Active Fixation for Scene Exploration
Kjell Brunnström, Jan-Olof Eklundh and Tomas Uhlin
To appear in International Journal of Computer Vision
(Original version March 1993; Revised version February 1994)
Abstract
It is well-known that active selection of fixation points in
humans is highly context and task dependent. It is therefore likely
that successful computational processes for fixation in active vision
should be so too. We are considering active fixation in the context of
recognition of man-made objects characterized by their shapes. In
this situation the qualitative shape and type of observed junctions
play an important role.
The fixatnada are driCVAP/ven by a grouping strategy, which forms sets of
connected junctions separated from the surrounding at depth
discontinuities.
We have, furthermore, developed a methodology for rapid
active detection and classification of junctions by selection of
fixation points. The approach is based on direct computations from
image data and allows integration of stereo and accommodation cues with
luminance information. This work form a part of an effort to perform
active recognition of generic objects, in the spirit of Malik and
Biederman, but on real imagery rather than on line-drawings.
Full paper:
PostScript 3.4M
Kjell Brunnström
<kjellb@bion.kth.se>
Jan-Olof Eklundh
<joe@bion.kth.se>
Tomas Uhlin
<tomas@bion.kth.se>