Vision-based detection and classification of pavement mark using neural network for autonomous driving system

Author

Yoon, Yu-Bin ; Oh, Se-young

Author_Institution

Dept. of Electr. Eng., POSTECH, Pohang, South Korea

fYear

2011

fDate

23-26 Nov. 2011

Firstpage

806

Lastpage

810

Abstract

This paper proposes an algorithm for an autonomous driving system which detects a pavement mark in an image of the road in front of a vehicle and identifies the mark. The algorithm uses edge pairing to find a pavement mark then identifies the type using a neural network which uses the horizontal and vertical projection of the founded mark as input. The network successfully classified 1073 of 1088 images. The result can be used to provide the accurate position of the vehicle in in-vehicle navigation systems.

Keywords

computer vision; image classification; neural nets; object detection; roads; traffic engineering computing; autonomous driving system; edge pairing algorithm; horizontal projection; neural network; pavement mark; road image; vertical projection; vision based classification; vision based detection; Classification algorithms; Global Positioning System; Image edge detection; Roads; Support vector machine classification; Vectors; Vehicles; Autonomous driving; frontal image; horizontal projection; vertical projection;

fLanguage

English

Publisher

ieee

Conference_Titel

Ubiquitous Robots and Ambient Intelligence (URAI), 2011 8th International Conference on

Conference_Location

Incheon

Print_ISBN

978-1-4577-0722-3

Type

conf

DOI

10.1109/URAI.2011.6146026

Filename

6146026