Vehicle detection device, vehicle detection system, vehicle detection method and program

Abstract

To detect a vehicle passing through a bridge at low cost.SOLUTION: A vehicle detection device includes: an acquisition unit for acquiring time-series data of an observation value representing displacement of a bridge in a traveling direction of a vehicle at a position where a sensor on the bridge is provided from the sensor provided on the bridge; a moving average unit for calculating time series data of a moving average value subjected to moving average using a time window set in advance relative to the time-series data of the observation value; a difference calculation unit for calculating time series data of a difference value representing a difference between the observation value and the moving average value; and a determination unit for comparing the time series data of the difference value with a preset threshold value to determine that the vehicle has passed through the bridge when the difference value exceeds the threshold value.SELECTED DRAWING: Figure 6

Description

[Technical field]

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

[0002] 2. Description of the Related Art Conventionally, a vehicle measurement system that measures traffic volume on a bridge or the like using an ultrasonic sensor is known. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-094992 A [Patent Document 2] International Publication No. 2020 / 031405 [Non-patent literature]

[0004] [Non-Patent Document 1] Toshitaka Azuma et al., "Development of a Next-Generation Information Collection System for Road Traffic Census," Journal of Civil Engineering Information Utilization Technology, Vol. 15, pp. 103-110, 2006 Summary of the Invention [Problem to be solved by the invention]

[0005] However, ultrasonic sensors are expensive, and when they are installed on roads, the roads must be closed to traffic, making installation difficult.

[0006] The present invention has been made in view of the above, and provides a vehicle detection device, a vehicle detection system, a vehicle detection method, and a program that are capable of detecting vehicles passing over a bridge at low cost. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems and achieve the object, a vehicle detection device according to the present invention includes an acquisition unit that acquires, from a sensor provided on a bridge, time series data of an observation value that represents a displacement of the bridge in a vehicle travel direction at a position on the bridge where the sensor is provided, and Move The vehicle control system includes a moving average unit that calculates time series data of moving average values ​​obtained by performing a moving average, a difference calculation unit that calculates time series data of difference values ​​representing the difference between the observed values ​​and the moving average values, a determination unit that compares the time series data of the difference values ​​with a preset threshold value and determines that the vehicle has passed over the bridge if the difference value exceeds the threshold value, and a setting unit. The setting unit sets the accuracy of determining that the vehicle has passed over the bridge, calculated based on the time series data of the observed values ​​in a first period before the process of determining that the vehicle has passed over the bridge, as follows: Multiple time lengths Time window of Obtained for each case and Multiple Time window of A first time window to be used for the moving average is determined based on the accuracy in each case, and the determined first time window is used prior to the process of determining that the vehicle has passed through the bridge. The moving average is used for the time series data of the observed value in the process of determining whether the vehicle has passed through the bridge. Set as a time window. Effect of the Invention

[0008] According to the present invention, a vehicle passing over a bridge can be detected at low cost. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating a vehicle detection system. [Diagram 2] FIG. 2 shows the arrangement of sensors when viewed from the side of the bridge. [Diagram 3] FIG. 3 shows the arrangement of sensors when viewed from above the bridge. [Figure 4] FIG. 4 is a diagram showing the sensor and a portion of the main girder of a bridge. [Diagram 5] FIG. 5 is a diagram showing the sensor together with the first member and the second member. [Figure 6] FIG. 6 is a diagram illustrating a functional configuration of the vehicle detection device. [Figure 7] FIG. 7 is a flowchart showing a flow of processing performed by the vehicle detection device. [Figure 8] FIG. 8 is a flowchart showing the flow of the vehicle type determination process. [Figure 9] FIG. 9 is a diagram showing an example of time series data of the expansion / contraction amount in the traveling direction when a vehicle passes over a bridge and time series data of the moving average value. [Figure 10] FIG. 10 is a diagram showing the detection rate when the number of samples in the time window is changed. [Figure 11] FIG. 11 is a graph showing the detection rate versus the number of samples in the time window. [Figure 12] FIG. 12 is a diagram illustrating a hardware configuration of the vehicle detection device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, embodiments will be described with reference to the drawings.

[0011] 1 is a diagram showing a vehicle detection system 10 according to an embodiment. The vehicle detection system 10 detects that a vehicle has passed a bridge. For example, when a vehicle has passed a bridge, the vehicle detection system 10 identifies the time when the vehicle passed the bridge.

[0012] The vehicle detection system 10 includes a sensor 20 , a transmitting device 22 , and a vehicle detection device 30 .

[0013] The sensor 20 is provided at a predetermined target portion of the bridge. The sensor 20 detects an observation value that indicates a displacement in the travel direction or in a direction perpendicular to the bridge at the target portion of the bridge where the sensor 20 is provided. In this embodiment, the sensor 20 measures the amount of expansion and contraction in the travel direction at the target portion of the bridge. The amount of expansion and contraction is, for example, a change in distance of about several nanometers to several hundreds of nanometers between two points that are separated by a distance of about several tens of centimeters.

[0014] Note that the sensor 20 may detect other physical quantities instead of the amount of expansion and contraction in the traveling direction, as long as it can detect observed values ​​that indicate displacement in the traveling direction or the vertical direction. For example, the sensor 20 may be a strain meter that detects strain in the traveling direction in a target portion of the bridge. Also, for example, the sensor 20 may be an accelerometer that detects the magnitude of expansion and contraction acceleration in the traveling direction in the target portion of the bridge, or the magnitude of expansion and contraction acceleration in the vertical direction in the target portion of the bridge. Also, in the case of a bridge that has a thickness in the vertical direction, such as a box bridge, the sensor 20 may detect the amount of expansion and contraction in the vertical direction in the target portion.

[0015] The sensor 20 continuously detects observation values ​​representing displacement in the travel direction or vertical direction of the target portion of the bridge at predetermined time intervals. For example, the sensor 20 detects observation values ​​every few milliseconds. The sensor 20 continuously detects observation values ​​at predetermined time intervals. The sensor 20 may continuously detect observation values ​​at predetermined time intervals at all times (for example, continuously 24 hours a day).

[0016] The transmitting device 22 transmits the observation values ​​detected by the sensor 20 to the vehicle detection device 30 via a network. The network may be wired, wireless, or a mixture of wired and wireless. The network may be, for example, a personal area network (PAN), a local area network (LAN), or a wide area network (WAN), or a mixed network of a PAN, a LAN, and a WAN. The network may also include the Internet, a telephone communication line, or the like.

[0017] The vehicle detection device 30 receives time series data of observed values ​​that indicate displacement in the travel direction or vertical direction of a target portion of a bridge, transmitted from the transmitting device 22 via a network. The vehicle detection device 30 detects whether a vehicle has passed over the bridge based on the received time series data of observed values. Furthermore, the vehicle detection device 30 identifies the time when the vehicle passed over the bridge. Furthermore, the vehicle detection device 30 identifies the type of the passing vehicle, such as whether it is a small vehicle, a medium-sized vehicle, or a large vehicle.

[0018] The vehicle detection device 30 is a computer such as a server device that can be connected to a network. The vehicle detection device 30 may be a single computer, or may be configured by multiple computers such as a cloud system.

[0019] The vehicle detection system 10 may not include the transmission device 22. In this case, the vehicle detection device 30 directly acquires an observation value representing a displacement in the travel direction or vertical direction of a target portion of a bridge from the sensor 20. In this case, the vehicle detection device 30 may be provided near the sensor 20, i.e., near the bridge.

[0020] FIG. 2 is a diagram showing the arrangement of the sensor 20 when the bridge is viewed from the side. FIG. 3 is a diagram showing the arrangement of the sensor 20 when the bridge is viewed from above. The sensor 20 is attached, for example, to the end side of the bridge rather than the center in the travel direction. The sensor 20 is attached, for example, to the lower surface of the bridge, near the abutment. This allows the worker to easily attach the sensor 20 to the bridge even after the bridge is completed. The sensor 20 may be attached to any position in the travel direction of the bridge. For example, the sensor 20 may be attached to the center of the bridge in the travel direction, although this may make the installation difficult for the worker. The sensor 20 may also be attached to the side of the bridge. In this case, the sensor 20 can measure the amount of expansion and contraction of the bridge in the vertical direction.

[0021] 4 is a diagram showing the sensor 20 and a portion of the bridge's main girder 54. The sensor 20 measures the amount of change in the distance between a first point 62 and a second point 64 on the underside 56 of the bridge's main girder 54. The amount of change in the distance between the first point 62 and the second point 64 corresponds to the amount of expansion and contraction in the travel direction of the target portion of the bridge.

[0022] The first point 62 and the second point 64 are at the same position in the bridge width direction but at different positions in the travel direction. The distance between the first point 62 and the second point 64 is, for example, about several tens of centimeters. The sensor 20 measures the amount of change in the distance in the travel direction between the first point 62 and the second point 64 in units of, for example, several nanometers to several hundred nanometers.

[0023] The sensor 20 includes a first member 66, a second member 68, and a displacement detection device 70.

[0024] The first member 66 is a cantilever beam having a support portion 66a and a beam portion 66b. One end of the support portion 66a is a fixed end 66c fixed to the first point 62. The support portion 66a extends a predetermined distance downward from the first point 62 in a direction perpendicular to the lower surface 56 of the main girder 54. The beam portion 66b extends a predetermined distance from an end of the support portion 66a opposite to the fixed end 66c toward the second point 64 in the traveling direction. The end of the beam portion 66b not connected to the support portion 66a is a free end 66d that is not connected to any member. The free end 66d may be supported by a mechanism that limits movement in a direction other than the direction in which the change in distance is measured, such as a linear slider.

[0025] The second member 68 is a cantilever beam having a support portion 68a and a beam portion 68b. One end of the support portion 68a is a fixed end 68c fixed to the second point 64. The support portion 68a extends a predetermined distance downward from the second point 64 in a direction perpendicular to the lower surface 56 of the main girder 54. The beam portion 68b extends a predetermined distance from an end of the support portion 68a opposite to the fixed end 68c toward the first point 62 in the traveling direction. The end of the beam portion 68b not connected to the support portion 68a is a free end 68d that is not connected to any member. The free end 68d may be supported by a mechanism that limits movement in a direction other than the direction in which the change in distance is measured, such as a linear slider.

[0026] Here, the free end 66d of the first member 66 and the free end 68d of the second member 68 are arranged in overlapping positions in the running direction without mechanical interference. As a result, the free end 66d of the first member 66 and the free end 68d of the second member 68 are arranged in opposing positions in a direction perpendicular to the lower surface 56 of the main girder 54. When the distance between the first point 62 and the second point 64 changes, the relative positions of the free end 66d of the first member 66 and the free end 68d of the second member 68 are displaced in the running direction.

[0027] The displacement detection device 70 is provided at a portion where the free end 66d of the first member 66 and the free end 68d of the second member 68 face each other. The displacement detection device 70 detects the displacement of the relative position between the free end 66d of the first member 66 and the free end 68d of the second member 68. Then, the displacement detection device 70 outputs the detected displacement as the amount of expansion and contraction between two points in the traveling direction on the bridge.

[0028] 5 is a diagram showing the displacement detection device 70 together with the first member 66 and the second member 68. The displacement detection device 70 includes a scale 72 and a detector 74.

[0029] The scale 72 is attached to one of the free end 66d of the first member 66 or the free end 68d of the second member 68. The detector 74 is attached to the other of the free end 66d of the first member 66 or the free end 68d of the second member 68 to which the scale 72 is not attached.

[0030] The scale 72 is an optical member whose reflected light amount (or transmitted light amount) changes depending on the irradiated position of the light in the traveling direction. For example, the scale 72 is a diffraction grating or a light absorber in which a plurality of optical slits or stripes are formed at predetermined intervals in the traveling direction.

[0031] The detector 74 includes a half mirror 76, a light emitting section 78, a light receiving section 80, and a detection circuit 82. The half mirror 76 reflects a part of the irradiated light and transmits the other part.

[0032] The light emitting unit 78 irradiates light onto the scale 72 via the half mirror 76. The light receiving unit 80 receives the light reflected by the scale 72 via the half mirror 76. The detection circuit 82 outputs a signal representing the displacement of the relative position between the first member 66 and the second member 68 based on the change in the amount of light detected by the light receiving unit 80, as the amount of expansion and contraction.

[0033] The position of the light irradiated onto the scale 72 shifts in the travel direction in response to the shift in the travel direction of the relative positions of the first member 66 and the second member 68. Since the scale 72 has optical slits or stripes formed in the travel direction, the amount of light reflected from the scale 72 increases or decreases in response to the shift in the travel direction of the light irradiation position. Specifically, the amount of light reflected from the scale 72 increases or decreases one cycle when the position of the light irradiated onto the scale 72 shifts by the spacing of the optical slits or stripes. Therefore, for example, the detection circuit 82 can obtain the amount of change in the relative positions of the first member 66 and the second member 68 by counting the increase or decrease in the signal output from the light receiving unit 80.

[0034] Furthermore, the displacement detection device 70 may include two scales 72 whose optical slits or stripes are shifted from each other by a quarter period, and two light-emitting units 78 and two light-receiving units 80 corresponding to the two scales 72. This allows the two light-receiving units 80 to output two periodic signals that are shifted in phase by a quarter period in response to a change in the relative position between the first member 66 and the second member 68. Therefore, for example, the detection circuit 82 can detect the direction of change in the relative position between the first member 66 and the second member 68 and the amount of change in the relative position between the first member 66 and the second member 68 at an interval shorter than the period of the optical slits or stripes, based on the values ​​of the two signals.

[0035] 5, the scale 72 is configured to reflect light. Alternatively, the scale 72 may be configured to transmit light. In this case, the amount of transmitted light through the scale 72 changes depending on the position of the light irradiated on the scale 72 in the traveling direction.

[0036] Furthermore, the detector 74 may be configured not to include the half mirror 76. In this case, the light emitted from the light-emitting unit 78 is incident on the scale 72 at a predetermined angle. Then, the light reflected by the scale 72 is directly incident on the light-receiving unit 80.

[0037] The displacement detection device 70 configured as above uses a cantilever beam to detect a change in distance between two points with an optical sensor. As a result, the displacement detection device 70 can accurately detect very small expansion and contraction of the bridge using simple and low-cost components.

[0038] 6 is a diagram showing a functional configuration of the vehicle detection device 30. The vehicle detection device 30 includes an acquisition unit 112, a storage unit 114, a moving average unit 116, a difference calculation unit 118, a peak detection unit 120, a determination unit 122, a time identification unit 124, a type determination unit 126, and an output unit 128.

[0039] The acquisition unit 112 acquires, via a network, from the sensor 20 installed on the bridge, time series data of observed values ​​that indicate displacement in the traveling direction or vertical direction in the target portion of the bridge where the sensor 20 is installed. In this embodiment, the observed value is the amount of expansion and contraction in the traveling direction in the target portion. The acquisition unit 112 may acquire the observed value for each sample in real time, or may acquire a predetermined number of samples of observed values ​​collectively at regular intervals.

[0040] Each of the multiple observation values ​​included in the time series data of the observation values ​​is associated with a detection time. For example, the time series data of the observation values ​​may include multiple observation values ​​and multiple time data associated with the multiple observation values ​​in a one-to-one relationship. Each of the multiple time data represents a time at which the corresponding observation value was detected. The time series data of the observation values ​​has a predetermined sample interval, which is a time interval between samples. Therefore, the time series data of the observation values ​​may include multiple observation values ​​and time data of the first observation value. In this case, the detection time of each of the multiple observation values ​​is calculated based on the time data of the first observation value, the order of the corresponding observation values, and the sample time interval.

[0041] The storage unit 114 stores the time series data of the observed values ​​acquired by the acquisition unit 112 .

[0042] The moving average unit 116 calculates time series data of moving average values ​​by performing a moving average using a preset time window on the time series data of observed values ​​stored in the storage unit 114. The time window may be represented by the number of consecutive observed values ​​(number of samples) for which the moving average is performed. The time window may also be represented by time. When the time window is represented by time, the moving average unit 116 calculates the moving average value using the number of observed values ​​obtained by dividing the time window by the sample interval.

[0043] The moving average unit 116 may calculate time series data of the moving average value by performing a simple moving average on the time series data of the observed values. That is, the moving average unit 116 adds up all the observed values ​​included in the time window (e.g., N values), and divides the sum by N to calculate the moving average value.

[0044] Furthermore, the moving average unit 116 may calculate time series data of moving average values ​​by performing weighted moving averaging on the time series data of the observed values. That is, the moving average unit 116 multiplies each of the observed values ​​included in the time window by a predetermined weight, adds up all of the N observed values ​​multiplied by the weights, and divides the sum by N to calculate the moving average value.

[0045] The moving average unit 116 may also calculate time series data of moving average values ​​by performing a moving average on the time series data of the observed values ​​using a FIR (Finite Impulse Response) filter.The moving average unit 116 may also calculate time series data of moving average values ​​by performing a convolution operation on the time series data of the observed values ​​with time series window function data of a time length corresponding to the time window.

[0046] The moving average unit 116 may calculate the moving average value by arithmetic processing using a software program. The moving average unit 116 may calculate the moving average value by arithmetic processing using a hardware circuit such as a filter circuit.

[0047] The difference calculation unit 118 acquires the time series data of the observed values ​​stored in the storage unit 114 and the time series data of the moving average values ​​calculated by the moving average unit 116. The difference calculation unit 118 calculates the difference between the observed values ​​and the moving average values ​​for each sample, thereby calculating the time series data of the difference values ​​representing the difference between the observed values ​​and the moving average values. For example, the calculation unit 118 calculates the time series data of the difference values ​​by subtracting the moving average values ​​from the observed values.

[0048] The peak detection unit 120 analyzes the time series data of the difference values ​​to detect the sample positions of the peaks of the waveform. The peak detection unit 120 also detects peaks in the waveform that are convex on either the positive side or the negative side in the time series data of the difference values. When the time series data of the difference values ​​for the observation period includes multiple peaks, the peak detection unit 120 detects each of the multiple peaks.

[0049] For example, the peak detection section 120 may detect, as a peak, any sample position in a continuous range that exceeds a predetermined value in the time series data of difference values. Also, for example, the peak detection section 120 may detect, as a peak, the sample position of the maximum or minimum difference value in a continuous range that exceeds a predetermined value in the time series data of difference values.

[0050] Also, for example, the peak detection unit 120 may detect a peak after removing noise (for example, minute high-frequency increase / decrease components) included in the time-series data of the difference values. Also, for example, the peak detection unit 120 may calculate time-series data of differential values ​​by differentiating the time-series data of the difference values ​​after removing the noise, and detect a sample position where the time-series data of the differential values ​​becomes 0 as a peak.

[0051] A threshold value is set in advance for the determination unit 122. For the peaks detected by the peak detection unit 120, the determination unit 122 compares the peak value of the waveform in the time series data of the difference value with a preset threshold value. Then, the determination unit 122 determines that the vehicle has passed over a bridge when the peak value exceeds the threshold value. Note that, when the peak detection unit 120 detects multiple peaks, the determination unit 122 compares the peak value with the threshold value for each of the detected multiple peaks, and determines that the vehicle has passed over a bridge when the peak value exceeds the threshold value.

[0052] For example, if the detected peak is a waveform that is convex on the positive side, the determination unit 122 determines that the vehicle has passed over a bridge if the peak value is greater than a threshold value. Also, for example, if the detected peak is a waveform that is convex on the negative side, the determination unit 122 determines that the vehicle has passed over a bridge if the peak value is smaller than a threshold value.

[0053] When the determination unit 122 determines that the vehicle has passed over the bridge, the time identifying unit 124 identifies the time corresponding to the peak as the time when the vehicle passed over the bridge. For example, the time identifying unit 124 acquires the time corresponding to the peak by referring to the time data corresponding to each of the multiple observation values ​​included in the time series data of the observation values.

[0054] When it is determined that the vehicle has passed over a bridge, the type determination unit 126 determines the type of the vehicle according to the magnitude of the peak value. For example, the type determination unit 126 determines whether the vehicle is a small vehicle, a medium vehicle, or a large vehicle according to the magnitude of the peak value. For example, if the detected peak is a waveform that is convex on the positive side, the type determination unit 126 determines that the vehicle is a small vehicle if the peak value is smaller than a first determination value, a medium vehicle if the peak value is equal to or greater than the first determination value and smaller than a second determination value, and a large vehicle if the peak value is equal to or greater than the second determination value. Note that the second determination value is greater than the first determination value. For example, if the detected peak is a waveform that is convex on the negative side, the type determination unit 126 determines that the vehicle is a large vehicle if the peak value is smaller than the first determination value, a medium vehicle if the peak value is equal to or greater than the first determination value and smaller than the second determination value, and a small vehicle if the peak value is equal to or greater than the second determination value.

[0055] The output unit 128 outputs to an external device the determination result of the vehicle passage by the determination unit 122, the time when the vehicle specified by the time determination unit 124 passed over the bridge, and the determination result of the vehicle type by the type determination unit 126. For example, the output unit 128 displays this information on a display device. Also, for example, the output unit 128 may transmit this information to a terminal device held by an administrator or the like.

[0056] 7 is a flowchart showing the flow of processing in the vehicle detection device 30. The vehicle detection device 30 executes processing according to the flow shown in FIG.

[0057] First, in S11, the vehicle detection device 30 acquires time series data of observed values ​​for a predetermined observation time range. For example, the vehicle detection device 30 acquires time series data of observed values ​​for a range of several minutes, several tens of minutes, or several hours.

[0058] Next, in S12, the vehicle detection device 30 calculates time series data of moving average values ​​by performing a moving average on the time series data of the observed values ​​in the observation time range using a preset time window.

[0059] Next, in S13, the vehicle detection device 30 calculates the difference between the observed value and the moving average value for each sample, thereby calculating time-series data of difference values ​​that indicate the difference between the observed value and the moving average value.

[0060] Next, in S14, the vehicle detection device 30 analyzes the time series data of the difference values ​​to detect waveform peaks. For example, the vehicle detection device 30 detects peaks in the waveform that are convex on either the positive side or the negative side in the time series data of the difference values. When the time series data of the difference values ​​for the observation period includes multiple peaks, the vehicle detection device 30 detects each of the multiple peaks.

[0061] Next, in S15, the vehicle detection device 30 compares the value of the peak of the waveform in the time series data of the difference value with a preset threshold value for each detected peak. Then, the vehicle detection device 30 determines that the vehicle has passed over the bridge if the value of the peak exceeds the threshold value. For example, if the detected peak is a peak in a waveform that is convex on the positive side, the vehicle detection device 30 determines that the vehicle has passed over the bridge if the value of the peak is greater than the threshold value. Also, for example, if the detected peak is a peak in a waveform that is convex on the negative side, the vehicle detection device 30 determines that the vehicle has passed over the bridge if the value of the peak is less than the threshold value.

[0062] Next, in S16, the vehicle detection device 30 determines whether or not a vehicle has passed a bridge during the observation time range. If a vehicle has not passed a bridge during the observation time range (No in S16), the vehicle detection device 30 ends the processing of this flow. If a vehicle has passed a bridge during the observation time range (Yes in S16), the vehicle detection device 30 advances the processing to S17.

[0063] In S17, the vehicle detection device 30 identifies the time corresponding to the peak for each vehicle determined to have passed as the time when the vehicle passed over the bridge. For example, the vehicle detection device 30 acquires the time corresponding to the peak by referring to the time data corresponding to each of the multiple observation values ​​included in the time series data of the observation values.

[0064] Next, in S18, the vehicle detection device 30 determines the type of vehicle for each vehicle determined to have passed, depending on the magnitude of the peak value. For example, the vehicle detection device 30 determines whether the vehicle is a small vehicle, a medium vehicle, or a large vehicle, depending on the magnitude of the peak value.

[0065] Next, in S19, the vehicle detection device 30 outputs to an external device, for each vehicle determined to have passed, the time when the identified vehicle passed over the bridge and the determination result of the type of vehicle. For example, the vehicle detection device 30 may display this information on a display device, or may transmit this information to a terminal device held by an administrator or the like.

[0066] When the process of S19 is completed, the vehicle detection device 30 ends the process of this flow.

[0067] Fig. 8 is a flowchart showing the flow of the vehicle type determination process. In the vehicle type determination process of S18 in Fig. 7, the vehicle detection device 30 executes, for example, the process shown in Fig. 8. Note that the process in Fig. 8 is performed when the detected peak is a waveform that is convex on the positive side.

[0068] First, in S21, the vehicle detection device 30 obtains a difference value for the corresponding peak.

[0069] Next, in S22, the vehicle detection device 30 judges whether the acquired difference value is smaller than a first judgment value. The first judgment value is a preset value that is larger than a threshold value for judging whether the vehicle has passed over a bridge. If the acquired difference value is smaller than the first judgment value (Yes in S22), the vehicle detection device 30 advances the process to S23. In S23, the vehicle detection device 30 judges the type of the passing vehicle to be a compact car.

[0070] If the acquired difference value is equal to or greater than the first judgment value (No in S22), the vehicle detection device 30 proceeds to S24. In S24, the vehicle detection device 30 determines whether the acquired difference value is smaller than the second judgment value. The second judgment value is a preset value that is larger than the first judgment value. If the acquired difference value is smaller than the second judgment value (Yes in S24), the vehicle detection device 30 proceeds to S25. In S25, the vehicle detection device 30 determines the type of the passing vehicle to be a medium-sized vehicle.

[0071] If the acquired difference value is equal to or greater than the second determination value (No in S24), the vehicle detection device 30 advances the process to S26. In S26, the vehicle detection device 30 determines that the type of the passing vehicle is a large vehicle.

[0072] Then, when the vehicle detection device 30 finishes the process of S23, S25, or S26, it ends the vehicle type determination process for the vehicle. If the vehicle detection device 30 detects another vehicle, it repeats the process from S21 for that vehicle again.

[0073] FIG. 9 is a diagram showing an example of time series data of the expansion / contraction amount in the traveling direction when a vehicle passes over a bridge and time series data of the moving average value.

[0074] The inventor compared the amount of expansion and contraction of the bridge in the travel direction detected by the sensor 20 with an image captured by a monitoring camera that captures an image of the bridge. As a result, the inventor confirmed that the amount of expansion and contraction of the bridge in the travel direction increases and decreases significantly at the timing when the vehicle passes over the bridge. In other words, the inventor confirmed that it is possible to identify the time when the vehicle passes over the bridge by identifying the timing of the peak of the waveform in the time-series data of the observation value obtained from the sensor 20.

[0075] The inventor also confirmed that the expansion and contraction of the bridge in the travel direction increases and decreases more slowly than the rate of increase and decrease caused by a vehicle passing over the bridge. In other words, the inventor confirmed that the expansion and contraction fluctuates over a period that is sufficiently longer than the period of vibration caused by a vehicle passing over the bridge. The inventor presumed that the component of the bridge's long-period fluctuations affects the accuracy of determining whether or not a vehicle is passing over the bridge.

[0076] Therefore, the inventor developed a vehicle detection device 30 that generates time series data of difference values ​​by subtracting the moving average value of the expansion and contraction amounts in the travel direction of the bridge detected by the sensor 20, and detects whether or not a vehicle has passed over a bridge by identifying the waveform peaks in the time series data of the difference values.

[0077] Fig. 10 is a diagram showing the detection rate when the number of samples in the time window is changed, and Fig. 11 is a diagram showing a graph showing the detection rate versus the number of samples in the time window.

[0078] 10 and 11 show an example of a detection rate calculated from time series data of observed values ​​obtained by installing a sensor 20 on a bridge with a length of about 20 meters. The sample period is 1 / 20 seconds. The inventors also confirmed from a surveillance camera that 8 vehicles passed through the bridge in the upbound lane and 7 vehicles passed through the bridge in the downbound lane during the observation period.

[0079] In such settings, when the moving average time window was set to 41 samples and a vehicle was detected by the vehicle detection device 30, the detection rate was approximately 86.6%. Furthermore, when the moving average time window was set to 51 samples, the detection rate was approximately 92.9%. Furthermore, when the moving average time window was set to 61 samples, the detection rate was 100%. Furthermore, when the moving average time window was set to 71 samples, the detection rate was approximately 92.9%. Furthermore, when the moving average time window was set to 81 samples, the detection rate was approximately 86.6%.

[0080] From the above, the inventor confirmed that when detecting whether a vehicle has passed over a bridge by identifying a waveform peak in time-series data of difference values, the length of the time window affects the accuracy.

[0081] Here, the time corresponding to 61 samples where the detection rate was 100% is (1 / 20) seconds x 61 samples = 3.05 seconds.

[0082] Moreover, the time it takes for a vehicle traveling at 30 kilometers per hour to pass over a 20-meter bridge is 2.4 seconds. The time it takes for a vehicle traveling at 20 kilometers per hour to pass over a 20-meter bridge is 3.6 seconds. The time it takes for a vehicle traveling at 40 kilometers per hour to pass over a 20-meter bridge is 1.8 seconds. From this, it is clear that there is an optimum value for the length of the time window that provides high vehicle detection accuracy. Therefore, it is preferable to determine the time window for the moving average set in the vehicle detection device 30 by conducting experiments or the like in advance to measure detection rates for time windows of a plurality of time lengths.

