I've
been pursuing the idea of creating an artificial vision "machine"
since 1986. Check CMU's
Virtualized Reality if
you are not from the field. I've had a lot of fun on many subjects but some
problems never left my mind: 3D reconstruction and "the
correspondence problem". Those are the problems I've shared
with my PhD students and people I had the previlege to collaborate with.
3D
Reconstruction
Multiple motion
segmentation for rigid and articulated moving objects
By tracking points in a video sequence with several objects moving,
points are grouped according to "rigidity".
The 3D
model of "Casa da Musica" is computed from point
coordinates in the images.
Main contributions:
- Uncalibrated
reconstruction (images obtained on google images).
- Very dissimilar images
- Visible are can be degenrate (planar). State
of the art brakes down.
Ricardo
Ferreira, João Xavier,
João Paulo Costeira,Reconstruction
of
Isometrically Deformable Flat Surfaces in 3D from Multiple Camera
Images, Proc. of ICASSP 2009 - IEEE International Conference
on
Acoustics, Speech, and Signal Processing, Taipei, Taiwan, 2009