JP2021174043A - Object detection system - Google Patents

Abstract

To reliably detect an object on a road even in bad weather.SOLUTION: An object detection system is applied to a road 2 having a structure formed by using pickets erected in an area where the road 2 is constructed and a precast concrete slab (roadbed) to be placed on the pickets. The object detection system inputs a distribution of weights into a learning model so as to detect objects, as well as, to detect positions, movement directions and movement speeds of the respective objects as of when having detected, which distribution of weights is measured by load sensors 6 attached to the pickets and acquired via a communication device 10, and which learning model receives the distribution of weights as of when the objects (vehicle 7 or person 8) existing on a road as an input and outputs presence or absence of the object on the road. The communication device 10 notifies the vehicle 7 of approach of the object, and also notifies the person 8 by presentation on a sign board 9. When snow is accumulated, input is performed into the learning model after performing correction to subtract from the measured load, a load of the snow applied onto the roadbed.SELECTED DRAWING: Figure 2

Description

The present invention relates to an object detection system, particularly to detect an object on a road whose road surface is constructed of precast concrete slabs.

Conventionally, there is a technique for detecting an object on the road such as a vehicle or a human using a camera or a laser. For example, Patent Document 1 proposes a technique for detecting a vehicle in a monitoring area using a laser radar.

JP-A-2019-207654

However, since the camera uses visible light, it becomes difficult to see the surroundings in bad weather such as heavy rain, snow, and fog, and the detection function of objects on the road deteriorates. In laser radar, the laser is reflected and scattered by raindrops, snow, and fog. That is, even when a laser radar is used, the detection function of an object on the road may deteriorate in bad weather.

An object of the present invention is to enable more reliable detection of an object on the road even in bad weather.

The object detection system according to the present invention detects an object on a road having a structure formed by using a pile erected in an area where a road is constructed and a precast concrete slab placed on the pile. In the object detection system, a plurality of sensor means arranged on the road, a sensor information acquisition means for acquiring sensor information including at least the sensor value of the sensor means, and a road surface obtained from the sensor value of the sensor means. It is characterized by having a detecting means for detecting an object on the road by referring to such a load.

Further, when the load applied to the road surface is gradually increased or decreased, the detecting means refers to a load obtained by subtracting the load obtained from the sensor value of the sensor means when there is no object on the road surface. It is characterized by detecting an object on the road.

Further, the detection means is a learning model that inputs the distribution of the load applied to the pile when the object is present on the road when the sensor means is attached to the pile, and outputs the presence or absence of the object. It is characterized in that an object on the road is detected by inputting the distribution of the load applied to the pile obtained from the sensor value of the sensor means.

Further, the detection means for detecting the position, the moving direction, and the moving speed of the object detected by the detecting means by referring to the distribution of the load applied to the road surface obtained from the sensor value of the sensor means and the transition thereof, and the detection. It is characterized by having a reporting means for notifying other objects located around the object detected by the means of the detection of the object.

Further, the reporting means has a discriminating means for discriminating the type of the object detected by the detecting means from the load applied to the road surface obtained from the sensor value of the sensor means, and the reporting means discriminates the object as a person by the discriminating means. If so, the presence of the person is notified to the vehicle approaching the person, and if the object is determined to be a vehicle by the discrimination means, the person located in the traveling direction of the vehicle is notified of the approach of the vehicle. It is characterized by doing.

Further, the sensor means is a load sensor or a sensor that measures sensor data that can be converted into a load.

According to the present invention, an object on the road can be detected more reliably even in bad weather.

It is a perspective view which shows the structure of the road in this embodiment. It is an overall block diagram of the object detection system in this embodiment. It is a block block diagram of the communication device and the object detection device in this embodiment. It is a figure which shows an example of the teacher data used for learning to the learning model in this embodiment. It is a figure which shows another example of the teacher data used for learning to the learning model in this embodiment. It is a flowchart which shows the object detection processing in this embodiment. It is a figure which shows the graph which shows the example of the transition of the load measured by one load sensor in the fine weather. It is a figure which shows the graph which shows the example of the transition of the load measured by one load sensor when there is snow cover.

Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings.

FIG. 1 is a perspective view showing a road structure according to the present embodiment. The precast concrete slab (hereinafter referred to as “road slab”) 1 is a plate-shaped concrete manufactured in advance in a shape and size that can be transported in a factory or the like for assembling and installing on site. The size of the road slab 1 is assumed to be 1.2 m square, but it is not necessary to limit it to this size. The road slab 1 in the present embodiment is formed in a rectangular shape.

In the road 2 in the present embodiment, as shown in FIG. 1, the road slab 1 is laid side by side on the pile 3 erected on the road body 4, and each corner of the road slab 1 is laid with a pile 3 with bolts. It has a structure that is fixed to and formed. The “road body” 4 refers to the lowest layer of the road structure formed by digging into the area where the road is constructed. Since the road slab 1 is laid on the pile 3 erected on the road body 4, it is necessary to dig down at least the thickness of the road slab 1. In the present embodiment, as shown in FIG. 1, the space 5 is dug deeply so as to form a space 5 between the road slab 1 and the road body 4.

A load sensor 6 is attached to each pile 3. The load sensor 6 constantly measures the load applied to the road slab 1 mounted on the pile 3. In this embodiment, an example of mounting on the upper part of the pile 3 is shown, but the mounting position is not limited to this example as long as the load can be measured, and the pile 3 may be mounted at another place such as the top. Alternatively, it may be provided by incorporating it into the front surface, the back surface, or the inside of the road slab 1.

FIG. 2 is an overall configuration diagram of the object detection system according to the present embodiment. Further, FIG. 2 shows the situation around the road 2. Vehicles 7 and people 8 corresponding to the objects to be detected are shown on the road. Further, at the installation position of the pedestrian crossing, a sign board 9 for providing information to the crossing person 8 is installed. Further, FIG. 2 shows a load sensor 6 attached to a pile (not shown), a communication device 10 installed near the road 2, and an object detection device installed at a remote location on the road 2. 20 is shown. The communication device 10 is connected to the load sensor 6 and the sign plate 9 installed in the vicinity by wire or wirelessly, and collects the sensor data measured by each connected load sensor 6 to the object detection device 20. At the same time as transmitting, it is notified that an object has been detected in the vicinity in response to an instruction from the object detection device 20. The object detection device 20 detects an object on the road by analyzing sensor information transmitted by wire or wirelessly from each of the plurality of communication devices 10 installed around the road 2. In the present embodiment, it is assumed that the function provided by the object detection device 20 described later is provided on the cloud, but the present invention is not limited to this, and one or more server computers or supercomputers are placed outside the cloud, for example. It may be realized by installing it on a road management sensor or the like.

Although a plurality of load sensors 6 and communication devices 10 are installed on the road 2, they operate in the same manner. Therefore, one each of the load sensor 6 and the communication device 10 is shown in FIG. 2 for convenience.

FIG. 3 is a block configuration diagram of the communication device and the object detection device according to the present embodiment. The components not used in the description in the present embodiment are omitted from the drawings.

The communication device 10 can be realized by a hardware configuration of a conventional general-purpose computer having a communication function. That is, the communication device 10 includes a processor, ROM, RAM, storage, and a network interface.

The communication device 10 includes a sensor data receiving unit 11, a sensor information transmitting unit 12, a detection information receiving unit 13, and a reporting unit 14. The sensor data receiving unit 11 collects sensor data from the connected load sensor 6. The sensor information transmission unit 12 transmits sensor information including at least the collected sensor data to the object detection device 20. The detection information receiving unit 13 receives the detection information sent when the object detection device 20 detects an object. The reporting unit 14 notifies other objects located around the detected object of the detection of the object according to the detected detection information sent.

Each component 11 to 14 in the communication device 10 is realized by a cooperative operation of a computer forming the communication device 10 and a program operated by a processor mounted on the computer.

The object detection device 20 can be realized by a hardware configuration such as a general-purpose server computer that has a communication function and has existed in the past. That is, the object detection device 20 includes a storage means such as a processor, a ROM, a RAM, a hardware disk drive (HDD), and a network interface.

The object detection device 20 includes a sensor information receiving unit 21, an object detection unit 22, a notification control unit 23, a sensor information storage unit 24, and a management information storage unit 25. The sensor information receiving unit 21 receives the sensor information transmitted from the communication device 10 and stores it in the sensor information storage unit 24. The object detection unit 22 detects an object on the road and detects the position of the object on the road by referring to the sensor information received by the sensor information receiving unit 21. Further, the object detection unit 22 detects the moving direction and moving speed of the object from the history of the sensor information stored in the sensor information storage unit 24. Further, when the object is detected, the object detection unit 22 determines the type of the detected object, that is, whether the object is a person or a vehicle. When an object is detected, the notification control unit 23 transmits the detection information to the communication device 10.

The management information storage unit 25 stores management information for managing the communication device 10, the sign plate 9, and the load sensor 6 installed on the road 2. The management information includes identification information of the communication device 10 and position information for specifying the position where the communication device 10 is installed as management information regarding the communication device 10. Further, as management information regarding the load sensor 6, identification information of the load sensor 6 and position information for specifying the position where the load sensor 6 is installed (when the position of the pile 3 is managed, the installed pile). Information that identifies 3) is included. Further, the management information regarding the sign board 9 includes identification information of the sign board 9 and position information for specifying the position where the sign board 9 is installed. Further, the management information includes information for associating each communication device 10 with the sign plate 9 and the load sensor 6 connected to the communication device 10.

Each component 21 to 23 in the object detection device 20 is realized by a cooperative operation of a computer forming the object detection device 20 and a program operated by a CPU mounted on the computer. Further, the storage units 24 and 25 are realized by the HDD mounted on the object detection device 20. Alternatively, RAM or an external storage means may be used via the network.

Further, the program used in the present embodiment can be provided not only by communication means but also by storing it in a computer-readable recording medium such as a CD-ROM or a USB memory. Programs provided from communication means and recording media are installed in a computer, and various processes are realized by sequentially executing the programs by the CPU of the computer.

If a camera or laser radar is used to detect an object on the road, the ability to detect the object may decrease in bad weather. On the other hand, in the present embodiment, since the object on the road is detected by the load applied to the road surface, the object on the road can be detected more reliably even in bad weather. Hereinafter, the operation in the present embodiment will be described.

In the present embodiment, the object detection unit 22 detects an object on the road by referring to the sensor information, but the object detection unit 22 detects the object by using a learning model formed in advance by machine learning. .. The learning of this learning model will be described with reference to FIGS. 4A and 4B.

4A and 4B (hereinafter collectively referred to as “FIG. 4”) correspond to conceptual diagrams showing teacher data used for learning a learning model. The learning model used in this embodiment inputs the distribution of the load applied to the pile 3 and outputs the presence / absence of detection of the object.

First, the viewpoint of FIG. 4 will be described. In FIG. 4, a part of the road 2 is cut out and shown. As shown in FIG. 4A (a), the road 2 is provided with a sidewalk 2a and a roadway 2b. The rectangle included in the road 2 is a road slab 1, and circular piles 3 are shown at each corner of the road slab 1. Further, in FIG. 4, the road 2 on the left side of the drawing shows the size and position of the vehicle 7 and the person 8, and the road 2 on the right side of the corresponding drawing shows the vehicle 7 and the person 8 at the positions shown on the left side. It shows the magnitude of the load measured by the load sensor when it is positioned. As shown in FIG. 4A (a), in the present embodiment, the load is shown in four stages for convenience. The load sensor 6 constantly measures the weight of the road slab 1 mounted on the pile 3 regardless of the presence or absence of an object, but the load measured in a state where no object exists on the road slab 1. Will be referred to as a "reference load". In FIG. 4, the pile 3 measuring the reference load is indicated by a white circle. Then, the magnitude of the measured load is divided into small, medium, and large by comparison with each predetermined threshold value. In FIG. 4, the heavier the pile 3, the darker the color.

In this embodiment, only the reference load may be subtracted from the load applied to the pile 3 to learn only by the load of the object. In the present embodiment, the latter, that is, the teacher data based only on the load of the object not including the reference load will be used.

Here, the learning model is trained using the (b) to (h) shown in FIG. 4 as teacher data. For example, by inputting the teacher data of (b) into the learning model, when the object is the person 8, the distribution of the load and the magnitude of the load when the person 8 is at the position shown in (b) are learned. Similarly, by inputting the teacher data of (c) to (e) into the learning model, when the object is the vehicle 7 and the vehicle 7 is the general vehicle 7a, the motorcycle 7b, and the large vehicle 7c (c). ) To (e), the load distribution and the magnitude of the load when the vehicles 7a to 7c are at the positions shown in (e) are learned. Further, since the plurality of vehicles continuously travel on the road 2, the teacher data (f) to (h) assuming the case where the plurality of vehicles 7 travel on the road 2 are used so as to cope with this case as well. Let the learning model train.

Since the type of vehicle does not have to be limited to the general vehicle 7a, the motorcycle 7b, and the large vehicle 7c shown in FIG. 4, other types of vehicles and vehicles of the same type but having different sizes and weights are used. By training the learning model based on the teacher data based on the above, the arrangement of a plurality of vehicles, and the traveling position (for example, near the sidewalk of the road 2), the detection accuracy of the object is improved.

The load sensor 6 constantly measures the load applied to the pile 3. The sensor data indicating the measured load (also referred to as “sensor value” or “load value”) is sent to the communication device 10. When the sensor data is sent from the load sensor 6, the communication device 10 is a sensor including the sensor data, the identification information of the load sensor 6 that measured the sensor data, the measurement date and time, and the position information for specifying the measured position. Information is generated and transmitted to the object detection device 20. The position information is also used by the object detection device 20 to specify the instruction destination of the report. The position information may be, for example, the identification information of the communication device 10 or the identification information of the load sensor 6.

When the sensor information is transmitted from the communication device 10, the object detection device 20 executes a process of detecting an object on the road based on the sensor information. Hereinafter, the object detection process according to the present embodiment will be described with reference to the flowchart shown in FIG. There may be a plurality of objects on the road 2, but here, for convenience of explanation, it is assumed that a predetermined range on the road is focused on and the objects are detected in that range. The predetermined range may be, for example, a range in which the load is measured by the load sensor 6 connected to one communication device 10. Further, when an object exists in the range, the description will be given focusing on the detection of one object. As described with reference to FIG. 4, the object detection unit 22 can detect all the objects included in the predetermined range by using the learning model.

In the object detection device 20, when the sensor information receiving unit 21 receives the sensor information corresponding to each load sensor 6 transmitted from the communication device 10, it stores it in the sensor information storage unit 24. The object detection unit 22 acquires the sensor information of the same measurement date and time in a predetermined range by extracting it from the sensor information storage unit 24 (step 110). Alternatively, it may be acquired directly from the sensor information receiving unit 21. The object detection unit 22 creates a load distribution as shown on the right side of the drawing shown in FIG. 4 with reference to the sensor value included in the sensor information (step 120). The arrangement of the load sensor 6 can be specified by comparing the sensor identification information included in the sensor information with the management information stored in the management information storage unit 25.

Subsequently, the object detection unit 22 performs a correction process for correcting the load represented by the created load distribution as necessary so that the object can be detected even in bad weather (step 130), but the correction process will be described later. Here, the subsequent processing will be described assuming that the correction processing has been completed.

The object detection unit 22 inputs the created load distribution to the learning model and determines whether or not an object exists on the road (step 140). If only the reference load is measured in all the piles 3 as shown in (a) of FIG. 4 in the created load distribution, in other words, if the load of the object is not detected, the object exists in a predetermined range. Will not. That is, the object detection unit 22 does not detect an object. On the other hand, when the created load distribution matches or is similar to any of the load distributions shown on the right side of the drawing of FIG. 4, the object detection unit 22 detects an object within a predetermined range. For example, when the load distribution created in step 120 is the same as or similar to the load distribution shown on the right side of the drawing of FIG. 4A (c), the object detection unit 22 detects an object within a predetermined range. Can be done. The detected object can be identified as a general vehicle 7a.

In the present embodiment, the object is detected not by simply referring to the load value measured by the load sensor 6, that is, by the degree of agreement of the load distribution, not by simply detecting whether the load is detected in a predetermined range. Therefore, it is desirable to make the learning model train the vehicle 7 and the person 8 to be detected by using more teacher data. As a result, it is possible to avoid erroneously detecting an object simply placed on the road as a vehicle 7 or a person 8.

If no object is detected within the predetermined range (N in step 150), the process proceeds to step 110 in order to acquire the next sensor information. When an object is detected in a predetermined range (Y in step 150), the object detection unit 22 subsequently determines the type of the object detected on the road (step 160). In the present embodiment, the object is discriminated by the load measured by the load sensor 6, that is, the weight. More specifically, the load point (center of gravity) applied to the road slab 1 is obtained from the load applied to the four piles 3 supporting the road slab 1 in which the load of the object is detected. Similarly, the load points are obtained for the other road slabs 1 in which the load of the object is detected, and the weight of the object is calculated from the load at the load points of each road slab 1. Since the weights of the vehicle 7 and the person 8 are clearly different, a predetermined threshold value is set, and the case where the weight is equal to or more than the threshold value is determined as the vehicle 7 and the case where the weight is less than the threshold value is determined as the person 8. The learning model may be made to output the type of the object.

When the type of the object is known, the object detection unit 22 calculates the position, the moving direction, and the traveling speed of the object (step 170). For the position of the object, the center point of the object is obtained from the position of the load point (center of gravity) applied to each road slab 1 in which the load of the object is detected, and the center point is detected as the position of the object. Further, once an object is detected in a predetermined range, it basically moves within the predetermined range after being detected. The object detection unit 22 detects an object as described above based on the received sensor information, but since the sensor information storage unit 24 includes the sensor information received in the past, it is based on the past sensor information. The direction of movement of the object can be specified by the change in the position of the detected object, and the movement speed can be calculated by the amount of movement of the object per hour.

The notification control unit 23 instructs the communication device 10 to report by transmitting the detection information including the fact that the object has been detected, the type of the detected object, the moving direction and the moving speed to the communication device 10 (step 180). The transmission destination of the detection information is the communication device 10 corresponding to a predetermined range. Alternatively, the communication device 10 corresponding to a range adjacent to a predetermined range may be included in the transmission destination. Further, the object detection device 20 may hold the object for the purpose of managing the detection status of the object.

In the notification control unit 23, when another object different from the detected object within a predetermined range is further detected, for example, when the vehicle 7 is detected, the person 8 moves in the traveling direction of the vehicle 7. When it is determined that the road is in a situation to be reported, such as when it is detected, or when a person 8 is detected and a vehicle 7 traveling in the walking direction of the person 8 is detected. It may be controlled to transmit the detection information only. Further, the communication device 10 may be provided with the control function of this notification.

When the detection information receiving unit 13 receives the detection information in the communication device 10, the reporting unit 14 is traveling in the direction of the detected vehicle 7, at least the person 8, when the detected object is the person 8. Report valid information to vehicle 7. The valid information is, for example, that a person 8 is detected around the traveling position, or that there is a person 8 crossing the pedestrian crossing in front of the vehicle. Further, when the detected object is the vehicle 7, the reporting unit 14 displays information useful for the person 8 on the sign board 9 installed in the traveling direction of the vehicle 7. The valid information is, for example, that the vehicle 7 is approaching. Alternatively, when the person 8 carries an information device provided with a display means, the reporting unit 14 may notify the person 8 that the vehicle 7 is approaching by notifying the information device.

In the present embodiment, the communication device 10 receives an instruction from the object detection device 20 to make a report, but the object detection device 20 directly reports to the vehicle 7, the person 8, and the sign board 9. Or it may be marked.

Here, the correction process in step 130 will be described.

FIG. 6 is a diagram showing an example of a load transition measured by one load sensor 6. FIG. 6 shows the transition of the load measured in fine weather as non-bad weather. In the graph shown in FIG. 6, the horizontal axis is time and the vertical axis is the measured load.

FIG. 6A is a graph showing a time when measurement is performed in a state where there is no object on one road slab 1 mounted on the pile 3 corresponding to the load sensor 6. Since there is no object, only a constant load, that is, a reference load is measured, and the load does not change. FIG. 6B shows a graph in which the load of an object is detected at t1 for a certain period of time.

Then, FIG. 6 (c) shows the load transition when only the load of the object is extracted by subtracting the load shown in FIG. 6 (a), that is, the reference load from the load transition shown in FIG. 6 (b). It is a graph which shows. In the correction process, a load distribution that detects only the load of the object is created as in the case of the teacher data.

As bad weather, for example, fog, mist, etc. that do not apply a load to the road slab 1 may be corrected in the same manner as in the case of fine weather. In the case of rainfall, a load due to rainwater is applied on the road, but it is considered to be within the error range, that is, the noise level of the measured value when compared with the weight of the road slab 1. Therefore, the rainfall does not affect the determination result of the presence or absence of the object on the road slab 1 and the determination result of the type of the object. In other words, in the case of fog, haze, and rain, it is sufficient to correct in the same way as in the case of fine weather. Even in the case of heavy rainfall with a lot of rainfall, the judgment result is not affected.

FIG. 7 is a diagram showing an example of a load transition measured by one load sensor 6. FIG. 7 shows the transition of the load measured when the weather is snow, especially when the weather is such that snow cover is observed. In the graph shown in FIG. 7, the horizontal axis is time and the vertical axis is the measured load.

FIG. 7A is a graph showing a time when measurement is performed in a state where there is no object on one road slab 1 mounted on the load sensor 6. Due to the absence of objects, the load is gradually increasing as snowfall is observed on the road slab 1. Here, for convenience of explanation, the amount of snowfall is assumed to increase constantly, and thus the amount of increase in load is constant. FIG. 7B shows a graph in which the load of an object is detected at t1 for a certain period of time when snow cover is observed on the road slab 1 as in FIG. 7A.

Then, FIG. 7 (c) is a graph showing the load transition when only the load of the object is extracted by subtracting the load shown in FIG. 7 (a) from the load transition shown in FIG. 7 (b). .. In the present embodiment, it is possible to create a load distribution that extracts only the load of the object even when there is snow.

Whether the load applied to the road slab 1 is due to snow cover or the load of an object can be determined by the amount of increase in the load per hour. In the case of snow cover, the load increases slowly, that is, gradually increases, whereas in the case of an object, it increases relatively rapidly as compared with the case of snow cover, although it depends on the moving speed. Therefore, it can be discriminated by the amount of increase in the load per hour. More specifically, a threshold value for the amount of increase may be set, and the determination may be made by comparing the amount of increase per hour with the threshold value.

On the other hand, in the case of melting snow, the correction may be made in the same manner as in the case of snow accumulation. In the case of thaw, the load when the object does not exist gradually decreases, but as explained with reference to FIG. 7, the load transition when the object is detected changes from the load transition when the object is not detected. By subtracting it, it is possible to create a load distribution that extracts only the load of the object.

As described above, according to the present embodiment, by measuring the load applied on the road, it is possible to reliably detect an object even in bad weather such as when snow cover is observed.

In the present embodiment, the load sensor 6 on the road 2 is installed to detect the load applied to the pile 3 and eventually the road slab 1. This is because the load sensor 6 obtains the load itself as a sensor value. However, as a sensor means other than the load sensor 6, for example, a vibration sensor may be provided on the pile 3 or the road slab 1. Alternatively, a strain sensor may be provided on the road slab 1. The vibration value measured by the vibration sensor and the strain value measured by the strain sensor can be converted into a load. Therefore, the object detection device 20 converts the sensor data (vibration value or strain value) acquired from the communication device 10 into a load value, and then performs the above-mentioned object detection process. The conversion of the sensor data to the load value may be performed by the communication device 10.

The vibration sensor is not affected by fog or haze. In addition, vibration caused by rainfall or snowfall is only noise and is hardly affected. The strain sensor is not affected by fog, haze, or rain. In addition, the road slab 1 may be slightly distorted due to snow cover, but it is a degree of noise. That is, an object can be detected even by using a vibration sensor or a distorted sensor. Any other sensor means may be used as long as it is a sensor means for measuring sensor data that can be converted into a load.

1 Precast concrete slab (road slab), 2 roads, 2a sideways, 2b roads, 3 piles, 4 road bodies, 5 spaces, 6 load sensors, 7 vehicles, 7a general vehicles, 7b motorcycles, 7c large vehicles, 8 people, 9 Marking board, 10 Communication device, 11 Sensor data receiver, 12 Sensor information transmitter, 13 Detection information receiver, 14 Notification unit, 20 Object detection device, 21 Sensor information receiver, 22 Object detection unit, 23 Notification control unit , 24 sensor information storage unit, 25 management information storage unit.

Claims (6)

In an object detection system that detects an object on a road having a structure formed by using a pile erected in an area where a road is constructed and a precast concrete slab placed on the pile.
A plurality of sensor means arranged on the road and
A sensor information acquisition means for acquiring sensor information including at least the sensor value of the sensor means, and a sensor information acquisition means.
A detection means that detects an object on the road by referring to a load applied to the road surface obtained from the sensor value of the sensor means, and a detection means.
An object detection system characterized by having. When the load applied to the road surface is gradually increased or decreased, the detecting means refers to the load obtained by subtracting the load obtained from the sensor value of the sensor means when there is no object on the road surface. The object detection system according to claim 1, wherein the object above is detected. When the sensor means is attached to the stake, the detection means inputs the distribution of the load applied to the stake when an object exists on the road, and outputs the presence or absence of the object to the learning model. The object detection system according to claim 1, wherein the object on the road is detected by inputting the distribution of the load applied to the pile obtained from the sensor value of the sensor means. A detection means that detects the position, moving direction, and moving speed of an object detected by the detecting means by referring to the distribution of the load applied to the road surface obtained from the sensor value of the sensor means and its transition.
A reporting means for notifying other objects located around the object detected by the detecting means of the detection of the object, and
The object detection system according to claim 1, wherein the object detection system is characterized by having. It has a discriminating means for discriminating the type of an object detected by the detecting means from the load applied to the road surface obtained from the sensor value of the sensor means.
When the object is determined to be a person by the determination means, the reporting means notifies the vehicle approaching the person of the existence of the person, and when the object is determined to be a vehicle by the determination means, the vehicle is concerned. Notify the person located in the direction of travel of the approach of the vehicle,
The object detection system according to claim 4, wherein the object detection system is characterized by the above. The object detection system according to claim 1, wherein the sensor means is a load sensor or a sensor that measures sensor data that can be converted into a load.

Images