Title :
Driving skill recognition: New approaches and their comparison
Author_Institution :
GM R&D & Planning, Warren, MI, USA
Abstract :
Driving skill characterization is an important step towards future enhancement of vehicle adaptation control and active safety. This paper presents new approaches for driving skill recognition and their comparison. New feature extractors based on wavelet transform are developed to include temporal (spatial) information into discriminant features. The extractors are integrated with three classifiers for evaluation. Results show advantages of new approaches over existing approaches.
Keywords :
automated highways; feature extraction; pattern classification; road safety; road vehicles; wavelet transforms; active safety; discriminant features; driving skill recognition; spatial information; temporal information; vehicle adaptation control; wavelet transform; Data mining; Discrete Fourier transforms; Feature extraction; Fourier transforms; Frequency; Signal analysis; Testing; Vehicle safety; Wavelet transforms; Wheels;
Conference_Titel :
American Control Conference, 2009. ACC '09.
Conference_Location :
St. Louis, MO
Print_ISBN :
978-1-4244-4523-3
Electronic_ISBN :
0743-1619
DOI :
10.1109/ACC.2009.5160160
