Robust Localization Using Eigenspace of Spinning-Images

			    Ales Leonardis

		       University of Ljubljana

Under in-plane rotations of a panoramic camera, the information
content of a panoramic image is, in general, preserved. However,
different representations that can be derived have important
implications on further processing, e.g.~for appearance-based
localization.  I will discuss several approaches based on different
representations that have been proposed and evaluate them from
different points-of-view, in particular, I will argue that most of
them are not suitable for robust localization under partially occluded
views. Then I will propose to use a representation---eigenspace of
spinning-images---which enables a straightforward application of the
robust estimation of eigenimage coefficients which is directly related
to the localization.