@device(postscript)
@libraryfile(Mathematics10)
@libraryfile(Accents)
@style(fontfamily=timesroman,fontscale=11)
@pagefooting(immediate, left "@c<Technical Report 1996>",
center "@c<Computer Science>",
right "@c<Carnegie Mellon>")
@heading(Characterizing Stereo Matching Problems
using Local Spatial Frequency)
@heading(CMU-CS-96-125)
@center(@b(Mark W. Maimone))
@center(May 1996 - Ph.D. Thesis)
@center(FTP: CMU-CS-96-125.ps.gz, CMU-CS-96-125A.ps.gz, CMU-CS-96-125B.ps.gz)
@blankspace(1)
@begin(text)

The model of local spatial frequency provides a powerful analytical tool
for image analysis.  In this thesis we explore the application of this
representation to long-standing problems in stereo vision.  As the basis
for this analysis, we develop a phase-based algorithm for stereo matching
that uses an adaptive scale selection process.  Our approach demonstrates
a novel solution to the phase-wraparound problem that has limited the
applicability of other phase-based methods.

The problem of ambiguous matches, or false targets, can greatly reduce the
accuracy of a stereo vision system.  A common approach to alleviating the
problem is the use of a coarse to fine refinement strategy, but we show that
this approach imposes some (perhaps overly) strong requirements on the
stereo images.  Our phase-based method relaxes those requirements, and is
therefore able to handle a wider variety of otherwise ambiguous images.  But
sometimes ambiguity is inherent in the images, so we propose a generalized
disparity model to explicitly represent multiple candidates.

Perspective foreshortening, an effect that occurs when a surface is viewed
at a sharp angle, can reduce the precision of stereo methods. Many methods
tacitly assume that the projection of an object will have the same area in
both images, but this condition is violated by perspective foreshortening.
We show how to overcome this problem using a local spatial frequency
representation.  A simple geometric analysis leads to an elegant solution in
the frequency domain which, when applied to our phase-based system,
increases the system's maximum matchable surface angle from 30 degrees to
over 75 degrees.

The analysis of stereo vision algorithms can be greatly enhanced through the
use of datasets with ground truth.  We outline a taxonomy of datasets
with ground truth that use varying degrees of realism to characterize
particular aspects of stereo vision systems, and show that each component
of this taxonomy can be effectively realized with current technology.  We
propose that datasets generated in this way be used as the foundation for a
suite of statistical analyses to effectively characterize the performance of
stereo vision systems.

@blankspace(2line)
@begin(transparent,size=10)
@b(Keywords:@ )@c<Computer vision, stereo matching, local spatial frequency,
Gabor filters, scalogram, phase-based stereo, scale space, perspective
foreshortening, ambiguous (false) matches, ground truth>
@end(transparent)
@blankspace(1line)
@end(text)
@flushright(@b[(203 pages)])