JP7812957B2 - Monitoring device, monitoring system, monitoring method, and monitoring program - Google Patents

Description

The present invention relates to technology for monitoring production lines, and in particular to technology for monitoring work status.

Work procedures are established on production lines to maintain quality and ensure safety, and workers follow these procedures as they go about their work. When a quality abnormality occurs, the work may be checked to ensure it is the correct procedure. However, finding the timing of the abnormality from work records requires a huge amount of work. Furthermore, if the work being performed at the time the abnormality occurred is verified based on the worker's memory, there is a risk that the cause of the abnormality will not be accurately identified. For this reason, it is desirable to have technology that can detect abnormalities and confirm the work status when an abnormality occurs. Patent Document 1, for example, discloses such an abnormality detection technology.

Patent Document 1 relates to a production management device that detects abnormalities in the production status. The production management device in Patent Document 1 obtains the cycle time using a signal output when a product is fed from the production equipment. The production management device in Patent Document 1 detects an abnormality when the cycle time is below a lower threshold value.

Patent Document 2 discloses a process monitoring device that uses a camera to capture images of multiple processes. When a worker who recognizes an abnormality operates a switch, the process monitoring device in Patent Document 2 saves image data of the work area corresponding to the operated switch.

Patent Document 3 discloses a device for recording image data from a surveillance camera. The recording device in Patent Document 3 compares two sets of image data from different times, and if it determines that the two sets are different, it adds a chapter to the image data and records it.

Japanese Patent Application Laid-Open No. 2019-061628 Japanese Patent Application Laid-Open No. 2018-128729 Japanese Patent Application Laid-Open No. 2007-081662

However, the technology in Patent Document 1 is insufficient in the following respects. The production management device in Patent Document 1 detects cycle time abnormalities using signals output from production equipment, but is unable to verify how work was performed when an abnormality occurs. Furthermore, the technology in Patent Document 2 does not record video unless the worker recognizes it as an abnormality, so it is unable to verify abnormalities that the worker is not aware of. Furthermore, the technology in Patent Document 3 compares images taken at different times, so it is unable to verify whether work was performed correctly in the specified order.

In order to solve the above problems, the present invention aims to provide a monitoring device or the like that can detect work that differs from normal work and verify the content of that work.

To solve the above problems, the monitoring device of the present invention comprises an image acquisition unit, an abnormality detection unit, and an output unit. The image acquisition unit acquires image data of work performed in a predetermined order. The abnormality detection unit monitors abnormalities in the work time, which is the time required for the work, and if an abnormality is detected, adds information indicating that an abnormality has been detected to the image data acquired at the time the abnormality was detected. The output unit outputs the image data with the added information.

The monitoring method of the present invention acquires image data of work performed in a predetermined order. The monitoring method of the present invention monitors abnormalities in work time, which is the time required for work, and if an abnormality in work time is detected, adds information indicating the detection of the abnormality to the image data acquired when the abnormality is detected. The monitoring method of the present invention outputs the image data with the added information.

The monitoring program of the present invention causes a computer to execute a process of acquiring image data of work performed in a predetermined order. The monitoring program of the present invention monitors abnormalities in work time, which is the time required for work, and, if an abnormality is detected, causes the computer to execute a process of adding information indicating the detection of the abnormality to the image data acquired when the abnormality was detected. The monitoring program of the present invention causes the computer to execute a process of outputting the image data with the added information.

This invention makes it possible to detect work that differs from normal work and verify the content of that work.

1 is a diagram illustrating an outline of a configuration of a first exemplary embodiment of the present invention. 1 is a diagram illustrating an example of a configuration of a monitoring device according to a first embodiment of the present invention; FIG. 2 is a diagram illustrating an example of a work procedure according to the first embodiment of the present invention. FIG. 4 is a diagram illustrating an example of an operation flow of the monitoring device according to the first exemplary embodiment of the present invention. FIG. 3 is a graph showing an example of operation time in the first embodiment of the present invention. FIG. 10 is a diagram illustrating another example of the configuration of the first exemplary embodiment of the present invention. FIG. 10 is a diagram illustrating an outline of the configuration of a second embodiment of the present invention. FIG. 10 illustrates an example of the configuration of a monitoring device according to a second exemplary embodiment of the present invention. FIG. 10 is a diagram illustrating an example of an operation flow of a monitoring device according to a second exemplary embodiment of the present invention. FIG. 10 illustrates an example of the configuration of a monitoring device according to a third exemplary embodiment of the present invention. FIG. 11 is a diagram illustrating an example of an operation flow of a monitoring device according to a third exemplary embodiment of the present invention. FIG. 10 is a diagram illustrating an example of another configuration of an embodiment of the present invention.

