摘要
驾驶员疲劳是引发交通事故的主要原因之一,严重威胁道路安全。拟研究一种基于机器视觉的驾驶员疲劳检测系统,利用车载摄像头采集驾驶员面部图像,运用人脸检测、特征提取算法,实时分析眼睛、嘴巴等区域状态变化,据此判断驾驶员是否疲劳。系统性能在准确率、精确率、召回率和F1得分上优于其他模型,显示出93.5%的准确率和快速响应能力。
Driver fatigue is one of the main causes of traffic accidents and seriously threatens road safety.We plan to study a driver fatigue detection system based on machine vision,which uses a vehicle mounted camera to capture facial images of the driver,and applies facial detection and feature extraction algorithms to analyze real-time changes in the state of areas such as the eyes and mouth,in order to determine whether the driver is fatigued.The system performance is superior to other models in accuracy,precision,recall,and F1 score,showing an accuracy of 93.5%and fast response capability.
作者
郑瀚
ZHENG Han(College of Artificial Intelligence and Manufacturing,Hechi University,Hechi,Guangxi Zhuang Autonomous Region,546300 China)
出处
《大众科学》
2024年第24期93-96,共4页
China Public Science
基金
2024度广西高校中青年教师基础能力提升项目“驾驶员情绪识别的关键技术研究”(项目编号:2024KY0629)。
关键词
驾驶员疲劳
检测算法
特征提取
人脸检测
Driver fatigue
Detection algorithm
Feature extraction
Facial detection
