A decision network based frame-work for visual off-road path detection problem

Author

Broggi, Alberto ; Caraffi, Claudio ; Cattani, Stefano ; Fedriga, Rean Isabella

Author_Institution

Dipt. di Ingegneria dell´´Informazione, Universita di Parma

fYear

2006

fDate

2006

Firstpage

951

Lastpage

956

Abstract

This paper describes a decision network based frame-work used for path-detection algorithm development in autonomous vehicle applications. Lane marker detection algorithms do not work in off-road environments. Off-road trails have too much complexity, with widely varying textures and many differing natural boundaries. The authors have developed a general approach. Images are segmented into regions, based on the homogeneity of some pixel properties and the resulting regions are classified as road or not-road by a decision network process. Combinations of contiguous clusters form the path surface, allowing any arbitrary path to be represented

Keywords

decision theory; image classification; image segmentation; mobile robots; object detection; path planning; vehicles; autonomous vehicle; decision network based framework; image classification; image segmentation; visual off-road path detection; Application software; Detection algorithms; Face detection; Machine vision; Marine vehicles; Mobile robots; Pixel; Remotely operated vehicles; Roads; Vehicle detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Transportation Systems Conference, 2006. ITSC '06. IEEE

Conference_Location

Toronto, Ont.

Print_ISBN

1-4244-0093-7

Electronic_ISBN

1-4244-0094-5

Type

conf

DOI

10.1109/ITSC.2006.1706867

Filename

1706867