CN107784835B - Traffic state mode prediction system based on traffic data analysis and prediction method thereof - Google Patents
Traffic state mode prediction system based on traffic data analysis and prediction method thereof Download PDFInfo
- Publication number
- CN107784835B CN107784835B CN201710070741.0A CN201710070741A CN107784835B CN 107784835 B CN107784835 B CN 107784835B CN 201710070741 A CN201710070741 A CN 201710070741A CN 107784835 B CN107784835 B CN 107784835B
- Authority
- CN
- China
- Prior art keywords
- traffic
- intersection
- vehicle
- data
- road
- 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.)
- Active
Links
- 238000007405 data analysis Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 title claims description 24
- 238000004891 communication Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000007423 decrease Effects 0.000 claims description 7
- 238000007418 data mining Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 6
- 238000010295 mobile communication Methods 0.000 description 4
- 238000013480 data collection Methods 0.000 description 1
Images
Classifications
-
- G06Q50/40—
-
- 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
Abstract
The invention relates to a traffic state mode prediction system based on traffic data analysis, which comprises: a queue length estimating unit that receives, from the cloud server, vehicle passage time information and vehicle speed information of a first intersection or a second intersection, which are measured by a first beacon installed on the first intersection or a sensor capable of measuring a queue length of a waiting vehicle on the first intersection or a second beacon installed on a second intersection adjacent to the first intersection or a sensor capable of measuring a queue length of a waiting vehicle on the second intersection, and estimates a queue length of a vehicle entering the first intersection but not having passed the second intersection, based on the vehicle passage time information and the vehicle speed information of the first intersection or the second intersection; a traffic volume estimation unit; a traffic volume correction unit; and a traffic state information arithmetic unit.
Description
Technical Field
The invention relates to a traffic state mode prediction system based on traffic data analysis and a prediction method thereof, in particular to a system for predicting a future traffic state mode in an optimal mode after correcting estimated traffic volume data based on historical traffic data of each road section and a prediction method thereof.
Background
The statements in the background section, which are included to enhance an understanding of the background of the invention, may include statements that are not prior art to the ordinary skill in the art.
A conventional traffic information supply system is an equipment device for collecting specific traffic information using various instruments such as an electromagnetic vehicle detector for grasping a vehicle speed from a remaining amount due to a variation amount of a magnetic beam when the vehicle moves after passing a current through a circular wire buried in a road, a Closed Circuit Television (CCTV) lens installed on the road, a speed detector installed on the road, and the like. The existing traffic information providing system controls signal lights using traffic information collected by the above-mentioned instruments or provides information on roads to users in a wireless or wired manner, and collects traffic information in real time and then delivers it to users.
Also, recently, various content services using mobile communication terminals have appeared with the increase of users carrying mobile communication terminals. One of the content services is a service for receiving information on a departure point and a destination from a mobile communication terminal provided in a traveling vehicle and wirelessly informing the shortest route from the departure point to the destination. For example, after a user inputs a departure place name and a destination place name in the form of voice or short message into a mobile communication terminal or an independent navigator terminal, path information from the departure place to the destination is generated and provided to the driver in the form of voice, short message, signal sound, or the like.
However, the conventional traffic jam information provision service cannot accurately predict the traffic state of a specific road at a specific time point in real time based on the historical traffic data of each road section. Furthermore, it is not only impossible to optimize the signal cycle of each road section, but also the signal cycle of the unit of urban area to which a plurality of road sections belong.
Documents of the prior art
Patent document 1: korean laid-open patent publication No. 2006-0037481 (2007.03.28 publication)
Disclosure of Invention
The present invention is directed to solving the above-mentioned problems of the prior art, and an object of the present invention is to provide a traffic status pattern prediction system and a prediction method thereof, which can accurately predict a traffic status of a specific road in real time at a specific time point based on historical traffic data of each road section stored in a cloud server.
Further, another object of the present invention is to provide a traffic state pattern prediction system and a prediction method thereof, which not only optimize a signal cycle of each road section, but also further optimize a signal cycle of a unit of a metropolitan area to which a plurality of road sections belong.
A traffic state pattern prediction system based on traffic data analysis according to an embodiment of the present invention includes: a queue length estimating unit that receives, from the cloud server, vehicle passage time information and vehicle speed information of a first intersection or a second intersection measured by a first beacon (beacon) installed on the first intersection or a sensor capable of measuring a queue length of a waiting vehicle on the first intersection or a second beacon installed on a second intersection adjacent to the first intersection or a sensor capable of measuring a queue length of a waiting vehicle on the second intersection, and estimates a queue length of a vehicle that has not passed through the second intersection after entering the first intersection, based on the vehicle passage time information and the vehicle speed information of the first intersection or the second intersection; the traffic estimation unit is used for calculating the traffic density of each road section between the first cross road and the second cross road by using the estimated queuing length and estimating the traffic; a traffic volume correction unit for correcting the estimated traffic volume data based on the historical traffic data of each road section stored in the cloud server; and a traffic state information calculation unit for calculating the traffic state mode and the traffic flow rate of each road section at each time interval by applying a data mining and mode matching method to the corrected traffic flow data.
Here, the first beacon or the sensor capable of detecting the length of the queue of the waiting vehicle on the first intersection and the second beacon or the sensor capable of detecting the length of the queue of the waiting vehicle on the second intersection detect the time when the vehicle passes through the first intersection or the second intersection and the speed of the vehicle passing through the first intersection or the second intersection by wireless communication with the portable terminal of the passenger in the vehicle.
Further, the queue length estimating unit estimates the vehicle queue length after identifying a specific location of the road section where the vehicle speed decreases from above the preset speed to below the preset speed.
Also, the historical traffic data is based on the travel speed and travel time of the specific time period and the specific road section.
The traffic volume correction unit analyzes the pattern of the historical traffic data, and corrects the traffic data of the road sections and the time periods which are not collected by the historical traffic data of the road sections and the time periods.
The traffic state information calculation means then obtains the real-time signal cycle of the first intersection or the second intersection based on machine learning from the calculated traffic state pattern and traffic flow rate of each road section.
The traffic flow division ratio is a right traffic flow ratio, a left traffic flow ratio, and a straight traffic flow ratio with respect to the traffic flow flowing into each road section.
The traffic volume correction unit corrects the estimated traffic volume data with the historical traffic data of each road section having the highest similarity by means of pattern matching between the estimated traffic volume data and the historical traffic data of each road section.
The traffic volume correction means calculates the euclidean distance between the estimated traffic volume data and the historical traffic data of each road section, and calculates the similarity value using the calculated euclidean distance.
A traffic state pattern prediction method based on traffic data analysis according to an embodiment of the present invention is a traffic state pattern prediction method using a traffic state pattern prediction system based on traffic data analysis, including the steps of: a first beacon arranged on a first cross road or a sensor capable of measuring the queuing length of waiting vehicles on the first cross road, or a second beacon arranged on a second cross road adjacent to the first cross road or a sensor capable of measuring the queuing length of waiting vehicles on the second cross road, measures the vehicle passing time information and the vehicle speed information of the first cross road or the second cross road and then sends the information to a cloud server; the method comprises the steps that after vehicle passing time information and vehicle speed information of a first crossroad or a second crossroad are received from a cloud server, the queuing length of vehicles which do not pass through the second crossroad after entering the first crossroad is estimated; calculating the traffic density of each road section between the first intersection road and the second intersection road by using the estimated queuing length, and then estimating the traffic; correcting the estimated traffic data on the basis of historical traffic data of each road section stored in the cloud server; and calculating the traffic state mode and the traffic flow split rate of each road section in each time period by applying a data mining and mode matching method to the corrected traffic flow data.
According to the invention, the traffic state of the specific road can be accurately predicted in real time at a specific time based on the historical traffic data of each road section stored in the cloud server.
According to the present invention, it is possible to optimize not only the signal cycle of each road section but also the signal cycle of each urban area unit to which a plurality of road sections belong.
Drawings
Fig. 1 is a diagram for explaining a road condition overview of a traffic state pattern prediction system based on traffic data analysis according to an embodiment of the present invention.
Fig. 2 is an organizational diagram of a traffic status pattern prediction system based on traffic data analysis according to one embodiment of the invention.
Fig. 3 is a schematic diagram for explaining calculation of euclidean distances according to an embodiment of the present invention.
FIG. 4 is a screen illustrating road segments and historical traffic data according to one embodiment of the invention.
Fig. 5 is a screen showing vehicle speed with respect to time according to an embodiment of the present invention.
Fig. 6 is a schematic view for explaining a traffic division ratio according to an embodiment of the present invention.
Fig. 7 is a screen illustrating multiple intersection traffic data in units of nets according to an embodiment of the present invention.
Fig. 8 is a flowchart of a traffic status pattern prediction method based on traffic data analysis according to an embodiment of the present invention.
Description of reference numerals
10: first beacons or sensors able to measure the length of the queue of waiting vehicles on the first cross road
20: second beacons or sensors capable of measuring the length of the queue of waiting vehicles on the second cross road
30: cloud server
100: queue length estimation unit
200: traffic volume estimation unit
300: traffic volume correction unit
400: traffic state information arithmetic unit
Detailed Description
The advantages, features and methods of accomplishing the same will become apparent from the following detailed description of the embodiments when taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, and the present invention can be implemented in various forms, which are different from each other, and the embodiments are only for facilitating the complete disclosure of the present invention, and the main purpose of the present invention is to fully explain the scope of the present invention to those having ordinary skill in the art to which the present invention pertains, and the scope of the present invention can be defined only by the claims.
Fig. 1 is a diagram for explaining a road condition overview of a traffic state pattern prediction system based on traffic data analysis according to an embodiment of the present invention.
The traffic state mode of one embodiment of the present invention refers to such things as traffic mix and hazard type and hazard rate.
Referring to fig. 1, there are a first intersection and a second intersection on the road, and there are vehicles passing through or waiting in line between the first intersection and the second intersection. Further, since the first intersection and the second intersection are provided with the first beacon or the sensor 10 and the second beacon capable of measuring the length of the queue of the waiting vehicle on the first intersection or the sensor 20 capable of measuring the length of the queue of the waiting vehicle on the second intersection, respectively, the first beacon or the sensor 10 and the second beacon or the sensor 20 are connected to the cloud server 30 close server in wireless communication, and the cloud server 30 is connected to the traffic state pattern prediction system in wireless communication, the traffic state pattern prediction system can receive the vehicle elapsed time information and the vehicle speed information of the first intersection or the second intersection from the cloud server 30.
The traffic state pattern prediction application APP needs to be installed in the portable terminal for wireless communication with the first beacon or the sensor 10 capable of measuring the length of the queue of the waiting vehicle on the first cross road or the second beacon or the sensor 20 capable of measuring the length of the queue of the waiting vehicle on the second cross road. The portable terminal may use any portable terminal such as a smart phone, a tablet computer, a PC, and the like.
When the vehicle passes through the second intersection after passing through the first intersection, the first beacon 10 or the sensor detects the time when the vehicle passes through the first intersection and the speed of the vehicle passing through the first intersection by wireless communication with the portable terminal of the vehicle occupant. Further, the second beacon 20 or the sensor detects the time when the vehicle passes through the second intersection and the speed of the vehicle passing through the second intersection by wireless communication with the portable terminal of the passenger in the vehicle.
The second beacon 20 or the sensor cannot detect the time when the vehicle passes the second intersection and the speed of the vehicle passing the second intersection while the vehicle is waiting without passing the second intersection. In this case, the length of the queue in which the vehicle waits may be estimated, and the length of the queue may be estimated from the vehicle elapsed time information and the vehicle speed information of the first intersection or the second intersection. The speed of the vehicle waiting before passing the second intersection will gradually decrease and the vehicle speed information can be used for estimation of the length of the queue. X in fig. 1 represents a distance from the first intersection, and v represents a speed of the vehicle. As can be seen from fig. 1, the speed of the vehicle sharply decreases after passing through the first intersection and the rate of speed decrease at the specific point a is moderate.
Fig. 2 is an organizational diagram of a traffic status pattern prediction system based on traffic data analysis according to one embodiment of the invention. Referring to fig. 1 and 2, the traffic state pattern prediction system based on traffic data analysis may include a queue length estimation unit 100, a traffic volume estimation unit 200, a traffic volume correction unit 300, and a traffic state information calculation unit 400.
The queue length estimating unit 100 receives vehicle transit time information and vehicle speed information of a first intersection or a second intersection measured by a first beacon installed on the first intersection or a sensor 10 capable of measuring the queue length of a waiting vehicle on the first intersection, or a second beacon installed on a second intersection adjacent to the first intersection or a sensor 20 capable of measuring the queue length of a waiting vehicle on the second intersection, from the cloud server 30. Here, the first beacon 10 or the sensor and the second beacon 20 or the sensor detect the time when the vehicle passes through the first intersection or the second intersection and the speed of the vehicle passing through the first intersection or the second intersection by wireless communication with the portable terminal of the passenger in the vehicle. The first beacon 10 or the sensor or the second beacon 20 or the sensor receives Vehicle elapsed time information from the portable terminal through V2I (Vehicle to Infrastructure) communication and Vehicle speed information from the portable terminal through M2C communication.
Then, queue length estimation section 100 estimates the queue length of a vehicle that has not passed through the second intersection after entering the first intersection, based on the vehicle passage time information and the vehicle speed information of the first intersection or the second intersection. At this time, the queue length estimation unit 100 estimates the queue length of the vehicle after recognizing the specific location (a of fig. 1) of the road section where the vehicle speed decreases from above the preset speed to below the preset speed. The way of estimating the queue length is not limited to this.
The traffic estimating unit 200 estimates the traffic by obtaining the traffic density of each road section between the first intersection and the second intersection using the queuing length estimated by the queuing length estimating unit 100.
The traffic volume correction unit 300 corrects the traffic volume data estimated by the traffic volume estimation unit 200 based on the historical traffic data big data of each road section stored in the cloud server. The reason why the estimated traffic data is corrected based on the historical traffic data as described above is that it is necessary to reflect traffic data caused by external influences (external force) such as weather and non-integrity of data collection hardware (hardware) on the estimated traffic data. Therefore, the traffic data of the road specific position and the specific time period which are not acquired can be corrected. The historical traffic data includes, but is not limited to, a traveling speed and a traveling time of a specific time zone and a specific road section.
Furthermore, since the historical traffic data of each road section stored in the cloud server 30 becomes increasingly huge as time passes, the estimated traffic volume data can be corrected more accurately. The reason why the estimated data can be corrected more accurately as described above is that the cloud server 30 is used, which solves the existing problem that huge data cannot be stored.
The traffic volume correction unit 300 analyzes a pattern of historical traffic data such as traffic congestion and a type of danger and a danger rate, and corrects traffic data of a road section and a period of time that are not collected with the historical traffic data of the road section and the period of time. Specifically, the traffic volume correction unit 300 corrects the estimated traffic volume data with the historical traffic data of each road section having the highest similarity by pattern matching of the estimated traffic volume data and the historical traffic data of each road section. At this time, the traffic volume correction unit 300 calculates euclidean distances (distances) between the estimated traffic volume data and the historical traffic data of each road section, and calculates the similarity value using the calculated euclidean distances.
The traffic state information arithmetic unit 400 calculates the traffic state pattern and the traffic flow splitting rate of each road section at each time period by applying data mining and a pattern matching method (pattern matching method) to the traffic volume data corrected by the traffic volume correction unit 300. Then, the traffic state information calculation unit 400 obtains a real-time signal cycle of the first intersection or the second intersection based on machine learning (machine running) from the calculated traffic state pattern and traffic flow rate of each road section. Machine learning is a technique for predicting the future by analyzing enormous large data such as data generation, amount, period, form, and the like, and a detailed description thereof will be omitted here since it is a known manner. The real-time signal period is a period until the blue signal lamp is turned on again after the blue signal lamp is turned on, or a period until the red signal lamp is turned on again after the red signal lamp is turned on. The traffic flow division ratio is a right-turn traffic flow ratio, a left-turn traffic flow ratio, and a straight-going traffic flow ratio with respect to the traffic flow flowing into each road section.
Fig. 3 is a schematic diagram for explaining calculation of euclidean distances according to an embodiment of the present invention. Referring to fig. 3, a method of calculating the euclidean distance from traffic data representing the estimation of the subject data (subject data) and the historical traffic data (historical data) of each road section can be known.
The part shown as "X" in the subject data and the historical traffic data of each road section is missing data (missing data) of the estimated traffic volume data. The euclidean distance is displayed as "X" for the portion shown as "X" in the subject data or the historical traffic data of each road section. Fig. 3 shows two cases (Case 1, Case 2), which can be known to calculate the euclidean distance according to this principle.
FIG. 4 is a screen illustrating road segments and historical traffic data according to one embodiment of the invention. Referring to fig. 4, fig. 4 shows a road section and historical traffic data.
The portion shown in a square shape in the left graph is a road section between 2 adjacent intersections, and the right data is historical traffic data having a Travel Speed (Link Speed (km/h)) and a Travel Time (Link Travel _ Time (s)) based on a specific Time Period (Time _ Period) and a specific road section (Link Number). The specific period is preset in units of 5 minutes, but is not limited thereto. The road sections are divided into 6, such as 1-6, and the left graph divides each road section into Link (section) 1, Link 2, Link 3, Link 4, Link 5 and Link 6.
The travel speed in road section No. 1 from point 8, 30 to point 8, 35 is 19km/h and the travel time is 28(s). Here, the specific period is set to 5 minutes, but is not limited thereto.
Fig. 5 is a screen showing vehicle speed with respect to time according to an embodiment of the present invention. Referring to fig. 5, the vehicle speed variation occurring with the passage of time in a specific road section can be known.
Red indicates the predicted value of the vehicle speed, and blue indicates the measured value.
Fig. 6 is a schematic view for explaining a traffic division ratio according to an embodiment of the present invention. Referring to fig. 6, the inflow traffic volume, the right traffic volume ratio a, the left traffic volume ratio β, and the straight traffic volume ratio γ at the road sections (road links) 1, 2, and 3 are shown.
As can be seen from the figure, the traffic volume of the road section 1 is 1000, the right traffic volume ratio a, the left traffic volume ratio β, and the direct traffic volume ratio γ are 0.3, 0.2, and 0.5, respectively, the traffic volume of the road section 2 is 800, the right traffic volume ratio a, the left traffic volume ratio β, and the direct traffic volume ratio γ are 0.7, 0.1, and 0.2, respectively, the traffic volume of the road section 3 is 500, and the right traffic volume ratio a, the left traffic volume ratio β, and the direct traffic volume ratio γ are 0.5, 0.3, and 0.2, respectively.
Therefore, the right traffic ratio a is highest in the road section 2, the left traffic ratio β is highest in the road section 3, and the straight traffic ratio γ is highest in the road section 1.
Fig. 7 is a screen illustrating multiple intersection traffic data in units of a network (network) according to an embodiment of the present invention. Referring to FIG. 7, each intersection is shown in a different color, each showing vehicle speed.
As can be seen from the graph, the closer to red from green, the higher the vehicle speed. Therefore, the vehicle driver can quickly grasp the path with smooth vehicle speed and then drive the vehicle to the required destination.
One net in the road in units of nets as described above may be set as a plurality of subnets, and a subnet may be constituted by a plurality of intersections. Taking the highway as an example, the sub-network can be set as a section with large traffic flow variation, such as a good IC-field IC section, a field IC-north cuu IC section, and the like.
Fig. 8 is a flowchart of a traffic status pattern prediction method based on traffic data analysis according to an embodiment of the present invention. Referring to fig. 1, 2 and 8, a traffic state pattern prediction method based on traffic data analysis utilizes the traffic state pattern prediction system of fig. 2 and is described as follows. For a detailed description of the steps, reference will be made to fig. 1 and 2 above.
First, the first beacon 10 installed on the first intersection, the sensor capable of measuring the length of the queue of the waiting vehicle on the first intersection, the second beacon 20 installed on the second intersection adjacent to the first intersection, or the sensor capable of measuring the length of the queue of the waiting vehicle on the second intersection, measures the vehicle passing time information and the vehicle speed information of the first intersection or the second intersection (S100), and transmits the measured information to the cloud server 30 (S100').
After the step (S100'), the cloud server 30 stores the vehicle elapsed time information and the vehicle speed information received from the first intersection or the second intersection of the first beacon 10 or the sensor or the second beacon 20 or the sensor (S200).
After the step (S2OO), the queue length estimation unit 100 receives the vehicle elapsed time information and the vehicle speed information of the first intersection or the second intersection from the cloud server 30 (S200'), and then estimates the queue length of the vehicle that has not yet passed the second intersection after entering the first intersection (S300).
After the step (S300), the traffic estimating unit 200 receives the queuing length estimated by the queuing length estimating unit 100 (S300'), obtains the traffic density of each road section between the first intersection and the second intersection using the estimated queuing length, and estimates the traffic (S400).
After the step (S400), the traffic volume correction unit 300 receives the traffic volume data estimated by the traffic volume estimation unit 200 (S400'), and then corrects the estimated traffic volume data based on the historical traffic data of each road section stored by the cloud server 30 (S500).
After the step (S500), the traffic state information arithmetic unit 400 receives the traffic volume data corrected by the traffic volume correction unit 300 (S500'), and calculates the traffic state pattern and the traffic volume flow rate of each road section at each time slot by applying the data mining and pattern matching method to the corrected traffic volume data (S600).
While the foregoing is directed to embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow. Therefore, the true technical scope of the present invention should be defined by the claims.
Claims (5)
1. A traffic state pattern prediction system based on traffic data analysis is characterized in that,
the method comprises the following steps:
a queue length estimating unit that receives, from a cloud server, vehicle passage time information and vehicle speed information of a first intersection or a second intersection on which a first beacon attached to the first intersection or a sensor capable of measuring a queue length of a waiting vehicle on the first intersection or a second beacon attached to a second intersection adjacent to the first intersection or a sensor capable of measuring a queue length of a waiting vehicle on the second intersection, and estimates a queue length of a vehicle entering the first intersection but not having passed through the second intersection, based on the vehicle passage time information and the vehicle speed information of the first intersection or the second intersection;
a traffic estimating unit that estimates traffic by obtaining a traffic density of each road section between the first intersection and the second intersection using the estimated queuing length;
a traffic volume correction unit for correcting the estimated traffic volume data based on the historical traffic data of each road section as big data stored in the cloud server; and
a traffic state information calculation unit for calculating the traffic state mode and traffic flow rate of each road section in each time period by applying a data mining and mode matching method to the corrected traffic volume data,
the first beacon or the sensor capable of detecting the length of the waiting vehicle in the first intersection and the second beacon or the sensor capable of detecting the length of the waiting vehicle in the second intersection detect the time when the vehicle passes through the first intersection or the second intersection and the speed of the vehicle passing through the first intersection or the second intersection by wireless communication with a portable terminal of a passenger in the vehicle,
the above-mentioned queuing length estimating unit estimates the vehicle queuing length after identifying a specific location of a road section where the vehicle speed decreases from above the preset speed to below the preset speed,
the historical traffic data is based on the travel speed and travel time of a specific time period and a specific road section,
the traffic volume correction unit analyzes the pattern of the historical traffic data, corrects the traffic data of the road sections and the time periods which are not collected by the historical traffic data of the road sections and the time periods,
the traffic state information calculation means obtains a real-time signal cycle of the first intersection or the second intersection based on machine learning from the calculated traffic state pattern and traffic flow rate of each road section,
the traffic flow division ratio is a right traffic flow ratio, a left traffic flow ratio, and a straight traffic flow ratio with respect to the traffic flow flowing into each road section.
2. The traffic-data-analysis-based traffic-status-pattern prediction system of claim 1,
the traffic volume correcting unit corrects the estimated traffic volume data with the historical traffic data of the road sections having the highest similarity by means of pattern matching of the estimated traffic volume data and the historical traffic data of the road sections.
3. The traffic-data-analysis-based traffic-status-pattern prediction system of claim 2,
the traffic volume correction unit calculates euclidean distances between the estimated traffic volume data and the historical traffic data of the road sections, and calculates similarity values using the calculated euclidean distances.
4. The traffic-data-analysis-based traffic-status-pattern prediction system of claim 1,
the traffic state modes include traffic mix and danger types and danger rates.
5. A traffic state pattern prediction method based on traffic data analysis, which utilizes a traffic state pattern prediction system based on traffic data analysis, is characterized in that,
comprises the following steps:
a first beacon installed on a first cross road or a sensor capable of measuring the queuing length of waiting vehicles on the first cross road, or a second beacon installed on a second cross road adjacent to the first cross road or a sensor capable of measuring the queuing length of waiting vehicles on the second cross road, wherein the first beacon is used for measuring the vehicle passing time information and the vehicle speed information of the first cross road or the second cross road, and then the vehicle passing time information and the vehicle speed information are sent to a cloud server;
estimating a queuing length of a vehicle entering the first intersection but not passing through the second intersection after receiving vehicle passing time information and vehicle speed information of the first intersection or the second intersection from the cloud server;
calculating the traffic density of each road section between the first intersection and the second intersection by using the estimated queuing length, and then estimating the traffic;
correcting the estimated traffic data on the basis of the historical traffic data of each road section as big data stored in the cloud server; and
calculating the traffic state mode and traffic flow rate of each road section in each time period by applying a data mining and mode matching method to the corrected traffic flow data,
the first beacon or the sensor capable of detecting the length of the waiting vehicle in the first intersection and the second beacon or the sensor capable of detecting the length of the waiting vehicle in the second intersection detect the time when the vehicle passes through the first intersection or the second intersection and the speed of the vehicle passing through the first intersection or the second intersection by wireless communication with a portable terminal of a passenger in the vehicle,
the vehicle queue length is estimated after identifying a specific location of a road section where the vehicle speed decreases from above a preset speed to below the preset speed,
the historical traffic data is based on the travel speed and travel time of a specific time period and a specific road section,
and analyzing the pattern of the historical traffic data, correcting the traffic data of the road sections and the time periods which are not collected by the historical traffic data of the road sections and the time periods,
obtaining a real-time signal period of the first intersection or the second intersection based on machine learning from the calculated traffic state pattern and traffic flow rate of each road section,
the traffic flow division ratio is a right traffic flow ratio, a left traffic flow ratio, and a straight traffic flow ratio with respect to the traffic flow flowing into each road section.
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 CN107784835A (en) | 2018-03-09 |
| CN107784835B true 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) |
Families Citing this family (14)
| 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 |
| KR20190114127A (en) * | 2018-03-29 | 2019-10-10 | 주식회사 블루시그널 | Mehtod of providing distribution delivery route using predicted traffic information and server performing the same |
| 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 |
| 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 |
| CN110164132B (en) * | 2019-05-29 | 2020-03-06 | 浙江警察学院 | Method and system for detecting road traffic abnormity |
| 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 |
| 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 |
| CN112820123B (en) * | 2020-08-27 | 2022-04-08 | 湖南湘江智芯云途科技有限公司 | Intelligent green wave adjusting method and intelligent green wave adjusting system for traffic signal lamp |
| CN112489423B (en) * | 2020-11-20 | 2022-06-03 | 湖南警察学院 | Vision-based urban road traffic police command method |
| 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 |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004118735A (en) * | 2002-09-27 | 2004-04-15 | Toyota Central Res & Dev Lab Inc | Traffic situation estimation device and od traffic volume correction device |
| 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 |
| 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 |
| 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 |
| 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 (6)
| 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 |
| 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 |
| CN100416584C (en) * | 2005-01-19 | 2008-09-03 | 北京交通大学 | Road traffic flow data quality controlling method and apparatus |
| CN103914988B (en) * | 2013-01-04 | 2016-12-28 | 中国移动通信集团公司 | A kind of traffic road condition data processing method, device and system |
| CN105118294B (en) * | 2015-09-25 | 2017-03-29 | 山东易构软件技术股份有限公司 | A kind of Short-time Traffic Flow Forecasting Methods based on state model |
| CN105489018B (en) * | 2016-02-19 | 2017-09-29 | 上海果路交通科技有限公司 | A kind of intersection traffic signals control system method |
-
2016
- 2016-08-30 KR KR1020160110719A patent/KR101703058B1/en active Search and Examination
-
2017
- 2017-02-09 CN CN201710070741.0A patent/CN107784835B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004118735A (en) * | 2002-09-27 | 2004-04-15 | Toyota Central Res & Dev Lab Inc | Traffic situation estimation device and od traffic volume correction device |
| 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 |
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| KR101703058B1 (en) | 2017-02-06 |
| CN107784835A (en) | 2018-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107784835B (en) | Traffic state mode prediction system based on traffic data analysis and prediction method thereof | |
| JP4809321B2 (en) | Traffic information calculation device, traffic information calculation program, and traffic information calculation method | |
| WO2015166876A1 (en) | Traffic signal control device, traffic signal control method, and computer program | |
| US10475336B2 (en) | System for forecasting traffic condition pattern by analysis of traffic data and forecasting method thereof | |
| JP5256924B2 (en) | Traffic jam information generating apparatus, computer program, and traffic jam information generating method | |
| JP5435041B2 (en) | Traffic light cycle estimation device and traffic light cycle estimation method | |
| JP2009193212A (en) | Road traffic information system | |
| US20200143672A1 (en) | Traffic congestion estimating device, traffic congestion estimating method, and recording medium storing program thereof | |
| CN108171968A (en) | The road condition analyzing system and method for position data based on mobile terminal device signaling | |
| CN104819721A (en) | Navigation system | |
| KR20140119471A (en) | System for correcting and providing real-time dangerous road-section information based on device in the car and its method | |
| JP2021182332A (en) | Congestion prediction information provision system, congestion prediction information provision method, and congestion prediction information provision program | |
| JP2016133942A (en) | Traffic index calculation device, traffic index calculation method and computer program | |
| JP2005032226A (en) | Device for processing measured data, and measured data processing system | |
| JP5459837B2 (en) | Emergency vehicle support device, emergency vehicle support system, and emergency vehicle support method | |
| US11421999B2 (en) | Route selection using correction factors indicating phase interruptible traffic signals | |
| KR20090090049A (en) | Apparatus and method for real-time traffic information service | |
| US11348457B2 (en) | Analysis device and analysis method | |
| JP3748420B2 (en) | FCD system and apparatus using beacon | |
| JP2013214232A (en) | Traffic information prediction device, method for predicting traffic information, and computer program | |
| KR101773171B1 (en) | Bus Information Guidance System using Bus Information Terminal | |
| Minh et al. | Traffic state estimation with mobile phones based on the “3R” philosophy | |
| JP4635696B2 (en) | Road-to-vehicle communication device | |
| JP2018018129A (en) | Information providing method and information providing device | |
| KR102203569B1 (en) | Method and system for evaluating traffic signal operation based on communication data |
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 |