In this work, we present a new model for a dense disparity estimation
and the 3-D geometry reconstruction using a
color image stereo pair. First, we present a brief introduction to
the 3-D Geometry of a camera system. Next, we
propose a new model for the disparity estimation based on an energie
functional. We look for the local minima of
the energy using the associated Euler-Lagrange partial differential
equation. This model is a generalization to color
image of the model developed by L.Alvarez, R.Deriche, J.Sánchez
and J.Weickert in the paper Dense
Disparity Map
Estimation Respecting
Image Discontinuities with some changes in the strategy to avoid the
irrelevant local minima.
We present some numerical experiences of $3-D$ reconstruction, using
this method for some real stereo pairs.
For more details see the paper 3-D
Geometry reconstruction using a color image stereo pair and partial
differential equations
Next we present several experiments to illustrate the method
Figure 2. We present an stereo pair of the face of Julio Esclarín,
a member of the Comp.
Science Depart. at the University of Las Palmas, and 4 views of the
3-D reconstruction
using the proposed method. If you click
on
the image you will see a movie to
ilustrate the 3-D reconstruction.
Figure 3. We present an stereo pair of an outdoor scene of the laboratory
Instituto Universitario de
Ciencias y Tecnologías Cibernéticas de la Universidad
de Las Palmas de G.C., and 4 views of
the 3-D reconstruction using the proposed method. If you click
on
the image you will see a movie to
ilustrate the 3-D reconstruction.