Low-Cost Real-time Driver Drowsiness Detection based on Convergence of IR Images and EEG Signals

Abstract

This paper focused on low-cost real-time driver's drowsiness detection by fusing facial image information obtained through the IR camera (Infrared Camera) and EEG (Electroencephalogram) signal acquired through the EEG sensor. The proposed method was tested on the target board (i.MX6Quad). The i.MX6Quad is the SoCs (System-on-Chip) that integrate many processing units into one die, like the main CPU, a video processing unit and a graphics processing unit for instance. Instead of the RGB camera, the IR camera is applied to driver condition monitoring and drowsiness detection technology by extracting the driver's facial feature information robustly against daytime, night-time, and frequent change of brightness around the face. The headphone type EEG sensor is also used to minimize the user's discomfort. On the target board, the processing time per image frame is about 60ms, so that it can process about 17 frames per second. This processing time can be suitable for the driver's drowsiness detection systems.