[0083] As described above, the vehicle detection system 10 according to this embodiment detects vehicles passing over a bridge using the sensor 20 that can be easily attached to the bridge. As a result, the vehicle detection system 10 according to this embodiment can accurately detect vehicles passing over a bridge at low cost.

[0084] 12 is a diagram showing a hardware configuration of the vehicle detection device 30. As an example, the vehicle detection device 30 is realized by an information processing device having the same hardware configuration as a general computer. The vehicle detection device 30 includes a CPU (Central Processing Unit) 301, an operation device 302, a display device 303, a main memory device 305, an auxiliary memory device 306, a communication device 307, and a bus 309. Each unit is connected via the bus 309.

[0085] The CPU 301 executes various processes in cooperation with various programs stored in advance in the auxiliary storage device 306, etc., using a predetermined area of ​​the main storage device 305 as a working area, and comprehensively controls the operation of each unit constituting the vehicle detection device 30. The CPU 301 also operates the operation device 302, the display device 303, the communication device 307, etc. in cooperation with the programs.

[0086] The operation device 302 is an input device such as a touch panel, a mouse, or a keyboard, which receives information input by a user as an instruction signal, and outputs the instruction signal to the CPU 301 .

[0087] The display device 303 is a display unit such as an LCD (Liquid Crystal Display), etc. The display device 303 displays various information based on a display signal from the CPU 301.

[0088] The main storage device 305 is a volatile storage medium such as a Synchronous Dynamic Random Access Memory (SDRAM). The main storage device 305 functions as a working area for the CPU 301.

[0089] The auxiliary storage device 306 is a rewritable storage device such as a semiconductor storage medium such as a flash memory, a magnetically or optically recordable storage medium, etc. The auxiliary storage device 306 stores a program used for controlling the vehicle detection device 30.

[0090] The communication device 307 transmits and receives data to and from other devices. The communication device 307 may also transmit and receive data to and from a server or the like via a network.

[0091] The programs executed by the vehicle detection device 30 are provided, for example, by being stored on a computer connected to a network such as the Internet and downloaded via the network. In addition, the programs executed by the vehicle detection device 30 may be provided by being pre-installed in a portable storage medium or the like.

[0092] The program executed by the vehicle detection device 30 has a modular configuration including an acquisition module, a moving average module, a difference calculation module, a peak detection module, a judgment module, a time identification module, a type judgment module, and an output module. The CPU 301 reads out such a program from a storage medium or the like, and loads each of the above modules into the main storage device 305. By executing such a program, the CPU 301 functions as the acquisition unit 112, the moving average unit 116, the difference calculation unit 118, the peak detection unit 120, the judgment unit 122, the time identification unit 124, the type judgment unit 126, and the output unit 128. By executing such a program, the CPU 301 also causes the main storage device 305 or the auxiliary storage device 306 to function as the storage unit 114. In addition, some or all of the acquisition unit 112, moving average unit 116, difference calculation unit 118, peak detection unit 120, determination unit 122, time identification unit 124, type determination unit 126 and output unit 128 may be configured by hardware.

[0093] Although the embodiments of the present invention have been described above, these embodiments are presented as examples and are not intended to limit the scope of the invention. Various modifications can be made to the embodiments. [Explanation of symbols]

[0094] 10 Vehicle Detection System 20 Sensors 22 Transmitting device 30 Vehicle detection device 112 Acquisition Department 114 Storage section 116 Moving average part 118 Difference Calculation Unit 120 Peak detector 122 Judgment section 124 Time identification part 126 Type determination unit 128 Output section

Claims

1. an acquisition unit that acquires, from a sensor provided on a bridge, time series data of an observation value that represents a displacement of the bridge in a vehicle travel direction at a position on the bridge where the sensor is provided; a moving average unit that calculates time series data of a moving average value obtained by performing a moving average on the time series data of the observed values; a difference calculation unit that calculates time series data of a difference value that represents a difference between the observed value and the moving average value; a determination unit that compares the time series data of the difference value with a preset threshold value, and determines that the vehicle has passed over the bridge when the difference value exceeds the threshold value; A setting section; Equipped with The setting unit is acquiring an accuracy of determining that the vehicle has passed over the bridge for each of a plurality of time windows having different time lengths, the accuracy being calculated based on the time series data of the observation value in a first time period before a process of determining that the vehicle has passed over the bridge is executed; determining a first time window to be used for the moving average based on the accuracy for each of the plurality of time windows; Prior to the process of determining that the vehicle has passed over the bridge, the determined first time window is set as a time window to be used for the moving average of the time series data of the observation value in the execution of the process of determining that the vehicle has passed over the bridge. Vehicle detection device.

2. The sensor detects, as the displacement in the traveling direction, an amount of expansion and contraction in the traveling direction at a position on the bridge where the sensor is provided.

2. The vehicle detection device of claim 1.

3. a time specifying unit that, when it is determined that the vehicle has passed over the bridge, specifies a time corresponding to a peak of a waveform of the time-series data of the difference value as the time when the vehicle has passed over the bridge. The vehicle detection device according to claim 1 or 2, further comprising:

4. The determination unit compares a peak value of a waveform that is convex on either the positive side or the negative side in the time series data of the difference value with the threshold value, and determines that the vehicle has passed over the bridge when the peak value exceeds the threshold value. A vehicle detection device according to any one of claims 1 to 3.

5. The moving average unit calculates time series data of the moving average value by performing a simple moving average using the time window on the time series data of the observed value. A vehicle detection device according to any one of claims 1 to 4.

6. The moving average unit calculates time series data of the moving average value by performing a weighted moving average using the time window on the time series data of the observed value. A vehicle detection device according to any one of claims 1 to 4.

7. The moving average unit calculates time series data of a moving average value by performing a moving average using the time window on the time series data of the observed values ​​using an FIR (Finite Impulse Response) filter. A vehicle detection device according to any one of claims 1 to 4.

8. The moving average unit calculates time series data of a moving average value obtained by performing a moving average using the time window by performing a convolution operation on the time series data of the observed value with time series window function data of a time length corresponding to the time window. A vehicle detection device according to any one of claims 1 to 4.

9. A type determination unit that, when it is determined that the vehicle has passed over the bridge, determines the type of the vehicle according to the magnitude of a peak value of the waveform of the time-series data of the difference value. A vehicle detection apparatus according to any one of claims 1 to 8.

10. a sensor provided on a bridge and configured to output time-series data of observed values ​​representing a displacement of the bridge in a vehicle travel direction on the bridge; Vehicle detection device An information processing device; Equipped with The vehicle detection device includes: an acquisition unit that acquires time series data of the observed value from the sensor; a moving average unit that calculates time series data of a moving average value obtained by performing a moving average on the time series data of the observed values; a difference calculation unit that calculates time series data of a difference value that represents a difference between the observed value and the moving average value; a determination unit that compares the time series data of the difference value with a preset threshold value, and determines that the vehicle has passed over the bridge when the difference value exceeds the threshold value; having The information processing device includes: acquiring an accuracy of determining that the vehicle has passed over the bridge for each of a plurality of time windows having different time lengths, the accuracy being calculated based on the time series data of the observation value in a first time period before a process of determining that the vehicle has passed over the bridge is executed; determining a first time window to be used for the moving average based on the accuracy for each of the plurality of time windows; Prior to the process of determining that the vehicle has passed over the bridge, the determined first time window is set in the vehicle detection device as a time window to be used for the moving average of the time series data of the observation value in the execution of the process of determining that the vehicle has passed over the bridge. Vehicle detection system.

11. A vehicle detection method for detecting a vehicle passing through a bridge by a vehicle detection device and an information processing device, comprising: The vehicle detection device, acquiring, from a sensor provided on the bridge, time series data of observed values ​​representing a displacement of the bridge in the traveling direction of the vehicle at a position on the bridge where the sensor is provided; Calculating time series data of a moving average by performing a moving average on the time series data of the observed values; calculating time series data of difference values ​​representing differences between the observed values ​​and the moving average values; comparing the time series data of the difference value with a preset threshold value, and determining that the vehicle has passed over the bridge if the difference value exceeds the threshold value; The information processing device, acquiring an accuracy of determining that the vehicle has passed over the bridge for each of a plurality of time windows having different time lengths, the accuracy being calculated based on the time series data of the observation value in a first time period before a process of determining that the vehicle has passed over the bridge is executed; determining a first time window to be used for the moving average based on the accuracy for each of the plurality of time windows; Prior to the process of determining that the vehicle has passed over the bridge, the determined first time window is set in the vehicle detection device as a time window to be used for the moving average of the time series data of the observation value in the execution of the process of determining that the vehicle has passed over the bridge. Vehicle detection methods.

12. A program for causing a computer to function as an information processing device that sets information for a vehicle detection device that detects vehicles passing through a bridge, The vehicle detection device includes: an acquisition unit that acquires, from a sensor provided on a bridge, time series data of an observation value that represents a displacement of the bridge in a vehicle travel direction at a position on the bridge where the sensor is provided; a moving average unit that calculates time series data of a moving average value obtained by performing a moving average on the time series data of the observed values; a difference calculation unit that calculates time series data of a difference value that represents a difference between the observed value and the moving average value; a determination unit that compares the time series data of the difference value with a preset threshold value, and determines that the vehicle has passed over the bridge when the difference value exceeds the threshold value; having The information processing device includes: acquiring, for each of a plurality of time windows having different time lengths, an accuracy of determining that the vehicle has passed over the bridge, the accuracy being calculated based on the time series data of the observation value in a first time period before a process of determining that the vehicle has passed over the bridge is executed; determining a first time window to be used for the moving average based on the accuracy for each of the plurality of time windows; Prior to the process of determining that the vehicle has passed over the bridge, the determined first time window is set in the vehicle detection device as a time window to be used for the moving average of the time series data of the observation value in the execution of the process of determining that the vehicle has passed over the bridge. program.

Images