CN101510357B - Method for detecting traffic state based on mobile phone signal data - Google Patents

Method for detecting traffic state based on mobile phone signal data Download PDF

Info

Publication number
CN101510357B
CN101510357B CN 200910048300 CN200910048300A CN101510357B CN 101510357 B CN101510357 B CN 101510357B CN 200910048300 CN200910048300 CN 200910048300 CN 200910048300 A CN200910048300 A CN 200910048300A CN 101510357 B CN101510357 B CN 101510357B
Authority
CN
China
Prior art keywords
step
traffic
road
virtual sensor
phone
Prior art date
Application number
CN 200910048300
Other languages
Chinese (zh)
Other versions
CN101510357A (en
Inventor
冉斌
裘炜毅
邱志军
Original Assignee
美慧信息科技(上海)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 美慧信息科技(上海)有限公司 filed Critical 美慧信息科技(上海)有限公司
Priority to CN 200910048300 priority Critical patent/CN101510357B/en
Publication of CN101510357A publication Critical patent/CN101510357A/en
Application granted granted Critical
Publication of CN101510357B publication Critical patent/CN101510357B/en

Links

Abstract

The invention provides a method for detecting traffic state based on mobile phone signals. A virtual sensor network is set up to acquire the real-time signal data sent from all mobile phones within a time interval from a mobile phone network at a fixed time interval, a virtual sensor section and the traveling speed vi can be obtained according to the real-time signal data sent from an i-th mobilephone; the virtual sensor section is superposed onto a road network to obtain the road network section and the traveling speed Vi of the i-th mobile phone; a real-time traffic flow intensity K and a section traffic flow Q can be obtained by collecting the number n of the mobile phones on each road network section and the traveling speed V of each road network section; and finally, through a traffic parameter prediction model, the predicted traffic flow speed V, the traffic flow intensity K and the section traffic flow Q can be obtained. The method has the advantages that the large range of real-time traffic data acquisition in the city can be completed in a short time by fully relying on the existing mobile communication network resources, and utilizing the information in the existing mobile phone communication network, meanwhile, the initial investment is relatively small, the data coverage is wide, and data accuracy is high.

Description

一种基于手机信号数据检测交通状态的方法技术领域 In the technical field based on the detection signal data phone traffic state

[0001] 本发明涉及一种基于手机信号数据检测交通状态的方法,适用于城市交通运输管理及交通信息服务行业,属于用手机信号检测交通状态的方法技术领域。 [0001] The present invention relates to a cell phone signal based on the data traffic state detection method for urban transport management and traffic information services industry, traffic signal detection using a mobile phone belonging to the state FIELD. 背景技术 Background technique

[0002] 智能交通系统(Intelligent Transportation System,简称ITS)是运用信息通信技术,将人、车、路三者紧密协调、和谐统一,在大范围内全方位发挥作用的实时、准确、高效的交通运输管理系统。 [0002] intelligent transportation systems (Intelligent Transportation System, referred ITS) is the use of information and communication technology, close coordination of people, vehicles, roads three, harmony and unity, all-round play in real time, accurate and efficient transportation role in a wide range transportation management system. ITS能够有效地利用现有交通设施减少交通负荷和环境污染,保证交通安全,提高运输效率,从而促进社会经济发展,提高人民生活质量,并以其推动社会信息化及形成新产业的能力普遍受到世界各国的重视。 ITS can effective use of existing transport infrastructure to reduce traffic load and environmental pollution, to ensure traffic safety, improve transport efficiency, so as to promote social and economic development, improving people's quality of life, and its ability to promote the information society and the creation of new industries universally the world's attention.

[0003] 如何获取动态实时交通信息成为智能交通系统发展过程中重要的一环。 [0003] how to get a dynamic real-time traffic information to be intelligent transportation system development process, an important part. 从技术发展趋势来看,传统定点采集技术:如感应线圈、雷达、红外和视频,只能采集有限范围内的城市道路交通信息;而装载GPS设备的浮动车(通常是出租车、公交车或货运车等)技术,也受装载设备的车辆数规模限制,只能提供城市局部范围的动态交通信息。 From technology trends, the traditional site-collection technology: such as an induction coil, radar, infrared and video, can only collection of urban road traffic information within a limited range; and loading floating car GPS device (usually a taxi, bus or freight car, etc.) technology, the vehicle is also affected by the number of loading equipment size limit, it can only provide dynamic traffic information local scale city. 如何采集城市大范围内的实时交通信息成为一项技术难题。 How to collect real-time traffic information in the city become a wide range of technical problems. 手机终端的普及以及移动运营商的无线通讯网络、无线通讯网络信令采集和监控平台、安全加密机制等技术的发展和完善,为利用手机终端作为检测设备,获取手机正常使用过程中的无线信号参数,以此为基础采集广域实时交通信息的技术实现提供了重要的技术保障。 The popularity of mobile operators and mobile terminals of wireless communication networks, wireless communications network signaling and monitoring of collection development and improvement of technology platforms, security encryption mechanism for the use of mobile terminals as the detection equipment, acquiring a wireless signal during normal use of mobile phones parameters, real-time traffic information technology foundation to achieve this as a wide collection provides an important technical support.

[0004] 过去,交通数据都是用传统的固定传感器获取,比如,感应线圈、雷达、红外和视频等。 [0004] In the past, traffic data are acquired using a conventional fixed sensor, for example, induction coil, radar, infrared and video. 因为高昂的安装和维护费用,交通数据采集技术发展到利用手机或车载GPS的位置信息的浮动车技术。 Because of the high installation and maintenance costs, traffic data collection technology to use mobile phones or car GPS floating car technology location information. 基于GPS的浮动车是指运行在路上的车辆载着的装有GPS单元的移动设备。 GPS-based probe vehicle refers to a mobile device equipped with a GPS unit in the vehicle running road is carrying. 装有GPS单元的移动设备包括GPS手机、个人导航设备、装有GPS设备的车辆等。 Mobile devices equipped with GPS units include GPS mobile phones, personal navigation devices, and other vehicles equipped with GPS devices. 从GPS样本的GPS单元传递出的信号可以经过处理和用电子地图数据匹配,从而得到GPS样本在不同的道路路段上的旅行轨迹、旅行速度和旅行时间。 Signal transmitted from the GPS unit may be treated sample GPS data and map matching, to thereby obtain GPS sample to travel on different track road segment, the speed of travel and the travel time. 基于手机的浮动车是指手机移动终端,它可能不包括GPS单元。 Floating Car phone-based mobile terminal refers to a mobile phone, it may not include a GPS unit. 手机网络持续地生成各种具体记录,比如收短消息、发短消息、开机、关机等,这样手机用户才能接打电话并且在经过手机网络基站的边界时保证通话是连续的。 Mobile networks continue to generate various specific records, such as the short message received, PM, boot, shutdown and the like, so that users can make and receive calls and phone calls are guaranteed continuous through boundaries when the phone network base stations. 以前的方法和系统不能用交通科学或交通工程的基础知识来处理手机信号数据,获取实时和预测的交通状态。 Previous methods and systems can not handle the cell phone signal to the basics of data traffic or traffic engineering sciences, access to real-time and predicted traffic state. 发明内容 SUMMARY

[0005] 本发明的目的是提供一种用交通科学或交通工程的基础知识来处理手机信号数据,获取实时和预测的交通状态的基于手机信号数据检测交通状态的方法。 [0005] The present invention is to provide a cell phone signal to process traffic data with the basics of science or engineering transportation, access to real-time and predicted traffic state based cell phone signal data traffic state detection method.

[0006] 为了达到上述目的,本发明的技术方案是提供了一种基于手机信号数据检测交通状态的方法,步骤为: [0006] To achieve the above object, the technical solution of the present invention is to provide a mobile phone based on signal data traffic state detecting method, the steps of:

[0007] 步骤1、建立虚拟传感器网络; [0007] Step 1, establishing a virtual sensor network;

[0008] 步骤2、以固定时间间隔T从手机网络获取该时间间隔内所有手机发出的实时信号数据; [0008] Step 2, at fixed time intervals T acquire real-time signal within the time interval data sent from all mobile phone the mobile phone network;

[0009] 步骤3、根据第i部手机发出的实时信号数据中的基站标识号和位置区标识号通过虚拟传感器网络地理译码得到该手机所在的虚拟传感器路段及在该虚拟传感器路段上的旅行速度Vi ; [0009] Step 3, the i-th real-time data signal emitted by the mobile phone base station identification number and the location area identification number of the link to obtain a virtual sensor and the mobile phone is located on the virtual sensor traveling through the virtual sensor network link geocoding speed Vi;

[0010] 步骤4、从道路网络数据库中读取道路网络的电子地图信息,将步骤3得到的虚拟传感器路段叠加在道路网络上,得到第i部手机所在的道路网络路段,令该手机在道路网络路段上的旅行速度Vi = Vi ; [0010] Step 4, the road network is read from the road map database and network information, obtained in step 3 is superimposed on the virtual sensor link road network, road network link to obtain the phone where the i-th unit road enabling the phone travel speed on the network section of Vi = Vi;

[0011] 步骤5、重复步骤3及步骤4直至收集到时间间隔T内所有可能采样到的手机所在的道路网络路段,即得到每条道路网络路段上的可能采样到的手机个数η及每条道路网络路段的旅行速度ν,ν=έ「/η;/=1 [0011] Step 5 Repeat step 3 and step 4 until the time interval of the road network to collect all possible sampled segment where the mobile phone T, which exposes the phone number may be obtained on each sample to the road network and each segment η Article sections of the road network travel speed ν, ν = έ '/ η; / = 1

[0012] 步骤6、根据每条道路网络路段上的手机个数η及旅行速度V计算得到时间间隔T 内对应的道路网络路段的交通流密度K和路段交通流量Q。 [0012] Step 6, according to the phone number on each road link network and η calculated travel velocity V of traffic density interval T of the road network segment corresponding traffic segment K and Q.

[0013] 步骤7、根据不同道路类别交通流参数的时变特征,建立相应的交通流参数预测模型。 [0013] Step 7 The different road types varying characteristics of traffic flow parameters, the traffic flow to establish the corresponding parameter prediction model.

[0014] 本发明通过实时采集、分析移动通信网络中的通信数据,将普通用户使用的手机移动终端作为一种有效的交通检测器,利用本发明提出的方法,分析推算每个手机的运动轨迹和运动速度,得到实时和预测的道路交通状态信息。 [0014] The present invention is by real time acquisition, analysis, data communication in a mobile communication network, the mobile phone terminal used by ordinary users as an effective traffic detector, by the method proposed by the present invention, each handset Analysis calculated trajectory and movement speed, get real-time and predicted road traffic status information. 本发明无需在手机终端上安装任何特殊设备、无需安装任何软件,将每个个人用户使用的普通手机作为采集终端,突破了传统交通采集技术需要事先安装采集终端的初期投资建设瓶颈,可节约大量基础设施投资。 The present invention need not be installed on mobile terminals any special equipment, without having to install any software, ordinary mobile phones will be used for each individual user as a collection terminal, breaking the bottleneck of traditional initial investment and construction techniques need to install traffic collection collection terminal, you can save a lot investment in infrastructure.

[0015] 本发明可以为城市交通运输管理提供有效的检测和监控手段,适用于相关政府交通管理部门,为道路基础设施规划和运营维护、交通控制和管理、交通组织设计提供决策支持信息。 [0015] The present invention can provide for urban traffic management and effective detection and monitoring instruments for the relevant government department of traffic management, road infrastructure for the planning and operation and maintenance, traffic control and management, traffic organization designed to provide decision support information. 同时本发明也可以为交通信息服务行业提供有效的实时交通信息,为实时动态导航、各种媒体的交通信息发布、车队调度管理、特种车辆调度管理提供交通信息源。 Meanwhile, the invention can also provide traffic information service industry effective real-time traffic information, real-time dynamic navigation, traffic information of various media release, fleet dispatch management, special vehicles scheduling management provides traffic information source.

[0016] 本发明的优点是:充分依托现有的移动通信网络资源,利用已有手机通信网络中的信息,即能在短时间完成城市内大范围的实时交通数据采集,同时初期投资相对较小、数据覆盖范围大、数据精度高。 [0016] advantages of the invention are: fully rely on the existing mobile communication network resources, use of information existing mobile communications network, that is able to perform real-time traffic data collection within the city a wide range in a short time, while the initial investment is relatively small, the data cover a large range, high accuracy data. 附图说明 BRIEF DESCRIPTION

[0017] 图1为本发明的总体流程图; [0017] FIG. 1 is a general flowchart of the present invention;

[0018] 图2为建立虚拟传感器网络流程图。 [0018] FIG 2 is a flowchart of the establishment of a virtual sensor network. 具体实施方式 Detailed ways

[0019] 以下结合实施例来具体说明本发明。 [0019] The following examples specifically described in conjunction with the present invention.

[0020] 实施例 [0020] Example

[0021] 本发明提供的一种基于手机信号数据检测交通状态的方法,步骤为: [0021] A mobile phone according to the present invention provides a signal based on the traffic state data detection method, the steps of:

[0022] 步骤1、建立虚拟传感器网络; [0022] Step 1, establishing a virtual sensor network;

[0023] 步骤1. 1、由实地测试得到虚拟传感器节点的位置及小区基站的序列,其中虚拟传感器节点定义为在无线网络与道路网络的交叉区域中因为手机网络信号变化而产生无线网络事件的点: [0023] Step 1.1, and the cell base sequence position sensor node by the virtual field test result, wherein the sensor node is defined as a virtual network because the phone is a wireless network signal change event is generated at the intersection area wireless network and a road network in point:

[0024] 步骤1. 1. 1、由测试车实施无线网络路测作业,实地采集得到指定路段上的Um接口的越区切换信息和位置更新信息以及路段上发生这些信息时测试车的具体位置,指定路段根据不同的实时交通信息的需要选取不同的范围,通常情况下,只要是允许车辆行驶的公共道路都可以; DETAILED position [0024] Step 1. 1.1, the test vehicle road test job wireless network embodiment, collected in the field to obtain the Um interface on a designated path, handoff location information and the update information and the link information generating these test vehicle , a designated path, select a different range according to the needs of different real-time traffic information, under normal circumstances, is allowed as long as the vehicle is traveling public roads can be;

[0025] 路段的定义是交通方面的常识,对于有红绿灯控制的地面道路而言,路段的定义是从一个红绿灯控制的交叉口到另一个相邻的红绿灯控制的交叉口,此类路段的长度通常在200米到600米;对于没有红绿灯控制的高速路或快速路而言,路段的选取是从一特殊点到另外一特殊点,此类特殊点为上下匝道与高速路或快速路交点、道路拐弯点、车道数突变点等,此类路段的长度通常在400米到800米; The definition of [0025] section of the common sense of transport, road traffic lights for ground control, the definition of road is a traffic light-controlled intersection from another adjacent to the traffic light controlled intersection, the length of these sections typically 200 m to 600 m; no traffic light control for highway or expressway, the segment are selected from a specific point to another particular point, such as a special point on the highway off-ramps or fast road intersections, length of road turning points, number of lanes, point mutations and the like, such sections typically 400 meters to 800 meters;

[0026] 步骤1. 1. 2、对通过步骤1. 1. 1得到的路测信息沿着道路方向将多次测量所得同一越区切换信息或者位置更新信息所对应的位置数据进行求均值得到所有虚拟传感器节点的位置; [0026] Step 1. 1.2, the way to the measurement information obtained by the step 1. 1.1 plurality of measurements along a path in the same direction resulting handoff location information or data corresponding to the location update information is obtained averaging All virtual position sensor node;

[0027] 步骤1. 1.3、由于虚拟传感器节点定义为在无线网络与道路网络的交叉区域中因为手机网络信号变化而产生无线网络事件的点,因此虚拟传感器节点信息包含小区切换或位置更新前后进出的小区信息,将所有虚拟传感器节点各自代表的前后进出小区罗列出来即得到小区基站的序列; [0027] Step 1. 1.3, since the virtual sensor node defined as a mobile phone network signals to generate a change point of the wireless network in the event of crossing area wireless network is a road network, so virtual sensor before and after the node information comprises a cell handover or location update out cell information, before and after each represent all virtual sensor nodes and out of the cell to obtain the sequence set out cell base station;

[0028] 步骤1. 2、根据步骤1. 1得到的虚拟传感器节点的位置,按路测采集的小区基站的序列分别将相邻的先后两个虚拟传感器节点作为虚拟传感器路段的起点和终点,建立虚拟传感器路段与虚拟传感器节点的对应关系,同时得到虚拟传感器路段的旅行方向; [0028] Step 1.2, according to the position of the virtual sensor nodes obtained in step 1.1, road test sequence by the cell base stations are collected adjacent virtual sensor has two sensor nodes as a virtual link starting and ending points, establishing a corresponding relationship with the virtual link virtual sensor nodes of the sensor while obtaining a virtual sensor link direction of travel;

[0029] 步骤1. 3、得到各虚拟传感器路段的长度并将虚拟传感器路段与道路网络相互匹配,根据虚拟传感器路段和道路网络路段的空间重叠关系与旅行方向的一致性来确定其与道路网络的对应关系,其中,道路网络路段是自带方向信息的; [0029] Step 1.3, to give each virtual link length sensor and a virtual sensor sections of the road network match each other, an overlapping relationship with the consistency of the direction of travel of the virtual space is determined according to the road network and road sensor sections of the road network which the correspondence relationship, wherein the direction of the road network link is carrying information;

[0030] 步骤1. 4、所有的虚拟传感器节点及虚拟传感器路段构成了虚拟传感器网络; [0031 ] 步骤2、以固定时间间隔T从手机网络获取该时间间隔内所有手机发出的实时信号数据; [0030] Step 1.4, all virtual nodes and virtual sensor sections of the sensor constitute a virtual sensor network; [0031] Step 2, at fixed time intervals T acquire real-time signal within the time interval data sent from all mobile phone the mobile phone network;

[0032] 通常的时间间隔采用2分钟或5分钟作为时间间隔。 [0032] The interval is typically a 2 or 5 minutes as the time interval. 假定系统起始时间是上午8:00AM,如果时间间隔是2分钟的话,则,接下去的第一个计算周期为上午8:00:00到8:01:59,然后依次是8:02:00-8:03:59,......9:42:00-9:43:59,......;如果时间间隔是5分钟的话,则,接下去的第一个计算周期为上午8:00:00到8:04:59,然后依次是8:05:00-8:09:59,......9:45:00-9:49:59,......。 The system assumes that the start time is 8:00 AM, if the time interval is 2 minutes, then, the first calculation of the next cycle 8:00:00 AM to 8:01:59, followed by a 8:02: 00-8: 03: 59, ...... 9:42: 00-9: 43: 59, ......; if the time interval is 5 minutes, then, the next first calculation 8:00:00 aM to 8:04:59 period, followed by 8: 05: 00-8: 09: 59, ...... 9:45: 00-9: 49: 59 .. ..... 依靠时间范围来约束采样的手机数量; Rely on time to constrain the number of mobile phone samples;

[0033] 步骤3、根据步骤2得到的第i部手机发出的实时信号数据中的基站标识号和位置区标识号通过步骤1建立的虚拟传感器网络地理译码得到该手机所在的虚拟传感器路段及该手机在虚拟传感器路段上的旅行速度Vi : [0033] Step 3, the virtual sensor network real-time geo-coding signal data obtained in step 2 of the i-th unit in the mobile phone base station emits an identification number and the location area identification number established by the virtual sensor sections obtained in step 1 of the mobile phone is located and the phone on the virtual sensor section of the travel speed Vi:

[0034] 步骤3. 1、根据第i部手机发出的实时信号数据中的基站标识号和位置区标识号得到相匹配的两个虚拟传感器节点及经过这两个虚拟传感器节点的时间戳,经过第一个虚拟传感器节点的时间戳为、,经过第二个虚拟传感器节点的时间戳为t2 ; [0034] Step 3.1, to give two matched nodes and virtual sensor timestamps via two virtual real-time sensor node according to the data signal emitted by the i-phone base station identification number and the location area identification number, after the first time stamp to ,, virtual sensor node through the second virtual sensor nodes stamp is T2;

[0035] 步骤3. 2、通过虚拟传感器路段与虚拟传感器节点的对应关系将步骤3. 1中得到的第i部手机先后经过的虚拟传感器节点分别匹配至各个虚拟传感器路段,得到该手机所在的虚拟传感器路段,并由常规的几何公式计算得到虚拟传感器路段的长度d ; [0035] Step 3.2, the correspondence between the virtual sensor link virtual sensor node obtained in Step 3.1 of the i-th virtual phone has passed the sensor nodes are matched to each virtual sensor sections, to give the handset is located virtual sensor sections by a conventional geometric formulas calculated virtual sensor segment length D;

[0036] 步骤3. 3、第i部手机在虚拟传感器路段上的旅行速度Vi = (!/(Vt1); [0036] Step 3.3, the i-phone travel speed in the virtual sensor sections Vi = (/ (Vt1)!;

[0037] 步骤4、从道路网络数据库中读取道路网络的电子地图信息,将步骤3得到的虚拟传感器路段叠加在道路网络上,得到第i部手机所在的道路网络路段,并且该手机在道路网络路段上的旅行速度Vi = Vi ; [0037] Step 4, the road network is read from the road map database and network information, obtained in step 3 is superimposed on the virtual sensor link road network, road network link to obtain the i-th portion located phone, and the phone in the road travel speed on the network section of Vi = Vi;

[0038] 由于在建立虚拟传感器网络时已经确立了虚拟传感器路段和道路网络路段的对应关系,因此根据上述确立的关系即可完成叠加; [0038] Since the establishment of a virtual sensor network has established a correspondence relationship between the virtual sensor network links and sections a road, based on the relationship thus established to complete the above-described superposition;

[0039] 步骤5、重复步骤3及步骤4直至收集到时间间隔T内所有可能采样到的手机所在η的道路网络路段信息,即得到每条道路网络路段上的手机个数η及旅行速度V,V=ΣVi /n 若在某条道路网络路段上没有收集到任何手机所发出的实时信号数据,则通过下列公式计算得到该条道路网络路段上的旅行速度ν : [0039] Step 5 Repeat step 3 and step 4 until the time the collected information in the road network segment T η of all possible sample interval where the phone, the phone number that is obtained on each road network and link travel speed V [eta] , V = ΣVi / n if not collected on certain road network data link to any real-time signal emitted by the phone, then the calculated speed of travel of the strip on the road network segment by the following equation ν:

[0040] V = eXV(up)+fXV(down),e、f为根据历史数据训练得到的相关度因子,且e+f =1,V(up)为与该路段相邻上游路段的旅行速度,V(down)为与该路段相邻下游路段的旅行速度,上下游是一个相对的概念,上下游关系是由道路的实际地理位置分布和旅行方向来决定的。 [0040] V = eXV (up) + fXV (down), e, f is the factor according to the related historical training data obtained, and e + f = 1, V (up) adjacent to the upstream section of the link travel velocity, V (down) for the travel speed of the adjacent downstream segment of the road, the upstream and downstream is a relative concept, the upstream and downstream relationship is geographically distributed and the actual travel direction of the road determined. 每一个计算周期步骤五完成的是对所有道路网络路段旅行速度的计算,所以上下游的速度也即为已知。 Step five each calculation cycle is completed for all the road network is calculated link travel speed, so the speed is the known downstream. [0041 ] 步骤6、根据步骤5得到的每条道路网络路段上的手机个数η及旅行速度V计算得到时间间隔τ内的交通流密度K和路段交通流量Q : [0041] Step 6, η and the calculated travel velocity V of traffic density within a time interval of τ K and Q according to the number of phone link traffic on each link road network obtained in step 5:

[0042] 步骤6. 1、交通流密度K = AX BX NX EXP (-Β/Ν),其中,K为需要估计的路段交通流密度,N为通过步骤5得到的手机个数n,A和B为由历史数据训练所得的系统模型参数; [0042] Step 6.1, traffic density K = AX BX NX EXP (-Β / Ν), where, K is to be estimated road traffic flow density, N is the number of the mobile phone through n obtained in step 5, A, and B is a training system model parameters obtained historical data;

[0043] 步骤6. 2、路段交通流量Q = KXV,其中,K为通过步骤6. 1得到的交通流密度,V 为通过步骤5得到的旅行速度; [0043] Step 6.2, road traffic Q = KXV, wherein, K is obtained in step 6.1 of traffic density, V is the traveling speed obtained by the step 5;

[0044] 步骤7、根据不同道路类别交通流参数的时变特征,建立相应的交通流参数预测模型: [0044] Step 7 The different road types varying characteristics of traffic flow parameters, the traffic flow to establish the corresponding parameter prediction model:

[0045] 步骤7. 1、按照步骤2所述的时间间隔T将一天划分为Μ/Τ个时间段,建立路段旅行速度线性预测模型: [0045] Step 7.1, according to the time interval T of step 2 is divided into the day with Μ / Τ time period, establishing the link travel speed of the linear prediction model:

[0046] V(k+1) = aXV(k)+bXV(kl)+cXV(k_2) +dXV(k_3), [0046] V (k + 1) = aXV (k) + bXV (kl) + cXV (k_2) + dXV (k_3),

[0047] 其中,a、b、c、d为相关度因子,根据历史数据训练得到,且a+b+c+d= l,a>=b >=c >= d,k+l为待预测时间段编号,V(k+1)为待预测时间段k+1的旅行速度,V(k)为通过步骤5得到的待预测时间段k+Ι的前一个时间段的旅行速度,V(kl)为通过步骤5得到的待预测时间段k+Ι的前二个时间段的旅行速度,V(k-2)为通过步骤5得到的待预测时间段k+Ι的前三个时间段的旅行速度,V(k-3)为通过步骤5得到的待预测时间段k+1的前四个时间段的旅行速度; [0047] wherein, a, b, c, d is the correlation factor, based on historical data is trained, and a + b + c + d = l, a> = b> = c> = d, k + l is to be predicted time segment number, V (k + 1) is to be predicted time period k + travel speed 1, V (K) is to be predicted time period k + traveling speed Ι previous period of time at step 5 was, V (kl to) the speed of travel through the first two time periods to be predicted period k + Ι obtained in step 5, V (k-2) to be predicted for the first three time period k + Ι obtained by step 5 travel speed segments, V (k-3) is a time period to be predicted travel speed of the front four k + period by 1 step 5;

[0048] 步骤7. 2、建立路段交通流密度线性预测模型: [0048] Step 7.2, the establishment of road traffic flow density linear prediction model:

[0049] K (k+1) = a XK (k) +b XK (k-1) +c XK (k-2) +d XK (k-3), [0049] K (k + 1) = a XK (k) + b XK (k-1) + c XK (k-2) + d XK (k-3),

[0050] 其中,a、b、c、d为相关度因子,根据历史数据训练得到,且a+b+c+d = l,a>=b >=c >= d, k+1为待预测时间段编号;K(k+Ι)为待预测时间段k+1的交通流密度;K(k) 为通过步骤6得到的待预测时间段k+1的前一个时间段的交通流密度;[0051] K(kl)为通过步骤6得到的待预测时间段k+Ι的前二个时间段的交通流密度; [0050] wherein, a, b, c, d is the correlation factor, based on historical data is trained, and a + b + c + d = l, = b = c a>>> = d, k + 1 to be predicted time segment number; K (k + Ι) to be predicted time period k + traffic density 1; K (k) for the k + traffic density before a period to be predicted period of step 6 was 1 ; [0051] K (kl) through two traffic density before the predicted period of time to be obtained in step 6 of k + Ι;

[0052] K(k-2)为通过步骤6得到的待预测时间段k+Ι的前三个时间段的交通流密度; [0052] K (k-2) is the traffic density for the first three periods of the time period to be predicted by the k + Ι step 6;

[0053] K(k-3)为通过步骤6得到的待预测时间段k+Ι的前四个时间段的交通流密度。 [0053] K (k-3) is the density of the traffic to be predicted by the time step k + Ι 6 obtained in the first four time periods.

[0054] 步骤7. 3、建立路段交通流流量预测模型: [0054] Step 7.3, the establishment of road traffic prediction model of traffic flow:

[0055] Q(k+1) = V(k+1) XK(k+l) [0055] Q (k + 1) = V (k + 1) XK (k + l)

[0056] 其中,Q(k+1)为待预测时间段k+Ι的交通流流量,V(k+1)为步骤7. 1所得的待预测时间段k+Ι的交通速度,V(k+1)为步骤7. 2所得的待预测时间段k+Ι的交通速度。 [0056] wherein, Q (k + 1) is predicted to be the time period k + iota the traffic flow, V (k +. 1) is obtained in step 7.1 k + iota traffic speed period to be predicted, V ( k + 1) step 7.2 is predicted to be obtained in time period k + Ι speed of traffic.

[0057] 例如在某一路段RLl (RLl的长度为800m)对应三个虚拟传感器路段VLl、VL2及VL3,其对应关系如下表所示: [0057] For example, in a RLL link (800 - meter length of RLL) corresponding to the three sections of virtual sensors VLl, VL2 and VL3, the corresponding relation shown in the following table:

[0058] [0058]

Figure CN101510357BD00091

[0059] 设在该路段上有四部手机,则将手机信号匹配到虚拟传感器节点后得到下表: [0059] provided on the rear segment has four phone, then the phone signal is matched to the virtual sensor node obtained the following table:

[0060] [0060]

Figure CN101510357BD00092

[0061] 根据表1中的对应关系,可以计算得到各虚拟传感器路段对应的手机样本的旅行时间及旅行速度,如表2所示; [0061] According to the correspondence table 1, the sample can be calculated phone travel time and travel speed of each link corresponding to the virtual sensor, as shown in Table 2;

[0062] 表1 :虚拟传感器路段与虚拟传感器节点对应表 [0062] Table 1: Virtual sensor link correspondence table of the virtual sensor node

[0063] [0063]

Figure CN101510357BD00101

[0064] 表2 :各手机样本旅行时间及旅行速度计算结果,并匹配到各虚拟传感器路段 [0064] Table 2: Sample the mobile phone travel time and travel speed results, and matched to the respective virtual sensor link

[0065] [0065]

Figure CN101510357BD00111

[0066] 由上表可知,这四个手机样本均为路段RLl的样本,则: [0066] From the above table shows, these four samples are sample sections RLl phone, then:

[0067]路段 RLl 的估计旅行速度为:(36+34. 29+32. 14+34. 11)/4 = 34. 13(公里/ 小时); [0067] RLl link travel speed is estimated: (36 + 32 + 14 + 34 29 34 11...) / 4 = 34.13 (km / h);

[0068] 路段RLl的估计旅行时间为:3. 6X800/¾. 13 = 84. 4(秒); [0068] RLl segment estimated travel time: 3 6X800 / ¾ 13 = 84. 4 (seconds);.

[0069] 计算得到路段旅行速度和有效手机样本数量之后,根据交通流模型,可进一步得到其它交通流参数。 After [0069] the link travel speed is calculated and the number of effective samples mobile phone, according to traffic flow model, can be further other traffic flow parameters.

[0070] 如可建立路段交通流密度与有效样本数量的函数关系如下:K = AXBXNXEXP(-B/N),其中,K——需要估计的路段交通流密度,N——指手机样本数量,A, B——系统模型参数,由历史数据训练所得,在本例中A = 0. 2,B = 5,N = 4,则,路段估计交通流密度为:K = 0. 2X5X4XEXP(-l/4) = 12. 5 (辆车/每公里每车道)。 [0070] As can be established with an effective amount of traffic density function of the sample segment follows: K = AXBXNXEXP (-B / N), where, the estimated road traffic K-- required current density, the N-- phone refers to the number of samples, A, B-- system model parameters, resulting from the historical training data, in this embodiment, A = 0. 2, B = 5, N = 4, then, the estimated road traffic density: K = 0. 2X5X4XEXP (-l / 4) = 12.5 (cars / per kilometer per lane).

[0071] 再根据交通流三参数流量、密度及速度之间的关系:Q = KXV,则,路段估计交通流量为:Q = 12. 5X34. 20 = 426 (辆车/每小时每车道),预测下一时间段的旅行速度为: 0.4X34. 2+0.3X36. 4+0.2X37. 1+0. 1 X 39. 9 = 36. 01 (公里/ 小时)。 [0071] and then according to the relationship between the three-parameter flow traffic flow, density and speed: Q = KXV, then, road traffic is estimated as: Q = 12. 5X34 20 = 426 (vehicles / hour per lane). He predicted travel speed for the next time period:.... 0.4X34 2 + 0.3X36 4 + 0.2X37 1 + 0 1 X 39. 9 = 36. 01 (km / h).

Claims (8)

1. 一种基于手机信号数据检测交通状态的方法,其特征在于,步骤为: 步骤1、建立虚拟传感器网络;步骤2、以固定时间间隔T从手机网络获取该时间间隔内所有手机发出的实时信号数据;步骤3、根根据步骤2得到的第i部手机发出的实时信号数据中的基站标识号和位置区标识号通过虚拟传感器网络地理译码得到该手机所在的虚拟传感器路段及在该虚拟传感器路段上的旅行速度Vi ;步骤4、从道路网络数据库中读取道路网络的电子地图信息,将步骤3得到的虚拟传感器路段叠加在道路网络上,得到第i部手机所在的道路网络路段,令该手机在道路网络路段上的旅行速度Vi = Vi;步骤5、重复步骤3及步骤4直至收集到时间间隔T内所有可能采样到的手机所在的道路网络路段,即得到每条道路网络路段上的手机个数η及每条道路网络路段的旅行速度V,V=叙/… 1=\步骤6 A cell phone data detection signal based on the traffic state, wherein the following steps: Step 1, establishing a virtual sensor network; Step 2, to obtain a fixed time interval T for all real-time within the time interval from the cellular network phone emitted signal data; step 3, to give the root segment of the virtual sensor is located by the virtual sensor phone network base station identification number in accordance with geo-coding live signal data obtained in step 2 i-phone and sent in the location area identification number and the virtual Travel speed sensors on the road Vi; step 4, read electronic map information of the road network from the road network database from step 3 virtual sensor section superimposed on the road network, road network roads to get where i-phone unit, enabling the phone to travel on the road network segment velocity of Vi = Vi; step 5 repeat step 3 and step 4 until the time interval to collect all possible sample to the road network segment where the mobile phone T, which exposes the network to give each road segment η phone number on each road network and road travel speed V, V = Syria / ... 1 = \ step 6 根据每条道路网络路段上的手机个数η及旅行速度V计算得到时间间隔T内的交通流密度K和路段交通流量Q。 The phone number of the road network on each link and η calculated travel velocity V of traffic density K and the link traffic within the time interval T Q.
2.如权利要求1所述的一种基于手机信号数据检测交通状态的方法,其特征在于,包括:步骤7、根据不同道路类别交通流参数的时变特征,建立相应的交通流参数预测模型。 2. one of the claims 1 phone signal data detection method based on the traffic state, characterized by comprising: a step 7, according to different road class change feature parameters traffic flow, traffic flow to establish the appropriate parameter prediction model .
3.如权利要求1所述的一种基于手机信号数据检测交通状态的方法,其特征在于,所述步骤1包括:步骤1. 1、由实地测试得到虚拟传感器节点的位置及小区基站的序列,其中虚拟传感器节点定义为在无线网络与道路网络的交叉区域中因为手机网络信号变化而产生无线网络事件的点;步骤1. 2、根据步骤1. 1得到的虚拟传感器节点的位置,按路测采集的小区基站的序列分别将相邻的先后两个虚拟传感器节点作为虚拟传感器路段的起点和终点,建立虚拟传感器路段与虚拟传感器节点的对应关系,同时得到虚拟传感器路段的旅行方向;步骤1. 3、得到各虚拟传感器路段的长度并将虚拟传感器路段与道路网络路段相互匹配,根据虚拟传感器路段和道路网络路段的空间重叠关系与旅行方向的一致性来确定其与道路网络的对应关系;步骤1. 4、所有的虚拟传感器节点及 3. one of the claims 1 phone signal data detection method based on the traffic state, wherein said step 1 includes: a step, the sequence obtained from field testing virtual sensor nodes and the cell base station location 1.1 wherein the virtual sensor signal is the mobile phone network nodes defined as a change point of the wireless network events generated at the intersection area wireless network is a road network; step 1.2, according to the position of the virtual sensor nodes obtained in step 1.1, by way measuring the collected cell base sequences respectively have two adjacent nodes as a virtual sensor start and end sections of the virtual sensor, the sensor link correspondence between the virtual and the virtual sensor nodes simultaneously obtain virtual sensor link direction of travel; step 1 3, to give each virtual link length sensor and a virtual sensor sections of a road network sections matched to each other, overlapping relationship with the consistency of the direction of travel to determine the correspondence between the virtual space according to the road network and the sensor sections of the road network segment; step 1.4, and all virtual sensor nodes 拟传感器路段构成了虚拟传感器网络。 Quasi sensor sections constitute virtual sensor network.
4.如权利要求3所述的一种基于手机信号数据检测交通状态的方法,其特征在于,所述步骤1. 1包括:步骤1. 1. 1、由测试车实施无线网络路测作业,实地采集得到指定路段上的接口的越区切换信息和位置更新信息以及路段上发生这些信息时测试车的具体位置;步骤1. 1. 2、对通过步骤1. 1. 1得到的路测信息沿着道路方向将多次测量所得同一越区切换信息或者位置更新信息所对应的位置数据进行求均值得到所有虚拟传感器节点的位置;步骤1. 1. 3、将所有虚拟传感器节点各自代表的前后进出小区罗列出来即得到小区基站的序列。 4. An method according to claim 3 phone signal traffic state based on the detection data, wherein said step 1.1 comprises the steps of: 1. 1.1, the test vehicle road test operations wireless network embodiment, collected in the field to obtain the specified interface link handoff location information and the specific location update information and the link information generating these test car; step 1. 1.2, passage of the measurement information obtained in step 1. 1.1 step 1. 1.3 before and after, all the nodes each representing a virtual sensor; direction along the road of the same plurality of measurements resulting handoff message or a location update the location data corresponding to the position information obtained averaging all virtual sensor nodes set out to obtain a cell out of a cell of the base station sequence.
5.如权利要求3所述的一种基于手机信号数据检测交通状态的方法,其特征在于,所述步骤3包括:步骤3. 1、根据第i部手机发出的实时信号数据中的基站标识号和位置区标识号得到相匹配的两个虚拟传感器节点及经过这两个虚拟传感器节点的时间戳,经过第一个虚拟传感器节点的时间戳为、,经过第二个虚拟传感器节点的时间戳为t2 ;步骤3. 2、通过步骤1. 2建立起的虚拟传感器路段与虚拟传感器节点的对应关系将步骤3. 1中得到的第i部手机先后经过的虚拟传感器节点分别匹配至各个虚拟传感器路段, 得到该手机所在的虚拟传感器路段,并由常规的几何公式计算得到虚拟传感器路段的长度d;步骤3. 3、虚拟传感器路段的旅行速度Vi = (!/(Vt1)。 5. one of the phone signal to claim 3, data detection method based on traffic condition, wherein said step 3 comprises: step 3.1, real-time signal in accordance with data transmitted in the i-phone base station identity number and the location area identification number matches the obtained two virtual sensor nodes and sensor nodes through two virtual time stamp, the time stamp via the first node is a virtual sensor ,, sensor node through the second virtual timestamp is T2; step 3.2, step 1.2 to establish a link virtual sensor correspondence between the virtual sensor node obtained in step 3.1 of the i-th virtual phone has passed the sensor nodes are matched to each virtual sensor link, the phone link to obtain a virtual sensor is located, by a conventional geometric formulas calculated virtual sensor segment length D;! step 3.3, virtual sensor link travel speed Vi = (/ (Vt1).
6.如权利要求1所述的一种基于手机信号数据检测交通状态的方法,其特征在于,所述步骤6包括:步骤6. 1、交通流密度K = AXBXNXEXP(-B/N),其中,K为需要估计的路段交通流密度,N为通过步骤5得到的手机个数n,A和B为由历史数据训练所得的系统模型参数;步骤6. 2、路段交通流量Q = KXV,其中,K为通过步骤6. 1得到的交通流密度,V为通过步骤5得到的旅行速度。 6. one of the claims 1 phone signal data detection method based on the traffic state, wherein said step 6 includes: Step 6.1, traffic density K = AXBXNXEXP (-B / N), wherein , K is to be estimated road traffic flow density, N is the historical data by training the system model parameters obtained phone number through n obtained in step 5, a and B; step 6.2, road traffic Q = KXV, wherein , K is obtained in step 6.1 of traffic density, V is the traveling speed obtained in step 5.
7.如权利要求2所述的一种基于手机信号数据检测交通状态的方法,其特征在于,所述步骤7包括:步骤7. 1、按照步骤2所述的时间间隔T将一天划分为M/T个时间段,建立路段旅行速度线性预测模型:V(k+1) = aXV(k)+bXV(kl)+cXV(k_2) +dXV(k_3),其中,a、b、c、d为相关度因子,根据历史数据训练得到,且a+b+c+d= l,a>=b > = c >= d,k+1为待预测时间段编号,V(k+1)为待预测时间段k+1的旅行速度,V(k)为通过步骤5得到的待预测时间段k+Ι的前一个时间段的旅行速度,V(kl)为通过步骤5得到的待预测时间段k+Ι的前二个时间段的旅行速度,V(k-2)为通过步骤5得到的待预测时间段k+Ι的前三个时间段的旅行速度,V(k-3)为通过步骤5得到的待预测时间段k+1的前四个时间段的旅行速度;步骤7. 2、建立路段交通流密度线性预测模型: K (k+1) = a XK (k) +b XK (k-1) +c XK (k-2) +d XK (k_3),其中,a、b、c、d为 7. The one of the claim 2, Mobile data detection signal based on the traffic state, wherein said Step 7 comprises: Step 7.1, the second step in a time interval T is divided into the day with M / T time period, the establishment of the link travel speed of the linear prediction model: V (k + 1) = aXV (k) + bXV (kl) + cXV (k_2) + dXV (k_3), wherein, a, b, c, d relevant factor, based on historical data is trained, and a + b + c + d = l, a> = b> = c> = d, k + 1 is a predicted time period to be numbers, V (k + 1) is be the predicted time period k + travel speed 1, V (k) through step 5 to be predicted period k + traveling speed before a period Ι of, V (kl) to be the predicted time at step 5 to give the k + segment travel speed of the first two periods of Ι, V (k-2) to be predicted by the time step k + 5 obtained travel speed of the front of the three time periods Ι, V (k-3) is by k + traveling speed of the previous four periods of the time period to be predicted 1 step 5; a step 7.2, road traffic density for establishing a linear predictive model: K (k + 1) = a XK (k) + b XK (k-1) + c XK (k-2) + d XK (k_3), wherein, a, b, c, d is 相关度因子,根据历史数据训练得到,且a+b+c+d = l,a > = b > = c >=d,k+l为待预测时间段编号;K(k+Ι)为通过步骤6得到的待预测时间段k+1的交通流密度;K(k)为通过步骤6得到的待预测时间段k+1的前一个时间段的交通流密度;K(k-1) 为通过步骤6得到的待预测时间段k+1的前二个时间段的交通流密度;K(k-2)为通过步骤6得到的待预测时间段k+Ι的前三个时间段的交通流密度;K(k-3)为通过步骤6得到的待预测时间段k+Ι的前四个时间段的交通流密度; 步骤7. 3、建立路段交通流流量预测模型: Q (k+1) = V (k+1) XK (k+1),其中,Q (k+1)为待预测时间段k+Ι的交通流流量,V (k+1)为步骤7. 1所得的待预测时间段k+Ι的交通速度,V(k+1)为步骤7. 2所得的待预测时间段k+Ι的交通速度。 Correlation factor, based on historical data is trained, and a + b + c + d = l, a> = b> = c> = d, k + l is to be predicted period number; K (k + Ι) through step 6 to be predicted period k + traffic density 1; K (k) through step 6 to be predicted period k + traffic density before a period of 1; K (k-1) is by traffic density k obtained in step 6 to be predicted period of the first two periods + 1; K (k-2) through the first three periods of the traffic to be predicted period k + iota obtained in step 6 current density; K (k-3) to the prediction time period to be obtained in step 6 k + Ι traffic flow before the four time periods density; step 7.3, road traffic flow to establish prediction model: Q (k + 1) = V (k + 1) XK (k + 1), wherein, Q (k + 1) is the traffic flow k + Ι period to be predicted, V (k + 1) is obtained in step 7.1 be the predicted time period k + Ι transport velocity, V (k + 1) step 7.2 is predicted to be obtained in time period k + Ι speed of traffic.
8.如权利要求1至7中任一项所述的一种基于手机信号数据检测交通状态的方法,其特征在于,在进行步骤5时,若在某条道路网络路段上没有收集到任何手机所发出的实时信号数据,则通过下列公式计算得到该条道路网络路段上的旅行速度V :V = eXV(up)+fXV(down),e、f为根据历史数据训练得到的相关度因子,且e+f = 1, V(up)为与该路段相邻上游路段的旅行速度,V(down)为与该路段相邻下游路段的旅行速度。 8. 1-1 kinds of phone signal based on one of the traffic status data detection method of any of claims 7, wherein the 5, if not collected in the step of performing a road link to any phone network real-time data signal emitted, the calculated travel velocity V on the piece of road network link by the following formula: V = eXV (up) + fXV (down), e, f is the correlation factor based on the historical training data, and e + f = 1, V (up) for the travel speed of the upstream segment and the adjacent segment, V (down) for the travel speed of the downstream segment is adjacent to the road.
CN 200910048300 2009-03-26 2009-03-26 Method for detecting traffic state based on mobile phone signal data CN101510357B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 200910048300 CN101510357B (en) 2009-03-26 2009-03-26 Method for detecting traffic state based on mobile phone signal data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 200910048300 CN101510357B (en) 2009-03-26 2009-03-26 Method for detecting traffic state based on mobile phone signal data

Publications (2)

Publication Number Publication Date
CN101510357A CN101510357A (en) 2009-08-19
CN101510357B true CN101510357B (en) 2011-05-11

Family

ID=41002747

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 200910048300 CN101510357B (en) 2009-03-26 2009-03-26 Method for detecting traffic state based on mobile phone signal data

Country Status (1)

Country Link
CN (1) CN101510357B (en)

Families Citing this family (45)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102262819B (en) * 2009-10-30 2014-10-15 国际商业机器公司 Based on the method and apparatus of a mobile communication network in real time to determine the transit time of a road
CN101794516B (en) 2009-12-25 2011-11-23 北京工业大学 Mobile phone information based section speed calculation method
CN102136192B (en) * 2011-01-31 2013-04-24 上海美慧软件有限公司 Method for identifying trip mode based on mobile phone signal data
US20130176433A1 (en) * 2011-01-31 2013-07-11 Ntt Docomo, Inc. Unique-terminal-count estimation device and unique-terminal-count estimation method
CN102157070B (en) * 2011-03-31 2013-01-09 天津大学 Road traffic flow prediction method based on cell phone data
CN102214395B (en) * 2011-05-13 2013-07-31 天津大学 Road traffic flow monitoring method considering privacy protection
CN102332210B (en) * 2011-08-04 2013-09-18 东南大学 Method for extracting real-time urban road traffic flow data based on mobile phone positioning data
CN103124411B (en) * 2011-11-18 2017-06-20 中国移动通信集团内蒙古有限公司 Evaluation Method and system for road network, road users and matching module
CN102521984A (en) * 2011-12-31 2012-06-27 北京世纪高通科技有限公司 Method and device for acquiring real-time traffic information of road
CN102609616A (en) * 2012-01-29 2012-07-25 上海美慧软件有限公司 Dynamic population distribution density detecting method based on mobile phone positioning data
CN103325247B (en) * 2012-03-19 2015-07-01 中国移动通信集团辽宁有限公司 Method and system for processing traffic information
JP5605918B2 (en) * 2012-03-29 2014-10-15 株式会社デンソーアイティーラボラトリ Traffic data prediction device, traffic data prediction method and a computer program
CN102629418B (en) * 2012-04-09 2014-10-29 浙江工业大学 Traffic Flow Forecasting Method Based on Fuzzy Kalman Filter
CN104376718A (en) * 2012-06-19 2015-02-25 张家港市鸿嘉数字科技有限公司 Remote intelligent monitoring method for real-time traffic status
CN102708689B (en) * 2012-06-19 2014-10-08 张家港市鸿嘉数字科技有限公司 A real-time traffic monitoring system
CN102722984B (en) * 2012-06-19 2015-01-28 张家港市鸿嘉数字科技有限公司 Real-time road condition monitoring method
CN102737510B (en) * 2012-07-03 2014-05-21 浙江大学 Real-time traffic condition acquisition method based on mobile intelligent terminal
TWI485665B (en) * 2012-07-09 2015-05-21 Ind Tech Res Inst Method and system for estimating traffic information using integration of location update and call events
CN102968903A (en) * 2012-12-18 2013-03-13 江南大学 Consciousness-participation-free traffic flow real-time monitoring system
CN103093625B (en) * 2013-01-09 2015-01-14 杭州师范大学 City road traffic condition real-time estimation method based on reliability verification
CN103415038A (en) * 2013-01-16 2013-11-27 郭锋 Method for collecting and recording mobile phone signals and apparatus
CN103116990B (en) * 2013-01-18 2015-05-20 西南交通大学 Traffic speed vehicle-mounted acquisition system and method based on mobile phone switch position
CN103426309B (en) * 2013-07-29 2015-05-13 吉林大学 Method of judging level of traffic jam according to taxi running conditions
CN103606279B (en) * 2013-11-27 2016-05-18 中国航天系统工程有限公司 A road trip mode smartphone-based identification method and system
CN103778784B (en) * 2013-12-31 2016-06-15 上海云砥信息科技有限公司 Obtaining state highway road traffic information in real time phone-based data methods
CN104112361B (en) * 2014-04-25 2016-08-31 浙江大学 Road network traffic bottlenecks and recognition often made occasional bottlenecks
CN104200667B (en) * 2014-09-19 2016-07-27 上海美慧软件有限公司 A traffic jam mobile phone signals detection based on hierarchical data
CN104318770B (en) * 2014-11-02 2017-02-01 上海云砥信息科技有限公司 Real-time detection method for mobile phone data highway traffic congestion based on the state
CN104408917B (en) * 2014-11-18 2016-08-24 浙江工商大学 Real-time traffic estimation method based smartphone accelerometer
CN104408923B (en) * 2014-12-03 2018-01-26 百度在线网络技术(北京)有限公司 Traffic State Evaluation Method and apparatus
CN104599499B (en) * 2015-01-12 2017-08-29 北京中交兴路车联网科技有限公司 A distributed statistical traffic location method and apparatus
CN104978858B (en) * 2015-06-15 2017-12-22 北京拓明科技有限公司 Highway monitoring method based on real-time traffic signaling cell phone
CN105006149B (en) * 2015-07-10 2017-07-21 信融源大数据科技(北京)有限公司 Iterative method to estimate the dynamic traffic and road conditions
CN105117789A (en) * 2015-07-29 2015-12-02 西南交通大学 Resident trip mode comprehensive judging method based on handset signaling data
CN105608890B (en) * 2015-09-08 2017-11-03 上海美慧软件有限公司 Phone signal data based on staff travel parametric statistical method
CN105303831A (en) * 2015-10-20 2016-02-03 四川公用信息产业有限责任公司 Method for determining congestion state of highway based on communication data
CN105491532B (en) * 2015-11-25 2019-07-12 交科院(北京)交通技术有限公司 A kind of mobile phone SIP signaling filtering method and apparatus for road network running state analysis
CN105679019B (en) * 2016-01-28 2019-01-01 广州杰赛科技股份有限公司 A kind of road traffic state recognition methods and device
CN105702019B (en) * 2016-04-12 2018-01-02 东南大学 A method for obtaining Urban Activity of the road speed limit value method
CN106504524B (en) * 2016-09-14 2019-02-26 杭州诚智天扬科技有限公司 A method of express highway section is divided based on mobile signaling protocol dynamic
CN106530693B (en) * 2016-11-02 2019-02-05 浙江大学 Urban expressway traffic state based on fused data rolls estimation method
CN106781479B (en) * 2016-12-23 2019-03-22 重庆邮电大学 A method of highway operating status is obtained based on mobile phone signaling data in real time
CN106991815A (en) * 2017-05-23 2017-07-28 招商局重庆交通科研设计院有限公司 Traffic jam control method
CN107172215B (en) * 2017-07-18 2018-03-02 吉林大学 Future vehicle driving conditions under networked environment information acquisition method
CN108171968A (en) * 2017-11-29 2018-06-15 江苏速度信息科技股份有限公司 System and method for road condition analysis based on position data of mobile terminal signaling

Also Published As

Publication number Publication date
CN101510357A (en) 2009-08-19

Similar Documents

Publication Publication Date Title
Bar-Gera Evaluation of a cellular phone-based system for measurements of traffic speeds and travel times: A case study from Israel
Schäfer et al. A traffic information system by means of real-time floating-car data
Mathur et al. Parknet: drive-by sensing of road-side parking statistics
De Fabritiis et al. Traffic estimation and prediction based on real time floating car data
JP4733251B2 (en) Method and system for data acquisition using the position of the road network and the matched mobile phone
US7433889B1 (en) Method and system for obtaining traffic sign data using navigation systems
An et al. A survey of intelligent transportation systems
Yim et al. Investigation of vehicles as probes using global positioning system and cellular phone tracking: field operational test
US20020107634A1 (en) Traffic monitoring system and method
Caceres et al. Review of traffic data estimations extracted from cellular networks
Gong et al. A GPS/GIS method for travel mode detection in New York City
US9958280B2 (en) Assessing inter-modal passenger travel options
Qureshi et al. A survey on intelligent transportation systems
Sun et al. Predicting bus arrival time on the basis of global positioning system data
JP4657728B2 (en) Apparatus and method for providing traffic information
US8918278B2 (en) Method and system for modeling and processing vehicular traffic data and information and applying thereof
Tao et al. Real-time urban traffic state estimation with A-GPS mobile phones as probes
Li et al. Performance evaluation of vehicle-based mobile sensor networks for traffic monitoring
Boyce et al. Design and implementation of ADVANCE: The Illinois dynamic navigation and route guidance demonstration program
Reynolds et al. Development of an emissions inventory model for mobile sources
EP1177508A2 (en) Apparatus and methods for providing route guidance for vehicles
Lin et al. A review of travel-time prediction in transport and logistics
WO2007061734A2 (en) Vehicle information systems and methods
CN102576491A (en) Traffic routing using intelligent traffic signals, GPS and mobile data devices
Hamilton et al. The evolution of urban traffic control: changing policy and technology

Legal Events

Date Code Title Description
C06 Publication
C10 Request of examination as to substance
C14 Granted
ASS Succession or assignment of patent right

Owner name: SHANGHAI MEIHUI SOFTWARE INC.

Free format text: FORMER OWNER: MEIHUI INFORMATION TECHNOLOGY (SHANGHAI) CO., LTD.

Effective date: 20110901

C41 Transfer of the right of patent application or the patent right