(First embodiment)
A first embodiment of the present invention will be described in detail with reference to the drawings. FIG. 1 is a diagram showing an outline of the configuration of a monitoring system of this embodiment. The monitoring system of this embodiment includes a monitoring device 10, an imaging device 20, and an input device 30. FIG. 1 shows an example in which a work object is placed on a workbench, and the imaging device 20 is installed in a position where it can capture images of work performed by a worker on the work object. The monitoring device 10 is connected to the imaging device 20 via a network. The monitoring device 10 is also connected to the input device 30 via a network.

The monitoring system of this embodiment is a system that monitors work performed on a production line. The monitoring system of this embodiment is used to monitor a production line where work is repeatedly performed according to a preset order. Work that follows a preset order refers to work that is performed in a set order, such as placing work objects on a workbench, removing components, attaching the components to the product, and removing the work objects once the work is complete, in a product assembly process. The work may be other than product assembly work, such as product packaging and transporting products between processes. Furthermore, as long as the work is performed in a set order, it may also be work that is not repeated at short intervals, such as workers putting on work clothes and protective gear, washing workers' bodies and removing dust, and equipment maintenance.

The configuration of the monitoring device 10 will now be described. Figure 2 is a diagram showing an example of the configuration of the monitoring device 10. The monitoring device 10 includes an image acquisition unit 11, a work data acquisition unit 12, an abnormality detection unit 13, a memory unit 14, and an output unit 15.

The image acquisition unit 11 acquires image data of images of work performed on the production line in a predetermined order. The image acquisition unit 11 acquires image data of images of work performed on the production line captured by the imaging device 20. The image acquisition unit 11 stores the acquired image data in the storage unit 14.

Figure 3 is a diagram showing an example of a work instruction manual that indicates the order of tasks to be performed on a production line. Figure 3 shows an example in which the order of tasks to be performed in process X of a production line is set. In the example of Figure 3, a worker in process X takes tool A from the tool shed and part B from the parts shelf, then attaches part B to the product and returns tool A to the tool shed. After storing tool A in the tool shed, the worker performs tasks number 5 and onwards in order. The worker in process X repeats tasks in the order specified in the work procedure manual, changing the product being worked on. The image acquisition unit 11 acquires, from the imaging device 20, image data of images captured of the tasks repeatedly performed by the worker in the predetermined order as shown in the work instruction manual in Figure 3.

The work data acquisition unit 12 acquires data on the worker's identification information, the work object's identification information, and the start and end times of the work as work history data. For example, the work data acquisition unit 12 acquires, from the input device 30, the worker's identification information that was entered into the input device 30 when the worker started work. The work data acquisition unit 12 may also acquire the worker's identification information from a production management system (not shown). The worker's identification information may also be entered directly into the monitoring device 10.

The work data acquisition unit 12 acquires from the input device 30 the identification information of the work object, which is read, for example, at the start and end of the work. The identification information of the work object is read, for example, from a barcode containing identification information attached to the work object. A barcode reading device is installed, for example, on a workbench. The barcode containing identification information is read, for example, by the worker operating the barcode reading device. The work data acquisition unit 12 also acquires the times at which the identification information is read as the start and end times of the work. The work data acquisition unit 12 associates the data of the worker's identification information, the identification information of the work object, and the start and end times of the work and stores them in the memory unit 14. The start and end times of the work may be input into the input device 30 by the worker's operation.

The anomaly detection unit 13 calculates the time required for a task as the task time from data on the start and end times of the task. The task time per task performed repeatedly in a set order is also known as the cycle time. The anomaly detection unit 13 identifies an abnormality in the task time when the task time is outside the standard range of normal task times. The task time for tasks performed according to a predetermined procedure will not deviate significantly from the average value when performed in the correct order. Therefore, by comparing the task time with the standard and identifying task time outside the standard range as an abnormality, the anomaly detection unit 13 can detect tasks that may be a cause of defects in the product being worked on.

