The research will attempt to automatically classify certain aspects of driver state (such as fatigue) or distraction due to a conversation using a handheld device (such as a cell phone). This will be done in part by continuously estimating the facial head pose of a driver to see if the driver is paying attention to the road and his/her surroundings. Other facial cues, such as mouth movement and eye movement, as well as whether the driver has both hands on the steering wheel, will be used to determine driver attentiveness. The proposed system will automatically detect 'soft' biometric information about the driver, such as age, gender, ethnicity, glasses, etc.
Develop face detection, landmarking, behavioral, and soft biometric detection modules.