|
abstract
For recovering precise object boundaries
in area-based stereo matching,
there are two problems.
One is the so-called ``occlusion problem''.
This can be avoided if we can select only ``visible'' cameras
among many cameras used.
Another one
is the problem called ``boundary overreach'',
i.e. the recovered object boundary turns out to be wrongly located
away from the real one
due to the window's coverage beyond a boundary.
This is especially harmful to segmenting objects using depth information.
A few approaches have been proposed to solve this problem.
However, these techniques tend to degrade on smooth surfaces.
That is,
there seems to be a trade-off problem
between recovering precise object edges
and obtaining smooth surfaces.
In this paper,
we propose a new simple method to solve these problems.
Using multiple stereo pairs and multiple windowing,
our method detects the region where the boundary overreach is likely to occur
(let us call it ``BO region'')
and adopts appropriate methods for the BO and non-BO regions.
Although the proposed method is quite simple,
the experimental results have shown that it is very
effective at recovering both sharp object edges at their correct locations
and smooth object surfaces.
We also present a sound analysis of the boundary overreach
which has not been clearly explained in the past.
|
(mpeg 660K)