Probabilistic fusion of rural road course estimations

Author

Schule, Florian ; Koch, Christian ; Hartmann, Oliver ; Schweiger, Roland ; Dietmayer, Klaus

Author_Institution

Inst. of Meas., Control, & Microtechnol., Univ. of Ulm, Ulm, Germany

fYear

2013

fDate

6-9 Oct. 2013

Firstpage

1701

Lastpage

1706

Abstract

This paper presents an advanced road course prediction algorithm focusing on longer distances. It shows how to simply combine the different sensors available in modern cars for a road course estimation task. Concretely, a digital-map-based estimation is fused with an optical lane recognition system. Both sensors are evaluated on a representative subset of test sequences to characterize their measurement uncertainties. Then a Bayesian fusion system combines the advantages of the single sensors. Extensive evaluations with high precision ground truth data demonstrate the feasibility of this approach.

Keywords

Bayes methods; image fusion; object recognition; roads; traffic engineering computing; Bayesian fusion system; advanced road course prediction algorithm; digital-map-based estimation; high precision ground truth data; optical lane recognition system; probabilistic fusion; road course estimation task; rural road course estimations; single sensors; Approximation methods; Cameras; Computational modeling; Estimation; Roads; Sensors; Vehicles;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Transportation Systems - (ITSC), 2013 16th International IEEE Conference on

Conference_Location

The Hague

Type

conf

DOI

10.1109/ITSC.2013.6728474

Filename

6728474