基于车载机器视觉的安全带识别方法研究
|
摘要
为提高安全带佩戴率,论文从三点式安全带使用过程中存在的问题出发,分析三点式安全带的不同佩戴方式对乘员损伤的影响,利用车载机器视觉对其进行识别,提出安全带识别评价方法,构建满足实时性和高精度要求的识别模型,实现了嵌入式车载安全带监控系统设计。论文研究内容包括：
1)三点式安全带使用情况调查与分析。针对我国典型城市安全带的使用状况展开调查,结果显示,安全带使用过程中存在两类问题：不规范佩戴安全带和卷曲佩戴安全带。其中,导致安全带佩戴提示系统失效的不规范佩戴行为包括：单独使用安全带带扣、预佩戴和仅系肩带；卷曲佩戴包括：肩带卷曲、腰带卷曲和严重卷曲。
2)三点式安全带的不同佩戴方式对乘员损伤影响。采用MADYMO构建乘员约束系统模型,并验证模型的有效性。运用该模型进行三点式安全带在不同佩戴方式下的乘员损伤分析,结果表明：车辆碰撞时,预佩戴安全带的乘员将从座椅位置飞出；仅系肩带将产生明显的下潜、滑移运动。上述情况均导致乘员受到致命性损伤。相比正确使用三点式安全带,卷曲佩戴将导致乘员各项损伤指标明显上升。因此,对三点式安全带不同的佩戴方式进行识别,为充分发挥安全带应有的保护作用,具有积极意义。
3)车载视频监控平台搭建及安全带图像采集试验设计。搭建安全带图像采集试验平台,在CCD传感器性能参数、红外补光装置和特殊材料安全带等方面展开具体研究；设计并实施不同光线环境下的车辆行驶试验,采集获得安全带不同佩戴方式下的乘员图像信息；研究适用于安全带识别的图像预处理技术,为构建安全带识别的多特征参数模型奠定基础。
4)构建满足实时性要求的安全带识别模型。针对安全带在线检测的要求,采用主成分分析法降维后的安全带空间参数特征作为输入向量,选用BP神经网络作为分类器,构建基于BP神经网络的安全带识别模型,以满足实时性要求。引入遗传算法(GA)对其内部参数进行优化,构建基于GA-BP神经网络的安全带识别实时性模型,以满足准确性要求。通过硬件在环测试(HIL)和模型在环测试(MIL)验证了模型的实时性和准确性。
5)构建满足高精度要求的卷曲佩戴识别模型。提取安全带结构参数的统计特征值作为输入向量,选用支持向量机(SVM)作为模型核心分类器,以交叉验证方法对内部参数进行选择,采用粒子群算法(PSO)对其进行优化,构建基于PSO-SVM的高精度识别模型,并进行软件在环测试以验证代码的有效性,从而将其应用于高精度离线检测之中。
6)实现了嵌入式车载安全带监控系统的设计。从分析车载系统对软硬件的性能要求着手,探讨了DSP内核高速处理数据的特点以及ARM内核控制和管理的功能,选择ICETEK-DM642-B评估板作为硬件平台,实现了基于嵌入式技术的安全带识别系统的设计；完成系统功能的总体设计和功能模块的软件设计,并进行程序优化。
论文研究的创新点如下：
1)提出基于车载机器视觉识别安全带的方法,搭建嵌入式车载安全带识别系统平台；
2)揭示了三点式安全带的不同佩戴方式(不规范佩戴和卷曲佩戴)与乘员损伤之间的关系；
3)提出安全带识别的实时性和准确性评价方法；
4)构建基于GA-BP神经网络的安全带识别实时性模型；
5)构建基于PSO-SVM的卷曲佩戴识别高精度模型。
In order to increase the wearing rate of seat belt, influence of different3point seat belt wearing patterns on occupant injury mechanism is analyzed, due to the existing problems in seat belt utilization. An evaluation criteria of seat belt identification is proposed by identifying seat belt with vehicle-mounted machine vision. An identification model is built to meet the requirements of real time and high precision, embedded vehicle-mounted seat belt identification system is designed and realized. The main research content is as follows:
1) Investigation and analysis of3point seat belt utilization. Investigations were launched in typical cities in China. The results show that, problems existing in using seat belt mainly are:non-standard wearing and curly wearing. Non-standard wearing patterns that cause the failure of seat belt identification system includes:using only seat belt buckle, pre-wearing seat belt and using only shoulder belt. Curly wearing patterns includes:shoulder belt curling, waist belt curling and severely curling.
2) Influence of different3point seat belt wearing patterns on occupant injury mechanism:the occupant restraint system model is built based on MADYMO software, and its validity is verified. Simulation on different seat belt wearing patterns is conducted. The simulation results demonstrate that:in the event of vehicle crash, the occupant without seat belt will be thrown out of the seat; the occupant wearing only the shoulder belt will have obvious diving and gliding movement. Compared with the situation when three-point seat belt are used correctly, curly wearing will cause a significant increase in occupant injury criterion. Therefore, identifying different wearing patterns has a positive impact on the protection function of the seat belt.
3) Vehicle-mounted video monitoring system platform construction and test design. Vehicle-mounted video monitoring system platform is built, research is conducted on CCD sensor performance parameter, infrared light device and seat belt of special material. Vehicle field driving tests in different lighting environments are designed and conducted, occupant image information of different seat belt wearing patterns is collected. Image preprocessing technology appropriate for seat belt identification is studied in order to lay the foundation of building multiple characteristic parameter model for seat belt identification.
4) Real-time seat belt identification modeling. Aimed at the requirement of seat belt on-line test, space parameter characteristic after dimensionality reduction based on PCA (principal component analysis) is selected as input vector, BP neural network is chosen to be the classifier to meet the requirement of real-time identification, genetic algorithm (GA) is brought in to optimize the internal parameters to improve accuracy. At last, a real-time seat belt identification model based on GA-BP neural network is built. The real-time performance and accuracy of this model are verified through hardware-in-loop (HIL) and model-in-loop (MIL).
5) Curly wearing identification model with high accuracy is established. Statistical characteristic value of seat belt structural parameters is extracted as input vector, support vector machine (SVM) is chosen as the core model classifier, internal parameters are selected by cross validation method and optimized by particle swarm optimization (PSO), an identification model with high precision based on PSO-SVM method is built. The validation of the code in this model is verified through software-in-loop test, so that it can be applied to high accuracy offline testing.
6) Embedded vehicle-mounted seat belt identification system is designed and realized. The requirement of vehicle-mounted system on hardware and software is analyzed, high-speed data processing in DSP kernel, control and management fuction of ARM kernel are studied. ICETEK-DM642-B evaluation board is chosen as the hardware platform, and the seat belt identification system is realized based on embedded technology. System function overall design and function module software design are achieved, system program is optimized.
The innovations of this paper are as follows:
1) A method of seat belt identification based on machine vision is proposed for the fist time, embedded vehicle-mounted seat belt identification system platform is built.
2) The relationship between seat belt wearing patterns (non-standard wearing and curly wearing) and occupant injury is revealed.
3) The criterion to evaluate real-time performance and accuracy in seat belt identification is proposed.
4) The real-time seat belt identification model based on GA-BP neural network is built.
5) The curly wearing identification model with high accuracy based on PSO-SVM is built.
1)三点式安全带使用情况调查与分析。针对我国典型城市安全带的使用状况展开调查,结果显示,安全带使用过程中存在两类问题：不规范佩戴安全带和卷曲佩戴安全带。其中,导致安全带佩戴提示系统失效的不规范佩戴行为包括：单独使用安全带带扣、预佩戴和仅系肩带；卷曲佩戴包括：肩带卷曲、腰带卷曲和严重卷曲。
2)三点式安全带的不同佩戴方式对乘员损伤影响。采用MADYMO构建乘员约束系统模型,并验证模型的有效性。运用该模型进行三点式安全带在不同佩戴方式下的乘员损伤分析,结果表明：车辆碰撞时,预佩戴安全带的乘员将从座椅位置飞出；仅系肩带将产生明显的下潜、滑移运动。上述情况均导致乘员受到致命性损伤。相比正确使用三点式安全带,卷曲佩戴将导致乘员各项损伤指标明显上升。因此,对三点式安全带不同的佩戴方式进行识别,为充分发挥安全带应有的保护作用,具有积极意义。
3)车载视频监控平台搭建及安全带图像采集试验设计。搭建安全带图像采集试验平台,在CCD传感器性能参数、红外补光装置和特殊材料安全带等方面展开具体研究；设计并实施不同光线环境下的车辆行驶试验,采集获得安全带不同佩戴方式下的乘员图像信息；研究适用于安全带识别的图像预处理技术,为构建安全带识别的多特征参数模型奠定基础。
4)构建满足实时性要求的安全带识别模型。针对安全带在线检测的要求,采用主成分分析法降维后的安全带空间参数特征作为输入向量,选用BP神经网络作为分类器,构建基于BP神经网络的安全带识别模型,以满足实时性要求。引入遗传算法(GA)对其内部参数进行优化,构建基于GA-BP神经网络的安全带识别实时性模型,以满足准确性要求。通过硬件在环测试(HIL)和模型在环测试(MIL)验证了模型的实时性和准确性。
5)构建满足高精度要求的卷曲佩戴识别模型。提取安全带结构参数的统计特征值作为输入向量,选用支持向量机(SVM)作为模型核心分类器,以交叉验证方法对内部参数进行选择,采用粒子群算法(PSO)对其进行优化,构建基于PSO-SVM的高精度识别模型,并进行软件在环测试以验证代码的有效性,从而将其应用于高精度离线检测之中。
6)实现了嵌入式车载安全带监控系统的设计。从分析车载系统对软硬件的性能要求着手,探讨了DSP内核高速处理数据的特点以及ARM内核控制和管理的功能,选择ICETEK-DM642-B评估板作为硬件平台,实现了基于嵌入式技术的安全带识别系统的设计；完成系统功能的总体设计和功能模块的软件设计,并进行程序优化。
论文研究的创新点如下：
1)提出基于车载机器视觉识别安全带的方法,搭建嵌入式车载安全带识别系统平台；
2)揭示了三点式安全带的不同佩戴方式(不规范佩戴和卷曲佩戴)与乘员损伤之间的关系；
3)提出安全带识别的实时性和准确性评价方法；
4)构建基于GA-BP神经网络的安全带识别实时性模型；
5)构建基于PSO-SVM的卷曲佩戴识别高精度模型。
In order to increase the wearing rate of seat belt, influence of different3point seat belt wearing patterns on occupant injury mechanism is analyzed, due to the existing problems in seat belt utilization. An evaluation criteria of seat belt identification is proposed by identifying seat belt with vehicle-mounted machine vision. An identification model is built to meet the requirements of real time and high precision, embedded vehicle-mounted seat belt identification system is designed and realized. The main research content is as follows:
1) Investigation and analysis of3point seat belt utilization. Investigations were launched in typical cities in China. The results show that, problems existing in using seat belt mainly are:non-standard wearing and curly wearing. Non-standard wearing patterns that cause the failure of seat belt identification system includes:using only seat belt buckle, pre-wearing seat belt and using only shoulder belt. Curly wearing patterns includes:shoulder belt curling, waist belt curling and severely curling.
2) Influence of different3point seat belt wearing patterns on occupant injury mechanism:the occupant restraint system model is built based on MADYMO software, and its validity is verified. Simulation on different seat belt wearing patterns is conducted. The simulation results demonstrate that:in the event of vehicle crash, the occupant without seat belt will be thrown out of the seat; the occupant wearing only the shoulder belt will have obvious diving and gliding movement. Compared with the situation when three-point seat belt are used correctly, curly wearing will cause a significant increase in occupant injury criterion. Therefore, identifying different wearing patterns has a positive impact on the protection function of the seat belt.
3) Vehicle-mounted video monitoring system platform construction and test design. Vehicle-mounted video monitoring system platform is built, research is conducted on CCD sensor performance parameter, infrared light device and seat belt of special material. Vehicle field driving tests in different lighting environments are designed and conducted, occupant image information of different seat belt wearing patterns is collected. Image preprocessing technology appropriate for seat belt identification is studied in order to lay the foundation of building multiple characteristic parameter model for seat belt identification.
4) Real-time seat belt identification modeling. Aimed at the requirement of seat belt on-line test, space parameter characteristic after dimensionality reduction based on PCA (principal component analysis) is selected as input vector, BP neural network is chosen to be the classifier to meet the requirement of real-time identification, genetic algorithm (GA) is brought in to optimize the internal parameters to improve accuracy. At last, a real-time seat belt identification model based on GA-BP neural network is built. The real-time performance and accuracy of this model are verified through hardware-in-loop (HIL) and model-in-loop (MIL).
5) Curly wearing identification model with high accuracy is established. Statistical characteristic value of seat belt structural parameters is extracted as input vector, support vector machine (SVM) is chosen as the core model classifier, internal parameters are selected by cross validation method and optimized by particle swarm optimization (PSO), an identification model with high precision based on PSO-SVM method is built. The validation of the code in this model is verified through software-in-loop test, so that it can be applied to high accuracy offline testing.
6) Embedded vehicle-mounted seat belt identification system is designed and realized. The requirement of vehicle-mounted system on hardware and software is analyzed, high-speed data processing in DSP kernel, control and management fuction of ARM kernel are studied. ICETEK-DM642-B evaluation board is chosen as the hardware platform, and the seat belt identification system is realized based on embedded technology. System function overall design and function module software design are achieved, system program is optimized.
The innovations of this paper are as follows:
1) A method of seat belt identification based on machine vision is proposed for the fist time, embedded vehicle-mounted seat belt identification system platform is built.
2) The relationship between seat belt wearing patterns (non-standard wearing and curly wearing) and occupant injury is revealed.
3) The criterion to evaluate real-time performance and accuracy in seat belt identification is proposed.
4) The real-time seat belt identification model based on GA-BP neural network is built.
5) The curly wearing identification model with high accuracy based on PSO-SVM is built.
引文
[1]中华人民共和国道路交通事故统计年报[R].公安部交通管理局,2006.
[2]中华人民共和国道路交通事故统计年报[R].公安部交通管理局,2007.
[3]中华人民共和国道路交通事故统计年报[R].公安部交通管理局,2008.
[4]中华人民共和国道路交通事故统计年报[R].公安部交通管理局,2009.
[5]中华人民共和国道路交通事故统计年报[R].公安部交通管理局,2010.
[6]中华人民共和国道路交通事故统计年报[R].公安部交通管理局,2011.
[7]中华人民共和国道路交通事故统计年报[R].公安部交通管理局,2012.
[8]方根名.带有气囊的安全带[J].汽车与配件,2010(20)：40-41.
[9]Antosia RE, Partridge RA, Virk AS. Airbag Safety[J]. Ann Emerg Med,1995(25): 794-798.
[10]Loo GT, Siegel JH, Dischinger PC, et al. Airbag protection versus compartment intrusion effect determines the pattern of injuries in multiple trauma motor vehicle crashes[J]. J Trauma,1996(41):935.
[11]Fifth/Sixth Report to Congress:Effectiveness of Occupant Protection Systems and Their Use[R]. National Highway Traffic Safety Administration,2001.
[12]Peter C, James DW, Frederick PR. Estimating seat belt effectiveness using matched-pair cohort methods[J]. Accident Analysis and Prevention,2003(35):143-149.
[13]Occupant Restraint Use in 2010:Results From the National Occupant Protection Use Survey Controlled Intersection Study[R]. National Highway Traffic Safety Administration, 2011.
[14]Transport surveys of seat belt use in Canada 2004-2005[R], Road Safety and Motor Vehicle Regulation Directorate,2006.
[15]Fildes B, Fitzharris M, Vulcan P, etal. Benefits of retrofit seat belt reminder systems to Australian passenger vehicles[R]. Monash University Accident Research Center,2004.
[16]Boontob N. A study of seat belt usage and its impact its impact in Thailand. K long Luang, Pathumthan[R], Thailand:School of Civil Engineering,2005.
[17]Silveira A. Seat belt use in Argentina:a 10-year struggle[R]. Traffic In j Prey,2003.
[18]Bendak S. Seat belt utilization in Saudi Arabia and its impaction road accident in juriesfJ]. Accid Anal Prev,2005(37):367-371.
[19]Occupant Restraint Use in 2011:Results From the National Occupant Protection Use Survey Controlled Intersection Study[R]. National Highway Traffic Safety Administration, 2012.
[20]赵新才,蒋志全,汤建国等.重庆市机动车驾驶员和前排乘员交通伤与安全带使用情况分析[J].中华创伤杂志,2005(21)：4522-454.
[21]杨亚明,杨婕,武鸣等.宜兴市2009年机动车驾乘人员安全带佩戴情况调查[J].职业与健康,2010,26(19)：2227.
[22]Zhang W, Huang Y H, Roetting M, etal. Drivers'views and behaviors about safety in China What do they NOT know about driving[J]. Accid Anal Prev,2006(38):22-27.
[23]Passmore J, Ozanne-Smith J. Seat belt use amongst taxi drivers in Beijing, China[J]. Int J In j Control Safe Promote,2006(13):187-188.
[24]Media Release:Seat Belt Reminders Saving Lives[R]. Australasian New Car Assessment Program,2010.
[25]中国汽车技术研究中心C-NCAP管理规则[S].2009.
[26]安全带提醒装置国家标准[S].GB/T 24551-2009,2009.
[27]吴德旭.中国乘用车安全带提醒装置[D].武汉：武汉理工大学,2006.
[28]《机动车驾驶证申领与使用规定》(公安部令第123号)[EB/OL]http://www.mps.gov.cn/n16/n1282/n3493/n3823/n442207/3386943.html.2012.
[29]国务院安委办关于贯彻国发[2011]40号文件的通知[EB/OL]http://www.gov.cn/zwgk/2011-12/02/content_2009363.htm.2011.
[30]交通运输部公安部安全监管总局关于印发2013年“道路客运安全年”活动方案的通知[EB/OL]http://www.moc.gov.cn/zhuzhan/zhengwugonggao/jiaotongbu/daoluyunshu/201304t20130 4071391611.html.
[31]请珍视生命主动向安全带卡扣说不![EB/OL]http://news.bitauto.com/security/20120207/0605586464.html.2012.
[32]朱海涛,孙振东,白鹏等.汽车正面碰撞中乘员的胸部伤害分析[J].交通与安全,2009(198)：23-28.
[33]蹇华胜,于长青,沈康强.安全带致胸骨体骨折伴心外膜下心肌损伤[J].中国急救医学,2005,25(1)：60--63.
[34]王秋颖.汽车安全气囊和安全带用材料[J].世界汽车,1998(7)：21-22.
[35]王国和.产业用织物-汽车安全带的研究与开发[J].丝绸,1997(1)：36-40.
[36]郭雅琳.丙纶汽车安全带的研制[J].上海纺织科技,1997(4)：48-49.
[37]GB/T 14166-1993.汽车安全带性能要求和试验方法[S].北京：中国标准出版社,1993
[38]Okada, Shoji (Anjo, JP), Suzuki etal. Seat Belt Warning Device, United States, US6239695B1[P], May 29,2001.
[39]TGuido Becker, Thierry Mousel, Paul Schockml. TOR (Total Occupant Recognition) SYSTEM[C]. Proceedings of 17th International Technical Conference on the EnhanceSafety of Vehicles. CDROM, Amsterdam, Netherlands,2001.
[40]刘辉,赵建彪,李闯等.基于限制车速的安全带强制使用装置[J].电子设计工程,2011,19(1)：141-144.
[41]刘冲,江振伟,周大永等.一种带有安全带报警装置的座椅,中国,实用新型专利,CN201895647U[P],2011.07.13.
[42]代孟铎.一种汽车安全带监测报警装置,中国,实用新型专利,CN201501381UP],2010.06.09.
[43]T Kanade. Picture processing by computer complex and recognition of human face. Department of Information Science[R], Dept. of Information Science, Kyoto University, Kyoto, Japan,1978.
[44]Knipling, R.R., Wang, J.S.&Kanianthra, J.N. Current NHTSA drowsy driver R&D[C]. Proceedings of the Fifteenth International Technical Conference on the Enhanced Safety of Vehicles. Melbourne, Australia.1996,1.
[45]Q.Ji, X. Yang. Real-Time Eye, Gaze, and Face Pose Tracking for Monitoring Driver Vigilance[J]. Real-Time Imaging,2002(8):357-377.
[46]FaceLAB [EB/OL]. http://www.seeingmachines.com/facelab.htm
[47]S. Boveris. Driver fatigue monitoring technologies and future ideas[C]. Proc. AWAKE Road Safety Workshop,2004.
[48]郑培.机动车驾驶员驾驶疲劳测评方法研究[D].北京：中国农业大学,2001.
[49]李峰,曾超,徐向东.驾驶防瞌睡装置中人眼快速定位方法研究[J].光学仪器,2002,24(4)：70-72.
[50]王光娟.基于DSP的驾驶疲劳检测系统的研究与实现[D].镇江：江苏大学,2007.
[51]陈家瑞.汽车构造[M].北京：机械工业出版社,2005.
[52]张铁柱,张洪信.汽车安全、节能与环保[M].北京：国防工业出版社,2004.
[53]钟志华.汽车耐撞性分析的有限元法[J].汽车工程,1994,16(1)：1-6.
[54]裘新,黄世霖等.非线性有限元模拟计算技术在汽车被动安全性研究中的应用[J].汽车技术,1998,12(2)：15-19.
[55]贾宏波,黄金陵等.数值模拟技术在汽车碰撞分析中的应用[J].中国公路学报,1999,12(2)：100-104.
[56]雷正保,钟志华.汽车碰撞仿真研究的发展趋势[J].长沙交通学院学报,1999,15(1)：18-22.
[57]Eberhard Haug.汽车碰撞仿真与设计的最新进展和发展趋势[J].机械工程学报,1998,34(1)：93-99.
[58]谷安涛.虚拟试验场(VPG)技术-汽车CAE技术的最新进展[J].天津：汽车被动安全研讨会,2001.10.
[59]顾力强,林忠钦.国内外汽车碰撞计算机模拟研究的现状及趋势[J].汽车工程,1999,21(1)：1-9.
[60]Frontal Impact Modeling and Application. [EB/OL] http://www.tass-safe.com.
[61]中国汽车工业协会.GB14166《机动车成年乘员用安全带和约束系统》[S].2003.
[62]葛如海.汽车正面碰撞乘员约束系统匹配研究[D].镇江：江苏大学,2007.
[63]National Highway Traffic Safety Admin. D.571.208 FMVSS 208 [S]. US:2010.
[64]成莹.基于机器视觉的物体识别定位系统的研究[D].重庆：西南大学,2011.
[65]Rafael C, Gonzalez, Richard E.数字图像处理[M].北京：电子工业出版社,2007.
[66]高成Matlab图像处理与应用[M].北京：国防工业出版社,2007.
[67]朱秀昌,刘峰,胡栋.数字图像处理与图像通信[M].北京：北京邮电大学出版社,2002.
[68]Tong Sun, Neuvo Y. Detail-preserving median based filters in image processing[J]. Pattern Recongnition Letters,1994,15(4):341-347.
[69]赵志刚,万娇娜,管聪慧.基于小波变换与自适应阈值的图像去噪[J].中国图象图形学报,2007,12(6)：977-980.
[70]Brink A D. Thresholding of Digital Image Using Two-dimensional Entropics[J]. Pattern Recognition,1992,25(8):803-808.
[71]Ostu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on System, Man and Cybernetics,1979.
[72]张震,胡洪涛.基于VC++的迭代阈值分割算法在图像处理中的应用[J].矿山机械,2008(8)：41-43.
[73]姜百宁.机器学习中的特征选择算法研究[D].青岛：中国海洋大学,2009.
[74]刘晶郁,李晓霞.汽车安全与法规[M].北京：人民交通出版社,2005.
[75]舒华,姚国平.汽车新技术[M].北京：国防工业出版社,2012.
[76]赵佳.道路光照模式分类器设计[D].吉林：吉林大学,2007.
[77]李睿.基于神经网络的油库安全评价技术研究[D].西安：西安石油大学,2009.
[78]艾永冠.粒子群优化神经网络在股市预测中的建模与应用[D].合肥：合肥工业大学,2009.
[79]牛洪瑜.基于神经网络的船舶柴油发电机组的故障诊断[D].兰州：兰州理工大学,2007.
[80]Goldberg D.E. Genetic Algorithms in Search and Optimization and Machine Learning[M]. The United States of New Jersey:Addison Wesley Publishing Company,1989.
[81]祝诗平,王一鸣,张小超等.基于遗传算法的近红外光谱谱区选择方法[J].农业机械学报,2004,35(5)：152-156.
[82]孙志田,张建梅,闫常丽.基于遗传算法公交线路网优化模型仿真研究[J].计算机仿真,2011,28(11)：335-338.
[83]廖娟.基于遗传算法优化的正交小波盲均衡算法[D].合肥：安徽理工大学,2011.
[84]格罗斯曼,费里德著,张华平等译.信息检索：算法与启发式方法[M].北京：人民邮电出版社,2010.
[85]雷英杰,张善文,李续武等[M].西安：西安电子科技大学出版社,2005.
[86]王化楠.Hough变换在视觉检测系统中的应用研究[D].大连：大连理工大学,2006.
[87]魏旭.基于主成分分析的特征融合及其应用[D].成都：电子科技大学,2008.
[88]杨万扣,吉善兵,任明武等.基于增加的二维主成分分析的特征提取方法及其在人脸识别中的应用[J].中国图像图形学报,2009,14(2)：227-232.
[89]龚炯,余立建,魏文.基于PCA-SVM的交通事件检测研究[J].物流工程与管理,2010,32(3)：87-90.
[90]姜德美.基于BP神经网络的驾驶员疲劳状态研究[D].重庆：西南大学,2008.
[91]Li Y G, Pilidis P, GA-based design-point performance adaptation and its comparison with ICM-based approach[J]. Applied Energy,2010,87(1):340-348.
[92]Deep K, Dipti. A self-organizing migrating genetic algorithm for constrained optimization[J]. Applied Mathematics and Computation,2008(198):237-250.
[93]刘大维,将荣超,朱龙龙等.基于遗传算法的路面有理函数功率谱密度参数识别[J].农业机械学报,2012,28(8)：128-133.
[94]卢启衡,冯晓云,王青元.基于遗传算法的追踪列车节能优化[J].西南交通大学学报,2012,47(2)：265-270.
[95]Mylene C.A.F. Rezende, Caliane B. B. COSTA, Aline C. Costa, M.R. Wolf Maciel. Optimization of a large scale industrial reactor by genetic algorithms[J]. Chemical Engineering Science,2008(63):330-341.
[96]李汝宁,何勇灵.基于遗传算法的柴油机喷油系统模型参数辨识[J].北京航空航天大学学报,2012,38(4)：464-467.
[97]吴飞.机器视觉在农产品检测中的应用研究[D].重庆：重庆大学,2009.
[98]董俊.基于BP神经网络的图像复原算法研究[D].西安：西安科技大学,2009.
[99]陈圭光.精通MATLAB GUI设计[M].北京：电子工业出版社,2011.
[100]Vapnik V. Statistical Learning Theory [M].Wiley, New York, NY,1998.
[101]Boser B, Guyou I, Vapnik V. A training algorithm for optimal margin classifiers[J]. ACM press:In Proceeding of the Fifth Annual Workshop on Computational Learning Theory, 1992.
[102]Cortes C, Vapnik V. Support-Vector network [J].Machine Learning,1995(20):273-297.
[103]Hsu C W, Lin C J. A comparison of methods for multi-class support vector machines[J].IEEE Transactions on Neural Network,2002,13(2):415-425.
[104]谭孝贤.支持向量机在小波包去噪方法中的应用[D].上海：上海交通大学,2009.
[105]黄静华.支持向量机算法研究及在气象数据挖掘中的应用[D].北京：中国矿业大学,2011.
[106]胡满江,葛如海,苏清祖.基于GA-SVM的汽车追尾预测方法研究[J].汽车技术,2012(11)：24-26.
[107]张利.基于转向盘转角特性的驾驶疲劳检测方法研究[D]镇江：江苏大学,2012.
[108]冯建强,刘文波,于盛林.基于灰度积分投影的人眼定位[J].计算机仿真,2005,22(4)：75-77.
[109]李国正(译).支持向量机导论[M].北京：电子工业出版社,2004.
[110]汤宝平,刘文艺,蒋永华.基于交叉验证法优化参数的Morlet小波消噪方法[J].重庆大学学报,2010,33(1)：1-5.
[111]张玉洁,李志明,宋广宇等.基于鱼群算法的独立成分分析算法研究[J].计算机工程与应用,2013,49(13)：187-190.
[112]袁东辉.蚁群算法在飞行模拟器平台中若干应用问题的研究[D].长春：吉林大学,2011.
[113]张烈平,张云生,杨桂华.基于粒子群算法的流程工业生产调度研究[J].计算机工程与应用,2011,48(6)：225-229.
[114]Russell C. Eherhart, Yuhui Shi. Particle swarm optimization:developments, applications and resources[C].Proceedings of the IEEE Congress on Evolutionary Computation,2001.
[115]Eberhart R C, Shi Y. Guest editorial special issue on particle swarm optimization[J].Transactions on Evolutionary Computation,2004,8(3):201-203.
[116]杜玉平.关于粒子群算法改进的研究[D].西安：西北大学,2008.
[117]徐宇亮,孙际哲,陈西宏等.采用多目标粒子群算法的模拟电路故障诊断研究[J].西安交通大学学报,2012,46(6)：111-115.
[118]唐玉兰,徐明亮,梅娟等.粒子群算法在PID控制器参数整定中的研究与应用[J].计算机工程与应用,2012,48(34)：221-224.
[119]TMS320DM642中文手册[EB/OL] http://www.helloDSP.com.
[2]中华人民共和国道路交通事故统计年报[R].公安部交通管理局,2007.
[3]中华人民共和国道路交通事故统计年报[R].公安部交通管理局,2008.
[4]中华人民共和国道路交通事故统计年报[R].公安部交通管理局,2009.
[5]中华人民共和国道路交通事故统计年报[R].公安部交通管理局,2010.
[6]中华人民共和国道路交通事故统计年报[R].公安部交通管理局,2011.
[7]中华人民共和国道路交通事故统计年报[R].公安部交通管理局,2012.
[8]方根名.带有气囊的安全带[J].汽车与配件,2010(20)：40-41.
[9]Antosia RE, Partridge RA, Virk AS. Airbag Safety[J]. Ann Emerg Med,1995(25): 794-798.
[10]Loo GT, Siegel JH, Dischinger PC, et al. Airbag protection versus compartment intrusion effect determines the pattern of injuries in multiple trauma motor vehicle crashes[J]. J Trauma,1996(41):935.
[11]Fifth/Sixth Report to Congress:Effectiveness of Occupant Protection Systems and Their Use[R]. National Highway Traffic Safety Administration,2001.
[12]Peter C, James DW, Frederick PR. Estimating seat belt effectiveness using matched-pair cohort methods[J]. Accident Analysis and Prevention,2003(35):143-149.
[13]Occupant Restraint Use in 2010:Results From the National Occupant Protection Use Survey Controlled Intersection Study[R]. National Highway Traffic Safety Administration, 2011.
[14]Transport surveys of seat belt use in Canada 2004-2005[R], Road Safety and Motor Vehicle Regulation Directorate,2006.
[15]Fildes B, Fitzharris M, Vulcan P, etal. Benefits of retrofit seat belt reminder systems to Australian passenger vehicles[R]. Monash University Accident Research Center,2004.
[16]Boontob N. A study of seat belt usage and its impact its impact in Thailand. K long Luang, Pathumthan[R], Thailand:School of Civil Engineering,2005.
[17]Silveira A. Seat belt use in Argentina:a 10-year struggle[R]. Traffic In j Prey,2003.
[18]Bendak S. Seat belt utilization in Saudi Arabia and its impaction road accident in juriesfJ]. Accid Anal Prev,2005(37):367-371.
[19]Occupant Restraint Use in 2011:Results From the National Occupant Protection Use Survey Controlled Intersection Study[R]. National Highway Traffic Safety Administration, 2012.
[20]赵新才,蒋志全,汤建国等.重庆市机动车驾驶员和前排乘员交通伤与安全带使用情况分析[J].中华创伤杂志,2005(21)：4522-454.
[21]杨亚明,杨婕,武鸣等.宜兴市2009年机动车驾乘人员安全带佩戴情况调查[J].职业与健康,2010,26(19)：2227.
[22]Zhang W, Huang Y H, Roetting M, etal. Drivers'views and behaviors about safety in China What do they NOT know about driving[J]. Accid Anal Prev,2006(38):22-27.
[23]Passmore J, Ozanne-Smith J. Seat belt use amongst taxi drivers in Beijing, China[J]. Int J In j Control Safe Promote,2006(13):187-188.
[24]Media Release:Seat Belt Reminders Saving Lives[R]. Australasian New Car Assessment Program,2010.
[25]中国汽车技术研究中心C-NCAP管理规则[S].2009.
[26]安全带提醒装置国家标准[S].GB/T 24551-2009,2009.
[27]吴德旭.中国乘用车安全带提醒装置[D].武汉：武汉理工大学,2006.
[28]《机动车驾驶证申领与使用规定》(公安部令第123号)[EB/OL]http://www.mps.gov.cn/n16/n1282/n3493/n3823/n442207/3386943.html.2012.
[29]国务院安委办关于贯彻国发[2011]40号文件的通知[EB/OL]http://www.gov.cn/zwgk/2011-12/02/content_2009363.htm.2011.
[30]交通运输部公安部安全监管总局关于印发2013年“道路客运安全年”活动方案的通知[EB/OL]http://www.moc.gov.cn/zhuzhan/zhengwugonggao/jiaotongbu/daoluyunshu/201304t20130 4071391611.html.
[31]请珍视生命主动向安全带卡扣说不![EB/OL]http://news.bitauto.com/security/20120207/0605586464.html.2012.
[32]朱海涛,孙振东,白鹏等.汽车正面碰撞中乘员的胸部伤害分析[J].交通与安全,2009(198)：23-28.
[33]蹇华胜,于长青,沈康强.安全带致胸骨体骨折伴心外膜下心肌损伤[J].中国急救医学,2005,25(1)：60--63.
[34]王秋颖.汽车安全气囊和安全带用材料[J].世界汽车,1998(7)：21-22.
[35]王国和.产业用织物-汽车安全带的研究与开发[J].丝绸,1997(1)：36-40.
[36]郭雅琳.丙纶汽车安全带的研制[J].上海纺织科技,1997(4)：48-49.
[37]GB/T 14166-1993.汽车安全带性能要求和试验方法[S].北京：中国标准出版社,1993
[38]Okada, Shoji (Anjo, JP), Suzuki etal. Seat Belt Warning Device, United States, US6239695B1[P], May 29,2001.
[39]TGuido Becker, Thierry Mousel, Paul Schockml. TOR (Total Occupant Recognition) SYSTEM[C]. Proceedings of 17th International Technical Conference on the EnhanceSafety of Vehicles. CDROM, Amsterdam, Netherlands,2001.
[40]刘辉,赵建彪,李闯等.基于限制车速的安全带强制使用装置[J].电子设计工程,2011,19(1)：141-144.
[41]刘冲,江振伟,周大永等.一种带有安全带报警装置的座椅,中国,实用新型专利,CN201895647U[P],2011.07.13.
[42]代孟铎.一种汽车安全带监测报警装置,中国,实用新型专利,CN201501381UP],2010.06.09.
[43]T Kanade. Picture processing by computer complex and recognition of human face. Department of Information Science[R], Dept. of Information Science, Kyoto University, Kyoto, Japan,1978.
[44]Knipling, R.R., Wang, J.S.&Kanianthra, J.N. Current NHTSA drowsy driver R&D[C]. Proceedings of the Fifteenth International Technical Conference on the Enhanced Safety of Vehicles. Melbourne, Australia.1996,1.
[45]Q.Ji, X. Yang. Real-Time Eye, Gaze, and Face Pose Tracking for Monitoring Driver Vigilance[J]. Real-Time Imaging,2002(8):357-377.
[46]FaceLAB [EB/OL]. http://www.seeingmachines.com/facelab.htm
[47]S. Boveris. Driver fatigue monitoring technologies and future ideas[C]. Proc. AWAKE Road Safety Workshop,2004.
[48]郑培.机动车驾驶员驾驶疲劳测评方法研究[D].北京：中国农业大学,2001.
[49]李峰,曾超,徐向东.驾驶防瞌睡装置中人眼快速定位方法研究[J].光学仪器,2002,24(4)：70-72.
[50]王光娟.基于DSP的驾驶疲劳检测系统的研究与实现[D].镇江：江苏大学,2007.
[51]陈家瑞.汽车构造[M].北京：机械工业出版社,2005.
[52]张铁柱,张洪信.汽车安全、节能与环保[M].北京：国防工业出版社,2004.
[53]钟志华.汽车耐撞性分析的有限元法[J].汽车工程,1994,16(1)：1-6.
[54]裘新,黄世霖等.非线性有限元模拟计算技术在汽车被动安全性研究中的应用[J].汽车技术,1998,12(2)：15-19.
[55]贾宏波,黄金陵等.数值模拟技术在汽车碰撞分析中的应用[J].中国公路学报,1999,12(2)：100-104.
[56]雷正保,钟志华.汽车碰撞仿真研究的发展趋势[J].长沙交通学院学报,1999,15(1)：18-22.
[57]Eberhard Haug.汽车碰撞仿真与设计的最新进展和发展趋势[J].机械工程学报,1998,34(1)：93-99.
[58]谷安涛.虚拟试验场(VPG)技术-汽车CAE技术的最新进展[J].天津：汽车被动安全研讨会,2001.10.
[59]顾力强,林忠钦.国内外汽车碰撞计算机模拟研究的现状及趋势[J].汽车工程,1999,21(1)：1-9.
[60]Frontal Impact Modeling and Application. [EB/OL] http://www.tass-safe.com.
[61]中国汽车工业协会.GB14166《机动车成年乘员用安全带和约束系统》[S].2003.
[62]葛如海.汽车正面碰撞乘员约束系统匹配研究[D].镇江：江苏大学,2007.
[63]National Highway Traffic Safety Admin. D.571.208 FMVSS 208 [S]. US:2010.
[64]成莹.基于机器视觉的物体识别定位系统的研究[D].重庆：西南大学,2011.
[65]Rafael C, Gonzalez, Richard E.数字图像处理[M].北京：电子工业出版社,2007.
[66]高成Matlab图像处理与应用[M].北京：国防工业出版社,2007.
[67]朱秀昌,刘峰,胡栋.数字图像处理与图像通信[M].北京：北京邮电大学出版社,2002.
[68]Tong Sun, Neuvo Y. Detail-preserving median based filters in image processing[J]. Pattern Recongnition Letters,1994,15(4):341-347.
[69]赵志刚,万娇娜,管聪慧.基于小波变换与自适应阈值的图像去噪[J].中国图象图形学报,2007,12(6)：977-980.
[70]Brink A D. Thresholding of Digital Image Using Two-dimensional Entropics[J]. Pattern Recognition,1992,25(8):803-808.
[71]Ostu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on System, Man and Cybernetics,1979.
[72]张震,胡洪涛.基于VC++的迭代阈值分割算法在图像处理中的应用[J].矿山机械,2008(8)：41-43.
[73]姜百宁.机器学习中的特征选择算法研究[D].青岛：中国海洋大学,2009.
[74]刘晶郁,李晓霞.汽车安全与法规[M].北京：人民交通出版社,2005.
[75]舒华,姚国平.汽车新技术[M].北京：国防工业出版社,2012.
[76]赵佳.道路光照模式分类器设计[D].吉林：吉林大学,2007.
[77]李睿.基于神经网络的油库安全评价技术研究[D].西安：西安石油大学,2009.
[78]艾永冠.粒子群优化神经网络在股市预测中的建模与应用[D].合肥：合肥工业大学,2009.
[79]牛洪瑜.基于神经网络的船舶柴油发电机组的故障诊断[D].兰州：兰州理工大学,2007.
[80]Goldberg D.E. Genetic Algorithms in Search and Optimization and Machine Learning[M]. The United States of New Jersey:Addison Wesley Publishing Company,1989.
[81]祝诗平,王一鸣,张小超等.基于遗传算法的近红外光谱谱区选择方法[J].农业机械学报,2004,35(5)：152-156.
[82]孙志田,张建梅,闫常丽.基于遗传算法公交线路网优化模型仿真研究[J].计算机仿真,2011,28(11)：335-338.
[83]廖娟.基于遗传算法优化的正交小波盲均衡算法[D].合肥：安徽理工大学,2011.
[84]格罗斯曼,费里德著,张华平等译.信息检索：算法与启发式方法[M].北京：人民邮电出版社,2010.
[85]雷英杰,张善文,李续武等[M].西安：西安电子科技大学出版社,2005.
[86]王化楠.Hough变换在视觉检测系统中的应用研究[D].大连：大连理工大学,2006.
[87]魏旭.基于主成分分析的特征融合及其应用[D].成都：电子科技大学,2008.
[88]杨万扣,吉善兵,任明武等.基于增加的二维主成分分析的特征提取方法及其在人脸识别中的应用[J].中国图像图形学报,2009,14(2)：227-232.
[89]龚炯,余立建,魏文.基于PCA-SVM的交通事件检测研究[J].物流工程与管理,2010,32(3)：87-90.
[90]姜德美.基于BP神经网络的驾驶员疲劳状态研究[D].重庆：西南大学,2008.
[91]Li Y G, Pilidis P, GA-based design-point performance adaptation and its comparison with ICM-based approach[J]. Applied Energy,2010,87(1):340-348.
[92]Deep K, Dipti. A self-organizing migrating genetic algorithm for constrained optimization[J]. Applied Mathematics and Computation,2008(198):237-250.
[93]刘大维,将荣超,朱龙龙等.基于遗传算法的路面有理函数功率谱密度参数识别[J].农业机械学报,2012,28(8)：128-133.
[94]卢启衡,冯晓云,王青元.基于遗传算法的追踪列车节能优化[J].西南交通大学学报,2012,47(2)：265-270.
[95]Mylene C.A.F. Rezende, Caliane B. B. COSTA, Aline C. Costa, M.R. Wolf Maciel. Optimization of a large scale industrial reactor by genetic algorithms[J]. Chemical Engineering Science,2008(63):330-341.
[96]李汝宁,何勇灵.基于遗传算法的柴油机喷油系统模型参数辨识[J].北京航空航天大学学报,2012,38(4)：464-467.
[97]吴飞.机器视觉在农产品检测中的应用研究[D].重庆：重庆大学,2009.
[98]董俊.基于BP神经网络的图像复原算法研究[D].西安：西安科技大学,2009.
[99]陈圭光.精通MATLAB GUI设计[M].北京：电子工业出版社,2011.
[100]Vapnik V. Statistical Learning Theory [M].Wiley, New York, NY,1998.
[101]Boser B, Guyou I, Vapnik V. A training algorithm for optimal margin classifiers[J]. ACM press:In Proceeding of the Fifth Annual Workshop on Computational Learning Theory, 1992.
[102]Cortes C, Vapnik V. Support-Vector network [J].Machine Learning,1995(20):273-297.
[103]Hsu C W, Lin C J. A comparison of methods for multi-class support vector machines[J].IEEE Transactions on Neural Network,2002,13(2):415-425.
[104]谭孝贤.支持向量机在小波包去噪方法中的应用[D].上海：上海交通大学,2009.
[105]黄静华.支持向量机算法研究及在气象数据挖掘中的应用[D].北京：中国矿业大学,2011.
[106]胡满江,葛如海,苏清祖.基于GA-SVM的汽车追尾预测方法研究[J].汽车技术,2012(11)：24-26.
[107]张利.基于转向盘转角特性的驾驶疲劳检测方法研究[D]镇江：江苏大学,2012.
[108]冯建强,刘文波,于盛林.基于灰度积分投影的人眼定位[J].计算机仿真,2005,22(4)：75-77.
[109]李国正(译).支持向量机导论[M].北京：电子工业出版社,2004.
[110]汤宝平,刘文艺,蒋永华.基于交叉验证法优化参数的Morlet小波消噪方法[J].重庆大学学报,2010,33(1)：1-5.
[111]张玉洁,李志明,宋广宇等.基于鱼群算法的独立成分分析算法研究[J].计算机工程与应用,2013,49(13)：187-190.
[112]袁东辉.蚁群算法在飞行模拟器平台中若干应用问题的研究[D].长春：吉林大学,2011.
[113]张烈平,张云生,杨桂华.基于粒子群算法的流程工业生产调度研究[J].计算机工程与应用,2011,48(6)：225-229.
[114]Russell C. Eherhart, Yuhui Shi. Particle swarm optimization:developments, applications and resources[C].Proceedings of the IEEE Congress on Evolutionary Computation,2001.
[115]Eberhart R C, Shi Y. Guest editorial special issue on particle swarm optimization[J].Transactions on Evolutionary Computation,2004,8(3):201-203.
[116]杜玉平.关于粒子群算法改进的研究[D].西安：西北大学,2008.
[117]徐宇亮,孙际哲,陈西宏等.采用多目标粒子群算法的模拟电路故障诊断研究[J].西安交通大学学报,2012,46(6)：111-115.
[118]唐玉兰,徐明亮,梅娟等.粒子群算法在PID控制器参数整定中的研究与应用[J].计算机工程与应用,2012,48(34)：221-224.
[119]TMS320DM642中文手册[EB/OL] http://www.helloDSP.com.