基于主动形状模型及模糊推理的驾驶疲劳检测

Driving fatigue detection based on active shape model and fuzzy inference

为了提高基于单一特征检测算法的准确率和鲁棒性,提出了一种基于多个特征的驾驶员疲劳融合检测算法。选取能够直接反映驾驶员疲劳程度的2个面部特征(眼睛和嘴巴)对驾驶员状态进行综合判断。针对驾驶员头部多角度变化时导致面部特征定位困难的问题,提出了基于主动形状模型(ASM)人脸特征定位算法,应用12个ASM特征标记点,准确定位出眼睛和嘴部特征。针对疲劳程度三级分类(清醒、疲劳及严重疲劳)难以确定的问题,提出了基于模糊推理系统的疲劳检测算法,根据人的经验,"智能"地判断疲劳程度,从而准确地量化疲劳这一模糊概念。实验结果对比表明,综合眼睛和嘴部信息,比采用单参数检测算法减少了误判的概率,具有较高的准确性和鲁棒性。

In order to improve the accuracy and robustness of the driver fatigue detection algorithm based on a single feature, this paper proposes a multiple-feature-based driver fatigue fusion detection algorithm. Two facial features （eyes and mouth） that could directly reflect the fatigue are chosen to estimate the state of the driver synthetically. Aiming at the problem that the angle change of the driver~ head makes it difficult to locate the facial features, a fa- cial feature location algorithm based on active shape model （ASM） is proposed. Applying 12 feature mark points of ASM, the algorithm can locate the features of eyes and mouth exactly. Focusing on the problem that it is difficult to determine the three-level classification of driver＇ s fatigue level （ awaking, fatigue, severe fatigue） , we put forward a fatigue detection algorithm based on fuzzy inference system. The algorithm can estimate the level of fatigue smartly according to the experience of human, thus the fuzzy concept of fatigue can be quantified accurately. The comparison of experiment results shows that using the proposed algorithm the probability of misjudgment is lower than that using the single parameter detection algorithm, and the proposed algorithm has higher accuracy and robustness.