Pilot facial feature recognition and fatigue classification method under high exposure environment

Abstract

To improve the recognition efficiency of pilot fatigue detection in high exposure environment, a facial feature recognition and fatigue classification method for pilots is proposed. Firstly, the high exposure images are pre-processed with frequency domain light normalization; secondly, a human face detector is trained based on YOLOv5s network model and detects the face, eyes and mouth; again, the fatigue feature values of eyes and mouth are obtained by fusing PERCLOS fatigue detection algorithm; finally, a fatigue classifier is built by RBF-ELM neural network and the fatigue parameters of eyes, mouth and yawning The fatigue parameters of the eye, mouth and yawn features were input to the classifier for fatigue classification. The experimental results show that the fatigue detection speed of the proposed method is up to 310 FPS when computed with GPU, which has higher recognition rate and better robustness compared with the classical PCA, CNN and DCT methods. The method can effectively improve the accuracy of pilot facial feature recognition and eye localization in high exposure environment, and has high practicality for non-contact pilot fatigue detection.