JP7449891B2 - Traffic condition monitoring device, traffic condition monitoring method and program - Google Patents

Description

The present disclosure relates to a traffic condition monitoring device, a traffic condition monitoring method, and a program.

Patent Document 1 discloses the following on-vehicle device. In other words, the on-vehicle device described in Patent Document 1 measures the inter-vehicle distance between the own vehicle to be monitored and another vehicle traveling in front of it, and compares the time margin according to the inter-vehicle distance with a threshold value. to determine whether there is an abnormal approach. Furthermore, this on-vehicle device grasps the meandering state from time-series changes in the travel trajectory of the own vehicle based on the lateral positional relationship between the white line on the road and the own vehicle. Additionally, this on-vehicle device learns statistics representing the meandering state when there is no abnormal approach. In addition, in the case of an abnormal approach, this on-vehicle device determines whether or not the vehicle is driving aggressively by determining the magnitude of the difference between the latest statistical value representing the meandering state and the learned statistical value. According to this on-vehicle device, abnormal driving behavior such as aggressive driving by the driver of the own vehicle can be detected.

JP2020-24580A

However, the on-vehicle device described in Patent Document 1 determines the meandering state from time-series changes in the travel trajectory of the own vehicle based on the positional relationship between the white line on the road and the own vehicle, so if the white line cannot be detected, the meandering state The problem was that it was not possible to understand the

The present disclosure has been made to solve the above problems, and includes a traffic condition monitoring device, a traffic condition monitoring method, and a traffic condition monitoring device that can stably monitor the traffic condition (driving condition) of a moving object (for example, a vehicle). The purpose is to provide programs.

In order to solve the above-mentioned problems, a traffic situation monitoring device according to the present disclosure is based on a time series of position information of the evaluation target mobile object, and information representing the traffic situation of the evaluation target mobile object for each predetermined traffic section. A traffic information generation unit that generates traffic information, and a determination that determines whether or not the traffic of the evaluation target mobile body is unique by comparing the traffic information of the evaluation target mobile body and the traffic information of other mobile bodies. It is equipped with a section and a section.

The traffic situation monitoring method according to the present disclosure includes the step of generating traffic information that is information representing the traffic situation of the evaluation target mobile object for each predetermined traffic section based on the time series of position information of the evaluation target mobile object; The method further includes the step of determining whether or not the traffic of the evaluation target mobile body is unique by comparing the traffic information of the evaluation target mobile body with the traffic information of other mobile bodies.

According to each of the above-mentioned aspects, the traffic situation can be stably monitored.

FIG. 1 is a system diagram showing a configuration example of a driving condition monitoring device according to an embodiment of the present disclosure. FIG. 2 is a schematic diagram illustrating a configuration example of driving information used in a driving condition monitoring device according to an embodiment of the present disclosure. FIG. 7 is a schematic diagram illustrating another configuration example of driving information used in the driving condition monitoring device according to the embodiment of the present disclosure. FIG. 2 is a schematic diagram illustrating a configuration example of driving section information used in the driving condition monitoring device according to the embodiment of the present disclosure. It is a flow chart which shows an example of operation of a judgment part concerning an embodiment of this indication. FIG. 3 is a schematic diagram for explaining an example of the operation of the determination unit according to the embodiment of the present disclosure. FIG. 3 is a schematic diagram for explaining an example of the operation of the determination unit according to the embodiment of the present disclosure. FIG. 3 is a schematic diagram for explaining an example of the operation of the determination unit according to the embodiment of the present disclosure. It is a flow chart which shows an example of operation of a judgment part concerning an embodiment of this indication. FIG. 3 is a schematic diagram for explaining an example of the operation of the determination unit according to the embodiment of the present disclosure. FIG. 3 is a schematic diagram for explaining an example of the operation of the determination unit according to the embodiment of the present disclosure. FIG. 1 is a schematic block diagram showing the configuration of a computer according to an embodiment of the present disclosure.

(Example of configuration of driving condition monitoring device)
Hereinafter, a configuration example of a driving condition monitoring device (traffic condition monitoring device) according to an embodiment of the present disclosure will be described with reference to FIGS. 1 to 4. FIG. 1 is a system diagram showing a configuration example of a driving condition monitoring device according to an embodiment of the present disclosure. FIG. 2 is a schematic diagram illustrating a configuration example of driving information used in the driving situation monitoring device according to the embodiment of the present disclosure. FIG. 3 is a schematic diagram showing another configuration example of driving information used in the driving situation monitoring device according to the embodiment of the present disclosure. FIG. 4 is a schematic diagram illustrating a configuration example of driving section information used in the driving condition monitoring device according to the embodiment of the present disclosure. In addition, in each figure, the same reference numerals are used for the same or corresponding components, and the description thereof will be omitted as appropriate.

As shown in FIG. 1, a driving condition monitoring device (or also called a driving condition monitoring system) 100 according to an embodiment of the present disclosure includes a central data device 1, a driving information processing device 2, a road charge determination device 3, It includes a traffic statistics information notification device 4, a traffic violation determination device 5, a road charge management device 6, a traffic statistics information management device 7, a traffic violation management device 8, and a plurality of in-vehicle devices 10. Each of the devices 1 to 8 can be configured using, for example, a server, a personal computer, and its peripheral devices.

The vehicle-mounted device 10 includes a GNSS (Global Navigation Satellite System) receiving device 11 , an information processing device 12 , and a mobile communication device 13 . The on-vehicle device 10 is mounted on a plurality of automobiles (mobile bodies) C1, C2, etc. that travel on a road 301. Note that the device on which the in-vehicle device 10 is mounted is not limited to a car, and may be a bicycle, a two-wheeled vehicle, a drone, or the like as long as it is mobile. Furthermore, the travel information to be described later may be compared between different moving objects, such as a car and a two-wheeled vehicle, a drone and a bicycle, and the like.

The GNSS receiving device 11 repeatedly calculates position information (latitude, longitude, sea level, etc. of the antenna position) at a predetermined period based on GNSS signals received from a plurality of GNSS satellites 401 using an antenna for receiving GNSS signals. Output to the processing device 12. Note that the GNSS receiving device 11 may have a function of correcting errors in position information by receiving a GNSS correction signal transmitted by an antenna 402 installed on the side of the road 301, for example.

The information processing device 12 repeatedly transmits the time series (time series data) of the position information acquired from the GNSS receiving device 11 to the central data device 1 using the mobile communication device 13, for example, repeatedly at regular intervals. For example, the information processing device 12 may transmit unique information (for example, the type of vehicle, the vehicle number, etc.) of the vehicle C1 in which the on-vehicle device 10 is mounted together with the location information to the central data device 1. Note that the position information calculated by the GNSS receiving device 11 is also referred to hereinafter as the position information of the on-vehicle device 10 or the position information of the vehicle (C1 etc.).

The mobile communication device 13 establishes a communication connection with the central data device 1 via a communication network such as a mobile communication network by connecting to the mobile base station 403 or the like.

The central data device 1 collects all the time series of position information for a certain period transmitted by the plurality of onboard devices 10 and stores it in the storage device 1-1. The central data device 1 stores the time series of each location information using, for example, an individual identification number set in the mobile communication device 13 as an identification code (vehicle identification code) of each on-vehicle device 10. Further, the central data device 1 stores the travel information generated by the travel information processing device 2 in the storage device 1-1. Further, the central data device 1 provides the road charge determining device 3, the traffic statistical information notifying device 4, and the traffic violation determining device 5 with the driving information stored in the storage device 1-1. At that time, the central data device 1 can provide the driving information in the form of, for example, writing the vehicle and speed based on the driving information on the map (adding it to the map data).

(Example of configuration of driving information generation unit 21)
The travel information processing device 2 includes a travel information generation section 21 (traffic information generation section) as a functional configuration composed of a combination of hardware such as a computer and software such as a program executed by the computer. The driving information generation unit 21 calculates the “driving situation” (traffic situation) of the automobile C1 for each predetermined “driving section 310” (traffic section) based on the time series of position information of the automobile C1, etc., which is an example of the vehicle to be evaluated. ``Traveling information'' (traffic information) is generated. Then, the traveling information generation unit 21 transmits the generated traveling information to the central data device 1 and stores it in the central data device 1.

Note that the "driving section 310" is a portion of the road 301 that is divided into a plurality of sections by a predetermined distance, or divided into a plurality of sections corresponding to shapes such as straight lines, curves, and slopes. . Each traveling section 310 adjacent to each other may have an overlapping portion or may not have an overlapping portion.

In addition, "driving situation" is information representing the driving mode of the car, the surrounding environment of the car, etc., such as the driving time, driving time period, driving speed, driving acceleration (front/rear direction, left/right direction), weather at the time of driving, etc. , the travel trajectory (for example, the time series of position information itself), the passing time of the target section, the travel direction, and other information. The travel information generation unit 21 acquires the time series of position information of each vehicle from the central data device 1, identifies one or more travel sections based on the time series of the acquired position information, and determines the travel sections and travel conditions. Travel information is generated for each travel section in association with each other. At this time, the travel information generation unit 21 refers to, for example, map information or travel section information to be described later, specifies a travel section based on position information, and generates travel information for each specified travel section. Note that the driving information generation unit 21 acquires the weather during driving from, for example, an external server (not shown) that provides weather information.

FIG. 2 shows an example of the configuration of travel information (travel information 201) generated by the travel information generation unit 21. Traveling information 201 shown in FIG. 2 includes a traveling section identification code that is identification information of a traveling section 310, a vehicle identification code that is identification information of a car or on-vehicle device, and a time series of position information. The location information time series is, for example, a time series of location information (a set of data representing date and time, latitude, and longitude) corresponding to the travel section.

FIG. 3 shows another example of the configuration of the driving information (driving information 202) generated by the driving information generation unit 21. The travel information 202 shown in FIG. 3 includes a travel section identification code that is identification information of the travel section 310, a travel direction (traffic direction when the travel section is two-way traffic), and identification information of the vehicle or onboard device. Vehicle identification code, date and time (year, month, day, hour, minute, and second), weather information such as cloud cover, rainfall, snowfall, temperature, presence of fog, etc. around the relevant driving section, and speed (driving speed (average, minimum). , maximum)), acceleration (travel acceleration (front/rear, left/right)), and position information time series. However, for example, a part of the position information time series etc. may be omitted.

FIG. 4 shows a configuration example of driving section information (driving section information 203) that the driving information generation unit 21 refers to when specifying a driving section. The travel information processing device 2 stores each travel section information for each travel section. The traveling section information 203 shown in FIG. 4 includes a traveling section identification code that is identification information of the traveling section 310, a traveling direction (traffic direction when the traveling section is two-way traffic), and coordinates representing the range of the traveling section. It includes information (coordinates of latitude and longitude of the boundary), curvature (average, maximum) of the travel section, and speed limit.

The road charge determination device 3 shown in FIG. 1 acquires travel information stored in the central data device 1, and based on the travel information, performs driving that places a load on the road 301 (sudden start, sudden deceleration, etc.), for example. It is determined whether or not driving (including speeding, etc.) has occurred, and the road charge management device 6 is notified of the determined result. Alternatively, the road charge determination device 3 determines, based on the driving information, whether or not driving that avoids a specific lane occurs when an obstacle such as a fallen object exists on the road 301, for example. It is also possible to make a determination and notify the road charge management device 6 of the determined result. The road charge management device 6 is, for example, a device operated by a business operator that manages the road 301, and refers to the determination result of the road charge determination device 3 based on an operator's instruction, and determines whether, for example, a specific vehicle It performs billing management such as charging a certain extra fee, and arranges to patrol the place where a fallen object has occurred if it is determined that it exists.

The traffic statistical information notification device 4 shown in FIG. 1 acquires travel information stored in the central data device 1, and displays, for example, the number of vehicles and average speed on a map based on the travel information. The traffic statistical information management device 7 is notified of information representing a map created to facilitate understanding of the occurrence of traffic jams. The traffic statistics information management device 7 is, for example, a device operated by a local government that manages the road 301 or a business operator commissioned by the local government, and is configured to receive information from, for example, the traffic statistics information notification device 4 based on instructions from an operator. View, edit, or print the notified information.

(Configuration example and operation example of determination unit 51)
The traffic violation determination device 5 includes a determination unit 51 as a functional configuration composed of a combination of hardware such as a computer and software such as a program executed by the computer. The determination unit 51 compares the driving information of the car C1, which is an example of the vehicle to be evaluated, with the driving information of the car C2, which is an example of other vehicles, to determine whether the driving of the car C1 corresponds to, for example, dangerous driving. Determine whether it is unique. The traffic violation determination device 5 provides the determined results to the traffic violation management device 7.

For example, the determination unit 51 determines whether the values are different from each other by comparing, for example, a value based on the movement in the left and right direction based on the driving information of the evaluation target vehicle and a value based on the statistics of the movement in the left and right direction based on the driving information of other vehicles. It is possible to determine whether or not the running of the vehicle to be evaluated is unusual based on whether or not there is a difference greater than a certain level, and if it is determined to be peculiar, it can be determined that the vehicle to be evaluated is driving in a meandering manner. . Alternatively, when the curvature of the traveling section is greater than or equal to a predetermined value, the determination unit 51 determines the statistical value of the passing speed of the traveling section based on the traveling information of the evaluation target vehicle and the passing speed of the said traveling section based on the traveling information of other vehicles. By comparison with the values based on It can be determined that the vehicle is speeding. Alternatively, if the inter-vehicle distance between the vehicle to be evaluated and the vehicle ahead based on the travel information of the vehicle to be evaluated and the travel information of other vehicles is less than or equal to a predetermined threshold, the determination unit 51 determines that the vehicle to be evaluated is running abnormally. In this case, it can be determined that the driver is driving dangerously by not maintaining the following distance. However, if the running speeds of the vehicle to be evaluated and the vehicle ahead are lower by more than a predetermined value or lower than a predetermined ratio compared to the running speeds of surrounding vehicles, the determination unit 51 determines that there is a risk of not maintaining the following distance. It is possible to cancel the determination that the driver is driving, and determine that the vehicle ahead is driving dangerously due to low speed. In addition to the comparison using a predetermined value, the determination as to whether or not it is unique may be performed using artificial intelligence. Specifically, data related to dangerous driving such as meandering driving, excessive speed, and failure to maintain a following distance are learned in advance, and the learned data is compared with the driving information of the vehicle being evaluated to detect meandering driving, excessive speed, and failure to maintain a following distance. It may be determined whether this constitutes dangerous driving.

The process by which the determination unit 51 determines unusual driving corresponding to dangerous driving will be described below. FIG. 5 is a flowchart illustrating an example of the operation of the determination unit 51 according to the embodiment of the present disclosure. FIG. 5 shows an example of the basic operation of the determination unit 51. In the operation example shown in FIG. 5, first, the determination unit 51 acquires driving information of the evaluation target vehicle from the central data device 1 (step S101). Next, the determination unit 51 acquires driving information of other vehicles in the same driving section, same time zone, and same weather from the central data device 1 (step S102). Next, the determination unit 51 determines whether or not the running of the evaluation target vehicle is unusual by comparing the running information of the evaluation target vehicle with the travel information of other vehicles (step S103). If the running of the vehicle to be evaluated is unusual (“Yes” in step S103), the determining unit 51 determines that the vehicle to be evaluated is driving dangerously (step S104).

In addition, in determining whether or not the own vehicle alone (the number of persons to be evaluated alone) has engaged in dangerous driving, the determination unit 51 additionally records the driving information of the own vehicle, the speed limit, and the lane information in an arbitrary driving section. It compares map data or driving information of other cars at the same time and weather conditions (including past ones), and if your car violates traffic rules or is unusual in comparison to other cars, the system detects dangerous driving. It can be determined that Dangerous driving can be detected flexibly by changing the items that are determined to be dangerous driving depending on the road shape. For example, meandering driving on a straight road and running speed on a curved section can be used as a determination item for dangerous driving.

In the case of meandering driving, for example, machine learning can be used to determine whether or not it is unusual, based on the statistics of past data of driving information (dispersion of left/right movement relative to the direction of travel, second/fourth moment, distribution of This can be done by clustering (shapes, image identification of data graphs, etc.) and classifying driving into normal driving and dangerous driving using a trained model. Using the learned parameters, it is possible to determine whether dangerous driving is occurring or not based on the statistics of the vehicle to be determined. FIG. 6 is a schematic diagram for explaining an example of the operation of the determination unit according to the embodiment of the present disclosure. FIG. 6 shows a comparison between the travel of the automobile C1, which is the vehicle to be evaluated, (on the left) and the travel of a plurality of other vehicles C2 (on the right) in the same travel section 310a on the same road 301a. By classifying the driving information of the vehicle C1 using the learned model learned based on the driving information of the plurality of other vehicles C2, the determination unit 51 distinguishes between the driving information of the evaluation target vehicle and the driving information of the other vehicles. Through the comparison, it can be determined whether or not the running of the vehicle to be evaluated is unusual.

Furthermore, if the vehicle exceeds the speed limit, it can be determined that the vehicle is driving dangerously, based on the statistics of past data of the driving information, for example, if the vehicle speed is faster than μ+2σ (average + twice the standard deviation) for a certain period of time. 7 and 8 are schematic diagrams for explaining an example of the operation of the determination unit 51 according to the embodiment of the present disclosure. FIG. 7 shows a driving example of a car C1, which is an evaluation target vehicle, in a driving section 310b of a road 301b, and FIG. 8 shows a driving example of a plurality of other vehicles C2 in the same driving section 310b of the same road 301b.

As described above, the determination unit 51 calculates the statistics from the time series of the obtained position information, and calculates the results of class classification such as clustering, or the outliers from the average value of the statistics (more than several times the standard deviation). It can be determined that it is singular if there is a deviation, outliers when plotting a boxplot, etc.). Behaviors that are judged to be unusual include behavior that periodically deviates left and right like a sine wave with respect to the direction of travel, the distance between the vehicle in front is short, approaches or moves away from the vehicle in front, and acceleration and deceleration. Significant behavior can be mentioned.

Further, the determination unit 51 extracts past data to be compared (same weather time) based on weather and time information, but in the unlikely event that the amount of past data extracted is insufficient as the amount of comparison data, In other areas with similar road structures, calculate the statistical difference (amount of difference) between the same weather time and other areas. Then, the determination unit 51 adjusts the value of the statistic using the obtained difference amount and past data at times other than the same weather time, thereby making it possible to cope with data shortages. For example, if there is a lack of late night and rain data in a certain analysis area, compare the statistics in other areas (areas with similar road structures) under the same meteorological time and time conditions and in other cases. The error ΔS of the statistics is recorded, and when the analysis area is under the same weather and time conditions, the sum of the statistics for other cases and ΔS is defined as the statistics under the same weather and time conditions. That is, the determination unit 51 compares, for example, a predetermined value based on the driving information of the vehicle to be evaluated with a value obtained by statistically correcting a statistical amount based on the driving information of other vehicles linked to a similar driving section. Accordingly, it can be determined whether or not the running of the vehicle to be evaluated is unusual.

Next, regarding the determination of dangerous driving involving the own vehicle and another vehicle (e.g. not maintaining the distance between vehicles), the determination unit 51 uses driving information of the own vehicle and related other vehicles in any section or travel time, and the same time. Comparisons are made with the driving information (including past information) of other vehicles in the same region and weather conditions, and if the distance between the vehicle and the other vehicle is extremely short, the driver can determine that the driver is driving dangerously due to not maintaining a safe distance between vehicles. On the other hand, if the determining unit 51 determines that the distance between the vehicle and the vehicle ahead is short and the distance between the vehicle and the vehicle ahead is not maintained, but the traveling speed of the own vehicle and the vehicle ahead is significantly slow compared to the traveling speed of the surrounding vehicles, It is determined that the distance between the host vehicle and the vehicle in front of the vehicle has become shorter due to low speed driving, and it is possible to cancel the distance not maintained between the host vehicle and determine that dangerous driving is caused by the low speed travel of the vehicle in front of the vehicle.

FIG. 9 is a flowchart illustrating an example of the operation of the determination unit 51 according to the embodiment of the present disclosure. FIG. 9 shows an operation example in which the determining unit 51 determines dangerous driving based on not maintaining the following distance. In the operation example shown in FIG. 9, first, the determination unit 51 acquires travel information of the evaluation target vehicle from the central data device 1, and acquires the travel position and travel speed of the evaluation target vehicle (step S201). Next, the determination unit 51 acquires the traveling information of the vehicle ahead of the evaluation target vehicle from the central data device 1, and acquires the traveling position and traveling speed of the vehicle ahead (step S202). Next, the determination unit 51 determines whether the running speeds of the evaluation target vehicle and the vehicle ahead are approximately the same (step S203). If the traveling speeds are not substantially the same ("No" in step S203), the determination unit 51 returns to step S201 and acquires new traveling information.

On the other hand, if the traveling speeds are approximately the same ("Yes" in step S203), the determination unit 51 calculates the inter-vehicle distance between the evaluation target vehicle and the vehicle ahead (step S204). Next, the determining unit 51 determines whether the inter-vehicle distance is extremely short (step S205). If the inter-vehicle distance is not extremely short (“No” in step S205), the determination unit 51 returns to step S201 and acquires new travel information. On the other hand, if the inter-vehicle distance is extremely short ("Yes" in step S205), the determination unit 51 obtains the traveling speeds of surrounding vehicles at the same time (step S206).

Next, the determining unit 51 determines whether the traveling speed of the evaluation target vehicle and the traveling speeds of surrounding vehicles at the same time are approximately equal (step S207). On the other hand, if the traveling speed and the traveling speed are not substantially equal ("No" in step S207), the determination unit 51 determines that the vehicle ahead is driving dangerously due to low speed traveling (step S208); If they are substantially equal ("Yes" in step S207), the determining unit 51 determines that the evaluation target vehicle is driving dangerously due to not maintaining the distance between vehicles (step S209).

10 and 11 are schematic diagrams for explaining an example of the operation of the determination unit 51 according to the embodiment of the present disclosure. FIGS. 10 and 11 show an example in which the following distance is not maintained. FIG. 10 shows a driving example at a certain time (on the left) and a driving example (on the right) after a predetermined time of the vehicle C1, which is the evaluation target vehicle, and a plurality of other vehicles C21, C22, and C23 in the same driving section 310c on the same road 301c. and The inter-vehicle distance between the vehicle C1 and the vehicle C21 in front is extremely short (below a predetermined threshold value corresponding to the traveling speed). The traveling speed of the vehicle C1 and the plurality of other vehicles C21, C22, and C23 is 80 km/h. In the example shown in FIG. 10, the determination unit 51 determines that the evaluation target vehicle C1 is driving dangerously due to failure to maintain distance between vehicles ("Yes" in step S203 → "Yes" in step S205 → "Yes" in step S207 → Step S209).

FIG. 11 shows a driving example at a certain time (on the left) and a driving example (on the right) after a predetermined time of the vehicle C1, which is the vehicle to be evaluated, and a plurality of other vehicles C21, C22, and C23 in the same driving section 310c on the same road 301c. and The inter-vehicle distance between the vehicle C1 and the vehicle C21 in front is extremely short (below a predetermined threshold value corresponding to the traveling speed). The traveling speed of the car C1 and the plurality of other cars C21 is 40 km/h. The traveling speed of cars C22 and C23 is 80 km/h. In the example shown in FIG. 11, the determination unit 51 determines that the forward vehicle C21 is driving in a dangerous manner due to low-speed driving ("Yes" in step S203 → "Yes" in step S205 → "No" in step S207 → step S208 ).

(effects, effects, etc.)
In the embodiment described above, the use of GNSS eliminates the need for an on-vehicle camera, eliminates the need for image processing and the inability to take pictures due to the surrounding environment, and has the advantage that speed and the like can be measured more accurately. Therefore, according to the driving situation monitoring device and the driving situation monitoring method of the present disclosure, it is possible to stably monitor the driving situation.

Furthermore, by aggregating GNSS information in the central data device 1, it is possible to prevent falsification of position information, and there are also advantages in that it is possible to understand the movement of vehicles around the own vehicle and to understand the origin of dangerous driving.

Furthermore, by utilizing this technology, it is possible to provide a variety of services other than dangerous driving, such as evaluating driver driving ability, charging tolls on toll roads, and creating traffic statistics.

(Other embodiments)
Although the embodiment of the present disclosure has been described above in detail with reference to the drawings, the specific configuration is not limited to this embodiment, and includes design changes within the scope of the gist of the present disclosure. . For example, the onboard device 10 uses a CAN (Controller Area Network) or the like to acquire information indicating the steering angle, information indicating the angle of the brake pedal, etc., information corresponding to the acceleration in the left and right direction, and the presence or absence of sudden braking. The information shown may be added to the location information and transmitted to the central data device 1. In this case, the driving information generation unit 21 can include these additional information in the driving information. In addition to the conditions for the comparison targets, in addition to the same travel section, time of day, and weather, the conditions for comparison may be the same day of the week and whether it is a weekday or a holiday.

(computer configuration)
FIG. 12 is a schematic block diagram showing the configuration of a computer according to at least one embodiment.
Computer 90 includes a processor 91, main memory 92, storage 93, and interface 94.
The above-mentioned central data device 1, driving information processing device 2, road charge determination device 3, traffic statistics information notification device 4, traffic violation determination device 5, road charge management device 6, traffic statistics information management device 7, traffic violation management device 8 , and the in-vehicle device 10 are installed in a computer 90. The operations of each processing section described above are stored in the storage 93 in the form of a program. The processor 91 reads the program from the storage 93, expands it into the main memory 92, and executes the above processing according to the program. Further, the processor 91 reserves storage areas corresponding to each of the above-mentioned storage units in the main memory 92 according to the program.

The program may be for realizing a part of the functions to be performed by the computer 90. For example, the program may function in combination with other programs already stored in storage or in combination with other programs installed in other devices. Note that in other embodiments, the computer may include a custom LSI (Large Scale Integrated Circuit) such as a PLD (Programmable Logic Device) in addition to or in place of the above configuration. Examples of PLDs include PAL (Programmable Array Logic), GAL (Generic Array Logic), CPLD (Complex Programmable Logic Device), and FPGA (Field Programmable Gate Array). In this case, some or all of the functions implemented by the processor may be implemented by the integrated circuit.

Examples of the storage 93 include HDD (Hard Disk Drive), SSD (Solid State Drive), magnetic disk, magneto-optical disk, CD-ROM (Compact Disc Read Only Memory), and DVD-ROM (Digital Versatile Disc Read Only Memory). , semiconductor memory, etc. Storage 93 may be an internal medium connected directly to the bus of computer 90, or may be an external medium connected to computer 90 via an interface 94 or a communication line. Furthermore, when this program is distributed to the computer 90 via a communication line, the computer 90 that received the distribution may develop the program in the main memory 92 and execute the above processing. In at least one embodiment, storage 93 is a non-transitory, tangible storage medium.

<Additional notes>
The driving situation monitoring device 100 described in each embodiment is understood as follows, for example.

(1) The driving condition monitoring device 100 (traffic condition monitoring device) according to the first aspect is based on the time series of position information of the evaluation target vehicle (evaluation target moving object), and the driving condition monitoring device 100 (traffic condition monitoring device) ) for each predetermined travel section (traffic section); a determining unit 51 that determines whether or not the running of the evaluation target vehicle is unusual by comparing the running information of the vehicle (moving body). According to this aspect and each of the following aspects, the driving situation can be stably monitored.

(2) The driving situation monitoring device 100 according to the second aspect is the driving situation monitoring device 100 of (1), in which the determination unit 51 links the driving information to the same driving section as the evaluation target vehicle. It is determined whether or not the running of the evaluation target vehicle is unusual by comparing the running information of other vehicles.

(3) The driving condition monitoring device 100 according to the third aspect is the driving condition monitoring device 100 of (1), in which the determination unit 51 determines a predetermined value based on the driving information of the evaluation target vehicle, and the driving condition monitoring device 100 according to the third aspect. Determine whether or not the running of the vehicle to be evaluated is unusual by comparing it with a statistically corrected value of statistics based on running information of other vehicles linked to running sections similar to the predetermined running section. do. According to this aspect, by using information on a travel section similar to the predetermined travel section, it is possible to perform accurate determination when the number of data regarding other vehicles in the predetermined travel section is small.

(4) The driving situation monitoring device 100 according to the fourth aspect is the driving situation monitoring device 100 of (1) to (3), in which the determination unit 51 is configured to perform a left-right direction based on the driving information of the evaluation target vehicle. It is determined whether or not the running of the evaluation target vehicle is peculiar by comparing the value based on the movement of the vehicle with the value based on the statistics of the movement in the left and right directions based on the running information of the other vehicle. If it is determined that the evaluation target vehicle is driving in a meandering manner.

(5) The driving condition monitoring device 100 according to the fifth aspect is the driving condition monitoring device 100 of (1) to (4), in which the determination unit 51 determines that when the curvature of the driving section is equal to or greater than a predetermined value, , determining whether or not the running of the evaluation target vehicle is unusual by comparing the passing speed based on the running information of the evaluation target vehicle with a value based on statistics of the passing speed based on the running information of the other vehicle. However, if it is determined that the vehicle is abnormal, it is determined that the evaluation target vehicle is speeding.

(6) The driving situation monitoring device 100 according to the sixth aspect is the driving situation monitoring device 100 according to (1) or (2), in which the determination unit uses the driving information of the evaluation target vehicle and the driving information of the other vehicle. If the inter-vehicle distance between the evaluation target vehicle and the preceding vehicle (moving object in front) based on the driving information is less than or equal to a predetermined threshold, the evaluation target vehicle is traveling in an unusual manner and the inter-vehicle distance is not maintained. It is determined that this is dangerous driving.

(7) The driving condition monitoring device 100 according to the seventh aspect is the driving condition monitoring device 100 according to (6), in which the determination unit 51 determines whether the driving speed of the evaluation target vehicle and the vehicle in front are If the speed is lower than the predetermined value or lower than the predetermined percentage compared to the traveling speed of the vehicle, it is determined that the preceding vehicle is driving at a low speed and is driving dangerously.

100 Driving situation monitoring device (traffic situation monitoring device)
1 Central data device 2 Driving information processing device 3 Road charge determination device 4 Traffic statistics information notification device 5 Traffic violation determination device 6 Road charge management device 7 Traffic statistics information management device 8 Traffic violation management device 10 In-vehicle device 21 Driving information generation unit ( traffic information generation section)
51 Judgment section

Claims (7)

a traffic information generation unit that generates traffic information that is information representing the traffic situation of the evaluation target mobile object for each predetermined traffic section based on the time series of position information of the evaluation target mobile object;
a determination unit that determines whether or not the traffic of the evaluation target mobile body is unique by comparing the traffic information of the evaluation target mobile body with the traffic information of other mobile bodies;
Equipped with
The determining unit determines that when the inter-vehicle distance between the evaluation target moving object and the moving object in front based on the traffic information of the evaluation target moving object and the traffic information of the other moving object is less than or equal to a predetermined threshold, Determining whether the passing speeds of the evaluation target moving object and the moving object ahead are approximately equal to the passing speeds of surrounding moving objects;
If the passing speed of the moving object to be evaluated and the moving object in front of the moving object are approximately equal to the passing speeds of surrounding moving objects, the passing of the moving object to be evaluated is unusual and dangerous driving is caused by not maintaining the following distance. It is determined that there is
If the passing speed of the evaluation target moving object and the moving object in front is lower than the passing speed of surrounding moving objects by a predetermined value or more, or lower than a predetermined ratio, the moving object in front is low. determining that the driving is dangerous due to speeding, and not determining that the traffic of the evaluation target moving object is unusual;
Traffic monitoring device. The determination unit determines whether or not the traffic of the evaluation target mobile body is unique by comparing the traffic information of the evaluation target mobile body with traffic information of other mobile bodies linked to the same traffic section. The traffic situation monitoring device according to claim 1. The determination unit compares a predetermined value based on traffic information of the evaluation target moving body with a value obtained by statistically correcting a statistical amount based on traffic information of other moving bodies linked to a similar traffic section. The traffic situation monitoring device according to claim 1, wherein it is determined whether the traffic of the evaluation target moving object is unusual. The determination unit determines the above by comparing a value based on the movement in the left and right direction based on the traffic information of the evaluation target moving body and a value based on the statistics of the movement in the left and right direction based on the traffic information of the other moving body. According to any one of claims 1 to 3, it is determined whether or not the traffic of the evaluation target moving object is unusual, and when it is determined that the evaluation target moving object is unusual, it is determined that the evaluation target moving object is driving in a meandering manner. traffic monitoring device. When the curvature of the traffic section is greater than or equal to a predetermined value, the determination unit determines a value based on statistics of a passing speed based on traffic information of the evaluation target moving object and a passing speed based on traffic information of the other moving object. It is determined whether the passage of the evaluation target moving body is unusual by comparing the above, and if it is determined that the traffic of the evaluation target moving body is unusual, it is determined that the evaluation target moving body is overspeeding. The traffic condition monitoring device according to item 1. generating traffic information, which is information representing the traffic situation of the evaluation target mobile object for each predetermined traffic section, based on the time series of position information of the evaluation target mobile object;
determining whether the traffic of the evaluation target moving body is unique by comparing the traffic information of the evaluation target mobile body with the traffic information of other mobile bodies;
Equipped with
In the step of determining, further, the distance between the vehicle to be evaluated and the moving body in front based on the traffic information of the mobile body to be evaluated and the traffic information of the other mobile body is less than or equal to a predetermined threshold. If so, determining whether the passing speed of the evaluation target moving object and the moving object in front of the moving object is approximately equal to the passing speed of surrounding moving objects;
If the passing speed of the moving object to be evaluated and the moving object in front of the moving object are approximately equal to the passing speeds of surrounding moving objects, the passing of the moving object to be evaluated is unusual and dangerous driving is caused by not maintaining the following distance. It is determined that there is
If the passing speed of the evaluation target moving object and the moving object in front is lower than the passing speed of surrounding moving objects by a predetermined value or more, or lower than a predetermined ratio, the moving object in front is low. determining that the driving is dangerous due to speeding, and not determining that the traffic of the evaluation target moving object is unusual;
How to monitor traffic conditions. generating traffic information, which is information representing the traffic situation of the evaluation target mobile object for each predetermined traffic section, based on the time series of position information of the evaluation target mobile object;
determining whether the traffic of the evaluation target moving body is unique by comparing the traffic information of the evaluation target mobile body with the traffic information of other mobile bodies;
A program that executes
In the step of determining, further, the distance between the vehicle to be evaluated and the moving body in front based on the traffic information of the mobile body to be evaluated and the traffic information of the other mobile body is less than or equal to a predetermined threshold. If so, determining whether the passing speed of the evaluation target moving object and the moving object in front of the moving object is approximately equal to the passing speed of surrounding moving objects;
If the passing speed of the moving object to be evaluated and the moving object in front of the moving object are approximately equal to the passing speeds of surrounding moving objects, the passing of the moving object to be evaluated is unusual and dangerous driving is caused by not maintaining the following distance. It is determined that there is
If the passing speed of the evaluation target moving object and the moving object in front is lower than the passing speed of surrounding moving objects by a predetermined value or more, or lower than a predetermined ratio, the moving object in front is low. determining that the driving is dangerous due to speeding, and not determining that the traffic of the evaluation target moving object is unusual;
program.

Images