Work machine and monitor system

Abstract

To provide a work machine capable of properly grasping abnormality having occurred in another work machine.SOLUTION: The work machine comprises: a periphery monitor camera which images the periphery; and a controller. In a case of having detected abnormality in another work machine operating within a predetermined distance range from the work machine, the controller extracts an extraction image including an abnormality detection time out of an image obtained by imaging by the periphery monitor camera.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to a work machine equipped with a surroundings monitoring camera and a monitoring system. [Background technology]

[0002] Work machines, typified by hydraulic excavators, are used in unstable locations such as rough terrain and operate for long periods in harsh environments, so there is a risk of various problems occurring (for example, tipping over, submersion in water, engine malfunctions, etc.) To solve these problems, Patent Documents 1 and 2 disclose work machines equipped with detection sensors that detect the state of the vehicle body and surroundings monitoring cameras that monitor the surroundings of the vehicle. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2022-155699 [Patent Document 2] Patent No. 6545498 Summary of the Invention [Problem to be solved by the invention]

[0004] However, depending on the type of abnormality, it may not be possible to accurately grasp the situation using only the images from the surrounding monitoring camera mounted on the vehicle.

[0005] The present invention has been made in consideration of the above-described circumstances, and its object is to provide a work machine that is capable of appropriately detecting an abnormality that has occurred in another work machine. [Means for solving the problem]

[0006] In order to achieve the above object, the present invention provides a work machine equipped with a surroundings monitoring camera that captures images of the surroundings and a controller, wherein when the controller detects an abnormality in another work machine operating within a predetermined distance range from the work machine, it extracts an extracted image from the image captured by the surroundings monitoring camera, the extracted image including the time the abnormality was detected. [Effects of the Invention]

[0007] According to the present invention, it is possible to obtain a work machine that is capable of appropriately detecting an abnormality that has occurred in another work machine. Note that problems, configurations, and effects other than those described above will become apparent from the description of the following embodiments. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a conceptual diagram of a monitoring system. [Figure 2] FIG. 2 is a hardware configuration diagram of the work machine. [Figure 3] FIG. 2 is a hardware configuration diagram of a monitoring server. [Figure 4] 10 is a flowchart of a monitoring process according to the present embodiment. [Figure 5] 10A and 10B are diagrams illustrating an example of extracting an extracted image including an abnormality detection time from a captured image. [Figure 6] FIG. 10 is a diagram showing an example of trimming an area including a work machine from an extracted image. [Figure 7] 10 is a screen example of a status notification screen. [Figure 8] FIG. 10 is a diagram showing another example of the data structure of a captured image according to the first modification. [Figure 9] 10 is a flowchart of a monitoring process according to Modification 2. DETAILED DESCRIPTION OF THE INVENTION

[0009] [Overview of monitoring system 100] FIG. 1 is a conceptual diagram of a monitoring system 100. The monitoring system 100 is a system in which multiple work machines 1, 2, and 3 mutually monitor each other for abnormalities in the vehicle bodies from a third-party perspective. The monitoring system 100 comprises, for example, multiple work machines 1, 2, and 3, a monitoring server 4, and a monitoring terminal 5. Note that the number of work machines 1 to 3 is not limited to three. Also, one or both of the monitoring server 4 and the monitoring terminal 5 can be omitted.

[0010] [Configuration of work machines 1 to 3] The work machines 1 to 3 according to this embodiment are hydraulic excavators. However, specific examples of the work machines 1 to 3 are not limited to hydraulic excavators, and any work machine such as a dump truck, wheel loader, or crane can be used. The work machines 1 to 3 operate within a predetermined distance range (for example, the same work site). More specifically, the work machines 1 to 3 operate within a range where they can capture images of each other using a surroundings monitoring camera 13, which will be described later.

[0011] Furthermore, each of the work machines 1 to 3 is assigned an identifier (hereinafter referred to as a "machine identifier") that uniquely identifies it. Below, work machine 1 is identified by the machine identifier "001," work machine 2 by the machine identifier "002," and work machine 3 by the machine identifier "003." Below, work machine 1 will be explained, but work machines 2 to 3 also have a common configuration.

[0012] Figure 2 is a hardware configuration diagram of the work machine 1. As shown in Figure 2, the work machine 1 is equipped with a controller 10, a surroundings monitoring camera 13, a status detection sensor 14, a GPS antenna 15, and a communication interface (hereinafter referred to as "communication I / F") 16.

[0013] The controller 10 includes a CPU (Central Processing Unit) 11 and a memory 12. The memory 12 is configured, for example, with a ROM (Read Only Memory), a RAM (Random Access Memory), an HDD (Hard Disk Drive), or a combination of these. The controller 10 realizes the processes described below by having the CPU 11 read and execute program code stored in the ROM or HDD. The RAM is used as a work area when the CPU 11 executes the program.

[0014] However, the specific configuration of the controller 10 is not limited to this, and may be realized by hardware such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field-Programmable Gate Array).

[0015] The perimeter monitoring camera 13 captures images of the surroundings of the work machine 1 to generate captured images. The captured images in this embodiment are video (moving images), but may also be still images captured repeatedly at predetermined time intervals. The captured images are, for example, panoramic images of the surroundings of the work machine 1. The perimeter monitoring camera 13 may be made up of multiple cameras with different imaging directions in order to capture panoramic images. Furthermore, the perimeter monitoring camera 13 constantly captures images of the surroundings while the work machine 1 is in operation, and stores image data representing the captured images in the memory 12 as a single file. The configuration of the perimeter monitoring camera 13 is already well known, so a detailed description will be omitted. However, the imaging range of the perimeter monitoring camera 13 does not have to be the entire circumference of the work machine 1, as shown in Figure 6(A), for example, but may be only a portion of the circumference of the work machine 1.

[0016] The status detection sensor 14 is a sensor for detecting the status of the work machine 1. The status detection sensor 14 detects the status of the work machine 1 and outputs a status signal indicating the detected status to the controller 10. There are no particular limitations on specific examples of the status detection sensor 14, but the following sensors are possible. Also, an example of detecting (determining) an abnormality in the work machine 1 based on the detection results of the status detection sensor 14 will be described below, but it is not necessary for the occurrence of an abnormality to be confirmed, and it is sufficient for the controller 10 to be able to detect that there is a possibility of an abnormality.

[0017] As one example, the status detection sensor 14 is a temperature sensor that detects the temperature of the engine (for example, the temperature of the cooling water or the temperature of the exhaust gas). If the temperature detected by the temperature sensor is equal to or greater than a threshold temperature, the controller 10 detects that a fire has broken out around the engine. As another example, the status detection sensor 14 is an angle sensor (gyro sensor) that detects the inclination angle of the work machine 1. If the angle detected by the angle sensor is equal to or greater than a threshold angle, the controller 10 detects that the work machine 1 has overturned.

[0018] The GPS (Global Positioning System) antenna 15 is a position sensor that receives signals from GPS satellites and outputs position information indicating the current position of the work machine 1 to the controller 10. However, the method of acquiring the current position of the work machine 1 is not limited to GPS. The controller 10 may also compare the current position of the work machine 1 acquired from the GPS antenna 15 with a map of the area around the work machine 1 to detect that the work machine 1 has been submerged in a river, pond, lake, ocean, etc. In other words, the GPS antenna 15 may be another example of the condition detection sensor 14.

[0019] The communication I / F 26 is a communication interface that transmits and receives data to and from external devices (for example, work machines 2 and 3, monitoring server 4, monitoring terminal 5) via a communication network (for example, the Internet, a mobile communication system, Wi-Fi (registered trademark)). As an example, the work machines 1 to 3 and the monitoring terminal 5 may communicate via the monitoring server 4, or may communicate directly with each other.

[0020] [Configuration of monitoring server 4] FIG. 3 is a hardware configuration diagram of the monitoring server 4. The monitoring server 4 relays data sent and received between the work machines 1 to 3 and the monitoring terminal 5. The monitoring server 4 may also execute some of the processing shown in FIG. 4 in place of the work machines 1 to 3. The monitoring server 4 is realized by, for example, a workstation or a general-purpose computer such as a personal computer. As shown in FIG. 3, the monitoring server 4 mainly comprises a CPU 21, memory 22, storage 23, an input device 24, a display 25, and a communication I / F 26. The components of the monitoring server 4 are connected to a communication bus 27.

[0021] The CPU 21 performs the processing described below by executing a series of instructions included in the monitoring program 28 loaded into the memory 22. The memory 22 is realized, for example, as a RAM or other volatile memory. The storage 23 is realized, for example, as a ROM, a hard disk drive, a flash memory, or other non-volatile storage device. The monitoring program 28 is stored in the storage 23, and is loaded into the memory 22 as needed and executed by the CPU 21.

