Detection of Driver Drowsiness from Video

Vural, Cetin, Ercil, Movellan, Bartlett

Automatic facial expression recognition has advanced to the point that we can develop applications that respond to spontaneous expressions in real time. This work explores the real-time measurement of drowsiness. Drowsiness detection has crucial implications for safety in situations involving heavy machinery or control towers, as well as application in fields such as adaptive tutoring systems. The US National Highway Traffic Safety Administration (NHTSA) has concluded that drowsy driving is just as dangerous as drunk driving. Thus methods to automatically detect drowsiness may help save many lives. Other drowsiness detection systems focus on blink rate, yawning, and head nods. Here, we apply automated measurement of the face during actual drowsiness to discover new signals of drowsiness in facial expression and head motion.

Vural, E., Bartlett, M.S., Littlewort, G., Cetin, M. Ercil, E., and Movellan, J. (2010). Discrimination of Moderate and Acute Drowsiness Based on Spontaneous Facial Expressions. IEEE International Conference on Pattern Recognition. Download pdf

Vural, E., Cetin, M., Ercil, A., Littlewort, G., Bartlett, M., and Movellan, J. (2007). Drowsy driver detection through facial movement analysis. ICCV Workshop on Human Computer Interaction. 
Download pdf

Vural, E., Cetin, M., Ercil, A., Littlewort, G., Bartlett, M., and Movellan, J. (2007). Machine learning systems for detecting driver drowsiness. Proc. Digital Signal Processing for in-Vehicle and Mobile Systems, Istanbul, Turkey. p. 97-110. Best paper award.