Paper Info
Title
Discriminating subsequent lane-crossing and driver-correction events using trajectory models of lateral slopes
Abstract
In this paper, we propose a new framework to discriminate the initial maneuver of lane-crossing event from driver-correction event, which is the primary reason for false warnings of the Lane Departure Prediction Systems. The proposed algorithm validates the beginning episode of the trajectory of driving signals whether it will cause a Lane Crossing Event or not, by employing driver behavior models of Directional Sequence of Piecewise Lateral Slopes (DSPLS) representing lane-crossing and driver-correction events. The framework utilizes only common driving signals, and allows adaptation scheme of driver behavior models to better represent individual driving characteristics. The experimental evaluation shows that the proposed DSPLS has detection error as low as 17% Equal Error Rate. Furthermore, the proposed algorithm reduces the False Alarm rate of the original Lane Departure Prediction System from 38.8% to 6.1% with less trade-off for the prediction accuracy.
Year
DOI
Venue
2009
10.1109/ICASSP.2009.4959848
ICASSP
Keywords
Field
DocType
subsequent lane-crossing,individual driving characteristic,prediction system,lane crossing event,common driving signal,driver behavior model,proposed algorithm,lateral slope,proposed dspls,driver-correction event,lane departure,original lane departure,trajectory model,accuracy,human factors,false alarm rate,predictive models,trajectory,data models
Data modeling,Computer science,Artificial intelligence,Vehicle safety,Trajectory,Piecewise,Prediction system,Pattern recognition,Simulation,Word error rate,Algorithm,Vehicle driving,Constant false alarm rate
Conference
ISSN
Citations 
PageRank 
1520-6149
0
0.34
References 
Authors
4
2
Name
Order
Citations
PageRank
Pongtep Angkititrakul117915.47
Ryuta Terashima2315.62