基于头动与眼电信号的疲劳检测研究

针对疲劳识别率有待提高和现行疲劳检测设备不便携带的问题,提出一种以便携式眼镜为载体结合处理头动与眼电信号的疲劳检测方法.利用便携式眼镜采集头动与眼电信号并通过蓝牙将数据传输到手机终端.采用融合卡尔曼滤波算法处理头动信号并提取点头频率特征,采用Perclos算法P80原理和分段平均功率比值法处理眼电信号得到眨眼频率和低高...

FATIGUE DETECTION BASED ON HEAD MOVEMENT AND EOG SIGNAL

In order to solve the problem that fatigue recognition rate needs to be improved and the current fatigue detection equipment is not easy to carry,a fatigue detection method combining head movement and EOG signals using portable glasses as a carrier is proposed.The head movement and EOG signal were collected by portable glasses and transmitted to the mobile phone terminal by bluetooth.The head motion signals were processed by fusion Kalman filtering method,and the nodding frequency characteristics were extracted.The EOG signal was processed to get the blinking frequency and low high frequency power ratio characteristics by using P80 principle of Perclos algorithm and piecewise average power ratio method.According to the principal component analysis(PCA)method,the fatigue eigenvalues were obtained to determine the fatigue degree,and the Pearson method was used to analyze the correlation between the results of this artical and the results of fatigue detection through EEG signals.The experimental results show that the fatigue detection recognition rate of this method is 90.6%and the correlation with the fatigue results of EEG detection is 0.82.It has good accuracy,effectiveness and easy to carry,so it has good practical value.