Traffic disruption detection device, traffic disruption detection method, and program

Abstract

The present invention provides a traffic congestion detection device, a traffic congestion detection method, and a program that can detect the occurrence of vehicle congestion or stagnation within a specified range. [Solution] The vehicle congestion detection device 1 is equipped with a data acquisition unit 11 that acquires probe data including information identifying a vehicle and location information of the vehicle at first and second time intervals, a data fitting unit 12 that distributes the probe data at the first time interval and the probe data at the second time interval to each mesh of a mesh map of an arbitrary area, an inflow / outflow determination unit 13 that compares the mesh to which the probe data at the first time interval is assigned to each vehicle with the mesh to which the probe data at the second time interval is assigned to each vehicle to determine whether the vehicle entered, left, or remained in that mesh between the first time interval and the second time interval, an inflow / outflow count calculation unit 14 that calculates the number of vehicles entering and leaving each mesh, and an obstacle detection unit 15 that detects the occurrence of traffic disruptions from the number of vehicles entering and leaving each mesh.

Description

Technical Field

[0001] The present invention relates to a traffic obstacle detection device, a traffic obstacle detection method, and a program for detecting traffic jams and stagnation of vehicles.

Background Art

[0002] In recent years, large-scale traffic obstacles have occurred on roads due to vehicle congestion caused by heavy snowfall and flooding of roads due to concentrated heavy rain. Examples of road traffic obstacles include traffic jams and stagnation of vehicles. "Traffic jam" refers to a state in which running vehicles are concentrated and a long column of vehicles that repeatedly slow down or stop and start continues. "Stagnation" refers to a state in which vehicles are staying in the same place, and includes cases where a plurality of vehicles are lined up and stopped, as well as cases where a single vehicle is stopped on the road. Generally, "stagnation" has more vehicles than "traffic jam", and the length from the leading vehicle to the trailing vehicle (traffic jam length · stagnation length) is likely to be longer.

[0003] Conventionally, a technique for collecting road traffic information using probe data provided from a running vehicle has been proposed (see, for example, Patent Documents 1 to 3). Probe data is data acquired from various sensors mounted on a vehicle via a mobile communication system, and in addition to the position (latitude and longitude) and speed of the vehicle, various information such as engine speed, fuel consumption information, driving history, and alarm history can be obtained.

[0004] For example, the traffic congestion information providing device described in Patent Document 1 includes a probe information storage unit that receives probe information including vehicle position and vehicle behavior information provided by multiple vehicles and stores the probe information in a probe database, map data that stores map information, a traffic congestion area detection unit that detects areas where traffic congestion occurs based on the vehicle position and vehicle behavior information in the probe information, a traffic congestion factor estimation unit that estimates the causes of traffic congestion from the location of the traffic congestion area detected by the traffic congestion area detection unit and the map information in the map data, and an information providing unit that provides information on the traffic congestion area based on the detection by the traffic congestion area detection unit and the information on the causes of traffic congestion estimated by the traffic congestion factor estimation unit, thereby enabling the identification of areas where traffic congestion occurs and the causes of traffic congestion.

[0005] Furthermore, the traffic disruption risk prediction device described in Patent Document 2 combines probe data and weather data to predict the risk of traffic disruption occurring on a road, based on congestion information created by a traffic disruption information creation server and weather information created by a weather information creation server.

[0006] Furthermore, the traffic congestion risk display device described in Patent Document 3 includes a traffic information meshing unit that colors the congestion information created by the traffic congestion information creation server based on map data with colors set according to numerical values ​​that decrease as the congestion level increases, and a traffic congestion risk display unit that calculates and displays predicted values ​​of traffic congestion risk for a road based on the congestion information drawn by the traffic information meshing unit, making it possible to visually check predicted values ​​of traffic congestion risks that may occur in the future. [Prior art documents] [Patent Documents]

[0007] [Patent Document 1] Japanese Patent Publication No. 2013-020524 [Patent Document 2] Japanese Patent Publication No. 2018-055207 [Patent Document 3] Japanese Patent Publication No. 2018-055208 [Overview of the project] [Problems that the invention aims to solve]

[0008] However, the traffic congestion information device described in Patent Document 1 can detect the occurrence of "traffic congestion," but it cannot detect the "stagnation" of vehicles. Furthermore, the devices described in Patent Documents 2 and 3 predict the degree of traffic disruptions that will occur in the future, and do not detect the degree of "traffic congestion" or "stagnation" that is currently occurring. Moreover, the information used for prediction in the devices of Patent Documents 2 and 3 is the "degree of congestion," and "stagnation" is not taken into consideration.

[0009] Therefore, the present invention aims to provide a traffic congestion detection device, a traffic congestion detection method, and a traffic congestion detection program that can detect the occurrence of vehicle congestion or stagnation within any range. [Means for solving the problem]

[0010] The traffic disruption detection device according to the present invention includes: a data acquisition unit that acquires probe data including at least information identifying a vehicle and location information of the vehicle during a first time and a second time a predetermined time has elapsed from the first time; a data fitting unit that distributes the probe data from the first time and the probe data from the second time to each mesh of a mesh map created by dividing a map of an arbitrary area; an inflow / outflow determination unit that compares the mesh to which the probe data from the first time is assigned with the mesh to which the probe data from the second time is assigned for each vehicle, and determines whether the vehicle entered, left, or remained in that mesh between the first time and the second time; an inflow / outflow number calculation unit that calculates the number of vehicles entering and leaving each mesh based on the determination result of the inflow / outflow determination unit; and a disruption detection unit that detects the occurrence of a traffic disruption from the number of vehicles entering and leaving each mesh. The fault detection unit determines, for example, that a vehicle stagnation has occurred in the mesh if, between the first time and the second time, the number of vehicles entering the mesh is 1 or more, and the number of vehicles leaving the mesh is 0. Furthermore, the fault detection unit determines, for example, that vehicle congestion is occurring in the mesh if, between the first time and the second time, the number of vehicles leaving the mesh is 1 or more, and the value obtained by subtracting the number of vehicles leaving from the number of vehicles entering the mesh exceeds a set value. The traffic disruption detection device of the present invention may rank each mesh in the mesh map by the number of vehicles that remain within the same mesh from the first time to the second time. Furthermore, the traffic disruption detection device of the present invention may also be provided with an event information matching unit that extracts information on events that occurred in the arbitrary area from the first time to the second time from posted data on incidents, accidents, disasters, and weather collected via the Internet, and applies the event information to each mesh of the mesh map. Furthermore, the traffic disruption detection device of the present invention may further divide each mesh of the mesh map to calculate the number of vehicles entering and exiting in a narrower area.

[0011] The traffic disruption detection method according to the present invention is A method for detecting traffic disruptions using a vehicle congestion detection device, wherein the vehicle congestion detection device,The process includes: a data acquisition step of acquiring probe data that includes at least information identifying a vehicle and location information of the vehicle during a first time and a second time a predetermined time has elapsed from the first time; a data fitting step of distributing the probe data from the first time and the probe data from the second time to each mesh of a mesh map created by dividing a map of an arbitrary area; an inflow / outflow determination step of comparing the mesh to which the probe data from the first time is assigned for each vehicle with the mesh to which the probe data from the second time is assigned, and determining whether the vehicle entered, left, or remained in that mesh between the first time and the second time; an inflow / outflow count calculation step of calculating the number of vehicles entering and leaving each mesh based on the determination result in the inflow / outflow determination step; and a fault detection step of detecting the occurrence of a traffic disruption from the number of vehicles entering and leaving each mesh. conduct.

[0012] The traffic disruption detection program according to the present invention causes a computer to execute: a data acquisition function that acquires probe data including at least information identifying a vehicle and location information of the vehicle at a first time and a second time a predetermined time has elapsed from the first time; a data fitting function that distributes the probe data from the first time and the probe data from the second time to each mesh of a mesh map created by dividing a map of an arbitrary area; an inflow / outflow determination function that compares the mesh to which the probe data from the first time is assigned with the mesh to which the probe data from the second time is assigned for each vehicle, and determines whether the vehicle entered, left, or remained in that mesh between the first time and the second time; an inflow / outflow count calculation function that calculates the number of vehicles entering and leaving each mesh based on the determination result of the inflow / outflow determination function; and a disruption detection function that detects the occurrence of a traffic disruption from the number of vehicles entering and leaving each mesh. [Effects of the Invention]

[0013] According to the present invention, it is possible to detect the occurrence of traffic disruptions such as congestion and delays of vehicles within any range, from the national level to the municipal level.

Brief Description of Drawings

[0014] [Figure 1] It is a block diagram showing a configuration example of a traffic obstacle detection device according to a first embodiment of the present invention. [Figure 2] It is a flowchart showing a method of detecting vehicle congestion by the traffic obstacle detection device 1 shown in FIG. 1. [Figure 3] It is a block diagram showing a configuration example of a traffic obstacle detection device according to a second embodiment of the present invention. [Figure 4] It is a conceptual diagram showing a detection example of vehicle congestion.

Modes for Carrying Out the Invention

[0015] Hereinafter, modes for carrying out the present invention will be described in detail with reference to the accompanying drawings. Note that the present invention is not limited to the embodiments described below.

[0016] (First Embodiment) First, a traffic obstacle detection device according to a first embodiment of the present invention will be described. FIG. 1 is a block diagram showing a configuration example of the traffic obstacle detection device of this embodiment. As shown in FIG. 1, the traffic obstacle detection device 1 of this embodiment includes at least a data acquisition unit 11, a data fitting unit 12, an inflow / outflow determination unit 13, an inflow / outflow number calculation unit 14, and an obstacle detection unit 15, and detects the occurrence of traffic obstacles such as vehicle congestion and stagnation in an arbitrary area.

[0017] [Data Acquisition Unit 11] The data acquisition unit 11 acquires probe data including at least information for identifying a vehicle and the position information of the vehicle at a first time and a second time after a predetermined time has elapsed from the first time. These probe data can be acquired, for example, from an automobile manufacturer or the like. The acquisition interval of the probe data (the interval between the first time and the second time) is not particularly limited and can be appropriately set according to the data volume, the area of the target region, the required accuracy, etc. For example, in the case of data provided by an automobile manufacturer, it is set to about 10 minutes.

[0018] [Data fitting unit 12] The data fitting unit 12 distributes the probe data at the first time and the probe data at the second time acquired by the above-described data acquisition unit 11 to each mesh of a mesh map created by dividing a map of an arbitrary region. The mesh map used here may be an externally input one, or a mesh map may be created by dividing a map of an arbitrary region in the vehicle stay detection device 1. At that time, the size and the number of divisions of each mesh are not particularly limited, and a generally used standard regional mesh can also be applied.

[0019] The distribution of the probe data to each mesh can be performed based on information for identifying the vehicle such as the vehicle ID and the position information (latitude, longitude, etc.) of the vehicle at the first and second times.

[0020] [Inflow / outflow determination unit 13] The inflow / outflow determination unit 13 compares the mesh to which the probe data at the first time is allocated and the mesh to which the probe data at the second time is allocated for each vehicle, and determines whether the vehicle "flowed into", "flowed out of", or "remained in" the mesh from the first time to the second time.

[0021] For example, if a vehicle is assigned to mesh No. 1 during the first time period and to mesh No. 2 during the second time period, it will be identified as "outflowing" in mesh No. 1 and as "inflowing" in mesh No. 2. On the other hand, if a vehicle is assigned to the same mesh during both the first and second time periods, it will be identified as "remaining."

[0022] [Inflow and outflow calculation unit 14] The inflow / outflow calculation unit 14 calculates the number of vehicles entering and leaving each mesh based on the discrimination results from the inflow / outflow discrimination unit 13.

[0023] [Fault detection unit 15] The congestion detection unit 15 detects the occurrence of traffic disruptions based on the number of vehicles entering and leaving each mesh, which is calculated by the inflow / outflow calculation unit 14. For example, the obstacle detection unit 15 determines that a vehicle "congestion" has occurred in a mesh if, between the first and second time periods, the number of vehicles entering a mesh is 1 or more, and the number of vehicles leaving the mesh is 0. Also, for example, if, between the first and second time periods, the number of vehicles leaving a mesh is 1 or more, and the value obtained by subtracting the number of vehicles leaving from the number of vehicles entering the mesh exceeds a set value, the unit determines that a vehicle "congestion" has occurred in that mesh.

[0024] Furthermore, the fault detection unit 15 can also determine that an area (mesh) is "closed to traffic" if, for example, both the number of vehicles entering and the number of vehicles leaving are 0. However, in that case, it is necessary to combine this with weather information, natural disaster information such as earthquakes, tsunamis, and floods, road construction information, and incident information such as traffic accidents and fires.

[0025] The detection results (detection data) from the aforementioned fault detection unit 15 are output externally and used for various purposes, such as being displayed on a monitor (display device) or used for processing by other devices. In the conventional method described above, congestion is detected by focusing on the road, but in the traffic obstruction detection device 1 of this embodiment, vehicle congestion and stagnation are detected on an area basis rather than on the road. This makes it possible to understand the situation not only on major roads but also on surrounding side roads and shortcuts.

[0026] <Operation> Next, the operation of the traffic obstruction detection device 1, that is, the method for detecting the occurrence of traffic obstructions such as vehicle congestion and traffic jams using the traffic obstruction detection device 1 of this embodiment, will be explained. Figure 2 is a flowchart showing the method for detecting traffic obstructions using the vehicle congestion detection device 1 shown in Figure 1. As shown in Figure 2, the traffic obstruction detection method of this embodiment includes a data acquisition step S1, a data fitting step S2, an inflow / outflow discrimination step S3, an inflow / outflow count calculation step S4, and a fault detection step S5.

[0027] In the traffic obstruction detection method of this embodiment, first, the data acquisition unit 11 acquires probe data that includes at least information identifying a vehicle and location information of the vehicle at a first time and a second time a predetermined time has elapsed from the first time (data acquisition step S1). Next, the data fitting unit 12 distributes the probe data at the first time and the probe data at the second time acquired in the data acquisition step S1 to each mesh of the mesh map created by dividing a map of an arbitrary area (data fitting step S2).

[0028] Subsequently, the inflow / outflow discrimination unit 13 compares the mesh to which the probe data for the first time period is assigned with the mesh to which the probe data for the second time period is assigned for each vehicle, and determines whether the vehicle entered, exited, or remained in that mesh between the first and second time periods (inflow / outflow discrimination step S3). Subsequently, the inflow / outflow count calculation unit 14 uses the discrimination results from the inflow / outflow discrimination step S3 to calculate the number of vehicles entering and exiting for each mesh (inflow / outflow count calculation step S4). Then, the fault detection unit 15 detects the occurrence of a traffic disruption based on the number of vehicles entering each mesh and the number of vehicles exiting from that mesh calculated in the inflow / outflow count calculation step S4 (fault detection step S5).

[0029] In the vehicle congestion detection method of this embodiment, each mesh in the mesh map may be further divided to determine the entry and exit of vehicles in a narrower area and detect the occurrence of vehicle congestion or traffic jams, or multiple meshes may be combined to determine the entry and exit of vehicles in a wider area. Furthermore, in the fault detection step S5, only the meshes in which it is determined that traffic obstructions such as congestion or traffic jams are occurring can be divided to determine the entry and exit of vehicles in a narrower range. This can improve the accuracy of the location of the detected traffic obstructions.

[0030] <Program> Each of the aforementioned steps can be carried out by creating a computer program to realize the functions of each part of the vehicle congestion detection device 1 and implementing it on one or more computers.

[0031] In other words, the vehicle congestion detection method of this embodiment can be implemented by running a program on a computer or traffic obstruction detection device 1 that executes: a data acquisition function that acquires probe data including at least information identifying a vehicle and location information of the vehicle during a first time and a second time a predetermined time has elapsed from the first time; a data fitting function that distributes the probe data from the first time and the probe data from the second time acquired by the data acquisition function to each mesh of a mesh map created by dividing a map of an arbitrary area; an inflow / outflow determination function that compares the mesh to which the probe data from the first time is assigned with the mesh to which the probe data from the second time is assigned for each vehicle, and determines whether the vehicle entered, left, or remained in that mesh between the first time and the second time; an inflow / outflow count calculation function that calculates the number of vehicles entering and leaving each mesh based on the determination result of the inflow / outflow determination function; and a traffic obstruction detection function that detects the occurrence of traffic obstruction from the number of vehicles entering and leaving each mesh.

[0032] Furthermore, the aforementioned functions do not need to be included in a single program; they can be executed by creating separate programs for each function and linking them together. In that case, each program can be divided and implemented on two or more computers or devices.

[0033] As detailed above, the traffic disruption detection device, traffic disruption detection method, and traffic disruption detection program of this embodiment calculate the number of vehicles entering and leaving an area (region) that includes not only major roads but also surrounding roads. Therefore, it can detect not only traffic congestion but also vehicle stagnation. By utilizing this information, it becomes possible to detect incidents, accidents, and disasters such as traffic accidents and fires in areas where congestion or stagnation is occurring.

[0034] On the other hand, conventional detection methods primarily determine the presence or absence of "congestion" based on vehicle speed. However, due to the nature of probe data, if a vehicle's speed remains at 0 km / h for a predetermined period, the road where the vehicle is stopped is judged as "impassable" or "not passed through." Therefore, while "congestion" can be detected, "stagnation" cannot. This is because the degree of congestion is also calculated based on vehicle speed, so "stagnation," where the vehicle's speed is 0 km / h, becomes an exception to detection.

[0035] In contrast, the traffic disruption detection device of this embodiment calculates based on two moving points at a first and second time, rather than the speed of a specific vehicle. Therefore, it can handle situations where the vehicle speed is 0 km / h or even when the speed is slow. As a result, the traffic disruption detection device of this embodiment can detect both "congestion" and "traffic congestion."

[0036] In particular, "traffic congestion" tends to be large in scale, and since the vehicle speed is 0 km / h, conventional detection methods that limit congestion to specific roads, such as when a vehicle is stopped at a traffic light or stationary, have too fine a granularity to detect it effectively. Therefore, the traffic disruption detection device of this embodiment divides the area using a standard mesh or similar method to detect traffic disruptions at a larger granularity. This makes it possible to detect vehicle "congestion" that cannot be detected by conventional methods.

[0037] (Second embodiment) Next, a traffic obstruction detection device according to a second embodiment of the present invention will be described. Figure 3 is a block diagram showing an example of the configuration of the traffic obstruction detection device of this embodiment, and Figure 4 is a conceptual diagram showing an example of vehicle congestion detection. In Figure 3, the same reference numerals are used for components that are the same as those in the traffic obstruction detection device 1 shown in Figure 1, and their detailed descriptions are omitted.

[0038] As shown in Figure 3, the traffic obstruction detection device 2 of this embodiment is provided with a ranking unit 16, an event information matching unit 17, and a display color determination unit 18, in addition to the components of the vehicle congestion detection device 1 of the first embodiment described above. These ranking unit 16, event information matching unit 17, and display color determination unit 18 are provided as needed, and in the vehicle congestion detection device 2 of this embodiment, only the event information matching unit 17 may be provided, or only the event information matching unit 17 may be provided.

[0039] [Ranking Section 16] The ranking unit 16 ranks each mesh on the mesh map based on the number of vehicles that remain within the same mesh (have not entered or left) between the first and second time periods.

[0040] [Event Information Matching Section 17] The event information fitting unit 17 extracts event information that occurred in the target area between the first and second time periods from posted data related to incidents, accidents, disasters, weather, etc. (hereinafter collectively referred to as "events") collected via the internet. Based on the location information of the posted data and location information estimated from the content of the posts, the extracted event information is then applied to each mesh of the mesh map. By combining vehicle congestion information and event information in this way, it becomes possible to predict the cause of traffic disruptions and the time it takes for traffic disruptions to be resolved.

[0041] [Display color determination section 18] The display color determination unit 18 determines the display color for each mesh based on whether or not congestion or stagnation has occurred as detected by the fault detection unit 15, and the ranking results from the ranking unit 16. For example, when determining the display color based on the detection results from the fault detection unit 15, one method is to assign a specific color only to areas where stagnation has occurred, such as assigning red to meshes where stagnation has occurred, and leaving other meshes uncolored.

[0042] Furthermore, when determining the display color based on the ranking results in the ranking unit 16, the color assigned to each mesh can be displayed in different colors according to the vehicle congestion detection results, as shown in the example in Figure 4. One method is to use darker colors as the ranking of the number of congested vehicles increases (as the number of congested vehicles increases). In addition, the color assigned to the mesh can be changed based on event information.

[0043] As described in detail above, the traffic disruption detection device of this embodiment is equipped with a ranking unit, an event information matching unit, and / or a display color determination unit, making it easier for users to recognize the state of traffic disruptions such as vehicle congestion, and also making it easier to predict the cause of the traffic disruption and the time it will take to resolve it. The other configurations and effects of this embodiment are the same as those of the first embodiment described above. [Explanation of Symbols]

[0044] 1, 2 Vehicle congestion detection device 11 Data Acquisition Unit 12. Data Fitting Section 13 Inflow / outflow discrimination section 14 Inflow / outflow calculation section 15. Fault detection unit 16. Ranking Section 17. Event Information Fitting Section 18 Display color determination section

Claims

1. A data acquisition unit acquires probe data that includes at least information identifying the vehicle and location information of the vehicle during a first time and a second time that has elapsed a predetermined time from the first time. A data fitting unit that distributes probe data from the first time and probe data from the second time to each mesh of a mesh map created by dividing a map of an arbitrary region, For each vehicle, an inflow / outflow determination unit compares the mesh to which the probe data for the first time is assigned with the mesh to which the probe data for the second time is assigned, and determines whether the vehicle entered, left, or remained in that mesh between the first time and the second time. Based on the determination results from the aforementioned inflow / outflow determination unit, an inflow / outflow count calculation unit calculates the number of vehicles entering and leaving each mesh, A fault detection unit detects the occurrence of traffic disruptions based on the number of vehicles entering and leaving each mesh, A traffic obstruction detection device having the following features.

2. The traffic obstruction detection device according to claim 1, wherein the obstruction detection unit determines that a vehicle congestion has occurred in the mesh when, between the first time and the second time, the number of vehicles entering the mesh is 1 or more and the number of vehicles leaving the mesh is 0.

3. Traffic obstruction detection device according to claim 1, wherein the obstruction detection unit determines that a traffic congestion is occurring in a mesh when, between the first time and the second time, the number of vehicles leaving the mesh is 1 or more, and the value obtained by subtracting the number of vehicles leaving from the number of vehicles entering the mesh exceeds a set value.

4. The traffic obstruction detection device according to claim 1, further comprising a ranking unit that ranks each mesh in the mesh map based on the number of vehicles remaining within the same mesh from the first time to the second time.

5. Traffic obstruction detection device according to claim 1, further comprising an event information matching unit that extracts information on events that occurred in the arbitrary area from the first time to the second time from posted data on incidents, accidents, disasters and weather collected via the Internet, and applies the event information to each mesh of the mesh map.

6. The traffic disruption detection device according to claim 1, wherein each mesh of the aforementioned mesh map is further divided to calculate the number of vehicles entering and leaving a narrower area.

7. A method for detecting an obstruction using a vehicle congestion detection device, The aforementioned vehicle congestion detection device, A data acquisition step in which probe data is acquired during a first time and a second time a predetermined time has elapsed from the first time, which includes at least information identifying the vehicle and location information of the vehicle. A data fitting step involves assigning probe data from the first time and probe data from the second time to each mesh of a mesh map created by dividing a map of an arbitrary region. For each vehicle, an inflow / outflow determination step is performed to compare the mesh to which the probe data for the first time is assigned with the mesh to which the probe data for the second time is assigned, and to determine whether the vehicle entered, left, or remained in that mesh between the first time and the second time. Based on the determination results in the aforementioned inflow / outflow determination process, an inflow / outflow calculation process is performed to calculate the number of vehicles entering and leaving each mesh, A fault detection process that detects the occurrence of traffic disruptions based on the number of vehicles entering and leaving each mesh, A method for detecting traffic disruptions.

8. On the computer, A data acquisition function that acquires probe data including at least information identifying the vehicle and location information of the vehicle during a first time and a second time after a predetermined time has elapsed from the first time, A data fitting function that distributes probe data from the first time and probe data from the second time to each mesh of a mesh map created by dividing a map of an arbitrary region, For each vehicle, an inflow / outflow determination function compares the mesh to which the probe data for the first time is assigned with the mesh to which the probe data for the second time is assigned, and determines whether the vehicle entered, left, or remained in that mesh between the first time and the second time. Based on the results of the aforementioned inflow / outflow discrimination function, an inflow / outflow count calculation function calculates the number of vehicles entering and leaving each mesh, A fault detection function that detects the occurrence of traffic disruptions based on the number of vehicles entering and leaving each mesh, A traffic disruption detection program that executes the following actions.

Images