基于多用户驾驶模拟平台的雾天高速公路跟驰模型参数标定及验证

高速公路连环追尾事故多发生在雾天环境下,且容易造成严重的事故人员伤亡。当前的跟驰及追尾风险研究多集中于两车跟驰,缺乏对雾天情况下车队跟驰的研究。利用雾天环境下车队跟驰轨迹数据对传统主流跟驰模型进行标定验证,基于多用户驾驶模拟平台设计了8个不同雾天等级和限速组合的高速公路虚拟场景,开展驾驶模拟试验并采集数据。试验招募了8名男性驾驶人并通过随机调整他们在车队中的位置顺序来获得足够的车队跟驰轨迹数据,根据判定标准筛选合适的车队跟驰轨迹数据,按照2:1的原则分配标定和验证阶段的数据组。选取Newell、Gipps和IDM三个主流跟车模型进行参数标定和验证,以时间序列的车头间距和相对均方根误差(RMSPE)分别作为性能指标参数和拟合优度函数,使用遗传算法搜寻目标函数最小值以标定跟驰模型参数,并用车辆轨迹完整性(CVT)和RMSPE评价验证阶段的仿真结果。结果表明:在标定阶段,Newell、Gipps和IDM三个模型的RMSPE整体平均值分别为30.1%、18.6%和27.7%,各个试验条件下Gipps模型的RMSPE值均小于另外2个模型,说明Gipps模型能更好地拟合试验数据;在验证阶段,Gipps模型的RMSPE整体平均值为21.2%,远小于另外2个模型,可见Gipps模型在局部精确度上的鲁棒性要优于Newell模型和IDM模型;Gipps模型的CVT整体平均值和波动幅度分别为98.1%和2.0%,均是3个模型中的最小值,说明Gipps模型在整体轨迹上的鲁棒性也优于另外2个模型。雾天环境下,Gipps模型具备更好的拟合能力和鲁棒性,因此推荐仿真软件使用Gipps模型模拟雾天环境下车队跟驰行为,不同雾天等级及限速下的Gipps模型参数可参考该研究标定的参数。     

新型国产轨道交通接触网检测系统研究

根据上海城轨交通接触网的现状及特点,阐述应用机器视觉理论研究开发专用非接触式接触网检测系统的关键技术,主要包括弓网关系、国内外检测技术现状、采用的技术路线、方案具体实施等,内容涉及高速数字成像、图像识别模型、图像边缘处理、几何光学布置设计、里程定位设计、多任务多进程软件设计。结果表明,接触网监测产品作为轨道交通接触网的专业检测装置,可适应国内轨道交通接触网的现状,同时利用自主研发的专业技术,可摆脱对国外进口设备的依赖,并能节约成本。     

基于多源信息融合的行人检测实时性方法研究

目前车辆安全预警系统中存在行人检测粗检不准,细检过慢的问题,孤立的采用激光、雷达、红外或是摄像机均很难满足行人检测实时而准确的需求.考虑用多源信息融合的方法进行行人检测即将雷达与摄像机结合运用,使它们的信息有机融合,在提高速度的同时又不以降低精度为代价.研究了适应车载安全系统的摄像机标定与确定行人重点检测区域的方法.     

水泥混凝土搅拌设备计量标定

水泥混凝土搅拌设备的计量精度和配料误差是控制搅拌设备混合料生产质量和稳定性的关键,结合内蒙古白霍线(白音华-霍林郭勒)水泥混凝土路面施工实体工程,介绍了搅拌站的静态计量标定原理、方法步骤,动态配料误差检查程序和方法。     

高压共轨EGR中型柴油机OBD标定技术探讨

按照法规要求,在满足国Ⅳ排放法规的同时,必须加装OBD系统。本文主要介绍了匹配了BOSCH电控高压共轨系统和EGR＋DOC＋POC方案的中小型发动机,OBD的基本原理和标定方法流程。     

CO2分析仪表便携式标校装置的实验研究

为解决预配标准气体钢瓶CO2分析仪表标校存在配气方法复杂、携带不便等问题,研制可用于CO2分析仪表标校的便携式装置,对利用定量碳酸氢钠和碳酸氢钾热分解获得定量二氧化碳并与N2混合制备出标校用CO2标准气体进行实验,结果表明此方案可行。     

基于全球定位系统的舰载三坐标雷达动态标校方法

为弥补舰载作战系统试验中传统三坐标雷达标校方法的不足,提高标校效率,提出一种基于全球定位系统(GPS)RTK模式动态标校舰载三坐标雷达的方法。该方法通过实时录取GPS的定位数据,经过坐标变换和插值修正,给出目标运动的约定真值。对所设计和实现的三坐标雷达标校系统精度的试验检查结果表明,该标校系统满足舰载三坐标雷达的标校工作,同时降低了对环境的依赖性,便于操作,距离误差在4 cm以内。     

Calibration of nonlinear car-following laws for traffic oscillation prediction

Frequency-domain analysis has been successfully used to (i) predict the amplification of traffic oscillations along a platoon of vehicles with nonlinear car-following laws and (ii) measure traffic oscillation properties (e.g., periodicity, magnitude) from field data. This paper proposes a new method to calibrate nonlinear car-following laws based on real-world vehicle trajectories, such that oscillation prediction (based on the calibrated car-following laws) and measurement from the same data can be compared and validated. This calibration method, for the first time, takes into account not only the driver’s car-following behavior but also the vehicle trajectory’s time-domain (e.g., location, speed) and frequency-domain properties (e.g., peak oscillation amplitude). We use Newell’s car-following model (1961) as an example and calibrate its parameters based on a penalty-based maximum likelihood estimation procedure. A series of experiments using Next Generation Simulation (NGSIM) data are conducted to illustrate the applicability and performance of the proposed approach. Results show that the calibrated car-following models are able to simultaneously reproduce observed driver behavior, time-domain trajectories, and oscillation propagation along the platoon with reasonable accuracy.     

Multilane first-order traffic flow model with endogenous representation of lane-flow equilibrium

In this study, we develop a multilane first-order traffic flow model for freeway networks. In the model, lane changing is considered as a stochastic behavior that can decrease an individual driver’s disutility or cost, and is represented as dynamics toward the equilibrium of lane-flow distribution along with longitudinal traffic dynamics. The proposed method can be differentiated from those in previous studies because in this study, the motivation of lane changing is explicitly considered and it is treated as a utility defined by the current macroscopic traffic state. In addition, the entire process of lane changing is computed macroscopically by an extension of the kinematic wave theory employing IT principle; moreover, in the model framework, the lane-flow equilibrium curve is endogenously generated because of self-motivated lane changes. Furthermore, the parsimonious representation enables parameter calibration using the data collected from conventional loop detectors. The calibration of the data collected at four different sites, including a sag bottleneck, on the Chugoku expressway in Japan reveals that the proposed method can represent the lane-flow distribution of any observation site with high accuracy, and that the estimated parameters can reasonably explain the multilane traffic dynamics and the bottleneck phenomena uphill of sag sections.     

Specific object re-identification across non-overlapping camera views in traffic accidents

ABSTRACT

To improve the robustness of object re-identification in complex outdoor environments for traffic safety systems, a novel object re-identification algorithm based on the Individual Similarity Difference Feature (ISDF) method is proposed. This method can provide reliable support for specific object tracking during traffic accidents in video surveillance networks. First, all the images in the gallery are divided into three parts according to a segmentation ratio, and six types of feature for each part are extracted. Second, prototypes for each feature of the three parts are constructed. Third, the image sequence of the same person is grouped, and then the ISDF is extracted from each image. Finally, we use the AdaBoost classifier to judge whether the two objects are matched and then output the final results. Extensive experiments are conducted on two public data sets (Eidgenössische Technische Hochschule Zürich and multi-camera object tracking). The performance of the object re-identification method is superior to the latest methods.