道路平面交叉口车辆违章右转弯行为识别研究

城市道路交叉口场景复杂,流量巨大,是交通事故多发地点。而交叉口处车辆违章转弯是造成事故多发的重要原因之一。因此,研究道路交叉口处违章转弯车辆的检测、跟踪与识别技术对于减少交叉口处的事故发生,提高通行能力和服务水平具有重要的意义。本文利用计算机视频技术,并结合道路交叉口交通信号相位特性以及车道内行车标志线等信息,研究了交叉口处违章右转弯车辆的检测与跟踪算法,给出了违章右转弯行为的判定方法。     

基于驾驶员短期记忆的限速标志合理间距研究

从驾驶安全性和驾驶员短期记忆特性两个方面综合考虑高速公路限速标志的设置间距.采用室内实验的方法,对驾驶员的短期记忆衰减规律进行研究,建立驾驶员短期记忆衰减规律指数模型,并将此结果应用于高速公路限速标志的设置过程中.根据高速公路的不同限速值,定量给出高速公路限速标志的合理设置间距.     

城市停车诱导系统设计研究

分析了该系统的目的、基本功能,提出了系统框架设计和功能模块设计内容 从管理层次和技术面层次,提出了系统总体设计框架,最后结合我国大城市停车现状和研究的交通拥挤状况,提出了停车诱导系统的发展方向。     

动态交通流诱导模型在交通出行服务中的应用研究

本文从浙江交通智能交通建设应用需求出发,分析了动态交通流诱导模型在浙江交通出行服务中的实际应用,提出了浙江交通高速公路、内河航道实时交通状况分析的方案。该方案包括了基于多个Agent诱导代理系统的诱导模型,交通流诱导系统框架等自主技术研究成果。同时,本文给出了在浙江交通出行服务实际应用中,结合GPS定位技术、GIS地理信息技术、GSM/CDMA无线通信技术,实现了浙江交通高速公路、内河航道实时交通状况的分析和播报的应用场景。     

An investigation of the reliability of real-time information for route choice decisions in a congested traffic system

This paper investigates the reliability of information on prevailing trip times on the links of a network as a basis for route choice decisions by individual drivers. It considers a type of information strategy in which no attempt is made by some central controller or coordinating entity to predict what the travel times on each link would be by the time it is reached by a driver that is presently at a given location. A specially modified model combining traffic simulation and path assignment capabilities is used to analyze the reliability of the real-time information supplied to the drivers. This is accomplished by comparing the supplied travel times (at the link and path levels) to the actual trip times experienced in the network after the information has been given. In addition, the quality of the decisions made by drivers on the basis of this information (under alternative path switching rules) is evaluated ex-post by comparing the actually experienced travel time (given the decision made) to the time that the driver would have experienced without the real-time information. Results of a series of simulation experiments under recurrent congestion conditions are discussed, illustrating the interactions between information reliability and user response.     

Efficient solution algorithm for finding spatially dependent reliable shortest path in road networks

Travel times are generally stochastic and spatially correlated in congested road networks. However, very few existing route guidance systems (RGS) can provide reliable guidance services to aid travellers planning their trips with taking account explicitly travel time reliability constraint. This study aims to develop such a RGS with particular consideration of travellers' concern on travel time reliability in congested road networks with uncertainty. In this study, the spatially dependent reliable shortest path problem (SD‐RSPP) is formulated as a multi‐criteria shortest path‐finding problem in road networks with correlated link travel times. Three effective dominance conditions are established for links with different levels of travel time correlations. An efficient algorithm is proposed to solve SD‐RSPP by adaptively using three established dominance conditions. The complexities of road networks in reality are also explicitly considered. To demonstrate the applicability of proposed algorithm, a comprehensive case study is carried out in Hong Kong. The results of case study show that the proposed solution algorithm is robust to take account of travellers' multiple routing criteria. Computational results demonstrate that the proposed solution algorithm can determine the reliable shortest path on real‐time basis for large‐scale road networks. Copyright © 2016 John Wiley & Sons, Ltd.     

地铁安全与防灾通用标志研究

地铁安全与防灾通用标志系统在保证地铁高效运行及灾时进行乘客的安全疏散与救助方面起着极其重要的作用.基于对国内外地铁安全与防灾通用标志系统的考察分析,结合相关规范,在认知心理学和人体工程学的基础上分析了影响标志设计的重要因素,从标志的颜色、内容、材料、采光形式等方面提出了设计及优化建议,以使地铁安全与防灾通用标志满足功能...     

罗德里格矩阵在盾构引导系统中的应用研究

空间三维坐标转换是盾构自动引导系统三棱镜模型的关键问题.将罗德里格矩阵用于盾构机姿态参数的计算当中,并用VC 6.0编写了基于三棱镜模型的盾构自动引导系统.解析了自动引导系统的数字模型.该系统在苏州地铁1号线某区间试验中运行稳定、仪器连接设置简单.罗德里格矩阵用于空间三维坐标转换有一定的实用性.     

基于网格搜索的PCA-SVM道路交通标志识别

针对现有识别方法对交通标志的识别精度和算法效率不高的问题,提出了一种基于网格搜索的主成分分析-支持向量机(PCA-SVM)道路交通标志识别方法。该方法首先采用主成分分析(PCA)法对交通标志进行降维处理,提取出交通标志的主元特征,然后利用网格搜索法(GS)对支持向量机(SVM)进行参数优化,最后利用参数优化好的支持向量机分类器实现对交通标志的识别。通过实验仿真,并与现有的其他交通标志识别算法进行分析对比,实验结果表明,本文方法在保证较高识别精度的同时,算法效率得到显著提高。