Calculate an optical flow using "SimpleFlow" algorithm

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

Input

• from First 8-bit 3-channel image.
• to Second 8-bit 3-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

• Layers Number of layers. default 3
• AveragingBlockSize Size of block through which we sum up when calculate cost function for pixel. default 2
• MaxFlow maximal flow that we search at each level. default 4
• SigmaDist vector smooth spatial sigma parameter. default 4.1
• SigmaColor vector smooth color sigma parameter. default 25.5
• PostprocessWindow window size for postprocess cross bilateral filter. default 18
• SigmaDistFix spatial sigma for postprocess cross bilateralf filter. default 55.0
• SigmaColorFix color sigma for postprocess cross bilateral filter. default 25.5
• OccThr threshold for detecting occlusions. default 0.35
• UpscaleAveragingRadius window size for bilateral upscale operation. default 18
• UpscaleSigmaDist spatial sigma for bilateral upscale operation. default 55.0
• UpscaleSigmaColor color sigma for bilateral upscale operation. default 25.5
• SpeedUpThr threshold to detect point with irregular flow - where flow should be recalculated after upscale. default 10

See [Tao2012]. And site of project: http://graphics.berkeley.edu/papers/Tao-SAN-2012-05/.

References

[Tao2012]:

Michael Tao, Jiamin Bai, Pushmeet Kohli, and Sylvain Paris. "Simpleflow: A non-iterative, sublinear optical flow algorithm". In Computer Graphics Forum, volume 31, pages 345-353. Wiley Online Library, 2012.