CN107784835A - Traffic behavior model prediction system and its Forecasting Methodology based on traffic data analyzing - Google Patents

Traffic behavior model prediction system and its Forecasting Methodology based on traffic data analyzing Download PDF

Info

Publication number
CN107784835A
CN107784835A CN201710070741.0A CN201710070741A CN107784835A CN 107784835 A CN107784835 A CN 107784835A CN 201710070741 A CN201710070741 A CN 201710070741A CN 107784835 A CN107784835 A CN 107784835A
Authority
CN
China
Prior art keywords
traffic
crossroad
mentioned
vehicle
traffic data
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.)
Granted
Application number
CN201710070741.0A
Other languages
Chinese (zh)
Other versions
CN107784835B (en
Inventor
白承太
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Blue Signal Corp
Original Assignee
Blue Signal Corp
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 Blue Signal Corp filed Critical Blue Signal Corp
Publication of CN107784835A publication Critical patent/CN107784835A/en
Application granted granted Critical
Publication of CN107784835B publication Critical patent/CN107784835B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F15/00—Digital computers in general; Data processing equipment in general
    • G06F15/16—Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q90/00—Systems or methods specially adapted for administrative, commercial, financial, managerial or supervisory purposes, not involving significant data processing
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0133—Traffic data processing for classifying traffic situation
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/07—Controlling traffic signals
    • G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
    • G06F2216/03—Data mining

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Analytical Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Computer Hardware Design (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Traffic Control Systems (AREA)
  • Operations Research (AREA)

Abstract

The present invention relates to a kind of traffic behavior model prediction system based on traffic data analyzing, it includes：Queue length estimation unit, the vehicle elapsed time information and vehicle speed information of the first crossroad or the second crossroad during the sensor of queue length of vehicle or the second beacon on the second crossroad of neighbouring first crossroad or can measure waits on the second crossroad during the first beacon for being arranged on from cloud server on the first crossroad or can measure waits on the first crossroad measured by the sensor of the queue length of vehicle, it is directed to according to the vehicle elapsed time information and vehicle speed information of the first crossroad or the second crossroad and enters the queue length of the vehicle that the first crossroad but has not gone through the second crossroad and estimated；Volume of traffic estimation unit；Volume of traffic amending unit；And traffic state information arithmetic element.

Description

Traffic behavior model prediction system and its Forecasting Methodology based on traffic data analyzing
Technical field
The present invention relates to a kind of traffic behavior model prediction system and its Forecasting Methodology based on traffic data analyzing, especially It is a kind of corrected based on the historical traffic data of each road segments after estimated traffic data out in the best way Predict the system and its Forecasting Methodology of future transportation state model.
Background technology
The item recorded in the introduction is used to promote the understanding to background of invention, and it may include following item, That is, the item is not to possess the prior art known to usual skill in the technology art.
Existing transport information supply system is a kind of apparatus for being used to collect particular traffic information, and it utilizes various Instrument, for example, allowing electric current to pass through when the round conductor rear vehicle being embedded on road moves according to caused by flux variable quantity Surplus is grasped the magnetic vehicle detector of car speed, closed-circuit television (CCTV) camera lens on road or is arranged on Speed detector on road etc..Existing transport information supply system utilizes the transport information collected by above-mentioned instrument to control Signal lamp provides the user information on road by wireless or cable, and is passed to after real-time collecting transport information User.
Moreover, increase recently as the user for carrying mobile communication terminal and occur utilizing the various of mobile communication terminal Content service.A service in the content service is the vehicle interior possessed mobile communication terminal reception from traveling Shortest path from origin to destination is wirelessly informed behind ground and destination information.For example, user is with voice or short After set out place name and purpose place name are inputted mobile communication terminal or independent navigator terminal by letter form, generate from departure place to The routing information of destination and it is supplied to driver in a manner of voice, short message, signal sound etc.
But existing traffic dredging information supply service can not be accurate based on the historical traffic data of each road segments The traffic behavior of the specified link of the specific time point of true ground real-time estimate.Moreover, do not simply fail to optimize the signal week of each road segments Phase, the signal period for the metropolitan area unit that multiple road segments are subordinate to can not be optimized.
Prior art literature
Patent document 1：Korean Patent Laid the 2006-0037481st (2007.03.28. bulletins)
The content of the invention
Present invention seek to address that above-mentioned problem of the prior art, it is an object of the invention to provide a kind of traffic behavior pattern is pre- Examining system and its Forecasting Methodology, it can be stored in the historical traffic data of each road segments of Cloud Server in specific time point Based on real-time estimate specified link exactly traffic behavior.
Moreover, it is a further object to provide a kind of traffic behavior model prediction system and its Forecasting Methodology, its Not only optimize the signal period of each road segments, moreover it is possible to further optimize the metropolitan area unit that multiple road segments are subordinate to Signal period.
Traffic behavior model prediction system according to an embodiment of the invention based on traffic data analyzing includes：It is lined up Length estimate unit, the first beacon (beacon) being arranged on from cloud server on the first crossroad or can measure first The sensor of the queue length of vehicle or on the second crossroad of neighbouring first crossroad in being waited on crossroad Second beacon or can measure on the second crossroad wait in vehicle queue length sensor measured by the first crossroad Or second crossroad vehicle elapsed time information and vehicle speed information, according to the first crossroad or the vehicle of the second crossroad Elapsed time information and vehicle speed information have not gone through the row of the vehicle of the second crossroad after being directed into the first crossroad Team leader's degree is estimated；Volume of traffic estimation unit, try to achieve the first crossroad using the queue length estimated and intersect with second Estimate the volume of traffic after the traffic density of each road segments between road；Volume of traffic amending unit, to be stored in Cloud Server Estimated traffic data out is corrected based on the historical traffic data of each road segments；And traffic state information computing list Member, the traffic behavior of each road segments of day part is calculated for the traffic data applicable data excavation of amendment and pattern matching method Pattern and volume of traffic streaming rate.
Here, the first beacon or can measure on the first crossroad wait in vehicle queue length sensor and second Beacon can measure the sensor of the queue length of vehicle in waiting on the second crossroad by taking personnel with vehicle The radio communication detection vehicle of portable terminal passes through the time of the first crossroad or the second crossroad and passes through the first crossroad Or second crossroad vehicle speed.
Moreover, queue length estimation unit falls below the road of pre-set velocity for car speed more than pre-set velocity Estimate vehicle queue length after being identified in the locality of road section.
Moreover, historical traffic data is the travel speed and running time according to specific time period and specified link section.
Moreover, the pattern of volume of traffic amending unit analysis of history traffic data, road segments for no collection and do not have The traffic data for having the period of collection is corrected with the historical traffic data of the road segments and period.
Moreover, traffic behavior pattern and the volume of traffic of the traffic state information arithmetic element from each road segments calculated Streaming rate tries to achieve the live signal cycle of the first crossroad or the second crossroad based on machine learning.
Moreover, volume of traffic streaming rate be relative to the volume of traffic for flowing into each road segments right-turn volume ratio, turn left Volume of traffic ratio and straight-going traffic amount ratio.
Moreover, volume of traffic amending unit is by feat of the traffic data estimated and the historical traffic number of each road segments According to pattern match with estimated by the historical traffic data amendment of each road segments of similarity highest out traffic data.
Moreover, volume of traffic amending unit calculates the historical traffic data of the traffic data and each road segments estimated Between Euclidean distance, then the Euclidean distance to calculate calculates the value of similarity.
Traffic behavior mode prediction method according to an embodiment of the invention based on traffic data analyzing, it is utilization The traffic behavior mode prediction method of traffic behavior model prediction system based on traffic data analyzing, comprises the following steps：Peace The sensor of the queue length of vehicle during the first beacon on the first crossroad or can measure waits on the first crossroad Or installed in the second beacon on the second crossroad of the first crossroad or it can measure on the second crossroad in waiting The sensor of the queue length of vehicle measures the vehicle elapsed time information and car speed of the first crossroad or the second crossroad Cloud Server is sent to after information；From the vehicle elapsed time information of the crossroad of cloud server first or the second crossroad and The queue length for the vehicle for having not gone through the second crossroad after being directed to after vehicle speed information into the first crossroad is estimated Meter；The volume of traffic that each road segments between the first crossroad and the second crossroad are tried to achieve using the queue length estimated is close The volume of traffic is estimated after degree；Estimated come out is corrected based on the historical traffic data of each road segments for being stored in Cloud Server Traffic data；And for calculating each road of day part after the traffic data applicable data excavation of amendment and pattern matching method The traffic behavior pattern and volume of traffic streaming rate of section.
In accordance with the invention it is possible to each road segments of the specific time point to be stored in Cloud Server historical traffic data as The traffic behavior of basic real-time estimate specified link exactly.
According to the present invention, it not only optimizes the signal period of each road segments, moreover it is possible to further optimizes multiple road segments The signal period for the metropolitan area unit being subordinate to.
Brief description of the drawings
Fig. 1 is for illustrating the traffic behavior model prediction according to an embodiment of the invention based on traffic data analyzing The condition of road surface skeleton diagram of system.
Fig. 2 is the group of the traffic behavior model prediction system according to an embodiment of the invention based on traffic data analyzing Knit figure.
Fig. 3 is the skeleton diagram calculated for illustrating Euclidean distance according to an embodiment of the invention.
Fig. 4 is the picture for showing road segments according to an embodiment of the invention and historical traffic data.
Fig. 5 is to show the car speed picture according to an embodiment of the invention relative to the time.
Fig. 6 is the skeleton diagram for illustrating volume of traffic streaming rate according to an embodiment of the invention.
Fig. 7 is the picture for showing the multiple cross road traffic data according to an embodiment of the invention in units of net.
Fig. 8 is the stream of the traffic behavior mode prediction method according to an embodiment of the invention based on traffic data analyzing Cheng Tu.
The explanation of reference
10：First beacon or the sensor that the queue length of vehicle in waiting on the first crossroad can be measured
20：Second beacon or the sensor that the queue length of vehicle in waiting on the second crossroad can be measured
30：Cloud Server
100：Queue length estimation unit
200：Volume of traffic estimation unit
300：Volume of traffic amending unit
400：Traffic state information arithmetic element
Embodiment
The aftermentioned embodiment being described with reference to the accompanying drawings will be helpful to be expressly understood that advantages of the present invention, feature and its realization Method.But the invention is not restricted to following disclosed embodiment, the present invention can be realized by various mutually different forms, The present embodiment only contributes to the complete announcement of the present invention, and its main purpose is that have usual knowledge into art of the present invention Person intactly illustrates scope of the invention, and scope of the invention can only be defined by the claims.
Fig. 1 is for illustrating the traffic behavior model prediction according to an embodiment of the invention based on traffic data analyzing The condition of road surface skeleton diagram of system.
The traffic behavior pattern of one embodiment of the invention refers to that such as traffic mixes and hazard types and level of significance.
Referring to Fig. 1, there are the first crossroad and the second crossroad on road, between the first crossroad and the second crossroad Then there is vehicle to pass through or wait in line.Moreover, the first crossroad beacon of self-configuring first each with the second crossroad or can measure Sensor 10 and the second beacon of the queue length of vehicle or can to measure the second crossroad first-class in being waited on first crossroad The sensor 20 of the queue length of vehicle in time, the first beacon or the beacon of sensor 10 and second or sensor 20 are with radio communication Cloud Server 30cloud server are connected, Cloud Server 30 is then connected to traffic behavior model prediction system with communication System, therefore traffic behavior model prediction system can receive the vehicle warp of the first crossroad or the second crossroad from Cloud Server 30 Cross temporal information and vehicle speed information.
In order to the first beacon or can measure on the first crossroad wait in vehicle queue length sensor 10 or The beacon of person second or can measure on the second crossroad wait in vehicle queue length sensor 20 carry out radio communication and Need that traffic behavior model prediction application APP is installed in portable terminal.Portable terminal can use such as intelligent hand Any portable terminal such as machine, tablet personal computer, PC.
Vehicle takes personnel's taking portable terminal, when vehicle after the first crossroad by the second crossroad Words, the first beacon 10 or sensor with the radio communication for taking personnel's portable terminal in vehicle by detecting vehicle by the The speed of the vehicle of the first crossroad of time and process of one crossroad.Moreover, the second beacon 20 or sensor by and vehicle The interior radio communication for taking personnel's portable terminal detection vehicle is by the time of the second crossroad and by the second crossroad Vehicle speed.
The second beacon 20 or sensor can not detect vehicle by second when vehicle does not wait by the second crossroad The speed of the vehicle of the second crossroad of time and process of crossroad.At this point it is possible to queue length when being waited for vehicle is entered Row estimation, queue length then can be from the vehicle elapsed time information and vehicle speed information of the first crossroad or the second crossroad Estimate.Speed can be reduced gradually if vehicle waits before by the second crossroad, and vehicle speed information can be used for arranging The estimation of team leader's degree.Fig. 1 x is represented and the spacing distance of the first crossroad, v represent the speed of vehicle.From fig. 1, it can be seen that vehicle Speed is drastically reduced and relaxed in locality A speed slip after the first crossroad.
Fig. 2 is the group of the traffic behavior model prediction system according to an embodiment of the invention based on traffic data analyzing Knit figure.Fig. 1 and Fig. 2 is referred to, the traffic behavior model prediction system based on traffic data analyzing can be estimated including queue length Count unit 100, volume of traffic estimation unit 200, volume of traffic amending unit 300 and traffic state information arithmetic element 400.
Queue length estimation unit 100 receives the first beacon on the first crossroad from Cloud Server 30 or can Measure the sensor 10 of the queue length of vehicle in being waited on the first crossroad or second installed in neighbouring first crossroad During the second beacon on crossroad or can measure waits on the second crossroad measured by the sensor 20 of the queue length of vehicle The first crossroad or the second crossroad vehicle elapsed time information and vehicle speed information.Here, the first beacon 10 or biography Sensor and the second beacon 20 or sensor are passed through by detecting vehicle with the radio communication for taking personnel's portable terminal in vehicle Cross the time of the first crossroad or the second crossroad and the speed by the first crossroad or the vehicle of the second crossroad.First letter Mark 10 or sensor or the second beacon 20 or sensor pass through the V2I (communications between vehicle and infrastructure：Vehicle to Infrastructure) communication receives vehicle elapsed time information from portable terminal and communicated by M2C from portable terminal End receives vehicle speed information.
Moreover, vehicle elapsed time information of the queue length estimation unit 100 according to the first crossroad or the second crossroad And vehicle speed information is estimated to have not gone through the queue length of the vehicle of the second crossroad into after the first crossroad.Now, Queue length estimation unit 100 identifies that car speed falls below the road segments of pre-set velocity more than pre-set velocity The queue length of vehicle is estimated afterwards in locality (Fig. 1 A).The estimation mode not limited to this of queue length.
Volume of traffic estimation unit 200 tries to achieve first using the estimated queue length out of queue length estimation unit 100 Estimate the volume of traffic after the traffic density of each road segments between crossroad and the second crossroad.
Volume of traffic amending unit 300 using be stored in Cloud Server each road segments historical traffic data big data as base The estimated traffic data out of plinth amendment volume of traffic estimation unit 200.As previously mentioned based on historical traffic data The reasons why traffic data come out estimated by amendment, is the external action (external force), it is necessary to meteorology etc And volume of traffic number of the traffic data reflection estimated by out caused by the incomplete property of data collection hardware (hardware) According to upper.Whereby, the road locality of no acquisition and the traffic data of specific time period can be modified.Historical traffic number According to travel speed and running time including specific time period Yu specified link section, but it is not limited to this.
Moreover, the historical traffic data big data of each road segments stored by Cloud Server 30 can pass through over time and Huge data are increasingly become, therefore can more accurately correct estimated traffic data out.As previously mentioned can More accurately it is to make use of Cloud Server 30 the reasons why data estimated by amendment, huge data can not be stored by which solving Existing issue.
Volume of traffic amending unit 300 analyzes such as traffic and mixes historical traffic data with hazard types and level of significance etc Pattern, road segments for no collection and traffic data the going through with the road segments and period without the period collected History traffic data is corrected.Specifically, volume of traffic amending unit 300 is by feat of the traffic data that estimates and each road The pattern match of the historical traffic data of road section is estimated with the historical traffic data amendment of each road segments of similarity highest The traffic data of meter out.Now, volume of traffic amending unit 300 calculates estimated traffic data out and each roadway area Euclidean distance (euclidean distance) between the historical traffic data of section, then the Euclidean distance to calculate calculate The value of similarity.
Traffic state information arithmetic element 400 is applicable number for the traffic data that volume of traffic amending unit 300 is corrected According to calculating each roadway area of day part after excavating (data mining) and pattern matching method (pattern matching method) The traffic behavior pattern and volume of traffic streaming rate of section.Moreover, traffic state information arithmetic element 400 is from each road calculated The traffic behavior pattern and volume of traffic streaming rate of section try to achieve the first crossroad based on machine learning (machine running) Or second crossroad the live signal cycle.Machine learning is a kind of for huge big such as data generation, amount, cycle, form Data predict the technology in future after being analyzed, because it belongs to known way, therefore thereof will be omitted its detailed description.In real time Signal period is that blue signal lamp is again red after the cycle untill bright light or red eye bright light after blue signal lamp bright light Chrominance signal lamp cycle untill bright light again.Volume of traffic streaming rate is handed over relative to the right-hand rotation for the volume of traffic for flowing into each road segments Flux ratio, left-turn volume ratio and straight-going traffic amount ratio.
Fig. 3 is the skeleton diagram calculated for illustrating Euclidean distance according to an embodiment of the invention.Referring to Fig. 3, can To learn from the traffic data estimated for representing subject data (subject data) and the history friendship of each road segments The method that logical data (historical data) calculate Euclidean distance.
The part that " X " is shown as in subject data and the historical traffic data of each road segments is the volume of traffic estimated The missing data (missing data) of data.Euclidean distance is in subject data or the historical traffic data of each road segments The part for being shown as " X " is shown with " X ".Fig. 3 shows two kinds of cases (Case 1, Case 2), and it can be learnt according to the original Reason calculates Euclidean distance.
Fig. 4 is the picture for showing road segments according to an embodiment of the invention and historical traffic data.Refer to figure 4, Fig. 4 show road segments and historical traffic data.
The part shown in left panels with square is the road segments between 2 adjacent crossroads, right data It is with the travel speed (Link based on specific time period (Time_Period) with specified link section (Link Number) Speed (km/h)) and running time (Link Travel_Time (s)) historical traffic data.Specific time period is preset as with 5 points Clock is unit, but is not limited to this.Road segments are divided into 1~6 grade 6, and the figure on the left side is divided into each road segments Link (section) 1, Link 2, Link 3, Link 4, Link 5, Link 6.
8 points 30 minutes~8 points in 35 minutes No. 1 road segments travel speed for 19km/h and running time is then 28 (s). Although specific time period is set as, using 5 minutes as unit, being not limited to this here.
Fig. 5 is to show the car speed picture according to an embodiment of the invention relative to the time.Referring to Fig. 5, can To learn the changes in vehicle speed passed through over time and occurred in specified link section.
Red represents car speed predicted value, blue then represent measured value.
Fig. 6 is the skeleton diagram for illustrating volume of traffic streaming rate according to an embodiment of the invention.It is referring to Fig. 6, aobvious The inflow volume of traffic, right-turn volume ratio a, the left-turning traffic at road segments (linking-up road (road link)) 1,2,3 are shown Measure ratio β and straight-going traffic amount ratio γ.
As seen from the figure, it is 1000 the volume of traffic to be flowed into road segments 1, right-turn volume ratio a, left-turn volume ratio β And straight-going traffic amount ratio γ is respectively 0.3,0.2,0.5, it is 800 to flow into the volume of traffic in road segments 2, right-turn volume ratio a, Left-turn volume ratio β and straight-going traffic amount ratio γ is respectively 0.7,0.1,0.2, and it is 500 to flow into the volume of traffic in road segments 3, Right-turn volume ratio a, left-turn volume ratio β and straight-going traffic amount ratio γ are respectively 0.5,0.3,0.2.
Therefore, right-turn volume ratio a is in the highest of road segments 2, and left-turn volume ratio β is in the highest of road segments 3, directly Row volume of traffic ratio γ is then in the highest of road segments 1.
Fig. 7 is to show the multiple cross road traffic number according to an embodiment of the invention with net (network) for unit According to picture.Referring to Fig. 7, each crossroad is shown in different colors, car speed each displays.
As seen from the figure, it is higher closer to red, car speed from green.Whereby, vehicle drive people can grasp car rapidly Speed smoothly travels behind path towards required destination.
A net can be set to multiple subnets in the road in units of net as previously described, and subnet can be by multiple friendships The cross road is formed.By taking highway as an example, subnet can be set as the traffic such as good ability IC- crop fields IC sections, crop field IC- Beijing University Qiu IC Flow the section changed greatly.
Fig. 8 is the stream of the traffic behavior mode prediction method according to an embodiment of the invention based on traffic data analyzing Cheng Tu.Fig. 1, Fig. 2 and Fig. 8 are referred to, the traffic behavior mode prediction method based on traffic data analyzing utilizes Fig. 2 traffic shape Morphotype formula forecasting system and this method is as described below.Detailed description on each step will refer to above-mentioned Fig. 1 and Fig. 2.
First, vehicle during the first beacon 10 on the first crossroad or can measure waits on the first crossroad The sensor of queue length or the second beacon 20 on the second crossroad of neighbouring first crossroad can be measured The sensor of the queue length of vehicle measures the first crossroad in being waited on second crossroad or the vehicle of the second crossroad passes through Cloud Server 30 (S100 ') is sent to after temporal information and vehicle speed information (S100).
After step (S100 '), the storage of Cloud Server 30 is received from the first beacon 10 or sensor or the second beacon 20 Or the first crossroad of sensor or the vehicle elapsed time information and vehicle speed information (S200) of the second crossroad.
After step (S2OO), queue length estimation unit 100 receives the first crossroad or second from Cloud Server 30 The vehicle elapsed time information and vehicle speed information (S200 ') of crossroad, being then directed to after entering the first crossroad does not have also Estimated (S300) by the queue length of the vehicle of the second crossroad.
After step (S300), volume of traffic estimation unit 200 receives what is come out estimated by queue length estimation unit 100 Queue length (S300 '), each road between the first crossroad and the second crossroad is tried to achieve using the queue length estimated The volume of traffic (S400) is estimated after the traffic density of section.
After step (S400), volume of traffic amending unit 300 receives the estimated friendship out of volume of traffic estimation unit 200 Flux data (S400'), then correct institute based on the historical traffic data of each road segments stored by Cloud Server 30 The traffic data (S500) estimated.
After step (S500), traffic state information arithmetic element 400 receives what volume of traffic amending unit 300 was corrected Traffic data (S500 '), on the traffic data of amendment applicable data excavate and pattern matching method and to calculate day part each The traffic behavior pattern and volume of traffic streaming rate (S600) of road segments.
Embodiments of the invention are described in detail with reference to accompanying drawing illustrated embodiment in order to promote understanding above, but it is only Illustrate, thus person with usual knowledge in their respective areas of the present invention can carry out various change and other realities of equivalence range when knowing Apply example.Therefore, real technical protection scope of the invention should be defined by tbe claims.

Claims (11)

  1. A kind of 1. traffic behavior model prediction system based on traffic data analyzing, it is characterised in that
    Including：
    Queue length estimation unit, the first beacon being arranged on from cloud server on the first crossroad or can measure first The sensor of the queue length of vehicle or the second crossroad installed in neighbouring above-mentioned first crossroad in being waited on crossroad On the second beacon or can measure waited on the second crossroad in vehicle queue length sensor measured by above-mentioned the The vehicle elapsed time information and vehicle speed information of one crossroad or above-mentioned second crossroad, according to above-mentioned first crossroad or The vehicle elapsed time information and vehicle speed information of above-mentioned second crossroad, which are directed into above-mentioned first crossroad, not to be had also but Queue length by the vehicle of above-mentioned second crossroad is estimated；
    Volume of traffic estimation unit, using the queue length estimated try to achieve above-mentioned first crossroad and above-mentioned second crossroad it Between each road segments traffic density after estimate the volume of traffic；
    Volume of traffic amending unit, institute is corrected based on the historical traffic data of each road segments for being stored in above-mentioned Cloud Server The traffic data estimated；And
    Traffic state information arithmetic element, when calculating each for the traffic data applicable data excavation of amendment and pattern matching method The traffic behavior pattern and volume of traffic streaming rate of each road segments of section.
  2. 2. the traffic behavior model prediction system according to claim 1 based on traffic data analyzing, it is characterised in that
    Above-mentioned first beacon or the sensor and above-mentioned second that the queue length of vehicle in waiting on the first crossroad can be measured Beacon can measure the sensor of the queue length of vehicle in waiting on the second crossroad by taking personnel with vehicle The radio communication detection vehicle of portable terminal passes through the time of above-mentioned first crossroad or above-mentioned second crossroad and by upper State the speed of the vehicle of the first crossroad or above-mentioned second crossroad.
  3. 3. the traffic behavior model prediction system according to claim 1 based on traffic data analyzing, it is characterised in that
    Above-mentioned queue length estimation unit falls below the roadway area of pre-set velocity for car speed more than pre-set velocity Estimate vehicle queue length after being identified in the locality of section.
  4. 4. the traffic behavior model prediction system according to claim 1 based on traffic data analyzing, it is characterised in that
    Above-mentioned historical traffic data is the travel speed and running time according to specific time period and specified link section.
  5. 5. the traffic behavior model prediction system according to claim 1 based on traffic data analyzing, it is characterised in that
    The pattern of above-mentioned volume of traffic amending unit analysis of history traffic data, road segments for no collection and is not collected The traffic data of period corrected with the historical traffic data of the road segments and period.
  6. 6. the traffic behavior model prediction system according to claim 1 based on traffic data analyzing, it is characterised in that
    Above-mentioned traffic state information arithmetic element shunts from the traffic behavior pattern and the volume of traffic of each road segments calculated Rate tries to achieve the live signal cycle of the first crossroad or the second crossroad based on machine learning.
  7. 7. the traffic behavior model prediction system according to claim 1 based on traffic data analyzing, it is characterised in that
    Above-mentioned volume of traffic streaming rate is right-turn volume ratio relative to the volume of traffic for flowing into each road segments, left-turn volume Ratio and straight-going traffic amount ratio.
  8. 8. the traffic behavior model prediction system according to claim 1 based on traffic data analyzing, it is characterised in that
    Above-mentioned volume of traffic amending unit is handed over by feat of the history of the above-mentioned traffic data estimated and above-mentioned each road segments The pattern match of logical data estimates so that the historical traffic data amendment of the above-mentioned each road segments of similarity highest is above-mentioned Traffic data.
  9. 9. the traffic behavior model prediction system according to claim 8 based on traffic data analyzing, it is characterised in that
    Above-mentioned volume of traffic amending unit calculates the historical traffic of the above-mentioned traffic data estimated and above-mentioned each road segments Euclidean distance between data, then the Euclidean distance to calculate calculate the value of similarity.
  10. 10. the traffic behavior model prediction system according to claim 1 based on traffic data analyzing, it is characterised in that
    Above-mentioned traffic behavior pattern mixes and hazard types and level of significance including traffic.
  11. 11. a kind of traffic behavior mode prediction method based on traffic data analyzing, it utilizes the friendship based on traffic data analyzing Logical state model forecasting system, it is characterised in that
    Comprise the following steps：
    The queue length of vehicle during the first beacon on the first crossroad or can measure waits on the first crossroad Sensor or the second beacon on the second crossroad of neighbouring above-mentioned first crossroad can measure the second intersection The sensor of the queue length of vehicle measures above-mentioned first crossroad in being waited on road or the vehicle of above-mentioned second crossroad passes through Cloud Server is sent to after temporal information and vehicle speed information；
    From the vehicle elapsed time information and vehicle of above-mentioned first crossroad of above-mentioned cloud server or above-mentioned second crossroad The queue length that the vehicle for but having not gone through above-mentioned second crossroad into above-mentioned first crossroad is directed to after velocity information is entered Row estimation；
    Each road segments between above-mentioned first crossroad and above-mentioned second crossroad are tried to achieve using the queue length estimated Traffic density after estimate the volume of traffic；
    Estimated traffic out is corrected based on the historical traffic data of each road segments for being stored in above-mentioned Cloud Server Measure data；And
    Traffic for calculating each road segments of day part after the traffic data applicable data excavation of amendment and pattern matching method State model and volume of traffic streaming rate.
CN201710070741.0A 2016-08-30 2017-02-09 Traffic state mode prediction system based on traffic data analysis and prediction method thereof Active CN107784835B (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020160110719A KR101703058B1 (en) 2016-08-30 2016-08-30 System for predicting traffic state pattern by analysis of traffic data and predicting method thereof
KR10-2016-0110719 2016-08-30

Publications (2)

Publication Number Publication Date
CN107784835A true CN107784835A (en) 2018-03-09
CN107784835B CN107784835B (en) 2021-06-25

Family

ID=58108814

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710070741.0A Active CN107784835B (en) 2016-08-30 2017-02-09 Traffic state mode prediction system based on traffic data analysis and prediction method thereof

Country Status (2)

Country Link
KR (1) KR101703058B1 (en)
CN (1) CN107784835B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108447261A (en) * 2018-04-04 2018-08-24 迈锐数据（北京）有限公司 Based on multimode vehicle queue length computational methods and device
CN110164132A (en) * 2019-05-29 2019-08-23 浙江警察学院 A kind of detection method and system of road traffic exception
CN110322188A (en) * 2018-03-29 2019-10-11 青信号有限公司 Utilize logistics distribution path providing method and its server of future traffic information
CN110533259A (en) * 2019-09-05 2019-12-03 北京云视科技有限公司 A kind of method, apparatus that estimating waiting time, system and storage medium
CN112489423A (en) * 2020-11-20 2021-03-12 湖南警察学院 Vision-based urban road traffic police command method
CN113257009A (en) * 2021-04-25 2021-08-13 安徽银徽科技有限公司 Intelligent traffic operation and maintenance method and system with vehicle guidance function

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102068981B1 (en) 2017-05-02 2020-01-22 주식회사 엘지유플러스 Apparatus and Method for controlling vehicle speed in indoor environment
CN110444010B (en) * 2018-05-02 2022-01-21 广州智丰设计研发有限公司 Expressway traffic flow prediction method based on Internet of things
KR102197251B1 (en) * 2018-08-29 2020-12-31 재단법인대구경북과학기술원 Deep learning based traffic signal control method and device for rlr detection and accident prevention
CN110634293B (en) * 2019-09-26 2021-06-04 同济大学 Trunk intersection control method based on fuzzy control
CN110634308B (en) * 2019-09-26 2021-09-03 同济大学 Single-intersection signal control method based on vehicle queuing dissipation time
CN113129582B (en) * 2019-12-31 2023-05-09 阿里巴巴集团控股有限公司 Traffic state prediction method and device
CN111627229B (en) * 2020-05-20 2022-07-22 深圳市有方科技股份有限公司 Control method and device of traffic signal equipment and computer equipment
CN111739315B (en) * 2020-08-27 2021-01-26 台州市远行客网络技术有限公司 Intelligent green wave adjusting method and intelligent green wave adjusting system for traffic signal lamp

Citations (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH09223295A (en) * 1996-02-20 1997-08-26 Hitachi Ltd Road traffic information providing method and road traffic information providing system
JP2004118735A (en) * 2002-09-27 2004-04-15 Toyota Central Res & Dev Lab Inc Traffic situation estimation device and od traffic volume correction device
CN1645402A (en) * 2005-01-19 2005-07-27 北京交通大学 Road traffic flow data quality controlling method and apparatus
KR20070106273A (en) * 2006-04-28 2007-11-01 (주)큰날개 Server, system, and method for creating and providing traffic information
CN101154318A (en) * 2006-09-05 2008-04-02 株式会社查纳位资讯情报 System and method for collecting and distributing traffic information, center device and vehicle carried terminal device
JP4415278B2 (en) * 2006-10-20 2010-02-17 住友電気工業株式会社 Traffic flow behavior estimation system at intersections
CN101894461A (en) * 2009-05-22 2010-11-24 上海宝康电子控制工程有限公司 Method for predicting travel time on urban ground level roads
CN102708679A (en) * 2012-05-29 2012-10-03 孙健 Method for forecasting short-time traffic flows at urban signalized intersections
CN102890862A (en) * 2012-09-29 2013-01-23 浙江大学 Traffic condition analyzing device and method based on vector mode
CN103632546A (en) * 2013-11-27 2014-03-12 中国航天系统工程有限公司 Floating car data-based urban road traffic accident influence prediction method
CN103914988A (en) * 2013-01-04 2014-07-09 中国移动通信集团公司 Traffic road condition data processing method, device and system
CN104217588A (en) * 2013-05-31 2014-12-17 张伟伟 Method, server and system for acquiring real-time traffic information
CN104299442A (en) * 2014-10-15 2015-01-21 河海大学 Urban route travel time forecasting method based on pattern matching
CN105118294A (en) * 2015-09-25 2015-12-02 山东易构软件技术股份有限公司 Short-time traffic flow prediction method based on state pattern
CN105160917A (en) * 2015-08-24 2015-12-16 武汉理工大学 Vehicle and road collaborative information-based signalized intersection vehicle speed guidance system and method
CN105489018A (en) * 2016-02-19 2016-04-13 上海果路交通科技有限公司 Road intersection traffic signal system control method
KR20160049691A (en) * 2014-10-28 2016-05-10 현대엠엔소프트 주식회사 Apparatus and method for providing traffic information
CN205247622U (en) * 2015-12-24 2016-05-18 深圳市综合交通运行指挥中心 Vehicle length monitoring system that lines up

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100702852B1 (en) 2004-10-28 2007-04-06 한국도로공사 Method and system for traffic prediction and dynamic route guidance based on historical and real-time traffic information

Patent Citations (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH09223295A (en) * 1996-02-20 1997-08-26 Hitachi Ltd Road traffic information providing method and road traffic information providing system
JP2004118735A (en) * 2002-09-27 2004-04-15 Toyota Central Res & Dev Lab Inc Traffic situation estimation device and od traffic volume correction device
CN1645402A (en) * 2005-01-19 2005-07-27 北京交通大学 Road traffic flow data quality controlling method and apparatus
KR20070106273A (en) * 2006-04-28 2007-11-01 (주)큰날개 Server, system, and method for creating and providing traffic information
CN101154318A (en) * 2006-09-05 2008-04-02 株式会社查纳位资讯情报 System and method for collecting and distributing traffic information, center device and vehicle carried terminal device
JP4415278B2 (en) * 2006-10-20 2010-02-17 住友電気工業株式会社 Traffic flow behavior estimation system at intersections
CN101894461A (en) * 2009-05-22 2010-11-24 上海宝康电子控制工程有限公司 Method for predicting travel time on urban ground level roads
CN102708679A (en) * 2012-05-29 2012-10-03 孙健 Method for forecasting short-time traffic flows at urban signalized intersections
CN102890862A (en) * 2012-09-29 2013-01-23 浙江大学 Traffic condition analyzing device and method based on vector mode
CN103914988A (en) * 2013-01-04 2014-07-09 中国移动通信集团公司 Traffic road condition data processing method, device and system
CN104217588A (en) * 2013-05-31 2014-12-17 张伟伟 Method, server and system for acquiring real-time traffic information
CN103632546A (en) * 2013-11-27 2014-03-12 中国航天系统工程有限公司 Floating car data-based urban road traffic accident influence prediction method
CN104299442A (en) * 2014-10-15 2015-01-21 河海大学 Urban route travel time forecasting method based on pattern matching
KR20160049691A (en) * 2014-10-28 2016-05-10 현대엠엔소프트 주식회사 Apparatus and method for providing traffic information
CN105160917A (en) * 2015-08-24 2015-12-16 武汉理工大学 Vehicle and road collaborative information-based signalized intersection vehicle speed guidance system and method
CN105118294A (en) * 2015-09-25 2015-12-02 山东易构软件技术股份有限公司 Short-time traffic flow prediction method based on state pattern
CN205247622U (en) * 2015-12-24 2016-05-18 深圳市综合交通运行指挥中心 Vehicle length monitoring system that lines up
CN105489018A (en) * 2016-02-19 2016-04-13 上海果路交通科技有限公司 Road intersection traffic signal system control method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
杨佩昆，张树升编: "《交通管理与控制》", 31 December 1995 *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110322188A (en) * 2018-03-29 2019-10-11 青信号有限公司 Utilize logistics distribution path providing method and its server of future traffic information
CN108447261A (en) * 2018-04-04 2018-08-24 迈锐数据（北京）有限公司 Based on multimode vehicle queue length computational methods and device
CN108447261B (en) * 2018-04-04 2020-09-18 迈锐数据（北京）有限公司 Vehicle queuing length calculation method and device based on multiple modes
CN110164132A (en) * 2019-05-29 2019-08-23 浙江警察学院 A kind of detection method and system of road traffic exception
CN110533259A (en) * 2019-09-05 2019-12-03 北京云视科技有限公司 A kind of method, apparatus that estimating waiting time, system and storage medium
CN110533259B (en) * 2019-09-05 2022-03-22 北京云视科技有限公司 Method, device and system for predicting waiting time and storage medium
CN112489423A (en) * 2020-11-20 2021-03-12 湖南警察学院 Vision-based urban road traffic police command method
CN112489423B (en) * 2020-11-20 2022-06-03 湖南警察学院 Vision-based urban road traffic police command method
CN113257009A (en) * 2021-04-25 2021-08-13 安徽银徽科技有限公司 Intelligent traffic operation and maintenance method and system with vehicle guidance function
CN113257009B (en) * 2021-04-25 2022-03-25 安徽银徽科技有限公司 Intelligent traffic operation and maintenance method and system with vehicle guidance function

Also Published As

Publication number Publication date
CN107784835B (en) 2021-06-25
KR101703058B1 (en) 2017-02-06

Similar Documents

Publication Publication Date Title
CN107784835A (en) Traffic behavior model prediction system and its Forecasting Methodology based on traffic data analyzing
WO2015051718A1 (en) Dynamic track navigation method and cloud platform
US9965950B2 (en) Method and apparatus for classifying a traffic jam from probe data
US10475336B2 (en) System for forecasting traffic condition pattern by analysis of traffic data and forecasting method thereof
CN107016861A (en) Traffic lights intelligent control system based on deep learning and intelligent road-lamp
CN104221065B (en) The system and method that traffic administration is carried out using lighting mains
CN105976062A (en) Signal lamp duration data mining method, and travel service implementation method and device
CN106781556B (en) A kind of traffic lights duration judgment method suitable for vehicle-mounted short distance communication network
US20190385449A1 (en) System and method for providing automatic on-street parking control and unoccupied parking spot availability detection
CN104851295A (en) Method and system for acquiring road condition information
CN101136140A (en) Roads traffic speed calculating and matching method and system
CN104880193A (en) Lane-level navigation system and lane-level navigation method thereof
CN103489048B (en) A kind of Route Travel Time Estimation Method based on RFID data
CN113223293B (en) Road network simulation model construction method and device and electronic equipment
CN108184203A (en) Multistage preventing control method, device, equipment and medium based on operator's position signaling
CN107085620A (en) A kind of taxi and subway are plugged into the querying method and system of travel route
CN105160867A (en) Traffic information prediction method
Costanzo An arduino based system provided with GPS/GPRS shield for real time monitoring of traffic flows
Gore et al. Exploring credentials of Wi‐Fi sensors as a complementary transport data: an Indian experience
CN109754606A (en) A method of based on taxi location prediction congestion in road situation
EP3010255A1 (en) Method, system, user terminal and computer programs for estimating user terminal mobile paths through cellular network and map information
CN110349428A (en) Whether identification user is going to the method and device of bus station
US11069231B2 (en) Method and system of linear road sampling providing road traffic flow measurements
CN105702034B (en) Intelligent traffic administration system based on monocular vision and route information method for pushing and system
Ramburn et al. DriveMU: A Real-time Road-Traffic Monitoring Android Application for Mauritius

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant