JP5071461B2 - Traffic information estimation apparatus, computer program for traffic information estimation, and traffic information estimation method - Google Patents

Description

  The present invention relates to a traffic information estimation device for estimating traffic information, a computer program for traffic information estimation, and a traffic information estimation method.

As a technology for providing road traffic information to drivers, VICS (Vehicle Information and Communication System: “VICS” is a registered trademark of the foundation) is widely known.
This VICS tabulates traffic information including traffic congestion and link travel time on each route based on fixed point observation information consisting of the number of vehicles, vehicle speed, etc. collected from various roadside sensors (vehicle detectors, loop coils, etc.). The traffic information is provided to the driver by wide-area communication such as narrow-area communication using beacons or FM broadcasting.

As another technique for providing road traffic information to a driver, a traffic information estimation system using a probe car (hereinafter referred to as a probe system) is also known.
For example, as shown in Patent Documents 1 and 2, this probe system uses a vehicle (probe vehicle) that actually travels on a road as a moving body sensor, and wirelessly transmits probe information such as the current vehicle position and time. It is collected from each probe vehicle by communication and generates road traffic information.

Japanese Patent Laid-Open No. 5-151696 Japanese Patent Laying-Open No. 2005-4467

  However, even if the VICS and the probe system are used, traffic information cannot be obtained for road links for which no data is obtained from either the VICS or the probe system.

  Therefore, an object of the present invention is to provide a new technique for estimating traffic information of an estimation target road link that is another road link for which traffic information is not obtained based on the traffic information of the road link. To do.

(1) The present invention is a traffic information estimation device including an estimation unit that estimates traffic information of other road links based on traffic information of road links, and acquires traffic information of a plurality of road links. Based on the traffic information acquired by the acquisition unit and the traffic information of one road link, and estimated information for estimating traffic information of another road link from traffic information of one road link, A calculation unit for obtaining a correlation; and a selection unit that selects a road link in which the correlation is recognized to be equal to or higher than a predetermined level as a selection group. The acquisition unit is obtained from the probe information transmitted from a probe vehicle as the traffic information. In addition to the probe traffic information, fixed point traffic information obtained from fixed point observation information collected using roadside sensors installed on the road can be acquired. Seeking and the correlation between the estimated information based on the respective chromatography Bed traffic information and the fixed-point traffic information, the estimation unit, the traffic information of the road link is obtained, it is within the selected group including the road links Traffic information of other road links is estimated based on estimated information having a higher correlation by comparing the correlation based on the probe traffic information and the correlation based on the fixed point traffic information.

According to the present invention, the selection unit selects, as a selection group, a road link in which the correlation between the traffic information of each road link is recognized at a predetermined level or more. Therefore, the traffic information of the road links included in the selection group is selected. It can be said that the correlation is high.
Therefore, when traffic information of a certain road link is acquired, the estimation unit estimates traffic information of other road links in the selected group including the road link based on the estimated information. The reliability of traffic information on other road links is high.
In addition to the probe traffic information, when the fixed point traffic information can be acquired, the estimation unit compares the correlation based on the probe traffic information with the correlation based on the fixed point traffic information, and based on the estimated information having the higher correlation. Therefore, the reliability of the estimated road information can be further increased.

(2) The present invention is a traffic information estimation apparatus including an estimation unit that estimates traffic information of other road links based on traffic information of road links, and acquires traffic information of a plurality of road links Based on the traffic information acquired by the acquisition unit and the traffic information of one road link, and estimated information for estimating traffic information of another road link from traffic information of one road link, According to an index related to the number of other road links for which traffic information is estimated by the estimation unit, a calculation unit for obtaining a correlation, a selection unit for selecting a road link in which the correlation is recognized at a predetermined level or more as a selection group, and the estimation unit and an adjustment unit for adjusting the predetermined level, the estimation unit, the traffic information of the road link is obtained, other road link in the selected group including the road links Traffic information, and estimates based on the estimated information.

According to the present invention, the selection unit selects, as a selection group, a road link in which the correlation between the traffic information of each road link is recognized at a predetermined level or more. Therefore, the traffic information of the road links included in the selection group is selected. It can be said that the correlation is high.
Therefore, when traffic information of a certain road link is acquired, the estimation unit estimates traffic information of other road links in the selected group including the road link based on the estimated information. The reliability of traffic information on other road links is high.
Further, the adjustment may be made according to the situation such as when it is desired to increase the number of road links whose traffic information is estimated by the estimation unit, or when priority is given to the level of correlation (that is, the strength of correlation) over the number. The unit can adjust the predetermined level.

(3) Moreover, in the traffic information estimation apparatus according to (2), the estimation information is obtained based on probe information transmitted from a probe vehicle and acquired by the acquisition unit, and the estimation unit is connected to another road link. In order to estimate the traffic information, the road information of the acquired road link can be based on the probe information transmitted from the probe vehicle.
In this case, the estimation information is obtained based on the probe information transmitted from the probe vehicle and acquired by the acquisition unit. Further, based on the probe information transmitted from the probe vehicle, the estimation unit calculates the traffic information of the road link. Estimation is performed.
For this reason, for example, even when it is not possible to acquire fixed point observation information (for example, VICS information) collected using a roadside sensor installed on the road, based on the probe information transmitted from the probe vehicle, It is possible to estimate road link traffic information.

( 4 ) Moreover, this invention is a computer program for functioning a computer as a traffic information estimation apparatus as described in any one of said (1)-( 3 ).

(5) Moreover, this invention is a traffic information estimation method which estimates the traffic information of another road link based on the traffic information of a road link, Comprising: The acquisition step which acquires the traffic information of several road links, On the basis of the acquired traffic information, estimation information for estimating traffic information of another road link from traffic information of one road link, and a calculation step for obtaining a correlation between the traffic information of each road link; A selection step of selecting a road link whose correlation is recognized at a predetermined level or more as a selection group, and when traffic information of the road link is acquired, traffic information of other road links in the selection group including the road link is obtained. And an estimation step of estimating based on the estimation information, and in the acquisition step, the traffic information is transmitted from the probe vehicle. In addition to the probe traffic information obtained from the lobe information, it is possible to obtain fixed point traffic information obtained from fixed point observation information collected using a roadside sensor installed on the road, and in the calculation step, the probe traffic information and The estimation information and the correlation are obtained based on each of the fixed point traffic information, and the estimation step compares the correlation based on the probe traffic information with the correlation based on the fixed point traffic information, and estimates the higher correlation The estimation is performed based on information.

According to the present invention, when traffic information of a certain road link is acquired, traffic information of another road link that is included in the selected group including the road link and has a high correlation is obtained based on the estimated information. Since it estimates, the reliability of the traffic information of the estimated other road link becomes high. As a result, it is possible to improve the accuracy of grasping the current traffic state and further predicting the future traffic state.

1 is an overall configuration diagram of a traffic information system. It is a block diagram of a traffic information estimation apparatus. It is explanatory drawing explaining a part of function of an acquisition part. It is explanatory drawing of the method of calculating the travel speed of a road link from probe information. It is a flowchart which shows the traffic information estimation method by a traffic information estimation apparatus. It is explanatory drawing of a 1st intermediate database. It is explanatory drawing which takes out and describes the speed information of one set of road links from the 1st intermediate database. It is explanatory drawing of a 2nd intermediate database. It is a figure which shows the example of a road link. It is a figure explaining the method of calculating | requiring a regression line, a contribution, etc. It is a figure explaining the method of calculating | requiring a regression line, a contribution, etc. It is explanatory drawing of a 2nd intermediate database. It is explanatory drawing of contribution matrix information.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
[1. overall structure]
FIG. 1 shows a traffic information system including a traffic information estimation device 1 of the present invention. In addition to the traffic information estimation device 1, this traffic information system includes a probe vehicle 3 equipped with an in-vehicle device 2, a roadside communication device 4 that communicates wirelessly with the in-vehicle device 2, a roadside sensor 5, and a VICS center 6.

  The traffic information estimation device 1 refers to one of various functions of a central control device provided in the traffic information system, for example. The traffic information estimation device 1 is a traffic information such as VICS information and probe information ( (Observation information) is obtained and traffic information for provision for providing to the vehicle is generated. The traffic information estimation device 1 may perform various traffic processing such as traffic signal control and traffic control based on the traffic information.

  The traffic information estimation device 1 can be configured by a computer having a processing device and a storage device. The storage device stores a computer program for causing a computer to function as the following traffic information estimation device 1. This computer program is executed by the processing device, and the processing device performs functions as the traffic information estimation device 1 by inputting and outputting to the storage device and the like. In addition, the below-mentioned estimation part 11 and input information processing part 16 (acquisition part 21, calculation part 22, selection part 23, adjustment part 24 (FIG. 2) which are each function parts with which the traffic information estimation apparatus 1 demonstrated below is provided. Unless otherwise specified, the reference)) is realized by the computer program.

  In FIG. 1, the in-vehicle device 2 generates probe information as observation information of the probe vehicle 3 and wirelessly transmits it to the roadside communication device 4. The probe information is traffic information including the position of the probe vehicle 3, the passing speed of the position, the vehicle ID of the probe vehicle 3, and the like. The position of the probe vehicle 3 is calculated based on a GPS signal received by a GPS receiver included in the in-vehicle device 2, and the speed of the probe vehicle 3 is calculated by an in-vehicle speed sensor.

  The roadside communication device 4 transmits and receives information to and from the in-vehicle device 2 by wireless communication. Specifically, the roadside communication device 4 receives probe information as observation information transmitted by the in-vehicle device 2 and transfers the probe information to the traffic information estimation device 1. Further, the roadside communication device 4 can acquire traffic information for provision to the vehicle from the traffic information estimation device 1 and transmit the traffic information to the in-vehicle device 2. The roadside communication device 4 and the traffic information estimation device 1 are connected by a communication line.

  The roadside sensor 5 measures, for example, a vehicle detector for ultrasonically detecting a vehicle passing underneath, a loop coil for detecting the vehicle by inductance change, or image processing of a camera image to measure traffic volume and vehicle speed. It consists of an image sensor. The roadside sensor 5 can measure the number of vehicles flowing into the intersection, vehicle speed, and the like as observation information, and is installed on a highway, a main trunk road, and the like for the purpose of acquiring such observation information.

  The observation information acquired by the roadside sensor 5 is transmitted to the server of the VICS center 6 via the communication line, and the server generates VICS information based on the observation information of the roadside sensor 5. This VICS information is transmitted to the traffic information estimation device 1 via a communication line.

The VICS information transmitted to the traffic information estimation device 1 is traffic information including a traffic jam situation and a link travel time on each road link. The VICS information is updated every time observation information is acquired from the roadside sensor 5 every 5 minutes, so that high-density information can be obtained in time. However, the roadside sensor 5 is not installed on all roads (20% or less on main roads), and the area coverage rate is low.
On the other hand, since the probe information is acquired from the probe vehicle 3 traveling on the road, the area coverage rate can be increased. However, since the penetration rate of the in-vehicle device 2 for becoming the probe vehicle 3 is still low, only low-density data can be obtained in terms of time.

  In the traffic information system of the present embodiment, a plurality of road links L1 to L10 are set on roads in a predetermined area (see FIG. 9), and the plurality of road links L1 to L10 are managed as one management group G. ing. In this case, among the plurality of road links L1 to L10 included in the management group G, for road links where the roadside sensor 5 is installed and VICS information is obtained, the VICS information is always updated every unit time. Traffic information (VICS information) can be obtained. On the other hand, for road links where the roadside sensor 5 is not installed and VICS information cannot be obtained, the road links and probe information from which probe information can be obtained as traffic information are obtained when viewed every update unit time of VICS information. Incompatible road links.

[2. Details of Traffic Information Estimator]
The traffic information estimation apparatus 1 according to the present embodiment estimates traffic information of a road link for which neither VICS information nor probe information is obtained, and complements the traffic information of the road link, so that a predetermined area (the management group Traffic information of all road links L1 to L10 in (G) is acquired. In this way, by supplementing road link traffic information for which neither VICS information nor probe information can be obtained, more accurate traffic information can be provided to the vehicle (navigation system), or traffic control can be performed with high accuracy. Is possible.
In the following, a road link for which traffic information is estimated and complemented without obtaining VICS information or probe information is referred to as an “estimation target road link”.

In the configuration diagram of FIG. 2, the traffic information estimation device 1 includes an estimation unit 11 that estimates traffic information of an estimation target road link in the management group G, and a road link in the management group G for performing this estimation. 1st intermediate database 12a and 2nd intermediate database 12b which accumulate | store the traffic information of L1-L10, and the estimation database (traffic information database) 13 for accumulating the traffic information etc. which were estimated by the estimation part 11 are provided. ing.
Although the estimation unit 11 will be described later, the traffic information of the estimation target road link in the management group G is related to the road link (related road link) in the management group G from which the traffic information can be acquired. Estimate based on traffic information.

In addition, the traffic information estimation device 1 has VICS information and probe information acquired by the traffic information estimation device 1 as functional units realized by the computer program (hereinafter, both information is referred to as “input information”). Is provided with an input information processing unit 16.
The input information processing unit 16 includes an acquisition unit 21, a calculation unit 22, a selection unit 23, and an adjustment unit 24. Although details of each of these functions will be described later, the acquisition unit 21 can acquire traffic information of a plurality of road links L1 to L10 in the management group G based on the input information. And the calculation part 22 is based on the traffic information which the acquisition part 21 acquired, the regression line as estimation information for estimating the traffic information of another road link from the traffic information of one road link in the management group G And the correlation (strength of correlation) between the traffic information of each of the plurality of road links in the management group G is obtained. Note that this correlation is the contribution of the regression line in the following embodiments. The selection unit 23 selects a predetermined road link from the management group G as a selection group. And the adjustment part 24 has a function which adjusts the below-mentioned threshold value (alpha) according to the parameter | index regarding the number of the estimation object road links whose traffic information is estimated by the estimation part 11. FIG.

  Some of the functions of the acquisition unit 21 will be described. The acquisition unit 21 performs processing for generating “travel speed” of each road link from the input information. The generated “travel speed” is given to the first intermediate database 12a. FIG. 3 is an explanatory diagram illustrating this function of the acquisition unit 21.

The acquisition unit 21 includes a VICS information processing unit 17 that generates “travel speed” from the acquired VICS information, and a probe information processing unit 18 that generates “travel speed” from the acquired probe information.
The VICS information processing unit 17 calculates the travel speed of the road link from the link travel time included in the VICS information obtained for a certain road link. That is, the travel speed [km / h] is calculated by dividing the link length of the road link for which the travel speed is to be calculated by the link travel time of the road link. The link lengths of all road links L1 to L10 in the management group G are set in the traffic information estimation device 1 in advance.

The probe information processing unit 18 calculates the travel speed [km / h] of the road link based on the position and time included in the probe information obtained in a certain road link. FIG. 4 shows a method of calculating the road link travel speed [km / h] from the probe information.
As shown in FIG. 4, when there are five continuous road links L1 to L4 and L10, in order to calculate the travel speed of the road link L3 to the right of the figure (direction of arrow A), The first probe information pr1 transmitted while the probe vehicle 3 is located on the road link L2 (first position) one direction ahead, and the road ahead of the direction of travel by moving the probe vehicle 3 The second probe information pr2 transmitted while being located at the link L4 (second position) is used.

  The distance D between the first position where the first probe information pr1 is transmitted and the second position where the second probe information pr2 is transmitted is determined by the position indicated by the first probe information pr1 and the position indicated by the second probe information pr2. . In addition, the time T required to move from the first position to the second position is determined by the time indicated by the first probe information pr1 and the time indicated by the second probe information pr2. By dividing the distance D by the time T, the travel speed of the section (normal speed calculation section) between the first position and the second position is obtained. Normally, this travel speed is regarded as the link travel speed on the road link L3 between the first position and the second position.

  However, when the distance D between the first position and the second position (the distance of the normal speed calculation section) is equal to or less than the set minimum distance (for example, 1 km), the speed calculation section becomes longer. Then, another piece of probe information is selected for use in calculating the link travel speed of the road link L3. Specifically, when the distance D of the normal speed calculation section is equal to or smaller than the minimum distance, the probe information processing unit 18 causes the vehicle 3 to be positioned on the road link L1 (front position) that is one more forward in the vehicle traveling direction. The probe information pr0 transmitted when it is located and the probe information pr2 transmitted when it is located on the road link L4 can be used. As a result, the travel speed for the extended speed calculation section from the front position to the second position is obtained, and this travel speed is calculated from the link travel speed of the road link L3 between the front position and the second position. I reckon.

  The reason why the extended speed calculation section is used when the distance D of the normal speed calculation section is short is as follows. That is, when the speed calculation section is short, the time required to move in the speed calculation section is greatly affected by the stop time due to the traffic signal. In other words, even if the time required to pass through the speed calculation section is 2 minutes, for example, the time that the vehicle actually traveled is 1 minute, and the remaining 1 minute is a waiting time due to a signal. obtain. On the other hand, another vehicle passing through the same speed calculation section does not stop by a signal, and the time required to pass through the speed calculation section may be one minute. Thus, if the speed calculation section is short, an error due to the influence of waiting for a signal becomes large, and accurate speed calculation becomes difficult.

  On the other hand, if it is a speed calculation section where the distance is sufficiently long and it is necessary to pass many traffic signals (intersections), the waiting time due to one of the traffic signals is almost all of the vehicles. Therefore, the error due to the signal waiting is small.

Therefore, as in the present embodiment, when the distance D of the normal speed calculation section is short, the speed can be calculated with higher accuracy by calculating the speed in the extended speed calculation section.
Even if the distance D of the normal speed calculation section is short, if the number of vehicles is large (for example, 10 or more), the time required to pass through the speed calculation section is calculated from a plurality of vehicles. By averaging with the probe information, the error can be reduced. Therefore, only when the distance D of the normal speed calculation section is not more than the set minimum distance and the number of probe vehicles per unit time (number of probe information) is not more than the set minimum number. The speed calculation in the extended speed calculation section may be performed.

In the above example, the extended speed section is from the front position (road link L1) to the second position (road link L4), but instead of the second position, the traveling direction is more than the second position. In view of this, it may be a further position (road link L10). The extended speed section may be between the first position (road link L2) and the previous position (road link L10).
With the function of the acquisition unit 21 described above, it is possible to acquire the travel speed of each of the road links L1 to L10 based on the probe information. This travel speed information will be described below as “speed information”.

[3. Contents of processing by traffic information estimation device]
[3.1 Overview of estimation processing]
FIG. 5 shows a traffic information estimation method by the traffic information estimation apparatus 1. First, based on the speed information acquired by the acquisition unit 21 as described above, the acquisition unit 21 generates the first intermediate database 12a (step S1).
That is, if the traffic information estimation device 1 can acquire the probe information and the VICS information if it can acquire the VICS information, as described in FIG. 3, the acquisition unit 21 obtains the VICS information and the probe information from the VICS information and the probe information. Generate speed information for each road link.
However, in all the road links L1 to L10 in the management group G, the probe vehicle 3 on which the in-vehicle device 2 is mounted is not always traveling. Therefore, in step S1, road links from which speed information can be acquired are usually There are road links that are part of all road links L1 to L10 in the management group G and for which speed information cannot be obtained.

Further, the probe information processing unit 18 (see FIG. 3) of the acquisition unit 21 obtains the speed information (V1 to V10) of each of the road links L1 to L10 in the management group G from the first intermediate database 12a in FIG. As shown in the figure, the information is acquired for each of a plurality of time slots t1 to t20, and each speed information is accumulated in the first intermediate database 12a. Further, when the VICS information is acquired, the speed information (U1, U2) based on the VICS information is accumulated in the first intermediate database 12a.
In FIG. 6, it consists of time slots from t1 to t20, and one time slot is the same as the update period of VICS information, for example, 5 minutes. The speed information acquired for each time slot by the probe information processing unit 18 becomes speed information (actual measurement value) in the time slot. When a plurality of speed information is acquired on the same road link in one time slot, the average value becomes speed information of the one time slot. In FIG. 6, the speed information of the road link Li is shown as Vi (i = 1 to 10).

Subsequently, the estimation unit 11 estimates speed information about a road link (estimation target road link) for which speed information could not be acquired based on the contents of the first intermediate database 12a created in step S1 of FIG. Is performed (step S2 in FIG. 5). Note that the processing for estimation includes Steps S2-1 to S2-4. This estimation process will be described later.
Then, the estimated speed information of the estimation target road link is set in the estimation database 13 (see FIG. 2), and the estimation database 13 is updated (step S3).
Through step S2, speed information (estimated value) of the estimation target road link for which speed information could not be acquired in step S1 is also obtained. As described above, the estimated database 13 is a mixture of actually measured values and estimated values.

  The processes in steps S1 to S3 described above are repeatedly performed every time one time slot elapses. In the first intermediate database 12a in FIG. 6, when the speed information in a new one time slot is acquired, the speed information may be updated by adding one after another. When the speed information is acquired, the speed information may be deleted and updated in the oldest one time slot instead of adding the new speed information.

[3.2 Specific Example of Processing for Estimation (Part 1: First Embodiment)]
If it demonstrates again from step S1 of FIG. 5, the probe information processing part 18 of the acquisition part 21 (refer FIG. 2) will be the traffic information of the road links L1-L10 in the management group G for every time slot (every 5 minutes). Get speed information as That is, in a certain time slot, the in-vehicle device 2 of the probe vehicle 3 existing on a certain road link transmits the probe information, the roadside communication device 4 receives the probe information, and the probe information processing unit 18 further performs the probe information processing. When the information is received, the probe information processing unit 18 generates speed information on the road link from the information included in the probe information. And the probe information processing part 18 accumulate | stores each speed information produced | generated and acquired in the 1st intermediate database 12a (refer FIG. 6).

And the said calculation part 22 (refer FIG. 2) is based on the speed information which the probe information processing part 18 acquired, ie, based on the information of the 1st intermediate | middle database 12a, one set by two in the management group G A regression line is obtained from the traffic information of one of the road links as estimated information for estimating the traffic information of the other road link (step S2-1 in FIG. 5).
In the present embodiment (FIG. 9), the management group G includes 10 road links. For this reason, when two road links are selected from the ten road links L1 to L10, 45 combinations are conceivable.

Therefore, in step S2-1, for each of the 45 combinations, a set of speed information that can be acquired together in the same time slot is extracted. A specific example will be described with reference to FIG. 7 with reference to the first intermediate database 12a shown in FIG. 6 and 7, the speed information of the road link Li is shown as Vi (i = 1 to 10).
In FIG. 7, among the 45 combinations, as a representative, a set of road links L1 and L2, a set of road links L1 and L3, a set of road links L2 and L3, a road link L3 and L4, And a set of road links L4 and L5. For example, in the combination of road links L1 and L2, 6 data sets are extracted from 20 time slots, and in the combination of road links L1 and L3, 8 data sets are extracted from 20 time slots. Is extracted.

  In addition, since probe information is not always acquired, as shown in FIG. 6, it is not always possible to acquire speed information of all road links L1 to L10 in one time slot. For this reason, the number of road links from which the speed information can be acquired from the probe information in one time slot is less than 10 in total, and there is a blank in FIG.

Thus, when the data set about the speed information for each of the 45 combinations is extracted, in this step S2-1, a regression line is further obtained by the calculation unit 22 (see FIG. 2) (step S2). -1).
As described above, when two road links are selected from 10 road links L1 to L10, there are 45 combinations, and in this case, 45 regression lines can be obtained. For example, a regression line used to estimate the traffic information of the other road link L2 from the traffic information of one road link L1 of the two road links L1 and L2, and the opposite, This is different from the regression line used for estimating the traffic information of one road link L1 from the traffic information of the other road link L2. For this reason, there are a total of 90 (45 × 2) combinations of road links for obtaining regression lines, and it is necessary to obtain regression lines for each of the 90 combinations.

  The regression line is determined based on the data set extracted for each combination (for example, in FIG. 7, in the case of a combination of the road link L1 and the road link L2, six data sets that are actually measured values). It is obtained by multiplication as follows.

A combination of the road link La and the road link Lb will be described with reference to FIG. In FIG. 10A, the speed information (actual value) of the road link La is x [km / h], and the speed information (actual value) of the road link Lb is y [km / h]. As speed information (x _i , y _i ), n = 3 of (x ₁ , y _i ), (x ₂ , y ₂ ), (x ₃ , y ₃ ) as data sets from the first intermediate database 12a Suppose that data could be extracted.
In this case, the variance S _x ² is expressed by equation (1) in FIG. 10B, and the covariance S _xy ² is expressed by equation (2).

Then, the regression line Y in the case of obtaining the speed information y [km / h] of the road link Lb from the speed information x [km / h] of the road link La is expressed by the equation (3) in FIG. The
On the other hand, the regression line X in the case of obtaining the speed information x [km / h] of the road link La from the speed information y [km / h] of the road link Lb is expressed by the equation (4) in FIG. The
In this case, the correlation coefficient r _xy is expressed by the equation (5) in FIG. 11A and the equation (6) in FIG. 11B.
Through the processing of the calculation unit 22 described above, the regression line Y and the regression line X between the road links in the management group G are obtained (90 ways), and information on these regression lines Y and X (regression lines Y and X are specified). Information, such as slope and intercept, is stored in the second intermediate database 12b (see FIG. 2).

Furthermore, when the calculation unit 22 obtains the regression lines Y and X for each of the 90 combinations, the regression lines Y and X are correlated as the speed information of two sets of road links in the management group G. The degree of contribution of X (also referred to as contribution rate or determination coefficient) is also determined for each combination (step S2-2 in FIG. 5).
The contribution R ² of the regression line Y is represented by the equation (7) in FIG. 11A, and the contribution R ² of the regression line X is represented by the equation (8) in FIG. . The degree of contribution is generally obtained by the formula of (variance of predicted value of objective variable) / (variance of measured value of target variable).

The calculation by the calculation unit 22 is executed for all 90 combinations, and the calculated contributions are as shown in FIG. 8 together with the information of the regression lines Y and X (not shown in FIG. 8). Are stored in the second intermediate database 12b. In FIG. 8, in addition to the matrix related to the contribution degree R ² , as will be described later, the contribution degree of the regression line for the road link speed information (U1, U2) obtained from the VICS information is also accumulated. Shows the case.

  Then, the selection unit 23 (see FIG. 2) selects a road link in which the correlation is recognized at a predetermined level or more as a selection group. That is, the selection unit 23 refers to the second intermediate database 12b and selects, from the management group G, a road link whose degree of contribution of the regression line has reached a predetermined level (threshold value α) as a selected group. Processing is performed (step S2-3 in FIG. 5).

More specifically, the threshold value α is a value set in the traffic information estimation apparatus 1 and is set to 0.8, for example. For the estimation unit 11 to estimate the speed information of the estimation target road link, for example, in the traffic information estimation device 1, speed information (probe information) of the road link L2 and the road link L8 is actually measured as the related road link. If it is acquired as a value, the selection unit 23 contributes in the relationship with the road link (related road link) L2 from which the speed information can be acquired, that is, in the V2 line indicating the speed information of the road link L2 in FIG. The road links L1, L3, and L4 whose degrees are equal to or greater than the threshold α = 0.8 are selected as the first selection group g1 including the road link L2. That is, the first selection group g1 is road links L1, L2, L3, and L4.
Further, the selection unit 23 has a contribution of a threshold α = threshold in the relationship with the road link (related road link) L8 from which the speed information can be acquired, that is, the V8 line indicating the speed information of the road link L8 in FIG. The road link L9 which is 0.8 or more is selected as the second selection group g2 including the road link L8.

Since the speed information V2 of the road link L2 is acquired as the actual road value as the related road link, the estimation unit 11 is the remaining road link in the first selection group g1 including the road link L2. Speed information V1, V3, V4 of L1, L3, L4 (estimation target road link) is converted into each regression line related to speed information V2 of road link L2 and speed information V1, V3, V4 of road links L1, L3, L4. Estimate based on.
Further, since the speed information V8 of the road link L8 is acquired as an actual measurement value as the related road link, the estimation unit 11 is the remaining road link in the second selection group g2 including the road link L8. The speed information V9 of L9 (estimation target road link) is estimated based on the regression lines related to the speed information V8 of the road link L8 and the speed information V9 of the road link L9 (step S2-4).
Each regression line is obtained in step S2-1, and the information is stored in the second intermediate database 12b together with the contribution (corresponding to the contribution).

  As described above, the selection unit 23 performs a correlation in which the degree of contribution has reached a predetermined level (the threshold α is 0.8 or more) in relation to the speed information of the related road links (L2 and L8). Since a certain road link (L1, L3, L4 and L9) is selected as a selection group (g1 and g2) from the management group G, speed information (V2 and V8) of the relevant road link (L2 and L8) And the contribution of the regression line with respect to the speed information (V1, V3, V4 and V9) of the road links (L1, L3, L4 and L9) included in the selected group (g1 and g2) is the predetermined level ( It can be said that it has reached 0.8).

Therefore, when the speed information (V2 and V8) of the related road links (L2 and L8) is acquired, the estimation unit 11 includes the speed information (V2 and V8) of the related road links (L2 and L8), Speed information (V1, V3, V4 and V9) of road links (L1, L3, L4 and L9) which are included in the selected group (g1 and g2) and whose contribution has reached a predetermined level (0.8 or higher) The road information (V1, V3, V4, and V9) of the road links (L1, L3, L4, and L9) can be estimated based on the regression line for and the road link speed information estimated. Is highly reliable.

Then, based on the speed information (V2 and V8) of the related road links (L2 and L8), which are actual measurement values acquired from the probe information by the acquisition unit 21 (probe information processing unit 18), and estimation based on the speed information The estimated speed information (V1, V3, V4 and V9) of the estimated road links (L1, L3, L4 and L9) is newly accumulated and updated in the estimation database 13 (step S3 in FIG. 5). Note that the speed information (V5, V6, V7, V10) of the road links (L5, L6, L7, L10) that are not newly estimated need not be updated.
As described above, the speed information in the estimation database 13 is a mixture of the actual measurement value and the estimation value. However, since the estimation value is highly reliable as described above, the information in the estimation database 13 is used for the traffic information system. Thus, it is possible to grasp the current traffic state and predict the future traffic state, and to improve the accuracy thereof.

Moreover, in the said embodiment, only the speed information based on the probe information transmitted from the probe vehicle is used for estimation of the speed information of the said estimation object road link.
That is, the regression line is obtained based on speed information (probe traffic information) obtained from probe information transmitted from the probe vehicle 3. Then, in order for the estimation unit 11 to estimate the traffic information of the estimation target road link, the acquired speed information of the related road link is the speed information (probe traffic) obtained from the probe information transmitted from the probe vehicle 3. Information).

  As described above, since the process for calculating the regression line and the degree of contribution and the estimation process are executed only by the speed information obtained from the probe information transmitted from the probe vehicle 3, the roadside sensor 5 (see FIG. 1), it is possible to estimate the traffic information of the estimation target road link even when the fixed point observation information collected (that is, VICS information) cannot be acquired.

  However, the acquisition unit 21 of the input information processing unit 16 illustrated in FIGS. 2 and 3 also includes the VICS information processing unit 17 in addition to the probe information processing unit 18, and any of the road links in the management group G When the crab road sensor 5 is installed, the probe information processing unit 18 can acquire speed information (probe traffic information) obtained from the probe information transmitted from the probe vehicle 3, in addition to the VICS information processing unit 17. According to this, speed information (fixed point traffic information) obtained from VICS information can also be acquired. Note that the speed information (U1, U2) obtained from the VICS information is stored in the first intermediate database 12a as in the case of the speed information (V1 to V10) obtained from the probe information shown in FIG.

  In this case, the calculation unit 22 obtains the regression line and the degree of contribution of the regression line based on the probe traffic information stored in the first intermediate database 12a in the same manner as described above. In addition, based on the fixed point traffic information, similarly to the above description, a process for obtaining the regression line and the degree of contribution of the regression line is performed. Then, this degree of contribution is accumulated in the second intermediate database 12b (see FIG. 8). In FIG. 8, the contributions to the road link speed information obtained from the VICS information are shown in the U1 line and the U2 line.

In this case, the estimation unit 11 compares the correlation based on the probe traffic information and the correlation based on the fixed point traffic information, and performs estimation based on the regression line having the higher correlation (the stronger correlation). That is, the degree of contribution by the probe traffic information is compared with the degree of contribution by the fixed point traffic information, and the estimation process is performed based on the regression line having the higher contribution.
More specifically, when the VICS information is acquired from the roadside sensor 5 installed at the first point, the VICS information processing unit 17 obtains fixed point traffic information from the VICS information. Based on the fixed point traffic information, the corresponding road link, the regression line between each road link, and the degree of contribution are obtained.

  Then, in the U1 row indicating the contribution, the speed information of the road link whose contribution is equal to or greater than the threshold value α (0.8) is the speed information V1 of the road link L1. Therefore, when the fixed point traffic information is acquired by the roadside sensor 5 of the first point, the estimation unit 11 can estimate the speed information V1 of the road link L1 based on the fixed point traffic information and the regression line. Become.

However, the contribution in this case is 0.92. On the other hand, as described above, when the speed information (probe information) of the road link L2 is acquired as an actual measurement value, the speed information V1 of the road link L1 is estimated in relation to the road link L2. The contribution of the regression line is 0.98.
Therefore, the estimation unit 11 performs a process of estimating the speed information V1 of the road link L1 based on the regression line having the higher contribution. That is, the estimation process is performed based on the velocity information obtained from the probe information and the regression line obtained from the probe information, and the estimation process is not performed based on the VICS information.

On the other hand, when the VICS information is acquired from the roadside sensor 5 installed at the second point, the fixed point traffic information is obtained from the VICS information by the VICS information processing unit 17. Based on the fixed point traffic information, the corresponding road link, the regression line between each road link, and the degree of contribution are obtained.
Then, in the U2 row indicating this contribution, the speed information of the road link whose contribution is equal to or greater than the threshold value α (0.8) is the speed information V4 of the road link L4. Therefore, when the fixed point traffic information is acquired by the roadside sensor 5 of the second point, the estimation unit 11 can estimate the speed information V4 of the road link L4 based on the fixed point traffic information and the regression line. Become.

The contribution in this case is 0.91. On the other hand, as described above, when the speed information (probe information) of the road link L2 is acquired as an actual measurement value, the speed information V4 of the road link L4 is estimated in relation to the road link L2. The contribution of the regression line is 0.86.
Therefore, the estimation unit 11 performs a process of estimating the speed information V4 of the road link L4 based on the regression line having the higher contribution. That is, the estimation process is performed based on the speed information obtained from the VICS information and the regression line obtained from the VICS information, and the estimation process is not performed based on the probe information.

  Thus, in addition to the speed information (probe traffic information) obtained from the probe information, when the speed information (fixed-point traffic information) obtained from the VICS information can be acquired, the estimation unit 11 determines the contribution degree of the probe traffic information and The contribution degree by the fixed point traffic information is compared, and the estimation process is performed based on the regression line with the higher contribution degree. For this reason, the reliability of the estimated road information can be further increased.

  From the above, when the threshold α is set to 0.8, the number of road links in the management group G is 10, whereas the road links that can be estimated by the estimation unit 11 are: Four of L1, L3, L4, and L9. Further, there are two related road links from which probe information (actually measured values) was obtained. Therefore, the total number n of road links whose speed information is obtained by actual measurement and estimation among all road links L1 to L10 existing in the management group G is 6 (n = 6), N = 10). This 60% value (n / N) is referred to as the coverage factor F.

The ratio F / K between the coverage rate F and the number K of selected groups can be used as an index related to the number of estimation target road links whose speed information is estimated by the estimation unit 11. Even if the cover rate F is large, if the number K of selected groups is large, the ratio F / K becomes small. In this case, the number of speed information of related road links required to achieve the cover rate F is small. , Mean to be more. On the other hand, if the number K of selected groups is small, the ratio F / K increases, and in this case, the number of related road link speed information required to achieve the coverage rate F is small. It means that.
That is, the ratio F / K means the probability that the coverage rate F can be achieved when the same number of speed information (probe information) as the number K of estimated groups is acquired from the road link as an actual measurement value. .
In the above case, since the coverage rate F is 60% (0.6) and the number K of selected groups is 2, the ratio F / K indicating the probability is 0.3. It can be said that the higher the ratio F / K, the more efficiently the speed information of the road link can be estimated.

Therefore, in the traffic information estimation device 1 of the present invention, the adjustment unit 24 (see FIG. 5) according to the probability (ratio F / K) as an index relating to the number of estimation target road links whose speed information is estimated by the estimation unit 11. 2) can adjust the threshold value α. That is, when the probability is smaller than the determination value set in the traffic information estimation device 1, the adjustment unit 24 changes the threshold value α to be smaller. When the comparison result is large, the adjustment unit 24 may change the threshold value α so as to increase it. This specific example will be described later.
In addition to the case where the adjustment unit 24 reduces the threshold value α in accordance with the probability (ratio F / K) as an index, the index is set as the number K of selected groups until the number K is equal to or less than the determination value. The threshold value α may be decreased, or the threshold value α may be decreased until the cover rate F is equal to or less than a determination value with the index being the cover rate F.

[3.3 Specific Example of Processing for Estimation (Part 2)]
The other form (2nd embodiment) of the estimation process by the traffic information estimation apparatus 1 is demonstrated. Also in the second embodiment, the configuration of the traffic information estimation device 1 is the same as that of the first embodiment, but in this embodiment, the method of creating the second intermediate database 12b is slightly different. FIG. 12 is an explanatory diagram of the second intermediate database 12b. In the second embodiment, in order to generate the second intermediate database 12b, the original contribution matrix information 12c shown in FIG. 13 is generated. 12 and 13, “-” for different road links indicates that probe information has not been acquired at the same time.

  First, the acquisition unit 21 (see FIG. 2) accumulates speed information in the first intermediate database 12a. Then, the calculation unit 22 (see FIG. 2) calculates the regression line and the contribution degree between the speed information of each pair of road links in the management group G based on the information of the first intermediate database 12a. The (original contribution degree) is obtained for every 90 combinations. These methods are the same as those in the first embodiment. This result is the original contribution matrix information shown in FIG.

And in this 2nd embodiment, the calculation part 22 calculates | requires the average of a transposed matrix. For example, the average of the contribution (0.33) in the V5 row-V1 column and the contribution (0.23) in the V1 row-V5 column is obtained [(0.33 + 0.22) / 2 = 0. 28]. This average value (0.28) is the true contribution of the regression line between the road link L1 and the road link L5, and the remaining combinations are similarly obtained. This result (true contribution) is accumulated in the second intermediate database 12b (see FIG. 12).
In the second intermediate database 12b, information on the regression line for each combination of two road links is also stored, as in the first embodiment.

  Then, the selection unit 23 (see FIG. 2) selects road links whose correlation is recognized at a predetermined level or more as a selection group. That is, referring to the second intermediate database 12b, a process is performed for selecting a road link having a regression line having a contribution degree equal to or greater than the threshold value α from the management group G as a selected group.

The threshold value α is a value set in the traffic information estimation apparatus 1 and is set to 0.99, for example. In this case, according to FIG. 12, the combinations having a contribution degree of 0.99 or more are combinations of the speed information V1 of the road link L1 and the speed information V2 of the road link L2, and the road link L2 speed information V2 and the road. This is a combination with the speed information V3 of the link L3.
Therefore, the road link having a regression line whose contribution degree reaches the threshold value α (0.99) is a combination of L1 and L2, and a combination of L2 and L3. These road links L1, L2, L3 is selected as a selection group. In this grouping process, in the relationship with at least one (L2) of the two road links (L1 and L2) having a regression line whose contribution reaches the threshold value α, the contribution A road link (L3) having a regression line that reaches the threshold value α is also selected as the same group.
That is, since the speed information has a strong correlation between the road links L1, V2, and V3 (because the contribution is 0.99 or more), the selection unit 23 selects as one selection group g1.

In this case, the selection group g1 includes road links L1, V2, and V3, and the speed information (probe information) of the road link L1 that is one of the selection groups g1 as the related road link. ) Is acquired as the actual measurement value V1, and estimated based on the regression lines of the speed information V1 and the speed information V2 and V3 of the remaining road links L2 and L3 included in the selected group g1. As the road information of the target road link, speed information V2 and V3 of the road links L2 and L3 are estimated.

  Thus, when the threshold value α is set to 0.99, the number of road links in the management group G is 10, whereas the road links that can be estimated by the estimation unit 11 are: L2 and L3. Further, there is one related road link from which probe information (actually measured value) is obtained. Therefore, the total number n of road links whose speed information is obtained by actual measurement and estimation among all the road links L1 to L10 existing in the management group G is 3 (n = 3), and the coverage rate F (= n / N) is 30%.

Further, as described above, the ratio F / K between the coverage rate F and the number K of selected groups is an index related to the number of estimation target road links whose speed information is estimated by the estimation unit 11, and is the number of estimation groups. When the same number of speed information (probe information) as K is acquired from the road link as an actual measurement value, it means the probability that the coverage rate F can be achieved.
In the above case, since the coverage rate F is 30% (0.3) and the number K of selected groups is 1, the ratio F / K indicating the probability is 0.3. It can be said that the higher the ratio F / K, the more efficiently the speed information of the road link can be estimated.

Therefore, the adjusting unit 24 (see FIG. 2) adjusts the threshold value α in accordance with the probability (ratio F / K) used as the index.
Specifically, the adjustment unit 24 compares the probability (ratio F / K) with a comparison value set in the traffic information estimation device 1, and if the ratio F / K is small, the adjustment unit 24 24 is changed so as to reduce the threshold value α. If the result of comparison is large, the adjustment unit 24 changes the threshold value α to be large.

  Therefore, when the adjustment unit 24 determines that the ratio F / K is small, the adjustment unit 24 adjusts the threshold α to be reduced from 0.99 to 0.8. In this case, according to FIG. 12, the combination whose contribution is 0.8 or more is a combination of the speed information V1 of the road link L1 and the speed information V2 of the road link L2, and the speed information V1 of the road link L1 and the road link. A combination of L3 speed information V3, a road link L2 speed information V2 and a road link L3 speed information V3, a road link L2 speed information V2 and a road link L4 speed information V4, and a road A combination of the speed information V3 of the link L3 and the speed information V4 of the road link L4, and the selection unit 23 selects the road links L1, L2, L3, and L4 as the first selection group g1. Between these road links L1, L2, L3, and L4, since the correlation between speed information is strong in any two combinations (because the contribution degree of the regression line is 0.8 or more), it is within one selected group g1. It can be said that there is.

Further, according to FIG. 12, the combinations having a contribution degree of 0.8 or more are the combination of the speed information V5 of the road link L5 and the speed information V6 of the road link L6, and the speed information V6 of the road link L6 and the road. There is a combination with the speed information V7 of the link L7, and the selection unit 23 selects these road links L5, L6, and L7 as the second selection group g2.
Furthermore, according to FIG. 12, the other combinations whose contribution is 0.8 or more are the combination of the speed information V8 of the road link L8 and the speed information V9 of the road link L9, and the speed information V9 of the road link L9. And the speed information V10 of the road link L10, and the selection unit 23 selects the road links L8, L9, and L10 as the third selection group g3.

In this case, the first selection group g1 includes road links L1, L2, L3, and L4, and one of the first selection groups g1 as speed information of related road links is included. When the speed information V1 (probe information) of the road link L1 is acquired as an actual measurement value, the speed information V1 and the remaining road links L2, L3, L4 included in the first selection group g1 are acquired. Based on each regression line with the speed information V2, V3, V4, the speed information V2, V3, V4 of the road links L2, L3, L4 is estimated as the road information of the estimation target road link.
Similarly, in the second selection group g2, for example, when the speed information V5 of the road link L5 is acquired as an actual measurement value, the speed information V6 and V7 of the road links L6 and L7 are estimated.
Similarly, in the third selection group g3, for example, when the speed information V8 of the road link L8 is acquired as an actual measurement value, the speed information V9 and V10 of the road links L9 and L10 are estimated.

  As described above, when the threshold value α is adjusted to 0.8, there are seven road links L2, L3, L4, L6, L7, L9, and L10 that can be estimated by the estimation unit 11. Further, there are three related road links from which probe information (actually measured values) was obtained. Therefore, the total number n of road links whose speed information is obtained by actual measurement and estimation among all road links L1 to L10 existing in the management group G is 10 (n = 10), and the coverage rate F (= n / N) is 100%.

  In this case, the ratio F / K between the cover ratio F and the number K of selected groups is 100% (1.0), and the ratio F / K is 3 because the selected group number K is 3. 0.33. This ratio (F / K) is higher than when the threshold value α is 0.99 (0.3).

In this way, by adjusting the threshold value α to be reduced by the adjusting unit 24, the probability (the same number of speed information (probe information) as the number of estimated groups K) is obtained as an actual measurement value for each estimated group from the road link. When acquired one by one, it is possible to increase the probability that the coverage rate F can be achieved. As a result, the road information can be estimated efficiently.
Further, regarding the coverage rate F, if the contribution threshold value α is lowered, the strength of the correlation between the speed information slightly decreases, but the speed information (probe information) is acquired because the number of estimation groups is large. Even if there are few opportunities, the speed information of a relatively large number of road links can be estimated. On the other hand, when the contribution threshold value α increases, the number of estimated groups decreases, but the correlation between the speed information increases, so the reliability of the estimated speed information is high.
Therefore, in a management group having many opportunities to acquire speed information (probe information), it is preferable to set the contribution threshold α high, and there is an opportunity to acquire speed information (probe information). In a small management group, it is preferable to set the threshold value α of contribution low, and the threshold value α may be set and adjusted for each management group according to the situation of the number of speed information (probe information) that can be acquired.

  Also in the second embodiment, as in the first embodiment, the estimation unit 11 compares the correlation based on the probe traffic information with the correlation based on the fixed point traffic information, and the higher correlation is obtained. An estimation process may be performed based on the regression line.

  The embodiment disclosed this time should be considered as illustrative in all points and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the meanings described above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims.

  For example, the road link (related road link) used to estimate the speed information of the estimation target road link is not limited to that connected to the estimation target road link, but is separated from the estimation target road link. It may be a road link (for example, a road link parallel to the estimation target road link) that is related to the method of temporal change of the speed information.

  Furthermore, in this embodiment, only the speed information in the same time slot (time slot) in time is used as the speed information of the related road link, but speed information in different time slots may be used. For example, in the case of a road link far away from the estimation target road link, there is a time delay until the traffic situation on the road link is reflected on the estimation target road link. Therefore, in the case of a road link far away, for example, more appropriate estimation can be performed by using the speed information of one hour ago for estimation.

  Furthermore, the traffic information to be estimated by the estimation unit 11 of the traffic information estimation apparatus 1 of the present embodiment is not limited to speed information, but may be other traffic information such as traffic jam information in addition to / in place of the speed information. it can. Further, the estimation information may be other than a regression line (linear regression), or may be another function (curve). The correlation may be an index other than the contribution of the regression line.

  1: traffic information estimation device, 11: estimation unit, 21: acquisition unit, 22: calculation unit, 23: selection unit, 24: adjustment unit, L1 to L10: road link

Claims (5)

A traffic information estimation device comprising an estimation unit that estimates traffic information of other road links based on traffic information of road links,
An acquisition unit for acquiring traffic information of a plurality of road links;
Based on the traffic information acquired by the acquisition unit, estimation information for estimating traffic information of another road link from traffic information of one road link, and correlation between the traffic information of the road links are obtained. A calculation unit;
A selection unit that selects, as a selection group, road links where the correlation is recognized at a predetermined level or higher;
With
The acquisition unit, as the traffic information, in addition to the probe traffic information obtained from the probe information transmitted from the probe vehicle, the fixed point traffic information obtained from the fixed point observation information collected by using the roadside sensor installed on the road Is available and
The calculation unit obtains the estimated information and the correlation based on the probe traffic information and the fixed point traffic information,
When the traffic information of the road link is acquired, the estimation unit obtains the traffic information of the other road link in the selected group including the road link by using the correlation based on the probe traffic information and the fixed point traffic information. A traffic information estimation device characterized by comparing with a correlation and estimating based on the estimation information with a higher correlation. A traffic information estimation device comprising an estimation unit that estimates traffic information of other road links based on traffic information of road links,
An acquisition unit for acquiring traffic information of a plurality of road links;
Based on the traffic information acquired by the acquisition unit, estimation information for estimating traffic information of another road link from traffic information of one road link, and correlation between the traffic information of the road links are obtained. A calculation unit;
A selection unit that selects, as a selection group, road links where the correlation is recognized at a predetermined level or higher;
An adjusting unit that adjusts the predetermined level according to an index related to the number of other road links whose traffic information is estimated by the estimating unit;
With
When the traffic information of a road link is acquired, the estimation unit estimates traffic information of another road link in the selected group including the road link based on the estimation information. Information estimation device. The estimation information is obtained based on probe information transmitted from a probe vehicle and acquired by the acquisition unit,
The traffic information estimation according to claim 2, wherein the road information of the road link acquired is based on probe information transmitted from a probe vehicle so that the estimation unit estimates traffic information of another road link. apparatus.   A computer program for causing a computer to function as the traffic information estimation device according to any one of claims 1 to 3. A traffic information estimation method for estimating traffic information of other road links based on traffic information of road links,
An acquisition step of acquiring traffic information of a plurality of road links;
On the basis of the acquired traffic information, estimation information for estimating traffic information of another road link from traffic information of one road link, and a calculation step for obtaining a correlation between the traffic information of each road link;
A selection step of selecting road links in which the correlation is recognized at a predetermined level or more as a selection group;
When the road link traffic information is acquired, an estimation step of estimating traffic information of other road links in the selected group including the road link based on the estimation information;
Including
In the acquisition step, fixed-point traffic information obtained from fixed-point observation information collected by using a roadside sensor installed on the road in addition to the probe traffic information obtained from the probe information transmitted from the probe vehicle as the traffic information. Is available and
In the calculation step, the estimated information and the correlation are obtained based on the probe traffic information and the fixed point traffic information,
In the estimation step, the correlation based on the probe traffic information is compared with the correlation based on the fixed-point traffic information, and the estimation is performed based on estimation information having a higher correlation.

Images