Estimating
egomotion in a 3D cluttered scene
In our optical snow research, we showed how to estimate motion parallax
in cluttered 3D scenes. Such estimates are useful for solving for
egomotion, namely the instantaneous 3D camera motion.
Previous techniques for computing have assumed that one can reliably
estimate pointwise image velocities. Unfortunately, this
assumption is dubious in cluttered scenes, since occlusion boundaries
and spurious features such T-junctions are dense and classical optical
flow methods do not perform well in these conditions. We
developed an alternative method estimating local motion parallax
directly from image intensities (see optical
snow), which avoids these prior pointwise estimates, and shown how
to combine these local estimates to estimate the observer's egomotion.
Selected Publications
- Spectral estimation of
motion parallax and application to egomotion, R. Mann and
M.S. Langer, Journal of the Optical Society of America A. 22(9)
1717-1731, 2005. (PDF)
- Estimating camera motion
through a 3D cluttered scene, R. Mann and M. S.
Langer. Canadian Conf. on Computer and Robot
Vision. London, Canada. pp. 472-479.
2004
(PDF) BEST PAPER AWARD