Cv2CalcOpticalFlowFarneback Method

public static void CalcOpticalFlowFarneback(
	InputArray prev,
	InputArray next,
	InputOutputArray flow,
	double pyrScale,
	int levels,
	int winsize,
	int iterations,
	int polyN,
	double polySigma,
	OpticalFlowFlags flags
)

Public Shared Sub CalcOpticalFlowFarneback ( 
	prev As InputArray,
	next As InputArray,
	flow As InputOutputArray,
	pyrScale As Double,
	levels As Integer,
	winsize As Integer,
	iterations As Integer,
	polyN As Integer,
	polySigma As Double,
	flags As OpticalFlowFlags
)

public:
static void CalcOpticalFlowFarneback(
	InputArray^ prev, 
	InputArray^ next, 
	InputOutputArray^ flow, 
	double pyrScale, 
	int levels, 
	int winsize, 
	int iterations, 
	int polyN, 
	double polySigma, 
	OpticalFlowFlags flags
)

static member CalcOpticalFlowFarneback : 
        prev : InputArray * 
        next : InputArray * 
        flow : InputOutputArray * 
        pyrScale : float * 
        levels : int * 
        winsize : int * 
        iterations : int * 
        polyN : int * 
        polySigma : float * 
        flags : OpticalFlowFlags -> unit 

Parameters

prev

Type: OpenCvSharpInputArray
first 8-bit single-channel input image.

next

Type: OpenCvSharpInputArray
second input image of the same size and the same type as prev.

flow

Type: OpenCvSharpInputOutputArray
computed flow image that has the same size as prev and type CV_32FC2.

pyrScale

Type: SystemDouble
parameter, specifying the image scale (<1) to build pyramids for each image; pyrScale=0.5 means a classical pyramid, where each next layer is twice smaller than the previous one.

levels

Type: SystemInt32
number of pyramid layers including the initial image; levels=1 means that no extra layers are created and only the original images are used.

winsize

Type: SystemInt32
averaging window size; larger values increase the algorithm robustness to image noise and give more chances for fast motion detection, but yield more blurred motion field.

iterations

Type: SystemInt32
number of iterations the algorithm does at each pyramid level.

polyN

Type: SystemInt32
size of the pixel neighborhood used to find polynomial expansion in each pixel; larger values mean that the image will be approximated with smoother surfaces, yielding more robust algorithm and more blurred motion field, typically poly_n =5 or 7.

polySigma

Type: SystemDouble
standard deviation of the Gaussian that is used to smooth derivatives used as a basis for the polynomial expansion; for polyN=5, you can set polySigma=1.1, for polyN=7, a good value would be polySigma=1.5.

flags

Type: OpenCvSharpOpticalFlowFlags
operation flags that can be a combination of OPTFLOW_USE_INITIAL_FLOW and/or OPTFLOW_FARNEBACK_GAUSSIAN

Reference