高速公路驾驶人换道意图识别方法研究
|
摘要
由于行驶速度快，高速公路事故造成的生命和财产损失相对其它道路事故更为严重。换道和车道保持是高速公路两类典型的驾驶行为模式，对行车安全有重大的影响。因此，研究人员开发了多种辅助换道系统。现有的换道辅助系统进行环境感知时，主要通过雷达或视觉感知周围环境信息和本车状态，忽略了驾驶人的行为动机和驾驶意图。这样，由于系统不能理解驾驶人的真实意图，往往会发出与驾驶人意图相异的警报或强制执行动作，从而导致驾驶人注意力分散、心理紧张甚至失去对机动车辆的正常操控，进而使得此类主动安全系统成为诱发道路交通事故的主要因素之一。因此，对高速公路行车环境下驾驶人换道意图进行识别对于提高驾驶安全性改善交通环境具有重要的意义。
在特定的交通环境下，驾驶行为具有一定的规律性。驾驶意图是驾驶人的自我内心状态，在驾驶过程中无法直接获取，只能依靠驾驶过程中驾驶人的动作、姿态及车辆状态等间接信息进行推测。简单来说，驾驶意图决定驾驶行为，驾驶行为实现了驾驶意图。从驾驶人对车辆的控制及驾驶人本身的视觉特性两个角度进行分析与推演，是进行驾驶人意图识别的重要方法。
本文结合国家自然科学基金青年科学基金项目“换道超车驾驶行为安全性预警方法研究”，在分析、总结国内外驾驶意图识别方法现有成果的基础上，以准确识别不同风格驾驶人高速公路行车环境下的换道意图为目标，对换道意图阶段和车道保持阶段驾驶人视觉特性参数及车辆运行状态参数进行了深入研究和分析，提出了表征驾驶人换道意图的不同类型特征参数组，研究并建立了不同风格驾驶人换道意图识别模型，从准确率、灵敏度和特异性等方面研究了驾驶风格、特征参数类型及建模方法对换道意图识别效果的影响，为换道意图识别系统的实用化奠定了一定的理论基础和技术支撑。具体研究内容如下：
1.试验方案设计和数据采集。首先，在分析国内外相关研究的基础上，结合论文的研究目的，将换道行为划分为意图阶段和执行阶段。接着，进行试验方案的设计，包括采集设备的安装调试、试验场景的开发、试验过程的规范化及需求参数的选择等。同时，基于调查问卷对21名驾驶人按驾驶风格进行分类，分为谨慎型、正常型和激进型。通过异常数据剔除对原始数据进行了预处理，并结合换道意图时窗确定方法，分别建立了不同驾驶风格的驾驶人在左、右换道意图阶段和车道保持阶段的训练样本库和测试样本库，为后续章节的研究提供数据支撑。
2.不同意图阶段驾驶人视觉特性分析。首先，采用基于驾驶人特性的静态及动态结合的注视区域划分方法，将驾驶人高速公路行车过程中的感兴趣区域划分为车辆正前方、左后视镜、右后视镜、仪表盘及内后视镜等五个区域。接着，结合试验数据及录像，分别从注视行为、扫视行为及头部转动情况三个角度，深入分析了不同风格驾驶人在换道意图阶段和车道保持阶段的视觉特性参数的变化规律，并运用独立样本T检验和单因素方差分析分别量化了驾驶阶段和驾驶风格对视觉参数的影响。最终，提出了表征驾驶人换道意图的视觉特性参数为：对后视镜的注视次数、平均扫视幅度和头部水平转角标准差。
3.不同意图阶段车辆运行状态参数分析。首先，对转向灯使用情况进行了统计分析，结果表明，因驾驶风格及个人习惯的不同，转向灯开启率和提前开启时间存在显著差异，但整体来看，转向灯提前开启时间明显不足。接着，从车辆横向运动及纵向运动表征参数两个角度，研究了不同风格驾驶人在换道意图阶段和车道保持阶段车辆运行状态参数的变化规律，在对参数进行直观分析的基础上，运用独立样本T检验和单因素方差分析量化了驾驶阶段和驾驶风格对车辆运行状态参数的影响，利用相关性分析，研究了不同参数之间的相关性，为降低高维特征空间的维数提供了一定的依据。最终，提出了表征高速公路驾驶人换道意图的车辆运行状态参数为方向盘转角熵值。
4.换道意图识别模型建立。基于混合高斯隐马尔科夫模型(GaussianMixture-Hidden Markov Model，GM-HMM)和支持向量机(Support Vector Machine，SVM)建立了驾驶人换道意图识别模型。为了对比不同特征参数类型对识别效果的影响，模型建立过程中采用了五类特征参数集分别对模型进行了离线训练，得到了相应的模型参数。
5.模型评价及识别效果分析。利用测试样本集对所建立的模型进行测试，并利用准确率、灵敏度和特异性三个模型评价函数对所建立的模型进行评价，深入分析了驾驶风格、特征参数类型及建模方法对识别效果的影响。结果表明，以“Head&Eye&Vehicle”为特征参数，基于GM-HMM建立的驾驶人换道意图识别模型识别效果最优。
论文针对高速公路驾驶人换道意图识别系统面临的关键技术问题进行了系统深入的研究，分析了驾驶风格对驾驶行为的影响，确立了表征高速公路驾驶人换道意图的特征参数组，并建立了换道意图识别模型。其研究成果能够为汽车主动安全辅助系统的研究和应用提供一定的理论和技术支持，从而提高驾驶人的行车安全性和舒适性并改善交通环境。
Owing to the high speed, the loss of life and property caused by traffic accidents inhighway is relatively more serious. Lane changing and keeping are two typical drivingbehaviors of highway, which have serious impact on driving safety. Therefore, variouslane-changing assistant systems have been developed by researchers. When perceivingenvironment, the existing systems mainly use radar and vision for environment informationand vehicle state perception and always neglect driver’s behavior motivation and drivingintention. So due to the misunderstanding of driver’s true intention, systems often alarm andexecute actions forcibly dissimilarly with driver intention, which could lead to driver’sdistraction, tension even losing regular control of vehicle, then the active safety systembecomes the incentive for traffic accidents. As a result, intention recognition of driver’slane-changing in highway environment has important significance for enhancing drivingsafety and improving traffic environment.
In specific traffic environment, driver’s behavior has a certain regularity and similarity.As an ego inner state, driver intention couldn’t be obtained directly during driving process,but conjectured through indirect information such as driver’s action, gesture and vehiclestate during the driving. Simply, drive intention determines the behavior and drive behaviorrealizes the intention. Analyzing and deducing the driver’s visual characteristics and drivingperformance measures is an important method for driver intention recognition.
This research was supported by the National Natural Science Foundation for YoungScholars of China “Research on driving behavior safety warning system for lane-changingand overtaking”. By summarizing current research achievement at home and aboard, withthe aim of recognizing lane change intention on highway situation accurately and timely, thisresearch went into the driver’s visual characteristics and vehicle performance measureschanging law during the stage of lane-changing intention and lane-keeping from drivers withdifferent driving styles. As a result, the effective characteristic parameters set of lane changeintention was got optimized. Lane-changing and keeping intention recognition model forhighway were researched and established. Finally, the effect of driving styles, characteristicparameters and modeling methods on intention recognition was analyzed and compared according to accuracy, sensitivity and specificity. The achievements lay the theoreticalfoundation and technical support for the pratical lane change intention recognition system.The specific research contents are as follows:
1. Experiment program designation and data collection. First, the lane-changingbehavior was divided into intentional and executive section based on the related research athome and abroad combined with this research’s purpose. Second, experiment project wasdesigned, including installing the collecting devices, developing the traffic scenes,standarding the experiment process, selecting the measuers, etc. Based on questionnaires,21drivers were divided into radical, conservative and normal according to their driving styles.Through removing the abnormal data and combining the lane-changing intention timewindow for different style drivers, trainning and test database for different styles drivers andintentions was established, which could provide data support for following research.
2. Law analysis of drivers’ visual characteristics in different intention stages. First, thegaze areas in driving was divided into forward、left rear-mirror、right rear-mirror、instrumentpanel and internal rear-mirror by means of combing static and dynamic state based on drivercharacteristics. Second, from the perspective of gaze behavior、glance behavior and headrotation, combining with experimental data and videotape, the change law of visualcharacteristic parameters of different style drivers in lane-changing intention andlane-keeping stages were analyzed deeply, and independent-samples T test (T-test) andanalysis of variance (ANOVA) were used to quantify the effects of driving stage and drivingstyle on visual parameters. Finally, the optimal visual characteristics parameters set whichcould characterize the lane-changing intention was the fixation number of rear-mirror，theaverage saccade amplitude and the standard deviation of head horizontal direction angle.
3. Law analysis of driving performance measures in different stages. First, turn signalopen rate and open time in advance of different style drivers were statistically analyzed.Second, with classifying driving performance measures by lateral and longitudinalmovement, driving performance measures of different style drivers in lane-changingintention and lane-keeping stages were analyzed deeply. Based on the visual analysis ofessential features, the independent-samples T test (T-test) and analysis of variance (ANOVA)were used to quantify the effects of driving stage and driving style on driving performancemeasures. Besides, the research studied the correlation between driving performancemeasures by taking advantage of correlation analysis, and provides the basis for reducing thedimensionality of the multidimensional feature space. Finally, steering entropy was choosenas the driving performance characteristics parameters which could reflect the lane-changingintention in highway.
4. Research on the driver intention recognition model. According to the visual anddriving performance characteristics parameters of driver lane-changing intention in highway,driver intention recognition models were developed separately based on GM-HMM theoryand SVM theory. Different types of characteristics parameters were used respectively to trainthe driver intention recognition models off-line for constrasting the effect under differentcharacteristics parameters, and then the relevant model parameters were obtained.
5. Model evaluation and recognition effect analysis. Tested the established models usingthe test set, and evaluated the models by utilizing three model evaluation functions whichincluded accuracy, sensitivity and specificity，and the effect of driving styles, characteristicparameters and modeling methods on intention recognition was analyzed deeply. The resultsshow that the optimal recognition effect is achieved when choose Vehicle&Head&Eye asthe observation sequences and develop the recognition model based on GM-HMM theory.
Lane-Changing intention recognition methods and theories on highway were studieddeeply in this paper. The research analyzed that the impact of driving styles on drivingbehavior and established characteristic parameters which reflect lane-changing intentioneffectively. Finally, reasonable intention recognition model was set up. The research resultsprovide theoretical and technical support to the related field of active safety assistancesystems, and improve traffic safety, comfort and the traffic environment.
