...
首页> 外文期刊>IFAC PapersOnLine >Research on Drowsy-driving Monitoring and Warning System Based on Multi-feature Comprehensive Evaluation
【24h】

Research on Drowsy-driving Monitoring and Warning System Based on Multi-feature Comprehensive Evaluation

机译:基于多特征综合评价的困倦驾驶监控预警系统研究

获取原文
           

摘要

Drowsy driving is a major cause of traffic accidents. Based on the theory of comprehensive evaluation, a driving fatigue evaluation program, that combines the four indicators of eye movement, Electromyogram (EMG), Electrocardiograph (ECG), and grip force, is proposed in this paper. First, the fatigue evaluation models of each indicator are studied. The eyeballs are located using the segmentation method and the eye movement is judged by the PERCLOS eigenvalues. The median frequency is used to evaluate EMG, the standardized high-frequency power is used to evaluate ECG and the mean change rate is used to evaluate grip strength. Then, the principal component analysis (PCA) method is applied to determine the weight coefficient, and the comprehensive evaluation method is constructed with the maximum criterion of the decision theory. Based on this, a comprehensive evaluation algorithm is designed and the normalized comprehensive evaluation eigenvalue can be obtained. Finally, the fatigue alarm algorithm and corresponding system are designed, and its performance is verified by tests.
机译:困倦驾驶是交通事故的主要原因。本文基于综合评价理论,提出了一种将眼睛运动的四个指标-肌电图(EMG),心电图仪(ECG)和抓地力-结合在一起的驾驶疲劳评价程序。首先,研究每种指标的疲劳评估模型。使用分割方法定位眼球,并通过PERCLOS特征值判断眼睛的运动。中位数频率用于评估EMG,标准化高频功率用于评估ECG,平均变化率用于评估握力。然后,应用主成分分析(PCA)方法确定权重系数,并以决策理论的最大准则构建综合评价方法。在此基础上,设计了一种综合评价算法,可以获得归一化的综合评价特征值。最后,设计了疲劳报警算法和相应的系统,并通过测试验证了其性能。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号