Traffic monitoring device, traffic monitoring system, traffic monitoring method and program

Abstract

This traffic monitoring device (103) is provided with a front position detection unit (112) which detects the front position of congestion in a road R, and an output unit (114) which, in the case that movement of the detected front position satisfies predefined criteria, outputs congestion information corresponding to said criteria. The front position detection unit (112) acquires the vehicle position in road R obtained on the basis of optical fiber sensing that utilizes optical fibers installed in the road R.

Description

[Technical field]

[0001] The present invention relates to a traffic monitoring device, a traffic monitoring system, a traffic monitoring method, and a program. [Background technology]

[0002] Special In the technology described in Patent Document 1, wrong-way vehicle detection processing is performed when it is determined that no traffic congestion is occurring. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2007-72796 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, when a wrong-way vehicle is traveling on a road, vehicles traveling in the correct direction on road R often slow down for safety. As a result, traffic jams may occur due to wrong-way vehicles. With the technology described in Patent Document 1, it is difficult to grasp traffic jams caused by wrong-way vehicles. As a result, it is difficult to accurately grasp the traffic conditions on the road.

[0005] The present invention has been made in consideration of the above-mentioned circumstances, and has an object to provide a traffic monitoring device, a traffic monitoring system, a traffic monitoring method, and a program that are capable of accurately grasping the traffic conditions on a road. [Means for solving the problem]

[0006] In order to achieve the above object, a traffic monitoring device according to a first aspect of the present invention comprises: a head position detection means for detecting a head position of a traffic jam on a road; and an output means for outputting congestion information according to a predetermined criterion when the detected movement of the head position satisfies the predetermined criterion. 、 the criteria include a first criterion including that a moving direction of the head position is a direction opposite to a traveling direction of the road, When the detected movement of the head position satisfies the first criterion, the output means performs an output according to the first criterion. .

[0007] A traffic monitoring system according to a second aspect of the present invention comprises: The traffic monitoring device; an optical fiber laid on the road and having one end terminated with a termination treatment for suppressing reflection of an optical signal; a sensing device that inputs an optical signal into the optical fiber and observes a change in optical interference intensity, which is the intensity of light produced by interference between backscattered lights occurring in response to the input of the optical signal; The head position detection means acquires a vehicle position on the road based on the amount of change in the optical interference intensity observed by the sensing device, and detects the head position of a traffic jam on the road based on the vehicle position.

[0008] A traffic monitoring method according to a third aspect of the present invention comprises: The computer Detecting a head position of a traffic jam on a road; When the detected movement of the head position satisfies a predetermined criterion, outputting according to the criterion is performed. fruit, the criteria include a first criterion including that a moving direction of the head position is a direction opposite to a traveling direction of the road, In the output, when the detected movement of the head position satisfies the first criterion, the output is performed according to the first criterion. .

[0009] A program according to a fourth aspect of the present invention causes a computer to function as the traffic monitoring device. Effect of the Invention

[0010] According to the present invention, it is possible to grasp the traffic conditions over a wide area in real time from a bird's-eye view. [Brief description of the drawings]

[0011] [Figure 1] 1 is a diagram showing a first example of a configuration and history information of a traffic monitoring system according to an embodiment of the present invention. [Diagram 2]2 is an example of history information showing a wider range of positions and times than the first example of history information shown in FIG. 1. [Diagram 3] FIG. 11 is a diagram illustrating a second example of history information according to an embodiment. [Figure 4] 4 is an example of history information showing a second example of the history information shown in FIG. 3 over a wider range of positions and times than FIG. [Diagram 5] 1 is a diagram showing a functional configuration of a traffic monitoring device according to an embodiment of the present invention. [Figure 6] FIG. 4 is a diagram illustrating an example of congestion pattern information according to an embodiment. [Figure 7] FIG. 2 is a diagram illustrating a functional configuration of an output unit according to an embodiment. [Figure 8] FIG. 11 is a diagram illustrating an example of reference information according to an embodiment. [Figure 9] 1 is a diagram showing an example of a physical configuration of a traffic monitoring device according to an embodiment of the present invention. [Figure 10] 5 is a flowchart showing an example of a traffic monitoring process according to an embodiment of the present invention. [Figure 11] 11 is a flowchart showing an example of a start position detection processing step S101 shown in FIG. [Figure 12] 11 is a flowchart showing an example of the output processing step S102 shown in FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The same elements are designated by the same reference numerals throughout the drawings. Note that the same reference numerals are designated to similar components in all the drawings, and the description thereof will be omitted as appropriate.

[0013] <Configuration of a traffic monitoring system according to an embodiment> As shown in Fig. 1, a traffic monitoring system 100 according to an embodiment of the present invention is a system for monitoring traffic of vehicles 101 traveling on a road R by using optical fiber sensing technology. The road R shown in Fig. 1 is an uphill road, and includes a driving lane TL and an overtaking lane OL. The vehicles 101 may be automobiles, motorcycles, buses, trucks, etc.

[0014] The road R is typically an expressway, but may be any other general road. The number of lanes included in the road R is not limited to two, and may be one or more.

[0015] The traffic monitoring system 100 includes an optical fiber OF, a sensing device 102, and a traffic monitoring device 103.

[0016] The optical fiber OF is an optical fiber cable laid on the road R. The optical fiber OF is, for example, one core of a multi-core optical fiber cable for communication that is generally laid on the shoulders or median strips of expressways, and has one end connected to the sensing device 102 and the other end terminated to suppress reflection of optical signals. Note that a plurality of fiber cables of the multi-core optical fiber cable may be adopted as the optical fiber OF for optical fiber sensing.

[0017] The sensing device 102 inputs an optical signal into the optical fiber OF, and observes the amount of change in optical interference intensity, which is the intensity of light resulting from interference between backscattered lights occurring in response to the input of the optical signal.

[0018] More specifically, for example, an optical signal having a pulse waveform is input to the sensing device 102 from one end of the optical fiber OF. As a result, weak return light called backscattered light is generated from all positions of the optical fiber OF. The sensing device 102 observes the backscattered light.

