Open AccessRoad Tracking Method Suitable for Both Unstructured and Structured Roads
Author(s) -
Zdeněk Procházka
Publication year - 2013
Publication title -
international journal of advanced robotic systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.394
H-Index - 46
eISSN - 1729-8814
pISSN - 1729-8806
DOI - 10.5772/55015
Subject(s) - computer science , computer vision , artificial intelligence , tracking (education) , segmentation , monocular , range (aeronautics) , road surface , psychology , pedagogy , materials science , composite material
This paper deals with a problem of road tracking and vehicle positioning based on sequential images captured by a vehicle mounted monocular colour camera. The paper presents a new region-based road tracking method, which is suitable for both structured and unstructured roads. The proposed method is based on our original road segmentation algorithm and estimates road model parameters from measurements obtained by analysis of segmented road region. Although the proposed method is tested over a limited range, evaluation on real image sequences shows promising results for various types of road