高速公路网运行监测若干关键技术研究
|
摘要
近年来我国各省加快高速公路建设进程，高速公路网已基本形成，随着车流量日益增长，路网的交通拥堵问题也越来越突出。因此，作为路网管理数据支撑基本条件的高速公路网运行状态监测工作的重要性不言而喻。本文围绕高速公路网运行监测信息获取与加工，力争实现路网运行监测信息的“可视”与“可测”相结合这一主题，对基于高速公路监控视频的交通参数获取、车型分类与雾霾检测，以及高速公路网多源交通信息融合处理等关键问题展开研究，针对现有技术方法的不足，提出了若干具有创新性和实用性的解决方案和算法，并通过丰富的在实际路网运行中的实验数据加以验证，同时通过本人以攻博期间亲自主持设计实施的广东省高速公路网运行监测与服务信息平台建设的工程实践，实现了部分技术研究成果的转化，取得了良好成效，也为未来系统升级完善发展奠定了坚定基础和指明了方向。完成的主要科研工作和研究成果如下：
（1）针对固定单摄像机非标定的检测系统，综合研究了现有检测方法在交通场景中最常出现的影响检测鲁棒性的各种因素，分析原因并提出提高可靠性的约束条件。为消除主要因素的影响，提出一种适合在交通检测情形下应用的背景参考模型——基于区域的码本模型。并围绕此背景参考模型，提出一系列可裁剪、可扩展、全时段且适应复杂应用环境的交通流参数鲁棒性检测方法。通过对实际交通场景不同时段下的检测结果与传统检测方法进行对比，验证了检测方法的有效性和可靠性。
（2）不同于现有的利用大气学物理模型、基于能见度检测方法的思想，本文提出了一种基于高速公路监控视频内容的自动雾霾级别检测方法，无需对摄像机标定以计算能见度，而是利用雾天图像的视觉特性进行检测。本文利用边缘检测提取出粗略的疑似雾区，通过梯度计算和距离变换区分天空与真实雾霾区并分割出真实雾霾区，提取出真实雾霾区内的颜色直方图作为特征向量，同时为了增强特征的表达能力，对一系列视频帧序列的特征进行融合，最后，通过SVM支持向量机分类器进行雾霾级别分类。实验表明能够针对各种有雾和无雾天气，以及雾霾的级别进行检测，具有较高的正确率。
（3）提出了一种新颖的基于高速公路监控视频的车型分类方法。该方法通过提取车型图像的纹理特征，然后使用在线学习方式得到特征的编码字典，通过稀疏编码的稀疏性，挑选出最适合表达该车型的特征。稀疏编码能够更好地挑选适合的特征，与传统的量化相比能够防止过拟合的情况。同时为了排除车型图像提取中多车重叠等情况的干扰，使用低秩表示技术，通过对训练集中无干扰的图片进行矩阵分解，保留矩阵的低秩部分，去除稀疏（噪声）部分。得到表达矩阵与之前稀疏编码系数和字典进行连乘，从而得到车型图像中的主要成分，大大减轻了车型分类中引入的误差，得到优良的分类结果。最后使用BP神经网络结合改进的BOW分类结果、基于稀疏和低秩去噪的分类结果、深信网络分类结果，进行决策数据融合，得到最终结果。通过对实际数据的分析实验表明该方法进行得到了较高的分类准确度。
（4）提出了一种基于模糊聚类方法（FCM）的高速公路交通拥挤判别方法。研究了高速公路交通信息数据融合处理技术，结合广东省佛开高速真实高速公路历史数据对本章提出的交通拥挤判别方法进行验证，实验结果表明该方法能够很好的应用于高速公路监控系统中。以排队论为基础，对高速公路交通拥挤扩散特性进行了研究，包括分析了传统累计到达-离去模型对估计最大排队长队估计存在的缺陷，并建立了改进的最大排队长度估算模型及其求解流程。仿真实验结果表明模型能够很好的与实际交通流相匹配，在高速公路管理中具有较高的应用价值。
（5）提出了一种基于有限混合模型的高速公路行程时间估计模型。分析车牌识别数据或收费数据处理方法，分析不同车型的行程时间概率分布规律，提出高速公路路段行程时间概率分布是由若干车型的行程时间组成的混合概率分布模型，进而对行程时间进行估计。将高速公路路径行程时间划分为主干道和出入匝道的行程时间组成，提出一种对高速公路路径行程时间的估计方法。提出了一种基于卡尔曼滤波的高速公路网行程时间的融合估计与预测模型。在考虑高速公路网中有限的、低覆盖率的交通信息采集，整合、融合区域高速公路网监控系统中的基于现有交通信息资源的行程时间估计值，并充分利用海量的行程时间历史数据，构建基于卡尔曼滤波模型的行程时间估计模型，完成对高速公路网行程时间的融合估计与预测。实例分析表明该方法的可行性和有效性。
最后，在上述研究成果的背景基础上，本文最后以广东省高速公路网运行监测与服务信息共享平台实际工程为例，介绍了其系统的设计与实现。从平台的总体功能定位和系统功能结构设计开始，简要介绍了八个核心子系统——联网设施与设备管理子系统、交通流数据采集分析子系统、联网视频监控子系统、高清卡口车牌识别子系统、应急与救援子系统、交通地理信息子系统、出行信息服务子系统、基于移动互联网的“广东高速通”移动应用子系统的实现。并在已实现的系统功能基础上，结合未来智能交通系统技术的发展趋势，提出了系统未来技术升级研究发展的展望。
In recent years, freeways in our country have witnessed a rapid development and thenetwork of freeways in provinces has been formed gradually. At the same time, trafficcongestion in freeways has been increasingly serious with the development of society andeconomy. Therefore, it's very important to obtain traffic condition data for monitoring trafficconditions in freeway network.
In this paper, we focus on acquiring the traffic condition data and processingmulti-source data to achieve the goal of the combination of “visualization" and"measurability". Therefore, we study on the acquiring of traffic parameters based on freewaysurveillance video, models classification, detection of haze and multi-source trafficinformation fusion processing about freeways and other key issues. Concerning theshortcomings of the existing methods, it puts forward some innovative and practical solutionsand algorithms, which have been verified through abundant experimental data in actual roadnetwork operations. At the same time, through the engineering practice personally presidedover by the author himself about the construction of information platform about freewaysystem operation monitoring and service in Guangdong province, part of the implementationof technical research has been realized and good results has been achieved. A firm foundationhas been laid for the future development and pointing out the direction.
The main work and achievements are summarized as follows:
1. For the calibration of test system of single fixed cameras we comprehensively studiedthe existing test methods of testing the influence of the traffic most commonly occurring inthe scene of robustness of various factors, analyzed related reasons and improved constraintsabout reliability. To eliminate the influence of main factors, a kind of suitable application inthe situation of traffic detection background reference model based on the area code isestablished. And around the background reference model, a series of cutting, extensible, themethods of robustness test about traffic flow parameters adapting to the complex applicationenvironment as well as in full time were proposed. Through the comparison between actualtraffic scene detection results under different times and the traditional detection method, thevalidity and reliability of the test method have been verified.
2. On the basis of the analysis of the monitoring vehicle in the video image extractionmethod, three methods about the model classification have been proposed. The first one isbased on improved bag-of-word (BOW) models of the classification method, the second oneis based on sparse coding and low rank denoising algorithm, the third one is based on the edgeof the conviction in the network model. On this basis, the surveillance video is proposed inthis paper based on the freeway of multimodal fusion model classification method.Experimental results have verified the effectiveness and practicability of these models.
3. This paper proposes a new fog haze level detecting method based on freewaysurveillance video. This method is different from the existing atmospheric physics modelbased on the idea of visibility detecting method. By using of the characteristics of imagecontrast, innovative statistical histogram is proposed using HSV color space as a featurevector, using the SVM classifier to detect fog haze level.The method does not need tocompute the visibility of camera calibration, therefore it is not limited to the scene referenceand be compatible with the original freeway network video monitoring system, making fulluse of the traffic camera video images. The cost is low. Through the experiment, the methodfunctions well in all kinds of foggy and fogless weather, as well as different fog haze levels.
4. A novel freeway traffic congestion identification method based on the fuzzy clusteringmethod (FCM) has been put forward. Freeway traffic information data fusion processingtechnology is studied. With the real historical running data of Foshan-Kaiping Freeway inGuangdong Province,the traffic congestion identification method of this paper has beenvalidated. The experimental results show that this method can be applied to freewaymonitoring system very well. Based on queuing theory, the dispersion characteristics offreeway traffic are studied, including the analysis of the traditional cumulative reach-leavemodel to estimate the defects, and to estimate the maximum queue. And maximum queuelength estimation model and its solving process has been established and improved.Simulation experiment results show that the model can well match the actual traffic flow, andhas higher application value in the freeway management.
5. A novel travel time estimation model based on limited mixture distribution wasproposed. It’s usually difficult to obtain the accurate travel time in freeway network as trafficdetector is limited. To integrate or fuse the travel time in freeway network which is estimated from single-point detector (such as microwave traffic detector), point-to-point detector(license plate recognition/toll data) and the floating car data, a novel travel time fusingestimation or prediction algorithm based on Kalman filtering is proposed to obtain moreaccurate and complete travel time in freeway network.
On the basis of the above research results, in the final this paper takes the real project ofGuangdong provincial expressway network monitoring system platform as an example toanalyze the design, the overall orientation and functional structure of the system. The eightcore subsystems are introduced one by one: traffic flow detection subsystem, entrance ramplimiting subsystem, the main road control subsystem, exit ramp information subsystem, trafficillegal catch beat system, CCTV system and traffic information issuing system. This papercombines with the development trend of freeway monitoring technology and proposes thefuture technical development prospect of the system based on the realized system function.
（1）针对固定单摄像机非标定的检测系统，综合研究了现有检测方法在交通场景中最常出现的影响检测鲁棒性的各种因素，分析原因并提出提高可靠性的约束条件。为消除主要因素的影响，提出一种适合在交通检测情形下应用的背景参考模型——基于区域的码本模型。并围绕此背景参考模型，提出一系列可裁剪、可扩展、全时段且适应复杂应用环境的交通流参数鲁棒性检测方法。通过对实际交通场景不同时段下的检测结果与传统检测方法进行对比，验证了检测方法的有效性和可靠性。
（2）不同于现有的利用大气学物理模型、基于能见度检测方法的思想，本文提出了一种基于高速公路监控视频内容的自动雾霾级别检测方法，无需对摄像机标定以计算能见度，而是利用雾天图像的视觉特性进行检测。本文利用边缘检测提取出粗略的疑似雾区，通过梯度计算和距离变换区分天空与真实雾霾区并分割出真实雾霾区，提取出真实雾霾区内的颜色直方图作为特征向量，同时为了增强特征的表达能力，对一系列视频帧序列的特征进行融合，最后，通过SVM支持向量机分类器进行雾霾级别分类。实验表明能够针对各种有雾和无雾天气，以及雾霾的级别进行检测，具有较高的正确率。
（3）提出了一种新颖的基于高速公路监控视频的车型分类方法。该方法通过提取车型图像的纹理特征，然后使用在线学习方式得到特征的编码字典，通过稀疏编码的稀疏性，挑选出最适合表达该车型的特征。稀疏编码能够更好地挑选适合的特征，与传统的量化相比能够防止过拟合的情况。同时为了排除车型图像提取中多车重叠等情况的干扰，使用低秩表示技术，通过对训练集中无干扰的图片进行矩阵分解，保留矩阵的低秩部分，去除稀疏（噪声）部分。得到表达矩阵与之前稀疏编码系数和字典进行连乘，从而得到车型图像中的主要成分，大大减轻了车型分类中引入的误差，得到优良的分类结果。最后使用BP神经网络结合改进的BOW分类结果、基于稀疏和低秩去噪的分类结果、深信网络分类结果，进行决策数据融合，得到最终结果。通过对实际数据的分析实验表明该方法进行得到了较高的分类准确度。
（4）提出了一种基于模糊聚类方法（FCM）的高速公路交通拥挤判别方法。研究了高速公路交通信息数据融合处理技术，结合广东省佛开高速真实高速公路历史数据对本章提出的交通拥挤判别方法进行验证，实验结果表明该方法能够很好的应用于高速公路监控系统中。以排队论为基础，对高速公路交通拥挤扩散特性进行了研究，包括分析了传统累计到达-离去模型对估计最大排队长队估计存在的缺陷，并建立了改进的最大排队长度估算模型及其求解流程。仿真实验结果表明模型能够很好的与实际交通流相匹配，在高速公路管理中具有较高的应用价值。
（5）提出了一种基于有限混合模型的高速公路行程时间估计模型。分析车牌识别数据或收费数据处理方法，分析不同车型的行程时间概率分布规律，提出高速公路路段行程时间概率分布是由若干车型的行程时间组成的混合概率分布模型，进而对行程时间进行估计。将高速公路路径行程时间划分为主干道和出入匝道的行程时间组成，提出一种对高速公路路径行程时间的估计方法。提出了一种基于卡尔曼滤波的高速公路网行程时间的融合估计与预测模型。在考虑高速公路网中有限的、低覆盖率的交通信息采集，整合、融合区域高速公路网监控系统中的基于现有交通信息资源的行程时间估计值，并充分利用海量的行程时间历史数据，构建基于卡尔曼滤波模型的行程时间估计模型，完成对高速公路网行程时间的融合估计与预测。实例分析表明该方法的可行性和有效性。
最后，在上述研究成果的背景基础上，本文最后以广东省高速公路网运行监测与服务信息共享平台实际工程为例，介绍了其系统的设计与实现。从平台的总体功能定位和系统功能结构设计开始，简要介绍了八个核心子系统——联网设施与设备管理子系统、交通流数据采集分析子系统、联网视频监控子系统、高清卡口车牌识别子系统、应急与救援子系统、交通地理信息子系统、出行信息服务子系统、基于移动互联网的“广东高速通”移动应用子系统的实现。并在已实现的系统功能基础上，结合未来智能交通系统技术的发展趋势，提出了系统未来技术升级研究发展的展望。
In recent years, freeways in our country have witnessed a rapid development and thenetwork of freeways in provinces has been formed gradually. At the same time, trafficcongestion in freeways has been increasingly serious with the development of society andeconomy. Therefore, it's very important to obtain traffic condition data for monitoring trafficconditions in freeway network.
In this paper, we focus on acquiring the traffic condition data and processingmulti-source data to achieve the goal of the combination of “visualization" and"measurability". Therefore, we study on the acquiring of traffic parameters based on freewaysurveillance video, models classification, detection of haze and multi-source trafficinformation fusion processing about freeways and other key issues. Concerning theshortcomings of the existing methods, it puts forward some innovative and practical solutionsand algorithms, which have been verified through abundant experimental data in actual roadnetwork operations. At the same time, through the engineering practice personally presidedover by the author himself about the construction of information platform about freewaysystem operation monitoring and service in Guangdong province, part of the implementationof technical research has been realized and good results has been achieved. A firm foundationhas been laid for the future development and pointing out the direction.
The main work and achievements are summarized as follows:
1. For the calibration of test system of single fixed cameras we comprehensively studiedthe existing test methods of testing the influence of the traffic most commonly occurring inthe scene of robustness of various factors, analyzed related reasons and improved constraintsabout reliability. To eliminate the influence of main factors, a kind of suitable application inthe situation of traffic detection background reference model based on the area code isestablished. And around the background reference model, a series of cutting, extensible, themethods of robustness test about traffic flow parameters adapting to the complex applicationenvironment as well as in full time were proposed. Through the comparison between actualtraffic scene detection results under different times and the traditional detection method, thevalidity and reliability of the test method have been verified.
2. On the basis of the analysis of the monitoring vehicle in the video image extractionmethod, three methods about the model classification have been proposed. The first one isbased on improved bag-of-word (BOW) models of the classification method, the second oneis based on sparse coding and low rank denoising algorithm, the third one is based on the edgeof the conviction in the network model. On this basis, the surveillance video is proposed inthis paper based on the freeway of multimodal fusion model classification method.Experimental results have verified the effectiveness and practicability of these models.
3. This paper proposes a new fog haze level detecting method based on freewaysurveillance video. This method is different from the existing atmospheric physics modelbased on the idea of visibility detecting method. By using of the characteristics of imagecontrast, innovative statistical histogram is proposed using HSV color space as a featurevector, using the SVM classifier to detect fog haze level.The method does not need tocompute the visibility of camera calibration, therefore it is not limited to the scene referenceand be compatible with the original freeway network video monitoring system, making fulluse of the traffic camera video images. The cost is low. Through the experiment, the methodfunctions well in all kinds of foggy and fogless weather, as well as different fog haze levels.
4. A novel freeway traffic congestion identification method based on the fuzzy clusteringmethod (FCM) has been put forward. Freeway traffic information data fusion processingtechnology is studied. With the real historical running data of Foshan-Kaiping Freeway inGuangdong Province,the traffic congestion identification method of this paper has beenvalidated. The experimental results show that this method can be applied to freewaymonitoring system very well. Based on queuing theory, the dispersion characteristics offreeway traffic are studied, including the analysis of the traditional cumulative reach-leavemodel to estimate the defects, and to estimate the maximum queue. And maximum queuelength estimation model and its solving process has been established and improved.Simulation experiment results show that the model can well match the actual traffic flow, andhas higher application value in the freeway management.
5. A novel travel time estimation model based on limited mixture distribution wasproposed. It’s usually difficult to obtain the accurate travel time in freeway network as trafficdetector is limited. To integrate or fuse the travel time in freeway network which is estimated from single-point detector (such as microwave traffic detector), point-to-point detector(license plate recognition/toll data) and the floating car data, a novel travel time fusingestimation or prediction algorithm based on Kalman filtering is proposed to obtain moreaccurate and complete travel time in freeway network.
On the basis of the above research results, in the final this paper takes the real project ofGuangdong provincial expressway network monitoring system platform as an example toanalyze the design, the overall orientation and functional structure of the system. The eightcore subsystems are introduced one by one: traffic flow detection subsystem, entrance ramplimiting subsystem, the main road control subsystem, exit ramp information subsystem, trafficillegal catch beat system, CCTV system and traffic information issuing system. This papercombines with the development trend of freeway monitoring technology and proposes thefuture technical development prospect of the system based on the realized system function.
引文
[1] VIARANI E. Extraction of traffic information from images at DEIS[C]. Proc. Int. Conf.on Image Analysis and Processing，1999：1073-1076.
[2] Toyama K，Krumm J，Brumitt B，et al. Wallflower：Principles and practice of backgroundmaintenance[C]. Proceedings of the IEEE International Conference on Computer Vision，1999，1：255-261.
[3] Stauffer C，Grimson W E L. Adaptive background mixture models for real-timetracking[C]. Proceedings of the IEEE Computer Society Conference on Computer Visionand Pattern Recognition，1999，2：246-252.
[4] Elgammal A，Duraiswami R，Harwood D，et al. Background and foreground modelingusing nonparametric kernel density estimation for visual surveillance [J]. Proceedings ofthe IEEE，2002，90(7)：1151-1163.
[5]李宇成，李雷，王目树.多车道的车流量统计[J].自动化仪表，2010，31(10)：57-60.
[6] Elgammal A，Harwood D，Davis LS. Non-parametric model for background subtraction
[C]. European Conference on Computer Vision2000，2：751-67.
[7] Amer A，Dubois E，Mitiche A. A real-time system for high-level video representation：Application to video surveillance[C]. Proceedings of SPIE-The International Society forOptical Engineering，2003，5022I：530-541.
[8] Greiffenhagen M，Ramesh V，Comaniciu D， et al. Statistical modeling and performancecharacterization of a real-time dual camera surveillance system[C]. Proceedings of theIEEE Computer Society Conference on Computer Vision and Pattern Recognition，2000，2：335-342.
[9] Cristani M，Bicego M，Murino V. Integrated region-and pixel-based approach tobackground modeling[C]. Proceedings IEEE Workshop on Motion and Video Computing，2002：3-8.
[10] Kim K，Chalidabhongse T H，Harwood D，et al. Real-time foreground–backgroundsegmentation using codebook model [J]. Real-time imaging，2005，11(3)：172-185.
[11] Tseng B L，Lin C Y，Smith J R. Real-time video surveillance for traffic monitoringusing virtual line analysis[C]. Proceedings IEEE International Conference onMultimedia and Expo，2002，2：541-544.
[12]王勃，贾克斌.基于视频分析的车流量综合检测算法[J].交通信息与安全，2010，28(1)：20-25.
[13]王圣男，郁梅，蒋刚毅.智能交通系统中基于视频图像处理的车辆检测与跟踪方法综述[J].计算机应用研究，2005，22(9)：9-14.
[14]罗东华，余志，李熙莹，等.基于边缘的背景差法在车流量检测中的应用[J].光电工程，2007，34(11)：70-73.
[15]陈彦燕，王元庆.常用边缘检测算法的定量比较[J].计算机工程，2008，34(17)：202-204.
[16]陈功，周荷琴，严捷丰.采用UKF建模的实时背景提取和运动阴影检测[J].中国图象图形学报，2009，14(5)：931-937.
[17]王小鹏，郭莉琼.公路车流量视频检测方法[J].计算机应用，2012，32(6)：1585-1588.
[18]巨永锋，朱辉，潘勇.基于计算机视觉的车流量检测算法[J].长安大学学报(自然科学版)，2004，24(1)：92-95.
[19]朱扛，宣国荣，邦振东.基于视频动态投影的实时车辆流量检测系统[J].计算机工程，2001，27(11)：25-26，64.
[20]王佐成，贾佳，薛丽霞.基于虚拟窗口的自适应车流量检测应用研究[J].计算机工程与设计，2012，33(4)：1458-1462.
[21]檀甲甲，张建秋.实时采集道路车流量信息的视频新方法[J].仪器仪表学报，2007，29(1)：158-166.
[22] Sen-Ching S C，Kamath C. Robust techniques for background subtraction in urbantraffic video[C]. Proceedings of SPIE-The International Society for OpticalEngineering，2004，5308：881-892.
[23] Smids M. Background subtraction for urban traffic monitoring using webcams [D].Master Thesis，Universiteit van Amsterdam，FNWI，2006.
[24] Prati A，Mikic I，Grana C，et al. Shadow detection algorithms for traffic flow analysis：A comparative study[C]. IEEE Conference on Intelligent Transportation Systems，2001：340-345.
[25] Wang G，Xiao D，Gu J. Review on vehicle detection based on video for trafficsurveillance[C]. Proceedings of the IEEE International Conference on Automation andLogistics，2008：2961-2966..
[26] Bas E，Tekalp M，Salman F S. Automatic vehicle counting from video for traffic flowanalysis[C]. IEEE Intelligent Vehicles Symposium，2007：392-397..
[27] Jung Y K，Ho Y S. Traffic parameter extraction using video-based vehicle tracking[C].IEEE Conference on Intelligent Transportation Systems，1999：764-769.
[28] Michalopoulos P G. Vehicle detection video through image processing： The autoscopesystem [J]. IEEE Transactions on Vehicular Technology，1991，40(1)：21-29.
[29] Coifman B，Beymer D，McLauchlan P，et al. A real-time computer vision system forvehicle tracking and traffic surveillance [J]. Transportation Research Part C：EmergingTechnologies，1998，6(4)：271-288.
[30] Gupte S，Masoud O，Martin R F K，et al. Detection and classification of vehicles [J].IEEE Transactions on Intelligent Transportation Systems，2002，3(1)：37-47.
[31] Lowe D G. Distinctive image features from scale-invariant keypoints [J]. Internationaljournal of computer vision，2004，60(2)：91-110.
[32] Mairal J，Bach F，Ponce J，et al. Online dictionary learning for sparse coding[C]. ACMInternational Conference Proceeding Series，2009，382：689-696.
[33] Cortes C，Vapnik V. Support-vector networks [J]. Machine learning，1995，20(3)：273-297.
[34] Boser B E，Guyon I M，Vapnik V N. A training algorithm for optimal marginclassifiers[C]. Proceedings of the Fifth Annual ACM Workshop on ComputationalLearning Theory，1992：144-152.
[35] Dalal， Navneet， and Bill Triggs. Histograms of oriented gradients for humandetection[C]. Proceedings-2005IEEE Computer Society Conference on ComputerVision and Pattern Recognition，2005(1)：886-893.
[36]张春霞，姬楠楠，王冠伟.受限波尔兹曼机简介[OL].中国科技论文在线，2013: http：//www.paper.edu.cn/releasepaper/content/201301-528.
[37] Bengio Y. Learning deep architectures for AI [J]. Foundations and Trends in MachineLearning，2009，2(1)：1-127.
[38] Chen H，Murray A F. Continuous restricted Boltzmann machine with an implementabletraining algorithm[C]. IEE Proceedings：Vision，Image and Signal Processing，150(3)：153-158.
[39] Mairal J，Bach F，Ponce J，et al. Online learning for matrix factorization and sparsecoding [J]. The Journal of Machine Learning Research，2010，11：19-60.
[40] Hinton G E，Sejnowski T J. Learning and relearning in Boltzmann machines [J]. MITPress，Cambridge，Mass，1986，1：282-317.
[41] Freund Y，Haussler D. Unsupervised learning of distributions of binary vectors usingtwo layer networks [M]. University of California，Santa Cruz，1994.
[42] Hinton G E. Training products of experts by minimizing contrastive divergence [J].Neural computation，2002，14(8)：1771-1800.
[43] Hinton G E， Osindero S， Teh Y W. A fast learning algorithm for deep belief nets [J].Neural computation，2006，18(7)：1527-1554.
[44] G. Fung，N.Yung，G. Pang. Vehicle shape approximation from motion for visual trafficsurveillance [J]. In Proc. IEEE Conf. Intelligent Transport System，2008，18(2)：611-613.
[45] G. S. Sullivan，K. D. Baker，A. D. Worrall，et al. Model-based vehicle detection andclassification using orthographic approximations [J]. Image and Vision Computing，1997，15(8)：649-654.
[46] Lim T R，Guntoro A T. Car recognition using Gabor filter feature extraction[C].2002IEEE Asia-Pacific Conference on Circuits and Systems，2002，2：451-455.
[47] W.Sinatra，J.A.K. Suykens. Vehicle Recognition Based on Support Vector Machine[C].International Symposium on Distributed Computing and Applications to Business，Engineering and Science，Stockholm，2010：179-182.
[48]周爱军，杜宇人.基于视频图像Harris角点检测的车型识别[J].扬州大学学报(自然科学版)，2009，18(3)：13-15..
[49]马蓓，张乐.基于纹理特征的汽车车型识别[J].电子科技，2010，8(7)：31-33.
[50]黄灿.基于局部特征的车辆识别[J].中国图象图形学报，2010，20(1)：14-16.
[51]潘振赣，龚声蓉.浅谈数字图像处理技术的基本原理[J].电脑知识与技术，2010，11(6)：47-49.
[52]季晨光，张晓宇，白相宇.基于视频图像中的车型识别[J].辽宁工业大学学报(自然科学版)，2010，7(1)：13-15.
[53]马丽娜，曹新德.基于图像处理技术的车型自动识别系统设计[J].郑州轻工业学院学报(自然科学版)，2011，16(3)：10-13.
[54]阴国富. ITS中数字图像处理技术的研究[J].微计算机应用.2010，8(4)：24-26.
[55]吴志攀，赵跃龙.基于序列图像的车型识别研究[J].惠州学院学报(自然科学版)，2009，25(3)：27-29.
[56]李晋惠，赵建涛.一种图像处理的汽车类型识别算法[J].西安工业大学学报，2009，30(3)：11-13.
[57] Dessauer M P，Dua S. Optical flow object detection，motion estimation，and trackingon moving vehicles using wavelet decompositions [J]. The International Society forOptical Engineering，2010，6(12)：40-42.
[58]徐蕾，李一民，赵晓辉.基于特征点光流的车辆检测[J].重庆理工大学学报(自然科学)，2011，28(9)：13-15.
[59]崔星，闫清东.基于帧间差分方法的道路车辆检测系统[J].微计算机信息，2007，20(10)：10-13.
[60] Lipton A J，Fujiyoshi H，Patil R S. Moving target classification and tracking fromreal-time video[C]. IEEE Workshop Application of Computer Vision，1998：8-14.
[61] Wren C R，Azarbayejani A，Darrell T，et al. Pfinder：Real-time tracking of the humanbody [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence，1997，19(7)：780-785.
[62]张显亭，陈树越，陈颖鸣.一种改进的复杂场景运动目标检测算法[J].传感技术学报，2009，22(8)：1146-1149.
[63] Schechner Y Y，Narasimhan S G，Nayar S K. Instant dehazing of images usingpolarization[C]. Proceedings of the IEEE Computer Society Conference on ComputerVision and Pattern Recognition，2001，1：I325-I332.
[64] Shwartz S，Namer E，Schechner Y Y. Blind haze separation[C]. Proceedings of the IEEEComputer Society Conference on Computer Vision and Pattern Recognition，2006，2：1984-1991.
[65] Narasimhan S G，Nayar S K. Chromatic framework for vision in bad weather[C].Proceedings of the IEEE Computer Society Conference on Computer Vision and PatternRecognition，2000，1：598-605.
[66] Narasimhan S G，Nayar S K. Contrast restoration of weather degraded images[J]. IEEETransactions on Pattern Analysis and Machine Intelligence，2003，25(6)：713-724.
[67] Kopf J，Neubert B，Chen B，et al. Deep photo：Model-based photograph enhancementand viewing[C]. ACM Transactions on Graphics (TOG). ACM，2008，27(5)：116..
[68] Tan R T. Visibility in bad weather from a single image[C].26th IEEE Conference onComputer Vision and Pattern Recognition，2008：1-8.
[69] Fattal R. Single image dehazing[C]. ACM Transactions on Graphics (TOG). ACM，2008，27(3)：72.
[70] He K，Sun J，Tang X. Single image haze removal using dark channel prior [J]. IEEETransactions on Pattern Analysis and Machine Intelligence，2011，33(12)：2341-2353.
[71] KWON T M. Final Report on Signal and Image Processing for Road ConditionClassification [C]. Aerotech Telub and Dalarma University under the7SwedishNational Road Agency. Report，2002，6.
[72] Kwon T M. Atmospheric visibility measurements using video cameras：Relativevisibility[R]. University of Minnesota，Center for Transportation Studies，2004.
[73] Hallowell R G，Matthews M P，Pisano P A. Automated extraction of weather variablesfrom camera imagery[C]. Proceedings of the2005Mid-Continent TransportationResearch Symposium，Ames，IA.2005.
[74] Hautiere N，Labayrade R，Aubert D. Detection of visibility conditions through use ofonboard cameras[C]. IEEE Intelligent Vehicles Symposium，Proceedings.2005：193-198.
[75] Bronte S，Bergasa L M， Alcantarilla P F. Fog detection system based on computervision techniques[C]. IEEE Conference on Intelligent Transportation Systems，2009：30-35.
[76]周庆逵，陈钊正，陈启美.基于视频的路况能见度检测系统的设计与实现[J].电子测量技术，2009，32(6)：72-76.
[77]李佳，葛嘉琦，陈启美.路况视频能见度检测算法[J].计算机工程，2009，35(16)：175-177.
[78]李勃，董蓉，陈启美.无需人工标记的视频对比度道路能见度检测[J].计算机辅助设计与图形学学报，2009，21(11)：1575-1582.
[79]张潇，李勃，陈启美.基于亮度特征的PTZ视频能见度检测算法及实现[J].仪器仪表学报，2011，32(002)：381-387.
[80] Dumont E，Cavallo V. Extended photometric model of fog effects on road vision [J].Transportation Research Record：Journal of the Transportation Research Board，2004，1862(1)：77-81.
[81] Petty K F，Bickel P，Ostland M，et al. Accurate estimation of travel times fromsingle-loop detectors1[J]. Transportation Research Part A：Policy and Practice，1998，32(1)：1-17.
[82] Coifman B. Estimating travel times and vehicle trajectories on freeways using dual loopdetectors [J]. Transportation Research Part A：Policy and Practice，2002，36(4)：351-364.
[83] Nam D H，Drew D R. Traffic dynamics：Method for estimating freeway travel times inreal time from flow measurements [J]. Journal of Transportation Engineering，1996，122(3)：185-191.
[84] Coifman B，Cassidy M. Vehicle reidentification and travel time measurement oncongested freeways [J]. Transportation Research Part A：Policy and Practice，2002，36(10)：899-917.
[85] Coifman B，Ergueta E. Improved vehicle reidentification and travel time measurementon congested freeways [J]. Journal of transportation engineering，2003，129(5)：475-483.
[86] Tsuge M，Tokunaga M，Nakano K，et al. On Estimation of link travel time in floatingcar systems [J]. International Journal of Intelligent Transportation Systems Research，2010，8(3)：175-187..
[87]唐俊.基于浮动车数据的高速公路路段行程时间预测方法研究及系统实现[D].中山大学，2011.
[88] Bar-Gera H. Evaluation of a cellular phone-based system for measurements of trafficspeeds and travel times：A case study from Israel[J]. Transportation Research Part C：Emerging Technologies，2007，15(6)：380-391.
[89] Yim Y，Cayford R. Field operational test using anonymous cell phone tracking forgenerating traffic information[C]. Transportation Research Board85th Annual Meeting.2006(06-2511).
[90] Soriguera F，Rosas D，Robusté F. Travel time measurement in closed toll highways [J].Transportation Research Part B：Methodological，2010，44(10)：1242-1267.
[91]杨晓光，蔡润林，庄斌.基于车牌自动识别系统的城市道路行程时间预测算法[J].交通与计算机，2005，23(3)：29-32.
[92]叶长征，钟足峰.基于联网收费数据预测行程时间的实现[J].微计算机信息，2007，23(17)：44-46..
[93] Ohba Y，Ueno H，Kuwahara M. Travel time calculation method for expressway usingtoll collection system data[C]. IEEE Conference on Intelligent Transportation Systems，1999：471-475..
[94] Haghani A，Hamedi M，Sadabadi K F，et al. Data collection of freeway travel timeground truth with bluetooth sensors [J]. Transportation Research Record：Journal of theTransportation Research Board，2010，2160(1)：60-68.
[95]杨露菁，余华.多源信息融合理论与应用[M].北京邮电大学出版社，2006.
[96] Faouzi N E E，Leung H，Kurian A. Data fusion in intelligent transportation systems：Progress and challenges–A survey[J]. Information Fusion，2011，12(1)：4-10.
[97]邹亮，徐建闽，朱玲湘，等.基于浮动车移动检测与感应线圈融合技术的行程时间估计模型[J].公路交通科技，2007，24(6)：114-117.
[98]聂庆慧，夏井新，张韦华.基于多源ITS数据的行程时间预测体系框架及核心技术[J].东南大学学报：自然科学版，2011，41(1)：199-204.
[99]丛玉良，陈万忠，孙永强，等.基于联合卡尔曼滤波器的交通信息融合算法研究[J].公路交通科技，2010，27(7)：114-122.
[100]张存保，严新平.固定检测器和移动检测器的交通信息融合方法[J].交通与计算机，2007，25(3)：14-17.
[101] Kong Q J，Li Z，Chen Y，et al. An approach to urban traffic state estimation by fusingmultisource information [J]. Intelligent Transportation Systems，IEEE Transactions on，2009，10(3)：499-511.
[102] Choi K，Chung Y S. A data fusion algorithm for estimating link travel time [J]. ITSjournal，2002，7(3-4)：235-260.
[103] Park T，Lee S. A Bayesian approach for estimating link travel time on urban arterialroad network [M]. Computational Science and Its Applications–ICCSA2004.Springer Berlin Heidelberg，2004：1017-1025.
[104] Park S， Oh C， Ritchie S G. Heterogeneous Sensor Data Fusion for Freeway TrafficSurveillance and Performance[C]. Intelligent Transportation Society of America-12thWorld Congress on Intelligent Transport Systems2005.2009：2181-2195.
[105] Faouzi N E，Klein L A，De Mouzon O. Improving travel time estimates from inductiveloop and toll collection data with dempster-shafer data fusion[J]. TransportationResearch Record：Journal of the Transportation Research Board，2009，2129(1)：73-80..
[106]刘红红，杨兆升.基于数据融合技术的路段出行时间预测方法[J].交通运输工程学报，2008，8(6)：88-92.
[107] Kim S，Lim K， Lee Y. A Travel Time Fusion Algorithm Based on Point and IntervalDetector Data [J]. International Journal of Multimedia and Ubiquitous Engineering，2007，2(4)：67-84.
[108] Soriguera F，Robusté F. Highway travel time accurate measurement and short-termprediction using multiple data sources [J]. Transportmetrica，2011，7(1)：85-109.
[109] Lim S， Lee C. Data fusion algorithm improves travel time predictions [J]. IntelligentTransport Systems，IET，2011，5(4)：302-309.
[110] Hwang K P，Lee W H，Wu W B. Travel time prediction by weighted fusion of probingvehicles and vehicle detectors data sources[C].201212th International Conference onITS Telecommunications，2012：476-481.
[111]杨兆升，高学英.基于影响因素分类的路段行程时间融合研究[J].公路交通科技，2010，27(4)：116-127.
[112] Kwon J，Coifman B，Bickel P. Day-to-day travel-time trends and travel-time predictionfrom loop-detector data [J]. Transportation Research Record： Journal of theTransportation Research Board，2000，1717(1)：120-129.
[113] Rice J，Van Zwet E. A simple and effective method for predicting travel times onfreeways [J]. Intelligent Transportation Systems，IEEE Transactions on，2004，5(3)：200-207.
[114] Oda T. An algorithm for prediction of travel time using vehicle sensor data[C]. ThirdInternational Conference on Road Traffic Control，1990：40-44.
[115] Nanthawichit C，Nakatsuji T，Suzuki H. Application of probe-vehicle data forreal-time traffic-state estimation and short-term travel-time prediction on a freeway [J].Transportation Research Record：Journal of the Transportation Research Board，2003，1855(1)：49-59.
[116]朱中，杨兆升.基于卡尔曼滤波理论的实时行程时间预测模型[J].系统工程理论与实践，1999，19(9)：74-78.
[117] Park D，Rilett L R. Forecasting multiple-period freeway link travel times usingmodular neural networks [J]. Transportation Research Record： Journal of theTransportation Research Board，1998，1617(1)：163-170.
[118]杨兆升，朱中.基于BP神经网络的路径行程时间实时预测模型[J].系统工程理论与实践，1999，8：59-64.
[119]刘红红，杨兆升.基于数据融合技术的路段出行时间预测方法[J].交通运输工程学报，2008，8(6)：88-92.
[120]江龙晖.基于数据融合的城市快速路交通参数短时预测方法研究[D].长春：吉林大学交通学院，2004.
[121] Perrin J，Hansen B，Kump R. Incident detection algorithm evaluation[R]. University ofUtah，2001.
[122] Persaud B N，Hall F L，Hall L M. Congestion identification aspects of the McMasterincident detection algorithm [J]. Transportation Research Record，1990(1287)：167-175.
[123] Ritchie S G，Cheu R L. Simulation of freeway incident detection using artificial neuralnetworks [J]. Transportation Research Part C：Emerging Technologies，1993，1(3)：203-217.
[124] Yuan F， Cheu R L. Incident detection using support vector machines [J].Transportation Research Part C：Emerging Technologies，2003，11(3)：309-328.
[125]姜桂艳，温慧敏，杨兆升.高速公路交通事件自动检测系统与算法设计[J].交通运输工程学报，2001，1(1)：77-81.
[126] Dailey D J. A statistical algorithm for estimating speed from single loop volume andoccupancy measurements [J]. Transportation Research Part B：Methodological，1999，33(5)：313-322.
[127] Coifman B. Improved velocity estimation using single loop detectors [J].Transportation Research Part A：Policy and Practice，2001，35(10)：863-880.
[128] Coifman B，Dhoorjaty S， Lee Z H. Estimating median velocity instead of meanvelocity at single loop detectors [J]. Transportation Research Part C：EmergingTechnologies，2003，11(3)：211-222.
[129] Tang S，Wang F Y. A PCI-based evaluation method for level of services for trafficoperational systems [J]. IEEE Transactions on Intelligent Transportation Systems，2006，7(4)：494-499..
[130] Quiroga C A，Bullock D. Travel time studies with global positioning and geographicinformation systems：An integrated methodology [J]. Transportation Research Part C：Emerging Technologies，1998，6(1)：101-127.
[131] Hellinga B R，Fu L. Reducing bias in probe-based arterial link travel time estimates [J].Transportation Research Part C：Emerging Technologies，2002，10(4)：257-273.
[132] Li Y，McDonald M. Link travel time estimation using single GPS equipped probevehicle[C]. The IEEE5th International Conference on Intelligent TransportationSystems，2002：932-937.
[133] Cho Y，Rice J. Estimating velocity fields on a freeway from low-resolution videos [J].Intelligent Transportation Systems，IEEE Transactions on，2006，7(4)：463-469.
[134] Morris B T，Trivedi M M. Learning，modeling，and classification of vehicle trackpatterns from live video [J]. Intelligent Transportation Systems，IEEE Transactions on，2008，9(3)：425-437.
[135] Sohn K，Hwang K. Space-based passing time estimation on a freeway using cellphones as traffic probes [J]. IEEE Transactions on Intelligent Transportation Systems，2008，9(3)：559-568.
[136] Kong Q J，Li Z，Chen Y，et al. An approach to urban traffic state estimation by fusingmultisource information [J]. IEEE Transactions on Intelligent Transportation Systems，2009，10(3)：499-511.
[137]刘澜，戢晓峰.基于Vague集的道路交通状态决策信息融合[J].公路交通科技，2009，26(5)：112-115.
[138]陈红，章渺，王龙飞，等.高等级公路路段交通状态融合识别模型[J].重庆交通大学学报：自然科学版，2010，29(5)：772-775.
[139]徐涛，杨晓光，徐爱功，等.面向城市道路交通状态估计的数据融合研究[J].计算机工程与应用，47(7)：218-221.
[140] Golob T F，Recker W W，Leonard J D. An analysis of the severity and incidentduration of truck-involved freeway accidents [J]. Accident Analysis&Prevention，1987，19(5)：375-395.
[141] Garib A，Radwan A E，Al-Deek H. Estimating magnitude and duration of incidentdelays [J]. Journal of Transportation Engineering，1997，123(6)：459-466.
[142] Khattak A J，Schofer J L，Wang M. A simple time sequential procedure for predictingfreeway incident duration [J]. Journal of Intelligent Transportation Systems，1995，2(2)：113-138.
[143] Kim W，Natarajan S，Chang G L. Empirical analysis and modeling of freeway incidentduration[C].11th International IEEE Conference on Intelligent Transportation Systems，2008：453-457.
[144] Nam D，Mannering F. An exploratory hazard-based analysis of highway incidentduration [J]. Transportation Research Part A：Policy and Practice，2000，34(2)：85-102.
[145] Valenti G，Lelli M，Cucina D. A comparative study of models for the incident durationprediction [J]. European Transport Research Review，2010，2(2)：103-111.
[146] Wei C H，Lee Y. Sequential forecast of incident duration using Artificial NeuralNetwork models [J]. Accident Analysis&Prevention，2007，39(5)：944-954.
[147]刘伟铭，管丽萍，尹湘源.基于决策树的高速公路事件持续时间预测[J].中国公路学报，2005，18(1)：99-103.
[148]姬杨蓓蓓.交通事件持续时间预测方法研究[D].上海：同济大学，2008.
[149] Morales J M. Analytical procedures for estimating freeway traffic congestion [J].Public Roads，1986，50(2)：55-61.
[150] Newell G F. A simplified theory of kinematic waves in highway traffic，Part I：General theory [J]. Transportation Research Part B：Methodological，1993，27(4)：281-287.
[151] Newell G F. A simplified theory of kinematic waves in highway traffic， Part II：Queueing at freeway bottlenecks [J]. Transportation Research Part B：Methodological，1993，27(4)：289-303..
[152] Lawson T W，Lovell D J，Daganzo C F. Using input-output diagram to determinespatial and temporal extents of a queue upstream of a bottleneck [J]. TransportationResearch Record：Journal of the Transportation Research Board，1997，1572(1)：140-147.
[153] Sheu J B，Chou Y H，Chen A. Stochastic modeling and real-time prediction of incidenteffects on surface street traffic congestion [J]. Applied Mathematical Modelling，2004，28(5)：445-468.
[154]彭春露，杨晓光，张存宝.基于I/O模型对拥挤交通流状态变化的研究[J].交通与计算机，2004，22(6)：1-5.
[155]姜桂艳，代磊磊，白竹，等.城市主干路常发性拥挤扩散规律的模拟研究[J].交通与计算机，2006，24(1)：1-3.
[156] Stephanopoulos G，Michalopoulos P G，Stephanopoulos G. Modeling and analysis oftraffic queue dynamics at signalized intersections [J]. Transportation Research Part A：General，1979，13(5)：295-307.
[157]郭冠英.道路阻塞时的车辆排队长度计算法[J].中国公路学报，1998，11(3)：92-95.
[158]臧华，彭国雄.高速道路异常状况下车辆排队长度的预测模型[J].交通与计算机，2003，21(3)：10-12.
[159]王建军，周伟.线性模型下高速公路交通事故和干涉车流波模拟理论研究[J].西安公路交通大学学报，1998，18(3)：283-289.
[160]赵祥模，靳引利，张洋.高速公路监控系统理论及应用[M].电子工业出版社，2003.
[161]中华人民共和国交通部. GTJB01-2003.公路工程技术标准[S].北京：人民交通出版社，2004：44-45.
[162]高宏岩.融合移动信号流的高速公路交通拥挤预警与调控[D].山东科技大学，2011.
[163]王晓丹.基于模糊聚类及神经网络的纹理分割方法研究[D].西安：西北工业大学，2000.
[164]赵风波，孙敏.基于模糊聚类分析的交通状态识别方法[J].微型电脑应用，2006，22(2)：9-11.
[165] Rakha H, El-Shawarby I, Arafeh M, et al. Estimating path travel-time reliability[C].IEEE Conference on Intelligent Transportation Systems，2006：236-241.
[166] Kalman R E. A new approach to linear filtering and prediction problems [J]. Journal ofbasic Engineering，1960，82(1)：35-45.
[167]苏金明，阮沈勇，王永利编. MATLAB工程数学，北京：电子工业出版社，2005.
[2] Toyama K，Krumm J，Brumitt B，et al. Wallflower：Principles and practice of backgroundmaintenance[C]. Proceedings of the IEEE International Conference on Computer Vision，1999，1：255-261.
[3] Stauffer C，Grimson W E L. Adaptive background mixture models for real-timetracking[C]. Proceedings of the IEEE Computer Society Conference on Computer Visionand Pattern Recognition，1999，2：246-252.
[4] Elgammal A，Duraiswami R，Harwood D，et al. Background and foreground modelingusing nonparametric kernel density estimation for visual surveillance [J]. Proceedings ofthe IEEE，2002，90(7)：1151-1163.
[5]李宇成，李雷，王目树.多车道的车流量统计[J].自动化仪表，2010，31(10)：57-60.
[6] Elgammal A，Harwood D，Davis LS. Non-parametric model for background subtraction
[C]. European Conference on Computer Vision2000，2：751-67.
[7] Amer A，Dubois E，Mitiche A. A real-time system for high-level video representation：Application to video surveillance[C]. Proceedings of SPIE-The International Society forOptical Engineering，2003，5022I：530-541.
[8] Greiffenhagen M，Ramesh V，Comaniciu D， et al. Statistical modeling and performancecharacterization of a real-time dual camera surveillance system[C]. Proceedings of theIEEE Computer Society Conference on Computer Vision and Pattern Recognition，2000，2：335-342.
[9] Cristani M，Bicego M，Murino V. Integrated region-and pixel-based approach tobackground modeling[C]. Proceedings IEEE Workshop on Motion and Video Computing，2002：3-8.
[10] Kim K，Chalidabhongse T H，Harwood D，et al. Real-time foreground–backgroundsegmentation using codebook model [J]. Real-time imaging，2005，11(3)：172-185.
[11] Tseng B L，Lin C Y，Smith J R. Real-time video surveillance for traffic monitoringusing virtual line analysis[C]. Proceedings IEEE International Conference onMultimedia and Expo，2002，2：541-544.
[12]王勃，贾克斌.基于视频分析的车流量综合检测算法[J].交通信息与安全，2010，28(1)：20-25.
[13]王圣男，郁梅，蒋刚毅.智能交通系统中基于视频图像处理的车辆检测与跟踪方法综述[J].计算机应用研究，2005，22(9)：9-14.
[14]罗东华，余志，李熙莹，等.基于边缘的背景差法在车流量检测中的应用[J].光电工程，2007，34(11)：70-73.
[15]陈彦燕，王元庆.常用边缘检测算法的定量比较[J].计算机工程，2008，34(17)：202-204.
[16]陈功，周荷琴，严捷丰.采用UKF建模的实时背景提取和运动阴影检测[J].中国图象图形学报，2009，14(5)：931-937.
[17]王小鹏，郭莉琼.公路车流量视频检测方法[J].计算机应用，2012，32(6)：1585-1588.
[18]巨永锋，朱辉，潘勇.基于计算机视觉的车流量检测算法[J].长安大学学报(自然科学版)，2004，24(1)：92-95.
[19]朱扛，宣国荣，邦振东.基于视频动态投影的实时车辆流量检测系统[J].计算机工程，2001，27(11)：25-26，64.
[20]王佐成，贾佳，薛丽霞.基于虚拟窗口的自适应车流量检测应用研究[J].计算机工程与设计，2012，33(4)：1458-1462.
[21]檀甲甲，张建秋.实时采集道路车流量信息的视频新方法[J].仪器仪表学报，2007，29(1)：158-166.
[22] Sen-Ching S C，Kamath C. Robust techniques for background subtraction in urbantraffic video[C]. Proceedings of SPIE-The International Society for OpticalEngineering，2004，5308：881-892.
[23] Smids M. Background subtraction for urban traffic monitoring using webcams [D].Master Thesis，Universiteit van Amsterdam，FNWI，2006.
[24] Prati A，Mikic I，Grana C，et al. Shadow detection algorithms for traffic flow analysis：A comparative study[C]. IEEE Conference on Intelligent Transportation Systems，2001：340-345.
[25] Wang G，Xiao D，Gu J. Review on vehicle detection based on video for trafficsurveillance[C]. Proceedings of the IEEE International Conference on Automation andLogistics，2008：2961-2966..
[26] Bas E，Tekalp M，Salman F S. Automatic vehicle counting from video for traffic flowanalysis[C]. IEEE Intelligent Vehicles Symposium，2007：392-397..
[27] Jung Y K，Ho Y S. Traffic parameter extraction using video-based vehicle tracking[C].IEEE Conference on Intelligent Transportation Systems，1999：764-769.
[28] Michalopoulos P G. Vehicle detection video through image processing： The autoscopesystem [J]. IEEE Transactions on Vehicular Technology，1991，40(1)：21-29.
[29] Coifman B，Beymer D，McLauchlan P，et al. A real-time computer vision system forvehicle tracking and traffic surveillance [J]. Transportation Research Part C：EmergingTechnologies，1998，6(4)：271-288.
[30] Gupte S，Masoud O，Martin R F K，et al. Detection and classification of vehicles [J].IEEE Transactions on Intelligent Transportation Systems，2002，3(1)：37-47.
[31] Lowe D G. Distinctive image features from scale-invariant keypoints [J]. Internationaljournal of computer vision，2004，60(2)：91-110.
[32] Mairal J，Bach F，Ponce J，et al. Online dictionary learning for sparse coding[C]. ACMInternational Conference Proceeding Series，2009，382：689-696.
[33] Cortes C，Vapnik V. Support-vector networks [J]. Machine learning，1995，20(3)：273-297.
[34] Boser B E，Guyon I M，Vapnik V N. A training algorithm for optimal marginclassifiers[C]. Proceedings of the Fifth Annual ACM Workshop on ComputationalLearning Theory，1992：144-152.
[35] Dalal， Navneet， and Bill Triggs. Histograms of oriented gradients for humandetection[C]. Proceedings-2005IEEE Computer Society Conference on ComputerVision and Pattern Recognition，2005(1)：886-893.
[36]张春霞，姬楠楠，王冠伟.受限波尔兹曼机简介[OL].中国科技论文在线，2013: http：//www.paper.edu.cn/releasepaper/content/201301-528.
[37] Bengio Y. Learning deep architectures for AI [J]. Foundations and Trends in MachineLearning，2009，2(1)：1-127.
[38] Chen H，Murray A F. Continuous restricted Boltzmann machine with an implementabletraining algorithm[C]. IEE Proceedings：Vision，Image and Signal Processing，150(3)：153-158.
[39] Mairal J，Bach F，Ponce J，et al. Online learning for matrix factorization and sparsecoding [J]. The Journal of Machine Learning Research，2010，11：19-60.
[40] Hinton G E，Sejnowski T J. Learning and relearning in Boltzmann machines [J]. MITPress，Cambridge，Mass，1986，1：282-317.
[41] Freund Y，Haussler D. Unsupervised learning of distributions of binary vectors usingtwo layer networks [M]. University of California，Santa Cruz，1994.
[42] Hinton G E. Training products of experts by minimizing contrastive divergence [J].Neural computation，2002，14(8)：1771-1800.
[43] Hinton G E， Osindero S， Teh Y W. A fast learning algorithm for deep belief nets [J].Neural computation，2006，18(7)：1527-1554.
[44] G. Fung，N.Yung，G. Pang. Vehicle shape approximation from motion for visual trafficsurveillance [J]. In Proc. IEEE Conf. Intelligent Transport System，2008，18(2)：611-613.
[45] G. S. Sullivan，K. D. Baker，A. D. Worrall，et al. Model-based vehicle detection andclassification using orthographic approximations [J]. Image and Vision Computing，1997，15(8)：649-654.
[46] Lim T R，Guntoro A T. Car recognition using Gabor filter feature extraction[C].2002IEEE Asia-Pacific Conference on Circuits and Systems，2002，2：451-455.
[47] W.Sinatra，J.A.K. Suykens. Vehicle Recognition Based on Support Vector Machine[C].International Symposium on Distributed Computing and Applications to Business，Engineering and Science，Stockholm，2010：179-182.
[48]周爱军，杜宇人.基于视频图像Harris角点检测的车型识别[J].扬州大学学报(自然科学版)，2009，18(3)：13-15..
[49]马蓓，张乐.基于纹理特征的汽车车型识别[J].电子科技，2010，8(7)：31-33.
[50]黄灿.基于局部特征的车辆识别[J].中国图象图形学报，2010，20(1)：14-16.
[51]潘振赣，龚声蓉.浅谈数字图像处理技术的基本原理[J].电脑知识与技术，2010，11(6)：47-49.
[52]季晨光，张晓宇，白相宇.基于视频图像中的车型识别[J].辽宁工业大学学报(自然科学版)，2010，7(1)：13-15.
[53]马丽娜，曹新德.基于图像处理技术的车型自动识别系统设计[J].郑州轻工业学院学报(自然科学版)，2011，16(3)：10-13.
[54]阴国富. ITS中数字图像处理技术的研究[J].微计算机应用.2010，8(4)：24-26.
[55]吴志攀，赵跃龙.基于序列图像的车型识别研究[J].惠州学院学报(自然科学版)，2009，25(3)：27-29.
[56]李晋惠，赵建涛.一种图像处理的汽车类型识别算法[J].西安工业大学学报，2009，30(3)：11-13.
[57] Dessauer M P，Dua S. Optical flow object detection，motion estimation，and trackingon moving vehicles using wavelet decompositions [J]. The International Society forOptical Engineering，2010，6(12)：40-42.
[58]徐蕾，李一民，赵晓辉.基于特征点光流的车辆检测[J].重庆理工大学学报(自然科学)，2011，28(9)：13-15.
[59]崔星，闫清东.基于帧间差分方法的道路车辆检测系统[J].微计算机信息，2007，20(10)：10-13.
[60] Lipton A J，Fujiyoshi H，Patil R S. Moving target classification and tracking fromreal-time video[C]. IEEE Workshop Application of Computer Vision，1998：8-14.
[61] Wren C R，Azarbayejani A，Darrell T，et al. Pfinder：Real-time tracking of the humanbody [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence，1997，19(7)：780-785.
[62]张显亭，陈树越，陈颖鸣.一种改进的复杂场景运动目标检测算法[J].传感技术学报，2009，22(8)：1146-1149.
[63] Schechner Y Y，Narasimhan S G，Nayar S K. Instant dehazing of images usingpolarization[C]. Proceedings of the IEEE Computer Society Conference on ComputerVision and Pattern Recognition，2001，1：I325-I332.
[64] Shwartz S，Namer E，Schechner Y Y. Blind haze separation[C]. Proceedings of the IEEEComputer Society Conference on Computer Vision and Pattern Recognition，2006，2：1984-1991.
[65] Narasimhan S G，Nayar S K. Chromatic framework for vision in bad weather[C].Proceedings of the IEEE Computer Society Conference on Computer Vision and PatternRecognition，2000，1：598-605.
[66] Narasimhan S G，Nayar S K. Contrast restoration of weather degraded images[J]. IEEETransactions on Pattern Analysis and Machine Intelligence，2003，25(6)：713-724.
[67] Kopf J，Neubert B，Chen B，et al. Deep photo：Model-based photograph enhancementand viewing[C]. ACM Transactions on Graphics (TOG). ACM，2008，27(5)：116..
[68] Tan R T. Visibility in bad weather from a single image[C].26th IEEE Conference onComputer Vision and Pattern Recognition，2008：1-8.
[69] Fattal R. Single image dehazing[C]. ACM Transactions on Graphics (TOG). ACM，2008，27(3)：72.
[70] He K，Sun J，Tang X. Single image haze removal using dark channel prior [J]. IEEETransactions on Pattern Analysis and Machine Intelligence，2011，33(12)：2341-2353.
[71] KWON T M. Final Report on Signal and Image Processing for Road ConditionClassification [C]. Aerotech Telub and Dalarma University under the7SwedishNational Road Agency. Report，2002，6.
[72] Kwon T M. Atmospheric visibility measurements using video cameras：Relativevisibility[R]. University of Minnesota，Center for Transportation Studies，2004.
[73] Hallowell R G，Matthews M P，Pisano P A. Automated extraction of weather variablesfrom camera imagery[C]. Proceedings of the2005Mid-Continent TransportationResearch Symposium，Ames，IA.2005.
[74] Hautiere N，Labayrade R，Aubert D. Detection of visibility conditions through use ofonboard cameras[C]. IEEE Intelligent Vehicles Symposium，Proceedings.2005：193-198.
[75] Bronte S，Bergasa L M， Alcantarilla P F. Fog detection system based on computervision techniques[C]. IEEE Conference on Intelligent Transportation Systems，2009：30-35.
[76]周庆逵，陈钊正，陈启美.基于视频的路况能见度检测系统的设计与实现[J].电子测量技术，2009，32(6)：72-76.
[77]李佳，葛嘉琦，陈启美.路况视频能见度检测算法[J].计算机工程，2009，35(16)：175-177.
[78]李勃，董蓉，陈启美.无需人工标记的视频对比度道路能见度检测[J].计算机辅助设计与图形学学报，2009，21(11)：1575-1582.
[79]张潇，李勃，陈启美.基于亮度特征的PTZ视频能见度检测算法及实现[J].仪器仪表学报，2011，32(002)：381-387.
[80] Dumont E，Cavallo V. Extended photometric model of fog effects on road vision [J].Transportation Research Record：Journal of the Transportation Research Board，2004，1862(1)：77-81.
[81] Petty K F，Bickel P，Ostland M，et al. Accurate estimation of travel times fromsingle-loop detectors1[J]. Transportation Research Part A：Policy and Practice，1998，32(1)：1-17.
[82] Coifman B. Estimating travel times and vehicle trajectories on freeways using dual loopdetectors [J]. Transportation Research Part A：Policy and Practice，2002，36(4)：351-364.
[83] Nam D H，Drew D R. Traffic dynamics：Method for estimating freeway travel times inreal time from flow measurements [J]. Journal of Transportation Engineering，1996，122(3)：185-191.
[84] Coifman B，Cassidy M. Vehicle reidentification and travel time measurement oncongested freeways [J]. Transportation Research Part A：Policy and Practice，2002，36(10)：899-917.
[85] Coifman B，Ergueta E. Improved vehicle reidentification and travel time measurementon congested freeways [J]. Journal of transportation engineering，2003，129(5)：475-483.
[86] Tsuge M，Tokunaga M，Nakano K，et al. On Estimation of link travel time in floatingcar systems [J]. International Journal of Intelligent Transportation Systems Research，2010，8(3)：175-187..
[87]唐俊.基于浮动车数据的高速公路路段行程时间预测方法研究及系统实现[D].中山大学，2011.
[88] Bar-Gera H. Evaluation of a cellular phone-based system for measurements of trafficspeeds and travel times：A case study from Israel[J]. Transportation Research Part C：Emerging Technologies，2007，15(6)：380-391.
[89] Yim Y，Cayford R. Field operational test using anonymous cell phone tracking forgenerating traffic information[C]. Transportation Research Board85th Annual Meeting.2006(06-2511).
[90] Soriguera F，Rosas D，Robusté F. Travel time measurement in closed toll highways [J].Transportation Research Part B：Methodological，2010，44(10)：1242-1267.
[91]杨晓光，蔡润林，庄斌.基于车牌自动识别系统的城市道路行程时间预测算法[J].交通与计算机，2005，23(3)：29-32.
[92]叶长征，钟足峰.基于联网收费数据预测行程时间的实现[J].微计算机信息，2007，23(17)：44-46..
[93] Ohba Y，Ueno H，Kuwahara M. Travel time calculation method for expressway usingtoll collection system data[C]. IEEE Conference on Intelligent Transportation Systems，1999：471-475..
[94] Haghani A，Hamedi M，Sadabadi K F，et al. Data collection of freeway travel timeground truth with bluetooth sensors [J]. Transportation Research Record：Journal of theTransportation Research Board，2010，2160(1)：60-68.
[95]杨露菁，余华.多源信息融合理论与应用[M].北京邮电大学出版社，2006.
[96] Faouzi N E E，Leung H，Kurian A. Data fusion in intelligent transportation systems：Progress and challenges–A survey[J]. Information Fusion，2011，12(1)：4-10.
[97]邹亮，徐建闽，朱玲湘，等.基于浮动车移动检测与感应线圈融合技术的行程时间估计模型[J].公路交通科技，2007，24(6)：114-117.
[98]聂庆慧，夏井新，张韦华.基于多源ITS数据的行程时间预测体系框架及核心技术[J].东南大学学报：自然科学版，2011，41(1)：199-204.
[99]丛玉良，陈万忠，孙永强，等.基于联合卡尔曼滤波器的交通信息融合算法研究[J].公路交通科技，2010，27(7)：114-122.
[100]张存保，严新平.固定检测器和移动检测器的交通信息融合方法[J].交通与计算机，2007，25(3)：14-17.
[101] Kong Q J，Li Z，Chen Y，et al. An approach to urban traffic state estimation by fusingmultisource information [J]. Intelligent Transportation Systems，IEEE Transactions on，2009，10(3)：499-511.
[102] Choi K，Chung Y S. A data fusion algorithm for estimating link travel time [J]. ITSjournal，2002，7(3-4)：235-260.
[103] Park T，Lee S. A Bayesian approach for estimating link travel time on urban arterialroad network [M]. Computational Science and Its Applications–ICCSA2004.Springer Berlin Heidelberg，2004：1017-1025.
[104] Park S， Oh C， Ritchie S G. Heterogeneous Sensor Data Fusion for Freeway TrafficSurveillance and Performance[C]. Intelligent Transportation Society of America-12thWorld Congress on Intelligent Transport Systems2005.2009：2181-2195.
[105] Faouzi N E，Klein L A，De Mouzon O. Improving travel time estimates from inductiveloop and toll collection data with dempster-shafer data fusion[J]. TransportationResearch Record：Journal of the Transportation Research Board，2009，2129(1)：73-80..
[106]刘红红，杨兆升.基于数据融合技术的路段出行时间预测方法[J].交通运输工程学报，2008，8(6)：88-92.
[107] Kim S，Lim K， Lee Y. A Travel Time Fusion Algorithm Based on Point and IntervalDetector Data [J]. International Journal of Multimedia and Ubiquitous Engineering，2007，2(4)：67-84.
[108] Soriguera F，Robusté F. Highway travel time accurate measurement and short-termprediction using multiple data sources [J]. Transportmetrica，2011，7(1)：85-109.
[109] Lim S， Lee C. Data fusion algorithm improves travel time predictions [J]. IntelligentTransport Systems，IET，2011，5(4)：302-309.
[110] Hwang K P，Lee W H，Wu W B. Travel time prediction by weighted fusion of probingvehicles and vehicle detectors data sources[C].201212th International Conference onITS Telecommunications，2012：476-481.
[111]杨兆升，高学英.基于影响因素分类的路段行程时间融合研究[J].公路交通科技，2010，27(4)：116-127.
[112] Kwon J，Coifman B，Bickel P. Day-to-day travel-time trends and travel-time predictionfrom loop-detector data [J]. Transportation Research Record： Journal of theTransportation Research Board，2000，1717(1)：120-129.
[113] Rice J，Van Zwet E. A simple and effective method for predicting travel times onfreeways [J]. Intelligent Transportation Systems，IEEE Transactions on，2004，5(3)：200-207.
[114] Oda T. An algorithm for prediction of travel time using vehicle sensor data[C]. ThirdInternational Conference on Road Traffic Control，1990：40-44.
[115] Nanthawichit C，Nakatsuji T，Suzuki H. Application of probe-vehicle data forreal-time traffic-state estimation and short-term travel-time prediction on a freeway [J].Transportation Research Record：Journal of the Transportation Research Board，2003，1855(1)：49-59.
[116]朱中，杨兆升.基于卡尔曼滤波理论的实时行程时间预测模型[J].系统工程理论与实践，1999，19(9)：74-78.
[117] Park D，Rilett L R. Forecasting multiple-period freeway link travel times usingmodular neural networks [J]. Transportation Research Record： Journal of theTransportation Research Board，1998，1617(1)：163-170.
[118]杨兆升，朱中.基于BP神经网络的路径行程时间实时预测模型[J].系统工程理论与实践，1999，8：59-64.
[119]刘红红，杨兆升.基于数据融合技术的路段出行时间预测方法[J].交通运输工程学报，2008，8(6)：88-92.
[120]江龙晖.基于数据融合的城市快速路交通参数短时预测方法研究[D].长春：吉林大学交通学院，2004.
[121] Perrin J，Hansen B，Kump R. Incident detection algorithm evaluation[R]. University ofUtah，2001.
[122] Persaud B N，Hall F L，Hall L M. Congestion identification aspects of the McMasterincident detection algorithm [J]. Transportation Research Record，1990(1287)：167-175.
[123] Ritchie S G，Cheu R L. Simulation of freeway incident detection using artificial neuralnetworks [J]. Transportation Research Part C：Emerging Technologies，1993，1(3)：203-217.
[124] Yuan F， Cheu R L. Incident detection using support vector machines [J].Transportation Research Part C：Emerging Technologies，2003，11(3)：309-328.
[125]姜桂艳，温慧敏，杨兆升.高速公路交通事件自动检测系统与算法设计[J].交通运输工程学报，2001，1(1)：77-81.
[126] Dailey D J. A statistical algorithm for estimating speed from single loop volume andoccupancy measurements [J]. Transportation Research Part B：Methodological，1999，33(5)：313-322.
[127] Coifman B. Improved velocity estimation using single loop detectors [J].Transportation Research Part A：Policy and Practice，2001，35(10)：863-880.
[128] Coifman B，Dhoorjaty S， Lee Z H. Estimating median velocity instead of meanvelocity at single loop detectors [J]. Transportation Research Part C：EmergingTechnologies，2003，11(3)：211-222.
[129] Tang S，Wang F Y. A PCI-based evaluation method for level of services for trafficoperational systems [J]. IEEE Transactions on Intelligent Transportation Systems，2006，7(4)：494-499..
[130] Quiroga C A，Bullock D. Travel time studies with global positioning and geographicinformation systems：An integrated methodology [J]. Transportation Research Part C：Emerging Technologies，1998，6(1)：101-127.
[131] Hellinga B R，Fu L. Reducing bias in probe-based arterial link travel time estimates [J].Transportation Research Part C：Emerging Technologies，2002，10(4)：257-273.
[132] Li Y，McDonald M. Link travel time estimation using single GPS equipped probevehicle[C]. The IEEE5th International Conference on Intelligent TransportationSystems，2002：932-937.
[133] Cho Y，Rice J. Estimating velocity fields on a freeway from low-resolution videos [J].Intelligent Transportation Systems，IEEE Transactions on，2006，7(4)：463-469.
[134] Morris B T，Trivedi M M. Learning，modeling，and classification of vehicle trackpatterns from live video [J]. Intelligent Transportation Systems，IEEE Transactions on，2008，9(3)：425-437.
[135] Sohn K，Hwang K. Space-based passing time estimation on a freeway using cellphones as traffic probes [J]. IEEE Transactions on Intelligent Transportation Systems，2008，9(3)：559-568.
[136] Kong Q J，Li Z，Chen Y，et al. An approach to urban traffic state estimation by fusingmultisource information [J]. IEEE Transactions on Intelligent Transportation Systems，2009，10(3)：499-511.
[137]刘澜，戢晓峰.基于Vague集的道路交通状态决策信息融合[J].公路交通科技，2009，26(5)：112-115.
[138]陈红，章渺，王龙飞，等.高等级公路路段交通状态融合识别模型[J].重庆交通大学学报：自然科学版，2010，29(5)：772-775.
[139]徐涛，杨晓光，徐爱功，等.面向城市道路交通状态估计的数据融合研究[J].计算机工程与应用，47(7)：218-221.
[140] Golob T F，Recker W W，Leonard J D. An analysis of the severity and incidentduration of truck-involved freeway accidents [J]. Accident Analysis&Prevention，1987，19(5)：375-395.
[141] Garib A，Radwan A E，Al-Deek H. Estimating magnitude and duration of incidentdelays [J]. Journal of Transportation Engineering，1997，123(6)：459-466.
[142] Khattak A J，Schofer J L，Wang M. A simple time sequential procedure for predictingfreeway incident duration [J]. Journal of Intelligent Transportation Systems，1995，2(2)：113-138.
[143] Kim W，Natarajan S，Chang G L. Empirical analysis and modeling of freeway incidentduration[C].11th International IEEE Conference on Intelligent Transportation Systems，2008：453-457.
[144] Nam D，Mannering F. An exploratory hazard-based analysis of highway incidentduration [J]. Transportation Research Part A：Policy and Practice，2000，34(2)：85-102.
[145] Valenti G，Lelli M，Cucina D. A comparative study of models for the incident durationprediction [J]. European Transport Research Review，2010，2(2)：103-111.
[146] Wei C H，Lee Y. Sequential forecast of incident duration using Artificial NeuralNetwork models [J]. Accident Analysis&Prevention，2007，39(5)：944-954.
[147]刘伟铭，管丽萍，尹湘源.基于决策树的高速公路事件持续时间预测[J].中国公路学报，2005，18(1)：99-103.
[148]姬杨蓓蓓.交通事件持续时间预测方法研究[D].上海：同济大学，2008.
[149] Morales J M. Analytical procedures for estimating freeway traffic congestion [J].Public Roads，1986，50(2)：55-61.
[150] Newell G F. A simplified theory of kinematic waves in highway traffic，Part I：General theory [J]. Transportation Research Part B：Methodological，1993，27(4)：281-287.
[151] Newell G F. A simplified theory of kinematic waves in highway traffic， Part II：Queueing at freeway bottlenecks [J]. Transportation Research Part B：Methodological，1993，27(4)：289-303..
[152] Lawson T W，Lovell D J，Daganzo C F. Using input-output diagram to determinespatial and temporal extents of a queue upstream of a bottleneck [J]. TransportationResearch Record：Journal of the Transportation Research Board，1997，1572(1)：140-147.
[153] Sheu J B，Chou Y H，Chen A. Stochastic modeling and real-time prediction of incidenteffects on surface street traffic congestion [J]. Applied Mathematical Modelling，2004，28(5)：445-468.
[154]彭春露，杨晓光，张存宝.基于I/O模型对拥挤交通流状态变化的研究[J].交通与计算机，2004，22(6)：1-5.
[155]姜桂艳，代磊磊，白竹，等.城市主干路常发性拥挤扩散规律的模拟研究[J].交通与计算机，2006，24(1)：1-3.
[156] Stephanopoulos G，Michalopoulos P G，Stephanopoulos G. Modeling and analysis oftraffic queue dynamics at signalized intersections [J]. Transportation Research Part A：General，1979，13(5)：295-307.
[157]郭冠英.道路阻塞时的车辆排队长度计算法[J].中国公路学报，1998，11(3)：92-95.
[158]臧华，彭国雄.高速道路异常状况下车辆排队长度的预测模型[J].交通与计算机，2003，21(3)：10-12.
[159]王建军，周伟.线性模型下高速公路交通事故和干涉车流波模拟理论研究[J].西安公路交通大学学报，1998，18(3)：283-289.
[160]赵祥模，靳引利，张洋.高速公路监控系统理论及应用[M].电子工业出版社，2003.
[161]中华人民共和国交通部. GTJB01-2003.公路工程技术标准[S].北京：人民交通出版社，2004：44-45.
[162]高宏岩.融合移动信号流的高速公路交通拥挤预警与调控[D].山东科技大学，2011.
[163]王晓丹.基于模糊聚类及神经网络的纹理分割方法研究[D].西安：西北工业大学，2000.
[164]赵风波，孙敏.基于模糊聚类分析的交通状态识别方法[J].微型电脑应用，2006，22(2)：9-11.
[165] Rakha H, El-Shawarby I, Arafeh M, et al. Estimating path travel-time reliability[C].IEEE Conference on Intelligent Transportation Systems，2006：236-241.
[166] Kalman R E. A new approach to linear filtering and prediction problems [J]. Journal ofbasic Engineering，1960，82(1)：35-45.
[167]苏金明，阮沈勇，王永利编. MATLAB工程数学，北京：电子工业出版社，2005.