驾驶员注意力量化转换模型研究  

Research on Shift Model of Driver Visual Attention Based on Markov Process

作　　者：郭孜政[1] 张殿业[1] 陈崇双[2] 付雷[1] 

机构地区：[1]西南交通大学交通运输学院,成都610031 [2]西南交通大学数学系,成都610031

出　　处：《武汉理工大学学报（交通科学与工程版）》2010年第4期742-745,共4页Journal of Wuhan University of Technology（Transportation Science & Engineering）

基　　金：国家自然科学基金项目(批准号:70422201);西南交大创新资助项目(批准号:2007CTT006)资助

摘　　要：为研究驾驶员注意力转移规律,提出驾驶员注意力转换模型.将驾驶注意力分布状态划分为驾驶态、干扰态、内敛态,构建注意力转移状态空间.依据短时连续驾驶过程中注意力分布的齐次性,将马尔科夫过程引入到研究中,构建连续短时片段内驾驶员注意力转移模型.针对长时连续驾驶中注意力在各状态分布的非齐次性,通过时段划分采用短时模型叠加的方法得到长时连续驾驶注意力转移的近似处理模型组.结合实验数据对模型进行了检验,结果分析表明平均误差MAPE均小于5%,具有较高精度,模型可用.In order to study the shifting progress of driver＇s visual attention,the Markov Process is introduced to this paper.The shifting state space of visual attention is constructed by dividing the valid visual field of driver into seven subordinary fields,which are front visual field,left visual field,right visual field,left-view mirror,right-view mirror,rearview mirror and instrument board.Then through discussing the shifting relationship of visual attention among seven sub-fields,the matrix of shifting rate is constructed and a differential equation is set up by using Probability Therory.At last the function of state space vector is established by using Laplace transform and the stationary state vector of visual attention is acquired by calculation of limit under the condition that the sum of each element in state vector equals one.

关 键 词：驾驶员 转移模型 马尔科夫过程 视觉注意力 

分 类 号：U412.33[交通运输工程—道路与铁道工程]