Second Approach: Probabilistic Model
The objetive of this second approach is to evaluate the performance of a segmentation method where depth data is considered in GrabCut's energy function in analogous way to color. Here we propouse a seeding strategy based in depth data.
Energy Function Definition
The energy
function to be considered is,
where WC
represents
the Color Model and WD the Depth Model, both defined
as Gaussian Mixture Models.
The Data Term is
given by the expression,
|
where parameters
aC
and
aD
are control parameters for Color and Depth
Data.
Finally the
Smoothness Term is given by ,
|
|
where parameters
gC
and
gD
are control parameters for Color Smoothness and Depth
Smoothness.
Seeding
- Construct a
Background Depth Model from the pixels in the
border of the Selection Rectangle.
- Construct
a Foreground
Depth Model from the pixels in the interior of the Central
Rectangle, this is, the rectangle of sides 1/2 of the
Selection
Rectangle and located in its centre.
- Discard the
Gaussian components of the
Foreground Depth Model whose mean value have the highest probability
according to the Background Depth Model.
- Adjust the
participation coeficients of the remainig components of the Foreground
Depth Model to sum up to one.
- Evaluate all
pixels in the image respect to these models, and mark them as
Foreground Seeds or Background Seeds according to the obtain likelihood.
- From
the Foreground Seeds build the definite Foreground Depth and Color
Models. Do the same with the Background Seeds.
Results
Remarks
- Seeding was not accurate and consequently most of results were unsatisfactory.
- Try to build good models for depth data distribution from Gaussian Mixtures is a difficult task. You must deal with the fact that BG depth-variance is (in general) much larger than FG depth-variance.
- There is a lot of work to do in parameter calibration for the propoused energy function.