CN103903422A - Multi-source traffic information fusion method - Google Patents
Multi-source traffic information fusion method Download PDFInfo
- Publication number
- CN103903422A CN103903422A CN201210567492.3A CN201210567492A CN103903422A CN 103903422 A CN103903422 A CN 103903422A CN 201210567492 A CN201210567492 A CN 201210567492A CN 103903422 A CN103903422 A CN 103903422A
- Authority
- CN
- China
- Prior art keywords
- information
- type
- traffic information
- traffic
- transport information
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention provides a multi-source traffic information fusion method which comprises the following steps: all kinds of traffic information is preprocessed and is on a unified processing road network; the preprocessed traffic information is fused in a weighting method, and road sections without traffic information coverage after fusion are filled to form complete traffic information; and the complete traffic information is generated and released according to a standard position. According to the invention, floating car traffic information is fused with non-structured traffic information such as micro-blog information, event information, traffic website information and the like, and historical traffic information is used as a data source and fused with real-time traffic information based on the rules of the historical traffic information.
Description
Technical field
The present invention relates to intelligent transportation field, particularly a kind of fusion method of multi-source traffic information.
Background technology
At intelligent transportation field, real-time dynamic information service can provide efficient feasible traffic guidance and trip planning information for Public Traveling, communications and transportation etc., saves time, reduces costs and the object such as low-carbon environment-friendly thereby reach.At present, in city, traffic-information service can be traffic control department provides the foundation of traffic control and management, for the roading department road equipment of making rational planning for provides reference frame, reach the object of alleviating traffic congestion, energy-saving and emission-reduction, and day by day deeply and affect people's trip life.
The equipment that can be used as at present traffic information collection mainly contains Floating Car collection, inductive coil detecting device, video detector, traffic signal controlling machine, electronic police and Gate System etc.Wherein, compare with the point of fixity acquisition means such as traditional Road Detection technology and Video Supervision Technique, Floating Car has the advantages such as low cost, easily installation, easy care, measurement range are wide.Therefore, floating car technology is to provide the prevailing model of city inside road traffic-information service, also gradually expands to the transport information fields such as intercity, outskirts of a town simultaneously.
But urban traffic information is mainly to provide floating car data by taxi at present, due to the limited amount of taxi and the irregularities of travelling, makes within the same cycle, a lot of roads do not have taxi to cover, and particularly the taxi coverage rate in morning is less.Therefore, the road that does not much have taxi to cover, can not calculate the congestion information of road, thereby has reduced integrality and the availability of transport information.At present, the data of Floating Car are enriched constantly, have from two intercity visitor's one danger cars, the bus in outskirts of a town, and the data voluntarily that provide of some private cars, and by microblogging, traffic events, traffic website, and the transport information that the mode such as some manual entries provides is also constantly abundant and perfect.Therefore, the transport information that the transport information that Floating Car provides and microblogging, traffic events, traffic website, manual entry etc. provide merges, and can solve the problem of taxi coverage rate deficiency, thereby improves integrality and the availability of urban transportation.
The data source that multi-source traffic information merges at present mainly adopts fixed point checkout equipment and floating car data, as the publication number patent that is CN101571997A, the data source that gathers multiple checkout equipments has mainly been described, then described data source is proofreaied and correct, and calculating affects the parameter of road section traffic volume state, extract required characteristic parameter and obtain characteristic, finally characteristic is carried out fusion treatment and drawn the traffic state information of road.
Fixed point checkout equipment comprises video, coil, infrared ray etc., but equipment cost and manual maintenance expense are high, and the easily impact of the condition such as climate light, and limited quantity can only be installed.Again because of the problem of China's actual conditions and resource sharing, the data source of the checkout equipment that is difficult to obtain to fix a point.Therefore,, because fixed point checkout equipment data resource is difficult to obtain, its resource-constrained in addition, is difficult to effectively provide traffic-information service.
Summary of the invention
In view of this, the object of the present invention is to provide a kind of fusion method of multi-source traffic information, for realizing accuracy and the coverage rate of traffic information fusion.
The fusion method that the invention provides a kind of multi-source traffic information, comprising:
Various transport information are done to pre-service, make various transport information all on unified processing road network; Pretreated transport information is merged according to the method for weighting, the section still covering without transport information after merging is filled up, form complete transport information; Complete transport information is generated and issued according to the position table of standard.
The present invention is by floating car traffic information and non-structured transport information, as micro-blog information, event information, traffic site information etc. merge, and use the rule of historical traffic information, using historical traffic information as a kind of data source, merge with Real-time Traffic Information.Because unstructured information is very abundant, and easily obtain, having solved traffic information data source, to obtain difficulty large, the problem that cost is high; Again because unstructured information is all generally the Traffic Information situation that people experience, thereby it is more accurate to make to merge rear transport information, and coverage rate is larger.Accurate and comprehensive transport information can directly be used for the application such as issue, prediction, dynamic route planning, more reliably theoretical foundation and Technical Reference is provided also to traffic programme and administrative authority.
Accompanying drawing explanation
The fusion method process flow diagram of a kind of multi-source traffic information that Fig. 1 provides for the embodiment of the present invention.
Embodiment
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing, the present invention is described in further detail.
The embodiment of the present invention proposes a kind of new data source fusion method Real-time Traffic Information is merged, the method is in conjunction with multiple floating car data and destructuring transport information (microblogging, traffic events, traffic website and manual examination and verification), and the rule of the historical traffic information producing in conjunction with Floating Car, Real-time Traffic Information is merged.The method can guarantee to merge accuracy and the integrality of transport information.
In order to ensure accuracy and the extensibility of this technical scheme, traffic information fusion is carried out at processing road network, the position table that is created on certain standard of transport information, as: DTI(Dynamic TrafficInformation, dynamic information).
In order to ensure accuracy and the extensibility of the method, its technical scheme mainly comprises: various transport information are done to pre-service, make various transport information all on unified processing road network, transport information content mainly comprises road section ID, speed, confidence level (LinkId, Speed, Weight); Transport information obtained above is merged according to certain strategy (as the method for weighting), then fill up still not covering section in conjunction with the characteristic of traffic flow, thereby form complete transport information; Transport information after above-mentioned fusion is issued according to normal place table (as: DTI).
In order to simplify the description to technical scheme, the present embodiment is defined as follows content:
According to traffic flow character, traffic flow is divided into 8 characteristic day, Monday (Mon), Tuesday (Tue), Wednesday (Wed), Thursday (Thu), Friday (Fri), Saturday (Sat), Sunday (Sun), festivals or holidays (Hol).With the set of C representation feature day, C={Mon, Tue, Wed, Thu, Fri, Sat, Sun, Hol}.To the traffic flow data of each characteristic day according to morning evening peak variation tendency be divided into multiple time periods, each time period comprises multiple floating car data sampling period T, unit is minute; Definition k is time mark, t=kT, and k=1,2 ...If T=5 minute, is divided into 288 cycles for one day 24 hours, i.e. k=1,2 ..., 288, wherein k=1 represents 00:00～00:05, k=288 represents 23:55 ~ 00:00.
The fusion method process flow diagram of a kind of multi-source traffic information that Fig. 1 provides for the embodiment of the present invention, comprises the following steps:
1, initialization road network vecLink, according to system time initialization current slot tCur, setting transport information storage object is TrafficInfo(LinkId, Speed, Weight, Type), various transport information are all stored in container mapTrafficInfo, key is LinkId, is worth the set for TrafficInfo.
2, extract according to date D and time period t Cur the traffic information being produced by Floating Car, obtain successively the transport information in every section, and its type of mark Type, then put into container mapTrafficInfo.As the urban traffic information Type=1 that taxi produces, the Intercity Transportation information Type=2 that two visitor's one danger produce, the public transport traffic information Type=4 that bus produces, the Type=8 of road conditions voluntarily that self-moving vehicle produces.
3, extract according to date D and time period t Cur the traffic information that unstructured information produces, process successively the transport information in every section, and its Type of mark, then put into container mapTrafficInfo.As microblogging traffic information Type=16, event traffic information Type=32, manual examination and verification traffic information Type=64.
4, extract historical average storehouse and the pattern trend database data in historical traffic information according to characteristic day set C and time period t Cur, and its Type of mark, then put into container mapTrafficInfo.Historical average storehouse Type=128, Trend Pattern storehouse Type=256.
If there is the transport information of Type=64 in this Link, i.e. the information of manual examination and verification, the transport information of manual examination and verification is as the information of final fusion, and mark Type=64; Otherwise, obtain the weight F (w of this kind of transport information according to the weights W eight of transport information and type Type
i, t
i), and according to various transport information speed and weight F (w
i, t
i) be weighted and on average obtain last fusion speed
Every kind of Type that participates in the transport information merging is asked to union, obtain the type set of the transport information of all participations fusions
If this Link, in mapTrafficInfo container, does not process; Otherwise to still adopting traffic stream characteristics to fill up without the section of road conditions after merging, traffic flow temporal correlation is filled up with road network spatial coherence and is filled up.On same section, traffic flow generally can not be undergone mutation, and therefore the section to disappearance road conditions can be filled up according to the temporal correlation of traffic flow on time dimension, as: adopt and fill up V=V with the traffic information of section phase last week
t-1, T=512; At one time in section, in the time that Road form is constant, the traffic flow in each section can not be undergone mutation, and therefore can fill up the section of disappearance road conditions according to road conditions topological relation, as: at same period, according to the topological relation of road network, V=F{V is filled up in the section of disappearance road conditions
upstream, V
downstream, T=1024.
In order to guarantee the accuracy of traffic information fusion, the fusion of the present embodiment to transport information, proofread and correct, fill up and carry out processing on road network; In order to guarantee the extensibility of system,, in the time that road network is upgraded, other system is not impacted, the present embodiment adopts unified outlet to the generation of traffic information, as: DTI road network.
The embodiment of the present invention proposes a kind of new source of traffic information, as micro-blog information, and event information, traffic website, the transport information that the transport information of the unstructured information such as Traffic Announcement and manual examination and verification and Floating Car produce merges.Because unstructured information is very abundant, and easily obtain, having solved traffic information data source, to obtain difficulty large, the problem that cost is high; Again because unstructured information is all generally the Traffic Information situation that people experience, thereby it is more accurate to make to merge rear transport information, and coverage rate is larger.Accurate and comprehensive transport information can directly be used for the application such as issue, prediction, dynamic route planning, more reliably theoretical foundation and Technical Reference is provided also to traffic programme and administrative authority.
In a word, the foregoing is only preferred embodiment of the present invention, be not intended to limit protection scope of the present invention.
Claims (7)
1. a fusion method for multi-source traffic information, is characterized in that, comprising:
Various transport information are done to pre-service, make various transport information all on unified processing road network; Pretreated transport information is merged according to the method for weighting, the section still covering without transport information after merging is filled up, form complete transport information; Complete transport information is generated and issued according to the position table of standard.
2. the fusion method of multi-source traffic information according to claim 1, is characterized in that, the method further comprises the pretreated step of traffic flow, specifically comprises:
According to traffic flow character, traffic flow is divided into 8 characteristic day, Monday (Mon), Tuesday (Tue), Wednesday (Wed), Thursday (Thu), Friday (Fri), Saturday (Sat), Sunday (Sun), festivals or holidays (Hol), with the set of C representation feature day, C={Mon, Tue, Wed, Thu, Fri, Sat, Sun, Hol};
To the traffic flow data of each characteristic day according to morning evening peak variation tendency be divided into multiple time periods, each time period comprises multiple floating car data sampling period T, unit is minute;
Definition k is time mark, and t is the time period, t=kT, and k=1,2 ...
3. the fusion method of multi-source traffic information according to claim 2, is characterized in that, describedly various transport information are done to pretreated step specifically comprises:
Initialization road network vecLink, according to system time initialization current slot tCur, setting transport information storage object is TrafficInfo, comprising LinkId, Speed, Weight and the type field, various transport information are all stored in container mapTrafficInfo, key is LinkId, is worth the set for TrafficInfo;
Extract according to date D and time period t Cur the traffic information being produced by Floating Car, obtain successively the transport information in every section, and its type of mark Type, then put into container mapTrafficInfo; Wherein, the urban traffic information Type=1 that taxi produces, the Intercity Transportation information Type=2 that two visitor's one danger produce, the public transport traffic information Type=4 that bus produces, the Type=8 of road conditions voluntarily that self-moving vehicle produces;
Extract according to date D and time period t Cur the traffic information that unstructured information produces, process successively the transport information in every section, and its Type of mark, then put into container mapTrafficInfo; Wherein, microblogging traffic information Type=16, event traffic information Type=32, manual examination and verification traffic information Type=64;
Extract historical average storehouse and the pattern trend database data in historical traffic information according to characteristic day set C and time period t Cur, and its Type of mark, then put into container mapTrafficInfo; Wherein, historical average storehouse Type=128, Trend Pattern storehouse Type=256.
4. the fusion method of multi-source traffic information according to claim 3, is characterized in that, the described step that pretreated transport information is merged according to the method for weighting specifically comprises:
Traversal container mapTrafficInfo, does following processing to every Link successively:
If there is the transport information of Type=64 in this Link, the transport information of manual examination and verification is as the information of final fusion, and mark T=64; Otherwise, obtain the weight F (w of this kind of transport information according to the weights W eight of transport information and type Type
i, t
i), and according to various transport information speed and weight F (w
i, t
i) be weighted and on average obtain last fusion speed
Every kind of Type that participates in the transport information merging is asked to union, obtain the type set of the transport information of all participations fusions
5. the fusion method of multi-source traffic information according to claim 4, is characterized in that, the described step that the section still covering without transport information after merging is filled up specifically comprises:
Traversal vecLink container, does following processing to every Link successively:
If this Link, in mapTrafficInfo container, does not process; Otherwise, to still adopting traffic stream characteristics to fill up without the section of road conditions after merging.
6. the fusion method of multi-source traffic information according to claim 5, is characterized in that, described the step that still adopts traffic stream characteristics to fill up without the section of road conditions after merging is specifically comprised:
On same section, to the section of disappearance road conditions, the temporal correlation according to traffic flow on time dimension is filled up: adopt and fill up V=V with the traffic information of section phase last week
t-1, T=512; In section, in the time that Road form is constant, according to road conditions topological relation, the section of disappearance road conditions is filled up at one time: at same period, according to the topological relation of road network, V=F{V is filled up in the section of disappearance road conditions
upstream, V
downstream, T=1024.
7. according to the fusion method of the multi-source traffic information described in any one in claim 3 to 6, it is characterized in that, adopt the form of the fused data that described fusion method obtains to be: road section ID, speed, type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210567492.3A CN103903422A (en) | 2012-12-24 | 2012-12-24 | Multi-source traffic information fusion method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210567492.3A CN103903422A (en) | 2012-12-24 | 2012-12-24 | Multi-source traffic information fusion method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103903422A true CN103903422A (en) | 2014-07-02 |
Family
ID=50994723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210567492.3A Pending CN103903422A (en) | 2012-12-24 | 2012-12-24 | Multi-source traffic information fusion method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103903422A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105554077A (en) * | 2015-12-04 | 2016-05-04 | 镇江金山交通信息科技有限公司 | Traffic information exchange method |
| CN106558221A (en) * | 2016-11-29 | 2017-04-05 | 北京掌行通信息技术有限公司 | Real-time distributed traffic information processing system |
| CN108332766A (en) * | 2018-01-28 | 2018-07-27 | 武汉光庭信息技术股份有限公司 | A kind of dynamic fusion method and system for planning of multi-source road network |
| CN108520627A (en) * | 2018-03-21 | 2018-09-11 | 广州优路加信息科技有限公司 | Road conditions determine method, apparatus, system, computer equipment and storage medium |
| CN109410576A (en) * | 2018-11-08 | 2019-03-01 | 深圳北斗应用技术研究院有限公司 | Road condition analyzing method, apparatus, storage medium and the system of multisource data fusion |
| CN110517479A (en) * | 2018-05-22 | 2019-11-29 | 杭州海康威视系统技术有限公司 | A kind of urban highway traffic prediction technique, device and electronic equipment |
| CN112948054A (en) * | 2021-03-02 | 2021-06-11 | 华录智达科技股份有限公司 | Public transportation hybrid cloud platform system based on virtualization technology |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060111833A1 (en) * | 2000-08-28 | 2006-05-25 | Israel Feldman | Method and system for modeling and processing vehicular traffic data and information and applying thereof |
| CN101325004A (en) * | 2008-08-01 | 2008-12-17 | 北京航空航天大学 | Method for compensating real time traffic information data |
| CN101571997A (en) * | 2009-05-31 | 2009-11-04 | 上海宝康电子控制工程有限公司 | Method and device for fusion processing of multi-source traffic information |
| CN101794508A (en) * | 2009-12-30 | 2010-08-04 | 北京世纪高通科技有限公司 | Traffic information filling method, device and system |
| CN102163225A (en) * | 2011-04-11 | 2011-08-24 | 中国科学院地理科学与资源研究所 | A fusion evaluation method of traffic information collected based on micro blogs |
| CN102831766A (en) * | 2012-07-04 | 2012-12-19 | 武汉大学 | Multi-source traffic data fusion method based on multiple sensors |
-
2012
- 2012-12-24 CN CN201210567492.3A patent/CN103903422A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060111833A1 (en) * | 2000-08-28 | 2006-05-25 | Israel Feldman | Method and system for modeling and processing vehicular traffic data and information and applying thereof |
| CN101325004A (en) * | 2008-08-01 | 2008-12-17 | 北京航空航天大学 | Method for compensating real time traffic information data |
| CN101571997A (en) * | 2009-05-31 | 2009-11-04 | 上海宝康电子控制工程有限公司 | Method and device for fusion processing of multi-source traffic information |
| CN101794508A (en) * | 2009-12-30 | 2010-08-04 | 北京世纪高通科技有限公司 | Traffic information filling method, device and system |
| CN102163225A (en) * | 2011-04-11 | 2011-08-24 | 中国科学院地理科学与资源研究所 | A fusion evaluation method of traffic information collected based on micro blogs |
| CN102831766A (en) * | 2012-07-04 | 2012-12-19 | 武汉大学 | Multi-source traffic data fusion method based on multiple sensors |
Non-Patent Citations (1)
| Title |
|---|
| 邱奉翠: "基于城市快速路和主干道多源交通检测信息的数据融合技术研究", 《中国优秀硕士学位论文全文数据库工程科技II辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105554077A (en) * | 2015-12-04 | 2016-05-04 | 镇江金山交通信息科技有限公司 | Traffic information exchange method |
| CN106558221A (en) * | 2016-11-29 | 2017-04-05 | 北京掌行通信息技术有限公司 | Real-time distributed traffic information processing system |
| CN108332766A (en) * | 2018-01-28 | 2018-07-27 | 武汉光庭信息技术股份有限公司 | A kind of dynamic fusion method and system for planning of multi-source road network |
| CN108332766B (en) * | 2018-01-28 | 2020-09-15 | 武汉光庭信息技术股份有限公司 | Dynamic fusion planning method and system for multi-source road network |
| CN108520627A (en) * | 2018-03-21 | 2018-09-11 | 广州优路加信息科技有限公司 | Road conditions determine method, apparatus, system, computer equipment and storage medium |
| CN110517479A (en) * | 2018-05-22 | 2019-11-29 | 杭州海康威视系统技术有限公司 | A kind of urban highway traffic prediction technique, device and electronic equipment |
| CN110517479B (en) * | 2018-05-22 | 2020-11-03 | 杭州海康威视系统技术有限公司 | Urban road traffic prediction method and device and electronic equipment |
| CN109410576A (en) * | 2018-11-08 | 2019-03-01 | 深圳北斗应用技术研究院有限公司 | Road condition analyzing method, apparatus, storage medium and the system of multisource data fusion |
| CN112948054A (en) * | 2021-03-02 | 2021-06-11 | 华录智达科技股份有限公司 | Public transportation hybrid cloud platform system based on virtualization technology |
| CN112948054B (en) * | 2021-03-02 | 2021-12-10 | 华录智达科技股份有限公司 | Public transportation hybrid cloud platform system based on virtualization technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103903422A (en) | Multi-source traffic information fusion method | |
| CN102081859B (en) | Control method of bus arrival time prediction model | |
| Saneinejad et al. | Modelling the impact of weather conditions on active transportation travel behaviour | |
| CN102867422B (en) | Vehicle ad hoc network-based real-time single-point intersection signal lamp control method | |
| Booysen et al. | Walking on sunshine: Pairing electric vehicles with solar energy for sustainable informal public transport in Uganda | |
| CN106373425B (en) | A kind of parking management system based on big data | |
| Gonzales et al. | Multimodal transport modeling for Nairobi, Kenya: insights and recommendations with an evidence-based model | |
| CN109886508A (en) | Taxi high benefit based on GPS big data seeks objective multiple objective programming algorithm | |
| CN105046983A (en) | Traffic flow prediction system and method based on vehicle-road cooperation | |
| El-Geneidy et al. | Bus transit service planning and operations in a competitive environment | |
| Zhang et al. | A data-driven analysis for operational vehicle performance of public transport network | |
| CN103714694A (en) | Urban traffic information access processing system | |
| Zhang et al. | Analysis of Spatial‐Temporal Characteristics of Operations in Public Transport Networks Based on Multisource Data | |
| CN111009140A (en) | Intelligent traffic signal control method based on open-source road condition information | |
| Yu et al. | A bus-arrival time prediction model based on historical traffic patterns | |
| CN108847019A (en) | A method of it calculating variable line public transit vehicle and reaches fixed station journey time | |
| Park et al. | Speed prediction of urban freeway using LSTM and CNN-LSTM neural network | |
| Ma et al. | A method for queue length estimation in an urban street network based on roll time occupancy data | |
| Ji et al. | Commute equilibrium for mixed networks with autonomous vehicles and traditional vehicles | |
| Li et al. | How snowfalls affect the operation of taxi fleets? A case study from harbin, China | |
| Boccardo et al. | Application of geomatic techniques in infomobility and intelligent transport systems (ITS) | |
| Yuan | Application of intelligent technology in urban traffic congestion | |
| Shah et al. | Detroit freeway corridor ITS evaluation | |
| Fields | The correlates of congestion: Investigating the links between congestion and urban area characteristics | |
| Zhang et al. | Fare design in urban transit network considering elastic demand and adverse weather’s impact |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140702 |