基于信息融合的疲劳驾驶检测方法研究
|
摘要
随着社会经济的不断发展，各国汽车保有量的迅速增加，公路交通事故，特别是恶性交通事故发生率居高不下。研究表明疲劳驾驶是引发道路交通事故的主要原因之一。因此，研究疲劳驾驶实时在线检测方法，对改善道路交通安全具有重大意义。
基于驾驶行为和眼动特征融合的疲劳驾驶检测方法克服了单一信息源的局限性，充分考虑了各信息源的相关性和互补性，同时该方法具有非侵入性、准确性和实时性的特点，已成为疲劳驾驶在线实时检测方法中最有效的技术手段之一。然而由于疲劳特征的隐匿性、驾驶场景的易变性和驾驶人的个体差异性，其检测准确率的提高面临诸多挑战。本文围绕疲劳特征分析、特征参数提取、最优时间窗优化、最优特征子集筛选、信息融合及检测模型搭建等核心问题展开研究，开发了疲劳驾驶实时在线检测模型并进行了实验验证。具体研究内容如下：
1、实验方案设计和数据采集。基于驾驶模拟实验平台同步记录了20位驾驶人不同驾驶状态下驾驶行为和眼动行为数据，基于KSS标准采用视频专家评分的方法判断驾驶人疲劳水平，根据KSS得分切分实验数据，建立了疲劳驾驶样本数据库。
2、驾驶行为特征参数提取。采用统计学方法研究了不同驾驶状态下，方向盘转角、方向盘转角速度、加速踏板开度和车速等驾驶行为特征变量的波动幅度、速度、频度特征，提取量化的特征参数对隐藏在驾驶行为变量时间序列信息中的疲劳特征进行深入挖掘，基于方差分析的方法量化了各特征参数在不同驾驶状态之间差异的显著性水平，优化了各特征参数的最优时间窗。最终筛选出驾驶行为特征参数包括：方向盘转角绝对均值SAMEAN、方向盘转角标准差SASTD、方向盘转角下四分位值均值SAQ1MEAN、方向盘转角上四分位值均值SAQ3MEAN、方向盘转角熵SE、方向盘转角速度绝对值均值SAVMEAN、方向盘转角速度标准差SAVSTD和零速百分比PNS。
3、眼动特征参数提取。采用统计学方法研究了不同驾驶状态下，闭眼、注视、扫视等眼动行为的变化规律，提出了反应疲劳驾驶特性的眼动特征参数，基于方差分析的方法量化了各特征参数在不同驾驶状态之间差异的显著性水平，优化了各特征参数的最优时间窗，最终筛选出眼动特征参数包括：P80、闭眼速度AECS、最长闭眼时间MECD、眨眼频率BF和非正常驾驶区域累积注视时间GTFNRD。
4、疲劳驾驶通用检测模型搭建。以搭建的支持向量机（SVM）检测模型的分类性能为评价准则，以序列浮动前向选择算法为搜索策略，建立了疲劳特征参数优化选择算法，然后利用该算法对疲劳特征参数全集进行降维，提取了疲劳驾驶最优特征子集。以最优子集作为SVM的输入，搭建了疲劳驾驶通用检测模型，针对不同特征参数最优时间窗的差异，提出了滑移时间窗的数据融合方法，提高了检测实时性，实现了疲劳驾驶在线实时检测。通用检测模型的平均准确率为82.27%，灵敏度为82.54%，特异度为81.94%。
5、疲劳驾驶自适应检测模型搭建。基于配对样本t检验和方差分析，量化了驾驶人个体差异性因素对疲劳驾驶检测的影响。基于驾驶人自身稳定性，利用正常驾驶数据提取参考均值，根据特征参数计算个性参数，利用个性参数搭建了自适应检测模型。在驾驶初期阶段利用通用检测模型检测并对自适应检测模型初始化，之后利用自适应检测模型检测驾驶人疲劳状态。自适应检测模型的平均准确率为88.15%，灵敏度为88.25%，特异度为88.02%。
论文针对疲劳驾驶检测方法面临的关键技术问题进行了系统深入的研究，分析了疲劳驾驶对驾驶行为和眼动特征的影响，确立了疲劳驾驶检测的特征参数组，并建立了通用检测模型和自适应检测模型，实现了疲劳驾驶在线实时检测。其研究成果能够为疲劳驾驶检测系统应用提供一定的理论和技术支持，提高驾驶人的行车安全性。
With the enhancement of economy and the rapid increase of vehicle conservation,traffic accidents, especially the serious traffic accidents occurred more and more frequently.Researches show that most of highway accidents are closely related to driver fatigue.Therefore, researches on real time driver fatigue detection system have great significance toimprove road traffic safety.
The fusion of driving performance and eye movements overcome the limitation ofsingle measure approach, analysis the correlation and complementarities. At the same time,the fusion measure has proved to be the most promising technology due to the non intrusive,good accuracy and real time performance. However, the development of driver fatiguedetection system has been seriously hindered for the unapparent driving performance, thevariability of driving scenes and individual differences of drivers. This paper focuses on keyissues in analysis of fatigue driving characteristics, extraction characteristics parameters,selection best time window, information fusion and development driver fatigue model. Areal time driver fatigue detection model was developed and tested. The specific researchcontents are as follows:
1. Experiment program designation and data collection. Driving performance data andeye movements data from20drivers under different driving state were collectedsynchronized based on driving simulation. Fatigue level was scored on the KSS standard bythree researchers, driving performance data and eye movements data were coded andcatalogued according to the KSS score, training and test database for different fatigue levelwas established.
2. Driving performance characteristic parameters extraction. According to a thoroughanalysis on the fluctuation characteristics of the steering wheel angle, steering wheel angularvelocity, throttle position and vehicle velocity when a driver becomes fatigue, quantitativecharacteristic parameters for detecting diver fatigue were extracted from time sequenceinformation of these parameters. The differences level of each characteristic parameters weretested by the analysis of variance (ANOVA), with varying fatigue levels. The best timewindow for each parameter was selected. The extraction driving performance characteristicparameters include: SAMEAN, SASTD, SAQ1MEAN, SAQ3MEAN, SE, SAVMEAN, SAVSTD and PNS.
3. Eye movements characteristic parameters extraction. According to a thoroughanalysis on the change law of eye close behavior, gaze behavior and glance behavior when adriver becomes fatigue, eye movements characteristic parameters were extracted. Thedifferences level of each characteristic parameters were tested by the analysis of variance(ANOVA), with varying fatigue levels. The best time window for each parameter wasselected. The extraction eye movements characteristic parameters include: P80, AECS,MECD, BF and GTFNRD.
4. General detection model development. In order to get the best subset from theuniverse of the measures, an optimized measures selection algorithm was established. Thisalgorithm took the performance of support vector machine algorithm (SVM) as evaluationcriterion and used the search strategy of sequential forward floating selection algorithm(SFFS) to select the optimal measures combination from the driving performance measuresand the eye movements measures. General detection model was developed based on theoptimal characteristic parameters. During the fusion process, slip time window was used toconfuse the characteristic parameters with different best time window, real time performancewas improved in this method. General detection model had a good performance, the averageaccuracy was82.27%, sensitivity was82.54%and specificity was81.94%.
5. Adaptive detection model development. The impact of individual differences ondriver fatigue detection was qualified based on paired samples T test and ANOVA. Due toself stability, reference measure was extracted using alert driving data, and then individualparameters were calculated. Adaptive detection model was developed based on individualparameters. During the initial stage of driving, general model was used to detect driver’sstate and adaptive detection model was developed, after that, adaptive detection was used todetect driving state. This model detected driver fatigue state reaches an accuracy of88.15%,a sensitivity of88.25%and a specificity of88.02%.
Key issues in driver fatigue detection were studied deeply in this paper. The impacts offatigue driving on driving performance and eye movements were analyzed, and characteristicparameters were extracted. General model and adaptive model were developed for driverfatigue detection in real time. The research results provide theoretical and technical supportto driver fatigue detection systems, and improve traffic safety.
基于驾驶行为和眼动特征融合的疲劳驾驶检测方法克服了单一信息源的局限性，充分考虑了各信息源的相关性和互补性，同时该方法具有非侵入性、准确性和实时性的特点，已成为疲劳驾驶在线实时检测方法中最有效的技术手段之一。然而由于疲劳特征的隐匿性、驾驶场景的易变性和驾驶人的个体差异性，其检测准确率的提高面临诸多挑战。本文围绕疲劳特征分析、特征参数提取、最优时间窗优化、最优特征子集筛选、信息融合及检测模型搭建等核心问题展开研究，开发了疲劳驾驶实时在线检测模型并进行了实验验证。具体研究内容如下：
1、实验方案设计和数据采集。基于驾驶模拟实验平台同步记录了20位驾驶人不同驾驶状态下驾驶行为和眼动行为数据，基于KSS标准采用视频专家评分的方法判断驾驶人疲劳水平，根据KSS得分切分实验数据，建立了疲劳驾驶样本数据库。
2、驾驶行为特征参数提取。采用统计学方法研究了不同驾驶状态下，方向盘转角、方向盘转角速度、加速踏板开度和车速等驾驶行为特征变量的波动幅度、速度、频度特征，提取量化的特征参数对隐藏在驾驶行为变量时间序列信息中的疲劳特征进行深入挖掘，基于方差分析的方法量化了各特征参数在不同驾驶状态之间差异的显著性水平，优化了各特征参数的最优时间窗。最终筛选出驾驶行为特征参数包括：方向盘转角绝对均值SAMEAN、方向盘转角标准差SASTD、方向盘转角下四分位值均值SAQ1MEAN、方向盘转角上四分位值均值SAQ3MEAN、方向盘转角熵SE、方向盘转角速度绝对值均值SAVMEAN、方向盘转角速度标准差SAVSTD和零速百分比PNS。
3、眼动特征参数提取。采用统计学方法研究了不同驾驶状态下，闭眼、注视、扫视等眼动行为的变化规律，提出了反应疲劳驾驶特性的眼动特征参数，基于方差分析的方法量化了各特征参数在不同驾驶状态之间差异的显著性水平，优化了各特征参数的最优时间窗，最终筛选出眼动特征参数包括：P80、闭眼速度AECS、最长闭眼时间MECD、眨眼频率BF和非正常驾驶区域累积注视时间GTFNRD。
4、疲劳驾驶通用检测模型搭建。以搭建的支持向量机（SVM）检测模型的分类性能为评价准则，以序列浮动前向选择算法为搜索策略，建立了疲劳特征参数优化选择算法，然后利用该算法对疲劳特征参数全集进行降维，提取了疲劳驾驶最优特征子集。以最优子集作为SVM的输入，搭建了疲劳驾驶通用检测模型，针对不同特征参数最优时间窗的差异，提出了滑移时间窗的数据融合方法，提高了检测实时性，实现了疲劳驾驶在线实时检测。通用检测模型的平均准确率为82.27%，灵敏度为82.54%，特异度为81.94%。
5、疲劳驾驶自适应检测模型搭建。基于配对样本t检验和方差分析，量化了驾驶人个体差异性因素对疲劳驾驶检测的影响。基于驾驶人自身稳定性，利用正常驾驶数据提取参考均值，根据特征参数计算个性参数，利用个性参数搭建了自适应检测模型。在驾驶初期阶段利用通用检测模型检测并对自适应检测模型初始化，之后利用自适应检测模型检测驾驶人疲劳状态。自适应检测模型的平均准确率为88.15%，灵敏度为88.25%，特异度为88.02%。
论文针对疲劳驾驶检测方法面临的关键技术问题进行了系统深入的研究，分析了疲劳驾驶对驾驶行为和眼动特征的影响，确立了疲劳驾驶检测的特征参数组，并建立了通用检测模型和自适应检测模型，实现了疲劳驾驶在线实时检测。其研究成果能够为疲劳驾驶检测系统应用提供一定的理论和技术支持，提高驾驶人的行车安全性。
With the enhancement of economy and the rapid increase of vehicle conservation,traffic accidents, especially the serious traffic accidents occurred more and more frequently.Researches show that most of highway accidents are closely related to driver fatigue.Therefore, researches on real time driver fatigue detection system have great significance toimprove road traffic safety.
The fusion of driving performance and eye movements overcome the limitation ofsingle measure approach, analysis the correlation and complementarities. At the same time,the fusion measure has proved to be the most promising technology due to the non intrusive,good accuracy and real time performance. However, the development of driver fatiguedetection system has been seriously hindered for the unapparent driving performance, thevariability of driving scenes and individual differences of drivers. This paper focuses on keyissues in analysis of fatigue driving characteristics, extraction characteristics parameters,selection best time window, information fusion and development driver fatigue model. Areal time driver fatigue detection model was developed and tested. The specific researchcontents are as follows:
1. Experiment program designation and data collection. Driving performance data andeye movements data from20drivers under different driving state were collectedsynchronized based on driving simulation. Fatigue level was scored on the KSS standard bythree researchers, driving performance data and eye movements data were coded andcatalogued according to the KSS score, training and test database for different fatigue levelwas established.
2. Driving performance characteristic parameters extraction. According to a thoroughanalysis on the fluctuation characteristics of the steering wheel angle, steering wheel angularvelocity, throttle position and vehicle velocity when a driver becomes fatigue, quantitativecharacteristic parameters for detecting diver fatigue were extracted from time sequenceinformation of these parameters. The differences level of each characteristic parameters weretested by the analysis of variance (ANOVA), with varying fatigue levels. The best timewindow for each parameter was selected. The extraction driving performance characteristicparameters include: SAMEAN, SASTD, SAQ1MEAN, SAQ3MEAN, SE, SAVMEAN, SAVSTD and PNS.
3. Eye movements characteristic parameters extraction. According to a thoroughanalysis on the change law of eye close behavior, gaze behavior and glance behavior when adriver becomes fatigue, eye movements characteristic parameters were extracted. Thedifferences level of each characteristic parameters were tested by the analysis of variance(ANOVA), with varying fatigue levels. The best time window for each parameter wasselected. The extraction eye movements characteristic parameters include: P80, AECS,MECD, BF and GTFNRD.
