摘要：AbstractDrowsy driving is a major cause of traffic accidents. Based on the theory of comprehensive evaluation, a driving fatigue evaluation program, that combines the four indicators of eye movement, Electromyogram (EMG), Electrocardiograph (ECG), and grip force, is proposed in this paper. First, the fatigue evaluation models of each indicator are studied. The eyeballs are located using the segmentation method and the eye movement is judged by the PERCLOS eigenvalues. The median frequency is used to evaluate EMG, the standardized high-frequency power is used to evaluate ECG and the mean change rate is used to evaluate grip strength. Then, the principal component analysis (PCA) method is applied to determine the weight coefficient, and the comprehensive evaluation method is constructed with the maximum criterion of the decision theory. Based on this, a comprehensive evaluation algorithm is designed and the normalized comprehensive evaluation eigenvalue can be obtained. Finally, the fatigue alarm algorithm and corresponding system are designed, and its performance is verified by tests.
关键词：KeywordsDrowsy driving warningEye movement detectionEMGECGGrip ForceMulti-feature fusionComprehensive judgment
