基于面部表情识别的驾驶员防疲劳预警系统

晓毅 苏(西安工业大学电信学院，中国)
潇 王(西安工业大学电信学院，中国)
世震 提(西安工业大学电信学院，中国)
一鸣 仝(西安工业大学电信学院，中国)

摘要

论文研究的疲劳驾驶检测系统，是使用Opencv和dlib模型作为人脸检测和特征点提取的技术手段，对驾驶员进行人脸识别并且对驾驶员的眼镜和鼻子进行识别和定位，运用PERCLOS作为判定方法，从而统计出驾驶员眨眼、打哈欠和点头的次数。通过将驾驶员的眨眼、打哈欠和点头次数与预设的阈值进行比较，可以实时评估驾驶员的注意力水平，并判断其是否处于疲劳驾驶状态。这种方法可以通过监测驾驶员的行为特征来提供有关疲劳驾驶的警示和预警。

关键词

疲劳驾驶；面部表情识别；Opencv

参考

ZHOU F,ALSAID A,BLOMMER M,et al. Driver fatigue transition prediction in highly automated driving using physiological features[J]. Expert Systems with Applications, 2020,147:113204.

NAZ S, ZIAUDDIN S,SHAHID A R.Driver fatigue detection using mean intensity SVM and SIFT[J].International Journal of Interactive Multimedia and Artificial Intelligence,2019,5(4):86-93.

FATIMA B,SHAHID A R,ZIAUDDIN S,et al.Driver fatigue detection using Viola Jones and principal component analysis[J].Applied Artiticial Intelligence,2020,34(6):456-483.

LIU Z,PENG Y,HU W.Driver fatigue detection based on deeply-learned facial expression representation[J]. Journal of Visual Communication and Image Representation,2019,71(2):102723.

HEMANTKUMAR B,MALI,SHASHIKANT D,et al.Non-intrusive detection and prediction of driver’s fatigue using optimized yawning technique[J].Materials Today:Proceedings,2017,4(8):7859-7866.

CHENG Q,WANG W H, JIANG X B,et al.Assessment of driver mental fatigue using facial landmarks[J].IEEE Access,2019,7:150423-150434.

DOI: http://dx.doi.org/10.26549/bdai.v4i4.14316