[0019] When an environmental change occurs around the optical fiber OF, the optical fiber OFThe structural and characteristic parameters of the quartz glass that constitutes the quartz crystal change, and the signal quality of the backscattered light from the location where the change occurs also changes.

[0020] When an optical signal with high coherence is input and vibrations caused by a vehicle 101 traveling on a road R are transmitted to the optical fiber OF, the phase state of the backscattered light changes. This change in the phase state of the backscattered light is observed as a change in light intensity due to interference with other backscattered light received at the same time. That is, the sensing device 102 inputs an optical signal to the optical fiber OF and observes the amount of change in light interference intensity caused by the application of vibration.

[0021] The location where the vibration occurs can be found based on the amount of change in optical interference intensity, and is calculated from the round-trip time from when the optical signal is input until the backscattered light is observed, and the propagation speed of the optical signal. The optical signal is repeatedly input at a constant frequency so that the backscattered light from the other end of the optical fiber OF (i.e., the farthest end as viewed from the sensing device 102) is not mixed with the optical signal to be input next. This makes it possible to accurately observe the transition of environmental changes such as vibrations occurring around the optical fiber OF in real time.

[0022] Thus, optical fiber sensing is a technology that uses optical fiber OF as a sensing medium to detect the location of vibrations, etc. This technology can use general optical fiber OF, which is a transmission medium for communication data, as a linear passive sensor, making it possible to grasp the traffic conditions over a wide area in real time and at a high level without installing new sensors.

[0023] The traffic monitoring device 103 repeatedly acquires observation information including the location of vibration occurrence on road R from the sensing device 102. The location of vibration occurrence corresponds to the position (vehicle position) of the vehicle 101 on road R. Therefore, the observation information includes position information indicating the vehicle position.

[0024] The traffic monitoring device 103 obtains a vehicle position history (i.e., a change in the vehicle position over time) DH based on the position information repeatedly obtained from the sensing device 102. Then, the traffic monitoring device 103 detects a traffic jam that has occurred on the road R based on the vehicle position history DH. The traffic monitoring device 103 further outputs traffic jam information including the occurrence of the traffic jam and its cause to a predetermined device based on the movement of the head position of the detected traffic jam. The causes of the traffic jam in this embodiment are wrong-way vehicles, low-speed vehicles, and others (for example, accidents).

[0025] 1 also shows a first example of the history information 105a_1 according to the present embodiment. The history information 105a_1 shows a history DH of the vehicle positions of each vehicle 101 traveling on a road R when an accident occurs at a position X at a time T10.

[0026] 1, the history information 105a_1 is represented by the relationship between vehicle positions and time on road R. In FIG. 1, a solid line in the figure, with the horizontal axis representing the position on road R and the vertical axis representing time, represents the history DH of the vehicle positions of each vehicle 101 traveling on road R.

[0027] In detail, the history information 105a_1 includes the location of the accident at the time T10 of the accident. X The vehicle 101 traveling downstream of the vehicle 101 travels at a slower speed and stops in sequence. For example, the vehicle 101 traveling at the front at the time of the accident T10 is 101 starts traveling at a low speed from time T10 and stops at position FP0.

[0028] Low-speed driving refers to driving at a predetermined speed (for example, 40 km / h) or less.

[0029] FIG. 2 is an example of history information 105a_2 showing the first example of the history information 105a_1 shown in FIG. 1 over a wider range of positions and times than those in FIG.

[0030] Here, the dotted line L11 shown in FIGS. 1 and 2 is an example of a line where low-speed driving begins when an accident occurs.

[0031] The low-speed driving start line is an approximation line that connects the low-speed driving start points of the vehicles 101 that were traveling on the road R. In addition, the low-speed driving start point is a point that is specified in the diagram including the history DH by the time when the vehicle 101 started to travel at a low speed and the vehicle position at that time.

[0032] A dotted frame FR11 shown in FIG. 2 is a frame indicating an area corresponding to the definition of congestion.

[0033] A traffic jam may be defined as appropriate, but for example, it is defined as a state in which there are a predetermined number of vehicles traveling at a reference speed or less (for example, 40 km / h or less) within a predetermined time ΔT and a predetermined distance ΔD. In the following, an example will be described in which the predetermined number is 10 vehicles.

[0034] According to this definition, the predetermined time ΔT corresponds to the vertical length of the frame FR11. The predetermined distance ΔD corresponds to the horizontal length of the frame FR11. When there are 10 or more records DH (a number corresponding to a predetermined number of vehicles) within the area of ​​the frame FR11 indicating driving at or below the reference speed or stopping, a traffic jam has occurred. Here, the records DH within the area of ​​the frame FR11 are records DH extending from the top side to the bottom side.

[0035] Assume that the time difference between time T12 and time T13 is a predetermined time ΔT. At time T13, the number of history records DH indicating travel or stopping at or below the reference speed from the top to the bottom of the region of the frame FR11 reaches 10 for the first time after time T10. In other words, time T13 is the first time that congestion is detected after time T10.

[0036] At time T14, the accident restoration work is completed, and therefore, after time T14, the cars start traveling in order, starting from the leading car 101.

[0037] The dotted line L12 is an example of a congestion front line in an accident congestion. The congestion front line is an approximate line that connects the front positions of the congestion.

[0038] As shown by dotted line L12, the congestion front line in the accident congestion remains constant at position FP10 between time T10 and T14, and then moves in the direction opposite to the traveling direction after time T14.

[0039] In this way, in a general traffic jam such as an accident traffic jam, the head position of the traffic jam hardly moves for a certain period of time. That is, in a general traffic jam, the head position of the traffic jam is within a predetermined range for a predetermined period of time TTH or more after the traffic jam is detected.

[0040] 3 shows a second example of the history information 105b_1 according to the present embodiment. The history information 105b_1 shows a history DH of the vehicle positions of each vehicle 101 traveling on the road R when a wrong-way vehicle 106 is traveling on the road R. The wrong-way vehicle 106 is a vehicle traveling on the road R in the wrong direction.

[0041] In FIG. 3, the history information 105 shown in FIG. a As in FIG. 1, an example is shown in which the vehicle position history DH of each vehicle 101 traveling on road R is represented by a solid line in a diagram with the horizontal axis representing the position on road R and the vertical axis representing time.

[0042] In detail, the history information 105b_1 indicates the change over time in the vehicle positions of the vehicles 101 that were traveling downstream of the wrong-way vehicle 106, from when the vehicles 101 suddenly decelerated to a low speed and started traveling at an extremely slow speed. 101 The vehicle decelerated rapidly and started to travel at a low speed at time T20, then traveled at an extremely slow speed and reached position FP2 at time T21. 0 Indicates that it is in.

[0043] FIG. 4 is an example of history information 105b_2 showing the first example of the history information 105b_1 shown in FIG. 3 over a wider range of positions and times than those in FIG.

[0044] Here, the dotted line L21 shown in FIGS. 3 and 4 is an example of a low-speed travel start line when a wrong-way vehicle 106 is traveling.

[0045] The dotted line RH represents the travel history of the wrong-way vehicle 106.

[0046] Assume that the time difference between time T22 and time T23 is a predetermined time ΔT. At time T23, the number of history records DH indicating travel at or below the reference speed from the top to the bottom of the region of the frame FR21 reaches 10 for the first time after time T20. In other words, time T23 is the first time that congestion is detected after time T20.

[0047] At time T24, the leading vehicle traveling in the direction of travel on road R 101 After passing the wrong-way vehicle 106, the vehicle accelerates and starts traveling at high speed. High speed traveling is traveling at a speed faster than low speed traveling.

[0048] The dotted line L22 is an example of a congestion front line when a wrong-way vehicle 106 is traveling.

[0049] As shown by dotted line L22, the head position of the traffic jam at time T23 is position FP20. At time T24, vehicle 101, which had been at the head until then, begins to travel at high speed and leaves the traffic jam, so the head position of the traffic jam becomes position FP21.

[0050] At time T25, vehicle 101, which had been in the lead up until then, is now in position FP22. in The vehicle moves at high speed and leaves the traffic jam. As can be seen by referring to FR22, the traffic jam continues, and the head of the traffic jam is at position FP23.

[0051] In this way, in a traffic jam caused by a wrong-way vehicle 106, the head of the traffic jam rarely stays in a fixed position, but moves at a certain speed in the opposite direction to the driving direction of the road R. 106 In a traffic jam caused by the traffic jam, the head position of the traffic jam moves in a direction opposite to the driving direction of the road R within a time period shorter than a predetermined time TTH after the traffic jam is detected, and the moving speed of the head position is faster than a predetermined first threshold value.

[0052] Here, the patterns of the history DH of vehicle positions corresponding to traffic jams caused by accidents and traffic jams caused by wrong-way vehicles 106 have been described with reference to Figs. 1 to 4. In addition to these, traffic jams can also be caused by, for example, low-speed vehicles. A low-speed vehicle is a vehicle that is slower than an appropriately determined speed, and is a road sweeper, a general vehicle 101, or the like.

[0053] In the case of a traffic jam caused by low-speed vehicles, the head position of the traffic jam moves in the driving direction of the road R within a time period shorter than a predetermined time TTH after the traffic jam is detected. In this case, the moving speed of the head position of the traffic jam is slower than a predetermined second threshold value.

[0054] <Functional configuration of the traffic monitoring device 103> The traffic monitoring device 103 according to this embodiment comprises an input unit 110, a head position detection unit 112, and an output unit 114.

[0055] The input unit 110 is a keyboard, a mouse, a touch panel, or the like for a user to input instructions and the like.

[0056] The head position detection unit 112 acquires the vehicle position on the road R from the sensing device 102, and detects the head position of the congestion on the road R based on the vehicle position.

[0057] The head position detector 112 includes a position history generator 112a and a head detector 112b.

[0058] The position history generating unit 112a acquires the vehicle position on the road R, and generates, based on the vehicle position, history information 105 indicating a history DH of the vehicle position of the vehicle 101 on the road R. Here, the history information 105 is a collective term for the above-mentioned history information 105a_1, 105a_2, 105b_1, and 105b_2. In addition, the head detecting unit 112b detects the head position of a traffic jam occurring on the road R, based on the history DH of the vehicle position.

[0059] In detail, the position history generating unit 112a includes a vehicle position acquiring unit 112a_1, a history generating unit 112a_2, and a first learning model storage unit 112a_3.

[0060] The vehicle position acquisition unit 112a_1 acquires, from the sensing device 102, position information on the road R obtained based on optical fiber sensing using an optical fiber OF laid on the road R.

[0061] More specifically, the vehicle position acquisition unit 112a_1 repeatedly acquires, from the sensing device 102, position information on the road R that is obtained based on the amount of change in the optical interference intensity observed by the sensing device 102.

[0062] In this embodiment, an example will be described in which the location information is obtained based on optical fiber sensing, but the location information may be obtained based on information obtained from various sensors installed on the road R, such as a CCTV camera and a traffic volume meter (coil). Furthermore, the location information may be obtained based on probe information of ETC (Electronic Toll Collection System) 2.0.

[0063] The history generating unit 112a_2 generates history information 105 indicating a change over time in the vehicle position on the road R from the past to the present, based on the position information acquired by the vehicle position acquiring unit 112a_1.

[0064] In detail, the position information is included in the observation information acquired based on the optical signal input at a certain frequency, as described above. vehicle Position acquisition part 112a_1 The position information repeatedly acquired by the vehicle position sensor 1 indicates discrete vehicle positions, although at relatively short time intervals.

[0065] The history generating unit 112a_2 receives discrete vehicle positions as an input and generates history information 105 according to the first learning model. The history information 105 continuously indicates the change over time of the vehicle position as indicated by the line DH in FIGS.

[0066] The history generating unit 112a_2 may obtain an approximation curve, an approximation line, or a combination thereof for discrete vehicle positions, and generate history information indicating the obtained approximation curve, approximation line, or a combination thereof.

[0067] The first learning model storage unit 112a_3 is a storage unit for storing in advance the first learning model to be referred to by the history generating unit 112a_2.

[0068] The first learning model is a trained learning model that has undergone machine learning to generate history information 105 using position information included in observation information from the sensing device 102 as an input. Supervised learning may be employed for training the first learning model. In this case, the teacher data may be created based on probe information of the vehicle 101 that has actually traveled, an on-board camera, or the like.

[0069] Furthermore, the head detection unit 112b detects the head position of the congestion on the road R based on the history information 105 generated by the position history generation unit 112a.

[0070] In detail, the head detecting unit 112b includes a congestion pattern storage unit 112b_1, a congestion detecting unit 112b_2, and a head identifying unit 112b_3.

[0071] The congestion pattern storage unit 112b_1 is a storage unit in which congestion pattern information 121 indicating a congestion pattern is stored. The congestion pattern is a pattern of a history DH of a vehicle position on a road R when a congestion occurs. The congestion pattern is determined according to a definition adopted by the traffic monitoring device 103.

[0072] FIG. 6 shows an example of the congestion pattern information 121 according to the present embodiment.

[0073] In this embodiment, as described above, a traffic jam is defined as a state in which there are a predetermined number of vehicles traveling at or below the reference speed within a predetermined time ΔT and a predetermined distance ΔD. The predetermined number is defined as 10 vehicles. Here, vehicles traveling at or below the reference speed include stopped vehicles, and include vehicles that repeatedly stop and start so that their average speed is below the reference speed, for example.

[0074] The congestion pattern information 121 shown in Fig. 6 is an example including a congestion pattern according to this definition. In this congestion pattern, the vertical length of the frame FR is a predetermined time ΔT, and the horizontal length of the frame FR is a predetermined distance ΔD. In addition, within the frame FR, there are 10 or more vehicle position histories DH indicating that the vehicle is traveling at or below the reference speed. The frames FR11, FR21, and FR22 described above are examples of application of the frame FR included in the congestion pattern information 121 shown in Fig. 6.

[0075] The speed (e.g., Km / Hour) of the vehicle 101 is a value obtained by dividing a travel distance by the time required to travel the travel distance, and is reflected in the slope of the vehicle position history DH. In addition, the vehicle position history DH being within the frame FR means that the upper and lower ends of the vehicle position history DH intersect with the upper and lower sides, respectively, of the frame FR, rather than with the left and right sides.

[0076] The traffic congestion detection unit 112b_2 detects traffic congestion on the road R based on the history DH of the vehicle position indicated by the history information 105 generated by the position history generation unit 112a and the traffic congestion pattern indicated by the traffic congestion pattern information 121. The traffic congestion detection unit 112b_2 detects traffic congestion on the road R, for example, by matching (for example, pattern matching) the history DH of the vehicle position with the traffic congestion pattern.

[0077] When the congestion detection unit 112b_2 detects congestion, the head identification unit 112b_3 identifies the head position of the congestion.

[0078] In detail, for example, congestion is detected by comparing (for example, pattern matching) the history DH of the vehicle position up to the present with a congestion pattern, and if the comparison result shows that the history DH and the congestion pattern match to a predetermined extent, congestion is detected.

[0079] In this case, the head position of the congestion is identified as the vehicle position of the vehicle 101 located furthest forward in the traveling direction (to the right in the history DH of FIGS. 1 to 4) within the area matching the congestion pattern in the history DH.

[0080] Again, 5 For more information, please refer to. When the movement of the head position of the congestion detected by the head position detection unit 112 satisfies a predetermined criterion, the output unit 114 outputs congestion information according to the criterion.

[0081] In detail, as shown in FIG. 7, the output unit 114 includes a feature detection unit 114_a1, a reference storage unit 114_a2, a determination unit 114_a3, and a determination result output unit 114_a4.

[0082] The feature detection unit 114_a1 detects the feature of movement of the head position of the traffic jam based on the history DH of the vehicle positions where the traffic jam is detected by the head position detection unit 112. The feature of movement includes the direction and speed of movement.

[0083] The criterion storage unit 114_a2 is a storage unit that stores criterion information 124 for estimating the cause of a traffic jam. The criterion information 124 includes one or more criteria that are previously determined in relation to the movement of the head position of the traffic jam.

[0084] 8 shows an example of the criteria information 124 according to the present embodiment. As shown in the figure, the criteria information 124 includes a first criterion and a second criterion. Note that it is sufficient for the criteria information 124 to include at least one criterion for estimating the cause of traffic congestion.

[0085] The first criterion is a criterion for estimating a traffic jam caused by a wrong-way driving vehicle 106, and the moving direction includes being the opposite direction to the driving direction on road R, and the moving speed includes being faster than a predetermined first threshold value.

[0086] The second criterion is a criterion for estimating congestion due to low-speed vehicles, and includes the movement direction being the driving direction of road R, and the movement speed being slower than a predetermined second threshold value.

[0087] The determining unit 114_a3 determines the cause of the congestion based on the feature of the movement of the head position detected by the feature detecting unit 114_a1 and the reference information 124 stored in the reference storing unit 114_a2.

[0088] In detail, for example, when the movement characteristics satisfy a first criterion, the determination unit 114_a3 determines that the cause of the congestion is the wrong-way vehicle 106. When the movement characteristics satisfy a second criterion, the determination unit 114_a3 determines that the cause of the congestion is a slow-moving vehicle. When the movement characteristics do not satisfy the first criterion and the second criterion, the determination unit 114_a3 determines that the cause of the congestion is unknown.

[0089] The determination result output unit 114_a4 outputs congestion information according to the determination result by the determination unit 114_a3.

[0090] In detail, for example, the determination result output unit 114_a4 outputs the first congestion information when the determination unit 114_a3 determines that the cause of the congestion is the wrong-way vehicle 106. The first congestion information is information indicating that a congestion caused by the wrong-way vehicle 106 is occurring.

[0091] Also, for example, when the determining unit 114_a3 determines that the cause of the traffic jam is a low-speed vehicle, the determination result output unit 114_a4 outputs the second traffic jam information. The second traffic jam information is information indicating that a traffic jam caused by a low-speed vehicle is occurring.

[0092] Furthermore, for example, when the determining unit 114_a3 determines that the cause of the traffic jam is unknown, the determination result output unit 114_a4 outputs the third traffic jam information. The third traffic jam information is information indicating that a traffic jam of unknown cause has occurred.

[0093] When no congestion is detected by the congestion detection unit 112b_2, the determination result output unit 114_a4 may output congestion information indicating that no congestion is occurring.

[0094] The destination of the congestion information from the determination result output unit 114_a4 may be a display unit included in the traffic monitoring device 103, a driving control device mounted on the vehicle 101, or a predetermined information processing device such as a server. When output to the driving control device, the congestion information may be displayed on the display unit of the vehicle 101, or may be used for automatic driving of the vehicle 101 or communication between the vehicles 101 traveling on the road R.

[0095] <Physical configuration of the traffic monitoring device 103> From here, an example of the physical configuration of the traffic monitoring device 103 according to this embodiment will be described with reference to the drawings.

[0096] Physically, the traffic monitoring device 103 has a bus 1010, a processor 1020, a memory 1030, a storage device 1040, a network interface 1050, and a user interface 1060, as shown in FIG.

[0097] The bus 1010 is a data transmission path for transmitting and receiving data among the processor 1020, the memory 1030, the storage device 1040, the network interface 1050, and the user interface 1060. However, the method of connecting the processor 1020 and the like to each other is not limited to a bus connection.

[0098] The processor 1020 is implemented by a central processing unit (CPU) or a graphics processing unit (GPU).

[0099] The memory 1030 is a main storage device realized by a RAM (Random Access Memory) or the like.

[0100] The storage device 1040 is an auxiliary storage device realized by a hard disk drive (HDD), a solid state drive (SSD), a memory card, a read only memory (ROM), or the like.

[0101] The storage device 1040 realizes the functions of the memory units (the first learning model memory unit 112a_3, the congestion pattern memory unit 112b_1, and the reference memory unit 114_a2) of the traffic monitoring device 102 and storing information.

[0102] The storage device 1040 also stores program modules for realizing each functional unit (head position detection unit 112 (position history generation unit 112a (vehicle position acquisition unit 112a_1, history generation unit 112a_2), head detection unit 112b (traffic jam detection unit 112b_2, head identification unit 112b_3)), output unit 114 (characteristic detection unit 114_a1, judgment unit 114_a3, judgment result output unit 114_a4)) of the traffic monitoring device 102. The processor 1020 loads each of these program modules onto the memory 1030 and executes them to realize each functional unit corresponding to the program module.

[0103] The network interface 1050 is an interface for connecting the traffic monitoring device 102 to a network configured by a wired or wireless network or a combination of these. The traffic monitoring device 102 according to this embodiment communicates with the sensing device 102 and the like by being connected to the network via the network interface 1050. The traffic monitoring device 102 according to this embodiment also communicates with a driving control device mounted on the vehicle 101, a predetermined information processing device, and the like by being connected to the network via the network interface 1050.

[0104] The user interface 1070 is an interface through which information is input by the user and an interface that presents information to the user, and includes, for example, a mouse, keyboard, touch sensor, etc. as the input unit 105, and a liquid crystal display, etc. as the display unit.

[0105] In this way, the functions of the traffic monitoring device 102 can be realized by the software program being executed by each physical component in cooperation with each other. program(" Software Program Hm." The program may be realized as a program for executing the program, or as a non-transitory storage medium on which the program is recorded.

[0106] <Traffic monitoring process according to this embodiment> Hereinafter, the traffic monitoring process according to one embodiment of the present invention will be described with reference to the drawings.

[0107] FIG. 10 is a flowchart showing an example of the traffic monitoring process according to the present embodiment.

[0108] The traffic monitoring process is a process for monitoring traffic on road R, and is performed by referring to position information repeatedly acquired, for example, at regular time intervals, from the sensing device 102. For example, when a user's instruction to start the traffic monitoring process is received from the input unit 103, the traffic monitoring process is repeatedly executed until an instruction to end the process is received.

[0109] Please refer to Figure 10. The head position detection unit 112 acquires the vehicle position on the road R from the sensing device 102. Then, the head position detection unit 112 detects the head position of the traffic jam on the road R based on the acquired vehicle position (step S101).

[0110] 11 is a flow chart showing an example of the start position detection process (step S101).As shown in FIG 11, the position history generating unit 112a performs the position history generation process (step S101a).

[0111] In the position history generation process (step S101a), the position history generation unit 112a acquires position information of the vehicle 101 on the road R from the sensing device 102. Then, the position history generation unit 112a generates history information 105 indicating a history DH of the vehicle position of the vehicle 101 on the road R, based on the vehicle position included in the position information.

[0112] In detail, in step S101a, the vehicle position acquiring unit 112a_1 acquires the vehicle position of the vehicle 101 traveling on the road R based on the position information on the road R acquired from the sensing device 102 (step S101a_1).

[0113] The history generating unit 112a_2 generates the history information 105 including a time-dependent change in the vehicle position from the past to the present, that is, a history DH of the vehicle position, based on the vehicle position acquired at step S101a_1 (step S101a_2).

[0114] Here, since the vehicle position can be acquired at a relatively short interval in step S101, the history generating unit 112a_2 In step S101, the vehicle position is detected for a predetermined time period longer than the vehicle position acquisition period. a_1 This should be done when the information is acquired.

[0115] Next, the beginning detection unit 112b performs beginning detection processing (step S101b).

[0116] In the head detection process, the head detection part 112b detects the head position of the congestion on the road R based on the history information 105 generated in step S101a_2.

[0117] At step S101b, the congestion detection unit 112b_2 detects congestion on the road R based on the history information 105 generated at step S101a_2 and the congestion pattern information 121 in the congestion pattern storage unit 112b_1 (step S101b_1).

[0118] In detail, for example, the congestion detection unit 112b_2 compares (for example, pattern matching) the history DH of the vehicle position included in the history information 105 with the congestion pattern indicated by the congestion pattern information 121 to obtain the similarity between them.

[0119] Then, when the similarity is greater than a predetermined threshold, the traffic jam detection unit 112b_2 detects a traffic jam on the road R, and outputs detection information indicating the same to the front end identification unit 112b_. 3 When the similarity is equal to or smaller than a predetermined threshold, the congestion detection unit 112b_2 does not detect congestion on the road R, and notifies the front end identification unit 112b_2 of non-detection information indicating the same to the front end identification unit 112b_2.

[0120] If no congestion is detected, the congestion detection section 112b_2 may end the traffic monitoring process.

[0121] The congestion pattern is not limited to the one exemplified in this embodiment. To Various patterns are assumed depending on the traffic congestion. Therefore, the traffic congestion detection unit 112b_2 may detect traffic congestion based on a learning model using a change in the vehicle position over time as an input. In this case, the learning model may be a trained learning model that has undergone machine learning to generate information (detection information and non-detection information) indicating whether or not traffic congestion has occurred depending on the similarity between the change in the vehicle position over time and the traffic congestion pattern. This learning may be supervised learning, and the learning model may be stored in advance in a storage unit that replaces the traffic congestion pattern storage unit 112b_1.

[0122] Furthermore, the congestion detection unit 112b_2 may detect an abnormal event based on whether or not a feature of a congestion pattern is included in a change in the vehicle position over time.

[0123] When the head identifying portion 112b_3 acquires detection information from the traffic congestion detection portion 112b_2 in response to the detection of traffic congestion at step S101b_1, it identifies the head position of the traffic congestion (step S101b_2).

[0124] In detail, the head identifying unit 112b_3 identifies the head position of the traffic jam at each time based on the history DH of the vehicle position and the traffic jam pattern information 121 stored in the traffic jam pattern storage unit 112b_1. This allows the head identifying unit 112b_3 to identify the change over time in the movement of the head position of the traffic jam, that is, the history of the movement of the head position of the traffic jam.

[0125] More specifically, in identifying the history of the movement of the head position of the traffic jam, for example, the head identification unit 112b_3 detects an area that matches the traffic jam pattern information 121 in the vehicle position history DH. The head identification unit 112b_3 identifies, for example, the current position of the vehicle 101 that is located furthest forward in the driving direction (rightward in the history DH of Figs. 1 to 4) at each time among the detected areas as the head position of the traffic jam at each time. This makes it possible to obtain the history of the movement of the head position of the traffic jam, including the time and the head position on the road R at that time.

[0126] As a result, the head identifying part 112b_3 ends step S101, and returns to the traffic monitoring process shown in FIG.

[0127] Referring again to FIG. The output unit 114 determines whether or not the movement of the head position of the congestion detected in the head position detection process (step S101) satisfies a predetermined criterion, and outputs congestion information according to the result of the determination (step S102).

[0128] FIG. 12 is a flowchart showing an example of the output process (step S102). As shown in FIG. 12, the feature detecting unit 114_a1 detects the feature of movement of the head position of the traffic jam based on the history DH of the vehicle positions where the traffic jam was detected in Step S101b_1 (Step S102a).

[0129] More specifically, the feature detection unit 114_a1 detects the feature of the movement of the start position by determining the movement direction of the start position and its movement speed (e.g., Km / Hour) based on the history of the movement of the start position identified in step S101b_2.

[0130] Judgment section 114 _a3 It is determined whether or not the characteristic of the movement of the head position detected in step S102a satisfies a first criterion (step S102b).

[0131] In detail, the determination unit 114 _a3 The determination unit 114 acquires the first criterion included in the criterion information 124 stored in the criterion storage unit 114_a2. _a3 determines whether or not the movement characteristics of the start position detected in step S102a satisfy the first criterion, based on the acquired first criterion and the movement characteristics of the start position detected in step S102a.

[0132] For example, the first criteria may include a moving direction that is the opposite direction to the running direction and a moving speed that is faster than a first threshold value, as shown in FIG.

[0133] In this case, the determination unit 114 _a3 determines that the first criterion is met when the movement direction included in the movement characteristics of the head position is opposite to the driving direction of road R and the movement speed included in the movement characteristics of the head position is faster than a first threshold value.

[0134] Also, for example, the determination unit 114 _a3 The determination unit 114 determines that the first criterion is not satisfied when the movement direction included in the movement characteristics of the head position is not the opposite direction to the driving direction of the road R but is the driving direction, or when there is no movement. _a3 also determines that the first criterion is not satisfied when the movement speed included in the movement characteristics of the start position is the same as or slower than the first threshold value.

[0135] If it is determined that the first criterion is satisfied (step S102b; Yes), the determination result output unit 114 _a4The first congestion information is output (step S102c).

[0136] When it is determined that the first criterion is not satisfied (step S102b; No), the determination unit 114 _a3 It is determined whether or not the feature of the movement of the head position detected in step S102a satisfies a second criterion (step S102d).

[0137] In detail, the determination unit 114 _a3 The determination unit 114 obtains the second criterion included in the criterion information 124 stored in the criterion storage unit 114_a2. _a3 determines whether or not the movement characteristics satisfy the second criterion, based on the acquired second criterion and the movement characteristics of the start position detected in step S102a.

[0138] For example, the second criteria may include a movement direction, which is the running direction, and a movement speed, which is slower than a second threshold, as shown in FIG.

[0139] In this case, the determination unit 114 _a3 determines that the second criterion is satisfied when the movement direction included in the movement characteristics of the head position is the driving direction of road R and the movement speed included in the movement characteristics of the head position is slower than the second threshold value.

[0140] Also, for example, the determination unit 114 _a3 The determination unit 114 determines that the second criterion is not satisfied when the movement direction included in the movement characteristics of the head position is not the driving direction of the road R but is the opposite direction to the driving direction, or when the vehicle is not moving. _a3 also determines that the second criterion is not satisfied when the movement speed included in the movement characteristics of the start position is equal to or faster than the second threshold value.

[0141] If it is determined that the second criterion is satisfied (step S102d; Yes), the determination result output unit 114 _a4 The second congestion information is output (step S102e).

[0142] When it is determined that the second criterion is not satisfied (step S102d; No), the determination result output unit 114 _a4 The third congestion information is output (step S102f).

[0143] In addition, the determination unit 114 _a3 The result of the determination may be displayed on, for example, a display unit of the traffic monitoring device 103. Then, the user may operate the traffic monitoring device 103 to obtain a current image of the location where it has been determined that a traffic jam has occurred from a surveillance camera installed on the road R and refer to the image.

[0144] This makes it possible to check whether the result of the determination is correct or not, thereby making it possible to provide more accurate congestion information.

[0145] Furthermore, when it is determined that a traffic jam with an unknown cause has occurred, the user may, for example, operate the traffic monitoring device 103 to check the video and include more detailed information, such as an accident, in the third traffic jam information.

[0146] This allows more detailed traffic congestion information to be output, making it possible to provide more accurate and detailed traffic congestion information.

[0147] According to one embodiment of the present invention, the head position of a traffic jam on road R is detected, and if the movement of the detected head position satisfies a predetermined criterion, traffic information according to the criterion is output. This makes it possible to grasp the traffic conditions on road R at the time of the occurrence of traffic jam based on the movement of the head position of the traffic jam. Therefore, it becomes possible to accurately grasp the traffic conditions on the road.

[0148] In this embodiment, the criteria include a first criterion, and the first criterion includes that the movement direction of the head position is opposite to the traveling direction of the road R. Then, when the detected movement of the head position satisfies the first criterion, an output according to the first criterion is performed. Generally, in a traffic jam caused by a wrong-way vehicle 106, the movement direction of the head position is often opposite to the traveling direction of the road R. Therefore, the wrong-way vehicle 106 can be detected by performing an output based on whether or not the movement direction of the head position is opposite to the traveling direction of the road R. In addition, the cause of the traffic jam can be estimated almost in real time. Therefore, it is possible to grasp the traffic situation of the road more accurately.

[0149] In this embodiment, the first criterion further includes that the moving speed of the head position is faster than a first threshold value that is determined in advance. This makes it possible to more accurately detect the wrong-way vehicle 106 and more accurately estimate the cause of the congestion in almost real time. This makes it possible to grasp the traffic situation on the road more accurately.

[0150] In this embodiment, the criteria include a second criterion. The second criterion includes that the movement direction of the head position is the driving direction of the road R. Then, when the detected movement of the head position satisfies the second criterion, an output according to the second criterion is performed. Generally, in traffic jams caused by accidents, the head position often does not move and remains at a fixed position until the accident processing is completed, and traffic jams in which the head position moves in the driving direction are often caused by low-speed vehicles.

[0151] Therefore, it is possible to detect low-speed vehicles by outputting information based on whether the direction of movement of the head position is the driving direction of road R. It is also possible to estimate the cause of congestion almost in real time. This makes it possible to grasp the traffic conditions on the road more accurately.

[0152] In this embodiment, the second criterion further includes that the moving speed of the head position is slower than a second threshold value that is determined in advance. This makes it possible to more accurately detect low-speed vehicles and more accurately estimate the cause of congestion in almost real time. This makes it possible to grasp the traffic situation on the road more accurately.

[0153] In this embodiment, history information indicating the history of vehicle positions on road R is generated, and the head position of a traffic jam on road R is detected based on the history information. The vehicle position on road R can be acquired in real time from a wide area of ​​road R, and the traffic situation on road R can be grasped from a bird's-eye view. Therefore, it becomes possible to grasp the traffic situation of roads in a wide area from a bird's-eye view in real time.

[0154] In this embodiment, the history information 105 is generated based on the vehicle position, and the vehicle position is obtained based on optical fiber sensing using optical fibers laid on road R. Many roads, such as expressways, have optical fibers for communication laid thereon, and the vehicle position can be obtained using the optical fibers already laid.

[0155] In addition, by using optical fiber sensing technology, vehicle positions can be obtained in real time from a wide area of ​​road R, and the traffic conditions on road R can be grasped at a bird's-eye view.

[0156] Therefore, it is possible to grasp the traffic conditions on roads over a wide area in real time at a glance, while suppressing the occurrence of additional costs.

[0157] The present invention is not limited to the above-described embodiment. The embodiment may be modified as follows, for example.

[0158] (Variation 1) In the embodiment, an example has been described in which the vehicle position is acquired from the sensing device 102 and the head position of a traffic jam is detected without distinguishing between the lanes TL and OL for traveling in the same direction on the road R. However, the traffic monitoring device 103 may acquire the vehicle position of the vehicle 101 on each of the lanes TL and OL from the sensing device 102.

[0159] For example, because the pavement of the road R differs for each of the lanes TL and OL, it may be possible to acquire observation information that can identify the lanes TL and OL on which the vehicle R is traveling. In such a case, the head position detection unit 112 may acquire the vehicle positions of the vehicle 101 for each of the lanes TL and OL from the sensing device 102, and detect the head position of the congestion in each lane of the road R.

[0160] In addition, when the detected movement of the head position in each lane satisfies a predetermined criterion, the output unit 114 may output congestion information according to the criterion. The congestion information may include the occurrence of congestion for each lane and its cause.

[0161] Generally, wrong-way vehicles 106 often mistakenly drive on road R in the wrong direction at interchanges where road R intersects in a complex manner or when merging from a parking area onto road R. For this reason, for example, when road R is a left-hand traffic road and the right lane in the driving direction is set as an overtaking lane OL, wrong-way vehicles 106 often drive on the overtaking lane OL in the wrong direction.

[0162] By detecting the detection position of congestion for each lane, it is possible to particularly monitor congestion caused by wrong-way vehicles 106 in lanes where wrong-way vehicles 106 are likely to occur, such as the overtaking lane OL. This makes it possible to more reliably detect congestion caused by wrong-way vehicles 106 and provide congestion information, thereby improving traffic safety on the road R.

[0163] (Variation 2) For example, the first criterion may include a threshold value TTH that is defined with respect to the time from when congestion is detected to when the head position starts to move.

[0164] As described in the embodiment, in a traffic jam caused by a wrong-way vehicle 106, the time from when the traffic jam is detected until the head position starts to move is short, unlike a traffic jam caused by an accident or the like.

[0165] Therefore, by adding the condition that the time from when the traffic jam is detected in the history DH until the head position starts to move is shorter than the threshold value TTH, it is possible to more accurately distinguish between traffic jams caused by the wrong-way vehicle 106 and traffic jams caused by accidents, etc. Therefore, it is possible to more accurately estimate the cause of the traffic jam.

[0166] Although the embodiment and the modified examples of the present invention have been described above, the present invention is not limited to these. For example, the present invention also includes a form in which some or all of the embodiment and the modified examples described so far are appropriately combined, and a form in which the form is appropriately modified.

[0167] One or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes.

[0168] 1. A head position detection means for detecting the head position of a traffic jam on a road; and an output means for outputting congestion information according to a predetermined criterion when the detected movement of the head position satisfies the predetermined criterion. Traffic monitoring equipment. 2. The criteria include a first criterion including that the moving direction of the head position is a direction opposite to a traveling direction of the road, When the detected movement of the head position satisfies the first criterion, the output means performs an output according to the first criterion. 1. A traffic monitoring device as described above in paragraph 1. 3. The first criterion further includes that the moving speed of the head position is faster than a predetermined first threshold value. 2. A traffic monitoring device as described above in paragraph 2. 4. The criteria include a second criterion including that the movement direction of the head position is the driving direction of the road, When the detected movement of the head position satisfies the second criterion, the output means performs an output according to the second criterion. 1. A traffic monitoring device as described above in paragraph 1. 5. The second criterion further includes that the moving speed of the head position is slower than a predetermined second threshold value. 5. A traffic monitoring device as described in claim 4. 6. The head position detection means a position history generating means for generating history information indicating a history of vehicle positions on the road; and a head detection means for detecting a head position of a traffic jam on the road based on the history information. A traffic monitoring device according to any one of 1 to 5 above. 7. The position history generating means a vehicle position acquiring means for acquiring a vehicle position on the road based on optical fiber sensing using optical fibers laid on the road; and a history generating means for generating the history information based on the vehicle position. 7. A traffic monitoring device as described above in claim 6. 8. The head position detection means detects the head position of a traffic jam in each lane of a road when the road includes a plurality of lanes for traveling in the same direction. A traffic monitoring device according to any one of 1 to 7 above. 9. A traffic monitoring device according to any one of 1 to 8 above; an optical fiber laid on the road and having one end terminated with a termination treatment for suppressing reflection of an optical signal; a sensing device that inputs an optical signal into the optical fiber and observes a change in optical interference intensity, which is the intensity of light produced by interference between backscattered lights occurring in response to the input of the optical signal; The head position detection means acquires a vehicle position on the road obtained based on an amount of change in the optical interference intensity observed by the sensing device, and detects a head position of a traffic jam on the road based on the vehicle position. Traffic monitoring system. 10. The computer Detecting a head position of a traffic jam on a road; and when the detected movement of the head position satisfies a predetermined criterion, performing an output according to the criterion. Traffic monitoring methods. 11. A program for causing a computer to function as a traffic monitoring device described in any one of items 1 to 8 above.

[0169] This application claims priority based on Japanese Patent Application No. 2021-034187, filed on March 4, 2021, the disclosure of which is incorporated herein in its entirety. [Explanation of symbols]

[0170] 100 Traffic Monitoring System 101 vehicles OF Optical Fiber 102 Sensing Device 103 Traffic monitoring equipment 105, 105a_1, 105a_2, 105b_1, 105b_2 History information 106 Wrong-way vehicle 110 Input section 112 Head position detector 112a Location history generation unit 112a_1 Vehicle position acquisition unit 112a_2 History generation section 112a_3 First learning model memory unit 112b Head detection unit 112b_1 Traffic jam pattern memory section 112b_2 Traffic jam detection section 112b_3 Heading identification part 114 Output section 114_a1 Feature detection section 114_a2 Reference storage section 114_a3 Judgment part 114_a4 Judgment result output section 121 Traffic jam pattern information 124 Standard Information

Claims

1. a head position detection means for detecting a head position of a traffic jam on a road; an output means for outputting congestion information according to a predetermined criterion when the detected movement of the head position satisfies the predetermined criterion, the criteria include a first criterion including that a moving direction of the head position is a direction opposite to a traveling direction of the road, The output means performs an output according to the first criterion when the detected movement of the head position satisfies the first criterion. Traffic monitoring equipment.

2. The first criterion further includes that a moving speed of the head position is faster than a predetermined first threshold value.

2. A traffic monitoring device according to claim 1.

3. The criteria further include a second criterion including that the movement direction of the head position is a traveling direction of the road, The output means performs an output according to the second criterion when the detected movement of the head position satisfies the second criterion.

2. A traffic monitoring device according to claim 1.

4. The second criterion further includes that the moving speed of the head position is slower than a predetermined second threshold value. A traffic monitoring device according to claim 3.

5. The head position detection means a position history generating means for generating history information indicating a history of vehicle positions on the road; and a head detection means for detecting a head position of a traffic jam on the road based on the history information. A traffic monitoring device according to any one of claims 1 to 4.

6. The head position detection means detects the head position of a traffic jam in each lane of the road when the road includes a plurality of lanes for traveling in the same direction. A traffic monitoring device according to any one of claims 1 to 5.

7. A traffic monitoring device according to any one of claims 1 to 6; an optical fiber laid on the road and having one end terminated with a termination treatment for suppressing reflection of an optical signal; a sensing device that inputs an optical signal to the optical fiber and observes a change in optical interference intensity, which is the intensity of light produced by interference between backscattered lights occurring in response to the input of the optical signal; The head position detection means acquires a vehicle position on the road obtained based on an amount of change in the optical interference intensity observed by the sensing device, and detects a head position of a traffic jam on the road based on the vehicle position. Traffic monitoring system.

8. The computer Detecting a head position of a traffic jam on a road; and when the detected movement of the head position satisfies a predetermined criterion, performing an output according to the criterion. the criteria include a first criterion including that a moving direction of the head position is a direction opposite to a traveling direction of the road, In the output, when the detected movement of the head position satisfies the first criterion, an output according to the first criterion is performed. Traffic monitoring method.

9. A program for causing a computer to function as the traffic monitoring device according to any one of claims 1 to 6.

Images