flowPapenberg.zip
also uses two frames from the Yosemite Sequence.
The workflow here uses the same local weighting approach
as in [Sun2008Learning].
But instead using a mixture of gaussian model, it
uses the charbonnier functions as proposed by
[Papenberg2006].
The used energy functional looks as follows:
where
After execution, the result is visualized using the
ArgosDisplay module.
In the two tabs, the flow estimation result and the ground truth
are shown.