基于呼吸信号的驾驶员疲劳状态实时监测系统  

Real-Time Monitoring System for Driver's Fatigue States Based on Respiratory Signal

作　　者：祝宇虹[1] 刘海平[1] 査富生[1] 李满天[1] 郭伟[1] 王鹏飞[1] 

机构地区：[1]哈尔滨工业大学机器人技术与系统国家重点实验室,黑龙江哈尔滨150001

出　　处：《江南大学学报（自然科学版）》2014年第1期55-59,共5页Joural of Jiangnan University (Natural Science Edition)　

摘　　要：针对疲劳驾驶导致交通事故多发,提出一种三维疲劳评定方法用于确定驾驶员的真实疲劳状态,利用经验模态分解、信号重构等信号分析技术提取呼吸信号的周期、周期标准差、幅值、幅值标准差和哈欠频繁次数等作为判定疲劳的特征参数。通过构建驾驶员疲劳状态监测系统和大量的模拟驾驶试验证明这些特征参数能够有效地反映疲劳状态,为该系统现场实际应用奠定了基础,对于减少因疲劳驾驶造成的交通事故具有重要的应用价值。A three-dimensional method for the evaluation of fatigue levels for determining the real fatigue state is put forward. Respiratory cycle standard deviation of cycle respiratory amplitude standard deviation of the amplitude and the number of yawn, extracted by the signal analysis technique of empirical mode decomposition and signal reconstruction, are used as characteristic parameters to identify statement of fatigue. By constructing the real-time monitoring system for driver~ fatigue statement and doing plenty of simulation experiments,it is proved that the characteristic parameters can effectively reflect the fatigue statement. It is siginifcant decreasing the traffic accidents caused by driver fatigue.

关 键 词：疲劳驾驶 疲劳评定 呼吸信号 经验模态分解 模拟驾驶 

分 类 号：U491.2[交通运输工程—交通运输规划与管理]