In order to detect drivers under the influence of substances such as alcohol or drugs, police officers use a standardized set of tests such as the Horizontal Gaze Nystagmus (HGN) test, the eye convergence test and the pupil's reaction to light test. These tests are part of the more complete Drug Recognition Expert (DRE) procedures and are essentially applied to the eyes of a driver. These procedures are performed manually by law enforcement officers. The present work describes a video-based image processing system implementing the HGN test, the convergence test and the pupil's dark room examinations test. This system generates visual stimuli and captures video sequences of the eyes following and reacting to these visual stimuli. The video sequences are processed and analyzed using feature extraction techniques. In the present study, the video-based image processing system is used to detect alcohol related intoxication. This system was tested in an experiment involving 32 subjects dosed to a blood alcohol concentration (BAC) in the interval of 0.04% to 0.22%. In order to demonstrate the effects of alcohol on eye signs comparisons are made between pre-dose and post-dose BAC.
[1]
M. Burns,et al.
PSYCHOPHYSICAL TESTS FOR DWI ARREST
,
1977
.
[2]
Seiichiro Kagei,et al.
A Hough Based Eye Direction Detection Algorithm without On-site Calibration
,
2003,
DICTA.
[3]
B. Ball,et al.
Nystagmus testing in intoxicated individuals.
,
2003,
Optometry.
[4]
M. Burns,et al.
DEVELOPMENT AND FIELD TEST OF PSYCHOPHYSICAL TESTS FOR DWI ARREST
,
1981
.
[5]
D. V. D. Reyden.
Design and Analysis of Soil Insecticide Field Experiments
,
1954
.
[6]
Ioannis Pitas,et al.
Facial feature extraction and pose determination
,
2000,
Pattern Recognit..