COMPARISON OF GLOBAL-APPEARANCE TECHNIQUES APPLIED TO VISUAL MAP BUILDING AND LOCALIZATION
F. Amorós, L. Payá, O. Reinoso and L.M. Jiménez
VISAPP 2012, International Conference on Computer Vision Theory and Applications  (Rome, Italy. 24-26 February, 2012)
Ed. SciTePress – Science and Technology Publications  ISBN:978-989-8565-04-4  - Volume 2, pp. 395-398

Abstract:

Techniques based on the global appearance of visual information have proved to be a robust alternative in the field of robotic mapping and localization. However, they present some critical issues that must be studied when trying to build an application that works in real time. In this paper, we review and compare several methods to build a global descriptor of panoramic scenes and we study the critical parameters that make their applicable or not in real mapping and localizations tasks, such as invariance against rotations, computational costs and accuracy in robot localization. All the experiments have been carried out with omnidirectional images captured in a real environment under realistic lighting conditions.