4. General detection model development. In order to get the best subset from theuniverse of the measures, an optimized measures selection algorithm was established. Thisalgorithm took the performance of support vector machine algorithm (SVM) as evaluationcriterion and used the search strategy of sequential forward floating selection algorithm(SFFS) to select the optimal measures combination from the driving performance measuresand the eye movements measures. General detection model was developed based on theoptimal characteristic parameters. During the fusion process, slip time window was used toconfuse the characteristic parameters with different best time window, real time performancewas improved in this method. General detection model had a good performance, the averageaccuracy was82.27%, sensitivity was82.54%and specificity was81.94%.
5. Adaptive detection model development. The impact of individual differences ondriver fatigue detection was qualified based on paired samples T test and ANOVA. Due toself stability, reference measure was extracted using alert driving data, and then individualparameters were calculated. Adaptive detection model was developed based on individualparameters. During the initial stage of driving, general model was used to detect driver’sstate and adaptive detection model was developed, after that, adaptive detection was used todetect driving state. This model detected driver fatigue state reaches an accuracy of88.15%,a sensitivity of88.25%and a specificity of88.02%.
Key issues in driver fatigue detection were studied deeply in this paper. The impacts offatigue driving on driving performance and eye movements were analyzed, and characteristicparameters were extracted. General model and adaptive model were developed for driverfatigue detection in real time. The research results provide theoretical and technical supportto driver fatigue detection systems, and improve traffic safety.
引文
[1] World Health Organization. Global status report on road safety: time for action. Geneva:WHO,2009.http://www.who.int/violence_injury_prevention/road_safety_status/2009/en/
[2] NHTSA. Traffic Safety Facts [R]. Report DOT HS811402, NHTSA, US Departmentof Transportation,2011
[3] Jin L S, Niu Q N, Hou H J, et al. A pedestrian detection method using3D laser scanner[J], InformationAn International Interdisciplinary Journal,2012,15(12A):54815490.
[4]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（20002011）[R].公安部交通管理局，20012011.
[5] Klauer S G, Dingus T A, Neale V L, et al. The impact of driver inattention onnear crash/crash risk: An analysis using the100car naturalistic driving study data [R].Washington: National Highway Traffic Safety Administration,2006.
[6] Liu C, and Subramanian R. Factors related to fatal singlevehicle run off road crashes[R], DOTHS811232, U.S. Department of Transportation, American National HighwayTraffic Safety Administration, Washington, DC, USA,2009.
[7]刘灵,邓小燕,徐颖.汽车驾驶员驾驶疲劳监测方法与装置的研究现状[J].医疗卫生装备,2006,27(12):2830．
[8] MacLean A W, Davies D R T,&Thiele K. The hazards and prevention of driving whilesleepy [J]. Sleep Medicine Reviews,2003,7:507521.
[9] Jin L S, Niu Q N, Jiang Y Y, et al. Driver sleepiness detection system based on eyemovements variables [J], Advances in Mechanical Engineering,2013,2013:17.
[10]Nordbakke S, Sagberg F. Sleepy at the wheel: Knowledge, symptoms and behaviouramong car drivers [J], Transportation Research Part F,2007,10:110.
[11]邸巍.基于视觉的全天候驾驶员疲劳与精神分散状态监测方法研究[D],吉林大学博士学位论文,2010.
[12]Vanlaar W, Simpson H, Mayhew D, et al. Fatigued and drowsy driving: A survey ofattitudes, opinions and behaviors [J]. Journal of Safety Research,2008,9(3):303309.
[13]National Sleep Foundation,2009. Sleep in America Poll. National Sleep Foundation,Washington, D.C. http://sleepfoundation.org/
[14]谢晓莉.驾驶疲劳生成机理研究[D],北京工业大学博士学位论文,2010.
[15]毛喆.机动车疲劳驾驶行为识别方法研究[D],武汉理工大学博士学位论文,2009.
[16]Bartlett F C, Ferrier lecture: fatigue following highly skilled work [J]. Proceedings ofthe Royal Society, Series B,1943,131:247257.
[17]Grandjean E. Fatigue in industry [J]. British Journal of Industrial Medicine,1979,36:175186.
[18]周宝宽.中医疲劳与亚健康研究[D],辽宁中医学院博士学位论文,2003.
[19]Simons D J, Rensink R A. Change blindness: past, present, and future [J]. Trends inCognitive Sciences,2005,9(1):1620.
[20]Khushaba R N, Kodagoda S, Lal S, and Dissanayake G. Driver drowsiness classificationusing fuzzy wavelet packet based feature extraction algorithm [J], IEEE Transactions onBiomedical Engineering,2011,58(1):121131.
[21]Verwey W&Zaidel D. Predicting drowsiness accidents from personal attributes, eyeblinks, and ongoing driving behavior [J]. Personality and Individual Differences,1999,28(1):123142.
[22]Regan M A, Hallett C, Gordon C P. Driver distraction and driver inattention: definition,relationship and taxonomy [J], Accident Analysis and Prevention,2011,43:17711781.
[23]李志春.驾驶员疲劳状态检测技术研究与工程实现[D],江苏大学博士学位论文，2009.
[24] kerstedt T, Gillberg M. Subjective and objective sleepiness in the active individual [J].International Journal of Neuroscience,1990,52(1):2937.
[25]Morris T L, Miller J C. Electrooculographic and performance indices of fatigue duringsimulated flight [J], Biological Psychology,1996,42(3):343360.
[26]EMIly Nodine. The detection of drowsy drivers through driver performance indicators
[D]. Tufts University, master thesis,2008.
[27]Kaida K, Takahashi M, Akerstedt T, Nakata A, Otsuka Y, Haratani T, and Fukasawa K,Validation of the Karolinska sleepiness scale against performance and EEG variables [J].Clinical Neurophysiology,2006,117(7):15741581.
[28]Ingre M, Akerstedt T, Peters B. A. Anund, and G. Kecklund. Subjective sleepiness,simulated driving performance and blink duration: Examining individual differences [J],Journal of Sleep Research,2006,15(1):4753.
[29]Belz S M, Robinson G S,&Casali J G. Temporal separation and self rating of alertnessas indicators of driver fatigue in commercial motor vehicle operators [J]. Human Factors,2004,46(1):154169.
[30]Lal S K L, Craig A. Electroence phalography activity associated with driver fatigue:implications for a fatigue countermeasure device [J]. Joumal of Psychophysiology,2001,15(3):183189.
[31]屈肖蕾.基于转向操作和车辆状态的疲劳驾驶检测方法研究[D].清华大学硕士学位论文,2012.
[32]Carroll J S, Blisewise D L, Dement W C. A method for checking interobserver reliabilityin observational sleep studies [J]. Sleep,1989,12(4):363367.
[33]Wierwille W W, Ellsworth L A. Evaluation of driver drowsiness by trained observers [J].Accident Analysis and Prevention,1994,26(5):571581.
[34]Niu Q N, Jin L S, Hou H J, et al. Driver fatigue detection system based on eyemovements [C]. ICTIS2013,657663.
[35]Shen K Q, Li X P, Ong C J, Shao S Y, and Wilder Smith E P V. EEG based mentalfatigue measurement using multiclass support vector machines with confidence estimate[J], Clinical Neurophysiology,2008,119(7):15241533.
[36]Lin C T, Chen Y C, Huang T Y, Chiu T T. Development of wireless brain computerinterface with embedded multitask scheduling and its application on real time driver’sdrowsiness detection and warning [J]. IEEE Transactions on Biomedical Engineering,2008,55(5):15821591.
[37]Jap B T, Lal S, Fischer P, and Bekiaris E. Using EEG spectral components to assessalgorithms for detecting fatigue [J] Expert Systems Application,2009,36(2):23522359.
[38]Lal S K L, Craig A, Boord P, et al. Development of an algorithm for an EEG baseddriver fatigue countermeasure [J]. Journal of Safely Research,2003,34(3):321328.
[39]Yeo M V M, Li X P, Shen K, et al. Can SVM be used for automatic EEG detection ofdrowsiness during car driving [J]. Safety Science,2009,47(1):115124.
[40]毛科俊,刘小明,赵晓华等.基于脑电信号的驾驶疲劳预报关键参数选取[J].北京工业大学学报,2010,36(7):966970.
[41]毛科俊,赵晓华,刘小明等.基于脑电分析的驾驶疲劳预报研究[J].人类工效学,2009,15(4):2529.
[42]Patel M, Lala S K L, Kavanagha D, Rossiterb P, Applying neural network analysis onheart rate variability data to assess driver fatigue [J]. Expert Systems with Applications,2011,38(6):72357242.
[43]毛喆.基于驾驶员生理特征分析的驾驶疲劳状态识别方法研究[D].武汉理工大学硕士学位论文，2006.
[44]Murphy Chutorian E, and Trivedi M M. Head pose estimation in computer vision: asurvey [J] IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(4):607626.
[45]Fan X, Sun Y, Yin B, and Guo X. Gabor based dynamic representation for humanfatigue monitoring in facial image sequences [J]. Pattern Recognition Letters,2010,31(3):234243.
[46]施树明,金立生,王荣本,童兵亮.基于机器视觉的驾驶员嘴部状态检测方法[J].吉林大学学报(工学版),2004,34(2):232236.
[47]Wierwille W W, Ellsworth L A, Wreggit S S, Fairbanks R J, Kirn CL. Research onvehicle based driver status/performance monitoring: development, validation, andrefinement of algorithms for detection of driver drowsiness [R]. National HighwayTraffice Safety Administraion Final Report. DOT HS808247,1994.
[48]Murphy Chutorian E. Trivedi M M. Head pose estimation and augmented realitytracking: An integrated system and evaluation for monitoring driver awareness [J]. IEEETransactions on Intelligent Transportation Systems,2010,11(2),300311.
[49]Smith P, Shah M, Vitoria L N. Determining driver visual attention with one camera [J].IEEE Transactions on Intelligent Transportation Systems,2003,4(4),205218.
[50]D’Orazio T, Leo M, Guaragnella C, Distante A. A visual approach for driver inattentiondetection [J]. Pattern Recognition.2007,40(8):23412355.
[51]Friedrichs F, and Yang B. Camera based drowsiness reference for driver stateclassification under real driving conditions [C].2010IEEE Intelligent VehiclesSymposium,2010:101106.
[52]Suzuki M, Yamamoto N, Yamamoto O, et al. Measurement of driver’s consciousness byimage processing A method for presuming driver’s drowsiness by eye blinks copingwith individual differences [C]. IEEE International Conference on Systems, Man andCybernetics,2006,4:28912896.
[53]郭克友.驾驶员疲劳状态视觉监测技术的研究[D].吉林大学博士学位论文,2003.
[54]童兵亮.基于嘴部状态的疲劳驾驶和精神分散状态监测方法研究[D].吉林大学硕士学位论文,2004.
[55]张明恒.基于面部朝向的驾驶员精神分散监测方法研究[D].吉林大学博士学位论文,2007.
[56]孙海燕.基于双目视觉的驾驶人注意力分散监测方法研究[D].吉林大学硕士学位论文,2012.
[57]叶建.基于图像序列的自标定方法研究[D].吉林大学硕士学位论文,2013.
[58]http://www.seeingmachines.com/pdfs/brochures/DSS Fleet.pdf,2008.
[59]http://www.seeingmachines.com/pdfs/brochures/faceLAB5.pdf,2009.
[60]Mortazavi A, Eskandarian A, Sayed R A. Effect of drowsiness on driving performancevariables of commercial vehicle drivers [J]. International Journal of AutomotiveTechnology,2009,10(3):391404.
[61]Forsman P M, Vila B J, Short R A, et al. Efficient driver drowsiness detection atmoderate levels of drowsiness [J], Accident Analysis and Prevention,2013,50:341350.
[62]Berglund J. In vehicle prediction of truck driver sleepiness steering wheel variables [D].Link ping: Link pings Universitet,2007.
[63]Mattsson K. In vehicle prediction of truck driver sleepiness lane position variables [D].S dert lje: Lule University of Technology,2007.
[64]Friedrichs F, Yang Bin. Drowsiness monitoring by steering and lane data based feathersunder real driving conditions [C].18th European Signal Processing Conference, Aalborg,2010:2327.
[65]Emily Nodine. The detection of drowsy drivers through driver performance indicators[D]. Tufts University.2008.
[66]李伟,何其昌,范秀敏.基于汽车操纵信号的驾驶员疲劳状态检测[J].上海交通大学学报,2010,44(2):292296.
[67]石坚,吴远鹏,卓斌,等.汽车驾驶员主动安全性因素的辨识与分析[J].上海交通大学学报,2000,34(4):441444.
[68]张希波,成波,冯睿嘉.基于方向盘操作的驾驶人疲劳状态实时检测方法[J].清华大学学报:自然科学版,2010,50(7):10721076.
[69]Electronic Safety Products.(n.d.). S.A.M.G3steering attention monitor. Retrieved2005,September1, from http://www.driverfatigue.com/samg3.html.
[70]May J F, Baldwin C L. Driver fatigue: The importance of identifying causal factors offatigue when considering detection and countermeasure technologies [J]. TransportationResearch Part F,2009,12:218224.
[71]http://vico.vw.com.cn/zh/models/tiguan.html.
[72]A. Eskandarian, R. Sayed, P. Delaigue, J. Blum, and A. Mortazavi. Advanced driverfatigue research [R], Washington, DC, Report No. FMCSA RRR07001,2007.
[73]Yang G S, Lin Y Z, Bhattacharyac P. A driver fatigue recognition model based oninformation fusion and dynamic bayesian network [J]. Information Sciences,2010,180(10):19421954.
[74]Miyaji M, Kawanaka H, and Oguri K. Driver’s cognitive distraction detection usingphysiological features by the AdaBoost [C].12th International IEEE Conference onIntelligent Transportation Systems,2009:16.
