Sciweavers

Share
ICCV
2007
IEEE

Perspectively Invariant Normal Features

9 years 7 months ago
Perspectively Invariant Normal Features
We extend the successful 2D robust feature concept into the third dimension in that we produce a descriptor for a reconstructed 3D surface region. The descriptor is perspectively invariant if the region can locally be approximated well by a plane. We exploit depth and texture information, which is nowadays available in real-time from video of moving cameras, from stereo systems or PMD cameras (photonic mixer devices [19]). By computing a normal view onto the surface we still keep the descriptiveness of similarity invariant features like SIFT[11] while achieving invariance against perspective distortions, while descriptiveness typically suffers when using affine invariant features. Our approach can be exploited for structure-from-motion, for stereo or PMD cameras, alignment of large scale reconstructions or improved video registration.
Kevin Köser, Reinhard Koch
Added 14 Oct 2009
Updated 30 Oct 2009
Type Conference
Year 2007
Where ICCV
Authors Kevin Köser, Reinhard Koch
Comments (0)
books