Several approaches were proposed for the detection and pre- diction of drowsiness. The approaches can be categorized as estimating the fitness of duty, modeling the sleep-wake rhythms, measuring the ve- hicle based performance and online operator monitoring. Computer vi- sion based online operator monitoring approach has become prominent due to its predictive validity of detecting drowsiness. Previous studies with this approach detect driver drowsiness primarily by making pre- assumptions about the relevant behavior, focusing on blink rate, eye clo- sure, and yawning. Here we employ machine learning to datamine actual human behavior during drowsiness episodes. Automatic classifiers for 30 facial actions from the Facial Action Coding system were developed us- ing machine learning on a separate database of spontaneous expressions. These facial actions include blinking and yawn motions, as well as a num- ber of other facial movements. In addition, head motion was collected through automatic eye tracking and an accelerometer. These measures were passed to learning-based classifiers such as Adaboost and multino- mial ridge regression. The system was able to predict sleep and crash episodes during a driving computer game with 98% accuracy across sub- jects. This is the highest prediction rate reported to date for de-tecting real drowsiness. Moreover, the analysis revealed new information about human facial behavior during drowsy driving.
Mendeley saves you time finding and organizing research
There are no full text links
Choose a citation style from the tabs below