Class RLOFOpticalFlowParameter

Stores and sets up the parameters of the robust local optical flow (RLOF) algorithm.

public class RLOFOpticalFlowParameter : CvPtrObject, IDisposable

Inherited Members: CvPtrObject.RawPtr

CvObject.IsDisposed

CvObject.ptr

CvObject.SetSafeHandle(OpenCvSafeHandle)

CvObject.SetPostReleaseAction(Action)

CvObject.Dispose()

CvObject.Dispose(bool)

CvObject.DisposeManaged()

CvObject.DisposeUnmanaged()

CvObject.ThrowIfDisposed()

CvObject.CvPtr

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Constructors

RLOFOpticalFlowParameter(): Creates a new set of RLOF parameters, initialized to the algorithm's defaults.

CrossSegmentationThreshold: Color similarity threshold used by cross-based segmentation. Only used if SupportRegionType is Cross.

GlobalMotionRansacThreshold: Reprojection threshold (n-th percentile of the motion vectors magnitude, [0 .. 100]) used by the RANSAC homography estimation for the global motion prior.

LargeWinSize: Maximal window size of the support region. If SupportRegionType is Fixed this gives the exact support region size.

MaxIteration: Number of maximal iterations used for the iterative refinement.

MinEigenValue: Threshold for the minimal eigenvalue of the gradient matrix, defining when to abort the iterative refinement.

NormSigma0: Sigma parameter of the shrunk Hampel norm. If set to float.MaxValue the least-square estimator is used instead of the M-estimator.

NormSigma1: Sigma parameter of the shrunk Hampel norm. If set to float.MaxValue the least-square estimator is used instead of the M-estimator.

SmallWinSize: Minimal window size of the support region. Only used if SupportRegionType is Cross.

UseGlobalMotionPrior: Use global motion prior initialization for the iterative refinement.

UseIlluminationModel: Use the Gennert and Negahdaripour illumination model instead of the intensity brightness constraint.

SetUseMEstimator(bool): Enables the M-estimator by setting the norm sigma parameters to (3.2, 7.0), or disables it (least-square estimator, faster but less robust against outliers in the support region).