Estimation of Driver Drowsiness Using Blood Perfusion Analysis of Facial Thermal Images in a Driving Simulator
Background and Objective: Driver drowsiness is a major cause of fatal driving accidents worldwide, which can be prevented by an early detection. Driver drowsiness results in reduction of blood flow and change in facial thermal patterns. In this paper, a drowsiness detection system was designed to estimate the level of drowsiness by analyzing facial skin temperature patterns.
Materials and Methods: 12 subjects drove on a highway in a driving simulator, while their facial temperature image was captured by a thermal camera. The subjects’ drowsiness levels were independently estimated by the observer rating of drowsiness (ORD) method. Facial blood vessels were located by a four-step algorithm and tracked in each frame. The mean value of the pixel intensities of the facial blood regions formed a sequence of data. Variations of facial skin temperature signals were investigated for three main blood vessels.
Results: Facial skin temperature decreased at three levels of sleepiness from wakefulness to extreme drowsiness. Temperature near the supratrochlear, angular, and facial arteries decreased by 0.54 ºC, 0.33 ºC, and 0.32 ºC from wakefulness to extreme drowsiness, respectively. All subjects except one experienced skin temperature decrease from wakefulness to extreme drowsiness.
Conclusion: It was shown that the drivers’ facial blood vessels temperature decreased as the level of drowsiness increased. Driver drowsiness can be detected by monitoring the change in the facial skin temperature signal during driving. Facial thermal imaging is a promising non-intrusive method to detect driver drowsiness.
2. Stutts JC, Wilkins JW, Scott OJ, et al. Driver risk factors for sleep-related crashes. Accid Anal Prev 2003; 35: 321-31.
3. Sahayadhas A, Sundaraj K, Murugappan M. Detecting driver drowsiness based on sensors: A review. Sensors (Basel) 2012; 12: 16937-53.
4. Sigari MH, Fathy M, Soryani M. A driver face monitoring system for fatigue and distraction detection. International Journal of Vehicular Technology 2013; 2013: 263983.
5. Ring EF. History of thermology and thermography: Pioneers and progress. Proceedings of the 12th EAT Congress on Thermology (EAT2012); 2012 Sep 5-8; Porto, Portugal.
6. Wu S, Fang Z, Xie Z, et al. Blood perfusion models for infrared face recognition. In: Delac K, Editor. Recent advances in face recognition. London, UK: InTech Open; 2008. p. 183-206.
7. Gault TR, Blumenthal N, Farag AA, et al. Extraction of the superficial facial vasculature, vital signs waveforms and rates using thermal imaging. Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition; 2010 Jul 13; San Francisco, CA. p. 1-8.
8. Buddharaju P, Pavlidis IT, Tsiamyrtzis P, et al. Physiology-based face recognition in the thermal infrared spectrum. IEEE Trans Pattern Anal Mach Intell 2007; 29: 613-26.
9. Bando S, Oiwa K, Nozawa A. Evaluation of dynamics of forehead skin temperature under induced drowsiness. IEEJ Trans Elec Electron Eng 2017; 12: S104-S109.
10. Krauchi K, Cajochen C, Wirz-Justice A. A relationship between heat loss and sleepiness: effects of postural change and melatonin administration. J Appl Physiol (1985) 1997; 83: 134-9.
11. Gradisar M, Lack L. Relationships between the circadian rhythms of finger temperature, core temperature, sleep latency, and subjective sleepiness. J Biol Rhythms 2004; 19: 157-63.
12. Moradi S, Mansouri F, Sori F, et al. Sleepiness and changes in vital signs among the clinical shift workers staff at Imam Khomeini Hospital of Ilam. Int J Hosp Res 2014, 3: 19-24.
13. Wierwille WW, Ellsworth LA. Evaluation of driver drowsiness by trained raters. Accid Anal Prev 1994; 26: 571-81.
14. Perona P, Malik J. Scale-space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Mach Intell 1990; 12: 629-39.
15. Philip RC, Ram S, Gao X, et al. A comparison of tracking algorithm performance for objects in wide area imagery. Proceedings of the 2014 Southwest Symposium on Image Analysis and Interpretation; 2014 Apr 6-8; San Diego, CA, USA. Piscataway, NJ: IEEE; 2014. p. 109-12.
16. Zhang K, Zhang L, Liu Q, et al. Fast visual tracking via dense spatio-temporal context learning. Proceedings of the Computer Vision-ECCV 2014: 13th European Conference, 2014 Sep 6-12; Zurich, Switzerland. Cham, Switzerland: Springer International Publishing; 2014. p. 127-41.
17. Ebrahimian Hadi Kiashari S, Nahvi A, Homayounfard A, et al. Monitoring the variation in driver respiration rate from wakefulness to drowsiness: A non-intrusive method for drowsiness detection using thermal imaging. J Sleep Sci. 3:1-9. 18. 18.Benda NM, Eijsvogels TM, Van Dijk AP, et al. Altered core and skin temperature responses to endurance exercise in heart failure patients and healthy controls. Eur J Prev Cardiol 2016; 23: 137-44.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.