基于时序性面部动作信息的驾驶员状态检测框架

通过网络摄像头获取驾驶员面部视频输入网络进行检测的方法主要通过分析驾驶员口型等面部表情来判断是否疲劳驾驶，但说话等很多类似的状态也被误检为疲劳。针对以上问题提出了一种基于时序性面部动作信息的检测框架，对驾驶员状态进行检测，从而提高检测准确率、降低误检率。该框架通过检测视频中的脸部轮廓，提取脸部的多种特征，形成面部动作单元；通过训练对应的LSTM网络，形成时序性的面部动作单元，根据其相关性进行多种动作单元融合，检测最终驾驶员的状态。在公共YawDD数据集上的检测结果表明，相比于现有的方法，该检测方法的准确率提高到了93.1%，同时大幅降低了疲劳状态的误检率。

Driver state detection framework based on temporal facial action information

It is an effective means to detect abnormal driving such as fatigue by detecting the driver''s face video input network through a webcam. The previous method mainly analyzed the facial expressions such as the driver''s mouth shape to analyze whether or not to yawn, thereby judging whether or not fatigue driving, but many similar states such as speaking were also mistakenly detected as fatigue. Aiming at the above problems, this paper proposed a detection framework based on sequential facial motion information to detect the driver''s state, thus improving the detection accuracy and reducing the false detection rate. The framework extracted various features of the face to form a facial action unit by detecting the contour of the face in the video. It formed a sequential facial action by training the corresponding LSTM network. The unit performed a plurality of action unit fusions according to its correlation to detect the state of the final driver. The test results on the public YawDD data set show that the accuracy rate of the proposed ftamework is increased to 93.1% compared with the existing method, and the false detection rate of the fatigue state is greatly reduced.