setSupportRegionType (SupportRegionType val)
 
void setUseGlobalMotionPrior (bool val)
 
void setUseIlluminationModel (bool val)
 
void setUseInitialFlow (bool val)
 

Static Public Member Functions

static Ptr< RLOFOpticalFlowParametercreate ()
 Creates instance of optflow::RLOFOpticalFlowParameter. More...
 

Public Attributes

int crossSegmentationThreshold
 
float globalMotionRansacThreshold
 
int largeWinSize
 
int maxIteration
 
int maxLevel
 
float minEigenValue
 
float normSigma0
 
float normSigma1
 
int smallWinSize
 
SolverType solverType
 
SupportRegionType supportRegionType
 
bool useGlobalMotionPrior
 
bool useIlluminationModel
 
bool useInitialFlow
 

Detailed Description

This is used store and set up the parameters of the robust local optical flow (RLOF) algoritm.

The RLOF is a fast local optical flow approach described in [202] [203] [204] and [205] similar to the pyramidal iterative Lucas-Kanade method as proposed by [24]. More details and experiments can be found in the following thesis [206]. The implementation is derived from optflow::calcOpticalFlowPyrLK(). This RLOF implementation can be seen as an improved pyramidal iterative Lucas-Kanade and includes a set of improving modules. The main improvements in respect to the pyramidal iterative Lucas-Kanade are:

The RLOF can be computed with the SparseOpticalFlow class or function interface to track a set of features or with the DenseOpticalFlow class or function interface to compute dense optical flow.

See also
optflow::DenseRLOFOpticalFlow, optflow::calcOpticalFlowDenseRLOF(), optflow::SparseRLOFOpticalFlow, optflow::calcOpticalFlowSparseRLOF()

Constructor & Destructor Documentation

◆ RLOFOpticalFlowParameter()

cv::optflow::RLOFOpticalFlowParameter::RLOFOpticalFlowParameter ( )
inline

Member Function Documentation

◆ create()

static Ptr<RLOFOpticalFlowParameter> cv::optflow::RLOFOpticalFlowParameter::create ( )
static
Python:
retval=cv.optflow.RLOFOpticalFlowParameter_create()

Creates instance of optflow::RLOFOpticalFlowParameter.

◆ getCrossSegmentationThreshold()

int cv::optflow::RLOFOpticalFlowParameter::getCrossSegmentationThreshold ( ) const
Python:
retval=cv.optflow_RLOFOpticalFlowParameter.getCrossSegmentationThreshold()

◆ getGlobalMotionRansacThreshold()

float cv::optflow::RLOFOpticalFlowParameter::getGlobalMotionRansacThreshold ( ) const
Python:
retval=cv.optflow_RLOFOpticalFlowParameter.getGlobalMotionRansacThreshold()

◆ getLargeWinSize()

int cv::optflow::RLOFOpticalFlowParameter::getLargeWinSize ( ) const
Python:
retval=cv.optflow_RLOFOpticalFlowParameter.getLargeWinSize()

◆ getMaxIteration()

int cv::optflow::RLOFOpticalFlowParameter::getMaxIteration ( ) const
Python:
retval=cv.optflow_RLOFOpticalFlowParameter.getMaxIteration()

◆ getMaxLevel()

int cv::optflow::RLOFOpticalFlowParameter::getMaxLevel ( ) const
Python:
retval=cv.optflow_RLOFOpticalFlowParameter.getMaxLevel()

◆ getMinEigenValue()

float cv::optflow::RLOFOpticalFlowParameter::getMinEigenValue ( ) const
Python:
retval=cv.optflow_RLOFOpticalFlowParameter.getMinEigenValue()

◆ getNormSigma0()

float cv::optflow::RLOFOpticalFlowParameter::getNormSigma0 ( ) const
Python:
retval=cv.optflow_RLOFOpticalFlowParameter.getNormSigma0()

◆ getNormSigma1()

float cv::optflow::RLOFOpticalFlowParameter::getNormSigma1 ( ) const
Python:
retval=cv.optflow_RLOFOpticalFlowParameter.getNormSigma1()

◆ getSmallWinSize()

int cv::optflow::RLOFOpticalFlowParameter::getSmallWinSize ( ) const
Python:
retval=cv.optflow_RLOFOpticalFlowParameter.getSmallWinSize()

◆ getSolverType()

SolverType cv::optflow::RLOFOpticalFlowParameter::getSolverType ( ) const
Python:
retval=cv.optflow_RLOFOpticalFlowParameter.getSolverType()

◆ getSupportRegionType()

SupportRegionType cv::optflow::RLOFOpticalFlowParameter::getSupportRegionType ( ) const
Python:
retval=cv.optflow_RLOFOpticalFlowParameter.getSupportRegionType()

◆ getUseGlobalMotionPrior()

bool cv::optflow::RLOFOpticalFlowParameter::getUseGlobalMotionPrior ( ) const
Python:
retval=cv.optflow_RLOFOpticalFlowParameter.getUseGlobalMotionPrior()

◆ getUseIlluminationModel()

bool cv::optflow::RLOFOpticalFlowParameter::getUseIlluminationModel ( ) const
Python:
retval=cv.optflow_RLOFOpticalFlowParameter.getUseIlluminationModel()

◆ getUseInitialFlow()

bool cv::optflow::RLOFOpticalFlowParameter::getUseInitialFlow ( ) const
Python:
retval=cv.optflow_RLOFOpticalFlowParameter.getUseInitialFlow()

◆ setCrossSegmentationThreshold()

void cv::optflow::RLOFOpticalFlowParameter::setCrossSegmentationThreshold ( int  val)
Python:
None=cv.optflow_RLOFOpticalFlowParameter.setCrossSegmentationThreshold(val)

◆ setGlobalMotionRansacThreshold()

void cv::optflow::RLOFOpticalFlowParameter::setGlobalMotionRansacThreshold ( float  val)
Python:
None=cv.optflow_RLOFOpticalFlowParameter.setGlobalMotionRansacThreshold(val)

◆ setLargeWinSize()

void cv::optflow::RLOFOpticalFlowParameter::setLargeWinSize ( int  val)
Python:
None=cv.optflow_RLOFOpticalFlowParameter.setLargeWinSize(val)

◆ setMaxIteration()

void cv::optflow::RLOFOpticalFlowParameter::setMaxIteration ( int  val)
Python:
None=cv.optflow_RLOFOpticalFlowParameter.setMaxIteration(val)

◆ setMaxLevel()

void cv::optflow::RLOFOpticalFlowParameter::setMaxLevel ( int  val)
Python:
None=cv.optflow_RLOFOpticalFlowParameter.setMaxLevel(val)

◆ setMinEigenValue()

void cv::optflow::RLOFOpticalFlowParameter::setMinEigenValue ( float  val)
Python:
None=cv.optflow_RLOFOpticalFlowParameter.setMinEigenValue(val)

◆ setNormSigma0()

void cv::optflow::RLOFOpticalFlowParameter::setNormSigma0 ( float  val)
Python:
None=cv.optflow_RLOFOpticalFlowParameter.setNormSigma0(val)

◆ setNormSigma1()

void cv::optflow::RLOFOpticalFlowParameter::setNormSigma1 ( float  val)
Python:
None=cv.optflow_RLOFOpticalFlowParameter.setNormSigma1(val)

◆ setSmallWinSize()

void cv::optflow::RLOFOpticalFlowParameter::setSmallWinSize ( int  val)
Python:
None=cv.optflow_RLOFOpticalFlowParameter.setSmallWinSize(val)

◆ setSolverType()

void cv::optflow::RLOFOpticalFlowParameter::setSolverType ( SolverType  val)
Python:
None=cv.optflow_RLOFOpticalFlowParameter.setSolverType(val)

◆ setSupportRegionType()

void cv::optflow::RLOFOpticalFlowParameter::setSupportRegionType ( SupportRegionType  val)
Python:
None=cv.optflow_RLOFOpticalFlowParameter.setSupportRegionType(val)

◆ setUseGlobalMotionPrior()

void cv::optflow::RLOFOpticalFlowParameter::setUseGlobalMotionPrior ( bool  val)
Python:
None=cv.optflow_RLOFOpticalFlowParameter.setUseGlobalMotionPrior(val)

◆ setUseIlluminationModel()

void cv::optflow::RLOFOpticalFlowParameter::setUseIlluminationModel ( bool  val)
Python:
None=cv.optflow_RLOFOpticalFlowParameter.setUseIlluminationModel(val)

◆ setUseInitialFlow()

void cv::optflow::RLOFOpticalFlowParameter::setUseInitialFlow ( bool  val)
Python:
None=cv.optflow_RLOFOpticalFlowParameter.setUseInitialFlow(val)

Member Data Documentation

◆ crossSegmentationThreshold

int cv::optflow::RLOFOpticalFlowParameter::crossSegmentationThreshold

Color similarity threshold used by cross-based segmentation following [204] . (Only used if supportRegionType is SR_CROSS). With the cross-bassed segmentation motion boundaries can be computed more accurately.

◆ globalMotionRansacThreshold

float cv::optflow::RLOFOpticalFlowParameter::globalMotionRansacThreshold

To apply the global motion prior motion vectors will be computed on a regulary sampled which are the basis for Homography estimation using RANSAC. The reprojection threshold is based on n-th percentil (given by this value [0 ... 100]) of the motion vectors magnitude. See [205] for more details.

◆ largeWinSize

int cv::optflow::RLOFOpticalFlowParameter::largeWinSize

Maximal window size of the support region. If supportRegionType is SR_FIXED this gives the exact support region size. The speed of the RLOF is related to the applied win sizes. The smaller the window size the lower is the runtime, but the more sensitive to noise is the method.

◆ maxIteration

int cv::optflow::RLOFOpticalFlowParameter::maxIteration

Number of maximal iterations used for the iterative refinement. Lower values can reduce the runtime but also the accuracy.

◆ maxLevel

int cv::optflow::RLOFOpticalFlowParameter::maxLevel

Maximal number of pyramid level used. The large this value is the more likely it is to obtain accurate solutions for long-range motions. The runtime is linear related to this parameter.

◆ minEigenValue

float cv::optflow::RLOFOpticalFlowParameter::minEigenValue

Threshold for the minimal eigenvalue of the gradient matrix defines when to abort the iterative refinement.

◆ normSigma0

float cv::optflow::RLOFOpticalFlowParameter::normSigma0

&sigma paramter of the shrinked Hampel norm introduced in [202]. If &sigma = std::numeric_limist<float>::max() the least-square estimator will be used instead of the M-estimator. Althoug M-estimator is more robust against outlier in the support region the least-square can be fast in computation.

◆ normSigma1

float cv::optflow::RLOFOpticalFlowParameter::normSigma1

&sigma paramter of the shrinked Hampel norm introduced in [202]. If &sigma = std::numeric_limist<float>::max() the least-square estimator will be used instead of the M-estimator. Althoug M-estimator is more robust against outlier in the support region the least-square can be fast in computation.

◆ smallWinSize

int cv::optflow::RLOFOpticalFlowParameter::smallWinSize

Minimal window size of the support region. This parameter is only used if supportRegionType is SR_CROSS.

◆ solverType

SolverType cv::optflow::RLOFOpticalFlowParameter::solverType

Variable specifies the iterative refinement strategy. Please consider citing [203] when using ST_BILINEAR.

◆ supportRegionType

SupportRegionType cv::optflow::RLOFOpticalFlowParameter::supportRegionType

Variable specifies the support region shape extraction or shrinking strategy.

◆ useGlobalMotionPrior

bool cv::optflow::RLOFOpticalFlowParameter::useGlobalMotionPrior

Use global motion prior initialisation has been introduced in [205] . It allows to be more accurate for long-range motion. The computational complexity is slightly increased by enabling the global motion prior initialisation.

◆ useIlluminationModel

bool cv::optflow::RLOFOpticalFlowParameter::useIlluminationModel

Use the Gennert and Negahdaripour illumination model instead of the intensity brigthness constraint. (proposed in [205] ) This model is defined as follow:

\[ I(\mathbf{x},t) + m \cdot I(\mathbf{x},t) + c = I(\mathbf{x},t+1) \]

and contains with m and c a multiplicative and additive term which makes the estimate more robust against illumination changes. The computational complexity is increased by enabling the illumination model.

◆ useInitialFlow

bool cv::optflow::RLOFOpticalFlowParameter::useInitialFlow

Use next point list as initial values. A good intialization can imporve the algortihm accuracy and reduce the runtime by a faster convergence of the iteration refinement.


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