为有效降低车道变换行为诱发事故的风险性，提出一种基于Logistic 模型的驾驶人换道意图识别方法。利用faceLAB 视觉追踪系统，通过真实环境下的实车测试，结合换道前驾驶人对后视镜的注视特性确定换道意图时窗，分析车道保持与换道意图阶段的注视特性差异，提取扫视次数、扫视幅度、水平方向视觉搜索广度、头部水平转动角度标准差等驾驶人换道意图特征指标，构建了Logistic 模型，并经效度检验后应用于对驾驶人换道意图的识别。结果显示，基于Logistic 模型的驾驶人换道意图识别方法的识别成功率达到90.24%，与基于转向灯信号的驾驶人换道意图识别方法相比，具有明显的时序及成功率方面的优势。
To reduce the risk of lane changes, a method for lane changing intent identification is proposed based on the logistic model. By using faceLAB visual tracking system, experiments were conducted under real road environment for the purpose of studying drivers' lane changing intent identification. On the basis of the drivers' fixation characteristics of the rearview mirrors before lane changing operation, the size of the time window for lane changing behavior is determined. Based on difference analysis of visual characteristics between lane keeping and lane changing intent stages, saccade numbers, visual search width in the horizontal direction, saccade amplitude, and standard deviation of head rotation angles in the horizontal direction are selected as the characteristic indice to identify drivers' lane changing intent. The logistic model is constructed based on the leaning samples'characteristics. The model is applied to the lane changing intent identification process after the validity test. The results show that the identification rate reached 90.24%. Compared with the lane changing intent identification based on turn signals, the logistic model has significant advantages in terms of time series and identification rate.
[1] 霍克. 城市道路驾驶员车道变换行为及注视转移特性研究[D]. 西安: 长安大学, 2010. Huo Ke. Study on drivers' lane change behavior and law of eye movement in urban environment[D]. Xi'an: Chang'an University, 2010.
[2] Wang J S, Knipling R R. Lane change/merge: Problem size assessment and statistical description[R]. Virginia: National Highway Traffic Safety Administration, 2011.
[3] Jula H, Kosmatopoulos E B. Collision avoidance analysis for lane changing and merging[J]. Vehicular Technology, IEEE Transactions on, 2010, 49(6): 2295-2308.
[4] Salvucci D D, Liu A. The time course of a lane change: driver control and eye-movement behavior[J]. Transportation Research Part F, 2002, 5 (2): 123-132.
[5] 彭金栓, 付锐, 郭应时, 等. 基于有限零和灰色博弈的车道变换决策分 析[J]. 科技导报, 2011, 29(3): 52-56. Peng Jinshuan, Fu Rui, Guo Yingshi, et al. Analysis of lane change decision making based on the finite and zero-sum grey game theory[J]. Science&Technology Review, 2011, 29(3): 52-56.
[6] Lethaus F, Rataj J. Do eye movements reflect driving maneuvers?[J]. IET Intelligent Transport Systems, 2007(3): 199-204.
[7] Lee S E, Olsen E C B, Wierwille W W. A Comprehensive Examination of Naturalistic Lane-Changes[R]. Virginia: Virginia Tech Transportation Institute, 2004.
[8] 郭应时. 交通环境及驾驶经验对驾驶员眼动和工作负荷影响的研究[D]. 西安: 长安大学, 2009. Guo Yingshi. The effect of traffic environment and driving experience on drivers' eye movement and workload[D]. Xi'an: Chang'an University, 2009.
[9] Underwood G, Chapman P, Bowden K, et al. Visual search while driving: Skill and awareness during inspection of the scene[J]. Transportation Research Part F, 2002, 5(2): 87-97.
[10] Pearce J,Ferrier S. Evaluating the predictive performance of habitat models developed using logistic regression[J]. Ecological Modelling, 2000, 133(3): 225-245.
[11] 张良力. 面向安全预警的机动车驾驶意图识别方法研究[D]. 武汉: 武汉理工大学, 2011. Zhang Liangli. Research on motorists'intention recognition for traffic safety precaution[D]. Wuhan: Wuhan University of technology, 2011.
[12] 侯海晶. 高速公路驾驶人换道意图识别方法研究[D]. 长春: 吉林大 学, 2013. Hou haijing. Research on lane-changing intention recognition method for freeway drive[D]. Changchun: Jilin University, 2013.
