Fast dense optical flow based on PyrLK sparse matches interpolation

flow = cv.calcOpticalFlowSparseToDense(from, to)
flow = cv.calcOpticalFlowSparseToDense(from, to, 'OptionName',optionValue, ...)

Input

• from first 8-bit 3-channel or 1-channel image.
• to second 8-bit 3-channel or 1-channel image of the same size as from.

Output

• flow computed flow image that has the same size as from and type single (2-channels). Flow for (x,y) is stored in the third dimension.

Options

• GridStep stride used in sparse match computation. Lower values usually result in higher quality but slow down the algorithm. default 8
• K 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. default 128
• Sigma 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. default 0.05
• UsePostProcessing defines whether the cv.fastGlobalSmootherFilter is used for post-processing after interpolation. default true
• FGSLambda see the respective parameter of cv.fastGlobalSmootherFilter, default 500.0
• FGSSigma see the respective parameter of cv.fastGlobalSmootherFilter, default 1.5