Road recognition is of fundamental importance for many image understanding tasks involving cameras mounted on moving vehicles. In this paper we describe a variant of the well-known clothoid-based 3D road model and a novel algorithm for real-time estimation of its parameters. Extracted measures include road structure and host vehicle position relative to the road. The system is quantitatively and qualitatively tested on real world sequences acquired with the prototype vehicle developed for DIPLODOC pro ject.
Vision-based estimation of road parameters for intelligent vehicles
Zanin, Michele;
2006-01-01
Abstract
Road recognition is of fundamental importance for many image understanding tasks involving cameras mounted on moving vehicles. In this paper we describe a variant of the well-known clothoid-based 3D road model and a novel algorithm for real-time estimation of its parameters. Extracted measures include road structure and host vehicle position relative to the road. The system is quantitatively and qualitatively tested on real world sequences acquired with the prototype vehicle developed for DIPLODOC pro ject.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.
