Parametric Eigenspace Representations of Panoramic Images
ICAR 2001 -- Omnidirectional Vision Applied to Robotic Orientation and Nondestructive Testing (NDT), IEEE Computer Society, 2001
This paper describes a novel approach for robot localization using a view-based representation with panoramic images. We propose to use a representation based on a complex basis of eigenvectors. We demonstrate that this results in a speed up of building the eigenspace and in a fast and accurate localization.