39 0

Robust hypothesis generation method using binary blob analysis for multi-lane detection

Title
Robust hypothesis generation method using binary blob analysis for multi-lane detection
Author
신현철
Keywords
road traffic; driver information systems; computer vision; image classification; object detection; image filtering; multilane dataset; two-stage binary blob verification technique; two-stage binary blob filtering technique; inverse perspective mapping; vanishing point detection; improved lane hypothesis generation method; partial occlusions; possible low visibility-of-lanes; perspective effect; vehicle localisation; lane keeping; lane departure warning; advanced driver assistance systems; vision-based lane detection; multilane detection; reliable binary blob analysis; robust hypothesis generation method
Issue Date
2017-12
Publisher
INST ENGINEERING TECHNOLOGY-IET
Citation
IET IMAGE PROCESSING, v. 11, No. 12, Page. 1210-1218
Abstract
The vision-based lane detection is an important component of advanced driver assistance systems and it is essential for lane departure warning, lane keeping, and vehicle localisation. However, it is a challenging problem to improve the robustness of multi-lane detection due to factors, such as perspective effect, possible low visibility of lanes, and partial occlusions. To deal with these issues, the authors propose an improved lane hypothesis generation method using a reliable binary blob analysis. Most existing top-view based methods focused on the lane model fitting, but they neglected the reliability of hypothesis generation and the effectiveness in challenging conditions. To cope with these shortcomings, the authors carried out vanishing point detection and inverse perspective mapping to remove the perspective effect from the road images. Then two-stage binary blob filtering and blob verification techniques using classification are introduced to improve the robustness of lane hypothesis generation for lane detection. The experimental results show that the average detection accuracy on a new challenging multi-lane dataset is 97.7%. The performance of the proposed method outperforms that of the state-of-the-art method by 1.6% in detection accuracy on the Caltech lane benchmark dataset.
URI
https://digital-library.theiet.org/content/journals/10.1049/iet-ipr.2016.0506http://repository.hanyang.ac.kr/handle/20.500.11754/99219
ISSN
1751-9659; 1751-9667
DOI
10.1049/iet-ipr.2016.0506
Appears in Collections:
COLLEGE OF ENGINEERING SCIENCES[E](공학대학) > ELECTRICAL ENGINEERING(전자공학부) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE