高速公路动态环境下的摄像机自标定

提出一种动态环境下高速公路监控系统摄像机的自标定方法.首先利用混合高斯背景建模方法从动态视频图像中获取背景图像和目标频繁出现的目标区域;然后利用不同的直线检测算法检测和估计出目标区域内高速公路上大量存在的各种标志线和虚标志线以及水平线,基于这些线状特征计算出摄像机的灭点;最后根据灭点和线特征之间的几何关系计算出摄像机的内外参数,从而实现摄像机自标定.真实场景的实验结果表明,该算法非常合适于各种高速公路监控系统中摄像机的实时自标定,且精度高、稳定性好.     

基于相似度直方图的混合指纹匹配方法

指纹的匹配问题是指纹识别算法中的核心问题．文中介绍了一种基于相似度直方图的指纹混合匹配算法,该算法同时使用了指纹的细节特征和纹理特征．指纹的细节匹配部分通过相似度直方图函数来计算最优校准参数,并且将校准结果应用到纹理匹配中．在FVC2002数据库上的实验结果表明该混合识别算法比使用细节匹配的算法具有更高的识别率．     

在线高斯混合模型和纹理支持的运动分割

运动分割是基于视频的运动分析中的基本问题．通过颜色和纹理特征的线性组合,实现了一种新的检测运动目标的算法．在线高斯混合模型不仅用于对背景进行更新,而且也用于计算像素颜色差异和颜色权值;纹理特征用于描述局部区域内的结构信息,提高了运动检测算法的鲁棒性．对不同场景的运动分割结果表明,该算法是高效和实用的．     

基于Ｖｏｌｔｅｒｒａ频域核辨识的非线性模拟电路故障诊断

基于Ｖｏｌｔｅｒｒａ级数时域频域混合模型,提出了辨识非线性模拟电路频域核的故障诊断方法．利用混合模型辨识算法和范德蒙特法估计各种故障状态下电路响应的前３阶频域核,提取故障特征并与相应的故障模式一起构成特征样本集,借助于支持向量机多分类器进行分类识别,实现非线性模拟电路的故障诊断．阐述了诊断原理及诊断步骤,并给出了诊断实例．仿真结果表明,该方法的故障识别率较高,便于计算机计算．

     

基于增量式特征基背景模型的运动目标检测

背景差法是目标运动检测的主流方法,关键在于背景模型自适应更新.针对传统特征基背景模型批处理方式计算量大、更新速度慢的问题,采用增量式主成分分析来建立特征基背景模型.首先计算样本图像的初始背景图像,然后采用CCFIPCA算法更新特征基背景模型,最后通过输入帧和重建帧的欧氏距离检测前景运动目标.算法以视频帧整体来建立背景模型,克服了混合高斯模型和核密度估计以孤立像素点建模的不足,提高了背景建模的鲁棒性.在SIMULINK下的仿真实验表明,算法能很好地适应高速公路交通场景动态变化,在有光线变化和阴影影响的情况下能完整、准确地提取出运动车辆轮廓.     

映射技术在液-液混合中的应用

本文给出了描述非周期液-液混合流的映射方法．根据非周期混合流的特点,对周期映射方法进行了改进．针对不同时刻的映射矩阵,建立了计算该矩阵非零分量的优化算法．为减小网格单元重叠所导致的单元信息传递误差,用最初网格代替变形网格,提出了重构映射矩阵的概念用以传递映射过程中的相关变量．对不同雷诺数背景流体中单液滴和双液滴混合初始阶段的流变特征进行了模拟．数值实验表明:用偏析强度表征的混合质量随时间呈指数增长;较高的背景流体雷诺数,有利于混合质量的提高;多液滴之间的相互交融对混合过程存在较大影响．     

一种适用于局部特征的混合视觉伺服方法

提出一种基于图像矩的混合视觉伺服方法,有效解决了因匹配的局部特征改变而引起的雅可比矩阵结构改变及奇异等难点．该方法首先估计得到单应性矩阵,然后通过反向映射计算未匹配点的像素坐标,采用图像矩和单应性矩阵分解得到的姿态分别控制平动和转动自由度,采用特征的雅可比矩阵不存在奇异情况．从理论上证明了所采用控制策略的稳定性和对摄像机标定误差的鲁棒性,仿真实验结果表明该方法适用于局部特征．     

反求工程中的混合切片技术

提出一种基于平面与“点云”、平面与NURBS曲面求交计算的混合切片方法．该方法可以保证切片曲线在点云和曲面的连接处达到G^1连续，在此基础上的重构曲面既能保证与相邻曲面的连续性要求，又能满足对点云的逼近精度要求，对反求建模尤其是过渡特征的重建有着重要意义．文中详细探讨了平面与曲面求交和点云切片两个核心算法，并对基于模型特征的混合切片方案的选择原则以及不同方法进行了论述和比较．最后用实例证明该方法在反求建模中是切实可行的．     

基于风险指标的干旱期水资源系统运行优化分析

根据干旱期水资源系统运行性能分析特征,建立了基于供水可靠性最大、供水破坏恢复能力最强以及单一时段破坏深度最小等风险指标,同时考虑了城市和农业供水优先权问题的多目标混合整数规划模型．在实例研究中,运用多目标决策法中的协调规划原理,通过评价任一目标点与理想点的欧氏距离,获得多目标问题的最佳权衡解．计算结果表明,该多目标混合整数规划模型对解决需要考虑供水优先权的干旱期水库运行策略优化问题是可行而有效的．     

高速公路监控视频中运动车辆对象提取

结合高速公路交通视频的特点,提出了监控中运动车辆对象提取的方法。该方法利用混合背景差分法提取运动目标,并对目标进行形态学处理,最后结合后退N帧、半监督学习的阈值选取的思想提取车辆对象特征最显著的视频帧。实验结果表明,该方法有效地改善了传统的混合高斯背景差分提取运动对象过程中出现的孔洞、噪声和车辆对象非完整性及特征不显著的问题,进而优化了车辆对象的提取流程。     

高速公路主线限速与匝道融合的协调控制

为缓解高速公路的交通拥挤,主线限速、匝道融合等常被应用,因主线限速和匝道融合经各自优化获得的控制策略可能存在矛盾,故二者协调是必须的,而如何建立和求解二者的协调控制模型还没有有效方法.本文基于宏观交通流理论和多agent技术研究了此协调控制问题.为此首先阐述了高速公路的一般宏观交通流模型;然后分析主线限速、匝道融合的交通特性,建立了主线限速-匝道融合交通流模型;并协调主线限速和匝道融合,建立了协调控制模型.最后,基于多agent技术和分层递阶结构提出了协调控制模型的求解算法,并给出了应用此方法控制仿真高速公路的一个实例.     

Cellular automata on FPGA for real-time urban traffic signals control

Among different traffic features, the urban traffic has received a lot of attention due to the ongoing traffic congestion as a result of increased car usage, population growth, and changes in population density. In urban networks, the vehicles flow differs when compared with highways flow because of the freeway’s low speed limit but mostly because of the traffic lights control. In this paper, a real-time hardware implemented bio-inspired model for traffic lights control is presented. The proposed model arrives from Cellular Automata (CAs), which have been proven very flexible and powerful computational traffic models, in that they are able to capture all previously mentioned basic phenomena that occur in traffic flows. The resulting CA model was hardware implemented on FPGA to take full advantage of the inherent parallelism of the CAs and to support the function of an advanced electronic system able to provide real-time adaptive control of traffic lights designed to consider traffic conditions for the whole intersections. The analytical results, obtained by application of the aforementioned FPGA CA processor are found in excellent agreement with the numerical simulations.     

A Survey of Model Predictive Control Methods for Traffic Signal Control

Enhancing traffic efficiency and alleviating (even circumventing) traffic congestion with advanced traffic signal control (TSC) strategies are always the main issues to be addressed in urban transportation systems. Since model predictive control (MPC) has a lot of advantages in modeling complex dynamic systems, it has been widely studied in traffic signal control over the past 20 years. There is a need for an in-depth understanding of MPC-based TSC methods for traffic networks. Therefore, this paper presents the motivation of using MPC for TSC and how MPC-based TSC approaches are implemented to manage and control the dynamics of traffic flows both in urban road networks and freeway networks. Meanwhile, typical performance evaluation metrics, solution methods, examples of simulations, and applications related to MPC-based TSC approaches are reported. More importantly, this paper summarizes the recent developments and the research trends in coordination and control of traffic networks with MPC-based TSC approaches. Remaining challenges and open issues are discussed towards the end of this paper to discover potential future research directions.      

城市高速公路交通的神经网络建模与控制

从城市高速公路交通流的宏观、动态特性出发 ,分析了交通流控制中常用的宏观、动态、确定性模型 在此基础上 ,利用人工神经网络技术建立了城市高速公路的神经网络模型 ,并提出了入口匝道放行和路段速度相结合的多变量神经网络控制策略 利用该控制策略建立的自适应神经网络控制器 ,可以使高速公路上的交通密度维持在理想的密度值附近 .进一步分析可以得到 ,该控制器是一个状态和控制作用均可跟踪的伺服系统 .以杭州某高架高速公路为背景的仿真结果表明 :该控制器具有较强的鲁帮性 ,控制效果令人满意 .     

基于小脑模型关节控制器与PID复合的高速公路交通流密度控制

高速公路交通控制系统是一个复杂的非线性时变系统, 传统的匝道控制方法难以取得满意的控制效果. 为此, 本文提出基于小脑模型关节控制器(CMAC)与PID复合的匝道控制方法. 首先建立了二阶宏观动态交通流模型, 然后研究了CMAC与PID复合控制算法, 结合非线性反馈理论, 设计了基于CMAC与PID复合的高速公路交通流密度控制器, 该密度控制问题是一个输出跟踪和扰动抑制问题, 最后采用两个仿真实例对该方法的有效性进行验证. 结果表明, 复合控制具有优越的密度跟踪性能和抑制噪声干扰的能力; 复合控制方法能够有效地消除交通拥挤, 并使主线车流趋于稳定.     

An adaptive freeway traffic state estimator

Real-data testing results of a real-time nonlinear freeway traffic state estimator are presented with a particular focus on its adaptive features. The pursued general approach to the real-time adaptive estimation of complete traffic state in freeway stretches or networks is based on stochastic nonlinear macroscopic traffic flow modeling and extended Kalman filtering. One major innovative aspect of the estimator is the real-time joint estimation of traffic flow variables (flows, mean speeds, and densities) and some important model parameters (free speed, critical density, and capacity), which leads to four significant features of the traffic state estimator: (i) avoidance of prior model calibration; (ii) automatic adaptation to changing external conditions (e.g. weather and lighting conditions, traffic composition, control measures); (iii) enabling of incident alarms; (iv) enabling of detector fault alarms. The purpose of the reported real-data testing is, first, to demonstrate feature (i) by investigating some basic properties of the estimator and, second, to explore some adaptive capabilities of the estimator that enable features (ii)-(iv). The achieved testing results are quite satisfactory and promising for further work and field applications.     

高速公路动态交通流的BP神经网络建模

通过对高速公路宏观动态交通流模型的分析,针对高速公路交通系统的非线性时变特点,应用BP神经网络建立了高速公路宏观动态交通流模型。并利用一段高速公路的交通流数据对BP神经网络进行训练,得到网络参数。最后,为了验证BP网络模型的有效性,在MATLAB环境中对模型进行了仿真,并将仿真结果与原始模型的结果进行了比较。结果表明,该方法能较准确地描述高速公路交通流的真实行为,并且能够适应交通状况的变化。     

Freeway traffic estimation within particle filtering framework

This paper formulates the problem of real-time estimation of traffic state in freeway networks by means of the particle filtering framework. A particle filter (PF) is developed based on a recently proposed speed-extended cell-transmission model of freeway traffic. The freeway is considered as a network of components representing different freeway stretches called segments. The evolution of the traffic in a segment is modelled as a dynamic stochastic system, influenced by states of neighbour segments. Measurements are received only at boundaries between some segments and averaged within possibly irregular time intervals. This limits the measurement update in the PF to only these time instants when a new measurement arrives, while in between measurement updates any simulation model can be used to describe the evolution of the particles. The PF performance is validated and evaluated using synthetic and real traffic data from a Belgian freeway. An unscented Kalman filter is also presented. A comparison of the PF with the unscented Kalman filter is performed with respect to accuracy and complexity.     

Traffic Grammar and Algorithmic Complexity in Urban Freeway Flow Patterns

This paper uses techniques from formal language theory to describe the linear spatial patterns in urban freeway traffic flows in order to understand and analyze “hidden order” in such high volume systems. A method for measuring randomness based on algorithmic entropy is introduced and developed. These concepts are operationalized using Pincus’ approximate entropy formulation in an appropriate illustration. These measures, which may be viewed as counterintuitive, are believed to offer robust and rigorous guidance to enhance the overall understanding of efficiency in urban freeway traffic systems. Utilization of such measures should be facilitated by information generated by real time intelligent transportation systems (ITS) technologies and may prove helpful in real time traffic flow management. An earlier version of this paper was presented at the Fifth Joint Conference on Computing and Information Sciences, February 2000, Atlantic City, NJ. The authors appreciate the support of the NSF/ EPA Grant #SES-9976483 “Social Vulnerability Analysis and NSF Grant #ECS-0085981 “Road Transportation as a Complex Adaptive System” as well as the School of Public Policy’s USDOT Center of Excellence in Evaluation and Implementation funded under DOT Grant #DTRS98-G-0013. Any errors are the responsibility of the authors.     

面向交通流量预测的多组件时空图卷积网络

流量预测一直是交通领域研究者和实践者关注的热点问题.流量数据具有高度的非线性和复杂性,对其进行精准预测具有很大的挑战,现有的预测方法大多不能很好地捕获数据的时空相关性.提出一种新颖的基于深度学习的多组件时空图卷积网络（MCSTGCN）,以解决交通流量预测问题.MCSTGCN通过3个组件分别建模流量数据的近期、日周期、周周期特性,每个组件同时利用空间维图卷积和时间维卷积有效捕获交通数据的时空相关性.在美国加利福尼亚州高速公路流量公开数据集上进行了实验,结果表明,MCSTGCN模型的预测效果优于现有的预测方法.