Paper available: Neural Model of Visual Stereomatching

[Jonathan Marshall]

Paper available in http://www.cs.unc.edu/Research/brainlab/index.html


                 "NEURAL MODEL OF VISUAL STEREOMATCHING:
                      SLANT, TRANSPARENCY, AND CLOUDS"


     JONATHAN A. MARSHALL,  GEORGE J. KALARICKAL,  ELIZABETH B. GRAVES
                                      
          Department of Computer Science, CB 3175, Sitterson Hall
      University of North Carolina, Chapel Hill, NC 27599-3175, U.S.A.
         marshall at cs.unc.edu, +1-919-962-1887, fax +1-919-962-1799


Stereomatching of oblique and transparent surfaces is described using a
model of cortical binocular "tuned" neurons selective for disparities of
individual visual features and neurons selective for the position, depth,
and 3-D orientation of local surface patches. The model is based on a simple
set of learning rules.  In the model, monocular neurons project excitatory
connection pathways to binocular neurons at appropriate disparities.
Binocular neurons project excitatory connection pathways to appropriately
tuned "surface patch" neurons. The surface patch neurons project reciprocal
excitatory connection pathways to the binocular neurons.  Anisotropic
intralayer inhibitory connection pathways project between neurons with
overlapping receptive fields.  The model's responses to simulated stereo
image pairs depicting a variety of oblique surfaces and transparently
overlaid surfaces are presented.  For all the surfaces, the model
(1) assigns disparity matches and surface patch representations based on
global surface coherence and uniqueness, (2) permits coactivation of neurons
representing multiple disparities within the same image location,
(3) represents oblique slanted and tilted surfaces directly, rather than
approximating them with a series of frontoparallel steps, (4) assigns
disparities to a cloud of points at random depths, like human observers, and
unlike Prazdny's (1985) method, and (5) causes globally consistent matches
to override greedy local matches.  The model represents transparency, unlike
the Marr and Poggio (1976) model, and it assigns unique disparities, unlike
Prazdny's (1985) model.


In press, to appear in Network: Computation in Neural Systems, 11/96.