Driver Fatigue Detection Based on Residual Channel Attention Network and Head Pose Estimation

Driver fatigue is the culprit of most traffic accidents. Visual technology can intuitively judge whether driver in state fatigue. A detection system based on residual channel attention network (RCAN) and head pose estimation proposed. In proposed system, Retinaface employed for face location outputs five landmarks. Then RCAN to classify eyes mouth. The includes a module, which adaptively extract key feature vectors from map, significantly improves classification accuracy RCAN. self-built dataset, eye reaches 98.962% that mouth 98.561%, exceeding other classical convolutional neural networks. percentage eyelid closure over pupil time (PERCLOS) opening degree (POM) are used addition, this article proposes use Perspective-n-Point (PnP) method estimate as an essential supplement driving over-angle evaluate excessively deflected. On whole, integrates 3D deep learning. This evaluated by four datasets shows success with their high performance.