| CvOptFlowCalcOpticalFlowSparseToDense Method |
Fast dense optical flow based on PyrLK sparse matches interpolation.
Namespace:
OpenCvSharp.OptFlow
Assembly:
OpenCvSharp (in OpenCvSharp.dll) Version: 1.0.0
Syntax public static void CalcOpticalFlowSparseToDense(
InputArray from,
InputArray to,
OutputArray flow,
int gridStep = 8,
int k = 128,
float sigma = 0.05f,
bool usePostProc = true,
float fgsLambda = 500f,
float fgsSigma = 1.5f
)
Public Shared Sub CalcOpticalFlowSparseToDense (
from As InputArray,
to As InputArray,
flow As OutputArray,
Optional gridStep As Integer = 8,
Optional k As Integer = 128,
Optional sigma As Single = 0.05F,
Optional usePostProc As Boolean = true,
Optional fgsLambda As Single = 500F,
Optional fgsSigma As Single = 1.5F
)
public:
static void CalcOpticalFlowSparseToDense(
InputArray^ from,
InputArray^ to,
OutputArray^ flow,
int gridStep = 8,
int k = 128,
float sigma = 0.05f,
bool usePostProc = true,
float fgsLambda = 500f,
float fgsSigma = 1.5f
)
static member CalcOpticalFlowSparseToDense :
from : InputArray *
to : InputArray *
flow : OutputArray *
?gridStep : int *
?k : int *
?sigma : float32 *
?usePostProc : bool *
?fgsLambda : float32 *
?fgsSigma : float32
(* Defaults:
let _gridStep = defaultArg gridStep 8
let _k = defaultArg k 128
let _sigma = defaultArg sigma 0.05f
let _usePostProc = defaultArg usePostProc true
let _fgsLambda = defaultArg fgsLambda 500f
let _fgsSigma = defaultArg fgsSigma 1.5f
*)
-> unit
Parameters
- from
- Type: OpenCvSharpInputArray
first 8-bit 3-channel or 1-channel image. - to
- Type: OpenCvSharpInputArray
second 8-bit 3-channel or 1-channel image of the same size as from - flow
- Type: OpenCvSharpOutputArray
computed flow image that has the same size as from and CV_32FC2 type - gridStep (Optional)
- Type: SystemInt32
stride used in sparse match computation. Lower values usually
result in higher quality but slow down the algorithm. - k (Optional)
- Type: SystemInt32
number of nearest-neighbor matches considered, when fitting a locally affine
model. Lower values can make the algorithm noticeably faster at the cost of some quality degradation. - sigma (Optional)
- Type: SystemSingle
parameter defining how fast the weights decrease in the locally-weighted affine
fitting. Higher values can help preserve fine details, lower values can help to get rid of the noise in the output flow. - usePostProc (Optional)
- Type: SystemBoolean
defines whether the ximgproc::fastGlobalSmootherFilter() is used for post-processing after interpolation - fgsLambda (Optional)
- Type: SystemSingle
see the respective parameter of the ximgproc::fastGlobalSmootherFilter() - fgsSigma (Optional)
- Type: SystemSingle
see the respective parameter of the ximgproc::fastGlobalSmootherFilter()
See Also