摘要
为实现更快速、准确的疲劳预警,提出了一种基于并行短时面部特征的驾驶人疲劳检测方法。基于加入了MicroNet模块、CA注意力机制、Wise-IoU损失函数的YOLOv7-MCW目标检测网络提取驾驶人面部的短时面部特征,再使用并行Informer时序预测网络整合YOLOv7-MCW目标检测网络得到的面部时空信息,对驾驶人疲劳状态进行检测与预警。结果表明:在领域内公开数据集UTA-RLDD和NTHU-DDD上,YOLOv7-MCW-Informer模型的准确率分别为97.50%和94.48%,单帧检测时间降低至28 ms,证明该模型具有良好的实时疲劳检测性能。
A driver fatigue detection method based on parallel short-term facial features is proposed to achieve faster and more accurate fatigue warning.The method utilizes the YOLOv7-MCW object detection network,which incorporates the MicroNet module,CA attention mechanism,and Wise-IoU loss function,to extract short-term facial features of the driver’s face.The parallel Informer temporal prediction network is then used to integrate the spatiotemporal information obtained from the YOLOv7-MCW object detection network,enabling the detection and warning of driver fatigue.The results demonstrate that the YOLOv7-MCW-Informer model achieves accuracy rates of 97.50%and 94.48%on the publicly available datasets UTARLDD and NTHU-DDD,respectively,with a single-frame detection time reduced to 28 ms,proving the excellent real-time fatigue detection performance of the model.
作者
刘强
谢谦
方玺
李波
解孝民
Liu Qiang;Xie Qian;Fang Xi;Li Bo;Xie Xiaomin(School of Intelligent Systems Engineering,Sun Yat-sen University,Shenzhen 518107;Development&Research Center of State Post Bureau,Beijing 100868;Automobile Engineering Research Institute of Guangzhou Automobile Group Co.,Ltd.,Guangzhou 511434;Guangdong Marshell Electric Technology Co.,Ltd.,Zhaoqing 523268)
出处
《汽车技术》
CSCD
北大核心
2024年第5期15-21,共7页
Automobile Technology
基金
重庆市科技创新重大研发项目(CSTB2023TIAD-STX0030)
广东省重点领域研发计划项目(2022B0701180001)
广东省基础与应用基础研究基金项目(2022A1515010692)
肇庆市第四批西江创新创业团队与领军人才项目。
关键词
智能交通
疲劳检测
目标检测
注意力机制
时序预测
Intelligent transportation
Fatigue detection
Object detection
Attention mechanism
Time series prediction
