JPH08329381A - Start point and end point information generating device - Google Patents

Abstract

PURPOSE: To automatically generate OD information on a vehicle. CONSTITUTION: AVI devices 10 arranged at respective points recognize vehicle numbers and send the recognition results to a central information generating device 30 through a communication controller 20. The central information generating device 30 matches the vehicle numbers recognized by the AVI devices 10 according to the received information and selects the pair of AVI devices 10 which have outputted matching numbers and are arranged at the point at the largest interval, and generates OD information so that the point that one AVI device 10 belongs to is regarded as a start point and the point that the other AVI device 10 belongs to is regarded as an end point.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a starting point / ending point information creating device, and in particular, creates starting point / ending point information of a vehicle for the purpose of investigating the current state of routes frequently used by road administrators in a road network. The present invention relates to a starting point / ending point information creating apparatus suitable for doing the above.

[0002]

2. Description of the Related Art Conventionally, the starting point is for the purpose of investigating the current state of frequently used roads (routes) such as expressways.
An end point (OD) survey is being conducted. Roadside OD surveys and owner interview OD surveys are mainly conducted as this OD survey. The roadside OD survey is a survey in which the area subject to the OD survey is divided into a plurality of blocks, vehicles passing through the boundaries of each block are stopped beside the road, and the operation content and operation status are heard directly. On the other hand, the owner interview OD survey
Randomly select the owner of the car, visit the extracted person in advance and hand over the survey form, have them fill in the operation details and operation status on the survey day, and go to the survey form at a later date is there.

[0003]

However, in the above-mentioned prior art, in the case of the roadside OD survey, workers must be arranged at all boundaries of the blocks divided in the OD survey target area, and a large number of personnel are required. I need. In addition, since the vehicle that passes through the boundary of the block is stopped, it causes traffic congestion, and the driver is also restricted for the time required for the investigation. On the other hand, in the case of the owner interview OD survey, the worker has to visit the survey target person, the work load is high, and it takes time to collect the survey sheet and cost to create the survey sheet.

As described above, in the prior art, the workload and cost of the operator are high, it takes a long time to collect the survey sheet, and the number of samples is limited, so that it is not possible to create highly accurate OD information. For the above reasons, there is a problem that the survey can be carried out only once a year.

The present invention has been made to solve such a conventional problem, and an object of the present invention is to provide a starting point / ending point information creating apparatus capable of automatically creating starting point / ending point information of a vehicle. Is.

[0006]

In order to achieve the above object, the present invention provides, as a first device, a plurality of vehicle recognition means for recognizing vehicle numbers of vehicles traveling on a road at different points. One of the determination means for determining the match between the recognition results of the vehicle recognition means and the determination information for determining the coincidence between the vehicle recognition means and the traveling information of one of the vehicles recognized by the plurality of vehicle recognition means when the determination result is positive. A starting-point / ending-point information creating device is provided that includes starting-point / ending-point information generating means for generating starting-point / ending-point information with a point to which a vehicle recognizing means belongs as a starting point and a point to which another vehicle recognizing means belongs as an ending point. is there.

The present invention also provides, as a second device, a plurality of vehicle recognition means for recognizing vehicle numbers of vehicles traveling on a road at different points, and a pair of vehicle recognition means based on each vehicle recognition means. The combination designating means for designating a plurality of combinations, the determination means for collating the recognition results of the vehicle recognizing means belonging to each set designated by the combination designating means to determine whether the two match, and the positive determination result by the determination means Among the obtained sets, as the traveling information of the vehicle recognized by the vehicle recognizing means of the group arranged at the point with the maximum distance, the point to which one vehicle recognizing means belongs is the starting point and the point to which the other vehicle recognizing means belongs And a starting point / ending point information generating means for generating starting point / ending point information for terminating the starting point / ending point information.

The present invention also provides, as a third device, a plurality of vehicle recognizing means for recognizing vehicle numbers of vehicles traveling on a road at different points, and a vehicle recognizing means forming a pair on the basis of each vehicle recognizing means. A first combination designating means for designating vehicle recognition means at points adjacent to each other as a combination of the above and the recognition results of the vehicle recognition means belonging to the set designated by the first combination designating means are collated to determine whether the two match. As a combination of the 1 determination means and the vehicle recognition means forming a pair with each vehicle recognition means as a reference, the second combination designation means and the second combination designation means for designating the vehicle recognition means at a point downstream from the adjacent point. Second judging means, first judging means, and second judging means, which collate the recognition results of the vehicle recognizing means belonging to the designated set to judge whether the two match.
Among the vehicle recognition means for which a positive determination result is obtained by the determination means, the point to which the vehicle recognition means arranged on the most upstream side belongs and the point to which the vehicle recognition means arranged on the most downstream side belong are the end points. And a starting point / ending point information generating means for generating starting point / ending point information.

When configuring each of the above devices, it is desirable to have the following functions. (1) Capture that calculates a capture rate that indicates the ratio of the number of vehicles traveling at the point where each vehicle recognition means is arranged among the vehicles traveling on the road to the number of vehicles recognized by each vehicle recognition means The rate calculation means and the correction means for correcting the start point / end point information generated by the start point / end point information generation means based on the calculated value of the capture rate calculation means. (2) A recognition time measuring unit that measures the vehicle recognition time of each vehicle recognizing unit is included, and the determining unit recognizes the measurement value of the recognition time measuring unit included in the recognition result of each vehicle recognizing unit within the set time It has the function of collating only the results.

[0010]

Therefore, according to the present invention, the vehicle number of the vehicle is recognized by each vehicle recognition means, and when the recognition results match, the point where one vehicle recognition means belongs to the point where the other recognition means belongs to the vehicle. Has moved,
It is possible to automatically generate start point / end point information in which a point to which one vehicle recognition unit belongs is set as a starting point and a point to which the other vehicle recognition unit belongs is set as an end point. In this case, more accurate collation can be performed by collating only the recognition result in which the vehicle recognition time is included within the set time.

[0011]

An embodiment of the present invention will be described below with reference to the drawings.

FIG. 1 is an overall configuration diagram of a start point / end point information creating apparatus showing a first embodiment of the present invention. In FIG. 1, the start point / end point information creation device is a plurality of vehicle recognition devices (hereinafter,
It is called an AVI device. ) 10, a communication control device 20, and a central information creating device 30. Each AVI device 10 is arranged at different points along a route such as a highway, and is configured as a vehicle recognition unit that images the license plate of a vehicle traveling on the road and recognizes the vehicle number. Further, each AVI device 10 constitutes a recognition time measuring means for recognizing the time when the vehicle number is recognized as the passing time of the vehicle and outputting the data regarding the passing time. The communication control device 20 receives the data of the vehicle number and the passage time from each AVI device 10, and transmits the received data to the central information creating device 30. The central information creation device 30 collates the vehicle numbers recognized at the two points based on the received data, and when the vehicle numbers of the two match, the point to which the one AVI device 10 belongs is the starting point and the other AVI device 10 is the starting point. The starting point / end point information having the point to which the device 10 belongs as the end point is generated.

Specifically, the central information creating device 30 includes a constant setting device 301, an OD information creating device 302, and an OD (true value).
It is provided with an estimator 303. Constant setter 30
1 sets the interval between installation points of each AVI device 10 and the period for creating OD information. The OD information generator 302 uses the data received from the communication control device 20 and according to the condition set by the constant setter 301, the OD information creator 302.
(Start point / End point) information is created. That is, the OD information creator 302 is the AVI device 10 that makes a pair.
Combination designating means for designating the combination of the AVI apparatus 10 and the deciding means for collating the recognition result of the AVI apparatus 10 to determine whether the two match, and when a positive determination result is obtained by the deciding section, one of the AVI apparatuses 10 belongs. A starting point / ending point information generating means for generating starting point / ending point information having a point as a starting point and a point to which the other AVI device 10 belongs as an ending point is configured. The OD estimator 303 is used by each AVI device 1
Number of vehicles traveling at the point where 0 is placed and each AV
The capture rate calculating means for calculating the capture rate indicating the ratio with the number of vehicles recognized by the I-device, and the correction of the start point / end point information created by the OD information creator 302 based on the calculated value of the capture rate calculating means The correction means for performing the correction is configured.

Next, the operation of this embodiment will be described based on the function of the OD information generator 302. First, in the present embodiment, as shown in FIG. 2, the AVI devices 10 are arranged at points A to H, respectively, and as shown in FIG. 3, the point A is designated as a starting point and all other points are set. Among them, the vehicle number is collated with a point that can be the end point (hereinafter, the end point candidate point), and the collation result is coincident, that is, the pair having the longest distance and the longest interval among the pairs of the matched point and the end point candidate point is started. -It will be specified as the end point. This concrete processing procedure is shown in FIG.

First, the point A is designated as the starting point (step 401). Next, the vehicle to be checked at the starting point, that is, the point A is designated (step 402). Vehicles to be verified are
As shown in FIG. 5, the vehicle number data in order of passage time is used to sequentially select vehicles having earlier passage times. Next, considering the traveling direction of the vehicle from the designated starting point (point A), all points that can be the ending point are selected (step 403).
If the starting point is point A, the end point candidate points are points C, D,
It becomes E, F, G, H, and the point B is excluded. Thereafter, the vehicle number is collated between the designated point and all the end point candidate points designated in step 403 (step 40).
4). Next, it is determined whether or not there is an error in the verification result of the vehicle number (step 405). That is, step 40
It is determined whether or not the matching result in 4 is consistent. For example, in the vehicle matching with the starting point A, if both the ending point candidate points E and G are matched, it is considered that the matching with either of the ending point candidate points is incorrect. Therefore, step 40
At 6, the travel time of the target vehicle is calculated, and abnormal values are removed (erroneous matching is removed) based on the calculated time.

Next, in step 407, the end point candidate point farthest from the starting point is set as the end point among all the matched end point candidate points. By this processing, the starting point and the ending point are specified. That is, when the matched points are the points C and E with respect to the starting point A, the starting point / ending point candidates are A →
C, A → E, but if a pair with the largest distance is selected, the starting point / end point pair is A → E. After this step 408
Then, 1 (vehicle) is added to the traffic volume of the group determined as the start point / end point. For example, add 1 to the traffic volume of A → E, which is the combination of the starting point and the ending point. Next, at step 409, in the matching of the vehicle number with the starting point, the data of the target vehicle at all matched end point candidate points are marked as matched. This is because the target vehicle at the matched end point candidate point is excluded from the target vehicle at the starting point in the subsequent processing. Next, in step 410, it is determined whether or not the target vehicle exists at the starting point in consideration of the target period for creating the OD information. For example, when the OD information creation target period is one day, the target vehicle is until 23:59. Further, the maximum travel time from the point A to the farthest point H is set as the verification target vehicle from the end time of the target period to the time obtained by subtracting the maximum travel time. If there is no target vehicle, the process proceeds to step 411. In step 411, it is determined whether or not there is a candidate for the next starting point. In the case of the present embodiment, when all the points within the points F and H are designated as the starting points, it is determined that there is no candidate for the next starting point. This is because when the points F and H are the starting points, there are no end point candidate points. Through the above processing, the total traffic volume of each OD in the target period is calculated.

As described above, according to the present embodiment, the vehicle number recognized by the AVI device 10 is collated, the pair with the longest distance is selected from the pairs having the collated results, and the one belonging to the selected pair is selected. O from the point to which the AVI device 10 belongs to
Since the D information is created, the OD information of the target vehicle can be created automatically.

Further, according to this embodiment, the AVI device 1
By using 0, it is possible to collect a large amount of data automatically and create OD information in a short time, thus reducing the burden and cost on the operator and accurately obtaining desired OD information. Can be created. In addition, because OD information is created based on vehicle verification between two points,
OD information that is less affected by the capture rate in each AVI device 10 can be created, and the effect of high practicability is obtained.

Next, a second embodiment of the present invention will be described with reference to FIGS. 6 and 7. In this embodiment, as shown in FIG. 6, the vehicle number is collated between the upstream point and the adjacent downstream point,
When matched, the upstream point and the downstream point are moved in the downstream direction one by one, and the next vehicle matching is performed.
At this time, even if a pair of upstream point and downstream point is not matched, the process is continued unless two pairs are not matched in succession.

Specifically, as shown in FIG. 7, first, a starting point is designated (step 701). For example, points A, C,
Designate D, E, and F as downstream points. After that, the vehicle to be collated at the point is designated (step 702). After this, it is determined whether or not it is the first vehicle verification, and 1
If the determination is “Yes” for the second time, a downstream point is designated in step 704. For example, if the starting point is point A,
Point E is designated as the downstream point. Then, after the upstream point and the downstream point are designated, the vehicle numbers are collated between the upstream point and the downstream point (step 705).

On the other hand, if it is determined in step 703 that it is the second or subsequent vehicle verification, or if it is the first vehicle verification and the first vehicle verification is performed, step 706 follows. Execute the process. In addition, here, in order to simplify the explanation, it is assumed that after the starting point is the point A, the point E is designated as the downstream point and the vehicle matching between these points is completed. And step 70
At 6, it is determined whether or not there is a downstream point to be selected next. If vehicle verification has already been performed at points F and H as downstream points, there is no AVI device 10 further downstream, so the determination in step 706 is
It becomes "none". In other cases, it is determined to be “present”. In this example, F can be selected as the downstream point, so the determination in step 706 is “present”.

Next, in step 707, the next downstream point is designated. In the case of this example, the point F is designated. Next, the process proceeds to step 708, and it is determined whether or not the upstream point and the downstream point in the previous vehicle matching have been matched. In the case of this example, it is determined whether or not the upstream point D and the point E are matched. Step 708
If the determination in step 1 is “Yes” (matched), the downstream point in the previous vehicle verification is set to the upstream point in step 709. In the case of this example, the upstream point is point E and the downstream point is point F. After the upstream point and the downstream point have been set, vehicle verification is performed by exchanging the two points (step 71).
2).

On the other hand, the determination result in step 708 is "N
o ”(no match), step 7
Then, the process proceeds to step 10, and it is determined whether or not there is a match in the second vehicle matching (a point which is two points away from the downstream point designated in step 707). In this case,
Since the downstream point designated in step 707 is the point F, the point D becomes when the two points are reached, and when the downstream point is the point D, it is determined whether or not matching has been performed. Here, as an exception processing in step 710, when a point that is two downstream points coincides with an upstream point,
The determination result is “Yes”. This is step 707.
This is because, if the point designated by is the point C, the point A becomes the point A after the second point, which coincides with the upstream point.
In such a case, in step 711, the downstream point which is located at two points is set as the upstream point. For example, when the point F is designated in step 707, the upstream point is the point D. Then, vehicle matching between the two points thus set is performed (step 712).

The above-mentioned processing is repeated, and step 7 is performed.
If there are no downstream points to be selected in 06, or if the determination in step 710 is “No”, then the OD is specified in step 713. In this identification method, the most downstream point among the matched points is the end point.

The processing after step 714 is the same as that of the first embodiment, and in step 714, 1 (vehicle) is added to the traffic volume of the group determined as the start point / end point. Step 71
In step 5, the data of the matched target vehicle is marked to be matched, so that the process of excluding the target vehicle from the starting point in the subsequent processes is performed. In step 716, it is determined whether or not the target vehicle exists at the starting point in consideration of the target period for creating the OD information. In step 717, it is determined whether or not there is a next starting point candidate. Through the above processing, the total traffic volume of OD in the target period is calculated.

In the present embodiment, the vehicle number recognized by the AVI device 10 is collated, and the point to which one AVI device 10 belongs is set as the starting point and the point to which the other AVI device belongs is set as the end point in the set of matching results. Since the start point / end point information is generated as described above, it is possible to automatically create the OD information, reduce the burden and cost of the operator, and create the desired OD information with high accuracy. Further, according to the present embodiment, since the vehicle number is also collated at the point between the starting point and the ending point, even if there are a plurality of paths from the starting point to the ending point, one path is specified. be able to.

Next, a third embodiment of the present invention will be described with reference to FIGS.
Follow the instructions below. In this embodiment, the OD estimator 303 is
Using the vehicle number and passage record data obtained from each AVI device 10, the true OD is estimated from the obtained observation OD. That is, in each AVI device 10, the capture rate is 100% (all passing vehicles are detected,
Recognizing the vehicle number) is impossible and some miss it. Therefore, the observation OD created from the data including this error contains an error. Therefore, the OD estimator 30
3 is used to estimate the true OD from the observed OD using the value of the capture rate. The specific contents will be described below.

FIG. 8 shows the installation situation of each AVI device 10, and shows that the observation OD (in the case of the first embodiment) is from point B to point E. Here, the capture rate is B and the missed rate is (1-P). Then, in the present embodiment, as a precondition, a case where the vehicle to be collated is overlooked at an upstream point adjacent to the starting point and a downstream point adjacent to the ending point among the points in the observation OD is considered. In other words, the observation OD is B →
If it becomes E, consider missing points at points A and F. Therefore, when the observed OD is B → E, the true OD is B → E (not missed), A → E (missed at point A), B → F (missed at point F). , A → F
(It was overlooked at points A and F). The establishment of these four true ODs as the observation ODs (B → E) is as shown in FIG.

FIG. 9 is a diagram showing a true OD considered from one observation OD. On the other hand, FIG. 10 shows the opposite approach, showing a set of possible observed ODs and the probability of their occurrence from one true OD. That is, when the true OD is B → E, the overlooking at the points B and E is considered.

Each AV considering the contents shown in FIGS. 9 and 10
To summarize the entire installation location of I-device 10, observe O
The relationship between D and the true OD is shown in FIG.

The probability of occurrence from true OD to observation OD is P
², P²(1-P), P²(1-P)²One of the
Is clear, the relationship between observed OD and true OD is
It is expressed by the formula. [Observation OD] = [A (matrix represented by capture rate)] [true OD] (1) The matrix A is obtained by combining the occurrence probabilities with the relationship of FIG.
Therefore, if the value of the capture rate P is known, it is calculated in advance.
You can leave it out. Therefore, the inverse matrix A ^-1Calculate
It is possible to do, and the following formulas hold. [True OD] = [A^-1(Inverse matrix of A)] [Observation OD] (2) As described above, the OD estimator 303 uses A using the capture rate.
^-1By calculating the
Can be estimated. As described above, in this embodiment,
Using the capture rate of each AVI device 10, the OD information generator 3
The true OD is calculated from the observation OD calculated in 02.
Therefore, it is possible to create OD information that is closer to the actual phenomenon.
Therefore, the performance of the AVI device 10 can be supplemented.

In this embodiment, as a prerequisite, only the upstream point adjacent to the starting point and the downstream point adjacent to the ending point are taken into consideration when the passing vehicle is missed, but the upstream side of the starting point and the downstream side of the ending point are considered. It is also possible to consider many points.

[0033]

EFFECTS OF THE INVENTION The present invention has the following effects, as is apparent from the above embodiments. (1) The vehicle numbers recognized by the vehicle recognizing means arranged at different points are collated, and the point to which one of the vehicle recognizing means belongs in the set in which the collating results are coincident is set as a starting point and the other vehicle recognizing means Since the start point / end point information is generated with the point to which it belongs as the end point, the start point / end point information can be created automatically, and it is not necessary to place the worker on the site, and the workload of the worker can be reduced. You can (2) Since the vehicle recognition means can be provided at the designated point, it is possible to solve the problems that the survey points are limited and the number of samples is small. (3) Since the starting point / ending point information can be automatically created, it is not necessary to collect the survey form, and the OD information can be created in a short time. (4) Even when the range of creating the OD information is widened, it is possible to create the OD information in a wide range only by disposing the vehicle recognizing means at the designated position. (5) Since the OD information can be created without stopping the vehicle, it is possible to prevent the occurrence of traffic congestion due to the creation of the OD information. (6) Since a duplicate set is specified as a combination of vehicle recognition means, vehicle matching is performed between two points to which the specified set belongs, and one set is selected from the result of this matching to create OD information. The OD information can be created based on the information of the vehicle recognition means that is less affected by the capture rate. (7) When performing vehicle verification between two points, vehicle verification is performed from the set of downstream points adjacent to the starting point, and then 2 in order.
Since the vehicle verification is performed by designating a set of points, one path can be specified even when there are a plurality of paths from the start point to the end point. (8) By using the capture rate of the vehicle recognizing means, the true OD information can be obtained from the OD information based on the recognition result of the vehicle recognizing means, and the OD information close to the actual phenomenon can be created. (9) Since the true OD information is calculated using the capture rate for the recognition result of the vehicle recognition means, the performance of the vehicle recognition means can be supplemented.

[Brief description of drawings]

FIG. 1 is an overall configuration block diagram of a start point / end point information creating device according to a first embodiment of the present invention.

FIG. 2 is an explanatory diagram showing the installation status of the AVI device in the first and second embodiments.

FIG. 3 is an explanatory diagram showing a relationship between a starting point and an end point candidate point in the first embodiment.

FIG. 4 is a flowchart for explaining the operation of the starting point / ending point information creating apparatus of the first embodiment.

FIG. 5 is an explanatory diagram of a vehicle matching method in the first and second embodiments.

FIG. 6 is an explanatory diagram of a method of designating an upstream point and a downstream point in the second embodiment.

FIG. 7 is a flowchart for explaining the operation of the starting point / ending point information creating apparatus according to the second embodiment.

FIG. 8 is an explanatory diagram of the installation status of the AVI device in the third embodiment.

FIG. 9 is an explanatory diagram showing the relationship between the observed OD and the true OD in the third embodiment.

FIG. 10 is an explanatory diagram of a relationship between a true OD and an observed OD in the third embodiment.

FIG. 11 is an explanatory diagram showing the relationship between the true OD and the observed OD in the entire installation location of the AVI device in the third embodiment.

[Explanation of symbols]

 10 AVI device 20 Communication control device 30 Central information creation device 301 Constant setting device 302 OD information creation device 303 OD estimator

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Masahiro Kojima 4-3-1, Tsunashima-higashi, Kohoku-ku, Yokohama-shi, Kanagawa Matsushita Communication Industrial Co., Ltd.

Claims (5)

[Claims] 1. A plurality of vehicle recognition means for recognizing vehicle numbers of vehicles traveling on a road at different points, a judgment means for comparing the recognition results of the respective vehicle recognition means, and judging whether the two match. As a traveling information of the vehicle recognized by the plurality of vehicle recognition means when a positive determination result is obtained by the means, a starting point is a point to which one vehicle recognition means belongs and an end point to a point to which the other vehicle recognition means belongs. A starting point / ending point information creating device including a starting point / ending point information generating means for generating ending point information. 2. A plurality of vehicle recognizing means for recognizing vehicle numbers of vehicles traveling on a road at different points, and a combination designating means for designating a plurality of combinations of vehicle recognizing means based on each vehicle recognizing means. And a judgment means for judging the coincidence between the recognition results of the vehicle recognition means belonging to each combination designated by the combination designating means, and a pair for which a positive determination result is obtained by the determination means, the interval is the maximum. As the traveling information of the vehicle recognized by the pair of vehicle recognizing means arranged at the point, starting point / end point information is generated starting from the point to which one vehicle recognizing means belongs and ending to the point to which the other vehicle recognizing means belongs. A starting point / ending point information generating device including a starting point / ending point information generating means. 3. A vehicle at a point adjacent to each other as a combination of a plurality of vehicle recognition means for recognizing vehicle numbers of vehicles traveling on a road at different points and a pair of vehicle recognition means based on each vehicle recognition means. A first combination designating means for designating the recognition means and a first determination means for collating the recognition results of the vehicle recognition means belonging to the set designated by the first combination designating means to determine whether the two match, and each vehicle recognition means. A second combination designation means for designating a vehicle recognition means at a point on the downstream side of an adjacent point as a combination of vehicle recognition means forming a pair, and a vehicle recognition belonging to a set designated by the second combination designation means. The second judging means for collating the recognition results of the means to judge the coincidence of the both, and the vehicle recognizing hand for which a positive judgment result is obtained by the first judging means and the second judging means Generating start point / end point information starting from the point to which the vehicle recognizing means arranged on the most upstream side of the step belongs and ending at the point to which the vehicle recognizing means arranged most downstream side belongs A starting point / ending point information creating device including means. 4. A capture rate indicating a ratio of the number of vehicles traveling on a road where each vehicle recognition means is arranged among the vehicles traveling on the road to the number of vehicles recognized by each vehicle recognition means is calculated. 4. The start point according to claim 1, 2 or 3, further comprising: a capture rate calculation unit that performs the capture rate calculation, and a correction unit that corrects the start point / end point information generated by the start point / end point information generation unit based on the calculated value of the capture rate calculation unit. -End point information creation device. 5. The recognition time measuring means for measuring the vehicle recognition time of each vehicle recognizing means is provided, and the determining means includes the measurement value of the recognition time measuring means of the recognition result of each vehicle recognizing means within the set time. 5. The starting point / end point information creating device according to claim 1, which has a function of collating only the recognized recognition result.