This example is typical for a fluoroscopic bi-transparency: it stands for a part of the heart, which superimposes
to the ribs.
The lungs are also present, but their motion appears to be united to the one of the heart under this angulation of
imaging.
The estimated displacements are directed toward the past to respect the notations of the Transparent Motion Constraint.
As a result they are in the opposite direction compared to the usual represented velocity direction.
Estimation result at four interesting time instants
We report satisfactory results on the four presented images. The motion of the background is correctly computed as being static
(the corresponding motion field is not plotted when it is exactly 0), and the motions of the heart walls match the
observation.
Whole processed sequence
We also present the overall processed sequence. It shows the estimated affine motion fields, along with the corresponding
frames.
The results are satisfactory since we are dealing with a very noisy image sequence. Let us point out that no
temporal regularization is performed.
|
|