在特定的交通环境下，驾驶行为具有一定的规律性。驾驶意图是驾驶人的自我内心状态，在驾驶过程中无法直接获取，只能依靠驾驶过程中驾驶人的动作、姿态及车辆状态等间接信息进行推测。简单来说，驾驶意图决定驾驶行为，驾驶行为实现了驾驶意图。从驾驶人对车辆的控制及驾驶人本身的视觉特性两个角度进行分析与推演，是进行驾驶人意图识别的重要方法。
本文结合国家自然科学基金青年科学基金项目“换道超车驾驶行为安全性预警方法研究”，在分析、总结国内外驾驶意图识别方法现有成果的基础上，以准确识别不同风格驾驶人高速公路行车环境下的换道意图为目标，对换道意图阶段和车道保持阶段驾驶人视觉特性参数及车辆运行状态参数进行了深入研究和分析，提出了表征驾驶人换道意图的不同类型特征参数组，研究并建立了不同风格驾驶人换道意图识别模型，从准确率、灵敏度和特异性等方面研究了驾驶风格、特征参数类型及建模方法对换道意图识别效果的影响，为换道意图识别系统的实用化奠定了一定的理论基础和技术支撑。具体研究内容如下：
1.试验方案设计和数据采集。首先，在分析国内外相关研究的基础上，结合论文的研究目的，将换道行为划分为意图阶段和执行阶段。接着，进行试验方案的设计，包括采集设备的安装调试、试验场景的开发、试验过程的规范化及需求参数的选择等。同时，基于调查问卷对21名驾驶人按驾驶风格进行分类，分为谨慎型、正常型和激进型。通过异常数据剔除对原始数据进行了预处理，并结合换道意图时窗确定方法，分别建立了不同驾驶风格的驾驶人在左、右换道意图阶段和车道保持阶段的训练样本库和测试样本库，为后续章节的研究提供数据支撑。
2.不同意图阶段驾驶人视觉特性分析。首先，采用基于驾驶人特性的静态及动态结合的注视区域划分方法，将驾驶人高速公路行车过程中的感兴趣区域划分为车辆正前方、左后视镜、右后视镜、仪表盘及内后视镜等五个区域。接着，结合试验数据及录像，分别从注视行为、扫视行为及头部转动情况三个角度，深入分析了不同风格驾驶人在换道意图阶段和车道保持阶段的视觉特性参数的变化规律，并运用独立样本T检验和单因素方差分析分别量化了驾驶阶段和驾驶风格对视觉参数的影响。最终，提出了表征驾驶人换道意图的视觉特性参数为：对后视镜的注视次数、平均扫视幅度和头部水平转角标准差。
3.不同意图阶段车辆运行状态参数分析。首先，对转向灯使用情况进行了统计分析，结果表明，因驾驶风格及个人习惯的不同，转向灯开启率和提前开启时间存在显著差异，但整体来看，转向灯提前开启时间明显不足。接着，从车辆横向运动及纵向运动表征参数两个角度，研究了不同风格驾驶人在换道意图阶段和车道保持阶段车辆运行状态参数的变化规律，在对参数进行直观分析的基础上，运用独立样本T检验和单因素方差分析量化了驾驶阶段和驾驶风格对车辆运行状态参数的影响，利用相关性分析，研究了不同参数之间的相关性，为降低高维特征空间的维数提供了一定的依据。最终，提出了表征高速公路驾驶人换道意图的车辆运行状态参数为方向盘转角熵值。
4.换道意图识别模型建立。基于混合高斯隐马尔科夫模型(GaussianMixture-Hidden Markov Model，GM-HMM)和支持向量机(Support Vector Machine，SVM)建立了驾驶人换道意图识别模型。为了对比不同特征参数类型对识别效果的影响，模型建立过程中采用了五类特征参数集分别对模型进行了离线训练，得到了相应的模型参数。
5.模型评价及识别效果分析。利用测试样本集对所建立的模型进行测试，并利用准确率、灵敏度和特异性三个模型评价函数对所建立的模型进行评价，深入分析了驾驶风格、特征参数类型及建模方法对识别效果的影响。结果表明，以“Head&Eye&Vehicle”为特征参数，基于GM-HMM建立的驾驶人换道意图识别模型识别效果最优。
论文针对高速公路驾驶人换道意图识别系统面临的关键技术问题进行了系统深入的研究，分析了驾驶风格对驾驶行为的影响，确立了表征高速公路驾驶人换道意图的特征参数组，并建立了换道意图识别模型。其研究成果能够为汽车主动安全辅助系统的研究和应用提供一定的理论和技术支持，从而提高驾驶人的行车安全性和舒适性并改善交通环境。
Owing to the high speed, the loss of life and property caused by traffic accidents inhighway is relatively more serious. Lane changing and keeping are two typical drivingbehaviors of highway, which have serious impact on driving safety. Therefore, variouslane-changing assistant systems have been developed by researchers. When perceivingenvironment, the existing systems mainly use radar and vision for environment informationand vehicle state perception and always neglect driver’s behavior motivation and drivingintention. So due to the misunderstanding of driver’s true intention, systems often alarm andexecute actions forcibly dissimilarly with driver intention, which could lead to driver’sdistraction, tension even losing regular control of vehicle, then the active safety systembecomes the incentive for traffic accidents. As a result, intention recognition of driver’slane-changing in highway environment has important significance for enhancing drivingsafety and improving traffic environment.
In specific traffic environment, driver’s behavior has a certain regularity and similarity.As an ego inner state, driver intention couldn’t be obtained directly during driving process,but conjectured through indirect information such as driver’s action, gesture and vehiclestate during the driving. Simply, drive intention determines the behavior and drive behaviorrealizes the intention. Analyzing and deducing the driver’s visual characteristics and drivingperformance measures is an important method for driver intention recognition.
This research was supported by the National Natural Science Foundation for YoungScholars of China “Research on driving behavior safety warning system for lane-changingand overtaking”. By summarizing current research achievement at home and aboard, withthe aim of recognizing lane change intention on highway situation accurately and timely, thisresearch went into the driver’s visual characteristics and vehicle performance measureschanging law during the stage of lane-changing intention and lane-keeping from drivers withdifferent driving styles. As a result, the effective characteristic parameters set of lane changeintention was got optimized. Lane-changing and keeping intention recognition model forhighway were researched and established. Finally, the effect of driving styles, characteristicparameters and modeling methods on intention recognition was analyzed and compared according to accuracy, sensitivity and specificity. The achievements lay the theoreticalfoundation and technical support for the pratical lane change intention recognition system.The specific research contents are as follows:
1. Experiment program designation and data collection. First, the lane-changingbehavior was divided into intentional and executive section based on the related research athome and abroad combined with this research’s purpose. Second, experiment project wasdesigned, including installing the collecting devices, developing the traffic scenes,standarding the experiment process, selecting the measuers, etc. Based on questionnaires,21drivers were divided into radical, conservative and normal according to their driving styles.Through removing the abnormal data and combining the lane-changing intention timewindow for different style drivers, trainning and test database for different styles drivers andintentions was established, which could provide data support for following research.
2. Law analysis of drivers’ visual characteristics in different intention stages. First, thegaze areas in driving was divided into forward、left rear-mirror、right rear-mirror、instrumentpanel and internal rear-mirror by means of combing static and dynamic state based on drivercharacteristics. Second, from the perspective of gaze behavior、glance behavior and headrotation, combining with experimental data and videotape, the change law of visualcharacteristic parameters of different style drivers in lane-changing intention andlane-keeping stages were analyzed deeply, and independent-samples T test (T-test) andanalysis of variance (ANOVA) were used to quantify the effects of driving stage and drivingstyle on visual parameters. Finally, the optimal visual characteristics parameters set whichcould characterize the lane-changing intention was the fixation number of rear-mirror，theaverage saccade amplitude and the standard deviation of head horizontal direction angle.
3. Law analysis of driving performance measures in different stages. First, turn signalopen rate and open time in advance of different style drivers were statistically analyzed.Second, with classifying driving performance measures by lateral and longitudinalmovement, driving performance measures of different style drivers in lane-changingintention and lane-keeping stages were analyzed deeply. Based on the visual analysis ofessential features, the independent-samples T test (T-test) and analysis of variance (ANOVA)were used to quantify the effects of driving stage and driving style on driving performancemeasures. Besides, the research studied the correlation between driving performancemeasures by taking advantage of correlation analysis, and provides the basis for reducing thedimensionality of the multidimensional feature space. Finally, steering entropy was choosenas the driving performance characteristics parameters which could reflect the lane-changingintention in highway.
4. Research on the driver intention recognition model. According to the visual anddriving performance characteristics parameters of driver lane-changing intention in highway,driver intention recognition models were developed separately based on GM-HMM theoryand SVM theory. Different types of characteristics parameters were used respectively to trainthe driver intention recognition models off-line for constrasting the effect under differentcharacteristics parameters, and then the relevant model parameters were obtained.
5. Model evaluation and recognition effect analysis. Tested the established models usingthe test set, and evaluated the models by utilizing three model evaluation functions whichincluded accuracy, sensitivity and specificity，and the effect of driving styles, characteristicparameters and modeling methods on intention recognition was analyzed deeply. The resultsshow that the optimal recognition effect is achieved when choose Vehicle&Head&Eye asthe observation sequences and develop the recognition model based on GM-HMM theory.
Lane-Changing intention recognition methods and theories on highway were studieddeeply in this paper. The research analyzed that the impact of driving styles on drivingbehavior and established characteristic parameters which reflect lane-changing intentioneffectively. Finally, reasonable intention recognition model was set up. The research resultsprovide theoretical and technical support to the related field of active safety assistancesystems, and improve traffic safety, comfort and the traffic environment.
引文
[1] Wu Y H, Xie J X, Du LH, et al. Analysis on traffic safety distance of considering thedeceleration of the current vehicle[C].The Second International Conference onIntelligent Computation Technology and Automation.2009:490-493.
[2] Jin L S, Wang R B, Yu T H, et al. Lane departure warning system based on monocularvision[C].14th World Congress on ITS, Beijing,2007.
[3] Mammar S. Time to Line Crossing for Lane Departure Avoidance: A Theoretical Studyand an Experimental Setting [J].IEEE Transactions on Intelligent TransportationSystems，2006，7(11):226-241.
[4] Jin L S. Niu Q N. Hou H J, et al. Driver Cognitive Distraction Detection Using DrivingPerformance Measures [J]. Discrete Dynamics in Nature and Society,2012:1-12
[5] Pei Y L, Xu H Z. The Control Mechanism of Lane-Changing in Jam Condition [C].Proceedings of th6thWorld Congress on Intelligent Control and Automation, Dalian,2006:8650-8654.
[6] Ammoun S, Nashashibi F, Laurgeau C. An Analysis of the Lane Changing Maneuver onRoads: the Contribution of Inter-vehicle Cooperation via Communication[C].Proceedings of the Intelligent Vehicles Symposium. Istanbul: IEEE,2007:1095-1100.
[7] Wu L J，Liu Z D. Longitudinal Control Strategy for Vehicle Adaptive Cruise ControlSystems[J].Journal of Beijing Institute of Technology，2007，(1)：28-33.
[8] Kim S Y, Oh S Y, Kang J G, et al. Front and Rear Vehicle Detection and Tracking in theDay and Night Time Using Vision and Sonar Sensors[C].12th World Congress on ITS,2005:3145-3156.
[9] Tim V D, Geert A J V H. Vision-Sense: An advanced lateral collision warningsystem[C].IEEE Transactions on Control Systems Technology,2005:296-301.
[10]公安部交通管理局，中华人民共和国道路交通事故统计年报(2010年度)[M].2011年6月.
[11]Ishida S, Gayko J E, Development evaluation and introduction of a lane keepingassistance system [C].2004IEEE Intelligent Vehicle Symposium, Parma, Italy2004:943-944.
[12]Olson E C B, Modeling slow lead vehicle lane changing. Industrial and SystemsEngineering [D], Blacksburg: Virginia Polytechnic Institute and State University,2003.
[13]Lee S E, Olsen E C B, Wierwille W W. A Comprehensive Examination of NaturalisticLane-Changes[R]. Nat. Highway Traffic Safety Admin., U.S. Dept. Transp., Washington,DC, Rep. DOT HS809702.2004.
[14]张磊.基于驾驶员特性自学习方法的车辆纵向驾驶辅助系统[D].北京：清华大学.2009.
[15]Liu A, Pentland A. Towards real-time recognition of driver intentions[C]. IEEEConference on Intelligent Transportation System.1997:236-241.
[16]Pentland A, Liu A. Modeling and Prediction of Human Behavior [J]. NeuralComputation (1999)11:229–242.
[17]Oliver N, Pentland A P. Graphical Models for Driver Behavior Recognition in aSmartCar [C].2000Proceedings of the IEEE Intelligent Vehicles Symposium.2000:7-12.
[18]N Kuge, Yamamura T, Shimoyama O, Liu A. A Driver Behavior Recognition MethodBased On a Driver Model Framework [J]. SAE,2000.
[19]Berndt H, Emmert J, and Dietmayer K. Continuous Driver Intention Recognition withHidden Markov Models [C].11th International IEEE Conference on IntelligentTransportation Systems.2008:1189-1194.
[20]Mandalia H M, Pattern Recognition Techniques to Infer Driver Intentions [D].Philadelphia: Department of Computer Science, Drexel University,2004.
[21]Sathyanarayana A, Boyraz P, Hansen J H L. Driver Behavior Analysis and RouteRecognition by Hidden Markov Models [C], Proceedings of the2008IEEE InternationalConference on Vehicular Electronics and Safety,2008:276-281.
[22]Aoude G S, How J P. Using Support Vector Machines and Bayesian Filtering forClassifying Agent Intentions at Road Intersections[J/OL], Massachusetts Institute ofTechnology, Tech. Rep. ACL09-02, September2009.:http://hdl.handle.net/1721.1/46720.
[23]Salvucci D D, Inferring Driver Intent: a Case Study in Lane-Change Detection[C].Proceedings of the Human Factors Ergonomics Society48th Annual Meeting,2004.
[24]Ohashi L, Yamaguchi T, and Tamai I. Humane automotive system using driver intentionrecognition [C]. SICE2004Annual Conference.2004:1164-1167.
[25]Lethaus F, Rataj J. Do eye movements reflect driving manoeuvres?[C]. IET IntelligentTransportation System.2007,1(3):199-204.
[26]McCall J C, Wipf D P, Trivedi M M, et al. Lane change intent analysis using robustoperators and sparse Bayesian learning [J]. IEEE Transactions on IntelligentTransportation Systems,2007,8(3):431-440.
[27]Doshi A and Trivedi M M, A Comparative Exploration of Eye Gaze and Head MotionCues for Lane Change Intent Prediction [C].2008IEEE Intelligent Vehicles Symposium,2008:49-54.
[28]Doshi A, Trivedi M M. On the Roles of Eye Gaze and Head Dynamics in PredictingDriver's Intent to Change Lanes[C], IEEE Transactions on Intelligent TransportationSystem,2009,10(3):453-462.
[29]Zhou H P, Itoh M, and Inagaki T. Detection of Driver Intention of a Lane Changethrough Monitoring Eye and Head Movements[C]. Proc. SICE Symposium on Systemand Information,2006:231-236.
[30]Zhou H P, Itoh M, and Inagaki T. Influence of cognitively distracting activity on driver’seye movement during preparation of changing lanes[C]. SICE Annual Conference2008,Japan,2008:866-871.
[31]Zhou H P, Itoh M, and Inagaki T. How do cognitive distraction affect driver intent ofchanging lanes?[C]. ICIRA2009:235-244.
[32]魏丽英,隽志才,田春林.驾驶员车道变换行为模拟分析[J].中国公路学报,2001.14(1):77-80.
[33]韩珍.驾驶员-车辆Agent微观换道行为的建模[D].北京:中国科技大学,2011.
[34]曹珊.城市道路车辆换道模型及换道影响研究[D].武汉:华中科技大学,2009.
[35]杨小宝,张宁,黄留兵.通行能力仿真中的换道模型研究[J].公路交通科技,2007.24(5):109-113.
[36]金立生, Bart V A,杨双宾等.高速公路汽车辅助驾驶安全换道模型[J].吉林大学学报(工学版),2009.39(3):582-586.
[37]杨双宾.高速公路车辆行驶安全辅助换道预警系统研究[D].长春:吉林大学,2008.
[38]毛锦.考虑驾驶风格的换道预警方法[D].西安:长安大学,2012.
[39]徐慧智,裴玉龙,于涛等.驾驶员车道变换行为视点转移特性研究[J].哈尔滨理工大学学报,2010.15(5):57-60.
[40]裴玉龙,张银.车道变换期望运行轨迹仿真[J].交通与计算机,2008,26(4):68-71.
[41]霍克.城市道理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.
[42]吴付威.跟车和换道过程中驾驶人注视转移模式研究[D].西安:长安大学,2012.
[43]王玉海，宋健，李兴坤.驾驶员意图与行驶环境的统一识别及实时算法[J].机械工程学报,2006.42(4):206-212.
[44]王庆年，唐先智，王鹏宇等.基于驾驶意图识别的混合动力汽车控制策略[J].吉林大学学报(工学版),2012.42(4):789-795.
[45]王英范，宁国宝，余卓平.乘用车驾驶员制动意图识别参数的选择[J].汽车工程,2011.33(3):213-217.
[46]郭孜政,陈崇双,王欣.基于贝叶斯判别的驾驶行为危险状态辨识[J].西南交通大学学报,2009.44(5):771-775.
[47]宗长富,王畅,何磊等.基于双层隐式马尔科夫模型的驾驶意图辨识.汽车工程，2011(Vol.33)No.8.
[48]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.
[49]孙纯.基于驾驶人视觉特性的换道意图识别[D].西安:长安大学,2012.
[50]Winsum W V, Waard D D, Brookhuis K A. Lane Change Maneuvers and SafetyMargins[J]. Transportation Research Part F2(1999)139-149.
[51]杨建国,王金梅,李庆丰,王兆安.微观仿真中车辆换道的行为分析和建模.公路交通科技,2004.21(11):93-97.
[52]Worrall R D, Bullen A G. An empirical analysis of lane changing on multilane highways[R]. Washington: Highway Research Board，1970(303):30-43.
[53]黄秋菊.车道变换行为特性及其对交通安全影响的研究[D].哈尔滨:哈尔滨工业大学大学交通科学与工程学院,2007.
[54]Reason J T, Manstead A S R, Stradling S, et al. Errors and violations on the roads: a realdistinction?[J]. Ergonomics,1990,33(10-11):1315-1332.
[55]Ozkan T, Lajunen T. A new addition to DBQ: Positive Driver Behaviour Scale.Transportation Research Part F: Traffic Psychology and Behaviour.2005(8):355-368.
[56]Lajunen T, Parker D, Summala H. The Manchester driver behaviour questionnaire: across-cultural study [J]. Accident Analysis and Prevention,2004,36(2):231-238.
[57]King Y, Parker D. Driving violations, aggression and perceived consensus infractions aucode de la route, aggressive et consensus percu[J]. Revue Europeenne de PsychologieAppliquee,2008,58(1):43-49.
[58]柯惠新,沈浩.调查研究中的统计分析法(第二版)[M].北京:中国传媒大学出版社,2005, ISBN7-81085-261-2/K.119.
[59]Lee J. Cronbach. Coefficient alpha and the internal structure of tests [J]. Psychometrika,1951,16(3):297-334.
