Thursday, May 6th, 14.30.
Nick Barnes, National ICT, Australia.
Title
The space variant Hough Transform and some other recent biologically
inspired research.
Abstract
For space variant sensors the volume of world space that projects onto a single
sensing element varies significantly with its spatial position in the sensing
array. This includes the log-polar sensor, and central catadioptric cameras. In
this talk, we consider the Hough transform for space variant sensors. We show
that for real discrete images the voting equation must be modified to allow for
the fact that a larger sub-space of parallel world planes can intersect with a
larger sensing element than with a smaller one. We derive a voting algorithm for
the space variant Hough Transform. We demonstrate experimentally that for the
standard Hough transform, lines that cover the majority of the sensor do not
register a significantly larger vote count than shorter lines, while they are
gain full support in the space variant transform. Further, in real images we
show that this can lead to poor definition of peaks, while similar peaks are
well defined in the space variant Hough transform. Along the way we also show
that the Hough transform for the log-polar sensor is extremely computationally
efficient. The talk will also give an overview of other recent research in
insect-like behaviours, local shape detectors, and colour constancy.
Nick Barnes is a researcher at the National ICT Australia in the Autonomous Systems and Sensing Techologies Programme, and an Ajunct researcher at The Australian National University.