A robust and efficient face tracker for driver inattention monitoring system

摘要

For the application of Driver Inattention Monitoring System this paper propose a zero-order binocular EKF face tracker, which could estimate the face pose, the eyeball yaw & pitch, the eyelids animation and the mouth & jaw animation as well as shape parameters. Experiments shows the proposed full detection and tracking loop could give more reliable result than monocular tracker and LM tracker with real time performance on a general purpose personal computer. It is also shown the tracker has tolerance against feature point detection error.