[60]张宇镭,袁伟，城市道路环境中汽车驾驶员动态视觉特性试验研究[D]，西安：长安大学，2008年.
[61]袁伟，城市道路环境中汽车驾驶员动态视觉特性试验研究[D]，西安：长安大学，2008年.
[62]陈建珍，潘涌智，李任波.基于Matlab的二维实验数据粗差检测[J]，误差与数据处理，计量技术2007, No.5:61-63
[63]Kiefer R J, Hankey J M. Lane change behavior with a side blind zone alert system [J].Accident Analysis and Prevention40(2008):683-690.
[64]白学军，闫国利主编.眼动研究在中国[M].天津教育出版社.2008.6:3-18.
[65]Crundall D，Underwood G．Effects of experience and processing demands on visualinformation acquisition in drivers [J]．Ergonomics，1998，41(4):448-458.
[66]孟妮.不同道路交通环境中驾驶员注视行为分析[D].长安：长安大学.2009.
[67]Louis T, Garrott W G, Stoltzfus D, et al. Eye Glance Behavior of Van and Passenger CarDriver Eye Glance Behavior During the Lane Change Decision Phase [J]. TransportationResearch Record: Journal of the Transportation Research Board,1937/2005:37-43.
[68]Bao S, Boyle L N. Age-related differences in visual scanning at median-dividedhighway intersections in rural areas. Accident Analysis&Prevention,2009,41(1):146-152
[69]Geoffrey Underwood， David Crundall， Peter Chapman． Selective searching whiledriving: the role of experience in hazard detection and general surveillance[J]．Ergonomics，2002，45(1):1-15.
[70]Nakayama O, Tohru F, Nakamura T, Boer E R. Development of a steering entropymethod for evaluating driver workload[C].1999Proceeding SAE International Congressand Exposition:1-10.
[71]Mar J, Lin H T. The car-following and lane-changing collision prevention system basedon the cascaded fuzzy inference system [J].IEEE Transactions on Vehicular Technology,2005,54(3):910-924.
[72]Rabiner L R. A Tutorial on Hidden Markov Models and Selected Applications in SpeechRecognition[J]. Proceedings of the IEEE,1989,77(2):257.
[73]Kobayashi T, Haruyama S．Partly-Hidden Markov model and its application to gesturerecognition [C]. In：Taylor FJ，ed．Proc．of the Int’1Conf．on Acoustics，Speech andSignal Processing．New York：Academic Press，1997．3081-3084.
[74]易克初，田斌，付强.语音信号处理[M].国防工业出版社.2000.
[75]宋雪萍,马辉,毛国豪等.基于CHMM的旋转机械故障诊断技术[J].机械工程学报,2006,42(5):126-130.
[76]乔跃刚,赵铁军,李生等.基于SCHMM非特定人关键词检出语音识别系统[J].计算机应用,2005(25):295-297.
[77]刘河生，高小榕，杨福生.隐马尔可夫模型的原理与实现[J].国外医学生物医学工程分册,2002年,25(6)：253-259.
[78]http://www.cs.ubc.ca/~murphyk/Software/HMM/hmm.html
[79]Meng X N, Lee K K, Xu Y S. Human Driving Behavior Recognition Based on HiddenMarkov Models[C]. Proceedings of the2006IEEE International Conference onRobotics and Biomimetics, Kunming China,2006:274-279.
[80]Hou H J, Jin L S, Niu Q N, et al. Driver Intention Recognition Method UsingContinuous Hidden Markov Model [J], International Journal of ComputationalIntelligence Systems,2011,4(3):386-393
[81]Rabiner L R, Wilpon J G, Soong F K. High Performance Connected Digit RecognitionUsing Hidden Markov Models. IEEE Trans. ASSP,1989,37(8):1214-1225.
[82]Vapnik V N. The Nature of Statistical Learning Theory [M]. New York:Springer-Verlag,1995.
[83]VAPNIK V N.统计学习理论的本质[M].张学工,译.北京:清华大学出版社,2000.
[84]Chang C C, Lin C J, LIBSVM: A Library for Support Vector Machines.[Online].Available: http://www.csie.ntu.edu.tw/~cjlin/libsvm/index.html.
[85]王运生,谢丙炎,万方浩等. ROC曲线分析在评价入侵物种分布模型中的应用.生物多样性2007,15(4):365–372.
[2] Jin L S, Wang R B, Yu T H, et al. Lane departure warning system based on monocularvision[C].14th World Congress on ITS, Beijing,2007.
[3] Mammar S. Time to Line Crossing for Lane Departure Avoidance: A Theoretical Studyand an Experimental Setting [J].IEEE Transactions on Intelligent TransportationSystems，2006，7(11):226-241.
[4] Jin L S. Niu Q N. Hou H J, et al. Driver Cognitive Distraction Detection Using DrivingPerformance Measures [J]. Discrete Dynamics in Nature and Society,2012:1-12
[5] Pei Y L, Xu H Z. The Control Mechanism of Lane-Changing in Jam Condition [C].Proceedings of th6thWorld Congress on Intelligent Control and Automation, Dalian,2006:8650-8654.
[6] Ammoun S, Nashashibi F, Laurgeau C. An Analysis of the Lane Changing Maneuver onRoads: the Contribution of Inter-vehicle Cooperation via Communication[C].Proceedings of the Intelligent Vehicles Symposium. Istanbul: IEEE,2007:1095-1100.
[7] Wu L J，Liu Z D. Longitudinal Control Strategy for Vehicle Adaptive Cruise ControlSystems[J].Journal of Beijing Institute of Technology，2007，(1)：28-33.
[8] Kim S Y, Oh S Y, Kang J G, et al. Front and Rear Vehicle Detection and Tracking in theDay and Night Time Using Vision and Sonar Sensors[C].12th World Congress on ITS,2005:3145-3156.
[9] Tim V D, Geert A J V H. Vision-Sense: An advanced lateral collision warningsystem[C].IEEE Transactions on Control Systems Technology,2005:296-301.
[10]公安部交通管理局，中华人民共和国道路交通事故统计年报(2010年度)[M].2011年6月.
[11]Ishida S, Gayko J E, Development evaluation and introduction of a lane keepingassistance system [C].2004IEEE Intelligent Vehicle Symposium, Parma, Italy2004:943-944.
