A Lane Identifying Approach of the Intelligent Vehicle in Complex Condition: Intelligent Vehicle in Complex Condition

A Lane Identifying Approach of the Intelligent Vehicle in Complex Condition: Intelligent Vehicle in Complex Condition

Botao Wu (Hebei Institute of Machinery and Electricity, Hebei, China) and Huijuan Wang (North China Institute of Aerospace Engineering, Langfang, China)
Copyright: © 2019 |Pages: 20
DOI: 10.4018/IJACI.2019100102

Abstract

Lane identification by intelligent vehicles in some common complicated conditions is a key technique. The parabola model of lane boundary is established first for fitting the curved lane boundary, and the objective function is used to estimate the fitting quality of the lane boundary is designed with the grayness character and grads character of the lane boundary in a gray image. To improve the speed of the identifying algorithm, the ant colony algorithm is applied to lane identifying, and with the guidance of the designed objective function, the positive feedback of hormone will consistently allow the search the best path within the searching region of interest as soon as possible, thus, the lane boundary is found. The method can effectively eliminate the negative effect of illumination conditions or shadows of trees, etc., and identify linear or curving lane boundaries exactly. The pretreatment to image is found and the searching region of interest is set, so the real-time identifying is greatly improved.
Article Preview
Top

Introduction

Background

It is significant for the navigation of intelligent vehicles to identify the lane boundaries accurately. The complexity of actual circumstance demands the navigation system be characterized by well adjustability in identifying lane. For example, in sunshine brightly, in dark, in rain or there are shadow of trees and buildings on the road surface, etc. These actual circumstances ask for greater capability in identifying lane.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 11: 4 Issues (2020): 1 Released, 3 Forthcoming
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 2 Issues (2016)
Volume 6: 2 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing