Sensor Fusion-Based Line Detection for Unmanned Navigation

Title
Sensor Fusion-Based Line Detection for Unmanned Navigation
Authors
전창묵서승범노치원강연식강성철
Keywords
Sensor Fusion; Vision; Laser Range Finder; Line Detection; Filtration Algorithm; Extended Kalman Filter
Issue Date
2010-06
Publisher
IEEE Intelligent Vehicles Symposium (IV) 2010
Abstract
We propose an algorithm of reliable detection of line for unmanned navigation of mobile robots using sensor fusion. To detect the distance and the angle between the robot and the line, we use a vision sensor system and a laser range finder (LRF). Each sensor system runs its own extended Kalman filter (EKF) to estimate the distance and orientation of the line. The vision system processes images being captured using well-known edge detection algorithms, and the LRF detects the line using the measurement of the intensity of the laser beam reflected. However, depending on the condition of the road and ambient light, each sensor gives us wrong measurement of the line or sometimes completely fails to detect it. To resolve such uncertainty, we develop a simple and easy-to-implement sensor fusion algorithm that uses weighted sum of the output of each EKF, and it gives us more reliable estimate of the distance and orientation of the line than each measurement/estimator system.
URI
http://pubs.kist.re.kr/handle/201004/38592
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