[12]Olson E C B, Modeling slow lead vehicle lane changing. Industrial and SystemsEngineering [D], Blacksburg: Virginia Polytechnic Institute and State University,2003.
[13]Lee S E, Olsen E C B, Wierwille W W. A Comprehensive Examination of NaturalisticLane-Changes[R]. Nat. Highway Traffic Safety Admin., U.S. Dept. Transp., Washington,DC, Rep. DOT HS809702.2004.
[14]张磊.基于驾驶员特性自学习方法的车辆纵向驾驶辅助系统[D].北京：清华大学.2009.
[15]Liu A, Pentland A. Towards real-time recognition of driver intentions[C]. IEEEConference on Intelligent Transportation System.1997:236-241.
[16]Pentland A, Liu A. Modeling and Prediction of Human Behavior [J]. NeuralComputation (1999)11:229–242.
[17]Oliver N, Pentland A P. Graphical Models for Driver Behavior Recognition in aSmartCar [C].2000Proceedings of the IEEE Intelligent Vehicles Symposium.2000:7-12.
[18]N Kuge, Yamamura T, Shimoyama O, Liu A. A Driver Behavior Recognition MethodBased On a Driver Model Framework [J]. SAE,2000.
[19]Berndt H, Emmert J, and Dietmayer K. Continuous Driver Intention Recognition withHidden Markov Models [C].11th International IEEE Conference on IntelligentTransportation Systems.2008:1189-1194.
[20]Mandalia H M, Pattern Recognition Techniques to Infer Driver Intentions [D].Philadelphia: Department of Computer Science, Drexel University,2004.
[21]Sathyanarayana A, Boyraz P, Hansen J H L. Driver Behavior Analysis and RouteRecognition by Hidden Markov Models [C], Proceedings of the2008IEEE InternationalConference on Vehicular Electronics and Safety,2008:276-281.
[22]Aoude G S, How J P. Using Support Vector Machines and Bayesian Filtering forClassifying Agent Intentions at Road Intersections[J/OL], Massachusetts Institute ofTechnology, Tech. Rep. ACL09-02, September2009.:http://hdl.handle.net/1721.1/46720.
[23]Salvucci D D, Inferring Driver Intent: a Case Study in Lane-Change Detection[C].Proceedings of the Human Factors Ergonomics Society48th Annual Meeting,2004.
[24]Ohashi L, Yamaguchi T, and Tamai I. Humane automotive system using driver intentionrecognition [C]. SICE2004Annual Conference.2004:1164-1167.
[25]Lethaus F, Rataj J. Do eye movements reflect driving manoeuvres?[C]. IET IntelligentTransportation System.2007,1(3):199-204.
[26]McCall J C, Wipf D P, Trivedi M M, et al. Lane change intent analysis using robustoperators and sparse Bayesian learning [J]. IEEE Transactions on IntelligentTransportation Systems,2007,8(3):431-440.
[27]Doshi A and Trivedi M M, A Comparative Exploration of Eye Gaze and Head MotionCues for Lane Change Intent Prediction [C].2008IEEE Intelligent Vehicles Symposium,2008:49-54.
[28]Doshi A, Trivedi M M. On the Roles of Eye Gaze and Head Dynamics in PredictingDriver's Intent to Change Lanes[C], IEEE Transactions on Intelligent TransportationSystem,2009,10(3):453-462.
[29]Zhou H P, Itoh M, and Inagaki T. Detection of Driver Intention of a Lane Changethrough Monitoring Eye and Head Movements[C]. Proc. SICE Symposium on Systemand Information,2006:231-236.
[30]Zhou H P, Itoh M, and Inagaki T. Influence of cognitively distracting activity on driver’seye movement during preparation of changing lanes[C]. SICE Annual Conference2008,Japan,2008:866-871.
[31]Zhou H P, Itoh M, and Inagaki T. How do cognitive distraction affect driver intent ofchanging lanes?[C]. ICIRA2009:235-244.
[32]魏丽英,隽志才,田春林.驾驶员车道变换行为模拟分析[J].中国公路学报,2001.14(1):77-80.
[33]韩珍.驾驶员-车辆Agent微观换道行为的建模[D].北京:中国科技大学,2011.
[34]曹珊.城市道路车辆换道模型及换道影响研究[D].武汉:华中科技大学,2009.
[35]杨小宝,张宁,黄留兵.通行能力仿真中的换道模型研究[J].公路交通科技,2007.24(5):109-113.
[36]金立生, Bart V A,杨双宾等.高速公路汽车辅助驾驶安全换道模型[J].吉林大学学报(工学版),2009.39(3):582-586.
[37]杨双宾.高速公路车辆行驶安全辅助换道预警系统研究[D].长春:吉林大学,2008.
[38]毛锦.考虑驾驶风格的换道预警方法[D].西安:长安大学,2012.
[39]徐慧智,裴玉龙,于涛等.驾驶员车道变换行为视点转移特性研究[J].哈尔滨理工大学学报,2010.15(5):57-60.
[40]裴玉龙,张银.车道变换期望运行轨迹仿真[J].交通与计算机,2008,26(4):68-71.
[41]霍克.城市道理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.
[42]吴付威.跟车和换道过程中驾驶人注视转移模式研究[D].西安:长安大学,2012.
[43]王玉海，宋健，李兴坤.驾驶员意图与行驶环境的统一识别及实时算法[J].机械工程学报,2006.42(4):206-212.
[44]王庆年，唐先智，王鹏宇等.基于驾驶意图识别的混合动力汽车控制策略[J].吉林大学学报(工学版),2012.42(4):789-795.
[45]王英范，宁国宝，余卓平.乘用车驾驶员制动意图识别参数的选择[J].汽车工程,2011.33(3):213-217.
[46]郭孜政,陈崇双,王欣.基于贝叶斯判别的驾驶行为危险状态辨识[J].西南交通大学学报,2009.44(5):771-775.
[47]宗长富,王畅,何磊等.基于双层隐式马尔科夫模型的驾驶意图辨识.汽车工程，2011(Vol.33)No.8.
