DocumentCode
3014143
Title
Physical road marker property estimation using monoscopic vision
Author
Gumpp, Thomas ; Nienhüser, Dennis ; Zöllner, J. Marius
Author_Institution
Intell. Syst. & Production Eng., FZI Forschungszentrum Inf., Karlsruhe, Germany
fYear
2010
fDate
3-7 May 2010
Firstpage
1022
Lastpage
1027
Abstract
In this paper algorithms are presented to extract lane markers and their properties from monoscopic camera images. A filter approach that takes into account the visual appearance of the markers is presented. Another contribution constitutes the measurement of physical marker width and length from perspectively distorted images using only the calibrated camera images. Also distances between markers can be estimated. All algorithms are independent from a specific lane model.
Keywords
Kalman filters; computer vision; feature extraction; particle filtering (numerical methods); road traffic; traffic engineering computing; filter approach; lane marker extraction; monoscopic camera images; monoscopic vision; perspectively distorted images; physical road marker property; property estimation; Cameras; Data mining; Filters; Intelligent systems; Length measurement; Navigation; Remotely operated vehicles; Road vehicles; Vehicle driving; Vehicle safety;
fLanguage
English
Publisher
ieee
Conference_Titel
Robotics and Automation (ICRA), 2010 IEEE International Conference on
Conference_Location
Anchorage, AK
ISSN
1050-4729
Print_ISBN
978-1-4244-5038-1
Electronic_ISBN
1050-4729
Type
conf
DOI
10.1109/ROBOT.2010.5509286
Filename
5509286
Link To Document