Matjaž Jogan and Aleš Leonardis (2000) Robust localization using the eigenspace of spinning-images. In: IEEE Workshop on Omnidirectional Vision, Hilton Head Island, South Carolina.
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 view-based localization. In this paper we discuss several approaches that have been taken and evaluate them from different points-of-view, in particular, we argue that most of them are not suitable for robust localization under partially occluded views. Thus, we propose 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.
|Item Type: ||Conference or Workshop Item (Paper)|
|Keywords: ||mobile robot localization, omnidirectional vision, eigenspace, visual learning and recognition|
|Language of Content: ||English|
|Institution: ||University of Ljubljana|
|Department: ||Faculty of Computer and Information Science|
|Divisions: ||Faculty of Computer and Information Science > Computer Vision Laboratory|
|Item ID: ||48|
|Date Deposited: ||28 Feb 2003|
|Last Modified: ||13 Aug 2011 00:31|
Actions (login required)