[48]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.
[49]孙纯.基于驾驶人视觉特性的换道意图识别[D].西安:长安大学,2012.
[50]Winsum W V, Waard D D, Brookhuis K A. Lane Change Maneuvers and SafetyMargins[J]. Transportation Research Part F2(1999)139-149.
[51]杨建国,王金梅,李庆丰,王兆安.微观仿真中车辆换道的行为分析和建模.公路交通科技,2004.21(11):93-97.
[52]Worrall R D, Bullen A G. An empirical analysis of lane changing on multilane highways[R]. Washington: Highway Research Board，1970(303):30-43.
[53]黄秋菊.车道变换行为特性及其对交通安全影响的研究[D].哈尔滨:哈尔滨工业大学大学交通科学与工程学院,2007.
[54]Reason J T, Manstead A S R, Stradling S, et al. Errors and violations on the roads: a realdistinction?[J]. Ergonomics,1990,33(10-11):1315-1332.
[55]Ozkan T, Lajunen T. A new addition to DBQ: Positive Driver Behaviour Scale.Transportation Research Part F: Traffic Psychology and Behaviour.2005(8):355-368.
[56]Lajunen T, Parker D, Summala H. The Manchester driver behaviour questionnaire: across-cultural study [J]. Accident Analysis and Prevention,2004,36(2):231-238.
[57]King Y, Parker D. Driving violations, aggression and perceived consensus infractions aucode de la route, aggressive et consensus percu[J]. Revue Europeenne de PsychologieAppliquee,2008,58(1):43-49.
[58]柯惠新,沈浩.调查研究中的统计分析法(第二版)[M].北京:中国传媒大学出版社,2005, ISBN7-81085-261-2/K.119.
[59]Lee J. Cronbach. Coefficient alpha and the internal structure of tests [J]. Psychometrika,1951,16(3):297-334.
[60]张宇镭,袁伟，城市道路环境中汽车驾驶员动态视觉特性试验研究[D]，西安：长安大学，2008年.
[61]袁伟，城市道路环境中汽车驾驶员动态视觉特性试验研究[D]，西安：长安大学，2008年.
[62]陈建珍，潘涌智，李任波.基于Matlab的二维实验数据粗差检测[J]，误差与数据处理，计量技术2007, No.5:61-63
[63]Kiefer R J, Hankey J M. Lane change behavior with a side blind zone alert system [J].Accident Analysis and Prevention40(2008):683-690.
[64]白学军，闫国利主编.眼动研究在中国[M].天津教育出版社.2008.6:3-18.
[65]Crundall D，Underwood G．Effects of experience and processing demands on visualinformation acquisition in drivers [J]．Ergonomics，1998，41(4):448-458.
[66]孟妮.不同道路交通环境中驾驶员注视行为分析[D].长安：长安大学.2009.
[67]Louis T, Garrott W G, Stoltzfus D, et al. Eye Glance Behavior of Van and Passenger CarDriver Eye Glance Behavior During the Lane Change Decision Phase [J]. TransportationResearch Record: Journal of the Transportation Research Board,1937/2005:37-43.
[68]Bao S, Boyle L N. Age-related differences in visual scanning at median-dividedhighway intersections in rural areas. Accident Analysis&Prevention,2009,41(1):146-152
[69]Geoffrey Underwood， David Crundall， Peter Chapman． Selective searching whiledriving: the role of experience in hazard detection and general surveillance[J]．Ergonomics，2002，45(1):1-15.
[70]Nakayama O, Tohru F, Nakamura T, Boer E R. Development of a steering entropymethod for evaluating driver workload[C].1999Proceeding SAE International Congressand Exposition:1-10.
[71]Mar J, Lin H T. The car-following and lane-changing collision prevention system basedon the cascaded fuzzy inference system [J].IEEE Transactions on Vehicular Technology,2005,54(3):910-924.
[72]Rabiner L R. A Tutorial on Hidden Markov Models and Selected Applications in SpeechRecognition[J]. Proceedings of the IEEE,1989,77(2):257.
[73]Kobayashi T, Haruyama S．Partly-Hidden Markov model and its application to gesturerecognition [C]. In：Taylor FJ，ed．Proc．of the Int’1Conf．on Acoustics，Speech andSignal Processing．New York：Academic Press，1997．3081-3084.
[74]易克初，田斌，付强.语音信号处理[M].国防工业出版社.2000.
[75]宋雪萍,马辉,毛国豪等.基于CHMM的旋转机械故障诊断技术[J].机械工程学报,2006,42(5):126-130.
[76]乔跃刚,赵铁军,李生等.基于SCHMM非特定人关键词检出语音识别系统[J].计算机应用,2005(25):295-297.
[77]刘河生，高小榕，杨福生.隐马尔可夫模型的原理与实现[J].国外医学生物医学工程分册,2002年,25(6)：253-259.
[78]http://www.cs.ubc.ca/~murphyk/Software/HMM/hmm.html
[79]Meng X N, Lee K K, Xu Y S. Human Driving Behavior Recognition Based on HiddenMarkov Models[C]. Proceedings of the2006IEEE International Conference onRobotics and Biomimetics, Kunming China,2006:274-279.
[80]Hou H J, Jin L S, Niu Q N, et al. Driver Intention Recognition Method UsingContinuous Hidden Markov Model [J], International Journal of ComputationalIntelligence Systems,2011,4(3):386-393
[81]Rabiner L R, Wilpon J G, Soong F K. High Performance Connected Digit RecognitionUsing Hidden Markov Models. IEEE Trans. ASSP,1989,37(8):1214-1225.
[82]Vapnik V N. The Nature of Statistical Learning Theory [M]. New York:Springer-Verlag,1995.
[83]VAPNIK V N.统计学习理论的本质[M].张学工,译.北京:清华大学出版社,2000.
[84]Chang C C, Lin C J, LIBSVM: A Library for Support Vector Machines.[Online].Available: http://www.csie.ntu.edu.tw/~cjlin/libsvm/index.html.
[85]王运生,谢丙炎,万方浩等. ROC曲线分析在评价入侵物种分布模型中的应用.生物多样性2007,15(4):365–372.