|
" Development and Demonstration of a Cost Effective in-Vehicle Lane Departure and Advanced Curve Speed Warning System "
Faizan, Muhammad
Hayee, Imran
| Document Type
|
:
|
Latin Dissertation
|
| Language of Document
|
:
|
English
|
| Record Number
|
:
|
1104299
|
| Doc. No
|
:
|
TLpq2215571105
|
| Main Entry
|
:
|
Faizan, Muhammad
|
|
|
:
|
Hayee, Imran
|
| Title & Author
|
:
|
Development and Demonstration of a Cost Effective in-Vehicle Lane Departure and Advanced Curve Speed Warning System\ Faizan, MuhammadHayee, Imran
|
| College
|
:
|
University of Minnesota
|
| Date
|
:
|
2019
|
| student score
|
:
|
2019
|
| Degree
|
:
|
M.S.E.E.
|
| Page No
|
:
|
53
|
| Abstract
|
:
|
A lane departure warning system (LDWS) and advance curve warning system (ACWS) are critical elements among several Advanced Driver-Assistance Systems (ADAS) functions, which has significant potential to reduce crashes. Generally, LDWS use different image processing or optical scanning techniques to detect a lane departure. In case of LDWS, these systems have some limitations such as harsh weather or irregular lane markings can influence their performance. Other LDWS use GPS receiver with access to lane-level resolution digital maps to system's efficiency but make the overall system more complex and expensive. On the other hand, ADWS use road-level information which includes road curvature, speed-limit, position. etc. of a given curve. In this report, a lane detection method is proposed which uses a standard GPS receiver to determines the lateral shift of a vehicle by comparing a vehicle’s trajectory to the reference road direction without any lane-level but a road-level information from a standard digital mapping database. Furthermore, system estimates the road curvature and provides advisory speed-limit of a given curve simultaneously. The field test results show that the proposed system can detect a true lane departure with an accuracy of almost 100%. Although no true lane departure was left undetected, occasional false lane departures were detected about 10% of the time when the vehicle did not actually depart its lane. Furthermore, system always issue the curve warning about an advisory speed limit well ahead of time at a safe distance.
|
| Subject
|
:
|
Computer science
|
|
|
:
|
Electrical engineering
|
| |