Travel state discrimination device, travel state discrimination method, and program

Abstract

To provide a travel state discrimination device capable of accurately discriminating a two-wheel vehicle from a four-wheel vehicle.SOLUTION: A travel state discriminating device includes: a pressure signal acquisition section for acquiring a pressure signal capable of detecting pressure by tires of a vehicle passing a vehicle detection position; a vehicle detection signal acquisition section for acquiring a vehicle detection signal capable of detecting presence / absence of the vehicle based on presence / absence of light reception in a light receiving section of a vehicle detector; a time specification section for specifying an arrival time and passing time of the vehicle based on the vehicle detection signal; an estimation section for estimating whether the vehicle is the two-wheel vehicle based on a waveform pattern of the pressure signal; a silhouette acquisition section for acquiring a vehicle body silhouette of the vehicle to be obtained by arranging the vehicle detection signals on a temporal axis when the vehicle is estimated to be the two-wheel vehicle; and a discrimination section for discriminating whether the vehicle is the two-wheel vehicle based on the vehicle body silhouette.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present disclosure relates to a driving condition determination device, a driving condition determination method, and a program. [Background technology]

[0002] On toll roads, different tolls may be collected depending on the vehicle type classification of the vehicle traveling on the road. Vehicle types are classified into five categories, for example, extra-large vehicles, large vehicles, medium-sized vehicles, normal vehicles, and light vehicles (including two-wheeled vehicles). For this reason, toll booths on toll roads are provided with a sensor that detects characteristic information of the vehicle, and a vehicle type discrimination device that discriminates the vehicle type classification based on the detection results of the sensor. The vehicle characteristic information is, for example, the number of axles of the vehicle. A tread plate is known as a sensor for detecting the number of axles of a vehicle. The tread plate has multiple pressure sensors arranged in a line in the width direction of the lane of the toll booth, and detects the position and number of times the vehicle tires have been pressed down on it. The vehicle type discrimination device identifies the number of axles of the vehicle and discriminates the vehicle type classification based on the position and number of times the tread plate detects ...

[0003] In addition, in the future, there is a possibility that a separate toll fee will be charged for motorcycles. For this reason, it is necessary to determine whether a vehicle is a four-wheeled vehicle or a motorcycle. For example, Patent Document 1 describes a method for determining whether a vehicle is a motorcycle or not based on the stepping position, number of steps, and detection time detected by the tread. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-33819 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the width of the tread is not the same as the width of the lane, and there are places at both ends of the lane in the width direction where the tread pressure sensor is not installed. With conventional technology, for example, if one wheel of a four-wheeled vehicle passes through a place where a tread (pressure sensor) is not installed, it may be erroneously determined that a two-wheeled vehicle is traveling.

[0006] An object of the present disclosure is to provide a driving condition discrimination device, a driving condition discrimination method, and a program that are capable of discriminating between two-wheeled vehicles and four-wheeled vehicles with high accuracy. [Means for solving the problem]

[0007] According to one aspect of the present disclosure, a driving condition discrimination device includes a pressure signal acquisition unit that acquires, from a vehicle detection position of a lane, a pressure signal capable of detecting a pressure caused by a tire of a vehicle passing through the vehicle detection position, from each of a plurality of pressure sensors arranged in a line in a lane width direction, a vehicle detection signal acquisition unit that acquires a vehicle detection signal capable of detecting the presence or absence of a vehicle based on the presence or absence of light reception by the light receiving units from a vehicle detector having a plurality of light projecting units arranged in a line in a height direction at the vehicle detection position and projecting an inspection light, and a plurality of light receiving units that receive the inspection light from each of the plurality of light projecting units or reflected light of the inspection light, an estimation unit that estimates whether or not the vehicle is a two-wheeler based on a waveform pattern of the pressure signal acquired between the arrival time and the passing time; a silhouette acquisition unit that, when it is estimated that the vehicle is a two-wheeler, acquires a body silhouette of the vehicle obtained by arranging on a time axis the vehicle detection signals acquired between the arrival time and the passing time; and a discrimination unit that discriminates whether or not the vehicle is a two-wheeler based on the body silhouette.

[0008] According to one aspect of the present disclosure, a driving condition discrimination method includes the steps of: acquiring, from each of a plurality of pressure sensors arranged in a line in a lane width direction at a vehicle detection position of a lane, a pressure signal capable of detecting a pressure caused by a tire of a vehicle passing through the vehicle detection position; acquiring, from a vehicle detector having a plurality of light-projecting units arranged in a line in a height direction at the vehicle detection position and projecting an inspection light, and a plurality of light-receiving units receiving the inspection light of each of the plurality of light-projecting units or reflected light of the inspection light, a vehicle detection signal capable of detecting the presence or absence of the vehicle based on the presence or absence of light reception by the light-receiving units; the step of determining an arrival time when the vehicle arrives at the vehicle detection position and a passing time when the vehicle passes through the vehicle detection position based on the waveform pattern of the pressure signals acquired between the arrival time and the passing time, the step of estimating whether or not the vehicle is a two-wheeled vehicle based on the waveform pattern of the pressure signals acquired between the arrival time and the passing time, the step of acquiring a body silhouette of the vehicle obtained by arranging on a time axis the vehicle detection signals acquired between the arrival time and the passing time when the vehicle is estimated to be a two-wheeled vehicle, and the step of determining whether or not the vehicle is a two-wheeled vehicle based on the body silhouette.

[0009] According to one aspect of the present disclosure, the program includes steps of: acquiring, from each of a plurality of pressure sensors arranged in a line in a lane width direction at a vehicle detection position of a lane, a pressure signal capable of detecting a pressure caused by a tire of a vehicle passing through the vehicle detection position; acquiring, from a vehicle detector having a plurality of light-projecting units arranged in a line in a height direction at the vehicle detection position and projecting an inspection light, and a plurality of light-receiving units receiving the inspection light of each of the plurality of light-projecting units or reflected light of the inspection light, a vehicle detection signal capable of detecting the presence or absence of the vehicle based on the presence or absence of light reception by the light-receiving units; and detecting the presence or absence of the vehicle based on the vehicle detection signal. the vehicle detection position and the passing time; estimating whether or not the vehicle is a two-wheeler based on the waveform pattern of the pressure signal acquired between the arrival time and the passing time; if it is estimated that the vehicle is a two-wheeler, acquiring a body silhouette of the vehicle obtained by arranging on a time axis the vehicle detection signals acquired between the arrival time and the passing time; and determining whether or not the vehicle is a two-wheeler based on the body silhouette. Effect of the Invention

[0010] According to the above aspect, it is possible to distinguish between two-wheeled vehicles and four-wheeled vehicles with high accuracy. [Brief description of the drawings]

[0011] [Figure 1] 1 is a diagram showing an overall configuration of a fee collection system according to a first embodiment. [Diagram 2] FIG. 2 is a diagram showing a configuration of a step plate according to the first embodiment. [Diagram 3] 1 is a diagram showing a configuration of a vehicle detector according to a first embodiment. [Figure 4] 1 is a diagram showing a functional configuration of a traveling condition determination device according to a first embodiment. [Diagram 5] 4 is a first flowchart showing an example of processing of the traveling condition determination device according to the first embodiment. [Figure 6]5 is a second flowchart showing an example of processing of the traveling condition determination device according to the first embodiment. [Figure 7] FIG. 4 is a diagram showing an example of a pressing signal according to the first embodiment. [Figure 8] FIG. 2 is a first diagram showing an example of a vehicle body silhouette according to the first embodiment. [Figure 9] FIG. 4 is a second diagram showing an example of a vehicle body silhouette according to the first embodiment. [Figure 10] 2 is a schematic block diagram showing a hardware configuration of the driving condition determination device; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] <First embodiment> Hereinafter, the embodiments will be described in detail with reference to the drawings.

[0013] (Overall composition) FIG. 1 is a diagram showing the overall configuration of a fee collection system according to the first embodiment. The toll collection system 100 according to this embodiment is installed at a toll gate (entrance toll gate or exit toll gate) of a toll road, and collects tolls from vehicles V traveling on a lane L connecting the toll road and an ordinary road.

[0014] In this embodiment, an example will be described in which the toll collection system 100 is installed at an entrance toll gate. Hereinafter, the direction in which the lane L extends (±X direction) will be referred to as the "lane direction". The general road side (-X side) of the lane direction will also be referred to as the "upstream side", and the toll road side (+X side) will also be referred to as the "downstream side". Furthermore, the width direction of the lane L (±Y direction) will be referred to as the "lane width direction".

[0015] 1 shows an example in which only one lane L is provided at the toll gate, but the present invention is not limited to this. In other embodiments, a plurality of lanes L may be provided at the toll gate.

[0016] As shown in FIG. 1, the toll collection system 100 includes a driving condition determination device 10, a footboard 20, a vehicle detector 21, a license plate reader (NP reader) 22, and a vehicle type determination device .

[0017] The driving condition discrimination device 10 discriminates whether the vehicle V is a two-wheeled vehicle (or three-wheeled vehicle) or a four-wheeled vehicle on a toll road where vehicle type classifications (toll fees) differ between two-wheeled vehicles (or three-wheeled vehicles) and four-wheeled vehicles. The functional configuration of the driving condition discrimination device 10 will be described in detail later.

[0018] The tread plate 20 is laid on the lane L at a vehicle detection position X1, which is a predetermined position in the lane direction (X direction). The tread plate 20 outputs a pressure signal to the driving condition discrimination device 10 and the vehicle type discrimination device 23, which can detect the position and number of times the tread plate 20 is stepped on (pressed) by the tires of a vehicle V passing through the vehicle detection position X1.

[0019] The vehicle detector 21 is installed at a vehicle detection position X1, and outputs a vehicle detection signal capable of detecting the presence or absence of a vehicle V passing through the vehicle detection position X1 to the driving condition discrimination device 10 and the vehicle type discrimination device 23.

[0020] The NP reader 22 photographs the vehicle V when the vehicle detector 21 detects the presence of the vehicle V, and reads the license plate information (NP information) of the vehicle V from the photographed image. The NP information includes the size and color of the license plate, the symbol written on the license plate, the place name, the serial number, etc. The NP reader 22 outputs the read NP information to the vehicle type discrimination device 23.

[0021] The vehicle type discrimination device 23 discriminates the vehicle type classification of the vehicle V based on the pressing signal of the pedal 20, the vehicle detection signal of the vehicle detector 21, the NP information read by the NP reader 22, and the discrimination result of the driving condition discrimination device 10. The toll collection system 100 records the entrance information including the vehicle type classification discriminated by the vehicle type discrimination device 23 on a toll ticket or an ETC card inserted in an on-board device (not shown) of the vehicle V. The ETC card is an IC card that records various information related to toll collection in an electronic toll collection system (Electronic Toll Collection System; ETC (registered trademark) system, also called "automatic toll collection system"). At the exit toll gate, a toll is calculated according to the vehicle type classification included in the entrance information, and the toll is collected from the passenger of the vehicle V. The toll may be collected directly from the passenger of the vehicle V by a toll collector stationed in the lane L, or may be collected automatically using the ETC system.

[0022] In other embodiments, the toll collection system 100 may further include a device for acquiring characteristic information of the vehicle V, such as the vehicle height, length, and width. In this case, the vehicle type discrimination device 23 may discriminate the vehicle type classification of the vehicle V based on the characteristic information of the vehicle V, such as the vehicle height, length, and width. In addition, while FIG. 1 shows an example in which the vehicle type discrimination device 23 is provided as an independent device, this is not limiting. In other embodiments, the vehicle type discrimination device 23 may be configured to be provided within the housing of the vehicle detector 21.

[0023] (Stepping board configuration) FIG. 2 is a diagram showing a configuration of a step plate according to the first embodiment. As shown in Fig. 2, the step board 20 has multiple pressure sensors 200 arranged side by side in the lane width direction (Y direction). Fig. 2 shows an example in which the step board 20 has five pressure sensors 200A to 200E, but this is not limited to this. In other embodiments, the number of pressure sensors may be increased or decreased depending on the installation environment of the step board 20 (such as the width of the lane L), the characteristics of the pressure sensors used, etc.

[0024] Each pressing sensor 200 is configured by arranging at least two sensors in the lane direction. In the example of Fig. 2, each pressing sensor 200 (200A to 200E) has an upstream sensor 201 (201A to 201E) arranged on the upstream side (-X side) in the lane direction, and a downstream sensor 202 (202A to 202E) arranged on the downstream side (+X side) in the lane direction. For example, it is possible to detect whether the vehicle V is moving forward or backward from the order in which the upstream sensor 201 and the downstream sensor 202 are pressed.

[0025] (Vehicle detector configuration) FIG. 3 is a diagram showing the configuration of the vehicle detector according to the first embodiment. 3, the vehicle detector 21 according to this embodiment is a so-called transmission type vehicle detector, and has a light projecting tower 211a and a light receiving tower 211b arranged opposite each other across a lane L. The light projecting tower 211a and the light receiving tower 211b only need to be arranged opposite each other, and the light projecting tower 211a and the light receiving tower 211b may be arranged in the reversed manner.

[0026] The light projecting tower 211a has a plurality of light projecting units S1 arranged at equal intervals in the height direction (Z direction) and projecting inspection light P (e.g., infrared light) toward the light receiving tower 211b. The light receiving tower 211b has a plurality of light receiving units S2 arranged in one-to-one correspondence with each light projecting unit S1 and receiving the inspection light P. Each light receiving unit S2 detects whether the corresponding light projecting unit S1 is receiving the inspection light P (light reception ON) or not (light reception OFF). The vehicle detector 21 outputs a detection signal (vehicle detection signal) indicating the light reception ON / OFF of each light receiving unit S2 at each time.

[0027] When a vehicle V is present at vehicle detection position X1, the inspection light P is blocked by the body of the vehicle V, and the light receiving elements S2 located in the height direction range in which the vehicle body is present turn off their light receiving states. Therefore, when at least one light receiving element S2 has its light receiving state turned on, it is possible to detect that a vehicle V is present (vehicle detection ON), and when all light receiving elements S2 have their light receiving state turned off, it is possible to detect that a vehicle V is not present (vehicle detection OFF). Note that, in order to prevent erroneous detection of dust, etc., the presence of a vehicle V may be detected only when a predetermined number of light receiving elements S2 consecutive in the height direction have their light receiving state turned off.

[0028] In another embodiment, the vehicle detector 21 may be a reflection type vehicle detector. In this case, the vehicle detector 21 has a light emitting / receiving tower on one side of the lane width direction, in which pairs of a light emitting unit and a light receiving unit are arranged in the height direction. When the vehicle V is present at the vehicle detection position X1, the light receiving unit receives the inspection light P reflected by the body of the vehicle V, so that the light receiving unit located in the range in the height direction where the vehicle body is present turns on the light receiving state. Therefore, in the reflection type vehicle detector, when at least one light receiving unit is on the light receiving state, it is possible to detect that the vehicle V is present (vehicle detection ON), and when all the light receiving units S2 are off the light receiving state, it is possible to detect that the vehicle V is not present (vehicle detection OFF). In addition, as with the transmission type vehicle detector, in order to suppress erroneous detection of dust, etc., the presence of the vehicle V may be detected only when a predetermined number of light receiving units S2 successive in the height direction are on the light receiving state.

[0029] (Configuration of the driving condition determination device) FIG. 4 is a diagram showing a functional configuration of the traveling condition determination device according to the first embodiment. As shown in FIG. 4, the traveling condition determination device 10 includes a processor 11 and a storage medium 12.

[0030] The processor 11 operates according to a predetermined program to thereby fulfill the functions of a pressing signal acquiring unit 110, a vehicle detection signal acquiring unit 111, a time identifying unit 112, an estimating unit 113, a silhouette acquiring unit 114, and a discriminating unit 115.

[0031] The pressure signal acquisition unit 110 acquires pressure signals capable of detecting pressure from the tires of the vehicle V from each of the multiple pressure sensors 200 on the tread plate 20.

[0032] The vehicle detection signal acquisition unit 111 acquires a vehicle detection signal capable of detecting the presence of a vehicle V from the vehicle detector 21. The vehicle detection signal indicates the presence or absence (ON / OFF) of light reception by each of the multiple light receiving units S2 of the vehicle detector 21. As described above, in this embodiment, the vehicle detector 21 is a transmissive vehicle detector. Therefore, when at least one light receiving unit S2 is in light reception ON state, it is possible to detect that a vehicle V is present (vehicle detection ON), and when all light receiving units S2 are in light reception OFF state, it is possible to detect that a vehicle V is not present (vehicle detection OFF). Note that in order to prevent erroneous detection of dust, etc., the presence of a vehicle V may be detected only when a predetermined number of light receiving units S2 successive in the height direction are in light reception OFF state.

[0033] The time determination unit 112 determines the arrival time when the vehicle V reaches the vehicle detection position X1 and the passing time when the vehicle V passes the vehicle detection position X1 based on the vehicle detection signal. The arrival time is the time when the vehicle detection is switched from OFF to ON, and the passing time is the time when the vehicle detection is switched from ON to OFF.

[0034] The estimation unit 113 estimates whether the vehicle V is a two-wheeled vehicle based on the waveform pattern of the pressure signal acquired from the arrival time to the passage time.

[0035] When the vehicle V is estimated to be a two-wheeled vehicle, the silhouette acquisition unit 114 acquires a body silhouette of the vehicle V obtained by arranging on a time axis the vehicle detection signals acquired from the arrival time to the passage time.

[0036] The discrimination unit 115 discriminates whether or not the vehicle V is a two-wheeled vehicle based on the vehicle body silhouette.

[0037] The storage medium 12 is a so-called auxiliary storage device, and is a large-capacity storage device such as a hard disk drive (HDD) or a solid state drive (SSD). In the storage medium 12, information acquired or generated by each part of the processor 11 is recorded.

[0038] (Processing flow of the driving condition determination device) FIG. 5 is a first flowchart showing an example of processing of the traveling condition determination device according to the first embodiment. FIG. 6 is a second flowchart showing an example of the process of the traveling condition determination device according to the first embodiment. Here, the flow of processing by the traveling condition determination device 10 will be described with reference to FIGS.

[0039] 5, first, the pressure signal acquisition unit 110 acquires a pressure signal from each of the pressure sensors 200A to 200E (step S10). The acquired pressure signals are stored and accumulated in the storage medium 12.

[0040] Moreover, the vehicle detection signal acquisition unit 111 acquires a vehicle detection signal from the vehicle detector 21 (step S11).

[0041] Note that steps S10 and S11 may be performed simultaneously or in the reverse order.

[0042] Next, the time identifying unit 112 determines whether the vehicle detection signal acquired by the vehicle detection signal acquiring unit 111 has switched from vehicle detection OFF to ON (step S12). If the vehicle detection has not switched to ON (step S12: NO), that is, if the vehicle V is not present at the vehicle detection position X1, the time identifying unit 112 returns to step S10.

[0043] On the other hand, when the vehicle detection signal switches to vehicle detection ON (step S12: YES), that is, when the vehicle V reaches the vehicle detection position X1, the time determination unit 112 determines the arrival time of the vehicle V at the vehicle detection position X1 based on the acquisition time of the vehicle detection signal (step S13).

[0044] The pressing signal acquisition unit 110 also continues to acquire a pressing signal while the vehicle V is traveling through the vehicle detection position X1 (step S14). The acquired pressing signal is stored and accumulated in the storage medium 12. Similarly, the vehicle detection signal acquisition unit 111 also continues to acquire a vehicle detection signal (step S15).

[0045] Next, the time identifying unit 112 determines whether the vehicle detection signal acquired by the vehicle detection signal acquiring unit 111 has switched from vehicle detection ON to OFF (step S16). If the vehicle detection has not switched to vehicle detection OFF (step S16: NO), that is, if the vehicle V is traveling through the vehicle detection position X1, the time identifying unit 112 returns to step S14.

[0046] On the other hand, when the vehicle detection signal switches to vehicle detection OFF (step S16: YES), that is, when the vehicle V passes through the vehicle detection position X1, the time determination unit 112 determines the time when the vehicle V passed through the vehicle detection position X1 based on the acquisition time of the vehicle detection signal (step S17).

[0047] Next, the driving condition discrimination device 10 executes a process of estimating the driving condition of the vehicle V based on the pressing signal and the vehicle detection signal acquired between the arrival time and the passing time (step S18). In this embodiment, the driving condition of the vehicle V indicates any one of "one four-wheeled vehicle traveling", "one three-wheeled vehicle traveling", "one two-wheeled vehicle traveling", and "two two-wheeled vehicles traveling (side by side)". Specifically, the driving condition discrimination device 10 executes each process shown in FIG. 6 to estimate the driving condition of the vehicle V.

[0048] 6, first, the estimation unit 113 judges whether or not it has acquired pressure signals (pressure ON signals) indicating that the tires of the vehicle V have been pressed from two different pressure sensors 200 among the multiple pressure sensors 200 arranged in the lane width direction during the period from the arrival time of the vehicle V at the vehicle detection position X1 to the passing time (step S1801). In other words, it judges whether pressure by the tires has been detected at two points in the lane width direction (left and right).

[0049] FIG. 7 is a diagram illustrating an example of a pressing signal according to the first embodiment. In the example of case A in FIG. 7, during the period from arrival time t1 when vehicle detection is turned ON to passing time t10 when vehicle detection is turned OFF, pressure ON signals are acquired from the pressure sensors 200A, 200D in period D1 (times t2 to t3) and period D2 (times t4 to t5). From the waveform pattern of the pressure signal in case A, the estimation unit 113 assumes that the pressure ON signal in period D1 is from the first axle (front wheel) of the vehicle V, and the pressure ON signal in period D2 is from the second axle (rear wheel) of the vehicle V. In addition, in this case A, pressure ON signals are acquired from two different pressure sensors 200A, 200D in each period D1, D2, so the estimation unit 113 determines that pressure by tires has been detected at two locations in the lane width direction (step S1801; YES).

[0050] In the example of case B in FIG. 7, during the period from arrival time t1 when vehicle detection is turned ON to passing time t10 when vehicle detection is turned OFF, a pressure ON signal is acquired from pressure sensors 200B and 200D during period D1 (times t2 to t3), and a pressure ON signal is acquired only from pressure sensor 200C during period D2 (times t4 to t5). From the waveform pattern of the pressure signal in case B, the estimation unit 113 assumes that the pressure ON signal in period D1 is from the first axle (front wheel) of vehicle V, and the pressure ON signal in period D2 is from the second axle (rear wheel) of vehicle V. In addition, in this case B, since pressure ON signals are acquired from two different pressure sensors 200B and 200D during period D1, the estimation unit 113 determines that pressure by tires has been detected at two locations in the lane width direction (step S1801; YES). Although not shown in the figure, if tire pressure is detected at only one point in the lane width direction during period D1, and tire pressure is detected at two points in the lane width direction during period D2, the case will be judged in the same way as case B.

[0051] In the example of case C in FIG. 7, during the period from arrival time t1 when vehicle detection is turned ON to passing time t10 when vehicle detection is turned OFF, a pressure ON signal is acquired only from the pressure sensor 200C in period D1 (times t2 to t3) and period D2 (times t4 to t5). From the waveform pattern of the pressure signal in case C, the estimation unit 113 assumes that the pressure ON signal in period D1 is from the first axle (front wheel) of the vehicle V, and the pressure ON signal in period D2 is from the second axle (rear wheel) of the vehicle V. In addition, in this case C, since a pressure ON signal is acquired from only one pressure sensor 200C in each of periods D1 and D2, the estimation unit 113 determines that pressure by a tire is detected at only one point in the lane width direction (step S1801; NO).

[0052] First, a description will be given of case C in Fig. 7 (step S1801; NO) in which tire pressure is detected at only one point in the lane width direction on both the first and second axles of the vehicle V. In this case C, the estimation unit 113 tentatively estimates that the vehicle V is a two-wheeled vehicle (step S1812).

[0053] However, in reality, it is possible that the vehicle V is a four-wheeled or three-wheeled vehicle, but one wheel (either the left or right tire) does not pass over the pressure sensor 200. For this reason, in this embodiment, a process is further executed to determine whether the vehicle V is a two-wheeled vehicle or not.

[0054] Specifically, first, the silhouette acquisition unit 114 acquires a vehicle body silhouette of the vehicle V based on the vehicle detection signals acquired during the period from the arrival time t1 to the passage time t10 (step S1813).

[0055] FIG. 8 is a first diagram showing an example of a vehicle body silhouette according to the first embodiment. FIG. 9 is a second diagram showing an example of a vehicle body silhouette according to the first embodiment. FIG. 8 shows an example of a body silhouette of a four-wheeled vehicle, and FIG. 9 shows an example of a body silhouette of a two-wheeled vehicle. As shown in FIG. 8 and FIG. 9, the body silhouette is two-dimensional information obtained by arranging the vehicle detection signals acquired at each time on a time axis. The vertical axis is the spatial axis in the height direction where each light receiving unit S2 is arranged, and the horizontal axis is the time axis indicating the acquisition time of each vehicle detection signal. The white circles in the figures indicate the light reception ON (non-shaded area) of each light receiving unit S2 at each time, and the black circles indicate the light reception OFF (shaded area). The shaded area represented by the black circle is the projection of the side of the vehicle V as seen from one side in the lane width direction (Y direction), i.e., the body silhouette.

[0056] The vehicle body silhouette also varies depending on the speed of the vehicle V when it passes through the vehicle detection position X1. For example, the vehicle body silhouette is elongated in the horizontal axis (time axis) direction when the speed of the vehicle V is relatively low, and conversely, the vehicle body silhouette is compressed in the horizontal axis (time axis) direction when the speed is relatively high. Therefore, the silhouette acquisition unit 114 acquires the vehicle body silhouette by performing a normalization process to remove the fluctuation component according to the speed of the vehicle V. The normalization process may be performed using a known technique. The speed of the vehicle V may be acquired from a speedometer (not shown) provided on the lane L, or may be measured from the time difference between the pressing timing of the upstream sensor 201 and the downstream sensor 202 of the tread 20.

[0057] Next, the discrimination unit 115 determines whether or not the vehicle body silhouette is that of a two-wheeled vehicle (step S1814).

[0058] As shown in the examples of Figs. 8 and 9, the area of ​​the body silhouette (shaded area) of a two-wheeled vehicle is smaller than that of the body silhouette (shaded area) of a four-wheeled vehicle. Therefore, when the area of ​​the body silhouette is less than the first threshold, the discrimination unit 115 determines that this body silhouette is that of a two-wheeled vehicle (step S1814; YES). The first threshold is a value set in advance based on the body silhouettes of two-wheeled vehicles and four-wheeled vehicles acquired in advance as samples. In addition, in case C of Fig. 7, since it is known from the waveform pattern of the pressing signal that both the first and second axles are pressed by one tire, the discrimination unit 115 determines that this vehicle V is one two-wheeled vehicle (step S1815) and ends the processing for this vehicle V. The discrimination result is transmitted to the vehicle type discrimination device 23 and used as information for discriminating the vehicle type classification.

[0059] On the other hand, when the area of ​​the vehicle body silhouette is equal to or larger than the first threshold value, the discrimination unit 115 determines that this vehicle body silhouette is that of a four-wheeled vehicle (step S1814; NO). At this time, the discrimination unit 115 determines that the vehicle V is a single four-wheeled vehicle (step S1809) and ends the processing for this vehicle V. The discrimination result is transmitted to the vehicle type discrimination device 23 and used as information for discriminating the vehicle type category.

[0060] In addition, since a two-wheeled vehicle has a shorter vehicle length than a four-wheeled vehicle, it is assumed that the time from the arrival time t1 to the passing time t10 (vehicle detection ON period) for a two-wheeled vehicle is shorter than that for a four-wheeled vehicle. For this reason, the total area of ​​two-dimensional information in which only the vehicle detection signals from the arrival time t1 to the passing time t10 are arranged may differ greatly between a four-wheeled vehicle and a two-wheeled vehicle. For this reason, the silhouette acquisition unit 114 may create two-dimensional information normalized so that the total area of ​​the two-dimensional information in which the vehicle detection signals of each vehicle V are arranged is approximately the same, and then acquire the vehicle body silhouette. Specifically, the silhouette acquisition unit 114 predetermines the maximum vehicle detection ON period of a four-wheeled vehicle (light vehicle) to be distinguished from a two-wheeled vehicle, and when the actual vehicle detection ON period (from the arrival time t1 to the passing time t10) is shorter than the maximum vehicle detection ON period, creates two-dimensional information supplemented with the vehicle detection signals (all light receiving units S2 are ON for light reception) from the actual passing time t10 of the vehicle V to the time t10' after the maximum vehicle detection ON period. 9, in the case of a two-wheeled vehicle, all light receiving elements S2 are in light receiving ON (non-shaded area) during the period from actual passing time t10 to time t10'. In this way, the difference in area between the body silhouettes of two-wheeled vehicles and four-wheeled vehicles becomes clear, making it possible to more accurately distinguish whether the vehicle is a two-wheeled vehicle or a four-wheeled vehicle.

[0061] Next, cases A and B in FIG. 7 (step S1801; YES) in which tire pressure is detected at two locations in the lane width direction on at least one of the first and second axles of the vehicle V will be described.

[0062] In cases A and B, the estimation unit 113 judges whether the pressure ON signals detected at two points in the lane width direction indicate pressure from the left and right tires of one vehicle or pressure from each of two different two-wheeled vehicles. Here, if the pressure is from the left and right tires of one vehicle, it is assumed that the left and right tires pass over the pressure sensor 200 simultaneously or with a very short time difference. On the other hand, if the pressure is from each of the tires of two different two-wheeled vehicles, it is assumed that the time at which the tires pass over the pressure sensor 200 differs due to differences in the shape characteristics such as tire diameter and wheelbase of the two-wheeled vehicles and the speed. Under such assumptions, the estimation unit 113 judges whether the time difference between the times at which the pressure ON signals are acquired from each of the two pressure sensors 200 is less than a predetermined judgment threshold (step S1802). Note that the judgment threshold is set arbitrarily according to the characteristics of the pressure sensor 200, etc.

[0063] For example, in case A, the estimation unit 113 determines whether or not the time difference between the first time when the pressure signal of the pressure sensor 200A changes from OFF to ON and the second time when the pressure signal of the pressure sensor 200D changes from OFF to ON is less than the determination threshold in both periods D1 and D2. Also, in case B, the estimation unit 113 determines whether or not the time difference between the first time when the pressure signal of the pressure sensor 200A changes from OFF to ON and the second time when the pressure signal of the pressure sensor 200D changes from OFF to ON is less than the determination threshold in period D1.

[0064] If the time difference is equal to or greater than the determination threshold (step S1802; NO), the estimation unit 113 estimates that the vehicle V is not a single vehicle (step S1810). In this case, the discrimination unit 115 discriminates that the vehicle V is two two-wheeled vehicles (running side by side) (step S1811) and ends the processing for the vehicle V. The discrimination result is transmitted to the vehicle type discrimination device 23 and used as information for discriminating the vehicle type category.

[0065] On the other hand, if the time difference is less than the judgment threshold (step S1802; YES), the estimation unit 113 estimates that the vehicle V is a single vehicle (three-wheeled or four-wheeled vehicle) (step S1803). In this case, the estimation unit 113 further estimates whether the vehicle is a three-wheeled or four-wheeled vehicle.

[0066] Specifically, the estimation unit 113 determines whether the number of wheels of the vehicle V is "3" or not from the waveform pattern of the pressure signal acquired from the arrival time t1 to the passage time t10 (step S1804).

[0067] The estimation unit 113 determines the number of times a pressure ON signal is acquired (the number of rising edges at which the pressure signal changes from OFF to ON) from the waveform pattern of the pressure signal acquired between the arrival time t1 and the passage time t10 as the number of wheels of the vehicle V.

[0068] 7, two press ON signals are acquired in each of periods D1 and D2, totaling four press ON signals. Therefore, in case A, the estimation unit 113 determines that the number of wheels of the vehicle V is not "3" (step S1804; NO). In this case, the discrimination unit 115 determines that the vehicle V is a single four-wheeled vehicle (step S1809) and ends the processing for this vehicle V. The discrimination result is transmitted to the vehicle type discrimination device 23 and used as information for discriminating the vehicle type category.

[0069] 7, two pressed ON signals are acquired in period D1, and one pressed ON signal is acquired in period D2. Therefore, in case B, the estimation unit 113 determines that the number of wheels of the vehicle V is "3" (step S1804; YES). In this case, the estimation unit 113 tentatively estimates that the vehicle V is a three-wheeled vehicle (step S1805).

[0070] However, in reality, it is possible that the vehicle V is a four-wheel vehicle, but one wheel (either the left or right tire) of the first or second axle does not pass over the pressure sensor 200. For this reason, in this embodiment, a process is further executed to determine whether the vehicle V is a three-wheel vehicle or not.

[0071] Specifically, first, the silhouette acquisition unit 114 acquires a vehicle body silhouette of the vehicle V based on the vehicle detection signals acquired between the arrival time t1 and the passage time t10 (step S1806). This process is the same as the above-mentioned step S1813.

[0072] Next, the discrimination unit 115 determines whether or not the body silhouette is that of a three-wheeled vehicle (step S1807). In this embodiment, the body silhouette of a three-wheeled vehicle, like that of a two-wheeled vehicle, is smaller in area than that of a four-wheeled vehicle. Therefore, when the area of ​​the body silhouette is less than the first threshold value, the discrimination unit 115 determines that this body silhouette is that of a three-wheeled vehicle (step S1807; YES). In this case, the discrimination unit 115 determines that this vehicle V is a three-wheeled vehicle (step S1808) and ends the processing for this vehicle V. The discrimination result is transmitted to the vehicle type discrimination device 23 and used as information for discriminating the vehicle type category.

[0073] On the other hand, when the area of ​​the vehicle body silhouette is equal to or larger than the first threshold value, the discrimination unit 115 determines that this vehicle body silhouette is that of a four-wheeled vehicle (step S1807; NO). At this time, the discrimination unit 115 determines that the vehicle V is a single four-wheeled vehicle (step S1809) and ends the processing for this vehicle V. The discrimination result is transmitted to the vehicle type discrimination device 23 and used as information for discriminating the vehicle type category.

[0074] The traveling condition determination device 10 executes a series of processes shown in Figs. 5 to 6 every time the vehicle V arrives at a toll gate.

[0075] (Action, effect) As described above, the driving condition discrimination device 10 of this embodiment includes a pressure signal acquisition unit 110 that acquires, from each of the multiple pressure sensors 200, a pressure signal capable of detecting pressure from the tires of the vehicle V; a vehicle detection signal acquisition unit 111 that acquires, from the vehicle detector 21, a vehicle detection signal capable of detecting the presence or absence of vehicle V based on the presence or absence of light received by the light receiving unit S2; a time identification unit 112 that identifies the arrival time at which the vehicle V reaches the vehicle detection position X1 and the passing time at which the vehicle V passes the vehicle detection position X1 based on the vehicle detection signal; an estimation unit 113 that estimates whether the vehicle V is a two-wheeled vehicle based on the waveform pattern of the pressure signal acquired between the arrival time and the passing time; a silhouette acquisition unit 114 that acquires, when it is estimated that the vehicle V is a two-wheeled vehicle, a body silhouette of the vehicle V obtained by arranging on a time axis the vehicle detection signals acquired between the arrival time and the passing time; and a discrimination unit 115 that discriminates whether the vehicle V is a two-wheeled vehicle based on the body silhouette.

[0076] In the conventional technology, when one wheel of a four-wheeled vehicle passes through a location where no pressure sensor is installed (does not pass over the pressure sensor), it may be erroneously determined that the vehicle is a two-wheeled vehicle from the waveform pattern of the pressure signal. In contrast, the traveling condition determination device 10 according to the present embodiment can accurately determine whether the vehicle V is a two-wheeled vehicle or a four-wheeled vehicle from the body silhouette of the vehicle V, even if the vehicle V is estimated to be a two-wheeled vehicle from the waveform pattern of the pressure signal because one wheel of the four-wheeled vehicle does not pass over the pressure sensor.

[0077] Furthermore, the discrimination unit 115 discriminates that the vehicle V is a two-wheeled vehicle when the area of ​​the vehicle body silhouette is less than the first threshold value.

[0078] A two-wheeled vehicle has a smaller body size than a four-wheeled vehicle. Therefore, the body silhouette (shaded area) of a two-wheeled vehicle has a smaller area than the body silhouette (shaded area) of a four-wheeled vehicle. By utilizing such a difference in shape, the traveling condition determination device 10 can easily and accurately distinguish between a two-wheeled vehicle and a four-wheeled vehicle without performing complicated processing.

[0079] In addition, the estimation unit 113 further estimates whether or not the vehicle V is a tricycle based on the pressure signals acquired between the arrival time and the passing time, and the silhouette acquisition unit 114 acquires the body silhouette of the vehicle V if it is estimated that the vehicle V is a tricycle, and the discrimination unit 115 discriminates whether or not the vehicle V is a tricycle based on the body silhouette.

[0080] By doing this, the driving condition determination device 10 can accurately determine whether the vehicle V is a three-wheeled vehicle or a four-wheeled vehicle from the body silhouette of the vehicle V, even if it is estimated that the vehicle V is a three-wheeled vehicle from the waveform pattern of the pressure signal because either the front or rear wheel of the four-wheeled vehicle does not pass over the pressure sensor.

[0081] <Second embodiment> In the first embodiment, an example has been described in which the discrimination unit 115 discriminates between a two-wheeled vehicle (or a three-wheeled vehicle) and a four-wheeled vehicle based on the area of ​​the vehicle body silhouette, but the present invention is not limited to this. In the second embodiment, the discrimination unit 115 may discriminate between a two-wheeled vehicle (or a three-wheeled vehicle) and a four-wheeled vehicle by taking into account the vehicle body shape obtained from the vehicle body silhouette.

[0082] For example, when the side of the vehicle V is viewed from one side in the lane width direction (Y direction), in the case of a four-wheeled vehicle, the vehicle body (front bumper, bonnet, etc.) exists in front of the tire (front wheel) of the first axle. On the other hand, in the case of a two-wheeled vehicle or a three-wheeled vehicle, the vehicle body does not exist in front of the tire (front wheel) of the first axle. For this reason, in step S1814, the discrimination unit 115 of the traveling state discrimination device 10 according to the second embodiment first detects the front wheel of the vehicle V from the vehicle body silhouette. Since the tire of the vehicle V is in contact with the ground and the vehicle body is not in contact with the ground, the tire of the vehicle V can be detected by referring to the presence or absence of light reception by the light receiving unit S2 at the lowest level in the height direction (Z direction) of the vehicle body silhouette. In other words, the discrimination unit 115 detects the range from the time axis at which the light receiving unit S2 at the lowest level switches from light reception ON (non-shaded state) to light reception OFF (shaded state) and then switches from light reception OFF to light reception ON as the front wheel of the vehicle V.

[0083] Furthermore, when the area of ​​the vehicle body silhouette (shaded area) in front of the detected front wheel (front on the time axis) is less than the second threshold, the discrimination unit 115 discriminates that the vehicle V is a single two-wheeled vehicle (step S1814; YES). The second threshold is a value set in advance based on the vehicle body silhouettes of two-wheeled vehicles and four-wheeled vehicles acquired in advance as samples.

[0084] For example, assume that the front wheels of the vehicle V are detected in the range of times t2 to t3 on the time axis from the vehicle body silhouette in Fig. 8. At this time, the vehicle body silhouette on the time axis ahead of time t2 includes the bonnet of the vehicle V and is therefore equal to or greater than the second threshold (step S1814; NO). Therefore, the discrimination unit 115 discriminates that the vehicle V is a single four-wheeled vehicle from the vehicle body silhouette shown in Fig. 8 (step S1809).

[0085] On the other hand, suppose that the front wheels of the vehicle V are detected from the vehicle body silhouette in Fig. 9 between times t2 and t3 on the time axis. At this time, the vehicle body silhouette on the time axis ahead of time t2 is less than the second threshold value because there is no vehicle body (step S1814; YES). Therefore, the discrimination unit 115 discriminates that the vehicle V is a two-wheeled vehicle from the vehicle body silhouette shown in Fig. 9 (step S1815).

[0086] Also, in step S1807, the same process as in step S1814 is performed.

[0087] In this way, the driving condition determination device 10 can take into consideration the shape characteristics of the bodies of two-wheeled and four-wheeled vehicles and accurately determine whether the vehicle is a two-wheeled or four-wheeled vehicle from the body silhouette.

[0088] <Third embodiment> Also, the distance between the front and rear wheels of a two-wheeled vehicle (wheelbase) is shorter than that of a four-wheeled vehicle. For this reason, in step S1814, the discrimination unit 115 of the traveling condition discrimination device 10 according to the third embodiment first detects the tires of the first and second axles (front and rear wheels) of the vehicle V from the vehicle body silhouette. The method of detecting the front and rear wheels is the same as that of the second embodiment. That is, the discrimination unit 115 detects the range from when the light receiving unit S2 in the lowest stage, which is the frontmost side on the time axis, switches from light receiving ON to light receiving OFF, and then switches from light receiving OFF to light receiving ON, as the front wheel of the vehicle V. Also, the discrimination unit 115 detects the range from when the light receiving unit S2 in the lowest stage, which is the rear side of the detected front wheel on the time axis, switches from light receiving ON to light receiving OFF, and then switches from light receiving OFF to light receiving ON, as the rear wheel of the vehicle V.

[0089] Furthermore, when the length on the time axis between the detected front and rear wheels (i.e., the time from when the front wheel is detected to when the rear wheel is detected) is less than the third threshold, the discrimination unit 115 discriminates that the vehicle V is a two-wheeled vehicle (step S1814; YES). The third threshold is a value set in advance based on statistical information such as the wheelbase of two-wheeled and four-wheeled vehicles obtained in advance as samples and the average driving speed at the toll gate.

[0090] For example, from the body silhouette in Fig. 8, it is assumed that the front wheels of the vehicle V are detected in the range of times t2 to t3 on the time axis, and the rear wheels are detected in the range of times t4 to t5. At this time, the time from time t3 to t4 (length on the time axis) is equal to or greater than the third threshold (step S1814; NO). Therefore, the discrimination unit 115 discriminates that the vehicle V is a four-wheeled vehicle from the body silhouette shown in Fig. 8 (step S1809).

[0091] On the other hand, from the body silhouette in Fig. 9, it is assumed that the front wheel of the vehicle V is detected from time t2 to t3 on the time axis, and the rear wheel is detected in the range from time t4 to t5. At this time, the time from time t3 to t4 (length on the time axis) is less than the third threshold (step S1814; YES). Therefore, the discrimination unit 115 discriminates that the vehicle V is a two-wheeled vehicle from the body silhouette shown in Fig. 9 (step S1815).

[0092] Also, in step S1807, the same process as in step S1814 is performed.

[0093] In this manner, the driving condition determination device 10 can take into consideration the difference in wheelbase between two-wheeled vehicles and four-wheeled vehicles and accurately determine whether the vehicle is a two-wheeled vehicle or a four-wheeled vehicle from the vehicle body silhouette.

[0094] <Fourth embodiment> Furthermore, the discrimination unit 115 may acquire beforehand the body silhouettes of two-wheeled, three-wheeled, and four-wheeled vehicles as learning data and generate an inference model learned by deep learning. The inference model takes the body silhouette as input, and outputs whether the vehicle shown by the body silhouette is a two-wheeled, three-wheeled, or four-wheeled vehicle.

[0095] In step S1814, the discrimination unit 115 of the driving condition discrimination device 10 according to the fourth embodiment inputs the vehicle body silhouette acquired by the silhouette acquisition unit 114 to an inference model. If the output of the inference model is a two-wheeled vehicle (step S1814; YES), the discrimination unit 115 discriminates that the vehicle V is a single two-wheeled vehicle (step S1815). On the other hand, if the output of the inference model is a four-wheeled vehicle (step S1814; NO), the discrimination unit 115 discriminates that the vehicle V is a single four-wheeled vehicle (step S1809).

[0096] Also, in step S1807, the same process as in step S1814 is performed.

[0097] In this way, the driving condition determination device 10 can easily and accurately determine whether the vehicle is a two-wheeled vehicle or a four-wheeled vehicle from the vehicle body silhouette, using the inference model learned from the learning data.

[0098] <Other embodiments> Although one embodiment has been described in detail above with reference to the drawings, the specific configuration is not limited to the above, and various design changes are possible. That is, in other embodiments, the order of the above-mentioned processes may be changed as appropriate. Also, some of the processes may be executed in parallel.

[0099] For example, in the above embodiment, an example has been described in which the traveling condition determination device 10 obtains a pressure signal from the pressure sensor 200 of the tread 20, but the present invention is not limited to this. In other embodiments, the traveling condition determination device 10 may obtain a pressure signal from a pressure sensor of a weight measuring device for measuring the axle load of the vehicle V.

[0100] <Hardware configuration> FIG. 10 is a schematic block diagram showing a hardware configuration of the running condition determination device.

[0101] The computer 900 comprises a processor 901 , a main memory device 902 , an auxiliary memory device 903 , and an interface 904 .

[0102] The above-described running condition determination device 10 is implemented in a computer 900. The operations of the above-described processing units are stored in the auxiliary storage device 903 in the form of a program. The processor 901 reads the program from the auxiliary storage device 903, loads it in the main storage device 902, and executes the above-described processing in accordance with the program. The processor 901 also secures storage areas in the main storage device 902 corresponding to the above-described storage units in accordance with the program.

[0103] The program may be for realizing a part of the functions to be performed by the computer 900. For example, the program may be for realizing the functions by combining with other programs already stored in the auxiliary storage device 903 or by combining with other programs implemented in other devices. In another embodiment, the computer 900 may include a custom LSI (Large Scale Integrated Circuit) such as a PLD (Programmable Logic Device) in addition to or instead of the above configuration. Examples of PLDs include PAL (Programmable Array Logic), GAL (Generic Array Logic), CPLD (Complex Programmable Logic Device), and FPGA (Field Programmable Gate Array). In this case, some or all of the functions to be realized by the processor 901 may be realized by the integrated circuit.

[0104] Examples of the auxiliary storage device 903 include a hard disk drive (HDD), a solid state drive (SSD), a magnetic disk, a magneto-optical disk, a compact disc read only memory (CD-ROM), a digital versatile disc read only memory (DVD-ROM), and a semiconductor memory. The auxiliary storage device 903 may be an internal medium directly connected to the bus of the computer 900, or an external storage device 910 connected to the computer 900 via an interface 904 or a communication line. In addition, when the program is distributed to the computer 900 via a communication line, the computer 900 that receives the program may load the program into the main storage device 902 and execute the above-mentioned process. In at least one embodiment, the auxiliary storage device 903 is a non-transitory tangible storage medium.

[0105] The program may be for realizing part of the above-mentioned functions. Furthermore, the program may be a so-called differential file (differential program) that realizes the above-mentioned functions in combination with another program already stored in the auxiliary storage device 903.

[0106] <Additional Notes> The driving condition determination device, the driving condition determination method, and the program described in the above-described embodiment can be understood, for example, as follows.

[0107] (1) According to the first aspect, the driving condition discrimination device 10 includes a pressure signal acquisition unit 110 that acquires, from each of a plurality of pressure sensors 200 arranged in a line in the lane width direction at a vehicle detection position X1 of a lane L, a pressure signal capable of detecting a pressure applied by a tire of a vehicle V passing through the vehicle detection position X1, and a vehicle detection signal acquisition unit that acquires, from a vehicle detector 21 having a plurality of light-projecting units S1 arranged in a line in the height direction at the vehicle detection position X1 and projecting an inspection light P, and a plurality of light-receiving units S2 that receive the inspection light P of each of the plurality of light-projecting units S1 or the reflected light of the inspection light P, the vehicle detection signal acquisition unit 110 acquires a vehicle detection signal capable of detecting the presence or absence of a vehicle V based on the presence or absence of light reception by the light-receiving units S2 from a vehicle detector 21 having the plurality of light-projecting units S1 arranged in a line in the height direction at the vehicle detection position X1 and projecting an inspection light P, and The vehicle detection system includes an acquisition unit 111, a time determination unit 112 that determines the arrival time when the vehicle V arrives at the vehicle detection position X1 and the passing time when the vehicle V passes the vehicle detection position X1 based on the vehicle detection signal, an estimation unit 113 that estimates whether the vehicle V is a two-wheeled vehicle based on the waveform pattern of the pressure signal acquired between the arrival time and the passing time, a silhouette acquisition unit 114 that acquires a body silhouette of the vehicle V obtained by arranging the vehicle detection signals acquired between the arrival time and the passing time on a time axis when the vehicle V is estimated to be a two-wheeled vehicle, and a discrimination unit 115 that discriminates whether the vehicle V is a two-wheeled vehicle based on the body silhouette.

[0108] In the conventional technology, when one wheel of a four-wheeled vehicle passes through a location where no pressure sensor is installed (does not pass over the pressure sensor), it may be erroneously determined that the vehicle is a two-wheeled vehicle from the waveform pattern of the pressure signal. In contrast, the traveling condition determination device 10 according to the present embodiment can accurately determine whether the vehicle V is a two-wheeled vehicle or a four-wheeled vehicle from the body silhouette of the vehicle V, even if the vehicle V is estimated to be a two-wheeled vehicle from the waveform pattern of the pressure signal because one wheel of the four-wheeled vehicle does not pass over the pressure sensor.

[0109] (2) According to the second aspect, in the driving condition determination device 10 according to the first aspect, the determination unit 115 determines that the vehicle V is a two-wheeled vehicle when the area of ​​the vehicle body silhouette is less than the first threshold value.

[0110] A two-wheeled vehicle has a smaller body size than a four-wheeled vehicle. Therefore, the body silhouette (shaded area) of a two-wheeled vehicle has a smaller area than the body silhouette (shaded area) of a four-wheeled vehicle. By utilizing such a difference in shape, the traveling condition determination device 10 can easily and accurately distinguish between a two-wheeled vehicle and a four-wheeled vehicle without performing complicated processing.

[0111] (3) According to the third aspect, in the driving condition discrimination device 10 of the first aspect, the discrimination unit 115 detects the front wheel of the vehicle V based on the presence or absence of light reception by the light receiving unit S2 at the lowest level in the height direction of the vehicle body silhouette, and discriminates that the vehicle V is a two-wheeled vehicle when the area of ​​the vehicle body silhouette forward of the detected front wheel on the time axis is less than a second threshold value.

[0112] In this way, the driving condition determination device 10 can take into consideration the shape characteristics of the bodies of two-wheeled and four-wheeled vehicles and accurately determine whether the vehicle is a two-wheeled or four-wheeled vehicle from the body silhouette.

[0113] (4) According to the fourth aspect, in the driving condition discrimination device 10 of the first aspect, the discrimination unit 115 detects the front and rear wheels of the vehicle V based on the presence or absence of light reception by the light receiving unit S2 at the lowest level in the height direction of the vehicle body silhouette, and discriminates that the vehicle V is a two-wheeled vehicle if the length on the time axis of the detected front and rear wheels is less than a third threshold value.

[0114] In this manner, the driving condition determination device 10 can take into consideration the difference in wheelbase between two-wheeled vehicles and four-wheeled vehicles and accurately determine whether the vehicle is a two-wheeled vehicle or a four-wheeled vehicle from the vehicle body silhouette.

[0115] (5) According to the fifth aspect, in the driving condition discrimination device 10 of the first aspect, the discrimination unit 115 discriminates that the vehicle V is a two-wheeled vehicle using an inference model that has learned the body silhouettes of a plurality of vehicles V, the inference model taking the body silhouette as input and outputting a judgment result indicating whether the input body silhouette is a two-wheeled vehicle or not.

[0116] In this way, the driving condition determination device 10 can easily and accurately determine whether the vehicle is a two-wheeled vehicle or a four-wheeled vehicle from the vehicle body silhouette, using the inference model learned from the learning data.

[0117] (6) According to the sixth aspect, in the driving condition discrimination device 10 relating to any one of the first to sixth aspects, the estimation unit 113 further estimates whether or not the vehicle V is a tricycle based on the pressure signals acquired between the arrival time and the passing time, the silhouette acquisition unit 114 acquires a body silhouette of the vehicle V when it is estimated that the vehicle V is a tricycle, and the discrimination unit 115 discriminates whether or not the vehicle V is a tricycle based on the body silhouette.

[0118] By doing this, the driving condition determination device 10 can accurately determine whether the vehicle V is a three-wheeled vehicle or a four-wheeled vehicle from the body silhouette of the vehicle V, even if it is estimated that the vehicle V is a three-wheeled vehicle from the waveform pattern of the pressure signal because either the front or rear wheel of the four-wheeled vehicle does not pass over the pressure sensor.

[0119] (7) According to the seventh aspect, the driving condition discrimination method includes a step of acquiring, from each of a plurality of pressure sensors 200 arranged in a line in a lane width direction at a vehicle detection position X1 of a lane L, a pressure signal capable of detecting a pressure caused by a tire of a vehicle V passing through the vehicle detection position X1; and a step of acquiring, from a vehicle detector 21 arranged in a line in a height direction at the vehicle detection position X1, a vehicle detection signal capable of detecting the presence or absence of a vehicle V based on the presence or absence of light reception by the light receiving unit S2, from a vehicle detector 21 having a plurality of light projecting units S1 arranged in a line in a height direction at the vehicle detection position X1 and projecting an inspection light P and a plurality of light receiving units S2 receiving the inspection light P of each of the plurality of light projecting units S1 or the reflected light of the inspection light P. the step of estimating whether or not the vehicle V is a two-wheeler based on the waveform pattern of the pressure signal acquired between the arrival time and the passing time; if the vehicle V is estimated to be a two-wheeler, the step of acquiring a body silhouette of the vehicle V obtained by arranging on a time axis the vehicle detection signals acquired between the arrival time and the passing time; and the step of determining whether or not the vehicle V is a two-wheeler based on the body silhouette.

[0120] (8) According to the eighth aspect, the program includes a step of acquiring, from each of a plurality of pressure sensors 200 arranged in a line in a lane width direction at a vehicle detection position X1 of a lane L, a pressure signal capable of detecting a pressure caused by a tire of a vehicle V passing through the vehicle detection position X1; acquiring, from a vehicle detector 21 arranged in a line in a height direction at the vehicle detection position X1, a vehicle detection signal capable of detecting the presence or absence of a vehicle V based on the presence or absence of light reception by the light receiving unit S2, from the vehicle detector 21 having a plurality of light projecting units S1 arranged in a line in a height direction at the vehicle detection position X1 and projecting an inspection light P and a plurality of light receiving units S2 receiving the inspection light P of each of the plurality of light projecting units S1 or the reflected light of the inspection light P; The driving condition discrimination device 10 is caused to execute the following steps: a time determination unit 112 determines the arrival time at which the vehicle V reaches the vehicle detection position X1 and the passing time at which the vehicle V passes the vehicle detection position X1 based on the detection signal; a step of estimating whether or not the vehicle V is a two-wheeled vehicle based on the waveform pattern of the pressure signal acquired between the arrival time and the passing time; a step of acquiring a body silhouette of the vehicle V obtained by arranging on a time axis the vehicle detection signals acquired between the arrival time and the passing time when it is estimated that the vehicle V is a two-wheeled vehicle; and a step of determining whether or not the vehicle V is a two-wheeled vehicle based on the body silhouette. [Explanation of symbols]

[0121] 100 Toll collection system 10. Driving condition determination device 11 Processors 110 Pressing signal acquisition unit 111 Vehicle detection signal acquisition unit 112 Time identification part 113 Estimation Department 114 Silhouette Acquisition Department 115 Discrimination part 12 Storage medium 20 Treadboard 200,200A~200E Pressure sensor 201, 201A~201E Upstream sensor 202, 202A~202E Downstream sensor 21 Vehicle detector 211a Floodlight tower S1 Light emitter 211b Light receiving tower S2 light receiving section 22 License plate reader (NP reader) 23 Vehicle type identification device 900 Computers 901 Processor 902 Main storage 903 Auxiliary storage device 904 Interface 910 External storage device L Lane P Inspection light V Vehicle X1 Vehicle detection position

Claims

1. a pressure signal acquisition unit that acquires, from each of a plurality of pressure sensors arranged in a line in a lane width direction at vehicle detection positions of the lane, a pressure signal capable of detecting pressure applied by tires of a vehicle passing through the vehicle detection positions; a vehicle detection signal acquisition unit that acquires a vehicle detection signal capable of detecting the presence or absence of a vehicle based on the presence or absence of light received by the light receiving units from a vehicle detector having a plurality of light projecting units that are arranged in a vertical direction at the vehicle detection position and project inspection light, and a plurality of light receiving units that receive the inspection light from each of the plurality of light projecting units or reflected light of the inspection light; a time specifying unit that specifies an arrival time at which the vehicle arrives at the vehicle detection position and a passing time at which the vehicle passes through the vehicle detection position based on the vehicle detection signal; an estimation unit that estimates whether the vehicle is a two-wheeled vehicle based on a waveform pattern of the pressure signal acquired during the period from the arrival time to the passage time; a silhouette acquisition unit that acquires, when the vehicle is estimated to be a two-wheeled vehicle, a body silhouette of the vehicle obtained by arranging the vehicle detection signals acquired from the arrival time to the passage time on a time axis; a discrimination unit that discriminates whether the vehicle is a two-wheeled vehicle based on the vehicle body silhouette; A driving condition determination device comprising:

2. The discrimination unit discriminates that the vehicle is a two-wheeled vehicle when an area of ​​the vehicle body silhouette is less than a first threshold value. The driving condition determination device according to claim 1.

3. The discrimination unit is detecting a front wheel of the vehicle based on the presence or absence of light reception from the light receiving unit at the lowest level in a height direction of the vehicle body silhouette; When an area of ​​a vehicle body silhouette on a time axis forward of the detected front wheel is less than a second threshold, the vehicle is determined to be a two-wheeled vehicle. The driving condition determination device according to claim 1.

4. The discrimination unit is detecting front and rear wheels of the vehicle based on the presence or absence of light reception from the light receiving section at the lowest level in a height direction of the vehicle body silhouette; if the lengths of the detected front and rear wheels on the time axis are less than a third threshold, the vehicle is determined to be a two-wheeled vehicle. The driving condition determination device according to claim 1.

5. the discrimination unit discriminates that the vehicle is a motorcycle using an inference model that has learned vehicle body silhouettes of a plurality of vehicles, the inference model receiving an input of the vehicle body silhouette and outputting a determination result indicating whether the input vehicle body silhouette is a motorcycle or not; The driving condition determination device according to claim 1.

6. The estimation unit further estimates whether the vehicle is a three-wheeled vehicle based on the pressure signals acquired during the period from the arrival time to the passage time; the silhouette acquisition unit acquires a vehicle body silhouette of the vehicle when the vehicle is estimated to be a three-wheeled vehicle; The discrimination unit discriminates whether or not the vehicle is a three-wheeled vehicle based on the vehicle body silhouette. The driving condition determination device according to any one of claims 1 to 5.

7. acquiring, from each of a plurality of pressure sensors arranged in a line in a lane width direction at vehicle detection positions on a lane, a pressure signal capable of detecting pressure applied by a tire of a vehicle passing through the vehicle detection positions; a step of acquiring, from a vehicle detector having a plurality of light-projecting units arranged in a vertical direction at the vehicle detection position and projecting inspection light, and a plurality of light-receiving units receiving the inspection light from each of the plurality of light-projecting units or reflected light of the inspection light, a vehicle detection signal capable of detecting the presence or absence of the vehicle based on the presence or absence of reception of light by the light-receiving units; determining an arrival time when the vehicle arrives at the vehicle detection position and a passing time when the vehicle passes through the vehicle detection position based on the vehicle detection signal; estimating whether the vehicle is a two-wheeled vehicle based on a waveform pattern of the pressure signal acquired during the period from the arrival time to the passage time; acquiring a body silhouette of the vehicle by arranging the vehicle detection signals acquired from the arrival time to the passage time on a time axis when the vehicle is estimated to be a two-wheeled vehicle; determining whether the vehicle is a two-wheeled vehicle based on the vehicle body silhouette; A driving condition determination method comprising the steps of:

8. acquiring, from each of a plurality of pressure sensors arranged in a line in a lane width direction at vehicle detection positions on a lane, a pressure signal capable of detecting pressure applied by a tire of a vehicle passing through the vehicle detection positions; a step of acquiring, from a vehicle detector having a plurality of light-projecting units arranged in a vertical direction at the vehicle detection position and projecting inspection light, and a plurality of light-receiving units receiving the inspection light from each of the plurality of light-projecting units or reflected light of the inspection light, a vehicle detection signal capable of detecting the presence or absence of the vehicle based on the presence or absence of reception of light by the light-receiving units; determining an arrival time when the vehicle arrives at the vehicle detection position and a passing time when the vehicle passes through the vehicle detection position based on the vehicle detection signal; estimating whether the vehicle is a two-wheeled vehicle based on a waveform pattern of the pressure signal acquired during the period from the arrival time to the passage time; acquiring a body silhouette of the vehicle by arranging the vehicle detection signals acquired from the arrival time to the passage time on a time axis when the vehicle is estimated to be a two-wheeled vehicle; determining whether the vehicle is a two-wheeled vehicle based on the vehicle body silhouette; A program for causing a driving condition determination device to execute the above.

Images