JP7779694B2 - Vehicle Detection System - Google Patents

Description

The present invention relates to a vehicle detection system.

Systems in which an edge computer collects sensor data from multiple sensors are known. In such systems, Ethernet and TCP (Transmission Control Protocol)/IP (Internet Protocol) are generally used as the communication protocol between the edge computer and the multiple sensors. TCP/IP allocates up to 10% of the Ethernet packet length to redundant data such as headers. For this reason, for example, if a system collecting large amounts of sensor data from multiple sensors uses TCP/IP as its communication protocol, the communication bandwidth could become congested, potentially resulting in data loss.

There is also a known vehicle detection system that uses multiple sensors to detect vehicles passing over a bridge (see, for example, Patent Document 1). Such vehicle detection systems must perform sensing at short intervals and transmit large amounts of sensor data to a terminal device. Furthermore, in such vehicle measurement systems, it is preferable to synchronize the detection timing in order to accurately detect the passage of vehicles using multiple sensors.

Patent Documents 2 and 3 describe network protocols.

International Publication No. 2020/031405 Japanese Patent Application Laid-Open No. 2006-229977 Japanese Patent Application Laid-Open No. 2004-005661

The present invention has been made in consideration of the above, and provides a vehicle detection system that can efficiently synchronize multiple sensor devices using a small amount of data, and accurately detect when a vehicle has passed over a bridge.

In order to solve the above-mentioned problems and achieve the object, the vehicle detection system of the present invention comprises a plurality of sensor devices that are installed on a bridge and detect observation values that represent displacement of the bridge; a terminal device that collects the observation values from each of the plurality of sensor devices; and an information processing unit that detects that a vehicle has passed over the bridge based on time series data of the observation values of each of the plurality of sensor devices collected by the terminal device, wherein the terminal device transmits a detection request to the plurality of sensor devices every T seconds , and each of the plurality of sensor devices detects the observation values N times every Δt seconds from the time when the detection request is received and stores a group of the detected observation values, where Δt is a positive real number, N is an integer greater than or equal to 2, and T is N × Δt, and the terminal device periodically transmits read requests to the plurality of sensor devices, and when each of the plurality of sensor devices receives the read request, it transmits the group of observation values that it has stored to the terminal device.

According to the present invention, multiple sensor devices can be efficiently synchronized using a small amount of data, allowing for accurate detection of a vehicle passing over a bridge.

FIG. 1 is a diagram showing the configuration of a vehicle detection system. FIG. 2 is a diagram showing the arrangement of sensor devices when the bridge is viewed from the side. FIG. 3 is a diagram showing the arrangement of sensor devices when the bridge is viewed from above. FIG. 4 is a diagram illustrating the functional configuration of the sensor device and the terminal device. FIG. 5 is a sequence diagram showing the exchange of information between the terminal device and each of the plurality of sensor devices. FIG. 6 is a diagram illustrating a first example of the functional configuration of the information processing unit. FIG. 7 is a diagram showing an example of time-series data of observed values when a bridge has two lanes, an inbound lane and an outbound lane. FIG. 8 is a diagram showing an example of time-series data of observed values detected by each of a plurality of sensor devices. FIG. 9 is a diagram illustrating a second example of the functional configuration of the information processing unit. FIG. 10 is a graph showing time on the horizontal axis and observed values on the vertical axis. FIG. 11 is a diagram illustrating a third example of the functional configuration of the information processing unit. FIG. 12 is a diagram illustrating the functional configuration of the terminal device. FIG. 13 is a diagram showing the hierarchical structure of a communication protocol between a sensor device and a terminal device. FIG. 14 is a diagram illustrating the hardware configuration of the information processing unit.

The following describes the embodiment with reference to the drawings.

Figure 1 is a diagram showing the configuration of a vehicle detection system 10 according to an embodiment. The vehicle detection system 10 detects that a vehicle has passed over a bridge. Furthermore, the vehicle detection system 10 detects the weight of the vehicle that has passed over the bridge. The vehicle detection system 10 also identifies the time at which the vehicle passed over the bridge.

The vehicle detection system 10 includes multiple sensor devices 20, a terminal device 22, and an information processing device 24.

Each of the multiple sensor devices 20 is installed at a different, predetermined target portion of the bridge. The sensor devices 20 detect observed values that represent displacement in the direction of travel or perpendicular to the bridge at the target portion of the bridge where the sensor devices 20 are installed. In this embodiment, the sensor devices 20 measure the amount of expansion and contraction in the direction of travel at the target portion of the bridge. The amount of expansion and contraction is, for example, a change in distance of several nanometers to several hundred nanometers between two points that are several tens of centimeters apart.

Note that the sensor device 20 may detect other physical quantities in addition to the expansion/contraction amount in the traveling direction, as long as it can detect observed values representing displacement in the traveling direction or vertical direction. For example, the sensor device 20 may be a strain gauge that detects strain in the traveling direction in a target portion of the bridge. Also, for example, the sensor device 20 may be an accelerometer that detects the magnitude of expansion/contraction acceleration in the traveling direction in a target portion of the bridge, or the magnitude of expansion/contraction acceleration in the vertical direction in a target portion of the bridge. Furthermore, in the case of a bridge with a vertical thickness, such as a box bridge, the sensor device 20 may detect the amount of expansion/contraction in the vertical direction in the target portion.

Each of the multiple sensor devices 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 in response to receiving a detection request from the terminal device 22. For example, the sensor device 20 detects observation values every few milliseconds in response to receiving a detection request from the terminal device 22. For example, the sensor device 20 continuously detects observation values at predetermined time intervals for a predetermined number of times or for a predetermined period of time. The sensor device 20 transmits a group of observed values obtained through detection to the terminal device 22.

The terminal device 22 is an edge computer connected to each of the multiple sensor devices 20 via a network. For example, the terminal device 22 is connected by wire via a LAN (Local Area Network). The terminal device 22 and each of the multiple sensor devices 20 are assigned a MAC address (Media Access Control address), which is a unique physical address that can be identified on the network. The terminal device 22 sends and receives frames to and from each of the multiple sensor devices 20 using the MAC address via the Ethernet protocol.

The terminal device 22 periodically transmits a detection request to each of the multiple sensor devices 20. For example, the terminal device 22 periodically broadcasts a detection request to the multiple sensor devices 20. The terminal device 22 acquires a group of observed values detected in response to the detection request from each of the multiple sensor devices 20. The terminal device 22 then generates time-series data of the observed values, which is a data group in which the detection time is associated with each observed value included in the group of observed values for each of the multiple sensor devices 20.

Furthermore, the terminal device 22 detects whether a vehicle has passed over a bridge based on the time series data of the observation values received from each of the multiple sensor devices 20. The terminal device 22 also determines the weight of the passing vehicle. For example, the terminal device 22 may identify the vehicle type based on the weight of the passing vehicle, such as whether it is a small, medium, or large vehicle. Furthermore, the terminal device 22 also identifies the time at which the vehicle passed over the bridge.

The terminal device 22 transmits the detection result of whether or not a vehicle has passed over a bridge, the determination result of the weight of the passing vehicle, and the time the vehicle passed over the bridge to the information processing device 24 via the external network. This allows the terminal device 22 to notify the information processing device 24 only of the information processing result, thereby reducing communication traffic. The external network may be wired, wireless, or a mixture of wired and wireless. The external network may be, for example, a LAN, a PAN (Personal Area Network), or a WAN (Wide Area Network), or a mixed network of PAN, LAN, and WAN. The external network may also include cellular communication lines such as LTE (Long Term Evolution).

The information processing device 24 is a computer such as a server device that can be connected to an external network. The information processing device 24 may be a single computer, or may be composed of multiple computers, such as a cloud system.

The information processing device 24 receives the detection result indicating whether or not a vehicle has passed over a bridge from the terminal device 22 via the external network. Furthermore, the information processing device 24 receives the determination result of the weight of the passing vehicle from the terminal device 22 via the external network. The information processing device 24 may also receive the result of identifying the vehicle type based on the weight of the passing vehicle, such as whether it is a small, medium, or large vehicle. Furthermore, the information processing device 24 receives the time when the vehicle passed over the bridge from the terminal device 22 via the external network.

The information processing device 24 may also receive time-series data of observed values representing displacement in the traveling direction or vertical direction at a target portion of the bridge for each of the multiple sensor devices 20 from the terminal device 22 via an external network. In this case, the information processing device 24, in place of the terminal device 22, performs the processes of detecting whether a vehicle has passed over the bridge, identifying the vehicle type, and identifying the time the vehicle passed over the bridge.

Figure 2 shows the placement of sensor devices 20 when viewed from the side of a bridge. The multiple sensor devices 20 are attached, for example, closer to the end of the bridge than the center of the bridge in the direction of travel. The multiple sensor devices 20 are attached, for example, on the underside of the bridge, near the abutments. This allows workers to easily attach the multiple sensor devices 20 to the bridge even after the bridge is completed. The multiple sensor devices 20 may be attached at any position in the direction of travel on the bridge. For example, some of the multiple sensor devices 20 may be attached to the center of the bridge in the direction of travel, although this may make installation more difficult for workers. Some of the multiple sensor devices 20 may also be attached to the side of the bridge. In this case, some of the multiple sensor devices 20 may be able to measure the vertical expansion and contraction of the bridge.

Figure 3 shows the arrangement of multiple sensor devices 20 when viewed from above a bridge. Each of the multiple sensor devices 20 is installed approximately in the center of a lane in the width direction of the bridge. The multiple sensor devices 20 are also installed in a straight line in the width direction at the same position in the direction of travel. If the bridge has multiple lanes, each of the multiple sensor devices 20 is installed in one of the multiple lanes. For example, if the bridge has four lanes, four sensor devices 20 are installed in one of the four lanes.

Figure 4 shows the functional configuration of the sensor device 20 and the terminal device 22. Each of the multiple sensor devices 20 has a displacement detection unit 32, a sensor control unit 34, and a sensor communication unit 36.

The displacement detection unit 32 uses, for example, an optical scale to detect the amount of change in distance between two points on the bridge that are the same in the width direction but different in the direction of travel. The sensor control unit 34 controls the light-emitting elements provided in the displacement detection unit 32 and acquires signals from the light-receiving elements. The sensor control unit 34 then controls the detection timing of observed values, acquires observed values, and stores the observed values. The sensor communication unit 36 communicates with the terminal device 22 via the network. In this embodiment, the sensor communication unit 36 sends and receives frames to and from the terminal device 22 using MAC addresses according to the Ethernet protocol.

The terminal device 22 has a lower-level communication unit 42, an information processing unit 44, and an upper-level communication unit 46.

The downstream communication unit 42 communicates with multiple terminal devices 22 via the network. In this embodiment, the downstream communication unit 42 sends and receives frames to and from each of the multiple sensor devices 20 using the MAC address according to the Ethernet protocol.

The information processing unit 44 has a processor and memory, and executes a predetermined operating system to manage the entire terminal device 22. Furthermore, the information processing unit 44 controls each of the multiple sensor devices 20 by executing a sensor management application program on the operating system. Furthermore, the information processing unit 44 controls the acquisition of groups of observation values from each of the multiple sensor devices 20, generates time-series data of the observation values for each of the multiple sensor devices 20, detects whether a vehicle has passed over a bridge, determines the weight of a passing vehicle, identifies the time when a vehicle passed over a bridge, and controls the transmission of the processing results to the information processing device 24.

The upper communication unit 46 communicates with the information processing device 24 via an external network. In this embodiment, the upper communication unit 46 communicates with the information processing device 24 via an external network of a cellular communication line such as LTE.

Figure 5 is a sequence diagram showing the exchange of information between the terminal device 22 and each of the multiple sensor devices 20.

When observing displacement in the travel direction or vertical direction on a bridge, the terminal device 22 periodically sends detection requests to each of the multiple sensor devices 20 (S11, S13, S15). For example, the terminal device 22 generates a message including a detection request, generates a packet including the generated message, and broadcasts a frame including the generated packet to the multiple sensor devices 20.

When each of the multiple sensor devices 20 receives a detection request, it transmits a response indicating that it has received the detection request to the terminal device 22 (S12, S14, S16). Furthermore, when each of the multiple sensor devices 20 receives a detection request, it detects observed values at predetermined time intervals and stores the detected observed value groups.

For example, the terminal device 22 sends a detection request to each of the multiple sensor devices 20 every second. In this case, each of the multiple sensor devices 20 detects observed values 200 times, every 5 milliseconds, from the time when the detection request is received.

If the interval between detection requests is T seconds, the interval between observation value detections is Δt seconds, and the number of times an observation value is detected in response to one detection request is N, the terminal device 22 sets T = N x Δt. This allows each of the multiple sensor devices 20 to continuously detect observation values at Δt second intervals.

The terminal device 22 also periodically sends read requests to each of the multiple sensor devices 20. When each of the multiple sensor devices 20 receives a read request, it sends the group of observed values it has stored to the terminal device 22 via the network (S14, S16).

For example, after the second detection request, the terminal device 22 transmits a message including a detection request and a read request to the multiple sensor devices 20 (S13, S15). When each of the multiple sensor devices 20 receives a read request, it transmits a group of observed values detected in response to the immediately preceding detection request to the terminal device 22 (S14, S16).

This vehicle detection system 10 can operate each of the multiple sensor devices 20 in synchronization with a detection request sent from the terminal device 22. This allows the vehicle detection system 10 to convert the time series data of multiple observation values from the multiple sensor devices 20 into data without time lag. This allows the vehicle detection system 10 to accurately detect that a vehicle has passed over a bridge based on the time series data of multiple observation values from the multiple sensor devices 20.

Furthermore, such a vehicle detection system 10 can synchronize and operate multiple sensor devices 20 in response to detection requests periodically sent from the terminal device 22. Therefore, the vehicle detection system 10 can synchronize and operate multiple sensor devices 20 efficiently with a small amount of data. Furthermore, the vehicle detection system 10 uses a proprietary protocol instead of TCP as the data transfer protocol. This allows the vehicle detection system 10 to reduce redundant data contained in packet headers, etc. Therefore, the vehicle detection system 10 can eliminate communication bandwidth congestion and send detection requests to each of the multiple sensor devices 20 reliably and in a short time. The proprietary protocol will be described later with reference to Figures 12 and 13.

Figure 6 shows a first example of the functional configuration for executing processes such as detecting whether a vehicle has passed over a bridge in the information processing unit 44 of the terminal device 22. The information processing unit 44 includes an acquisition unit 62, a storage unit 64, a feature calculation unit 66, a determination unit 68, a time identification unit 70, a weight determination unit 72, and an output unit 74.

The acquisition unit 62 acquires time-series data of observed values representing displacement in the travel direction or vertical direction of the target portion of the bridge for each of the collected data from the multiple sensor devices 20. In this embodiment, the observed values are the amount of expansion and contraction in the travel direction of the target portion.

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

The memory unit 64 stores the time series data of the observed values for each of the multiple sensor devices 20 acquired by the acquisition unit 62.

The feature calculation unit 66 extracts the time series data of observed values stored in the storage unit 64 for each of the multiple sensor devices 20 for each predetermined time unit. Then, the feature calculation unit 66 calculates a feature corresponding to the magnitude of the peak waveform in the time series data of observed values for each of the multiple sensor devices 20 for each extracted time unit.

The time unit of the extracted time series data of observed values is at least longer than the time from when the change in the expansion/contraction amount in the travel direction of the portion of the bridge being measured due to the passage of a vehicle begins to when the change ends. The feature calculation unit 66 may also overlap two adjacent time units in time. For example, the feature calculation unit 66 may overlap the latter half of a first time unit with the former half of a second time unit following the first time unit, and calculate feature amounts for each of the multiple sensor devices 20 for each time unit.

The feature calculation unit 66 detects either an upwardly convex waveform or a downwardly convex waveform contained in the time series data as a peak waveform. In this embodiment, when detecting an upwardly convex peak waveform, the upper value is considered to be greater than the lower value, and when detecting a downwardly convex peak waveform, the lower value is considered to be greater than the upper value.

For example, the feature calculation unit 66 has a moving average unit 80, a difference calculation unit 82, and a peak value detection unit 84.

The moving average unit 80 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 for each of the multiple sensor devices 20. The time window may be represented by the number of consecutive observed values for which the moving average is calculated. The time window may also be represented by time. When the time window is represented by time, the moving average unit 80 calculates the moving average using the number of observed values obtained by dividing the time window by the sample interval.

The moving average unit 80 may calculate time series data of moving average values by performing a simple moving average on the time series data of observed values. In other words, the moving average unit 80 may add up all the observed values included in the time window, for example, N, and divide the result by N to calculate the moving average value.

The moving average unit 80 may also calculate time series data of moving average values by performing a weighted moving average on the time series data of observed values. That is, the moving average unit 80 may multiply each of the number of observed values included in the time window by a predetermined weight, add up all N weighted observed values, and divide the sum by N to calculate the moving average value.

The moving average unit 80 may also calculate time series data of moving average values by taking a moving average of the time series data of observed values using an FIR (Finite Impulse Response) filter. The moving average unit 80 may also calculate time series data of moving average values by performing a convolution operation on the time series data of observed values with time series window function data of a time length corresponding to the time window.

The difference calculation unit 82 acquires time series data of observed values and time series data of moving average values calculated by the moving average unit 80 for each of the multiple sensor devices 20. The difference calculation unit 82 calculates the difference between the observed value and the moving average value for each sample, thereby calculating time series data of difference values that represent the difference between the observed value and the moving average value. For example, the difference calculation unit 82 calculates time series data of difference values by subtracting the moving average value from the observed value.

The peak value detection unit 84 detects peak waveforms in the time-series data of difference values for each of the multiple sensor devices 20. Furthermore, the peak value detection unit 84 detects peak values, which are the difference values of the peak points of the detected peak waveforms. For example, the peak value detection unit 84 detects, as a peak waveform, a continuous range of the time-series data of difference values that is greater than a predetermined value. Then, the peak value detection unit 84 detects, as a peak point, the point at which the maximum observed value is obtained within the continuous range that is greater than the predetermined value.

The feature calculation unit 66 outputs the peak value calculated for each of the multiple sensor devices 20 for each time unit as a feature. Note that if a peak waveform cannot be detected, the feature calculation unit 66 may output the feature as 0, a negative value, or a predetermined value.

The determination unit 68 acquires feature quantities for each of the multiple sensor devices 20. A threshold value is set in advance for the determination unit 68. The determination unit 68 also compares the feature quantity for each of the multiple sensor devices 20 with the preset threshold value. If the feature quantity of any of the multiple sensor devices 20 is greater than the threshold value, the determination unit 68 determines that a vehicle has passed over a bridge in the corresponding time unit.

Note that a bridge may have multiple lanes, and each of the multiple sensor devices 20 may be installed in one of the multiple lanes. When it is determined that a vehicle has passed over the bridge in the corresponding time unit, the determination unit 68 identifies the largest maximum feature value among the feature values of the multiple sensor devices 20. The determination unit 68 then determines that the vehicle has passed over the lane in which the sensor device 20 that provided the identified maximum feature value is installed.

When the determination unit 68 determines that the vehicle has passed over a bridge, the time determination unit 70 determines the time at which the vehicle passed over the bridge. For example, the time determination unit 70 determines the time of the peak point in the peak waveform.

When the weight determination unit 72 determines that a vehicle has crossed a bridge in the corresponding time unit, it determines the weight of the vehicle based on the magnitude of the maximum feature amount. For example, the weight determination unit 72 determines whether the vehicle is a small, medium, or large vehicle based on the magnitude of the maximum feature amount. For example, the weight determination unit 72 determines that the vehicle is a small vehicle if the maximum feature amount is smaller than a first determination value, a medium vehicle if the maximum feature amount is equal to or greater than the first determination value but smaller than a second determination value, and a large vehicle if the maximum feature amount is equal to or greater than the second determination value.

The output unit 74 transmits the results of the vehicle passage determination made by the determination unit 68 for each unit time, the time at which the vehicle passed over the bridge identified by the time determination unit 70, and the vehicle weight determination made by the weight determination unit 72 to the information processing device 24 via an external network.

Figure 7 shows an example of time series data of observed values for a bridge with two lanes, an inbound lane and an outbound lane.

In the example of Figure 7, the information processing unit 44 detects peak waveforms at times t1, t2, and t3. At times t1 and t2, the feature amount for the outbound lane is greater than the feature amount for the inbound lane, so the information processing unit 44 determines that the vehicle has passed through the outbound lane and determines the vehicle weight based on the feature amount for the outbound lane. Furthermore, at time t3, the feature amount for the inbound lane is greater than the feature amount for the outbound lane, so the information processing unit 44 determines that the vehicle has passed through the inbound lane and determines the vehicle weight based on the feature amount for the inbound lane.

Figure 8 shows an example of time series data of observed values detected from each of multiple sensor devices 20.

When a vehicle passes over a bridge, the positions of the multiple sensor devices 20 on the bridge expand and contract in the direction of travel of the vehicle. Because the lane through which the vehicle passed sinks the lowest, the amplitude of the expansion and contraction of the lane through which the vehicle passed is the largest, and the amplitude of the expansion and contraction decreases as the lane becomes farther away from the lane through which the vehicle passed. Therefore, the information processing unit 44 can determine which lane the vehicle passed over by comparing the amplitude of the expansion and contraction detected almost simultaneously for each lane. However, if multiple sensor devices 20 detect the expansion and contraction of the bridge at different times, the information processing unit 44 cannot determine which lane the vehicle passed over.

In contrast, the terminal device 22 according to this embodiment periodically transmits detection requests to the multiple sensor devices 20. When each of the multiple sensor devices 20 receives a detection request, it detects observed values at predetermined time intervals and transmits the detected observed values at the predetermined time intervals to the terminal device 22. This allows the multiple sensor devices 20 to operate at the time managed by the terminal device 22. Therefore, the information processing unit 44 can accurately determine the timing of vehicle passage and which lane the vehicle has passed through.

Figure 9 is a diagram showing a second example of the functional configuration for executing processes such as detecting whether a vehicle has passed over a bridge in the information processing unit 44 of the terminal device 22. The feature calculation unit 66 may have the configuration shown in Figure 9 instead of the configuration shown in Figure 6. That is, the feature calculation unit 66 may have a configuration including a moving average unit 80, a peak point detection unit 86, and an area calculation unit 88.

The moving average unit 80 performs processing similar to that configured in Figure 6.

The peak point detection unit 86 detects peak points of peak waveforms in the time series data of observed values for each of the multiple sensor devices 20. For example, the peak point detection unit 86 may detect, as a peak waveform, a continuous range of the time series data of observed values that is greater than a predetermined value. The peak point detection unit 86 then detects, as a peak point, the point at which the largest observed value is obtained within the continuous range that is greater than the predetermined value.

For each of the multiple sensor devices 20, the area calculation unit 88 calculates the area of a triangle connecting the peak point, the closest point before the peak where the time series data of the observed value intersects with the time series data of the moving average value, and the closest point after the peak where the time series data of the observed value intersects with the time series data of the moving average value in a graph with time on the horizontal axis and observed value on the vertical axis. The area calculation unit 88 then outputs the calculated area as a feature for each of the multiple sensor devices 20.

Figure 10 shows a graph with time on the horizontal axis and observed values on the vertical axis.

The area calculation unit 88 calculates the area of a triangle on a graph such as that shown in Figure 10 for the peak waveform. The triangle has three vertices: the peak point, a first point, and a second point. The first point is the closest point in time before the peak point among the points where the time series data of the observed value and the time series data of the moving average intersect. The second point is the closest point in time after the peak point among the points where the time series data of the observed value and the time series data of the moving average intersect.

The area of such a triangle represents the amount of expansion and contraction of the bridge when a vehicle passes over it. When a vehicle passes over it at a relatively slow speed, the time period over which the expansion and contraction fluctuates is long, but the amplitude of the expansion and contraction is small. On the other hand, when a vehicle passes over it at a relatively high speed, the amplitude of the expansion and contraction is large, but the time period over which the expansion and contraction fluctuates is short.

By calculating the area of such a triangle as a feature, the feature calculation unit 66 can reliably detect whether a vehicle has passed and its weight, regardless of the vehicle's passing speed. However, if multiple vehicles pass over a bridge within a short time interval, the triangular waveforms may overlap. Therefore, by calculating the peak value as a feature rather than the triangular area as in the configuration shown in Figure 6, the feature calculation unit 66 can accurately detect whether a vehicle has passed and its weight, even if multiple vehicles pass over a bridge within a short time interval, because the peak waveforms are separated in time.

Figure 11 shows a third example of the functional configuration for executing processing such as detection of whether a vehicle has passed over a bridge in the information processing unit 44 of the terminal device 22. As shown in Figure 11, the feature calculation unit 66 may be configured to include a moving average unit 80, a difference calculation unit 82, a peak point detection unit 86, and an area calculation unit 88.

The moving average unit 80 and difference calculation unit 82 perform processing similar to that shown in Figure 6.

The peak point detection unit 86 detects peak points of peak waveforms in the time series data of difference values for each of the multiple sensor devices 20. For example, the peak point detection unit 86 may detect, as a peak waveform, a continuous range of the time series data of difference values that is greater than a predetermined value. The peak point detection unit 86 then detects, as a peak point, the point at which the largest difference value is obtained within the continuous range that is greater than the predetermined value.

For each of the multiple sensor devices 20, the area calculation unit 88 calculates the area of a triangle connecting the peak point, the closest point before the peak where the time series data for the difference value intersects with the time series data for the moving average value, and the closest point after the peak where the time series data for the difference value intersects with the time series data for the moving average value in a graph showing time on the horizontal axis and difference values on the vertical axis. The area calculation unit 88 then outputs the calculated area as a feature for each of the multiple sensor devices 20.

As with the second example, the area of the triangle in the third example represents the amount of expansion and contraction of the bridge when a vehicle passes over it. Therefore, by calculating the area of such a triangle as a feature, the feature calculation unit 66 can reliably detect whether a vehicle is passing and its weight, regardless of the vehicle's passing speed.

Figure 12 shows the functional configuration for generating time series data of observed values of the terminal device 22.

The terminal device 22 has a processor and memory, and runs a specific operating system. The terminal device 22 also runs a sensor management application program on the operating system.

The terminal device 22 functions as a sensor management unit 92 by executing a sensor management application program on the operating system. Furthermore, the terminal device 22 functions as a network interface unit 94 and a transport/Internet unit 96 by executing the operating system.

The sensor management unit 92 controls the operation of each of the multiple sensor devices 20 by sending messages to each of the multiple sensor devices 20. The sensor management unit 92 also acquires a group of observation values from each of the multiple sensor devices 20 and generates time-series data of the observation values for each of the multiple sensor devices 20. The generated time-series data of the observation values for each of the multiple sensor devices 20 is then acquired by the acquisition unit 62 shown in Figures 6, 9, and 11.

The sensor management unit 92 also manages a conversion table. The conversion table stores the correspondence between sensor identification information and physical addresses for each of the multiple sensor devices 20. The sensor identification information is information used to identify each of the multiple sensor devices 20 in the vehicle detection system 10. The physical address is information that physically identifies each of the multiple sensor devices 20 on the network, such as a MAC address.

The network interface unit 94 is a functional block for controlling the exchange of information over a network connecting multiple sensor devices 20 and terminal devices 22, and performs processing at the network interface layer in the hierarchical structure of the TCP/IP communication protocol. The network interface layer is the communication protocol closest to the physical layer.

The transport/Internet unit 96 is a functional block that mediates the exchange of information between the network interface unit 94 and the sensor management application program. The transport/Internet unit 96 performs processing at the internet layer and transport layer in the hierarchical structure of the TCP/IP communication protocol. However, the transport/Internet unit 96 executes a unique sensor network transport protocol that combines the internet layer and transport layer, which differs from the TCP/IP communication protocol.

Figure 13 shows the hierarchical structure of the communication protocol between the sensor device 20 and the terminal device 22.

The communication protocol between the sensor device 20 and the terminal device 22 is defined by the Ethernet protocol, the sensor network transport protocol, and the sensor management application.

The Ethernet protocol is similar to the network interface layer specifications in the TCP/IP protocol. Processing corresponding to the Ethernet protocol is performed by the network interface unit 94.

The sensor network transport protocol is a protocol uniquely defined in this embodiment. Processing corresponding to the sensor network transport protocol is performed by the transport/Internet unit 96.

The sensor management application is a protocol defined for exchanging information with the sensor device 20, and is implemented by the sensor management unit 92.

The communication protocol of the sensor management application defines the message content. The message content includes requests to the sensor device 20, responses from the sensor device 20, and sets of observed values.

The communication protocol of the sensor management application also defines the data structure of messages. Messages include sensor identification information, data size, message content, and CRC. The sensor identification information is information that identifies the sensor device 20 that sends the message or the sensor device 20 that generated the message. The CRC is an error correction code.

The sensor network transport protocol defines the data structure of a packet. A packet includes a physical address, data size, message content, and CRC. The physical address is an address assigned to the sensor device 20 that sends the packet or the sensor device 20 that generated the packet. The packet is similar to an IP packet defined by TCP/IP.

The Ethernet protocol defines the data structure of a frame. A frame contains DstMACAddr, SrcMACAddr, Type, Payload, and FCS. DstMACAddr indicates the physical address of the destination. SrcMACAddr indicates the physical address of the sender. Type indicates the frame type. Payload contains information such as the packet content. FCS is an error correction code.

When the terminal device 22 transmits information to the first sensor device 20-1, which is one of the multiple sensor devices 20, the following processing is performed.

First, the sensor management unit 92 generates a message addressed to sensor identification information that identifies the first sensor device 20-1. Next, the sensor management unit 92 replaces the address in the generated message with the physical address of the first sensor device 20-1 by referencing a conversion table, and passes the message to the transport/Internet unit 96.

The transport/Internet unit 96 then generates a packet whose header contains the physical address of the first sensor device 20-1 and whose payload contains the message obtained from the sensor management unit 92. The transport/Internet unit 96 then passes the generated packet to the network interface unit 94.

The network interface unit 94 then generates a frame whose header includes a physical address identifying the first sensor device 20-1 and whose payload includes the packet obtained from the transport/Internet unit 96. The network interface unit 94 then transmits the generated frame to each of the multiple sensor devices 20.

Furthermore, when the terminal device 22 receives information from the first sensor device 20-1, the following processing is performed.

First, the network interface unit 94 receives a frame from the first sensor device 20-1. Next, the network interface unit 94 passes the packet contained in the payload of the received frame to the transport/Internet unit 96.

The transport/Internet unit 96 then acquires the packet from the network interface unit 94. The transport/Internet unit 96 then passes the message contained in the payload of the acquired packet to the sensor management unit 92.

The sensor management unit 92 then refers to a conversion table and replaces the source physical address included in the message with the identification information of the first sensor device 20-1. The sensor management unit 92 then executes processing according to the message with the replaced source.

In the multiple sensor devices 20 and terminal devices 22 that perform this type of processing, the sensor management unit 92 uses a conversion table to convert sensor identification information to physical addresses. As a result, the multiple sensor devices 20 and terminal devices 22 do not need to include, for example, IP addresses in their packets, thereby reducing the amount of redundant data included in the packets. Furthermore, the transport/Internet unit 96 does not perform communication with sensor management applications running on the operating system. Therefore, the transport/Internet unit 96 does not need to include numbers or other information for identifying applications managed by the TCP/IP transport layer or the like in the packets, or manage related information, thereby reducing the amount of redundant data included in the packets.

In this way, the vehicle detection system 10 can reduce redundant data contained in packet headers, etc. This allows the vehicle detection system 10 to eliminate communication bandwidth congestion and send detection requests to each of the multiple sensor devices 20 reliably and in a short time.

Figure 14 is a diagram showing the hardware configuration of the information processing unit 44. As an example, the information processing unit 44 is realized by a device with a hardware configuration similar to that of a general computer. Note that the terminal device 22 may also have a hardware configuration similar to that shown in Figure 14. The information processing unit 44 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.

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 provides overall control over the operation of each component constituting the information processing unit 44. The CPU 301 also operates the operation device 302, display device 303, communication device 307, etc. in cooperation with the programs.

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

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

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

The auxiliary storage device 306 is a rewritable storage device, such as a semiconductor storage medium such as flash memory, or a magnetically or optically recordable storage medium. The auxiliary storage device 306 stores programs used to control the information processing unit 44.

The communication device 307 sends and receives data to and from other devices. The communication device 307 may also send and receive data to and from a server or the like via a network.

The program executed by the information processing unit 44 may be stored on a computer connected to a network such as the Internet and provided by downloading it via the network. The program executed by the information processing unit 44 may also be provided in advance on a portable storage medium or the like.

The program executed by the information processing unit 44 has a modular configuration including an acquisition module, a feature calculation module, a determination module, a time identification module, a weight determination module, and an output module. The CPU 301 reads this program from a storage medium or the like and loads each of the above modules into the main memory device 305. By executing this program, the CPU 301 functions as the acquisition unit 62, feature calculation unit 66, determination unit 68, time identification unit 70, weight determination unit 72, and output unit 74. By executing this program, the CPU 301 also causes the main memory device 305 or auxiliary memory device 306 to function as the memory unit 64. Note that some or all of the acquisition unit 62, feature calculation unit 66, determination unit 68, time identification unit 70, weight determination unit 72, and output unit 74 may be configured using hardware.

The above describes embodiments of the present invention, but 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.

REFERENCE SIGNS LIST 10 Vehicle detection system 20 Sensor device 22 Terminal device 24 Information processing device 32 Displacement detection unit 34 Sensor control unit 36 Sensor communication unit 42 Lower side communication unit 44 Information processing unit 46 Upper side communication unit 62 Acquisition unit 64 Storage unit 66 Feature amount calculation unit 68 Determination unit 70 Time identification unit 72 Weight determination unit 74 Output unit 80 Moving average unit 82 Difference calculation unit 84 Peak value detection unit 86 Peak point detection unit 88 Area calculation unit

Claims (14)

a plurality of sensor devices provided on a bridge to detect observed values representing displacement of the bridge;
a terminal device that collects the observed values from each of the plurality of sensor devices;
an information processing unit that detects that a vehicle has passed over the bridge based on time-series data of the observed values of each of the plurality of sensor devices collected by the terminal device;
Equipped with
the terminal device transmits a detection request to the plurality of sensor devices every T seconds ;
each of the plurality of sensor devices detects the observed value N times every Δt seconds from the timing of receiving the detection request, and stores a group of the detected observed values;
Δt is a positive real number, N is an integer equal to or greater than 2, and T is N×Δt;
the terminal device periodically transmits a read request to the plurality of sensor devices;
When the read request is received, each of the plurality of sensor devices transmits the group of observed values stored therein to the terminal device. The vehicle detection system according to claim 1 , wherein each of the plurality of sensor devices detects, as the displacement , an amount of expansion or contraction of a position on the bridge where the sensor device is provided. The information processing unit
an acquisition unit that acquires time-series data of the observed values for each of the plurality of sensor devices;
a feature calculation unit that calculates a feature according to the magnitude of a peak waveform in the time-series data of the observed value;
a determination unit that detects that the vehicle has passed over the bridge based on the feature amount;
3. The vehicle detection system of claim 1, further comprising: The feature amount calculation unit
a moving average unit that calculates time series data of a moving average value by performing a moving average on the time series data of the observed values using a preset time window for each of the plurality of sensor devices;
a difference calculation unit that calculates time series data of difference values representing differences between the observed values and the moving average values for each of the plurality of sensor devices;
a peak value detection unit that detects, for each of the plurality of sensor devices, a peak value that is the observed value at a peak point of a peak waveform in the time-series data of the difference values and outputs the detected peak value as the feature amount;
4. The vehicle detection system of claim 3, comprising: a plurality of sensor devices provided on a bridge to detect observed values representing displacement of the bridge;
a terminal device that collects the observed values from each of the plurality of sensor devices;
an information processing unit that detects that a vehicle has passed over the bridge based on time-series data of the observed values of each of the plurality of sensor devices collected by the terminal device;
Equipped with
the terminal device periodically transmits detection requests to the plurality of sensor devices;
When each of the plurality of sensor devices receives the detection request, the sensor devices detect the observed values at predetermined time intervals and transmit the detected observed values at predetermined time intervals to the terminal device;
The information processing unit
an acquisition unit that acquires time-series data of the observed values for each of the plurality of sensor devices;
a feature calculation unit that calculates a feature according to the magnitude of a peak waveform in the time-series data of the observed value;
a determination unit that detects that the vehicle has passed over the bridge based on the feature amount;
and
The feature amount calculation unit
a moving average unit that calculates time series data of a moving average value by performing a moving average on the time series data of the observed values using a preset time window for each of the plurality of sensor devices;
a peak point detection unit that detects a peak point of a peak waveform in the time series data of the observation value for each of the plurality of sensor devices;
an area calculation unit that calculates an area of a triangle connecting the peak point, a point before the peak point where time series data of the observed value intersects with the time series data of the moving average value, and a point after the peak point where time series data of the observed value intersects with the time series data of the moving average value in a graph that represents time on the horizontal axis and the observed value on the vertical axis for each of the plurality of sensor devices, and outputs the calculated area as the feature;
A vehicle detection system having : a plurality of sensor devices provided on a bridge to detect observed values representing displacement of the bridge;
a terminal device that collects the observed values from each of the plurality of sensor devices;
an information processing unit that detects that a vehicle has passed over the bridge based on time-series data of the observed values of each of the plurality of sensor devices collected by the terminal device;
Equipped with
the terminal device periodically transmits detection requests to the plurality of sensor devices;
When each of the plurality of sensor devices receives the detection request, the sensor devices detect the observed values at predetermined time intervals and transmit the detected observed values at predetermined time intervals to the terminal device;
The information processing unit
an acquisition unit that acquires time-series data of the observed values for each of the plurality of sensor devices;
a feature calculation unit that calculates a feature according to the magnitude of a peak waveform in the time-series data of the observed value;
a determination unit that detects that the vehicle has passed over the bridge based on the feature amount;
and
The feature amount calculation unit
a moving average unit that calculates time series data of a moving average value by performing a moving average on the time series data of the observed values using a preset time window for each of the plurality of sensor devices;
a difference calculation unit that calculates time series data of difference values representing differences between the observed values and the moving average values for each of the plurality of sensor devices;
a peak point detection unit that detects a peak point of a peak waveform in the time series data of the difference values for each of the plurality of sensor devices;
an area calculation unit that calculates an area of a triangle connecting the peak point, a point before the peak point where the time series data of the difference value intersects with the time series data of the moving average value, and a point after the peak point where the time series data of the difference value intersects with the time series data of the moving average value in a graph that represents time on the horizontal axis and the difference value on the vertical axis for each of the plurality of sensor devices, and outputs the calculated area as the feature amount;
A vehicle detection system having : The vehicle detection system according to claim 3 , wherein the determination unit determines that the vehicle has passed over the bridge when the feature amount for any of the plurality of sensor devices is greater than a threshold value. the bridge has a plurality of lanes;
each of the plurality of sensor devices is provided in one of the plurality of lanes;
8. The vehicle detection system according to claim 7, wherein, when the feature amount for any of the plurality of sensor devices is greater than the threshold value, the determination unit identifies a maximum feature amount that is the largest among the feature amounts for each of the plurality of sensor devices, and determines that the vehicle has passed through a lane in which a sensor device that obtained the identified maximum feature amount is installed. The vehicle detection system according to claim 8 , further comprising: a weight determination unit that, when it is determined that the vehicle has passed over the bridge, determines a weight of the vehicle according to the magnitude of the maximum feature amount. The vehicle detection system according to claim 1 , wherein the information processing unit is realized by the terminal device. further comprising an information processing device connected to the terminal device via an external network;
The vehicle detection system according to claim 10 , wherein the terminal device transmits the detection result by the information processing unit to the information processing device via the external network. Each of the plurality of sensor devices is assigned a unique physical address that can be identified on the network and sensor identification information that is identification information that can be identified in the terminal device,
The terminal device
By executing a sensor management application program on the operating system, the sensor management unit functions as a sensor management unit;
By executing the operating system, the device functions as a network interface unit that executes processing at a network interface layer and a transport/Internet unit that mediates the exchange of information between the network interface unit and the sensor management application program;
The vehicle detection system according to claim 1 , wherein the sensor management unit manages a conversion table that stores a correspondence between the sensor identification information and the physical address for each of the plurality of sensor devices. When the terminal device transmits information to a first sensor device among the plurality of sensor devices,
the sensor management unit generates a message addressed to the sensor identification information that identifies the first sensor device;
the sensor management unit replaces the destination in the generated message with the physical address of the first sensor device by referring to the conversion table, and passes the message to the transport/Internet unit;
the transport/Internet unit generates a packet including the physical address of the first sensor device in a header and the message acquired from the sensor management unit in a payload, and passes the generated packet to the network interface unit ;
13. The vehicle detection system according to claim 12, wherein the network interface unit generates a frame including the physical address that identifies the first sensor device in a header and the packet acquired from the transport/Internet unit in a payload, and transmits the generated frame to each of the plurality of sensor devices. When the terminal device receives information from the first sensor device,
the network interface unit receives the frame from the first sensor device and passes the packet included in the payload of the received frame to the transport/Internet unit;
the transport/Internet unit acquires the packet from the network interface unit, and passes the message included in the payload of the acquired packet to the sensor management unit;
the sensor management unit replaces the physical address of the sender included in the message with the identification information of the first sensor device by referring to the conversion table;
The vehicle detection system according to claim 13 , wherein the sensor management unit executes a process according to the message whose sender has been replaced.