[0022] The input device 24 is an input interface, such as a keyboard or pointing device, that accepts input operations from the administrator of the monitoring server 4. The display 25 is an output interface that outputs (displays) information to the administrator of the monitoring server 4. The communication I / F 26 is a communication interface that transmits and receives data to and from external devices (for example, the work machines 1 to 3 and the monitoring terminal 5) via a communication network.

[0023] [Configuration of monitoring terminal 5] The monitoring terminal 5 is a terminal carried by a serviceman or the like who performs maintenance on the work machines 1 to 3. The monitoring terminal 5 is realized, for example, as a tablet terminal, a smartphone, a feature phone, a laptop computer, a desktop computer, etc. The configuration of the monitoring terminal 5 is well known, so a detailed description thereof will be omitted.

[0024] [Monitoring process] Figure 4 is a flowchart of the monitoring process according to this embodiment. The monitoring process is a process for extracting an image showing the condition of work machine 1 from images taken by surroundings monitoring cameras 13 of work machines 2, 3 (second work machines) operating around work machine 1 when an abnormality occurs in work machine 1 (first work machine) of work machines 1 to 3. Work machines 1 to 3 continuously execute the monitoring process shown in Figure 4, for example, while they are in operation (while their engines are running).

[0025] The controller 10 of the work machine 1 waits to execute the processing from step S12 onwards until it detects an abnormality in the work machine 1 based on the status signal output from the status detection sensor 14 (S11: No), and operates in accordance with the operation of the operator in the cab. Similarly, the work machines 2 and 3 also operate in accordance with the operation of the operators in their respective cabs. Furthermore, it is assumed that the surroundings monitoring cameras 13 of the work machines 1 to 3 continuously capture images of the surroundings of their own devices and store image data representing the captured images in memory 12.

[0026] Next, if the status detection sensor 14 detects an abnormality in the work machine 1 (S11: Yes), the controller 10 of the work machine 1 sends an image extraction instruction to the work machines 2, 3 via the communication I / F 16 (S12). The image extraction instruction is an instruction to extract an extracted image that includes the time when the abnormality was detected by the status detection sensor 14 (hereinafter referred to as "abnormality detection time t0") from the images captured by the surroundings monitoring cameras 13 of the work machines 2, 3. The image extraction instruction includes, for example, the machine identifier "001" of the work machine 1, the abnormality detection time t0, and an abnormality identifier that uniquely identifies the detected abnormality.

[0027] As one example, the controller 10 of the work machine 1 may send an image extraction instruction to pre-registered work machines 2 and 3 (for example, work machines working at the same work site). As another example, the work machines 1 to 3 may repeatedly upload position information acquired from their respective GPS antennas 15 to the monitoring server 4 at predetermined time intervals. The controller 10 of the work machine 1 may then inquire of the monitoring server 4 about work machines 2 and 3 that are within a predetermined distance range from the work machine 1 when it detects an abnormality (and sends an image extraction instruction).

[0028] Next, when the controllers 10 of the work machines 2 and 3 receive an image extraction instruction from the work machine 1 via the communications I / F 16 (S12), they execute the processing of steps S13 to S15. As the processing of the work machines 2 and 3 is common, the processing of the work machine 2 will be explained below.

[0029] First, the controller 10 of the work machine 2 extracts an image (hereinafter referred to as an "extracted image") that includes the abnormality detection time t0 from the captured images taken by the perimeter monitoring camera 13 (S13). FIG. 5 is a diagram illustrating an example of extracting an extracted image that includes the abnormality detection time t0 from a captured image. As shown in FIG. 5, the extracted image is a temporally consecutive image (video) from the captured images taken by the perimeter monitoring camera 13. In other words, the extracted image is a consecutive image (video) from the extraction start time t1 to the extraction end time t2.

[0030] The extraction start time t1 is a time before the abnormality detection time t0. More specifically, the extraction start time t1 is the time obtained by subtracting a pre-abnormality extraction time α from the abnormality detection time t0. The extraction end time t2 is a time after the abnormality detection time t0. More specifically, the extraction end time t2 is the time obtained by adding a post-abnormality extraction time β to the abnormality detection time t0. The pre-abnormality extraction time α is a time indicating the length of the images to be extracted from the captured images starting before the abnormality detection time t0. The post-abnormality extraction time β is a time indicating the length of the images to be extracted from the captured images starting after the abnormality detection time t0.

[0031] As one example, the pre-abnormality extraction time α and the post-abnormality extraction time β may be predetermined fixed values. As another example, the controller 10 of the work machine 2 may change the lengths of the pre-abnormality extraction time α and the post-abnormality extraction time β in accordance with the type of abnormality of the work machine 1 identified by the abnormality identifier, as shown in Figures 5(A) and 5(B). Furthermore, the sum of the pre-abnormality extraction time α and the post-abnormality extraction time β (i.e., the length of the extracted image) may be constant (i.e., α1 + β1 = α2 + β2) or may be variable.

[0032] As one example, if the abnormality of the work machine 1 identified by the abnormality identifier is a fire around the engine, there will be no change in the appearance of the work machine 1 until smoke or flames appear. Therefore, the controller 10 of the work machine 2 may make the post-abnormality extraction time β1 longer than the pre-abnormality extraction time α1 (α1<β1), as shown in FIG. 5(A). As another example, if the abnormality of the work machine 1 identified by the abnormality identifier is tipping over (or submersion in water), the behavior of the work machine 1 before tipping over (or submersion in water) will be necessary for verification. Therefore, the controller 10 of the work machine 2 may make the pre-abnormality extraction time α2 longer than the post-abnormality extraction time β2 (α2>β2), as shown in FIG. 5(B).

[0033] Next, the controller 10 of the work machine 2 generates a trimmed image by trimming an area including the work machine 1 from the extracted image extracted from the captured image in step S13 (S14). More specifically, the controller 10 of the work machine 2 generates a trimmed image by trimming a part of the extracted image so that the work machine 1 has a predetermined size (ratio) within the trimmed image. Figure 6 is a diagram showing an example of trimming an area including the work machine 1 from the extracted image.

[0034] As one example, the controller 10 of the work machine 2 may perform image analysis on the extracted image (or captured image) to identify the work machine 1, and then crop out an area including the identified work machine 1. As another example, the controller 10 of the work machine 2 may identify the direction from the work machine 2 towards the work machine 1 based on the relationship between the current positions of the work machines 1 and 2, and crop out an area including the identified direction from the extracted image. The current position of the work machine 1 may be included in the image extraction instruction, or may be obtained from the monitoring server 4.

[0035] That is, the controller 10 of the work machine 2 extracts a portion in time from the image captured by the surroundings monitoring camera 13 in step S13, and spatially crops that portion in step S14 to generate a cropped image. The controller 10 of the work machine 2 then transmits image data showing the cropped image to the monitoring terminal 5 via the communications I / F 16 (S15). The controller 10 of the work machine 2 may further transmit to the monitoring terminal 5 some or all of the machine identifier and current position of the work machine 1, the machine identifier and current position of the work machine 2, and the abnormality identifier included in the image extraction instruction.

[0036] Sending image data to the monitoring terminal 5 is an example of outputting image data. As other examples of outputting image data, the image data may be sent to the monitoring server 4, the image data may be stored in the memory 12, or an image represented by the image data may be displayed on the display of the work machine 2.

[0037] When image data is received from the work machines 2, 3, the monitoring terminal 5 displays a status notification screen on the display (S16). Figure 7 is an example of the status notification screen. The status notification screen includes at least cropped images 52, 53 displayed using image data acquired from the work machines 2, 3, respectively. The status notification screen may also include the machine identifier "001" of the work machine 1 in which the abnormality has occurred, and the details of the abnormality identified by the abnormality identifier, "engine exhaust sound abnormality." Furthermore, the status notification screen may also include a map 54 showing the relative positions of the work machines 1 to 3. The information required to display the status notification screen may be acquired from the work machines 2, 3, as well as from the work machine 1 or the monitoring server 4.

[0038] [Effects of the embodiment] According to the above embodiment, the condition of the work machine 1 in which an abnormality has occurred can be confirmed from images captured by the surroundings monitoring cameras 13 of the other work machines 2, 3. In this way, by checking from a third-party perspective, the abnormality that has occurred in the work machine 1 can be properly grasped.

[0039] Furthermore, according to the above embodiment, by changing the pre-abnormality extraction time α and the post-abnormality extraction time β depending on the type of abnormality that has occurred in the work machine 1, it is possible to appropriately collect information necessary for understanding the situation and for subsequent verification.

[0040] Furthermore, according to the above embodiment, a predetermined area including the work machine 1 is trimmed from the panoramic image captured by the perimeter monitoring camera 13, making it possible to reduce the amount of data sent and received between the work machines 1-3 and the monitoring terminal 5. However, the processing of step S14 can be omitted. Furthermore, the perimeter monitoring camera 13 that has traditionally been mounted on the work machines 2, 3 can be reused to grasp the status of the work machine 1 in which an abnormality has occurred, so the above-mentioned effects can be obtained with minimal configuration changes.

[0041] Furthermore, according to the above embodiment, an abnormality is detected by the condition detection sensor 14 of the work machine 1 and an image extraction command is sent to the work machines 2 and 3, so the time when the abnormality was detected can be identified by utilizing the condition detection sensor 14 that has traditionally been mounted on the work machine 1. This makes it possible to obtain the above-mentioned effects with minimal configuration changes.

[0042] [Variation 1] Figure 8 is a diagram showing another example of the data structure of captured images according to Modification 1. Note that detailed explanation of the points in common with the above embodiment will be omitted, and the explanation will focus on the differences. In Modification 1, the data structure of captured images stored in memory 12 differs from that of the above embodiment. Below, the data structure for work machine 2 will be explained, but the same applies to work machine 3.

[0043] As shown in Fig. 8, the controller 10 of the work machine 2 may store images captured by the surroundings monitoring camera 13 in the memory 12 as one file for each predetermined time period (for example, every 10 minutes or every hour). That is, as shown in Fig. 8, the memory 12 of the work machine 2 stores multiple files 61, 62, 63, 64, 65 that indicate images captured at different times. However, the number of files 61 to 65 is not limited to the example in Fig. 8.

[0044] The controller 10 of the work machine 2 only needs to extract some of the multiple files 61 to 65 in step S13 shown in Figure 4. That is, the controller 10 of the work machine 2 only needs to extract at least file 63 that includes abnormality detection time t0. The controller 10 of the work machine 2 may also extract at least some of the files 61, 62, 64, 65 before and after file 63. Furthermore, the controller 10 of the work machine may extract different numbers of files before and after file 63 that includes abnormality detection time t0.

[0045] As an example, when the abnormality in the work machine 1 is a fire around the engine, the controller 10 of the work machine 2 may extract more files 64 and 65 after the file 63 including the abnormality detection time t0 than the file 62 before the file 63 including the abnormality detection time t0, as shown in Figure 8(A).

[0046] As another example, when the abnormality in the work machine 1 is, for example, tipping over or submersion in water, the controller 10 of the work machine 2 may extract more files 61 and 62 before the file 63 including the abnormality detection time t0 than files 63 after the file 63 including the abnormality detection time t0, as shown in Figure 8(B).

[0047] [Variation 2] Figure 9 is a flowchart of the monitoring process according to Modification 2. Note that a detailed description of the points in common with the above embodiment will be omitted, and the explanation will focus on the differences. The monitoring process according to Modification 2 differs from the above embodiment in that work machines 2 and 3 detect an abnormality in work machine 1. The process for work machine 2 will be explained below, but work machine 3 also executes similar processing.

[0048] 9, the controller 10 of the work machine 2 waits to execute the processing from step S13 onwards until it detects an abnormality in the work machine 1 (S11: No). The controller 10 of the work machine 2, for example, repeatedly analyzes images taken by the surroundings monitoring camera 13 of the work machine 2 at predetermined time intervals to constantly monitor whether or not an abnormality has occurred in the work machine 1. Furthermore, the controller 10 of the work machine 2 may limit the area within the panoramic image for image analysis based on the current position of the work machine 1 obtained from the monitoring server 4.

[0049] If the controller 10 of the work machine 2 detects an abnormality in the work machine 1 (S11: Yes), it may execute the processing from step S13 onwards. Note that the controller 10 of the work machine 2 may, for example, use the time when the abnormality is detected by image analysis as the "abnormality detection time", identify an "abnormality identifier" from the type of abnormality detected by image analysis, and identify the "machine identifier" of the work machine 1 by image analysis or information provided by the monitoring server 4.

[0050] According to Modification 2, abnormalities in the work machine 1 are detected from a third-party perspective, which may enable early detection of abnormalities that are difficult to detect by the own vehicle. Furthermore, compared to the above embodiment, the sending and receiving of information between the work machines 1 to 3 (S12) can be omitted, which also contributes to simplification of processing.

[0051] [Variation 3] Modification 3 is an example in which the monitoring server 4 executes some of the processing executed by the work machines 1 to 3. The basic processing flow is as shown in Figure 4 or Figure 9, so the following explanation will focus on the processing unique to Modification 3.

[0052] First, the controller 10 of the work machine 1 may repeatedly transmit status information indicating the status of the work machine 1 detected by the status detection sensor 14 to the monitoring server 4 at predetermined time intervals via the communication I / F 16. The monitoring server 4 may then detect an abnormality in the work machine 1 based on the status information received from the work machine 1 via the communication I / F 26. Furthermore, if the monitoring server 4 detects an abnormality in the work machine 1, it may transmit an image extraction instruction to the work machines 2, 3 via the communication I / F 26. The processing from step S13 onwards is the same as in Figure 4.

[0053] Furthermore, the controllers 10 of the work machines 2, 3 may repeatedly transmit image data showing images captured by the surroundings monitoring camera 13 to the monitoring server 4 at predetermined time intervals via the communication I / F 16. Furthermore, when the status detection sensor 14 detects an abnormality in the work machine 1, the controller 10 of the work machine 1 may transmit an image extraction instruction to the monitoring server 4 via the communication I / F 16. Then, when the monitoring server 4 receives an image extraction instruction from the work machine 1 via the communication I / F 26, it may execute the processing of steps S13 and S14 on the image data received from the work machines 2, 3 via the communication I / F 16.

[0054] Furthermore, both the detection of an abnormality in the work machine 1 and the processing of steps S13 and S14 may be executed by the monitoring server 4. As in Modification 3, by executing part of the processing in Figure 4 or Figure 9 by the monitoring server 4, the processing load on the work machines 1 to 3 can be reduced.

[0055] [Other variations] The division of roles among the work machines 1 to 3, the monitoring server 4, and the monitoring terminal 5 is not limited to the example described above. Some or all of the means implemented by the monitoring program 28 can also be implemented by hardware such as an integrated circuit. Furthermore, the monitoring program 28 may be provided in a state recorded on a non-transitory recording medium that can be read by a computer. Examples of recording media include hard disks, SD cards, DVDs, and servers on the Internet.

[0056] The above-described embodiments are merely illustrative examples of the present invention, and are not intended to limit the scope of the present invention to these embodiments. Those skilled in the art can implement the present invention in various other forms without departing from the spirit of the present invention. [Explanation of symbols]

[0057] 1, 2, 3: Work machine 4: Monitoring server 5: Monitoring terminal 10: Controller 11,21: CPU 12,22: Memory 13: Surrounding surveillance camera 14: Status detection sensor 15: GPS antenna 16,26: Communication I / F 23: Storage 24: Input device 25: Display 27: Communication bus 28: Monitoring program 52,53:Image 54: Map 61-65: File 100: Surveillance system

Claims

1. A work machine equipped with a surroundings monitoring camera that captures images of the surroundings and a controller, When the controller detects an abnormality in another work machine operating within a predetermined distance range from the work machine, the controller extracts an extracted image including the time when the abnormality was detected from images taken by the surroundings monitoring camera.

2. 2. The work machine according to claim 1, the controller changes, in accordance with the type of abnormality detected in the other work machine, the length of the images extracted from before the abnormality detection time and the length of the images extracted from after the abnormality detection time among the captured images.

3. 2. The work machine according to claim 1, The work machine is characterized in that the controller trims an area including the other work machine from the extracted image.

4. 2. The work machine according to claim 1, a communication interface for communicating with the other work machine; The construction machine is characterized in that, when the controller receives an image extraction instruction including the abnormality detection time from the other construction machine via the communication interface, it extracts the extracted image from the captured image.

5. 5. The work machine according to claim 4, a status detection sensor for detecting the status of the work machine; A work machine characterized in that, when the status detection sensor detects an abnormality in the work machine, the controller transmits the image extraction instruction to the other work machine via the communication interface.

6. 2. The work machine according to claim 1, The work machine is characterized in that the controller performs image analysis on the captured image to detect abnormalities in the other work machine.

7. 1. A monitoring system comprising a first work machine and a second work machine operating within a predetermined distance range, the second work machine is equipped with a surroundings monitoring camera that captures images of the surroundings, The monitoring system is characterized in that, when an abnormality is detected in the first work machine, the monitoring system extracts an extracted image including the time at which the abnormality was detected from the images captured by the surrounding monitoring camera.

Images