基于熵权灰色关联和D-S证据理论的疲劳驾驶险态辨识
|
摘要
为解决驾驶员疲劳驾驶险态辨识的复杂不确定性问题,提出了一种疲劳驾驶行为状态辨识方法。该方法基于熵权灰色关联和Dempster-Shafer(D-S)证据理论,兼顾处理了不同指标的综合性与标识目标的不确定性。利用熵权理论计算指标权重,运用灰色关联分析法,确定各指标的不确定信度,构建不同目标的Mass函数;基于D-S证据理论的Dempster证据合成法则,融合Mass函数,实现驾驶员疲劳驾驶行为险态辨识;运用面部视频的专家评价判断方法检验辨识方法。试验结果表明:该方法在高速工况下识别精度达91.25%。因而,与基于单传感器的检测方法相比,有效提高了驾驶行为辨识的准确性、可靠性。
An approach about dangerous driving behavior recognition was proposed to solve the problem of uncertainty and complex in driver's behavior identification. This approach was based on a combination of Dempster-Shafer(D-S) evidence theory with entropy weight grey incidence considering both the comprehension of different indexes and the uncertainty of different goals. The weights of indexes were calculated by entropy theory to determine uncertainty reliabilities with grey relation analysis and to construct a Mass Functions for different goals. Dangerous driver status was identified based on Dempster synthesis rule with D-S theory evidence that integrated Mass functions. An expert evaluation method based on facial video was used to judge driving behaviors. The experimental results show that the method provides the recognition accuracy of 91.25% under high-speed condition. Therefore, the reliability and accuracy of the identification method are significantly higher than those of single sensor are.
An approach about dangerous driving behavior recognition was proposed to solve the problem of uncertainty and complex in driver's behavior identification. This approach was based on a combination of Dempster-Shafer(D-S) evidence theory with entropy weight grey incidence considering both the comprehension of different indexes and the uncertainty of different goals. The weights of indexes were calculated by entropy theory to determine uncertainty reliabilities with grey relation analysis and to construct a Mass Functions for different goals. Dangerous driver status was identified based on Dempster synthesis rule with D-S theory evidence that integrated Mass functions. An expert evaluation method based on facial video was used to judge driving behaviors. The experimental results show that the method provides the recognition accuracy of 91.25% under high-speed condition. Therefore, the reliability and accuracy of the identification method are significantly higher than those of single sensor are.
引文
[1]杨方宜.基于机器视觉的车辆前方危险目标识别及风险评估研究[D].昆明:昆明理工大学,2014.YANG Fangyi.Study of Risk Recognition and Assessment for front of vehicles based on Machine Vision[D].Kun Ming:Kunming University of Science and Technology,2014.(in Chinese)
[2]AL-Madani H,AL-Janahi A R.Assessment of drivers,comprehension of traffic signs based on their traffic,personal and social characteristics[J].Transpo Res Part F,2002,5(1):63-76.
[3]Klauer S G,Dingus T A,Neale V L,et al.The impact of driver inattention on near-crash/crash risk:an analysis using the 100-car naturalistic driving study data[R].Washington:National Highway Traffic Safety Administration,2006.
[4]LIANG Yulan,Lee J D,Reyes M L.Non-intrusive Detection of Driver Cognitive Distraction in Real time Using Bayesian Networks[C]//TRB,Annual Meeting,2007:1~12.
[5]盛译萱.基于BP神经网络的驾驶员状态识别及行为分析[J].燕山大学学报,2016,40(4):366-371.SHENG Yixuan.Drivers’state recognition and behavior analysis based on BP neural network algorithm[J].J Yanshan Univ,2016,40(4):366-371.(in Chinese)
[6]司东美.高速公路驾驶员不良驾驶行为危险度研究[D].长春:吉林大学,2012.6.SI Dongmei.Research on the risk of drivers’adverse driving behavior on freeway[D].Changchun:Jiling University,2016.(in Chinese)
[7]孟宪营.基于灰色关联度的车辆运行安全模糊综合评价研究[D].哈尔滨:哈尔滨工业大学,2010.MENG Xianying.Fuzzy comprehensive evaluation of safety of vehicle operation based on grey relative analysis[D].Harbin:Harbin Institute of Technology,2010.(in Chinese)
[8]赵永,朱家诚,肖献强,等.基于D-S理论和BP网络的驾驶行为识别技术研究[J].机械设计与制造,2015(5):228-230.ZHAO Yong,ZHU Jiacheng,XIAO Xianiang.Research on driving behavior recognition based on combination of D-S evidence theory with BP neural network[J].Mach Design&Manu,2015(5):228-230.(in Chinese)
[9]段新生.证据理论与决策、人工智能[M].北京:中国人民大学出版社,l993:56-68.DUAN Xinsheng.Evidence Theory and Decision,Artificial Intelligence[M].Beijing:China Renmin University Press,l993:56-68.
[10]李嘉良,马东辉,王威,等.基于证据理论和熵权灰色关联的潜在地震滑坡危险性评价[J].中南大学学报:自然科版,2016,47(5):1730-1735.LI Jialiang,MA Donghui,WANG Wei,et al.Assessment of potential seismic landslide hazard based on evidence theory and entropy weight grey incidence[J].J Central South Univ:Sci and Tech,2016,47(5):1730-1735.(in Chinese)
[11]张肃.基于灰色关联度分析的目标威胁程度评估[J].制导与引信.2005,26(3):19-23.ZHANG Su.Evaluation on the aerial targets threat degree based on grey relationship analysis[J].Guidance Fuze.2005,26(3):19-23.(in Chinese)
[12]吴超仲,张晖,毛喆,等.基于驾驶操作行为的驾驶员疲劳状态识别模型研究[J].中国安全科学学报.2007,17(4):162-165.WU Chaozhong,ZHANG Hui,MAO Zhe.et al.A model for identifying fatigue status of vehicle drivers based on driving operation[J].Chin Safety Sci J,2007,17(4):162-165.(in Chinese)
[13]戴军,张进,姚洪略,等.基于信息融合技术的驾驶员疲劳度实时监控系统[J].广东技术师范学院学报,2006.6(6):29-31.DAI Jun,ZHANG Jin,YAO Honglu,et al.Fatigue driving status’monitoring system based on information fusion technology[J].J Guangdong Polytech Normal Univ,2006.6(6):29-31.(in Chinese)
[14]冯运卿,李雪梅,李学伟,等.基于熵权法与灰色关联分析的铁路安全综合评价[J].安全与环境学报,2014,14(2):73-79.FENG Yunqing,LI Xuemei,LI Xuewei,et al.Comprehensive evaluation method for the railway safety based on the entropy method and the grey relation analysis[J].J Safety and Envir,2014,14(2):73-79.(in Chinese)
[15]黄皓.基于驾驶操作及车辆状态的疲劳驾驶行为检测研究[D].南京:东南大学,2016.HUANG Hao.Fatigue driving detection based on driver behavior and vehicle state[D].Nanjing:Southeast University,2016.(in Chinese)
[16]屈肖蕾,成波,林庆峰,等.基于驾驶员转向操作特性的疲劳驾驶检测[J].汽车工程,2013,35(9):803-807.QU Xiaolei,CHENG Bo,LIN Qingfeng,et al.Drowsy driving detection based on driver's steering operation characteristics[J].Automotive Engineering,2013,35(9):803-807.(in Chinese)
[17]吴绍斌,高利,王刘安.基于脑电信号的驾驶疲劳检测研究[J].北京理工大学学报,2009,29(12):1072-1074.WU Shaobin,GAO Li,WANG Liuan.Detecting driving fatigue based on electroencephalogram[J].Trans Beijing Institute of Technology,2009,29(12):1072-1074.(in Chinese)
[18]谭德荣,吕长民,于广鹏,等.高速公路环境下驾驶员状态辨识[J].河南科技大学学报:自然科学版,2016,37(3):29-33.TAN Derong,LV Changmin,YU Guangpeng,et al.Identification of the Driver's State in Highway Environment[J].J Henan Univ Sci and Tech:Nat Sci,2016,37(3):29-33.(in Chinese)
[19]Smith S,Carrington M&Trinder J.Subjective and predicted sleepiness while driving in young adults[J].Accident Analysis and Prevention,2005,37(6):10661073.
[20]Philip P,Taillard J,Klein E,et al.Effect of fatigue on performance measured by a driving simulator in automobile drivers[J].Journal of Psychosomatic Research,2003,55:197 200.
[21]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].北京:清华大学,2012.QU Xiaolei.Detection of Driver Drowsiness Based on Steering Operation and Vehicle State[D].Bei Jing:Tsinghua University,2012.(in Chinese)
[22]Wierwille W W,Ellsworth L A.Evaluation of driver drowsiness by trained observers[J].Accident Analysis and Prevention,1994,26(5):571-581.
[23]成波,冯睿嘉,张伟,等.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(S1):13-17.CHENG Bo,FENG Ruijia,ZHANG Wei,et al.Driver Drowsiness Detection and Warning System Based on Multi-Source Information[J].J Highway and Transp Res and Dev,2009,26(S1):13-17.(in Chinese)
[2]AL-Madani H,AL-Janahi A R.Assessment of drivers,comprehension of traffic signs based on their traffic,personal and social characteristics[J].Transpo Res Part F,2002,5(1):63-76.
[3]Klauer S G,Dingus T A,Neale V L,et al.The impact of driver inattention on near-crash/crash risk:an analysis using the 100-car naturalistic driving study data[R].Washington:National Highway Traffic Safety Administration,2006.
[4]LIANG Yulan,Lee J D,Reyes M L.Non-intrusive Detection of Driver Cognitive Distraction in Real time Using Bayesian Networks[C]//TRB,Annual Meeting,2007:1~12.
[5]盛译萱.基于BP神经网络的驾驶员状态识别及行为分析[J].燕山大学学报,2016,40(4):366-371.SHENG Yixuan.Drivers’state recognition and behavior analysis based on BP neural network algorithm[J].J Yanshan Univ,2016,40(4):366-371.(in Chinese)
[6]司东美.高速公路驾驶员不良驾驶行为危险度研究[D].长春:吉林大学,2012.6.SI Dongmei.Research on the risk of drivers’adverse driving behavior on freeway[D].Changchun:Jiling University,2016.(in Chinese)
[7]孟宪营.基于灰色关联度的车辆运行安全模糊综合评价研究[D].哈尔滨:哈尔滨工业大学,2010.MENG Xianying.Fuzzy comprehensive evaluation of safety of vehicle operation based on grey relative analysis[D].Harbin:Harbin Institute of Technology,2010.(in Chinese)
[8]赵永,朱家诚,肖献强,等.基于D-S理论和BP网络的驾驶行为识别技术研究[J].机械设计与制造,2015(5):228-230.ZHAO Yong,ZHU Jiacheng,XIAO Xianiang.Research on driving behavior recognition based on combination of D-S evidence theory with BP neural network[J].Mach Design&Manu,2015(5):228-230.(in Chinese)
[9]段新生.证据理论与决策、人工智能[M].北京:中国人民大学出版社,l993:56-68.DUAN Xinsheng.Evidence Theory and Decision,Artificial Intelligence[M].Beijing:China Renmin University Press,l993:56-68.
[10]李嘉良,马东辉,王威,等.基于证据理论和熵权灰色关联的潜在地震滑坡危险性评价[J].中南大学学报:自然科版,2016,47(5):1730-1735.LI Jialiang,MA Donghui,WANG Wei,et al.Assessment of potential seismic landslide hazard based on evidence theory and entropy weight grey incidence[J].J Central South Univ:Sci and Tech,2016,47(5):1730-1735.(in Chinese)
[11]张肃.基于灰色关联度分析的目标威胁程度评估[J].制导与引信.2005,26(3):19-23.ZHANG Su.Evaluation on the aerial targets threat degree based on grey relationship analysis[J].Guidance Fuze.2005,26(3):19-23.(in Chinese)
[12]吴超仲,张晖,毛喆,等.基于驾驶操作行为的驾驶员疲劳状态识别模型研究[J].中国安全科学学报.2007,17(4):162-165.WU Chaozhong,ZHANG Hui,MAO Zhe.et al.A model for identifying fatigue status of vehicle drivers based on driving operation[J].Chin Safety Sci J,2007,17(4):162-165.(in Chinese)
[13]戴军,张进,姚洪略,等.基于信息融合技术的驾驶员疲劳度实时监控系统[J].广东技术师范学院学报,2006.6(6):29-31.DAI Jun,ZHANG Jin,YAO Honglu,et al.Fatigue driving status’monitoring system based on information fusion technology[J].J Guangdong Polytech Normal Univ,2006.6(6):29-31.(in Chinese)
[14]冯运卿,李雪梅,李学伟,等.基于熵权法与灰色关联分析的铁路安全综合评价[J].安全与环境学报,2014,14(2):73-79.FENG Yunqing,LI Xuemei,LI Xuewei,et al.Comprehensive evaluation method for the railway safety based on the entropy method and the grey relation analysis[J].J Safety and Envir,2014,14(2):73-79.(in Chinese)
[15]黄皓.基于驾驶操作及车辆状态的疲劳驾驶行为检测研究[D].南京:东南大学,2016.HUANG Hao.Fatigue driving detection based on driver behavior and vehicle state[D].Nanjing:Southeast University,2016.(in Chinese)
[16]屈肖蕾,成波,林庆峰,等.基于驾驶员转向操作特性的疲劳驾驶检测[J].汽车工程,2013,35(9):803-807.QU Xiaolei,CHENG Bo,LIN Qingfeng,et al.Drowsy driving detection based on driver's steering operation characteristics[J].Automotive Engineering,2013,35(9):803-807.(in Chinese)
[17]吴绍斌,高利,王刘安.基于脑电信号的驾驶疲劳检测研究[J].北京理工大学学报,2009,29(12):1072-1074.WU Shaobin,GAO Li,WANG Liuan.Detecting driving fatigue based on electroencephalogram[J].Trans Beijing Institute of Technology,2009,29(12):1072-1074.(in Chinese)
[18]谭德荣,吕长民,于广鹏,等.高速公路环境下驾驶员状态辨识[J].河南科技大学学报:自然科学版,2016,37(3):29-33.TAN Derong,LV Changmin,YU Guangpeng,et al.Identification of the Driver's State in Highway Environment[J].J Henan Univ Sci and Tech:Nat Sci,2016,37(3):29-33.(in Chinese)
[19]Smith S,Carrington M&Trinder J.Subjective and predicted sleepiness while driving in young adults[J].Accident Analysis and Prevention,2005,37(6):10661073.
[20]Philip P,Taillard J,Klein E,et al.Effect of fatigue on performance measured by a driving simulator in automobile drivers[J].Journal of Psychosomatic Research,2003,55:197 200.
[21]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].北京:清华大学,2012.QU Xiaolei.Detection of Driver Drowsiness Based on Steering Operation and Vehicle State[D].Bei Jing:Tsinghua University,2012.(in Chinese)
[22]Wierwille W W,Ellsworth L A.Evaluation of driver drowsiness by trained observers[J].Accident Analysis and Prevention,1994,26(5):571-581.
[23]成波,冯睿嘉,张伟,等.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(S1):13-17.CHENG Bo,FENG Ruijia,ZHANG Wei,et al.Driver Drowsiness Detection and Warning System Based on Multi-Source Information[J].J Highway and Transp Res and Dev,2009,26(S1):13-17.(in Chinese)