[75]Sathyanarayana A, Nageswaren S, Ghasemzadeh H, Jafari R, and Hansen J H. Bodysensor networks for driver distraction identification [C], IEEE ICVES,2008:120125.
[76]成波,冯睿嘉,张伟,李家文,张希波.基于多源信息融合的驾驶人疲劳状态监测及预警方法研究[J].公路交通科技,2009,26:1318.
[77]汪澎.驾驶人警觉状态检测技术研究[D].江苏大学博士学位论文,2010.
[78]顾征远.面向驾驶员的疲劳监测系统研究[D],浙江大学硕士学位论文,2013.
[79]陈勇,黄琦,刘霞,张昌华.一种全天候驾驶员疲劳检测方法研究[J].仪器仪表学报.2009,30(3):636640.
[80]李啸.转向盘转角特性在驾驶疲劳检测中的应用研究[D].北京林业大学硕士学位论文,2009.
[81]Godley S T, Triggs T J, Fildes B N. Driving simulator validation for speed research [J].Accident Analysis and Prevention,2002,34:589600.
[82]Williamson A, Boufous S. A data matching study of the role of fatigue in work relatedcrashes [J]. Transportation Research Part F: Traffic Psychology and Behavior,2007,10:242253.
[83]Johns M W. A sleep physiologist’s view of a drowsy driver [J]. Transportation ResearchPart F: Traffic Psychology and Behavior,2000.3(4):241249.
[84]Smith S, Carrington M&Trinder J. Subjective and predicted sleepiness while driving inyoung adults [J]. Accident Analysis and Prevention,2005,37(6):10661073.
[85]Philip P, Taillard J, Klein E, et al. Effect of fatigue on performance measured by adriving simulator in automobile drivers [J]. Journal of Psychosomatic Research,2003,55:197200.
[86]Moller H J, Kayumov L, Bulmash E L, et al. Simulator performance, microsleepepisodes, and subjective sleepiness: normative data using convergent methodologies toassess driver drowsiness [J]. Journal of Psychosomatic Research,2006,61:335342.
[87]Hebbale K V, Ghoneim Y A. A speed and acceleration estimation algorithm forpowertrain control [C]. Proceedings of the1991American Control Conference, Boston,MA, June1991.
[88]Nakayama O, Futami T, Nakamura T, et al. Development of steering entropy method forevaluating driver workload [R]. SAE Technical Paper Series:#1999010892. Paperpresented at the International Congress and Exposition, Detroit, Michigan.
[89]Fancher P, Ervin R, Sayer J, Hagan M, et al. Intelligent cruise control field operationaltest. National Highway Traffic Safety Administration Technical Document [R], ReportNumber DOTHS808849,1998.
[90]Brown I D. Prospects for technological countermeasures against driver fatigue [J].Accident Analysis and Prevention.1997,29(4):525531.
[91]Bergasa L M, Nuevo J, Sotelo M A, Barea R, Lopez M E. Real time system formonitoring driver vigilance [J]. IEEE Transactions on Intelligent Transportation Systems,2006,7(1):6377.
[92]Bishop R.Survey of intelligent vehicle applications worldwide [C]. Proeeedings of theIEEE intelligent Vehicles symposium,2000:2530.
[93]Dong Y C, Hu Z C, Uchimura K, Murayama N. Driver inattention monitoring systemfor intelligent vehicles: a review [J]. IEEE Transactions on Intelligent TransportationSystems,2011,12(2):596614.
[94]郑培,宋正河,周一鸣.基于PERCLOS的机动车驾驶员驾驶疲劳的识别算法[J],中国农业大学学报,2002,7(2):104109.
[95]Sahayadhas A, Sundaraj K, Murugappan M. Detecting driver drowsiness based onsensors: a review [J]. Sensors,2012,12:1693716953.
[96]李爽.疲劳驾驶特征和参数提取研究[D].山东大学硕士学位论文,2013.
[97]Lenskiy A A, Lee J S. Driver’s eye blinking detection using novel color and texturesegmentation algorithms [J]. International Journal of Control Automation and Systems,2012,10(2):317327.
[98]盛敬.驾驶员疲劳监控系统中人脸检测与识别研究[D].东北大学硕士学位论文.2006:2933.
[99]李玲玲.基于多视觉信息融合的驾驶员疲劳检测方法研究与实现[D].北方工业大学硕士学位论文,2010.
[100]张伟.基于机器视觉的驾驶人疲劳状态识别关键问题研究[D].清华大学博士学位论文,2011.
[101] Yekhshatyan L, Lee J D. Changes in the correlation between eye and steeringmovements indicate driver distraction [J]. IEEE Transactions on IntelligentTransportation Systems,2013,14(1):136145.
[102]侯海晶.高速公路驾驶人换道意图识别方法研究[D],吉林大学博士学位论文.2013.
[103] Zhu Z W, Ji Q, Bennett K P. Nonlinear eye gaze mapping function estimation viasupport vector regression [C]. Proceedings of the18th International Conference onPattern Recognition, Hong Kong, China,2006:11321135.
[104] Crundall D, Underwood G. Effects of experience and processing demands on visualinformation acquisition in drivers [J]. Ergonomics,1998,41(4):448458.
[105] Lethaus F, Rataj J. Do eye movements reflect driving manoeuvres?[C]. IETIntelligent Transportation System.2007,1(3):199204.
[106]孟妮.不同道路交通环境中驾驶员注视行为分析[D].长安大学硕士学位论文.2009.
[107] Shazzad K M, Park J S, Optimization of intrusion detection through fast hybridfeature selection [C]. Proceedings of the6th International Conference on Parallel andDistributed Computing,2005,264267.
[108]张丽新.高维数据的特征选择及基于特征选择的集成学习研究[D],清华大学博士学位论文,2004.
[109] Su Y, Murali T M, Pavlovic V. RankGene: identification of diagnostic genes basedon expression data [J], Bioinformatics,2003,19(12):15781579.
[110]胡洁.高维数据特征降维综述[J].计算机应用研究,2008,25(9):26012606.
[111] Lei Y, Huan L. Efficient feature selection via analysis of relevance and redundancy[J]. Journal of Machine Learning Research,2004,35(5):12051224.
[112] Lei Y, Huan L, Feature selection for high dimensional data: a fast correlation basedfilter solution [D]. Washington University,2003.
[113] Yvan S, Inaki I, Pedro L.A review of feature selection techniques in bioinformatics[J]. Bioinformatics,2007,23(19):25072517.
[114] Ververidis D, Kotropoulos C, Fast and accurate sequential floating forward featureselection with the bayes classifier applied to speech emotion recognition [J]. SignalProcessing,2008,88(5):29562970.
[115] Wang Y, Tetko I V, Hall M A. Gene selection from microarray data for cancerclassification a machine learning approach [J]. Computational Biology and Chemistry,2005,29(1):3746.
[116] Kohavi R, John G H. Wrappers for feature subset selection [J]. ArtificialIntelligence,1997,97(12):273324.
[117] Das S. Filters, wrappers and a boosting based hybrid for feature selection [C].ICML,2001:7481.
[118] Blum A L. Learning boolean functions in an infinite attribute space [J]. MachineLearning,1992,9(4):373386.
[119] Huang J, Cai Y, Xu X, A wrapper for feature selection based on mutual information[C],18th International Conference on Pattern Recognition, Washington DC,2006:618621
[120] Pudil P, Novovi ová J, Kittler J. Floating search methods in feature selection [J].Pattern Recognition Letters,1994,15(11):11191125.
[121]范昕炜.支持向量机算法的研究及其应用[D].浙江大学博士学位论文,2003.
[122]肖汉光,蔡从中.特征向量的归一化比较性研究[J].计算机工程与应用,2009,45(22):117119.
[123] Liang Y L, Reyes M L, and Lee J D. Real time detection of driver cognitivedistraction using support vector machines [J], IEEE Transactions on IntelligentTransportation Systems,2007,8(2):340350.
[2] NHTSA. Traffic Safety Facts [R]. Report DOT HS811402, NHTSA, US Departmentof Transportation,2011
[3] Jin L S, Niu Q N, Hou H J, et al. A pedestrian detection method using3D laser scanner[J], InformationAn International Interdisciplinary Journal,2012,15(12A):54815490.
[4]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（20002011）[R].公安部交通管理局，20012011.
[5] Klauer S G, Dingus T A, Neale V L, et al. The impact of driver inattention onnear crash/crash risk: An analysis using the100car naturalistic driving study data [R].Washington: National Highway Traffic Safety Administration,2006.
[6] Liu C, and Subramanian R. Factors related to fatal singlevehicle run off road crashes[R], DOTHS811232, U.S. Department of Transportation, American National HighwayTraffic Safety Administration, Washington, DC, USA,2009.
[7]刘灵,邓小燕,徐颖.汽车驾驶员驾驶疲劳监测方法与装置的研究现状[J].医疗卫生装备,2006,27(12):2830．
[8] MacLean A W, Davies D R T,&Thiele K. The hazards and prevention of driving whilesleepy [J]. Sleep Medicine Reviews,2003,7:507521.
[9] Jin L S, Niu Q N, Jiang Y Y, et al. Driver sleepiness detection system based on eyemovements variables [J], Advances in Mechanical Engineering,2013,2013:17.
[10]Nordbakke S, Sagberg F. Sleepy at the wheel: Knowledge, symptoms and behaviouramong car drivers [J], Transportation Research Part F,2007,10:110.
[11]邸巍.基于视觉的全天候驾驶员疲劳与精神分散状态监测方法研究[D],吉林大学博士学位论文,2010.
[12]Vanlaar W, Simpson H, Mayhew D, et al. Fatigued and drowsy driving: A survey ofattitudes, opinions and behaviors [J]. Journal of Safety Research,2008,9(3):303309.
[13]National Sleep Foundation,2009. Sleep in America Poll. National Sleep Foundation,Washington, D.C. http://sleepfoundation.org/
[14]谢晓莉.驾驶疲劳生成机理研究[D],北京工业大学博士学位论文,2010.
[15]毛喆.机动车疲劳驾驶行为识别方法研究[D],武汉理工大学博士学位论文,2009.
[16]Bartlett F C, Ferrier lecture: fatigue following highly skilled work [J]. Proceedings ofthe Royal Society, Series B,1943,131:247257.
[17]Grandjean E. Fatigue in industry [J]. British Journal of Industrial Medicine,1979,36:175186.
[18]周宝宽.中医疲劳与亚健康研究[D],辽宁中医学院博士学位论文,2003.
[19]Simons D J, Rensink R A. Change blindness: past, present, and future [J]. Trends inCognitive Sciences,2005,9(1):1620.
[20]Khushaba R N, Kodagoda S, Lal S, and Dissanayake G. Driver drowsiness classificationusing fuzzy wavelet packet based feature extraction algorithm [J], IEEE Transactions onBiomedical Engineering,2011,58(1):121131.
[21]Verwey W&Zaidel D. Predicting drowsiness accidents from personal attributes, eyeblinks, and ongoing driving behavior [J]. Personality and Individual Differences,1999,28(1):123142.
[22]Regan M A, Hallett C, Gordon C P. Driver distraction and driver inattention: definition,relationship and taxonomy [J], Accident Analysis and Prevention,2011,43:17711781.
[23]李志春.驾驶员疲劳状态检测技术研究与工程实现[D],江苏大学博士学位论文，2009.
[24] kerstedt T, Gillberg M. Subjective and objective sleepiness in the active individual [J].International Journal of Neuroscience,1990,52(1):2937.
[25]Morris T L, Miller J C. Electrooculographic and performance indices of fatigue duringsimulated flight [J], Biological Psychology,1996,42(3):343360.
[26]EMIly Nodine. The detection of drowsy drivers through driver performance indicators
[D]. Tufts University, master thesis,2008.
[27]Kaida K, Takahashi M, Akerstedt T, Nakata A, Otsuka Y, Haratani T, and Fukasawa K,Validation of the Karolinska sleepiness scale against performance and EEG variables [J].Clinical Neurophysiology,2006,117(7):15741581.
[28]Ingre M, Akerstedt T, Peters B. A. Anund, and G. Kecklund. Subjective sleepiness,simulated driving performance and blink duration: Examining individual differences [J],Journal of Sleep Research,2006,15(1):4753.
[29]Belz S M, Robinson G S,&Casali J G. Temporal separation and self rating of alertnessas indicators of driver fatigue in commercial motor vehicle operators [J]. Human Factors,2004,46(1):154169.
[30]Lal S K L, Craig A. Electroence phalography activity associated with driver fatigue:implications for a fatigue countermeasure device [J]. Joumal of Psychophysiology,2001,15(3):183189.
[31]屈肖蕾.基于转向操作和车辆状态的疲劳驾驶检测方法研究[D].清华大学硕士学位论文,2012.
[32]Carroll J S, Blisewise D L, Dement W C. A method for checking interobserver reliabilityin observational sleep studies [J]. Sleep,1989,12(4):363367.
[33]Wierwille W W, Ellsworth L A. Evaluation of driver drowsiness by trained observers [J].Accident Analysis and Prevention,1994,26(5):571581.
[34]Niu Q N, Jin L S, Hou H J, et al. Driver fatigue detection system based on eyemovements [C]. ICTIS2013,657663.
[35]Shen K Q, Li X P, Ong C J, Shao S Y, and Wilder Smith E P V. EEG based mentalfatigue measurement using multiclass support vector machines with confidence estimate[J], Clinical Neurophysiology,2008,119(7):15241533.
[36]Lin C T, Chen Y C, Huang T Y, Chiu T T. Development of wireless brain computerinterface with embedded multitask scheduling and its application on real time driver’sdrowsiness detection and warning [J]. IEEE Transactions on Biomedical Engineering,2008,55(5):15821591.
[37]Jap B T, Lal S, Fischer P, and Bekiaris E. Using EEG spectral components to assessalgorithms for detecting fatigue [J] Expert Systems Application,2009,36(2):23522359.
[38]Lal S K L, Craig A, Boord P, et al. Development of an algorithm for an EEG baseddriver fatigue countermeasure [J]. Journal of Safely Research,2003,34(3):321328.
[39]Yeo M V M, Li X P, Shen K, et al. Can SVM be used for automatic EEG detection ofdrowsiness during car driving [J]. Safety Science,2009,47(1):115124.
[40]毛科俊,刘小明,赵晓华等.基于脑电信号的驾驶疲劳预报关键参数选取[J].北京工业大学学报,2010,36(7):966970.
[41]毛科俊,赵晓华,刘小明等.基于脑电分析的驾驶疲劳预报研究[J].人类工效学,2009,15(4):2529.
[42]Patel M, Lala S K L, Kavanagha D, Rossiterb P, Applying neural network analysis onheart rate variability data to assess driver fatigue [J]. Expert Systems with Applications,2011,38(6):72357242.
[43]毛喆.基于驾驶员生理特征分析的驾驶疲劳状态识别方法研究[D].武汉理工大学硕士学位论文，2006.
[44]Murphy Chutorian E, and Trivedi M M. Head pose estimation in computer vision: asurvey [J] IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(4):607626.
[45]Fan X, Sun Y, Yin B, and Guo X. Gabor based dynamic representation for humanfatigue monitoring in facial image sequences [J]. Pattern Recognition Letters,2010,31(3):234243.
[46]施树明,金立生,王荣本,童兵亮.基于机器视觉的驾驶员嘴部状态检测方法[J].吉林大学学报(工学版),2004,34(2):232236.
[47]Wierwille W W, Ellsworth L A, Wreggit S S, Fairbanks R J, Kirn CL. Research onvehicle based driver status/performance monitoring: development, validation, andrefinement of algorithms for detection of driver drowsiness [R]. National HighwayTraffice Safety Administraion Final Report. DOT HS808247,1994.
[48]Murphy Chutorian E. Trivedi M M. Head pose estimation and augmented realitytracking: An integrated system and evaluation for monitoring driver awareness [J]. IEEETransactions on Intelligent Transportation Systems,2010,11(2),300311.
[49]Smith P, Shah M, Vitoria L N. Determining driver visual attention with one camera [J].IEEE Transactions on Intelligent Transportation Systems,2003,4(4),205218.
[50]D’Orazio T, Leo M, Guaragnella C, Distante A. A visual approach for driver inattentiondetection [J]. Pattern Recognition.2007,40(8):23412355.
[51]Friedrichs F, and Yang B. Camera based drowsiness reference for driver stateclassification under real driving conditions [C].2010IEEE Intelligent VehiclesSymposium,2010:101106.
[52]Suzuki M, Yamamoto N, Yamamoto O, et al. Measurement of driver’s consciousness byimage processing A method for presuming driver’s drowsiness by eye blinks copingwith individual differences [C]. IEEE International Conference on Systems, Man andCybernetics,2006,4:28912896.
[53]郭克友.驾驶员疲劳状态视觉监测技术的研究[D].吉林大学博士学位论文,2003.
[54]童兵亮.基于嘴部状态的疲劳驾驶和精神分散状态监测方法研究[D].吉林大学硕士学位论文,2004.
[55]张明恒.基于面部朝向的驾驶员精神分散监测方法研究[D].吉林大学博士学位论文,2007.
[56]孙海燕.基于双目视觉的驾驶人注意力分散监测方法研究[D].吉林大学硕士学位论文,2012.
[57]叶建.基于图像序列的自标定方法研究[D].吉林大学硕士学位论文,2013.
[58]http://www.seeingmachines.com/pdfs/brochures/DSS Fleet.pdf,2008.
[59]http://www.seeingmachines.com/pdfs/brochures/faceLAB5.pdf,2009.
[60]Mortazavi A, Eskandarian A, Sayed R A. Effect of drowsiness on driving performancevariables of commercial vehicle drivers [J]. International Journal of AutomotiveTechnology,2009,10(3):391404.
[61]Forsman P M, Vila B J, Short R A, et al. Efficient driver drowsiness detection atmoderate levels of drowsiness [J], Accident Analysis and Prevention,2013,50:341350.
[62]Berglund J. In vehicle prediction of truck driver sleepiness steering wheel variables [D].Link ping: Link pings Universitet,2007.
[63]Mattsson K. In vehicle prediction of truck driver sleepiness lane position variables [D].S dert lje: Lule University of Technology,2007.
[64]Friedrichs F, Yang Bin. Drowsiness monitoring by steering and lane data based feathersunder real driving conditions [C].18th European Signal Processing Conference, Aalborg,2010:2327.
[65]Emily Nodine. The detection of drowsy drivers through driver performance indicators[D]. Tufts University.2008.
[66]李伟,何其昌,范秀敏.基于汽车操纵信号的驾驶员疲劳状态检测[J].上海交通大学学报,2010,44(2):292296.
[67]石坚,吴远鹏,卓斌,等.汽车驾驶员主动安全性因素的辨识与分析[J].上海交通大学学报,2000,34(4):441444.
[68]张希波,成波,冯睿嘉.基于方向盘操作的驾驶人疲劳状态实时检测方法[J].清华大学学报:自然科学版,2010,50(7):10721076.
[69]Electronic Safety Products.(n.d.). S.A.M.G3steering attention monitor. Retrieved2005,September1, from http://www.driverfatigue.com/samg3.html.
[70]May J F, Baldwin C L. Driver fatigue: The importance of identifying causal factors offatigue when considering detection and countermeasure technologies [J]. TransportationResearch Part F,2009,12:218224.
[71]http://vico.vw.com.cn/zh/models/tiguan.html.
[72]A. Eskandarian, R. Sayed, P. Delaigue, J. Blum, and A. Mortazavi. Advanced driverfatigue research [R], Washington, DC, Report No. FMCSA RRR07001,2007.
[73]Yang G S, Lin Y Z, Bhattacharyac P. A driver fatigue recognition model based oninformation fusion and dynamic bayesian network [J]. Information Sciences,2010,180(10):19421954.
[74]Miyaji M, Kawanaka H, and Oguri K. Driver’s cognitive distraction detection usingphysiological features by the AdaBoost [C].12th International IEEE Conference onIntelligent Transportation Systems,2009:16.
[75]Sathyanarayana A, Nageswaren S, Ghasemzadeh H, Jafari R, and Hansen J H. Bodysensor networks for driver distraction identification [C], IEEE ICVES,2008:120125.
[76]成波,冯睿嘉,张伟,李家文,张希波.基于多源信息融合的驾驶人疲劳状态监测及预警方法研究[J].公路交通科技,2009,26:1318.
[77]汪澎.驾驶人警觉状态检测技术研究[D].江苏大学博士学位论文,2010.
[78]顾征远.面向驾驶员的疲劳监测系统研究[D],浙江大学硕士学位论文,2013.
[79]陈勇,黄琦,刘霞,张昌华.一种全天候驾驶员疲劳检测方法研究[J].仪器仪表学报.2009,30(3):636640.
[80]李啸.转向盘转角特性在驾驶疲劳检测中的应用研究[D].北京林业大学硕士学位论文,2009.
[81]Godley S T, Triggs T J, Fildes B N. Driving simulator validation for speed research [J].Accident Analysis and Prevention,2002,34:589600.
[82]Williamson A, Boufous S. A data matching study of the role of fatigue in work relatedcrashes [J]. Transportation Research Part F: Traffic Psychology and Behavior,2007,10:242253.
[83]Johns M W. A sleep physiologist’s view of a drowsy driver [J]. Transportation ResearchPart F: Traffic Psychology and Behavior,2000.3(4):241249.
[84]Smith S, Carrington M&Trinder J. Subjective and predicted sleepiness while driving inyoung adults [J]. Accident Analysis and Prevention,2005,37(6):10661073.
[85]Philip P, Taillard J, Klein E, et al. Effect of fatigue on performance measured by adriving simulator in automobile drivers [J]. Journal of Psychosomatic Research,2003,55:197200.
[86]Moller H J, Kayumov L, Bulmash E L, et al. Simulator performance, microsleepepisodes, and subjective sleepiness: normative data using convergent methodologies toassess driver drowsiness [J]. Journal of Psychosomatic Research,2006,61:335342.
[87]Hebbale K V, Ghoneim Y A. A speed and acceleration estimation algorithm forpowertrain control [C]. Proceedings of the1991American Control Conference, Boston,MA, June1991.
[88]Nakayama O, Futami T, Nakamura T, et al. Development of steering entropy method forevaluating driver workload [R]. SAE Technical Paper Series:#1999010892. Paperpresented at the International Congress and Exposition, Detroit, Michigan.
[89]Fancher P, Ervin R, Sayer J, Hagan M, et al. Intelligent cruise control field operationaltest. National Highway Traffic Safety Administration Technical Document [R], ReportNumber DOTHS808849,1998.
[90]Brown I D. Prospects for technological countermeasures against driver fatigue [J].Accident Analysis and Prevention.1997,29(4):525531.
[91]Bergasa L M, Nuevo J, Sotelo M A, Barea R, Lopez M E. Real time system formonitoring driver vigilance [J]. IEEE Transactions on Intelligent Transportation Systems,2006,7(1):6377.
[92]Bishop R.Survey of intelligent vehicle applications worldwide [C]. Proeeedings of theIEEE intelligent Vehicles symposium,2000:2530.
[93]Dong Y C, Hu Z C, Uchimura K, Murayama N. Driver inattention monitoring systemfor intelligent vehicles: a review [J]. IEEE Transactions on Intelligent TransportationSystems,2011,12(2):596614.
[94]郑培,宋正河,周一鸣.基于PERCLOS的机动车驾驶员驾驶疲劳的识别算法[J],中国农业大学学报,2002,7(2):104109.
[95]Sahayadhas A, Sundaraj K, Murugappan M. Detecting driver drowsiness based onsensors: a review [J]. Sensors,2012,12:1693716953.
[96]李爽.疲劳驾驶特征和参数提取研究[D].山东大学硕士学位论文,2013.
[97]Lenskiy A A, Lee J S. Driver’s eye blinking detection using novel color and texturesegmentation algorithms [J]. International Journal of Control Automation and Systems,2012,10(2):317327.
[98]盛敬.驾驶员疲劳监控系统中人脸检测与识别研究[D].东北大学硕士学位论文.2006:2933.
[99]李玲玲.基于多视觉信息融合的驾驶员疲劳检测方法研究与实现[D].北方工业大学硕士学位论文,2010.
[100]张伟.基于机器视觉的驾驶人疲劳状态识别关键问题研究[D].清华大学博士学位论文,2011.
[101] Yekhshatyan L, Lee J D. Changes in the correlation between eye and steeringmovements indicate driver distraction [J]. IEEE Transactions on IntelligentTransportation Systems,2013,14(1):136145.
[102]侯海晶.高速公路驾驶人换道意图识别方法研究[D],吉林大学博士学位论文.2013.
[103] Zhu Z W, Ji Q, Bennett K P. Nonlinear eye gaze mapping function estimation viasupport vector regression [C]. Proceedings of the18th International Conference onPattern Recognition, Hong Kong, China,2006:11321135.
[104] Crundall D, Underwood G. Effects of experience and processing demands on visualinformation acquisition in drivers [J]. Ergonomics,1998,41(4):448458.
[105] Lethaus F, Rataj J. Do eye movements reflect driving manoeuvres?[C]. IETIntelligent Transportation System.2007,1(3):199204.
[106]孟妮.不同道路交通环境中驾驶员注视行为分析[D].长安大学硕士学位论文.2009.
[107] Shazzad K M, Park J S, Optimization of intrusion detection through fast hybridfeature selection [C]. Proceedings of the6th International Conference on Parallel andDistributed Computing,2005,264267.
[108]张丽新.高维数据的特征选择及基于特征选择的集成学习研究[D],清华大学博士学位论文,2004.
[109] Su Y, Murali T M, Pavlovic V. RankGene: identification of diagnostic genes basedon expression data [J], Bioinformatics,2003,19(12):15781579.
[110]胡洁.高维数据特征降维综述[J].计算机应用研究,2008,25(9):26012606.
[111] Lei Y, Huan L. Efficient feature selection via analysis of relevance and redundancy[J]. Journal of Machine Learning Research,2004,35(5):12051224.
[112] Lei Y, Huan L, Feature selection for high dimensional data: a fast correlation basedfilter solution [D]. Washington University,2003.
[113] Yvan S, Inaki I, Pedro L.A review of feature selection techniques in bioinformatics[J]. Bioinformatics,2007,23(19):25072517.
[114] Ververidis D, Kotropoulos C, Fast and accurate sequential floating forward featureselection with the bayes classifier applied to speech emotion recognition [J]. SignalProcessing,2008,88(5):29562970.
[115] Wang Y, Tetko I V, Hall M A. Gene selection from microarray data for cancerclassification a machine learning approach [J]. Computational Biology and Chemistry,2005,29(1):3746.
[116] Kohavi R, John G H. Wrappers for feature subset selection [J]. ArtificialIntelligence,1997,97(12):273324.
[117] Das S. Filters, wrappers and a boosting based hybrid for feature selection [C].ICML,2001:7481.
[118] Blum A L. Learning boolean functions in an infinite attribute space [J]. MachineLearning,1992,9(4):373386.
[119] Huang J, Cai Y, Xu X, A wrapper for feature selection based on mutual information[C],18th International Conference on Pattern Recognition, Washington DC,2006:618621
[120] Pudil P, Novovi ová J, Kittler J. Floating search methods in feature selection [J].Pattern Recognition Letters,1994,15(11):11191125.
[121]范昕炜.支持向量机算法的研究及其应用[D].浙江大学博士学位论文,2003.
[122]肖汉光,蔡从中.特征向量的归一化比较性研究[J].计算机工程与应用,2009,45(22):117119.
[123] Liang Y L, Reyes M L, and Lee J D. Real time detection of driver cognitivedistraction using support vector machines [J], IEEE Transactions on IntelligentTransportation Systems,2007,8(2):340350.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |