An Analysis of Saccadic Eye Movements and Facial Images for Assessing Vigilance Levels During Simulated Driving
The authors analyzed facial video recordings and saccadic eye movements during 1-hour simulated driving in 10 subjects. Mean cross-correlation coefficient between the visually determined facial sleepiness and the proposed index of saccade (i.e. PV/D) for 9 subjects was -0.56 and the maximum coefficient of inverse cross-correlation was 0.83. Mean cross-correlation coefficient for 6 repetitive measurements for another subject was -0.72, and the maximum was 0.84. Variation in PV/D preceded that in facial sleepiness in 13 of 15 measurements and syncronized with it in other 2 measurements. From these results, we confirmed a fair potential of the PV/D to detect decline in vigilance levels earlier than facial sleepiness. We also revealed that narrow fluctuations throughout the measurement could lead to low inverse cross-correlation below 0.60 between the two indices. Therefore experimenter should pay attention to designing the experimental procedure to ensure broad fuctuations of the subject’s vigilance levels in the measurement.
Keywordsdoze prevention saccade facial sleepiness advanced safety vehicle
Unable to display preview. Download preview PDF.
- 1.Ueno, H., Kaneda, M., Tsukino, M.: Development of Drowsy Detection System. In: Vehicle Navigation & Information Systems, pp. 15–20 (1994) Google Scholar
- 3.Smith, P., Shah, M., Lobo, N.V.: Determining Driver Visual Attention with One Camera. IEEE Trans. ITS 4, 205–218 (2003)Google Scholar
- 4.Ueno, A., Ota, Y., Takase, M., Minamitani, H.: Relationship between Vigilance Levels and Characteristics of Saccadic Eye Movement. In: 17th Ann. Int. Conf. IEEE EMBS, pp. 572–573 (1995)Google Scholar
- 5.Ueno, A., Ota, Y., Takase, M., Minamitani, H.: Characteristics of Visually Triggered and Internally Guided Saccade Depending on Vigilance States. IEICE Trans. Information and Systems PT 2 J81-D-II, 1411–1420 (1998) (in Japanese) Google Scholar
- 6.Ueno, A., Ota, Y., Takase, M., Minamitani, H.: Parametric Analysis of Saccadic Eye Movement Depending on Vigilance States. In: 18th Ann. Int. Conf. IEEE EMBS, pp. 319–320 (1996)Google Scholar
- 7.Ueno, A., Hashimoto, H., Takase, M., Minamitani, H.: Diurnal Variation in Vertical Saccade Dynamics. In: 4th Asia-Pacific Conf. Medical and Biological Engineering, p. 373 (1999)Google Scholar
- 9.Ueno, A., Uchikawa, Y.: Relation between Human Alertness, Velocity Wave Profile of Saccade, and Performance of Visual Activities. In: 26th Ann. Int. Conf. IEEE EMBS, pp. 933–935 (2004)Google Scholar
- 10.Ueno, A., Sakamoto, S., Uchikawa, Y.: Relation between Dynamics of Saccade and Bit Rate for Visual Perception during Numerical Targets Comparing. IEICE Trans. Information and Systems PT 2 J87-D-II, 2062–2070 (2004) (in Japanese) Google Scholar
- 11.Ueno, A., Uchikawa, Y.: An Approach to Quantification of Human Alertness Using Dynamics of Saccadic Eye Movement: For an Application to Human Adaptive Mechatronics. In: 8th Int. Conf. Mechatronics. Technol., pp. 563–568 (2004)Google Scholar
- 12.Herscovitch, J., Broughton, R.: Sensitivity of the Stanford Sleepiness Scale to the Effects of Cumulative Partial Sleep Deprivation and Recovery Oversleeping. Sleep 4, 83–92 (1981)Google Scholar
- 14.Komatsu, Y., Ueno, A., Hoshino, H.: Real-time discrimination of saccade and eye blink from output signal of eye movement monitor. In: 19th Ann. Conf. The Society of Life Support Technology, p. 54 (2003) (in Japanese) Google Scholar
- 15.Ueno, A., Kokubun, S., Uchikawa, Y.: A Prototype Real-Time System for Assessing Vigilance Levels and for Alerting the Subject with Sound Stimulation. Int. J. Assist. Robotics and Mechatronics 8, 19–27 (2007)Google Scholar