The paper deals with the role of line features in self-localization, when an extended Kalman filter is adopted. First, a theoretical analysis is introduced, showing how the amount of range measurements contributing to lines extracted from 2D range data affects the localization accuracy. Second, a novel approach for line extraction, which takes the theoretical analysis into accountis considered. Experimental results are used to discuss the main properties of the system.
Learning to extract line features: beyond split and merge
MASTROGIOVANNI, FULVIO;SGORBISSA, ANTONIO;ZACCARIA, RENATO UGO RAFFAELE
2008-01-01
Abstract
The paper deals with the role of line features in self-localization, when an extended Kalman filter is adopted. First, a theoretical analysis is introduced, showing how the amount of range measurements contributing to lines extracted from 2D range data affects the localization accuracy. Second, a novel approach for line extraction, which takes the theoretical analysis into accountis considered. Experimental results are used to discuss the main properties of the system.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.