Abstract: Recovering the 3D
structure from 2D
images is a problem
dating back to the
1960s. It's only
recently, with the
advancement of
computing
technology, that
there has been
substantial progress
in solving this
problem. In this
thesis, we focus on
one such method for
recovering scene
structure given only
a single image. This
method works using
supervised learning
techniques and a
multiple-
segmentation
framework for adding
contextual
information to the
inference. We
evaluate the effect of
this added
contextual
information. We do
this by excluding this
additional
information to
measure system
performance. We
then go on to
evaluate the effect of
the other system
components that
remain which include
classifiers and image
features. For
example, in the case
of classifiers, we
substitute the
original with others
to see the level of
accuracy that these
provide. In the case
of the features, we
conduct experiments
that give us the most
important features
that contribute to
classification
accuracy. All of this
put together lets us
evaluate the effect of
adding contextual
information to the
learning process and
if it can be improved
by improving the
other non-contextual
components of the
system.

Adviser: Ross Beveridge
Co-Adviser: N/A
Non-ECE Member: Bruce Draper, Computer Science
Member 3: J. Rockey Luo
Addional Members: N/A

Publications:
N/A

Program of Study:
ECE561
CS410
GRAD511
CS420
CS510
CS556
CS575
ECE699