Robust Lane Recognition Technique for Vision-Based Navigation with Multiple Detection Clues

Title
Robust Lane Recognition Technique for Vision-Based Navigation with Multiple Detection Clues
Authors
서승범강연식노치원강성철
Keywords
Lane Detection; Multiple Clues; Filtration Algorithm; Data Association; Extended Kalman Filter
Issue Date
2009-10
Publisher
URAI 2009
Abstract
Lane detection is crucial function in autonomous navigation. Vision system is the most popular sensing modality used in detection. However, there exist many formidable challenges for detecting the lane with vision system under poor or high illumination, shadows, and road markings. Especially mosaic shadow produced by high illumination and surrounding environments causes the false detection frequently. This paper proposes a novel method called filtration algorithm to detect the lane using multiple clues for threshold of all edge points based on the Bayesian rules. Data association is carried out for diminishing the false detection rate under extended Kalman filter (EKF).
URI
http://pubs.kist.re.kr/handle/201004/36206
Appears in Collections:
KIST Publication > Conference Paper
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