Monitoring device

Abstract

To provide a monitoring device with an excellent monitoring ability of a working area.SOLUTION: A monitoring device 1 of the present invention performs the monitoring of a working area 100a where cargo handling work of a cargo 200 is done by a cargo handling vehicle 3. The monitoring device 1 comprises a camera 13 and a device body 19 as a setting part and a determination part. The camera 13 can obtain photographed images 11 taken from above the working area 100a, the cargo handling vehicle 3, and a target object 5. The device body 19 sets a first region X1 contacting an outline of a specific part 3c in the cargo handling vehicle 3, and a second region X2 contacting an outline of the target object 5, with respect to the photographed mage 11. The device body 19 determines that it is in a cautionary state if the first region X1 and the second region X2 overlap at a predetermined value or more in the photographed image 11.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a monitoring device. [Background technology]

[0002] Various monitoring devices have been proposed for monitoring work areas where cargo handling operations are performed by cargo handling vehicles. Such a monitoring device is disclosed, for example, in Patent Document 1. This monitoring device includes a camera and a control unit. The camera is attached to the cargo handling vehicle and captures images of an area behind the cargo handling vehicle in the work area. The control unit is attached to the cargo handling vehicle and connected to the camera. The cargo handling vehicle is specifically a manned forklift operated by a driver.

[0003] In this monitoring device, a control unit extracts a human image, which is a target object, from a captured image acquired by a camera. The control unit also estimates the skeleton of the human image as a virtual skeleton, associates the virtual skeleton with the extracted human image, and measures the length of a portion of the virtual skeleton. If the measured length of the portion of the virtual skeleton exceeds a threshold, the control unit determines that a human is approaching the rear of the loading / unloading vehicle. In this manner, the monitoring device monitors the work area. Furthermore, if the monitoring device determines that a human is approaching the rear of the loading / unloading vehicle, it notifies the operator of the loading / unloading vehicle that a human is approaching the rear of the loading / unloading vehicle. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2022-96845 Summary of the Invention [Problem to be solved by the invention]

[0005] This type of monitoring device can be used to monitor whether a specific part of a cargo handling vehicle is approaching an object. However, in the conventional monitoring device, a camera attached to the cargo handling vehicle captures an area behind the cargo handling vehicle in the work area. Therefore, if the specific part and object are located in front of the camera on the cargo handling vehicle, these specific parts and objects are located in the camera's blind spot when capturing the image. As a result, in this monitoring device, even if an object is actually approaching the specific part from the front in the work area, the control unit cannot determine that the specific part and object are approaching each other. As a result, this monitoring device cannot adequately monitor the work area.

[0006] The present invention has been made in view of the above-mentioned conventional circumstances, and an object to be achieved is to provide a monitoring device that has excellent capabilities for monitoring a work area. [Means for solving the problem]

[0007] The monitoring device of the present invention is a monitoring device for monitoring a work area where cargo handling work is performed by a cargo handling vehicle, a camera capable of acquiring photographed images of the work area, the cargo handling vehicle, and an object that is present in the work area and is different from the cargo handling vehicle, taken from above; a setting unit that sets a first region adjacent to a contour of a specific portion of the cargo handling vehicle and a second region adjacent to a contour of the target object in the captured image; The image capturing device is characterized by comprising a determining unit that determines that a caution is required if the first area and the second area overlap by a predetermined value or more in the captured image.

[0008] In the monitoring device of the present invention, the camera can capture images of the work area, the loading vehicle, and the target object from above. As a result, with this monitoring device, a specific part is unlikely to be located in the blind spot of the camera when taking images. Furthermore, with this monitoring device, regardless of the position of the target object relative to the specific part in the work area, it is unlikely to be located in the blind spot of the camera when taking images.

[0009] For these reasons, in this monitoring device, the camera can preferably capture an image of the cargo handling vehicle and the target object, including the specific portion. As a result, in this monitoring device, the setting unit can preferably set the first area and the second area in the captured image. Therefore, the determination unit can accurately determine whether the first area and the second area in the captured image overlap by a predetermined value or more, and therefore can preferably determine that a caution is required when the first area and the second area overlap by a predetermined value or more.

[0010] Therefore, the monitoring device of the present invention has excellent monitoring capabilities for the work area.

[0011] The setting unit may set the first area and the second area to be rectangular and planar, respectively. The determination unit may then determine that a location where the first area and the second area overlap is an overlapping area, and that a caution is required if the area of ​​the overlapping area is equal to or greater than a predetermined ratio of the area of ​​the first area.

[0012] In this case, the processing load imposed on the setting unit when setting the first and second areas from the captured image can be reduced. Also, in this monitoring device, the determination unit can appropriately determine whether or not the state requires attention while reducing the processing load on the determination unit.

[0013] The cargo handling vehicle may be a forklift having forks that can be raised and lowered while loading cargo, and the specific part may be the forks. Preferably, the target object is a human being.

[0014] In this case, the determination unit can suitably determine whether the forks of the forklift are approaching a person. Here, the determination unit can determine that a caution is required not only when a person is near the forks, but also when the forklift is being used in an inappropriate manner, such as when the forks are raised or lowered with a person on them.

[0015] The monitoring device of the present invention preferably includes a warning unit that issues a warning to at least a person when the judgment unit judges that a caution is required. In this case, the warning can encourage people to move away from the forks and ultimately the forklift, thereby preventing situations in the work area where people come into contact with the forklift and the forks.

[0016] The monitoring device of the present invention preferably also includes a restricting unit that restricts the operation of the cargo handling vehicle when the determining unit determines that a caution is required. In this case, too, it is possible to prevent the occurrence of an incident in the work area where the cargo handling vehicle, including a specific part, comes into contact with an object. Note that restricting the operation of the cargo handling vehicle may include restricting the operation of the cargo handling vehicle itself, such as the running of the cargo handling vehicle, as well as restricting only the operation of a specific part.

[0017] The monitoring device of the present invention preferably also includes a storage unit that stores the date and time when the determination unit determines that the vehicle is in a state requiring attention as a monitoring record. In this case, the monitoring record can be used to educate operators of cargo handling vehicles. [Effects of the Invention]

[0018] The monitoring device of the present invention has excellent monitoring capabilities for the work area. [Brief explanation of the drawings]

[0019] [Figure 1] FIG. 1 is a schematic diagram of a monitoring device according to an embodiment. [Figure 2] FIG. 2 is a schematic diagram of a forklift. [Figure 3] FIG. 3 is a schematic diagram of an image captured by a camera in the monitoring device of the embodiment. [Figure 4] FIG. 4 is a schematic diagram of an image captured by a camera in the monitoring device of the embodiment. [Figure 5] FIG. 5 is a schematic diagram of an image captured by a camera in the monitoring device of the embodiment. [Figure 6] FIG. 6 is a schematic diagram of a forklift when using forks to lift up and down a pallet together with a worker on the pallet. [Figure 7] FIG. 7 is a schematic diagram of an image captured by a camera in the monitoring device of the embodiment. [Figure 8] FIG. 8 is a flow diagram showing a control flow in the monitoring device of the embodiment. [Figure 9] FIG. 9 is a schematic diagram of the monitoring device of the embodiment, in which the first and second areas are set in the captured image of FIG. [Figure 10] FIG. 10 is a schematic diagram showing the positional relationship between the first area and the second area in the captured image of FIG. 2 in the monitoring device of the embodiment. [Figure 11] FIG. 11 is a schematic diagram of the monitoring device of the embodiment, in which the first and second areas are set in the captured image of FIG. [Figure 12] FIG. 12 is a schematic diagram showing the positional relationship between the first area and the second area in the captured image of FIG. 3 in the monitoring device of the embodiment. [Figure 13] FIG. 13 is a schematic diagram of the monitoring device of the embodiment, in which the first and second areas are set in the captured image of FIG. [Figure 14] FIG. 14 is a schematic diagram showing the positional relationship between the first area and the second area in the captured image of FIG. 4, relating to the monitoring device of the embodiment. [Figure 15] FIG. 15 is a schematic diagram of the monitoring device of the embodiment, in which the first and second areas are set in the captured image of FIG. [Figure 16] FIG. 16 is a schematic diagram showing the positional relationship between the first area and the second area in the captured image of FIG. 7, relating to the monitoring device of the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0020] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, specific embodiments of the present invention will be described with reference to the drawings.

[0021] As shown in FIG. 1, a monitoring device 1 of the embodiment is used in a warehouse 100. A plurality of forklifts 3 and a plurality of workers 5 are arranged in the warehouse 100. The forklifts 3 are an example of a "cargo handling vehicle" in the present invention. The workers 5 are an example of a "human being" and therefore an "object" in the present invention. The number of forklifts 3 and the number of workers 5 arranged in the warehouse 100 can be changed as appropriate.

[0022] In this embodiment, the up-down direction, left-right direction, and front-rear direction of the warehouse 100 are defined by solid arrows shown in Figure 1. These up-down direction, left-right direction, and front-rear direction are perpendicular to each other. Furthermore, the up-down direction, left-right direction, and front-rear direction of the forklift 3 correspond to the up-down direction, left-right direction, and front-rear direction of the warehouse 100.

[0023] The warehouse 100 is a building that stores a plurality of packages 200 and from which each of the stored packages 200 can be retrieved. The warehouse 100 has a work area 100a, a ceiling 100b, and peripheral walls 100c. The work area 100a is specifically the floor of the warehouse 100. In the work area 100a, forklifts 3 travel and perform loading and unloading work on the packages 200. Also, in the work area 100a, workers 5 move around and perform loading and unloading work on the packages 200. Although not shown in the figure, storage shelves for storing the packages 200 are installed in the work area 100a.

[0024] The ceiling 100b is spaced upward from the work area 100a, the forklifts 3, and the workers 5. The peripheral wall 100c is located between the work area 100a and the ceiling 100b. The peripheral wall 100c connects the work area 100a and the ceiling 100b, and encloses the work area 100a and the ceiling 100b from the outside.

[0025] As shown in Fig. 2, the forklift 3 has a vehicle body 3a, a pair of masts 3b, and forks 3c. The forklift 3 is a manned forklift operated by a driver 7. The forklift 3 may also be configured so that the driver 7 remotely controls it. Alternatively, the forklift 3 may be an unmanned forklift capable of automatic operation through autonomous control.

[0026] The vehicle body 3a is provided with a driver's cab 31 in which the operator 7 sits. The vehicle body 3a also includes a vehicle control unit 33 that controls the operation of the forklift 3, a power unit (not shown) that operates the forklift 3, and the like. The vehicle control unit 33 is an example of the "regulating unit" in the present invention. As shown in FIG. 1, the vehicle control unit 33 is communicably connected to the device body 19, which will be described later.

[0027] As shown in Figures 2 and 3, both masts 3b are disposed in front of the vehicle body 3a and extend in the vertical direction. The masts 3b are disposed spaced apart in the left-right direction of the vehicle body 3a. The forks 3c are disposed in front of both masts 3b. The forks 3c are capable of moving up and down along both masts 3b while carrying luggage 200. The luggage 200 may be placed directly on the forks 3c, or the luggage 200 may be placed on a pallet 201 or the like shown in Figure 6.

[0028] 1, the monitoring device 1 includes a camera 13, a warehouse speaker 15, a plurality of vehicle speakers 17, the vehicle control unit 33, and a device main body 19. The warehouse speaker 15 and each vehicle speaker 17 are examples of the "warning unit" of the present invention. The device main body 19 is an example of the "extraction unit," "determination unit," and "storage unit" of the present invention.

[0029] Camera 13 is attached facing downward on ceiling 100b. Camera 13 is located at approximately the center of ceiling 100b, that is, approximately the center of ceiling 100b in the front-to-back and left-to-right directions. As a result, camera 13 can be said to be installed on ceiling 100b at a position that is the upper center of work area 100a. Thus, camera 13 is located in warehouse 100 above work area 100a, each forklift 3, and each worker 5. Note that camera 13 does not have to be installed at a position that is the upper center of work area 100a, and may be installed at a position that allows a bird's-eye view of work area 100a from above.

[0030] The camera 13 photographs the interior of the warehouse 100 from the ceiling 100b downward to obtain the photographed image 11 shown in FIGS. 3 to 5 and 7. That is, the camera 13 obtains the photographed image 11 obtained by photographing the work area 100a, each forklift 3, and each worker 5 from the ceiling 100b in a bird's-eye view. The camera 13 also obtains the photographed image 11 as a video. As described above, the camera 13 is disposed in a position that is approximately the center of the ceiling 100b. The camera 13 is set to an angle of view that allows it to photograph the entire work area 100a from this position. As a result, the camera 13 photographs the entire work area 100a, thereby enabling it to photograph all of the forklifts 3 and workers 5 performing loading and unloading operations in the work area 100a.

[0031] Furthermore, the camera 13 is connected to the device main body 19 so as to be able to communicate with the device main body 19. As a result, the camera 13 transmits the captured image 11 that it has acquired to the device main body 19.

[0032] The warehouse speaker 15 is attached to the ceiling 100b. The warehouse speaker 15 is connected to the device main body 19 so as to be able to communicate with the device main body 19. The warehouse speaker 15 may also be attached to the peripheral wall 100c of the warehouse 100.

[0033] 1 and 2, each vehicle speaker 17 is attached to the forklift 3 and disposed in the driver's cab 31. Each vehicle speaker 17 is connected to a vehicle control unit 33 of each forklift 3. Note that each vehicle speaker 17 may be omitted.

[0034] 1, the device main body 19 is located outside the warehouse 100. The device main body 19 is communicatively connected to an external network such as the Internet. A storage medium 191 and a control circuit 192 are provided within the device main body 19. The device main body 19 may also be located within the warehouse 100 and communicatively connected to an internal network such as an intranet.

[0035] A monitoring control application (not shown) is stored in the storage medium 191. The storage medium 191 is also capable of storing monitoring records, which will be described later. The monitoring control application includes a control program for controlling the operation of the camera 13, warehouse speaker 15, and each vehicle control unit 33. The monitoring control application also includes information on the shapes of the forklift 3, the forks 3c, the luggage 200, the pallet 201, and the person, as well as information on the position of the forks 3c on the forklift 3.

[0036] The control circuit 192 is composed of a control board and multiple semiconductors mounted on the control board. The control circuit 192 performs various arithmetic processing based on a monitoring control application. As a result, the control circuit 192, and ultimately the device main body 19, controls the operation of the camera 13, the warehouse speaker 15, and each vehicle control unit 33. The device main body 19 also performs an identification process to identify a specific part and the worker 5 from the captured image 11. In this embodiment, the fork 3c of the forklift 3 is defined as the "specific part" in the present invention. Therefore, the device main body 19 identifies the fork 3c and the worker 5 from the captured image 11 in the identification process. The device main body 19 also performs a setting process to set the first area X1 and the second area X2 shown in FIGS. 9 to 16 for the captured image 11, and also performs a determination process to determine whether or not a caution is required.

[0037] The monitoring device 1 configured as described above monitors the work area 100a while loading and unloading work is being performed by the forklifts 3 and workers 5 in the work area 100a. To monitor the work area 100a, the device main body 19 of the monitoring device 1 executes a monitoring control application. This causes the monitoring device 1 to start monitoring the work area 100a.

[0038] When monitoring of the work area 100a begins, first, the device main body 19 controls the operation of the camera 13. This activates the camera 13, which then acquires photographed images 11 of the work area 100a, each forklift 3, and each worker 5 (step S101 in FIG. 8). The camera 13 then transmits the photographed images 11 to the device main body 19. Here, in this monitoring device 1, the camera 13 constantly transmits the photographed images 11 to the device main body 19 while the camera 13 is capturing images.

[0039] Furthermore, in the work area 100a, since each forklift 3 and each worker 5 is performing cargo handling work, the positions of the forklift 3 and the worker 5 change appropriately in the photographed image 11 as shown in FIGS.

[0040] However, as shown in Fig. 6, there may be cases where an inappropriate act is performed, such as raising and lowering the forks 3c while a worker 5 is on the pallet 201. When such an act is performed, the photographed image 11 shows each forklift 3 and worker 5 in the state shown in Fig. 7. For ease of explanation, in Figs. 3 to 5 and 7, there is one forklift 3 and one worker 5 in the photographed image 11.

[0041] The device main body 19 receives the captured image 11 from the camera 13 and identifies the fork 3c and the worker 5 from the captured image 11 (step S102 in FIG. 8 ). To identify the fork 3c and the worker 5, the device main body 19 references information about the shapes of the forklift 3, the fork 3c, the luggage 200, the pallet 201, and the person, and information about the position of the fork 3c on the forklift 3, which are stored in the monitoring control application. The device main body 19 also references information about past identifications of the fork 3c and the worker 5 via an external network. The device main body 19 then performs machine learning based on this information to identify the fork 3c and the worker 5 from the captured image 11. As a result, even if the fork 3c or the worker 5 is partially hidden by, for example, the luggage 200 or the pallet 201 in the captured image 11, the device main body 19 can appropriately identify the fork 3c and the worker 5 from the captured image 11 by estimating the shapes of the hidden parts of the fork 3c and the worker 5. The device main body 19 also stores, on the external network, information that the fork 3c and the worker 5 have been identified. Note that the device main body 19 may identify the fork 3c and the worker 5 from the captured image 11 by other methods.

[0042] Next, the device main body 19 sets the first area X1 and the second area X2 shown in FIGS. 9 to 16 in the captured image 11 (step S103 in FIG. 8). When setting the first area X1 and the second area X2, the device main body 19 references information from when the first area X1 and the second area X2 were previously set via an external network, based on the area setting algorithm of the monitoring and control application. As a result, the device main body 19 sets the first area X1 and the second area X2 in the captured image 11 while performing machine learning. For ease of explanation, the forklift 3 and the worker 5 are shown by virtual lines in FIGS. 9, 11, 13, and 15. Furthermore, the forklift 3 and the worker 5 are not shown in FIGS. 10, 12, 14, and 16.

[0043] Here, the device main body 19 sets the first area X1 to a rectangular plane tangent to the outline of the fork 3c. The device main body 19 also sets the second area X2 to a rectangular plane tangent to the outline of the worker 5. Although detailed illustration is omitted, when setting the first area X1, the device main body 19 sets multiple first provisional areas each having a rectangular plane tangent to the outline of the fork 3c. From these first provisional areas, the device main body 19 selects an optimal first provisional area that meets the conditions of being tangent to the outline of the fork 3c and overlapping with the entire fork 3c, and designates this as the first area X1. Similarly, the device main body 19 sets multiple second provisional areas each having a rectangular plane tangent to the outline of the worker 5. From these second provisional areas, the device main body 19 selects an optimal second provisional area that meets the conditions of being tangent to the outline of the worker 5 and overlapping with the entire worker 5, and designates this as the second area X2.

[0044] As a result, in the photographed image 11, the first area X1 is set at approximately the same position as the fork 3c, and the second area X2 is set at approximately the same position as the worker 5. The device main body 19 also stores information on the setting of the first area X1 and the second area X2 on the external network. Note that the device main body 19 may set the first area X1 and the second area X2 in the photographed image 11 by other methods.

[0045] Then, the device main body 19 determines whether or not the set first area X1 and second area X2 overlap in the photographed image 11 (step S104).

[0046] Specifically, in the photographed image 11 captured by the camera 13, when the worker 5 is spaced apart from the fork 3c by a certain distance as shown in Fig. 3, the first area X1 and the second area X2 do not overlap in the photographed image 11 as shown in Fig. 10 (step S104: NO in Fig. 8). As a result, in such a case, the device main body 19 determines that the fork 3c and the worker 5 are spaced apart in the work area 100a, and therefore determines that the state does not require attention (step S120).

[0047] On the other hand, when the worker 5 approaches the fork 3c in the photographed image 11 captured by the camera 13 as shown in Figures 4 and 5, the first area X1 and the second area X2 are set to be partially overlapping in the photographed image 11 as shown in Figures 12 and 14. Therefore, in such a case, it is determined that the first area X1 and the second area X2 are overlapping in the photographed image 11 (step S104: YES).

[0048] Furthermore, when the forks 3c are raised and lowered with the worker 5 on the pallet 201, the second area X2 is set to be completely overlapped with the first area X1 in the photographed image 11, as shown in Fig. 16. Therefore, even in such a case, the device main body 19 determines that the first area X1 and the second area X2 are overlapping (step S104: YES).

[0049] If the device main body 19 determines that the first area X1 and the second area X2 overlap, it sets the overlapping portion of the first area X1 and the second area X2 as an overlapping area X3. Then, the device main body 19 compares the area of ​​the first area X1 with the area of ​​the overlapping area X3 to determine whether the area of ​​the overlapping area X3 is equal to or greater than a predetermined ratio relative to the area of ​​the first area X1. In this embodiment, this predetermined ratio is set to 50%. In other words, the device main body 19 determines whether the area of ​​the overlapping area X3 is equal to or greater than 50% of the area of ​​the first area X1. Note that the value of the predetermined ratio is not limited to 50% and can be set as appropriate.

[0050] 12, if the device main body 19 determines that although an overlapping region X3 exists in the captured image 11, the area of ​​the overlapping region X3 is smaller than 50% of the area of ​​the first region X1 (step S105 in FIG. 8: NO), the device main body 19 determines that the state does not require attention (step S120). That is, in this monitoring device, when the fork 3c and the worker 5 are in the positional relationship shown in FIG. 4 in the work area 100a, the device main body 19 does not determine that the state requires attention.

[0051] In contrast, as shown in Figures 14 and 16, if the device main body 19 determines that an overlapping area X3 exists in the captured image 11 and that the area of ​​this overlapping area X3 is 50% or more of the area of ​​the first area X1 (step S105 in Figure 8: YES), the device main body 19 determines that the fork 3c and the worker 5 are close to each other in the work area 100a and that a caution is required (step S106).

[0052] Then, by determining that the state requires caution, the device main body 19 issues a warning to the worker 5 to move away from the forks 3c through the warehouse speaker 15. The device main body 19 also issues a warning to the operator 7 of the forklift 3 through the vehicle speaker 17 that the worker 5 is near the forks 3c (step S107).

[0053] Furthermore, by determining that the device main body 19 is in a state requiring attention, the device main body 19 transmits a restriction signal to the vehicle control unit 33. As a result, the vehicle control unit 33 restricts the lifting, lowering, and tilting of the forks 3c (step S108). Note that the restriction on the lifting, lowering, and tilting of the forks 3c is automatically released, for example, after a predetermined time has elapsed. Furthermore, the vehicle control unit 33 may release the restriction on the lifting, lowering, and tilting of the forks 3c when a restriction release signal is transmitted from the device main body 19.

[0054] Furthermore, the device main body 19 records the date and time when it was determined that the state required attention, as a monitoring record, in its own storage medium 191 (step S109).

[0055] Thus, while the camera 13 continues to capture the image 11 (step S110: NO), the device main body 19 again performs the processes from step S102 onwards. On the other hand, when the device main body 19 stops the camera 13 and the camera 13 finishes capturing the image 11 (step S110: YES), monitoring of the work area 100a by the monitoring device 1 ends.

[0056] In this way, in this monitoring device 1, the camera 13 can acquire a captured image 11 in which the work area 100a, the forklift 3, and the worker 5 are captured from above in a bird's-eye view. This makes it difficult for the fork 3c to be positioned in the blind spot of the camera 13 when capturing an image in this monitoring device 1. Also, in this monitoring device 1, no matter where the worker 5 is positioned relative to the fork 3c in the work area 100a, the worker 5 is unlikely to be positioned in the blind spot of the camera 13 when capturing an image.

[0057] For these reasons, in this monitoring device 1, the camera 13 can preferably capture an image of the forklift 3, including the fork 3c, and the worker 5. As a result, in this monitoring device 1, the device main body 19 can preferably identify the fork 3c and the worker 5 from the captured image 11, and therefore the device main body 19 can preferably set the first region X1 and the second region X2 in the captured image 11. As a result, the device main body 19 can accurately determine whether the area of ​​the overlapping region X3 in the captured image 11 is 50% or more of the area of ​​the first region X1, and therefore the device main body 19 can preferably determine whether or not a caution is required.

[0058] Furthermore, the monitoring device 1 can also suitably determine that a caution is required when the forks 3c are raised or lowered while the worker 5 is on the pallet 201. Therefore, the monitoring device 1 can also suitably monitor the worker 5 or the like for performing prohibited actions in the work area 100a.

[0059] Therefore, the monitoring device 1 of the embodiment has excellent monitoring capabilities for the work area 100a.

[0060] In particular, in this monitoring device 1, the device main body 19 sets the first area X1 to be a rectangular plane tangent to the contour of the fork 3c, and sets the second area X2 to be a rectangular plane tangent to the contour of the worker 5. Therefore, the processing load on the device main body 19 can be reduced compared to, for example, setting the first area X1 to be a complex shape that follows the contour of the fork 3c and setting the second area X2 to be a complex shape that follows the contour of the worker 5.

[0061] Furthermore, this monitoring device 1 determines that the device main body 19 is in a state requiring attention if the area of ​​the overlapping region X3 is 50% or more of the area of ​​the first region X1, which also reduces the processing burden when determining whether the device main body 19 is in a state requiring attention. Furthermore, this monitoring device 1 determines that the device main body 19 is not in a state requiring attention if the area of ​​the overlapping region X3 is less than 50% of the area of ​​the first region X1. In other words, this monitoring device 1 does not uniformly determine that the device main body 19 is in a state requiring attention even if the first region X1 and the second region X2 overlap.

[0062] Therefore, this monitoring device 1 can prevent the device main body 19 from determining that a condition requires attention, for example, when the fork 3c and the worker 5 inevitably come close to each other to a certain extent when performing loading and unloading work in the work area 100a, and also when the fork 3c and the worker 5 come close to each other but the safety of the worker 5 is guaranteed.

[0063] Furthermore, in this monitoring device 1, when the device main body 19 determines that a caution is required, a warning is issued to the worker 5 and the operator 7, and the raising and lowering of the forks 3c is restricted. This makes it possible for this monitoring device 1 to prevent the forks 3c from coming into contact with the worker 5. Furthermore, in the event that the worker 5 or the like is performing an action that is prohibited in the work area 100a, the monitoring device 1 can issue a warning to appropriately stop the action.

[0064] In addition, this monitoring device 1 records the date and time when the device main body 19 determines that a state requiring caution is occurring as a monitoring record, making it possible to provide safety education and other guidance to the worker 5 and operator 7 based on the monitoring record.

[0065] Furthermore, in this monitoring device 1, the device main body 19 performs machine learning to identify the fork 3c and the worker 5 and set the first area X1 and the second area X2. Therefore, in this monitoring device 1, the device main body 19 can, by accumulating experience, suitably improve the accuracy in identifying the fork 3c and the worker 5 and suitably improve the accuracy in setting the first area X1 and the second area X2.

[0066] Although the present invention has been described above with reference to the examples, it goes without saying that the present invention is not limited to the above examples and can be modified and applied as appropriate within the scope of the invention.

[0067] For example, in the monitoring device 1 of the embodiment, one camera 13 attached to the ceiling 100b photographs the work area 100a, the forklift 3, and the worker 5 from above to obtain the photographed image 11. However, this is not limiting, and multiple cameras 13 may be attached to the ceiling 100b, and each camera 13 may photograph the work area 100a, the forklift 3, and the worker 5 from above to obtain the photographed image 11.

[0068] In the monitoring device 1 of the embodiment, the camera 13 may be attached to a pillar or the like in the warehouse 100 so that the camera 13 can photograph the work area 100a, the forklift 3, and the worker 5 from above.

[0069] Furthermore, in the monitoring device 1 of the embodiment, the camera 13 acquires the photographed image 11 in which the work area 100a, each forklift 3, and each worker 5 are photographed from the ceiling 100b in a bird's-eye view. However, the present invention is not limited to this, and the camera 13 may photograph the work area 100a, each forklift 3, and each worker 5 from above in a manner other than a bird's-eye view.

[0070] Furthermore, in the monitoring device 1 of the embodiment, the camera 13 acquires the captured image 11 as a moving image. However, this is not limiting, and the camera 13 may acquire the captured image 11 as a still image at predetermined time intervals.

[0071] In addition, in the monitoring device 1 of the embodiment, images of the work area 100a, the forklift 3, and the worker 5 taken from the side at different angles can be obtained using multiple cameras 13, and by combining these images, an image 11 of the work area 100a, the forklift 3, and the worker 5 taken from above can be obtained.

[0072] In addition, in the monitoring device 1 of the embodiment, the forklift 3 is defined as the "cargo handling vehicle" in the present invention. However, the present invention is not limited to this, and a manned turret truck, an unmanned turret truck, or the like may also be defined as the "cargo handling vehicle" in the present invention.

[0073] In addition, in the monitoring device 1 of the embodiment, the fork 3c is the "specific portion" in the present invention, and the worker 5 is the "target body" in the present invention. However, without being limited thereto, the vehicle body 3a of the forklift 3 or the like may be the "specific portion" in the present invention, and a pillar or the like installed in the work area 100a may be the "target body" in the present invention.

[0074] In addition, in the monitoring device 1 of the embodiment, if the first area X1 and the second area X2 overlap but the area of ​​the overlapping area X3 is smaller than 50% of the area of ​​the first area X1, the device main body 19 may issue a notification to the operator 7 of the forklift 3 or the worker 5 to warn them.

[0075] Furthermore, in the monitoring device 1 of the embodiment, the work area 100a is the floor surface of the warehouse 100, but this is not limiting, and the work area 100a may be outdoors, for example.

[0076] In the monitoring device 1 of the embodiment, the device main body 19 serves as the "extraction unit," "determination unit," and "storage unit" of the present invention. However, without being limited to this, the monitoring device 1 may have a device dedicated to the "extraction unit" of the present invention, a device dedicated to the "determination unit" of the present invention, and a device dedicated to the "storage unit" of the present invention.

[0077] This specification also includes the following inventions. (Appendix 1) A monitoring device for monitoring a work area where cargo handling work is performed by a cargo handling vehicle, a camera capable of acquiring photographed images of the work area, the cargo handling vehicle, and an object that is present in the work area and is different from the cargo handling vehicle, taken from above; a setting unit that sets a first region adjacent to a contour of a specific portion of the cargo handling vehicle and a second region adjacent to a contour of the target object in the captured image; A monitoring device characterized by comprising a judgment unit that judges that a state requires attention if the first area and the second area overlap by a predetermined value or more in the captured image. (Appendix 2) the setting unit sets the first area and the second area to have a rectangular planar shape, The monitoring device of claim 1, wherein the judgment unit determines that the area where the first area and the second area overlap is an overlapping area, and determines that the state requires attention if the area of ​​the overlapping area is equal to or greater than a predetermined ratio of the area of ​​the first area. (Appendix 3) the cargo handling vehicle is a forklift having forks that can be raised and lowered while loading the cargo, the specific site is the fork, 3. The monitoring device according to claim 1, wherein the target is a human. (Appendix 4) 4. The monitoring device according to claim 3, further comprising a warning unit that issues a warning to at least the person when the judgment unit judges that the state requires attention. (Appendix 5) 5. The monitoring device according to claim 1, further comprising a restricting unit that restricts the operation of the cargo handling vehicle when the determining unit determines that the cargo handling vehicle is in the caution required state. (Appendix 6) 6. The monitoring device according to claim 1, further comprising a storage unit configured to store, as a monitoring record, the date and time when the determination unit determined that the state requires attention. [Industrial Applicability]

[0078] The present invention can be used in monitoring devices for warehouses, factories, port facilities, and the like. [Explanation of symbols]

[0079] 1...Monitoring device 3...Forklift (cargo handling vehicle) 3c...Fork (specific part) 5...Worker (object, human) 11...Photo 13...Camera 15...Warehouse speaker (warning unit) 17...Vehicle speaker (warning unit) 19...Device main body (setting unit, determination unit, memory unit) 33...Vehicle control unit (regulation unit) 100a...Work area 200…Luggage X1…1st area X2…Second area X3…Overlapping area

Claims

1. A monitoring device for monitoring a work area where cargo handling work is performed by a cargo handling vehicle, a camera capable of acquiring photographed images of the work area, the cargo handling vehicle, and an object that is present in the work area and is different from the cargo handling vehicle, taken from above; a setting unit that sets a first region that is adjacent to a contour of a specific portion of the cargo handling vehicle and a second region that is adjacent to a contour of the target object in the captured image; A monitoring device characterized by comprising a judgment unit that judges that a caution is required if the first area and the second area overlap by a predetermined value or more in the captured image.

2. the setting unit sets the first region and the second region to have a rectangular planar shape, The monitoring device of claim 1, wherein the judgment unit determines that the area where the first area and the second area overlap is an overlapping area, and if the area of ​​the overlapping area is equal to or greater than a predetermined ratio of the area of ​​the first area, the monitoring device judges that the state requires attention.

3. the cargo handling vehicle is a forklift having forks that can be raised and lowered while loading the cargo, the specific site is the fork, 3. The monitoring device according to claim 1, wherein the target is a human being.

4. 4. The monitoring device according to claim 3, further comprising a warning unit that issues a warning to at least the person when the judgment unit judges that the state requires attention.

5. 3. The monitoring device according to claim 1, further comprising a restricting unit that restricts the operation of the cargo handling vehicle when the determining unit determines that the cargo handling vehicle is in the caution-requiring state.

6. 3. The monitoring device according to claim 1, further comprising a storage unit for storing, as a monitoring record, the date and time when the determination unit determined that the condition requires attention.

Images