JP2021034917A - Sensor installation support device, sensor installation support method, and program - Google Patents

Abstract

To provide a technology that makes it possible to keep a more appropriate installation position for a sensor.SOLUTION: A sensor installation support device includes: a data acquisition unit that acquires measurement data on an area to be measured by a sensor; an area identification unit that attempts to identify the area to be monitored in which an object is to be detected based on the measurement data; and an installation position determination unit that determines whether the installation position of the sensor needs to be changed based on whether the area to be monitored can be identified or the position of the area to be monitored in the area to be measured.SELECTED DRAWING: Figure 1

Description

The present invention relates to a sensor installation support device, a sensor installation support method, and a program.

Conventionally, in order to ensure the safety of the construction site, a surveillance camera is installed at the construction site, an object (for example, a person or a vehicle) in the image captured by the camera is detected, and the detection result is used in the construction site. It has been done to confirm the situation. However, in recent years, with the spread of sensors using lasers (LiDAR (Light Detection and Ranger) sensors), LiDAR that can detect the position of an object more accurately is installed at the construction site to monitor the inside of the construction site. Is becoming.

Japanese Patent No. 5778237 Special Table 2016-522923

However, even if the work place (hereinafter, also referred to as "monitoring target area") is within the detectable range by the sensor (hereinafter, also referred to as "measurement target area") when the sensor is installed, the construction work is carried out. As the progress progresses, the monitored area may deviate from the measurement target area. Therefore, it is necessary to change the installation position of the sensor according to the progress of the construction. However, since the measurement target area cannot generally be visually confirmed, it is difficult for the operator to visually determine whether or not the sensor installation position needs to be changed.

Therefore, it is desired to provide a technique capable of maintaining the installation position of the sensor more appropriately.

In order to solve the above problem, according to a certain viewpoint of the present invention, a data acquisition unit that acquires measurement data of a measurement target area measured by a sensor and a monitoring target that an object should be detected based on the measurement data. An installation position that determines whether it is necessary to change the installation position of the sensor based on the area identification unit that attempts to specify the area, whether or not the monitoring target area can be specified, or the position of the monitoring target area in the measurement target area. A sensor installation support device including a determination unit is provided.

The installation position determination unit may determine whether it is necessary to change the installation position of the sensor when the position of the monitoring target area moves by a predetermined amount in a direction away from the sensor.

The sensor installation support device may include an information output unit that outputs predetermined warning information for prompting the change of the installation position of the sensor when it is determined that the installation position of the sensor needs to be changed. Good.

The information output unit may output the warning information including the distance to move the installation position of the sensor.

The information output unit may calculate the distance based on the amount of movement of the monitored area per predetermined time and a predetermined change allowable cycle of the installation position of the sensor.

The information output unit may output the maintainable period of the installation position of the sensor calculated based on the movement amount of the monitored area and the distance per predetermined time together with the warning information.

The installation position determination unit may determine that it is necessary to change the installation position of the sensor when the monitoring target area is not specified.

The installation position determination unit does not need to change the installation position of the sensor when the monitoring target area is no longer specified after the position of the monitoring target area moves in a direction different from the predetermined traveling direction. It may be determined that.

When the monitoring target area is specified, the installation position determination unit needs to change the installation position of the sensor when the position of the monitoring target area in the measurement target area exceeds a predetermined range. It may be determined that there is.

The installation position determination unit installs the sensor when the position of the monitoring target area exceeds a predetermined range after the position of the monitoring target area moves in a direction different from the predetermined traveling direction. It may be determined that the position change is unnecessary.

When the object is not detected based on the measurement data, the area specifying unit does not have to specify the monitored area.

When an object is detected based on the measurement data, the area specifying unit may try to specify the monitored area based on the transition of the position of the object.

When an object is detected based on the measurement data, the area specifying unit may attempt to specify an area where the frequency of the position of the object peaks as the monitored area.

The sensor installation support device includes an object identification unit that identifies the type of the object, and the area identification unit is based on the position of the object when the type of the object is identified as a predetermined type. You may try to identify the monitored area.

The object identification unit may specify the type of the object by the type of the object specified based on the video data captured by the camera.

The sensor may include a LiDAR sensor.

Further, according to another aspect of the present invention, it is possible to acquire the measurement data of the measurement target area measured by the sensor and to try to identify the monitoring target area in which the object should be detected based on the measurement data. The sensor installation support method includes determining whether or not the monitoring target area can be specified, or whether it is necessary to change the installation position of the sensor based on the position of the monitoring target area in the measurement target area. Provided.

Further, according to another aspect of the present invention, the computer has a data acquisition unit that acquires measurement data of the measurement target area measured by the sensor and a monitoring target area in which an object should be detected based on the measurement data. An installation position determination unit that determines whether it is necessary to change the installation position of the sensor based on the area identification unit to be identified, whether the monitoring target area can be specified, or the position of the monitoring target area in the measurement target area. And, a program for functioning as a sensor installation support device is provided.

As described above, according to the present invention, there is provided a technique that makes it possible to maintain the installation position of the sensor more appropriately.

It is a figure for demonstrating the outline of the work monitoring system which concerns on 1st Embodiment of this invention. It is a figure for demonstrating the outline of the work monitoring system which concerns on this embodiment. It is a block diagram which shows the functional structure example of the work monitoring system which concerns on the same embodiment. It is a flowchart which shows the operation example of the work monitoring system which concerns on this embodiment. It is a figure for demonstrating the outline of the work monitoring system which concerns on 2nd Embodiment of this invention. It is a block diagram which shows the functional structure example of the work monitoring system which concerns on the same embodiment. It is a flowchart which shows the operation example of the work monitoring system which concerns on this embodiment. It is a figure for demonstrating the outline of the work monitoring system which concerns on 3rd Embodiment of this invention. It is a block diagram which shows the functional structure example of the work monitoring system which concerns on 3rd Embodiment of this invention. It is a flowchart which shows the operation example of the work monitoring system which concerns on this embodiment. It is a figure which shows the hardware configuration of the information processing apparatus as an example of the sensor installation support apparatus which concerns on embodiment of this invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the present specification and the drawings, components having substantially the same functional configuration are designated by the same reference numerals, so that duplicate description will be omitted.

Further, in the present specification and the drawings, a plurality of components having substantially the same functional configuration may be distinguished by adding different numbers after the same reference numerals. However, if it is not necessary to distinguish each of a plurality of components having substantially the same functional configuration, only the same reference numerals are given. Further, similar components of different embodiments may be distinguished by adding different alphabets after the same reference numerals. However, if it is not necessary to distinguish each of the similar components of different embodiments, only the same reference numerals are given.

<1. First Embodiment>
First, the first embodiment of the present invention will be described.

(1-1. Overview of the system)
First, an outline of the work monitoring system according to the first embodiment of the present invention will be described. In the embodiment of the present invention, it is mainly assumed that construction is performed as an example of work. However, the type of work is not limited to construction as long as it requires monitoring by a sensor. Further, in the embodiment of the present invention, it is mainly assumed that tunnel construction is performed as an example of construction monitored by a sensor. However, as will be explained later, the construction monitored by the sensor is not limited to tunnel construction.

1 and 2 are diagrams for explaining the outline of the work monitoring system according to the first embodiment of the present invention. In particular, FIG. 1 shows an example of the situation at the initial construction site where the sensor was installed. On the other hand, FIG. 2 shows an example of the situation at the construction site after the construction progresses. With reference to FIGS. 1 and 2, the inside of the tunnel Tu is shown as an example of a construction site. Further, referring to FIGS. 1 and 2, the direction in which the excavation of the tunnel Tu should proceed is shown as the excavation direction X.

A LiDAR sensor 20 is installed inside the tunnel Tu, and the area measured by the LiDAR sensor 20 is indicated as a measurement target area R1. As described above, in the embodiment of the present invention, it is mainly assumed that the LiDAR sensor 20 is used as an example of the sensor for monitoring the construction work. However, the sensor that monitors the construction work is not limited to the LiDAR sensor 20. The sensor for monitoring the construction may be a sensor that can detect the movement of an object existing in the measurement target area R1 by non-contact, a camera, a depth sensor, or a radar ranging sensor. It may be. Further, in the embodiment of the present invention, it is mainly assumed that one LiDAR sensor 20 is installed. However, two or more LiDAR sensors 20 may be installed.

Further, inside the tunnel Tu, there are heavy machinery B1 and heavy machinery B2 used for construction. The monitoring target area R2 to which the heavy machine B1 and the heavy machine B2 should be detected is monitored by the LiDAR sensor 20. As described above, in the embodiment of the present invention, it is mainly assumed that a heavy machine is used as an example of an object monitored by the LiDAR sensor 20. However, the object monitored by the LiDAR sensor 20 is not limited to heavy machinery, and may be an operator or the like. Further, the type of heavy machinery is not limited, and may be a dump truck, an excavator car, an excavator, or the like. Also, the number of objects monitored by the LiDAR sensor 20 is not limited to two.

Here, since the LiDAR sensor 20 uses a laser, the larger the distance from the LiDAR sensor 20 to the heavy machine B1 and the heavy machine B2, the more difficult it is for the heavy machine B1 and the heavy machine B2 to be irradiated with the laser. Then, as shown in FIG. 1, when the LiDAR sensor 20 is initially installed, even if the monitored area R2 exists in the measurement target area R1 by the sensor (the position Xa of the monitored area R2 in the excavation direction X). ), As shown in FIG. 2, the monitored area R2 may deviate from the measurement target area R1 as the construction progresses (position Xb of the monitored area R2 in the excavation direction X). Therefore, it is necessary to change the installation position of the LiDAR sensor 20 according to the progress of the construction. However, since the measurement target area R1 is generally not visually confirmed, it is difficult for the operator to visually determine whether or not the installation position of the LiDAR sensor 20 needs to be changed.

Therefore, in the embodiment of the present invention, we mainly propose a technique that enables the installation position of the sensor to be maintained more appropriately. As described above, the construction monitored by the LiDAR sensor 20 is not limited to tunnel construction. For example, the work monitored by the LiDAR sensor 20 may be a work in which the monitored area moves according to the progress of the work, and the work in which the monitored area moves in a predetermined direction according to the progress of the work (for example, a bridge). It may be construction work or road paving work, etc.).

The outline of the work monitoring system according to the first embodiment of the present invention has been described above.

(1-2. Functional configuration example of work monitoring system)
Subsequently, a functional configuration example of the work monitoring system 1A according to the first embodiment of the present invention will be described with reference to FIG. 3 (see also FIGS. 1 and 2 as appropriate). FIG. 3 is a block diagram showing a functional configuration example of the work monitoring system 1A according to the first embodiment of the present invention. As shown in FIG. 3, the work monitoring system 1A according to the first embodiment of the present invention includes a sensor installation support device 10A, a LiDAR sensor 20, a presentation device 30, and a network 40. The sensor installation support device 10A, the LiDAR sensor 20, and the presentation device 30 are connected to the network 40.

The LiDAR sensor 20 obtains measurement data (hereinafter, also referred to as “point cloud data”) by continuously sensing the measurement target area R1. Then, the LiDAR sensor 20 outputs the point cloud data to the sensor installation support device 10A. As described above, in the embodiment of the present invention, it is mainly assumed that one LiDAR sensor 20 is installed. However, two or more LiDAR sensors 20 may be installed. In such a case, each of the plurality of LiDAR sensors 20 is connected to the network 40, and the point cloud data obtained by each of the plurality of LiDAR sensors 20 is output to the sensor installation support device 10A via the network 40. Then, the sensor installation support device 10A can perform the same processing on the point cloud data input from each of the plurality of LiDAR sensors 20.

The sensor installation support device 10A is composed of a computer. In the embodiment of the present invention, it is mainly assumed that the sensor installation support device 10A is installed at a construction site (near the LiDAR sensor 20). However, the place where the sensor installation support device 10A is installed is not limited. For example, the sensor installation support device 10A may be installed in a place away from the construction site (for example, a monitoring room in which an observer who monitors the work exists). Here, the sensor installation support device 10A includes a control unit (not shown), a storage unit (not shown), and a communication unit (not shown).

The control unit (not shown) includes a CPU (Central Processing Unit) and the like, and its function can be realized by the program stored in the storage unit being expanded and executed by the CPU in a RAM (Random Access Memory). At this time, a computer-readable recording medium on which the program is recorded may also be provided. Alternatively, the control unit (not shown) may be configured by dedicated hardware, or may be configured by a combination of a plurality of hardware.

The control unit (not shown) includes a data acquisition unit 101, an area identification unit 110, a detection result recording control unit 105, an installation position determination unit 106, and an information output unit 107. The area identification unit 110 includes an object detection unit 102, a distance calculation unit 103, and an area detection unit 104.

A storage unit (not shown) is a storage device capable of storing programs and data for operating a control unit (not shown). Further, the storage unit (not shown) can temporarily store various data required in the process of operation of the control unit (not shown). For example, the storage device may be a non-volatile storage device. A storage unit (not shown) includes a detection result DB (database) 111 and an installation condition DB 112.

The communication unit (not shown) is composed of a communication interface and is connected to the network 40. For example, a communication unit (not shown) receives the point cloud data transmitted from the LiDAR sensor 20 via the network 40. Further, the communication unit (not shown) transmits the information output by the sensor installation support device 10A to the presentation device 30 via the network 40.

The installation condition DB 112 records a condition (installation condition) for determining whether or not the installation position of the LiDAR sensor 20 needs to be changed. The installation conditions may be recorded in the installation condition DB 112 in advance. Here, it is assumed that the installation condition DB 112 records a condition in which the installation position of the LiDAR sensor 20 needs to be changed. However, the installation condition DB 112 may record a condition that does not require a change in the installation position of the LiDAR sensor 20.

The data acquisition unit 101 acquires the point cloud data of the measurement target area R1 measured by the LiDAR sensor 20 from the LiDAR sensor 20.

The area identification unit 110 attempts to identify the monitored area R2 based on the point cloud data acquired by the data acquisition unit 101. More specifically, the object detection unit 102 attempts to detect an object based on the measurement data. Here, the object detection method is not limited. For example, the object detection unit 102 may detect an object by clustering the point clouds existing within a predetermined distance as the positions where the same object exists after removing the point cloud data on the ground from the point cloud data. Good.

The distance calculation unit 103 calculates the distance between the object and the LiDAR sensor 20 when the object is detected by the object detection unit 102. Here, the method for calculating the distance between the object and the LiDAR sensor 20 is not limited. For example, since the distance calculation unit 103 reflects the distance from the LiDAR sensor 20 at each point constituting the point cloud, the distance between the object and the LiDAR sensor 20 is calculated by using the center of gravity of the point cloud belonging to the object. It may be calculated. By detecting the object by the object detection unit 102 and calculating the distance by the distance calculation unit 103, the current position of the object (three-dimensional position) with respect to the position of the LiDAR sensor 20 is acquired.

The area detection unit 104 does not specify the monitored area R2 when the object is not detected by the object detection unit 102. On the other hand, when the object is detected by the object detection unit 102, the area detection unit 104 may try to specify the monitoring target area R2 based on the transition of the position of the object. More specifically, the area detection unit 104 is an area of a predetermined size or less at which the frequency of the position of the object peaks based on the position of the current object and the position of the past object recorded in the detection result DB 111. May be attempted to be specified as the monitored area R2.

Here, the position of the object in the past may be the position of the object after a predetermined time retroactively from the present to the past. However, since the positional relationship between the LiDAR sensor 20 and the object changes before and after the change in the installation position of the LiDAR sensor 20, the installation position of the LiDAR sensor 20 has been changed since the last time (however, the installation position of the LiDAR sensor 20). If has not yet been changed, it needs to be the position of the object (since the LiDAR sensor 20 has been installed).

In the examples shown in FIGS. 1 and 2, it is assumed that the area where the frequencies of the positions of the plurality of objects (heavy machine B1 and heavy machine B2) both peak is specified as the monitoring target area R2. However, there is a possibility that the area where the frequency of each position of one or more objects peaks and the area where the frequency of each position of another one or more objects peaks are separate areas. At that time, the area where the frequency of each position of the larger number of objects peaks may be specified as the monitoring target area R2.

The detection result recording control unit 105 records the position of the detected current object, the detection time, and the position (three-dimensional position) of the monitoring target area R2 in the detection result DB 111.

The installation position determination unit 106 determines whether or not the installation position of the LiDAR sensor 20 needs to be changed based on the installation conditions acquired from the installation condition DB 112. For example, the installation position determination unit 106 determines whether or not the installation position of the LiDAR sensor 20 needs to be changed based on whether or not the monitoring target area R2 can be specified or the position of the monitoring target area R2 in the measurement target area R1. This makes it possible to maintain the installation position of the LiDAR sensor 20 more appropriately.

More specifically, the installation position determination unit 106 determines that the installation position of the LiDAR sensor 20 needs to be changed when the monitoring target area R2 is not specified. At this time, it is assumed that the monitored area R2 is no longer specified after the position of the monitored area R2 moves in a direction different from the predetermined traveling direction (for example, the opposite direction). In such a case, it is considered unnecessary to make the LiDAR sensor 20 follow the movement of the monitoring target area R2. Therefore, even if the installation position determination unit 106 determines that the installation position of the LiDAR sensor 20 does not need to be changed. Good.

The traveling direction may be one direction as in the excavation direction X shown in FIGS. 1 and 2, or may be a direction having a certain width (for example, with reference to the excavation direction X). Good. The traveling direction may be manually input in advance, or may be automatically recognized by the installation position determination unit 106 based on the point cloud data obtained by the LiDAR sensor 20. Further, the installation position determination unit 106 may automatically recognize in which direction the position of the monitoring target area R2 is moving according to the progress of the construction work, and update the traveling direction according to the recognized direction.

On the other hand, when the monitoring target area R2 is specified, the installation position determination unit 106 positions the monitoring target area R2 in the measurement target area R1 within a predetermined range (for example, a range within a predetermined distance from the LiDAR sensor 20). When the above is exceeded, it is determined that the installation position of the LiDAR sensor 20 needs to be changed. At this time, it is assumed that the position of the monitored area R2 exceeds a predetermined range after the position of the monitored area R2 moves in a direction different from the predetermined traveling direction (for example, the opposite direction). In such a case, it is considered unnecessary to make the LiDAR sensor 20 follow the movement of the monitoring target area R2. Therefore, even if the installation position determination unit 106 determines that the installation position of the LiDAR sensor 20 does not need to be changed. Good.

The installation position determination unit 106 may always determine whether the installation position of the LiDAR sensor 20 needs to be changed. However, the installation position determination unit 106 may determine whether the installation position of the LiDAR sensor 20 needs to be changed when the position of the monitoring target area R2 moves by a predetermined amount in the direction away from the LiDAR sensor 20. On the other hand, when the position of the monitoring target area R2 has not moved by a predetermined amount in the direction away from the LiDAR sensor 20, the installation position determination unit 106 does not have to determine whether the installation position of the LiDAR sensor 20 needs to be changed. Good. As a result, the processing cost of the sensor installation support device 10A can be suppressed.

When it is determined that the installation position of the LiDAR sensor 20 needs to be changed, the information output unit 107 outputs predetermined warning information for prompting the change of the installation position of the LiDAR sensor 20. Here, the warning information is not limited. For example, it may be some visual information or sound information indicating a warning. Alternatively, the information output unit 107 may output warning information including the distance to move the installation position of the LiDAR sensor 20.

At this time, it is assumed that the installation position of the LiDAR sensor 20 may be changed in any cycle (hereinafter, also referred to as “change allowable cycle”) in advance. For example, when it is desired to reduce the time and effort required to change the installation position of the LiDAR sensor 20, it is assumed that the change allowable cycle is set longer. On the other hand, when it is not desired to reduce the measurement accuracy of the monitored area R2 by the LiDAR sensor 20, it is assumed that the change allowable cycle is set short.

Therefore, the information output unit 107 should move the installation position of the LiDAR sensor 20 based on the movement amount of the monitored area R2 per predetermined time and the predetermined change allowable cycle of the installation position of the LiDAR sensor 20. The distance may be calculated. More specifically, the information output unit 107 installs the LiDAR sensor 20 by multiplying the movement amount of the monitored area R2 per predetermined time by a predetermined change allowable cycle of the installation position of the LiDAR sensor 20. The distance to move the position may be calculated.

Here, the movement amount of the monitored area R2 per predetermined time may be manually input in advance. Further, the information output unit 107 automatically recognizes how much the position of the monitored area R2 has moved per predetermined time according to the progress of the construction, and depending on the recognized degree of movement, the information output unit 107 per predetermined time. The movement amount of the monitored area R2 may be updated.

On the other hand, it is assumed that the permissible cycle for changing the installation position of the LiDAR sensor 20 is not determined in advance. In such a case, the information output unit 107 determines the installation position of the LiDAR sensor 20 for how long based on the movement amount of the monitored area R2 per predetermined time and the distance to move the installation position of the LiDAR sensor 20. You may calculate whether you do not need to change it (hereinafter, also referred to as "sustainable period"). Then, the information output unit 107 may output the warning information (for example, the distance that the installation position of the LiDAR sensor 20 should be moved) and the maintainable period of the installation position of the LiDAR sensor 20.

At this time, the distance to move the installation position of the LiDAR sensor 20 may be a fixed value. More specifically, the information output unit 107 can maintain the installation position of the LiDAR sensor 20 by dividing the distance to which the installation position of the LiDAR sensor 20 should be moved by the movement amount of the monitored area R2 per predetermined time. The period may be calculated.

The presenting device 30 has a function of presenting the information output from the information output unit 107. For example, the presenting device 30 presents the warning information output from the information output unit 107. Further, the presenting device 30 presents warning information output from the information output unit 107 (for example, the distance at which the installation position of the LiDAR sensor 20 should be moved), and installs the LiDAR sensor 20 output from the information output unit 107. Present the maintainable period of the position.

Here, the form of the presentation device 30 is not particularly limited. For example, the presentation device 30 may be a display that displays warning information, or a speaker that outputs warning information by voice. In the embodiment of the present invention, it is mainly assumed that the presentation device 30 is installed in a place away from the construction site (for example, a monitoring room in which an observer who monitors the work exists). In such a case, the observer may instruct the operator to change the installation position of the LiDAR sensor 20. However, the place where the presentation device 30 is installed is not limited. For example, the presentation device 30 may be installed at a construction site (near the LiDAR sensor 20). In such a case, the operator can directly grasp that the installation position of the LiDAR sensor 20 needs to be changed.

In the example shown in FIG. 3, the data acquisition unit 101, the object detection unit 102, the distance calculation unit 103, the area detection unit 104, the detection result recording control unit 105, the installation position determination unit 106, the information output unit 107, and the detection result. The DB 111 and the installation condition DB 112 are provided inside the sensor installation support device 10A. However, some or all of these functional blocks may be provided outside the sensor installation support device 10A.

The functional configuration example of the work monitoring system 1A according to the first embodiment of the present invention has been described above.

(1-3. Operation example of work monitoring system)
Subsequently, an operation example of the work monitoring system 1A according to the first embodiment of the present invention will be described. FIG. 4 is a flowchart showing an operation example of the work monitoring system 1A according to the first embodiment of the present invention. The operation example shown in FIG. 4 is only an example of the operation of the work monitoring system 1A according to the first embodiment of the present invention. Therefore, the operation of the work monitoring system 1A according to the first embodiment of the present invention is not limited to the operation example shown in FIG.

First, the LiDAR sensor 20 obtains point cloud data by continuously sensing the measurement target area R1. As shown in FIG. 4, the data acquisition unit 101 acquires the point cloud data of the measurement target area R1 measured by the LiDAR sensor 20 from the LiDAR sensor 20 (S101). The object detection unit 102 attempts to detect an object based on the measurement data acquired by the data acquisition unit 101 (S102). The distance calculation unit 103 calculates the distance between the detected object and the LiDAR sensor 20 when the object is detected by the object detection unit 102 (S103).

When an object is detected by the object detection unit 102, the area detection unit 104 attempts to identify the monitored area R2 based on the transition of the position of the object (S104). More specifically, the area detection unit 104 is an area of a predetermined size or less at which the frequency of the position of the object peaks based on the position of the current object and the position of the past object recorded in the detection result DB 111. Attempts to identify as the monitored area R2. Subsequently, the detection result recording control unit 105 saves the detected current position of the object, the detection time, and the position (three-dimensional position) of the monitored area R2 in the detection result DB 111 (S105).

The installation position determination unit 106 determines whether it is necessary to change the installation position of the LiDAR sensor 20 based on the installation conditions acquired from the installation condition DB 112 (S106). For example, the installation position determination unit 106 determines whether or not the installation position of the LiDAR sensor 20 needs to be changed based on whether or not the monitoring target area R2 can be specified or the position of the monitoring target area R2 in the measurement target area R1. This makes it possible to maintain the installation position of the LiDAR sensor 20 more appropriately.

More specifically, the installation position determination unit 106 determines that the installation position of the LiDAR sensor 20 needs to be changed when the monitoring target area R2 is not specified. On the other hand, when the monitoring target area R2 is specified, the installation position determination unit 106 positions the monitoring target area R2 in the measurement target area R1 within a predetermined range (for example, a range within a predetermined distance from the LiDAR sensor 20). When the above is exceeded, it is determined that the installation position of the LiDAR sensor 20 needs to be changed.

When it is determined that the installation position of the LiDAR sensor 20 needs to be changed, the information output unit 107 notifies the presenting device 30 of predetermined warning information for prompting the change of the installation position of the LiDAR sensor 20 (S107). ). Here, the warning information is not limited. For example, it may be some visual information or sound information indicating a warning. Alternatively, the information output unit 107 may output warning information including the distance to move the installation position of the LiDAR sensor 20.

At this time, it is assumed that the change allowable cycle is predetermined. In such a case, the information output unit 107 determines the installation position of the LiDAR sensor 20 based on the movement amount of the monitored area R2 per predetermined time and the predetermined change allowable cycle of the installation position of the LiDAR sensor 20. The distance to be moved may be calculated.

On the other hand, it is assumed that the permissible cycle for changing the installation position of the LiDAR sensor 20 is not determined in advance. In such a case, the information output unit 107 may calculate the maintainable period based on the movement amount of the monitoring target area R2 per predetermined time and the distance to move the installation position of the LiDAR sensor 20. Then, the information output unit 107 may output the warning information (for example, the distance that the installation position of the LiDAR sensor 20 should be moved) and the maintainable period of the installation position of the LiDAR sensor 20.

The presenting device 30 presents the warning information output from the information output unit 107. Further, the presenting device 30 presents warning information output from the information output unit 107 (for example, the distance at which the installation position of the LiDAR sensor 20 should be moved), and installs the LiDAR sensor 20 output from the information output unit 107. Present the maintainable period of the position.

The operation example of the work monitoring system 1A according to the first embodiment of the present invention has been described above.

(1-4. Effects of work monitoring system)
As described above, according to the first embodiment of the present invention, the data acquisition unit 101 that acquires the measurement data of the measurement target area measured by the sensor and the object should be detected based on the measurement data. Installation position determination to determine whether the sensor installation position needs to be changed based on the area identification unit 110 that attempts to identify the monitoring target area, whether the monitoring target area can be specified, or the position of the monitoring target area in the measurement target area. A sensor installation support device 10A comprising the unit 106 is provided.

According to such a configuration, the operator can know the timing when the sensor installation position needs to be changed (for example, by warning information), so that the operator changes the sensor installation position at an appropriate timing. It becomes possible. Therefore, according to such a configuration, it is possible to keep the installation position of the sensor more appropriately.

The first embodiment of the present invention has been described above.

<2. Second embodiment>
Subsequently, a second embodiment of the present invention will be described.

(2-1. Overview of the system)
First, an outline of the work monitoring system according to the second embodiment of the present invention will be described. FIG. 5 is a diagram for explaining an outline of the work monitoring system according to the second embodiment of the present invention. As shown in FIG. 5, at the construction site, the material B4 for construction or the use is used in a place where the work inside the measurement target area R1 is not performed (that is, outside the monitoring target area R2). Heavy equipment B3 and the like that have not been installed may be placed. In such a situation, the material B4 or the unused heavy machine B3 is detected as an object existing inside the measurement target area R1, so that the monitoring target area R2 exists outside the measurement target area R1. Therefore, it is not determined that the installation position of the LiDAR sensor 20 needs to be changed.

Therefore, in the second embodiment of the present invention, not only the object is detected, but also the type of the detected object is identified and the object to be monitored (heavy machine B1 and heavy machine B2 in the example shown in FIG. 5) is determined. By determining whether or not it exists inside the measurement target area R1, it is determined whether or not it is necessary to change the installation position of the LiDAR sensor 20.

The outline of the work monitoring system according to the second embodiment of the present invention has been described above.

(2-2. Functional configuration example of work monitoring system)
Subsequently, an example of the functional configuration of the work monitoring system 1B according to the second embodiment of the present invention will be described with reference to FIG. 6 (see also FIG. 5 as appropriate). FIG. 6 is a block diagram showing a functional configuration example of the work monitoring system 1B according to the second embodiment of the present invention. As shown in FIG. 6, the work monitoring system 1B according to the second embodiment of the present invention is a sensor installation support device instead of the sensor installation support device 10A (FIG. 3) according to the first embodiment of the present invention. It is equipped with 10B.

The sensor installation support device 10B includes an area identification unit 210 instead of the area identification unit 110 according to the first embodiment of the present invention. The area identification unit 210 includes an object identification unit 201, unlike the area identification unit 110 according to the first embodiment of the present invention. In addition, the sensor installation support device 10B includes the object feature DB 211 unlike the sensor installation support device 10A according to the first embodiment of the present invention. Hereinafter, the object identification unit 201 and the object feature DB 211 will be mainly described.

In the object feature DB 211, features for each type of object are recorded. Here, the characteristics of each type of object are not limited. For example, the characteristics of each type of object may include the morphological characteristics of the object, and the morphological characteristics of the object may include the length of the object, the width of the object, or the morphological characteristics of the object. It may include height.

The object identification unit 201 determines the type of the object detected by the object detection unit 102 based on the characteristics of the object detected by the object detection unit 102 and the characteristics of each type of the object recorded in the object feature DB 211. Identify. For example, the object identification unit 201 acquires from the object feature DB 211 the type of the object having features that match or resemble the features of the object detected by the object detection unit 102.

When the area detection unit 104 identifies that the type of the object is a predetermined type, the area detection unit 104 determines the monitored area based on the position of the object of the predetermined type (ignoring the position of the object other than the predetermined type). Attempts to identify R2. On the other hand, the area detection unit 104 does not specify the monitored area R2 when an object of a predetermined type does not exist.

In the example shown in FIG. 5, the heavy machine B1 and the heavy machine B2 are each a predetermined type of object. On the other hand, each of the material B4 and the unused heavy machine B3 is an object other than a predetermined type. As a result, the monitoring target area R2 is specified with higher accuracy, so that the installation position determination unit 106 can determine with higher accuracy whether or not the installation position of the LiDAR sensor 20 needs to be changed.

The functional configuration example of the work monitoring system 1B according to the second embodiment of the present invention has been described above.

(2-3. Operation example of work monitoring system)
Subsequently, an operation example of the work monitoring system 1B according to the second embodiment of the present invention will be described. FIG. 7 is a flowchart showing an operation example of the work monitoring system 1B according to the second embodiment of the present invention. The operation example shown in FIG. 7 is only an example of the operation of the work monitoring system 1B according to the second embodiment of the present invention. Therefore, the operation of the work monitoring system 1B according to the second embodiment of the present invention is not limited to the operation example shown in FIG. 7.

First, as shown in FIG. 7, S101 to S102 are executed, and S101 to S102 are the same as S101 to S102 (FIG. 4) executed by the work monitoring system 1A according to the first embodiment of the present invention. It is executed in the same way. Subsequently, the object identification unit 201 is an object detected by the object detection unit 102 based on the characteristics of the object detected by the object detection unit 102 and the characteristics of each type of the object recorded in the object feature DB 211. (S201). For example, the object identification unit 201 acquires from the object feature DB 211 the type of the object having features that match or resemble the features of the object detected by the object detection unit 102.

Subsequently, S103 to S107 are executed, and S103 to S107 are executed in the same manner as S103 to S107 (FIG. 4) executed by the work monitoring system 1A according to the first embodiment of the present invention. However, in S104, when the area detection unit 104 identifies that the type of the object is a predetermined type, the area detection unit 104 is based on the position of the object of the predetermined type (ignoring the position of the object other than the predetermined type). ), Attempts to identify the monitored area R2. On the other hand, the area detection unit 104 does not specify the monitored area R2 when an object of a predetermined type does not exist.

As a result, the monitoring target area R2 is specified with higher accuracy, so that the installation position determination unit 106 can determine with higher accuracy whether or not the installation position of the LiDAR sensor 20 needs to be changed.

The operation example of the work monitoring system 1B according to the second embodiment of the present invention has been described above.

(2-4. Effects of work monitoring system)
As described above, the sensor installation support device 10B according to the second embodiment of the present invention has the same configuration as the sensor installation support device 10A according to the first embodiment of the present invention. Further, the sensor installation support device 10B according to the second embodiment of the present invention includes an object identification unit 201 that identifies the type of the object, and the area identification unit 210 identifies that the type of the object is a predetermined type. In that case, an attempt is made to identify the monitored area based on the position of the object.

According to this configuration, even if an object other than the monitoring target exists inside the measurement target area R1, the position of the object other than the monitoring target is excluded, and the monitoring target area is based on the position of the object to be monitored. R2 is identified. That is, according to such a configuration, since the monitoring target area R2 is specified with higher accuracy, it can be determined with higher accuracy whether it is necessary to change the installation position of the LiDAR sensor 20.

The second embodiment of the present invention has been described above.

<3. Third Embodiment>
Subsequently, a third embodiment of the present invention will be described.

(3-1. Overview of the system)
First, an outline of the work monitoring system according to the third embodiment of the present invention will be described. FIG. 8 is a diagram for explaining an outline of the work monitoring system according to the third embodiment of the present invention. Here, in the second embodiment of the present invention, the case where the type of the object is specified based on the measurement data by the LiDAR sensor 20 has been described. However, since the LiDAR sensor 20 may have a lower resolution than an image sensor or the like, it is difficult to obtain sufficient measurement data for identifying the type of the object when the object is far away from the LiDAR sensor 20. There is.

Therefore, in the third embodiment of the present invention, as shown in FIG. 8, the camera 50 is installed at a position where the object is included in the imaging range, and the image data captured by the camera 50 (hereinafter, “camera”). (Also referred to as "video") is used to identify the type of object detected by the LiDAR sensor 20.

The outline of the work monitoring system according to the third embodiment of the present invention has been described above.

(3-2. Functional configuration example of work monitoring system)
Subsequently, an example of the functional configuration of the work monitoring system 1C according to the third embodiment of the present invention will be described with reference to FIG. 9 (see also FIG. 8 as appropriate). FIG. 9 is a block diagram showing a functional configuration example of the work monitoring system 1C according to the third embodiment of the present invention. As shown in FIG. 9, the work monitoring system 1C according to the third embodiment of the present invention includes the camera 50 and the sensor installation support device 10B (FIG. 6) according to the second embodiment of the present invention. Instead, a sensor installation support device 10C is provided.

The sensor installation support device 10C includes an area identification unit 310 instead of the area identification unit 210 according to the second embodiment of the present invention. The area identification unit 310 includes an object identification unit 301 instead of the object identification unit 201 according to the second embodiment of the present invention. Further, the sensor installation support device 10C includes an object feature DB311 instead of the object feature DB211 according to the second embodiment of the present invention. In addition, the sensor installation support device 10C includes an image acquisition unit 302 and an image analysis unit 303, unlike the sensor installation support device 10B according to the second embodiment of the present invention. Hereinafter, the object identification unit 301, the image acquisition unit 302, the image analysis unit 303, and the object feature DB 311 will be mainly described.

In the object feature DB311, features for each type of object are recorded. Here, the characteristics of each type of object are not limited. For example, the characteristics of each type of object may be learned in advance by machine learning (for example, deep learning). For example, when the characteristics of the object type are learned in advance by deep learning, the parameters of the prediction model for identifying the object type are recorded in the object feature DB as the characteristics for each object type.

The image acquisition unit 302 acquires the camera image captured by the camera 50. The image analysis unit 303 identifies the type of the object to be captured in the camera image captured by the image acquisition unit 302 based on the characteristics of each type of the object recorded in the object feature DB311. Then, the object identification unit 301 identifies the type of the object detected by the object detection unit 102 based on the type of the object specified by the video analysis unit 303. This allows the type of object to be identified with higher accuracy.

More specifically, by calibrating the positional relationship between the camera 50 and the LiDAR sensor 20, the position in the measurement data by the LiDAR sensor 20 and the position in the camera image captured by the camera 50 are associated with each other. Therefore, the object identification unit 301 has the object detection unit 102 based on such an association, the position of the object detected based on the measurement data by the LiDAR sensor 20, and the type of the object specified by the image analysis unit 303. The type of object detected by can be identified.

The functional configuration example of the work monitoring system 1C according to the third embodiment of the present invention has been described above.

(3-3. Operation example of work monitoring system)
Subsequently, an operation example of the work monitoring system 1C according to the third embodiment of the present invention will be described. FIG. 10 is a flowchart showing an operation example of the work monitoring system 1C according to the third embodiment of the present invention. The operation example shown in FIG. 10 is only an example of the operation of the work monitoring system 1C according to the third embodiment of the present invention. Therefore, the operation of the work monitoring system 1C according to the third embodiment of the present invention is not limited to the operation example shown in FIG.

First, as shown in FIG. 10, S101 to S102 are executed, and S101 to S102 are the same as S101 to S102 (FIG. 4) executed by the work monitoring system 1A according to the first embodiment of the present invention. It is executed in the same way. On the other hand, the image acquisition unit 302 acquires the camera image captured by the camera 50 (S301). The image analysis unit 303 identifies the type of the object to be captured in the camera image captured by the image acquisition unit 302 based on the characteristics of each type of the object recorded in the object feature DB311 (S302).

The object identification unit 301 identifies the type of the object detected by the object detection unit 102 based on the type of the object specified by the video analysis unit 303 (S303). More specifically, the object identification unit 301 was detected based on the correspondence between the position in the measurement data by the LiDAR sensor 20 and the position in the camera image captured by the camera 50 and the measurement data by the LiDAR sensor 20. The type of the object detected by the object detection unit 102 is specified based on the position of the object and the type of the object specified by the image analysis unit 303.

Subsequently, S103 to S107 are executed, and S103 to S107 are executed in the same manner as S103 to S107 (FIG. 4) executed by the work monitoring system 1A according to the first embodiment of the present invention. However, in the third embodiment of the present invention, since the type of the object is specified with higher accuracy, the monitored area R2 is also specified with higher accuracy, and the installation position determination unit 106 determines the installation position of the LiDAR sensor 20. It can be determined with higher accuracy whether a change is necessary.

The operation example of the work monitoring system 1C according to the third embodiment of the present invention has been described above.

(3-4. Effects of work monitoring system)
As described above, the sensor installation support device 10C according to the third embodiment of the present invention has the same configuration as the sensor installation support device 10B according to the second embodiment of the present invention. Further, in the sensor installation support device 10C according to the third embodiment of the present invention, the object identification unit 301 identifies the type of the object by the type of the object specified based on the image data captured by the camera 50. ..

According to such a configuration, the type of the object is specified with higher accuracy as compared with the case where the type of the object is specified using only the LiDAR sensor 20. Therefore, according to such a configuration, since the monitoring target area R2 is also specified with higher accuracy, it is possible to determine with higher accuracy whether it is necessary to change the installation position of the LiDAR sensor 20.

The third embodiment of the present invention has been described above.

<4. Hardware configuration example>
Subsequently, a hardware configuration example of the sensor installation support device 10 according to the embodiment of the present invention will be described. Hereinafter, as a hardware configuration example of the sensor installation support device 10 according to the embodiment of the present invention, a hardware configuration example of the information processing device 900 will be described. The hardware configuration example of the information processing device 900 described below is only an example of the hardware configuration of the sensor installation support device 10. Therefore, as for the hardware configuration of the sensor installation support device 10, an unnecessary configuration may be deleted from the hardware configuration of the information processing device 900 described below, or a new configuration may be added.

FIG. 11 is a diagram showing a hardware configuration of an information processing device 900 as an example of the sensor installation support device 10 according to the embodiment of the present invention. The information processing device 900 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, a RAM (Random Access Memory) 903, a host bus 904, a bridge 905, an external bus 906, and an interface 907. , An input device 908, an output device 909, a storage device 910, and a communication device 911.

The CPU 901 functions as an arithmetic processing device and a control device, and controls the overall operation in the information processing device 900 according to various programs. Further, the CPU 901 may be a microprocessor. The ROM 902 stores programs, calculation parameters, and the like used by the CPU 901. The RAM 903 temporarily stores a program used in the execution of the CPU 901, parameters that are appropriately changed in the execution, and the like. These are connected to each other by a host bus 904 composed of a CPU bus or the like.

The host bus 904 is connected to an external bus 906 such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 905. It is not always necessary to separately configure the host bus 904, the bridge 905, and the external bus 906, and these functions may be implemented in one bus.

The input device 908 includes input means for the user to input information such as a mouse, keyboard, touch panel, buttons, microphone, switch, and lever, and an input control circuit that generates an input signal based on the input by the user and outputs the input signal to the CPU 901. And so on. By operating the input device 908, the user who operates the information processing device 900 can input various data to the information processing device 900 and instruct the processing operation.

The output device 909 includes, for example, a CRT (Cathode Ray Tube) display device, a liquid crystal display (LCD) device, an OLED (Organic Light Emitting Node) device, a display device such as a lamp, and an audio output device such as a speaker.

The storage device 910 is a device for storing data. The storage device 910 may include a storage medium, a recording device for recording data on the storage medium, a reading device for reading data from the storage medium, a deleting device for deleting the data recorded on the storage medium, and the like. The storage device 910 is composed of, for example, an HDD (Hard Disk Drive). The storage device 910 drives a hard disk and stores programs and various data executed by the CPU 901.

The communication device 911 is, for example, a communication interface composed of a communication device or the like for connecting to a network. Further, the communication device 911 may support either wireless communication or wired communication.

The hardware configuration example of the sensor installation support device 10 according to the embodiment of the present invention has been described above.

<4. Summary>
Although the preferred embodiments of the present invention have been described in detail with reference to the accompanying drawings, the present invention is not limited to such examples. It is clear that a person having ordinary knowledge in the field of technology to which the present invention belongs can come up with various modifications or modifications within the scope of the technical idea described in the claims. , These are also naturally understood to belong to the technical scope of the present invention.

1 (1A to 1C) Work monitoring system 10 (10A to 10C) Sensor installation support device 101 Data acquisition unit 102 Object detection unit 103 Distance calculation unit 104 Area detection unit 105 Detection result recording control unit 106 Installation position determination unit 107 Information output unit 110 Area identification unit 201 Object identification unit 210 Area identification unit 310 Area identification unit 301 Object identification unit 302 Image acquisition unit 303 Image analysis unit 20 LiDAR sensor 30 Presentation device 40 Network 50 Camera R1 Measurement target area R2 Monitoring target area

Claims (18)

A data acquisition unit that acquires measurement data of the measurement target area measured by the sensor,
An area identification unit that attempts to identify a monitoring target area where an object should be detected based on the measurement data, and an area identification unit.
An installation position determination unit that determines whether or not the sensor installation position needs to be changed based on whether or not the monitoring target area can be specified or the position of the monitoring target area in the measurement target area.
A sensor installation support device equipped with. The installation position determination unit determines whether it is necessary to change the installation position of the sensor when the position of the monitoring target area moves by a predetermined amount in a direction away from the sensor.
The sensor installation support device according to claim 1. The sensor installation support device is
It is provided with an information output unit that outputs predetermined warning information for prompting the change of the installation position of the sensor when it is determined that the installation position of the sensor needs to be changed.
The sensor installation support device according to claim 1 or 2. The information output unit outputs the warning information including the distance to move the installation position of the sensor.
The sensor installation support device according to claim 3. The information output unit calculates the distance based on the amount of movement of the monitored area per predetermined time and a predetermined change allowable cycle of the installation position of the sensor.
The sensor installation support device according to claim 4. The information output unit outputs the maintainable period of the installation position of the sensor calculated based on the movement amount of the monitored area and the distance per predetermined time together with the warning information.
The sensor installation support device according to claim 4. The installation position determination unit determines that it is necessary to change the installation position of the sensor when the monitoring target area is not specified.
The sensor installation support device according to any one of claims 1 to 6. The installation position determination unit does not need to change the installation position of the sensor when the monitoring target area is no longer specified after the position of the monitoring target area moves in a direction different from the predetermined traveling direction. Judge that
The sensor installation support device according to claim 7. When the monitoring target area is specified, the installation position determination unit needs to change the installation position of the sensor when the position of the monitoring target area in the measurement target area exceeds a predetermined range. Judge that there is,
The sensor installation support device according to any one of claims 1 to 6. The installation position determination unit installs the sensor when the position of the monitoring target area exceeds a predetermined range after the position of the monitoring target area moves in a direction different from the predetermined traveling direction. Judge that the position change is unnecessary,
The sensor installation support device according to claim 9. The area specifying unit does not specify the monitored area when an object is not detected based on the measurement data.
The sensor installation support device according to any one of claims 1 to 8. When an object is detected based on the measurement data, the area specifying unit attempts to identify the monitored area based on the transition of the position of the object.
The sensor installation support device according to any one of claims 1 to 10. When an object is detected based on the measurement data, the area specifying unit attempts to specify an area where the frequency of the position of the object peaks as the monitored area.
The sensor installation support device according to claim 12. The sensor installation support device includes an object identification unit that identifies the type of the object.
When the type of the object is identified as a predetermined type, the area specifying unit attempts to identify the monitored area based on the position of the object.
The sensor installation support device according to claim 12 or 13. The object identification unit identifies the type of the object according to the type of the object specified based on the video data captured by the camera.
The sensor installation support device according to claim 14. The sensor includes a LiDAR sensor.
The sensor installation support device according to any one of claims 1 to 15. Acquiring the measurement data of the measurement target area measured by the sensor,
Attempting to identify the monitored area where the object should be detected based on the measurement data,
Determining whether it is necessary to change the installation position of the sensor based on whether or not the monitoring target area can be specified or the position of the monitoring target area in the measurement target area.
Sensor installation support methods, including. Computer,
A data acquisition unit that acquires measurement data of the measurement target area measured by the sensor,
An area identification unit that attempts to identify a monitoring target area where an object should be detected based on the measurement data, and an area identification unit.
An installation position determination unit that determines whether or not the sensor installation position needs to be changed based on whether or not the monitoring target area can be specified or the position of the monitoring target area in the measurement target area.
A program to function as a sensor installation support device equipped with.

Images