Analysis of Driver Point of Regard Determinations with Eye-Gesture Templates Using Receiver Operating Characteristic

An Advance Driver Assistance System (ADAS) is a computer system on board a vehicle which is used to reduce the risk of vehicular accidents by monitoring factors relating to the driver, vehicle and environment and taking some action when a risk is identified. Much work has been done on assessing vehicle and environmental state but there is still comparatively little published work that tackles the problem of driver state. Visual attention is one such driver state. In fact, some researchers claim that lack of attention is the main cause of accidents as factors such as fatigue, alcohol or drug use, distraction and speeding all impair the driver-s capacity to pay attention to the vehicle and road conditions [1]. This seems to imply that the main cause of accidents is inappropriate driver behaviour in cases where the driver is not giving full attention while driving. The work presented in this paper proposes an ADAS system which uses an image based template matching algorithm to detect if a driver is failing to observe particular windscreen cells. This is achieved by dividing the windscreen into 24 uniform cells (4 rows of 6 columns) and matching video images of the driver-s left eye with eye-gesture templates drawn from images of the driver looking at the centre of each windscreen cell. The main contribution of this paper is to assess the accuracy of this approach using Receiver Operating Characteristic analysis. The results of our evaluation give a sensitivity value of 84.3% and a specificity value of 85.0% for the eye-gesture template approach indicating that it may be useful for driver point of regard determinations.

• Siti Nor Hafizah binti Mohd Zaid
• Mohamed Abdel-Maguid
• Abdel-Hamid Soliman

• Advanced Driver Assistance Systems
• Eye-Tracking
• Hazard Detection.

[1] Fletcher,L., and Zelinsky, A., ÔÇÿDriver Inattention Detection Based on
Eye Gazed - Road Even Correlation-, The International Journal of
Robotics Research, pp.774-801, June 2009.
[2] WHO, ÔÇÿWorld Health Report, Technical Report-, World Health
Organisation, http://www.who.int/whr2001/2001/main/en/index.html,
2001.
[3] OECD/ECMT, ÔÇÿAmbitious Road Safety Targets and the Safe System
Approach-, OECD Publishing, 2006.
[4] Department for Transport Statistics, Retrieved September 20, 2012, from
theDepartment for Transport:
http://www.dft.gov.uk/statistics?orderby=date&post_type
=table&series=road-accidents-and-safety-series), 2010.
[5] MohdZaid, S.N.H., Mohamed, A.M., Soliman, A.H., ÔÇÿTowards
EyeGesture Analysis for Driver Assistance Systems using Template
Matching, Proceeding of 4th Engineering Conference (EnCon),
Kuching, Sarawak,Malaysia, 2011.
[6] MohdZaid, S., N., H., Mohamed, A.M., and Soliman, A.H.,
ÔÇÿEyeGesture Analysis for Driver Hazard Awareness-, World Academy
of Science,Engineering and Technology (WASET), Tokyo, Japan,
Vol.65,pp.1240-1246, 2012.
[7] MohdZaid , S., N., H., Mohamed, A.M., Soliman, A., H., ÔÇÿEye Gesture
Analysis with Head Movement for Advanced Driver Assistance
Systems-, World Academy of Science, Engineering and Technology
(WASET), France, Vol 66, pp. 1082- 1088, 2012.
[8] Dingus, T.A., Klauer, S.G., Neale, V.L., Petersen, A., Lee,
S.E.,Sudweeks, J., ÔÇÿThe 100-car Naturalistic Driving Study, Phase IIresults
of The 100 Car-Field Experiment (Technical Report No DOT HS
810593)--, Washington, DC-NHTSA, 2006.
[9] Klauer, S.G., Dingus, T.A., Neale, V.L., Sudweeks, J., and Ramsey,
D.,ÔÇÿThe impact of Driver Inattention on Near-Crash/Crash Risk :
AnAnalysis Using the 100-car Naturalistic Driving Study Data
(Technical Report No. DOT HS 810 594)-, Washington DC: NHTSA,
2006.
[10] Fletcher, L., Loy, G., Barnes, N., and Zelinsky, A., ÔÇÿCorrelating Driver
Gaze with Road Scene for Driver Assistance Systems-, Journal of
Robotics and Autonomous Systems, pp.71-84. 2005a.
[11] Fletcher, L., Petersson, L., Barnes, N., Austin, D., and Zelinsky, A., ÔÇÿA
Sign Reading Driver Assistance System Using Eye Gaze-,
Proceedingsof the IEEE International Conference on Robotics and
Automation, pp.4655- 4660.
[12] Gee, A.H. and Cipolla, R., ÔÇÿDetermining the Gaze of Faces in Images-,
Image and Vision Computing, Vol.12, No.10, pp. 639-647, 1994.
[13] Cheng,S.Y., and Trivedi, M.M., ÔÇÿTowards a Comparative Study of Lane
Tracking Using Omni-directional and Rectilinear Images for Driver
Assistance Systems-, ICRA, Workshop: Planning, Perception and
Navigation for Intelligent Vehicles, 2007.
[14] McCall, J.C. Wipf, D.P.Trivedi, M.M.Rao, B.D., ÔÇÿLane Change
IntentAnalysis Using Robust Operators and Sparse Bayesian Learning-,
IEEE Transaction on Intelligent Transportation Systems, Vol.8, No.3,
pp.431-440, 2007.
[15] Doshi, A., and Trivedi, M., ÔÇÿOn the Roles of Eye Gaze and Head
Dynamics in Predicting Driver-s Intent to Change Lanes-, IEEE
Intelligent Transportation Systems, Vol.3, No.10, pp.453-462, 2009.
[16] Youden W., J., ÔÇÿAn Index for Rating Diagnostic Tests-. Cancer vol.3
pp.32-35, 1950.