Naslov
A Framework for Scalable Vision-Only Navigation

Autori
Šegvić, Siniša ; Remazeilles, Anthony ; Diosi, Albert ; Chaumette, François

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Advanced Concepts for Intelligent Vision Systems, LNCS, ISSN 0302-9743, vol.4678 / Jacques Blanc-Talon, Wilfried Philips, Dan Popescu, Paul Scheunders - Berlin : Springer, 2007, 1-12

ISBN
X

Skup
Advanced Concepts for Intelligent Vision Systems

Mjesto i datum
Delft, Nizozemska, 28.08.2007. - 31.08.2007

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Autonomous navigation

Sažetak
Abstract. This paper presents a monocular vision framework enabling feature-oriented appearance-based navigation in large outdoor environ- ments containing other moving objects. The framework is based on a hybrid topological-geometrical environment representation, constructed from a learning sequence acquired during a robot motion under hu- man control. The framework achieves the desired navigation functional- ity without requiring a global geometrical consistency of the underlying environment representation. The main advantages with respect to con- ventional alternatives are unlimited scalability, real-time mapping and effortless dealing with interconnected environments once the loops have been properly detected. The framework has been validated in demanding, cluttered and interconnected environments, under different imaging con- ditions. The experiments have been performed on many long sequences acquired from moving cars, as well as in real-time large-scale navigation trials relying exclusively on a single perspective camera. The obtained results imply that a globally consistent geometric environment model is not mandatory for successful vision-based outdoor navigation.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA