基于驾驶员视觉特性的驾驶行为预测方法研究
|
摘要
城市道路交通环境复杂多变，车辆之间交通冲突频繁，错误的驾驶行为将导致冲突进一步加剧，引发交通事故，由于近年来城市交通流中驾驶员非职业化、车流密集化趋势日益明显，使得城市交通环境下的驾驶行为研究显得尤为重要。而驾驶意图是驾驶行为的内在状态，驾驶意图辨识是驾驶行为预测的前提，因此，通过辨识城市交通环境下的驾驶意图，进而预测驾驶行为，对于提高驾驶安全性和改善交通环境具有重要的意义。
本文在分析总结国内外现有的关于驾驶行为预测以及意图辨识成果的基础上，以驾驶意图辨识为桥梁，预测城市道路交通环境驾驶员在行车过程中的驾驶行为。通过深入分析和研究驾驶员在跟驰、超车以及换道（包括左换道、右换道）行为及意图阶段视觉特征表征参数的变化规律，选取典型视觉特性表征参数表征驾驶员行为与意图，建立驾驶行为预测模型，提出了基于驾驶员视觉特性的驾驶行为预测方法，分析了驾驶行为表征参数及驾驶意图时窗对驾驶行为预测的影响，从理论层面和技术层面促进了驾驶行为预警系统的实用化。
论文具体研究工作如下：
1、城市交通环境驾驶行为与驾驶意图分析。首先，通过分析城市交通环境下的驾驶意图及驾驶行为形成机理，将城市环境下的驾驶行为分为跟驰、超车、左换道以及右换道4类；然后，通过分析驾驶行为与驾驶意图的关系，确定基于驾驶意图辨识的驾驶行为预测方法。以驾驶行为预测为目的，分析驾驶意图及驾驶行为的影响因素，确定表征驾驶意图和行为的视觉特性参数，为驾驶行为试验方案的设计以及驾驶行为预测参数的选取奠定基础。
2、试验方案设计和数据采集。首先，设计了实车道路试验方案，包括试验设备安装和调试、试验人员和路线选取、试验过程设计等。其次，进行道路试验，实时采集驾驶员行为及视觉特性数据；再次，应用拉依达准则，对异常数据进行剔除，并通过试验录像分析驾驶员操作行为，选取驾驶行为样本；最后，选取合理的数据驾驶行为预测数据，本文分别以4s、4.5s及5s作为驾驶意图时窗选取用于驾驶行为预测的训练样本数据库和评价样本数据库，为建立驾驶行为预测模型提供了数据支撑。
3、基于驾驶员视线点分布规律的驾驶员视野平面划分方法研究。首先，运用k均值聚类，分别选取k6、 k7以及k8，将驾驶员的视线点进行动态聚类。其次，运用拉依达准则将聚类后的驾驶员视线点坐标进行异常数据剔除，剔除偏离各区域的异常视线点；然后，将多次聚类后的驾驶员视线点投影到车辆前挡风玻璃中，通过对比分析各次聚类的优缺点，确定最终的聚类结果；最后，基于视线点分布将驾驶员的视野平面划分为正前方车道、左侧车道、右侧车道、左侧车外后视镜、右侧车外后视镜、车内后视镜和车内仪表盘七个区域。
4、不同驾驶行为下驾驶员视觉表征参数变化规律分析。以试验数据为基础，结合试验录像，从注视、扫视和头部转动三方面，深入分析不同驾驶行为对应的驾驶员眼睛及头部运动特性表征参数的变化规律，并运用Nemenyi秩和检验方法检验不同驾驶行为过程中各驾驶员视觉特性表征参数的差异性，最终确定能够表征驾驶员驾驶行为的视觉及头部运动指标。
5、驾驶行为预测模型的建立。首先，从隐马尔科夫理论的基本思想、基本算法以及分类等方面阐述了HMM的建模思想；然后，根据论文研究目的及要求，选取建模所需的驾驶行为视觉表征参数，从所有驾驶行为中选取100个样本作为训练样本进行模型训练，基于HMM算法建立驾驶行为预测模型；利用相关性分析，对所选取的参数进行简化，最终选取注视次数、扫视持续时间、扫视速度、注视点转移概率以及头部转角为建模参数。
6、模型评价及预测效果分析。首先，通过计算模型预测准确率，分析了模型的效果，结果表明，以4.5s作为驾驶意图时窗选取驾驶行为预测样本时，预测模型的准确率达到85%以上；其次，以4s和5s作为驾驶意图时窗选取驾驶行为预测样本，研究了样本选取对驾驶行为预测结果的影响，以危险驾驶行为预警为目的，以4.5s作为驾驶意图时窗选取样本数据进行了驾驶行为预测。
论文以驾驶员视觉特性为基础，以隐马尔科夫理论为手段，深入系统的研究了城市道路交通中驾驶员驾驶行为预测及意图辨识面临的关键技术问题。通过分析驾驶行为及其驾驶意图形成机理和影响因素，选取了城市道路行车过程中有效表征驾驶员行为的视觉参数，建立了驾驶行为预测模型。论文研究成果可为危险驾驶行为预警及安全驾驶辅助系统的开发提供一定的理论基础和技术支持。
The traffic environment of urban road is complicated, and traffic conflicts occurfrequently between vehicles, wrong driving behavior will lead these conflicts to bemore serious and cause traffic accidents. Because the trend that drivers areunprofessional and traffic is intensive become apparent increasingly in urban trafficflow recently, the research on driving behavior in urban traffic environment isparticularly important. And because driving intention is the internal state of drivingbehavior, the study on driving intention is the premise of driving behavior prediction.So driving intention identification and behavior prediction in urban trafficenvironment is significant to improve driving safety and traffic environment.
This paper analyze and summarize the driving intention recognition and behaviorprediction methods that are existing at home and aboard, driving intention recognitionis selected as the bridge and predict driving behavior of the urban traffic environment.According to research and analysis driver's visual characteristic parameter in differentdriving behavior and intention of car following, overtaking, braking andlane-changing (including left lane-changing and right lane-changing) thoroughly,select typical visual characterization parameters to characterize driving behavior andintentions, and propose a driving behavior prediction method based on driver's visualcharacteristics by establishing driving behavior prediction model. These provide thetheoretical basis and technical support for the practical of driving behavior warningsystem.
The study contents are summarized as follows:
1. Urban Traffic driving behavior and driving intent analysis. Firstly, byanalyzing the driver's behavior under urban traffic environment, to divide the driver'sintentions under the urban environment into4class, car following, overtake and theleft and right lane changing; Secondly, by analyzing the relation between the driver'sbehavior and intention, to confirm the prediction method of driving behavior based onthe driving intention recognition. With the target of the driving behavior prediction,analyze the impact factors of driving intention and behavior, confirm the visualfeature parameters of driving intention and behavior, and all above would lay the foundation for the driving test design and the selection of driving behavior predictionparameters.
2. Test designation and data collection. Firstly, the real vehicle road test isdesigned, including the analysis of the test purpose, the selection, installation anddebugging of the test equipment, the selection of the personnel and route, the testprocess development and so on. Secondly, through the road test, collect the real-timedata of the driver behavior and visual characteristics; thirdly, eliminate abnormal databy using the PauTa, and analyze the driver behavior through the test video, and thenselect the driving behavior sample. Finally, select the reasonable data for the drivingbehavior prediction, this paper use4s,4.5s and5s data as the training sample andevaluating sample database for driving behavior prediction, and it also provides datasupport for the construction of driver behavior prediction model.
3. Research on the method of driver's vision plane divided based on the driver'sfixation points distribution. Firstly, use k means clustering and select k6， k7and k8, cluster driver's fixation points. Secondly, to driver’s abnormal fixationpoints are removed used the guidelines of PauTa. Then, the driver's fixation pointsafter clustering will be projected onto the front wind glass of the vehicle. Throughcomparative analysis of the advantages and disadvantages of each sub-cluster,determine the final clustering results. Finally, based on the distribution of the driver'sfixation points, divide the driver's vision plane into seven parts: front lane, left lane,right lane, left rearview mirror, right rearview mirror, interior mirrors and cardashboards.
4. Law analysis of driver's visual characterization parameters in different drivingbehavior. Firstly, from the three aspects of fixation, saccade and rotation of head,combining with the test video and test data, to deep analyze the driver’s differentdriving behavior that correspond to visual features and the change rule of headmovement characteristics parameters, and use multivariate analysis of variance tostudy the influence on driver visual parameters from different driving intentions. Then,determine visual indicator that could represent driver’s driving behavior.
5. Establishment of driving behavior prediction model. Firstly, Use the basic idea,arithmetic and classification of the theory of hidden Markov to elaborate the HMMmodeling idea; Then according to the research purpose and requirement, select thevisual characterization parameters needed for modeling driving behavior, and select100samples as the training sample from all driving behavior to train the model, andconstruct the driving behavior prediction model on the basis of HMM arithmetic; Through the correlation analysis, the selected characteristics can be simplified, andthe fixation count, saccade duration, saccade speed, Fixation point transitionprobability and rotation of head are selected as the modeling parameters.
6. Model evaluation and prediction result analysis. Firstly, analyze the predictionresult through calculating the accuracy of predict model. It shows that the accuracy ofprediction models can reach more than85%when using4.5s as the time window toselect prediction sample; Then the paper studied the impact when using4s or5s as thetime window, it shows that it is appropriate to use4.5s as the time window to predictdriving behavior on the purpose of dangerous driving behavior early-warning.
This paper systematically and deep studies the key technology problems aboutdriving behavior prediction and intention recognition system based on visualcharacteristic on urban road. By analyzes the influence factors of urban trafficenvironment on drivers and drivers’ driving intentions, establishes visualcharacteristic parameters that represent driving behavior on urban road, andestablishes driving behavior prediction model. These provide the theoretical basis andtechnical support for the practical of driving behavior warning system and applicationof vehicle active safety assistant system, thus to improve the driving safety andcomfort of drivers and improve the traffic environment.
本文在分析总结国内外现有的关于驾驶行为预测以及意图辨识成果的基础上，以驾驶意图辨识为桥梁，预测城市道路交通环境驾驶员在行车过程中的驾驶行为。通过深入分析和研究驾驶员在跟驰、超车以及换道（包括左换道、右换道）行为及意图阶段视觉特征表征参数的变化规律，选取典型视觉特性表征参数表征驾驶员行为与意图，建立驾驶行为预测模型，提出了基于驾驶员视觉特性的驾驶行为预测方法，分析了驾驶行为表征参数及驾驶意图时窗对驾驶行为预测的影响，从理论层面和技术层面促进了驾驶行为预警系统的实用化。
论文具体研究工作如下：
1、城市交通环境驾驶行为与驾驶意图分析。首先，通过分析城市交通环境下的驾驶意图及驾驶行为形成机理，将城市环境下的驾驶行为分为跟驰、超车、左换道以及右换道4类；然后，通过分析驾驶行为与驾驶意图的关系，确定基于驾驶意图辨识的驾驶行为预测方法。以驾驶行为预测为目的，分析驾驶意图及驾驶行为的影响因素，确定表征驾驶意图和行为的视觉特性参数，为驾驶行为试验方案的设计以及驾驶行为预测参数的选取奠定基础。
2、试验方案设计和数据采集。首先，设计了实车道路试验方案，包括试验设备安装和调试、试验人员和路线选取、试验过程设计等。其次，进行道路试验，实时采集驾驶员行为及视觉特性数据；再次，应用拉依达准则，对异常数据进行剔除，并通过试验录像分析驾驶员操作行为，选取驾驶行为样本；最后，选取合理的数据驾驶行为预测数据，本文分别以4s、4.5s及5s作为驾驶意图时窗选取用于驾驶行为预测的训练样本数据库和评价样本数据库，为建立驾驶行为预测模型提供了数据支撑。
3、基于驾驶员视线点分布规律的驾驶员视野平面划分方法研究。首先，运用k均值聚类，分别选取k6、 k7以及k8，将驾驶员的视线点进行动态聚类。其次，运用拉依达准则将聚类后的驾驶员视线点坐标进行异常数据剔除，剔除偏离各区域的异常视线点；然后，将多次聚类后的驾驶员视线点投影到车辆前挡风玻璃中，通过对比分析各次聚类的优缺点，确定最终的聚类结果；最后，基于视线点分布将驾驶员的视野平面划分为正前方车道、左侧车道、右侧车道、左侧车外后视镜、右侧车外后视镜、车内后视镜和车内仪表盘七个区域。
4、不同驾驶行为下驾驶员视觉表征参数变化规律分析。以试验数据为基础，结合试验录像，从注视、扫视和头部转动三方面，深入分析不同驾驶行为对应的驾驶员眼睛及头部运动特性表征参数的变化规律，并运用Nemenyi秩和检验方法检验不同驾驶行为过程中各驾驶员视觉特性表征参数的差异性，最终确定能够表征驾驶员驾驶行为的视觉及头部运动指标。
5、驾驶行为预测模型的建立。首先，从隐马尔科夫理论的基本思想、基本算法以及分类等方面阐述了HMM的建模思想；然后，根据论文研究目的及要求，选取建模所需的驾驶行为视觉表征参数，从所有驾驶行为中选取100个样本作为训练样本进行模型训练，基于HMM算法建立驾驶行为预测模型；利用相关性分析，对所选取的参数进行简化，最终选取注视次数、扫视持续时间、扫视速度、注视点转移概率以及头部转角为建模参数。
6、模型评价及预测效果分析。首先，通过计算模型预测准确率，分析了模型的效果，结果表明，以4.5s作为驾驶意图时窗选取驾驶行为预测样本时，预测模型的准确率达到85%以上；其次，以4s和5s作为驾驶意图时窗选取驾驶行为预测样本，研究了样本选取对驾驶行为预测结果的影响，以危险驾驶行为预警为目的，以4.5s作为驾驶意图时窗选取样本数据进行了驾驶行为预测。
论文以驾驶员视觉特性为基础，以隐马尔科夫理论为手段，深入系统的研究了城市道路交通中驾驶员驾驶行为预测及意图辨识面临的关键技术问题。通过分析驾驶行为及其驾驶意图形成机理和影响因素，选取了城市道路行车过程中有效表征驾驶员行为的视觉参数，建立了驾驶行为预测模型。论文研究成果可为危险驾驶行为预警及安全驾驶辅助系统的开发提供一定的理论基础和技术支持。
The traffic environment of urban road is complicated, and traffic conflicts occurfrequently between vehicles, wrong driving behavior will lead these conflicts to bemore serious and cause traffic accidents. Because the trend that drivers areunprofessional and traffic is intensive become apparent increasingly in urban trafficflow recently, the research on driving behavior in urban traffic environment isparticularly important. And because driving intention is the internal state of drivingbehavior, the study on driving intention is the premise of driving behavior prediction.So driving intention identification and behavior prediction in urban trafficenvironment is significant to improve driving safety and traffic environment.
This paper analyze and summarize the driving intention recognition and behaviorprediction methods that are existing at home and aboard, driving intention recognitionis selected as the bridge and predict driving behavior of the urban traffic environment.According to research and analysis driver's visual characteristic parameter in differentdriving behavior and intention of car following, overtaking, braking andlane-changing (including left lane-changing and right lane-changing) thoroughly,select typical visual characterization parameters to characterize driving behavior andintentions, and propose a driving behavior prediction method based on driver's visualcharacteristics by establishing driving behavior prediction model. These provide thetheoretical basis and technical support for the practical of driving behavior warningsystem.
The study contents are summarized as follows:
1. Urban Traffic driving behavior and driving intent analysis. Firstly, byanalyzing the driver's behavior under urban traffic environment, to divide the driver'sintentions under the urban environment into4class, car following, overtake and theleft and right lane changing; Secondly, by analyzing the relation between the driver'sbehavior and intention, to confirm the prediction method of driving behavior based onthe driving intention recognition. With the target of the driving behavior prediction,analyze the impact factors of driving intention and behavior, confirm the visualfeature parameters of driving intention and behavior, and all above would lay the foundation for the driving test design and the selection of driving behavior predictionparameters.
2. Test designation and data collection. Firstly, the real vehicle road test isdesigned, including the analysis of the test purpose, the selection, installation anddebugging of the test equipment, the selection of the personnel and route, the testprocess development and so on. Secondly, through the road test, collect the real-timedata of the driver behavior and visual characteristics; thirdly, eliminate abnormal databy using the PauTa, and analyze the driver behavior through the test video, and thenselect the driving behavior sample. Finally, select the reasonable data for the drivingbehavior prediction, this paper use4s,4.5s and5s data as the training sample andevaluating sample database for driving behavior prediction, and it also provides datasupport for the construction of driver behavior prediction model.
3. Research on the method of driver's vision plane divided based on the driver'sfixation points distribution. Firstly, use k means clustering and select k6， k7and k8, cluster driver's fixation points. Secondly, to driver’s abnormal fixationpoints are removed used the guidelines of PauTa. Then, the driver's fixation pointsafter clustering will be projected onto the front wind glass of the vehicle. Throughcomparative analysis of the advantages and disadvantages of each sub-cluster,determine the final clustering results. Finally, based on the distribution of the driver'sfixation points, divide the driver's vision plane into seven parts: front lane, left lane,right lane, left rearview mirror, right rearview mirror, interior mirrors and cardashboards.
4. Law analysis of driver's visual characterization parameters in different drivingbehavior. Firstly, from the three aspects of fixation, saccade and rotation of head,combining with the test video and test data, to deep analyze the driver’s differentdriving behavior that correspond to visual features and the change rule of headmovement characteristics parameters, and use multivariate analysis of variance tostudy the influence on driver visual parameters from different driving intentions. Then,determine visual indicator that could represent driver’s driving behavior.
5. Establishment of driving behavior prediction model. Firstly, Use the basic idea,arithmetic and classification of the theory of hidden Markov to elaborate the HMMmodeling idea; Then according to the research purpose and requirement, select thevisual characterization parameters needed for modeling driving behavior, and select100samples as the training sample from all driving behavior to train the model, andconstruct the driving behavior prediction model on the basis of HMM arithmetic; Through the correlation analysis, the selected characteristics can be simplified, andthe fixation count, saccade duration, saccade speed, Fixation point transitionprobability and rotation of head are selected as the modeling parameters.
6. Model evaluation and prediction result analysis. Firstly, analyze the predictionresult through calculating the accuracy of predict model. It shows that the accuracy ofprediction models can reach more than85%when using4.5s as the time window toselect prediction sample; Then the paper studied the impact when using4s or5s as thetime window, it shows that it is appropriate to use4.5s as the time window to predictdriving behavior on the purpose of dangerous driving behavior early-warning.
This paper systematically and deep studies the key technology problems aboutdriving behavior prediction and intention recognition system based on visualcharacteristic on urban road. By analyzes the influence factors of urban trafficenvironment on drivers and drivers’ driving intentions, establishes visualcharacteristic parameters that represent driving behavior on urban road, andestablishes driving behavior prediction model. These provide the theoretical basis andtechnical support for the practical of driving behavior warning system and applicationof vehicle active safety assistant system, thus to improve the driving safety andcomfort of drivers and improve the traffic environment.
引文
[1] B.Sultan, M.McDonald.The lane changing process: data analysis&modelingbehavior. Traffic Engineering Control.2001,42(3):202-207.
[2] National Transportation Safety Board. Special investigation report-highwayvehicle and infrastructure based technology for the prevention of rear-endcollisions[C]. NTSB Number SIR-01/01, May2001.
[3]刘雁飞．驾驶行为建模研究[D]．杭州：浙江大学,2007.
[4]肖献强.基于信息融合的驾驶行为识别关键技术研究[D].合肥：合肥工业大学，2011.
[5] Yoshifumi Kishimoto ete. A Modeling Method for Predicting Driving BehaviorConcerning with Driver’s Past Movements[J].Proceedings of the2008IEEEInternational Conference on Vehicular Electronics and Safety Columbus,2008:132-137.
[6] Andrew Liu，Dario Salvucci. Modeling and Prediction of Human Driver Behavior[J]. Conference on Human-Computer Interaction, New Orleans, LA,Aug,2001.
[7] JoelC.MeCal, DavidRWIPf. Lane change Intent Analysis Using Robust Operatorsand Sparse Bayesian Learning [J].IEEE Intelligent Transportation Systems,2007,8(3):431-440.
[8] Yamaguchi H, Narita Y, Takahashi H. Automatic transmission shift schedulecontrol using fuzzy logic [J].1993.
[9] Bruno Bossacchi, Ichird Masaki. Fuzzy logic technology&the intelligenthighway system (IHS).1993IEEE International Conference on Fuzzy System,1993:65-70.
[10]Weil H G, Probst G, Graf F. Fuzzy expert system for automatic transmissioncontrol[C]. Control Applications,1992, First IEEE Conference on. IEEE,1992:716-721.
[11]Bastian A, Tano S, Oyama T, et al. System overview and special features of FATE:fuzzy logic automatic transmission expert system[C]. Fuzzy Systems,1995.International Joint Conference of the Fourth IEEE International Conference onFuzzy Systems and the Second International Fuzzy Engineering Symposium,Proceedings of1995IEEE International Conference on. IEEE,1995,2:1063-1070.
[12]Sakai I, etc. Shift Scheduling method of automatic transmission vehicle usingfuzzy logic [J]. Proceeding of IEEE Roundtable Discussion on Fuzzy and NeuralSystem and VehicleApplication,1991:343-347.
[13]Sakaguchi S, Sakai I, Haga T. Application of fuzzy logic to shift schedulingmethod for automatic transmission[C]. Fuzzy Systems,1993. Second IEEEInternational Conference on. IEEE,1993:52-58.
[14]Liu A. What the driver’s eye tells the car’s brain? In: G. Under wood (Ed). Eyeguidance in reading and scene perception [J]. England: Elsevier,1998:431-452.
[15]Zou X, Levinson D. Modeling Intersection Driving Behaviors: A Hidden MarkovModelApproach [J].Journal of the Transportation Research Board,2006.
[16]Dario D. Salvucci, Andrew Liu. The time course of a lane change: Driver controland eye-movement behavior [J]. Transportation Research Part F5(2002):123-132.
[17]Miller S. A Driver Intent-based Collision Avoidance System. Proceedings of the19th Canadian Multidisciplinary Road Safety Conference, SaskatoonSaskatchewan,2009.
[18][Matthias J. Henning, Olivier georgeon, Josef F.krems. The quality of behavioraland environmental indicators used to infer the intention to change lanes [J].Transportation Research Part F4(2001):1-7.
[19]V.Bhise, J.Meldrum, D. Jack, G.Troell, D.Hoffmeister, and L.Forbes. Driverheadmovements in left outside mirror viewing [J]. Society of AutmotiveEngineers, no.810761,1981.
[20]F. Lethaus, J. Rataj. Do eye movements reflect driving maneuvers [J] IET Intell.September2007,1(3):199-204.
[21]Kuge N, Kimura T. Driving Intention Estimation System, Driver AssistingSystem,And Vehicle with the System: US,780950682[P/OL].
[22]N. Kuge, T. Yamamura, O. Shimoyama, A. Liu. A Driver Behavior RecognitionMethod Based on a Driver Model Framework [J]. SAE Technical Paper,2000-01-0349.
[23]Raksincharoensak P, Mizushima T, Nagai M. Direct Yaw Moment ControlSystem Based on Driver Behavior Recognition. Vehicle System Dynamics,2008,46(Supplement).
[24]Andrew Liu, Alex pretend. Towards real-time recognition of driver intentions[J].Intelligent Transportation System,1997, IEEE Conference, Boston, MA:236-241.
[25]Boer E R, Ward N J, Yamamura T, et al. Driver Performance Assessment with aCar Following Model. Proceedings of the3rd International Symposium onHuman Factors in DriverAssessment, Training, and Vehicle Design,2005.
[26]Kuge N, Kanagawa. Driving Intention Estimation System, Vehicle OperationAssistance System, and Vehicle Equipped There with: US,763433lB2.http://www.freepatentsonline.com/7634331.html.
[27]Pentland A, Liu A. Modeling and Prediction of Human Behavior [J].NeuralComputation,1999,11.
[28]Takano W, Matsushita A, Iwao K. Recognition of Human Driving Behaviorsbased on Stochastic Symbolization of Time Series Signal[C].Proceeding of the2008IEEE/RSJ, Nice, France,2008.
[29]Scullion J. Fatigue monitors to warn drivers. Australasian Science incorporatingSearch,1998,19(2):5-10.
[30]喻丹,吴义虎,王正武.基于隐Markov的机动车驾驶人状态预测[J].系统工程,2010,28(5)：99-103.
[31]王其东.基于隐马尔可夫模型的驾驶行为预测方法研究[J].机械工程学报,2013,24(21):2972-2976.
[32]宋健,王玉海,李兴坤.基于模糊推理的驾驶员意图辨识研究[J].公路交通科技,2005,22(12):113-118.
[33]宋健,王玉海,李兴坤.驾驶员意图与行驶环境的统一辨识及实时算法[J].机械工程学报,2006,42(4):206-212.
[34]候海晶.高速公路驾驶员换道意图识别方法研究[D].长春：吉林大学,2013.
[35]Qin G H, Lei Y L, Niu M K, etal. Estimation of Road Situations and Driver,5Intention in Automotive Electronic Control System [C].Proceedings of the IEEEInteractional Conference on Vehicle Electronics, Changchun China,1999.
[36]何仁,刘文光.考虑油门开度快速变化的自动变速器换挡控制策略[J].农业机械学报,2009,40(9):16-19.
[37]马晶晶.基于隐马尔可夫理论的驾驶意图辨识研究[J].长沙：长沙理工大学,2012.
[38]李弼程,邵美珍,黄洁．模式辨识原理与应用[M]．西安：西安电子科技大学出版社,2008.
[39]王英范,宁国宝,余卓平.乘用车驾驶员制动意图辨识参数的选择[J].汽车工程,2011,33(3):213-217.
[40]吕岸,胡振程,陈慧．基于高斯混合隐马尔可夫模型的高速公路超车行为辨识与分析[J]．汽车工程,2010.7,630-634.
[41]Zhao G Y, Peng C Y, Wang X T. Intelligent Control for AMT Based on Driver'sIntention and ANFIS Decision-Making. Proceedings of the7th World Congresson Intelligent Control andAutomation, Chongqing China,2008.
[42]Meng X N, Lee K K, Xu Y Sh. Human Driving Behavior Recognition Based onHidden Markov Models [C]. Proceedings of the2006IEEE InteractionalConference on Robotics and Biomimeties, Kunming China,2006.
[43]储颖,肖献强,朱家诚.基于驾驶行为及意图的汽车主动安全技术研究[J].机械设计与制造,2011(1):266-268.
[44]孙以泽,王其明.车辆AMT中道路条件及驾驶意图的模糊辨识[J].汽车工程,2001(6).
[45]彭金栓,付锐,郭应时.基于驾驶员视觉特性的换道意图辨识方法[J].武汉理工大学学报,2013,35(3):73-79.
[46]宗长富,杨肖,王畅,张广才．汽车转向时驾驶员驾驶意图辨识与行为预测[J]．吉林大学学报（工学版）,2009,27-32.
[47]王畅.基于隐形马尔科夫模型的驾驶员意图辨识方法研究[D].长春:吉林大学,2011.
[48]王庆年,唐先智,王鹏宇等.基于神经网络的混合动力汽车驾驶意图识别方法[J].农业机械学报,2012,43(8):32-36.
[49]J.M. Henderson,F.Ferreira, Scene perception for psycholinguists, in: J.M.Henderson, F.Ferreira(Eds.), The Interface of Language, Vision, and Action: EyeMovements and the Visual World, Psychology Press, NewYork,2004:1-58.
[50]张凤,李永娟,蒋丽.驾驶行为理论模型研究综述[J].中国安全科学学报,2010,20(2):23-28.
[51]Sasaki, M. and T. Nagatani. Transition and saturation of traffic flow controlled bytraffic lights [J]. Physical a-Statistical Mechanics and Its Applications,2003,325(3-4):531-546.
[52]吴超仲,张晖,毛品,等.基于驾驶操作行为的驾驶员状态识别模型研究[J].中国安全科学技术学报,2007,17(4):162-165.
[53]Frank Lai, Magnus Hjalmdahl, kathryn Chorlton, Mats Wiklund. The long-termeffect of intelligent speed adaptation on driver behavior [J]. Applied Ergonomics,2010,41:179-186.
[54]Martijn Tideman, Mascha C. van der Voort, Bart van Arem. Anew scenario basedapproach for designing driver support systems applied to the design of a lanechange support system [J].Transportation Research Part C,2010,18:247-258.
[55]肖献强,任春燕.基于隐马尔可夫模型的驾驶行为预测方法研究[J].中国机械工程,2013,24(21):2972-2976.
[56]黄思博.基于计算机视觉的异常驾驶行为检测方法研究[D].广州:华南理工大学,2011.
[57]Raymond J. Kiefer, Jonathan M. Hankey. Lane change behavior with a side blindzone alert system [J].AccidentAnalysis and Prevention.2008,40:683-690.
[58]Kristie L. Young, Michael G. Lenne, Amy R.Williamson. Sensitivity of the lanechange test as a measure of in-vehicle system demand [J]. Applied Ergonomics,2011,42:611-618.
[59]Firas Lethaus, Martin R.K.Baumann, FrankK ster, Karsten Lemmer. Acomparison of selected simple supervised learning algorithms to predict driverintent based on gaze data [J]. Neurocomputing,2013(121):108-130.
[60]Summala, H., Lamble, D., and Laakso, M. Driving experience and perception ofthe lead car’s breaking when looking at in-car targets. Accident Analysis andPrevention,30(4),401-407.
[61]李永芳.基于眼动技术的道路交通安全应用研究[J].工业安全与环保,2011,37(4):37-38.
[62]Louis Tijerina. Driver Eye Glance Behavior During Car Following on the Road[J]. International Congress and Exposition Detroit,1999(3):1-17.
[63][63]Sarah Barber, Dean Schwab, and Ken Zimmerman. Head Up and Eyes outEnabling Equivalent Visual Operations with the Head up Display [J]. SAE Int. J.Aerosp,2013,6(1):237-246.
[64]孙纯.基于驾驶员视觉特性的换道意图辨识[D].西安:长安大学,2012.
[65]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.
[66]陈建珍,潘涌智,李任波.基于Mat lab的二维试验数据粗差检测[J].误差与数据处理,计量技术2007, No.5:61-63.
[67]Doshi A, Trivedi M M. On the Roles of Eye Gaze and Head Dynamics inPredicting Driver's Intent to Change Lanes [C]. IEEE Transactions on IntelligentTransportation System,2009,10(3):453-462.
[68]Lethaus F, Rataj J. Do eye movements reflect driving manoeuvres?[C]. IETIntelligent Transportation System.2007,1(3):199-204.
[69]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.
[70]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.
[71]Kiefer R J, Hankey J M. Lane change behavior with a side blind zone alertsystem [J].AccidentAnalysis and Prevention40(2008):683-690.
[72]Crundall D,Underwood G．Effects of experience and processing demands onvisual information acquisition in drivers [J]．Ergonomics,1998,41(4):448-458.
[73]Lethaus F, Rataj J. Do eye movements reflect driving manoeuvres?[C]. IETIntelligent Transportation System.2007,1(3):199-204.
[74]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.
[75]Sivak M. The information that drivers use: Is it indeed90%visual [J]. Perception,1996,25:1081-1089.
[76]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.
[77]Riad I. Hammoud, Gerald Witt, Robert Dufour. On Driver Eye ClosureRecognition for Commercial Vehicles [J]. SAE Int. J. Commer.Veh,2008,(1):454-463
[78]Geoffrey Underwood, David Crundall, Peter ChaPman. Selective searching whiledriving: the role of experience in hazard detection and general surveillance [J].Ergonomies,2002,45(l): l-15.
[79]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.
[80]http://baike.so.com/doc/6953641.html.
[81]茹诗松,王静龙,史定华等.统计手册[M].北京:科学出版社.
[82]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.
[83]高祥宝,董寒青.数据分析与SPSS应用[M].北京:清华大学出版社,2007
[84]Doshi A, Trivedi M M. On the Roles of Eye Gaze and Head Dynamics inPredicting Driver's Intent to Change Lanes[C], IEEE Transactions on IntelligentTransportation System,2009,10(3):453-462.
[85]Rabiner L R. A Tutorial on Hidden Markov Models and Selected Applications inSpeech Recognition [J]. Proceedings of the IEEE,1989,77(2):257.
[86]Kobayashi T, Haruyama S．Partly-Hidden Markov model and its application togesture recognition [C]. In：Taylor FJ,ed．Proc．of the Int’1Conf．onAcoustics,Speech and Signal Processing． New York： AcademicPress,1997．3081-3084.
[87]易克初,田斌,付强.语音信号处理[M].国防工业出版社.2000.
[88]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.
[89]乔跃刚,赵铁军,李生等.基于SCHMM非特定人关键词检出语音辨识系统[J].计算机应用,2005(25):295-297.
[90]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.
[91]http://www.cs.ubc.ca/~murphyk/Software/HMM/hmm.html.
[92]Meng X N, Lee K K, Xu Y S. Human Driving Behavior Recognition Based onHidden Markov Models[C]. Proceedings of the2006IEEE InternationalConference on Robotics and Biomimetics, Kunming China,2006:274-279.
[93]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.
[94]Rabiner L R, Wilpon J G, Soong F K. High Performance Connected DigitRecognition Using Hidden Markov Models. IEEE Trans. ASSP,1989,37(8):1214-1225.
[2] National Transportation Safety Board. Special investigation report-highwayvehicle and infrastructure based technology for the prevention of rear-endcollisions[C]. NTSB Number SIR-01/01, May2001.
[3]刘雁飞．驾驶行为建模研究[D]．杭州：浙江大学,2007.
[4]肖献强.基于信息融合的驾驶行为识别关键技术研究[D].合肥：合肥工业大学，2011.
[5] Yoshifumi Kishimoto ete. A Modeling Method for Predicting Driving BehaviorConcerning with Driver’s Past Movements[J].Proceedings of the2008IEEEInternational Conference on Vehicular Electronics and Safety Columbus,2008:132-137.
[6] Andrew Liu，Dario Salvucci. Modeling and Prediction of Human Driver Behavior[J]. Conference on Human-Computer Interaction, New Orleans, LA,Aug,2001.
[7] JoelC.MeCal, DavidRWIPf. Lane change Intent Analysis Using Robust Operatorsand Sparse Bayesian Learning [J].IEEE Intelligent Transportation Systems,2007,8(3):431-440.
[8] Yamaguchi H, Narita Y, Takahashi H. Automatic transmission shift schedulecontrol using fuzzy logic [J].1993.
[9] Bruno Bossacchi, Ichird Masaki. Fuzzy logic technology&the intelligenthighway system (IHS).1993IEEE International Conference on Fuzzy System,1993:65-70.
[10]Weil H G, Probst G, Graf F. Fuzzy expert system for automatic transmissioncontrol[C]. Control Applications,1992, First IEEE Conference on. IEEE,1992:716-721.
[11]Bastian A, Tano S, Oyama T, et al. System overview and special features of FATE:fuzzy logic automatic transmission expert system[C]. Fuzzy Systems,1995.International Joint Conference of the Fourth IEEE International Conference onFuzzy Systems and the Second International Fuzzy Engineering Symposium,Proceedings of1995IEEE International Conference on. IEEE,1995,2:1063-1070.
[12]Sakai I, etc. Shift Scheduling method of automatic transmission vehicle usingfuzzy logic [J]. Proceeding of IEEE Roundtable Discussion on Fuzzy and NeuralSystem and VehicleApplication,1991:343-347.
[13]Sakaguchi S, Sakai I, Haga T. Application of fuzzy logic to shift schedulingmethod for automatic transmission[C]. Fuzzy Systems,1993. Second IEEEInternational Conference on. IEEE,1993:52-58.
[14]Liu A. What the driver’s eye tells the car’s brain? In: G. Under wood (Ed). Eyeguidance in reading and scene perception [J]. England: Elsevier,1998:431-452.
[15]Zou X, Levinson D. Modeling Intersection Driving Behaviors: A Hidden MarkovModelApproach [J].Journal of the Transportation Research Board,2006.
[16]Dario D. Salvucci, Andrew Liu. The time course of a lane change: Driver controland eye-movement behavior [J]. Transportation Research Part F5(2002):123-132.
[17]Miller S. A Driver Intent-based Collision Avoidance System. Proceedings of the19th Canadian Multidisciplinary Road Safety Conference, SaskatoonSaskatchewan,2009.
[18][Matthias J. Henning, Olivier georgeon, Josef F.krems. The quality of behavioraland environmental indicators used to infer the intention to change lanes [J].Transportation Research Part F4(2001):1-7.
[19]V.Bhise, J.Meldrum, D. Jack, G.Troell, D.Hoffmeister, and L.Forbes. Driverheadmovements in left outside mirror viewing [J]. Society of AutmotiveEngineers, no.810761,1981.
[20]F. Lethaus, J. Rataj. Do eye movements reflect driving maneuvers [J] IET Intell.September2007,1(3):199-204.
[21]Kuge N, Kimura T. Driving Intention Estimation System, Driver AssistingSystem,And Vehicle with the System: US,780950682[P/OL].
[22]N. Kuge, T. Yamamura, O. Shimoyama, A. Liu. A Driver Behavior RecognitionMethod Based on a Driver Model Framework [J]. SAE Technical Paper,2000-01-0349.
[23]Raksincharoensak P, Mizushima T, Nagai M. Direct Yaw Moment ControlSystem Based on Driver Behavior Recognition. Vehicle System Dynamics,2008,46(Supplement).
[24]Andrew Liu, Alex pretend. Towards real-time recognition of driver intentions[J].Intelligent Transportation System,1997, IEEE Conference, Boston, MA:236-241.
[25]Boer E R, Ward N J, Yamamura T, et al. Driver Performance Assessment with aCar Following Model. Proceedings of the3rd International Symposium onHuman Factors in DriverAssessment, Training, and Vehicle Design,2005.
[26]Kuge N, Kanagawa. Driving Intention Estimation System, Vehicle OperationAssistance System, and Vehicle Equipped There with: US,763433lB2.http://www.freepatentsonline.com/7634331.html.
[27]Pentland A, Liu A. Modeling and Prediction of Human Behavior [J].NeuralComputation,1999,11.
[28]Takano W, Matsushita A, Iwao K. Recognition of Human Driving Behaviorsbased on Stochastic Symbolization of Time Series Signal[C].Proceeding of the2008IEEE/RSJ, Nice, France,2008.
[29]Scullion J. Fatigue monitors to warn drivers. Australasian Science incorporatingSearch,1998,19(2):5-10.
[30]喻丹,吴义虎,王正武.基于隐Markov的机动车驾驶人状态预测[J].系统工程,2010,28(5)：99-103.
[31]王其东.基于隐马尔可夫模型的驾驶行为预测方法研究[J].机械工程学报,2013,24(21):2972-2976.
[32]宋健,王玉海,李兴坤.基于模糊推理的驾驶员意图辨识研究[J].公路交通科技,2005,22(12):113-118.
[33]宋健,王玉海,李兴坤.驾驶员意图与行驶环境的统一辨识及实时算法[J].机械工程学报,2006,42(4):206-212.
[34]候海晶.高速公路驾驶员换道意图识别方法研究[D].长春：吉林大学,2013.
[35]Qin G H, Lei Y L, Niu M K, etal. Estimation of Road Situations and Driver,5Intention in Automotive Electronic Control System [C].Proceedings of the IEEEInteractional Conference on Vehicle Electronics, Changchun China,1999.
[36]何仁,刘文光.考虑油门开度快速变化的自动变速器换挡控制策略[J].农业机械学报,2009,40(9):16-19.
[37]马晶晶.基于隐马尔可夫理论的驾驶意图辨识研究[J].长沙：长沙理工大学,2012.
[38]李弼程,邵美珍,黄洁．模式辨识原理与应用[M]．西安：西安电子科技大学出版社,2008.
[39]王英范,宁国宝,余卓平.乘用车驾驶员制动意图辨识参数的选择[J].汽车工程,2011,33(3):213-217.
[40]吕岸,胡振程,陈慧．基于高斯混合隐马尔可夫模型的高速公路超车行为辨识与分析[J]．汽车工程,2010.7,630-634.
[41]Zhao G Y, Peng C Y, Wang X T. Intelligent Control for AMT Based on Driver'sIntention and ANFIS Decision-Making. Proceedings of the7th World Congresson Intelligent Control andAutomation, Chongqing China,2008.
[42]Meng X N, Lee K K, Xu Y Sh. Human Driving Behavior Recognition Based onHidden Markov Models [C]. Proceedings of the2006IEEE InteractionalConference on Robotics and Biomimeties, Kunming China,2006.
[43]储颖,肖献强,朱家诚.基于驾驶行为及意图的汽车主动安全技术研究[J].机械设计与制造,2011(1):266-268.
[44]孙以泽,王其明.车辆AMT中道路条件及驾驶意图的模糊辨识[J].汽车工程,2001(6).
[45]彭金栓,付锐,郭应时.基于驾驶员视觉特性的换道意图辨识方法[J].武汉理工大学学报,2013,35(3):73-79.
[46]宗长富,杨肖,王畅,张广才．汽车转向时驾驶员驾驶意图辨识与行为预测[J]．吉林大学学报（工学版）,2009,27-32.
[47]王畅.基于隐形马尔科夫模型的驾驶员意图辨识方法研究[D].长春:吉林大学,2011.
[48]王庆年,唐先智,王鹏宇等.基于神经网络的混合动力汽车驾驶意图识别方法[J].农业机械学报,2012,43(8):32-36.
[49]J.M. Henderson,F.Ferreira, Scene perception for psycholinguists, in: J.M.Henderson, F.Ferreira(Eds.), The Interface of Language, Vision, and Action: EyeMovements and the Visual World, Psychology Press, NewYork,2004:1-58.
[50]张凤,李永娟,蒋丽.驾驶行为理论模型研究综述[J].中国安全科学学报,2010,20(2):23-28.
[51]Sasaki, M. and T. Nagatani. Transition and saturation of traffic flow controlled bytraffic lights [J]. Physical a-Statistical Mechanics and Its Applications,2003,325(3-4):531-546.
[52]吴超仲,张晖,毛品,等.基于驾驶操作行为的驾驶员状态识别模型研究[J].中国安全科学技术学报,2007,17(4):162-165.
[53]Frank Lai, Magnus Hjalmdahl, kathryn Chorlton, Mats Wiklund. The long-termeffect of intelligent speed adaptation on driver behavior [J]. Applied Ergonomics,2010,41:179-186.
[54]Martijn Tideman, Mascha C. van der Voort, Bart van Arem. Anew scenario basedapproach for designing driver support systems applied to the design of a lanechange support system [J].Transportation Research Part C,2010,18:247-258.
[55]肖献强,任春燕.基于隐马尔可夫模型的驾驶行为预测方法研究[J].中国机械工程,2013,24(21):2972-2976.
[56]黄思博.基于计算机视觉的异常驾驶行为检测方法研究[D].广州:华南理工大学,2011.
[57]Raymond J. Kiefer, Jonathan M. Hankey. Lane change behavior with a side blindzone alert system [J].AccidentAnalysis and Prevention.2008,40:683-690.
[58]Kristie L. Young, Michael G. Lenne, Amy R.Williamson. Sensitivity of the lanechange test as a measure of in-vehicle system demand [J]. Applied Ergonomics,2011,42:611-618.
[59]Firas Lethaus, Martin R.K.Baumann, FrankK ster, Karsten Lemmer. Acomparison of selected simple supervised learning algorithms to predict driverintent based on gaze data [J]. Neurocomputing,2013(121):108-130.
[60]Summala, H., Lamble, D., and Laakso, M. Driving experience and perception ofthe lead car’s breaking when looking at in-car targets. Accident Analysis andPrevention,30(4),401-407.
[61]李永芳.基于眼动技术的道路交通安全应用研究[J].工业安全与环保,2011,37(4):37-38.
[62]Louis Tijerina. Driver Eye Glance Behavior During Car Following on the Road[J]. International Congress and Exposition Detroit,1999(3):1-17.
[63][63]Sarah Barber, Dean Schwab, and Ken Zimmerman. Head Up and Eyes outEnabling Equivalent Visual Operations with the Head up Display [J]. SAE Int. J.Aerosp,2013,6(1):237-246.
[64]孙纯.基于驾驶员视觉特性的换道意图辨识[D].西安:长安大学,2012.
[65]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.
[66]陈建珍,潘涌智,李任波.基于Mat lab的二维试验数据粗差检测[J].误差与数据处理,计量技术2007, No.5:61-63.
[67]Doshi A, Trivedi M M. On the Roles of Eye Gaze and Head Dynamics inPredicting Driver's Intent to Change Lanes [C]. IEEE Transactions on IntelligentTransportation System,2009,10(3):453-462.
[68]Lethaus F, Rataj J. Do eye movements reflect driving manoeuvres?[C]. IETIntelligent Transportation System.2007,1(3):199-204.
[69]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.
[70]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.
[71]Kiefer R J, Hankey J M. Lane change behavior with a side blind zone alertsystem [J].AccidentAnalysis and Prevention40(2008):683-690.
[72]Crundall D,Underwood G．Effects of experience and processing demands onvisual information acquisition in drivers [J]．Ergonomics,1998,41(4):448-458.
[73]Lethaus F, Rataj J. Do eye movements reflect driving manoeuvres?[C]. IETIntelligent Transportation System.2007,1(3):199-204.
[74]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.
[75]Sivak M. The information that drivers use: Is it indeed90%visual [J]. Perception,1996,25:1081-1089.
[76]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.
[77]Riad I. Hammoud, Gerald Witt, Robert Dufour. On Driver Eye ClosureRecognition for Commercial Vehicles [J]. SAE Int. J. Commer.Veh,2008,(1):454-463
[78]Geoffrey Underwood, David Crundall, Peter ChaPman. Selective searching whiledriving: the role of experience in hazard detection and general surveillance [J].Ergonomies,2002,45(l): l-15.
[79]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.
[80]http://baike.so.com/doc/6953641.html.
[81]茹诗松,王静龙,史定华等.统计手册[M].北京:科学出版社.
[82]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.
[83]高祥宝,董寒青.数据分析与SPSS应用[M].北京:清华大学出版社,2007
[84]Doshi A, Trivedi M M. On the Roles of Eye Gaze and Head Dynamics inPredicting Driver's Intent to Change Lanes[C], IEEE Transactions on IntelligentTransportation System,2009,10(3):453-462.
[85]Rabiner L R. A Tutorial on Hidden Markov Models and Selected Applications inSpeech Recognition [J]. Proceedings of the IEEE,1989,77(2):257.
[86]Kobayashi T, Haruyama S．Partly-Hidden Markov model and its application togesture recognition [C]. In：Taylor FJ,ed．Proc．of the Int’1Conf．onAcoustics,Speech and Signal Processing． New York： AcademicPress,1997．3081-3084.
[87]易克初,田斌,付强.语音信号处理[M].国防工业出版社.2000.
[88]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.
[89]乔跃刚,赵铁军,李生等.基于SCHMM非特定人关键词检出语音辨识系统[J].计算机应用,2005(25):295-297.
[90]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.
[91]http://www.cs.ubc.ca/~murphyk/Software/HMM/hmm.html.
[92]Meng X N, Lee K K, Xu Y S. Human Driving Behavior Recognition Based onHidden Markov Models[C]. Proceedings of the2006IEEE InternationalConference on Robotics and Biomimetics, Kunming China,2006:274-279.
[93]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.
[94]Rabiner L R, Wilpon J G, Soong F K. High Performance Connected DigitRecognition Using Hidden Markov Models. IEEE Trans. ASSP,1989,37(8):1214-1225.