For example, the abnormality detection unit 13 determines that an abnormality has occurred in the work time when the work time is equal to or greater than a preset threshold. Furthermore, the abnormality detection unit 13 determines that an abnormality has occurred in the work time when the work time is less than a preset threshold. The threshold that sets the boundary between the normal range and an abnormality may be either an upper limit or a lower limit. The threshold used to determine whether or not there is an abnormality in the work time is set using the time required for the work when performed normally. The criteria indicating the range of normal work time are set for each type of work. Furthermore, the criteria indicating the range of normal work time may be set for each worker, or may be set according to the worker's level of proficiency in the work.

When the anomaly detection unit 13 identifies that an abnormality has occurred during work time, it adds information indicating that an abnormality has been detected to the image data. When an abnormality is detected, the anomaly detection unit 13 adds information indicating that an abnormality has been detected (hereinafter also referred to as anomaly detection information) to the image data stored in the memory unit 14.

The storage unit 14 stores image data and work history data. The storage unit 14 is configured, for example, by a hard disk drive. The storage unit 14 may also be configured by other storage devices, such as a non-volatile semiconductor storage device. The storage unit 14 may also be configured by a combination of multiple types of storage devices.

The output unit 15 outputs the image data to which the abnormality detection information has been added to a display device (not shown). The output unit 15 may also output the image data to which information indicating that an abnormality has been detected has been added to a terminal device or server connected via a network.

The processes in the image acquisition unit 11, work data acquisition unit 12, abnormality detection unit 13, and output unit 15 are performed, for example, by executing a computer program in a CPU (Central Processing Unit). The processes in the image acquisition unit 11, work data acquisition unit 12, abnormality detection unit 13, and output unit 15 may also be performed by semiconductor devices such as FPGAs (Field Programmable Gate Arrays) or ASICs (Application Specific Integrated Circuits).

The imaging device 20 captures images of work being done on the production line. The imaging device 20 is installed so that it can capture images of the work being done, such as the worker's hands. The imaging device 20 generates image data of the captured image and sends the generated image data to the monitoring device 10. The imaging device 20 is configured, for example, using a camera that captures images in the visible light range. The imaging device 20 may also use a camera that captures images in a range other than the visible light range, such as a far-infrared camera.

The input device 30 accepts input of data such as the worker's identification information, the work object's identification information, and the start and end times of the work as work history data. The input device 30 sends the accepted work history data to the monitoring device 10. The input device 30 acquires the worker's identification information, for example, by reading the identification information on an ID card carried by the worker. The input device 30 acquires information about the work object, for example, by reading the lot number information attached to the product being worked on. The input device 30 identifies the start and end times of the work, for example, as the times when the start and end of the work are entered by the worker's operation. The input device 30 may also acquire information about the start and end times of the work by reading the work object's identification information at the start and end of the work by the worker's operation. The input device 30 may also identify the start and end times of the work by acquiring information about the placement of the product being worked on on the work table and the removal of the product from the work table via a sensor.

The operation of the monitoring system of this embodiment will now be described. Figure 4 is a diagram showing an example of the operation flow of the monitoring device 10.

The imaging device 20 captures images of workers working on the production line. The imaging device 20 sends image data of the captured images to the monitoring device 10. The input device 30 also acquires identification information for the worker, identification information for the work object, and information on the start and end times of the work, and sends this information to the monitoring device 10 as work history data.

In FIG. 4, the image acquisition unit 11 acquires image data of the work from the imaging device 20 (step S11). Upon acquiring the image data, the image acquisition unit 11 stores the acquired image data in the storage unit 14.

The work data acquisition unit 12 also acquires data on the worker's identification information, the work object's identification information, and the start and end times of the work as work history data (step S12). Once the work history data has been acquired, the anomaly detection unit 13 calculates the work time from the work start time and work end time (step S13). After calculating the work time, the anomaly detection unit 13 compares the calculated work time with a standard for normal work time.

If the calculated work time is within the standard range (Yes in step S14) and the production line being monitored is continuing to operate (Yes in step S17), the monitoring device 10 continues to monitor for abnormalities in work time, as in step S11.

When the calculated work time is outside the reference range (No in step S14), the abnormality detection unit 13 adds information indicating that an abnormality has occurred in the work time to the image data (step S15). The abnormality detection unit 13 adds the abnormality detection information to the image data acquired when an abnormality in the work time is detected, and stores the image data in the storage unit 14. The abnormality detection information may also include identification information for the worker who was performing the work when the abnormality was detected and identification information for the work target.

Once the abnormality detection information has been added to the image data, the output unit 15 outputs the image data of the portion to which the abnormality detection information has been added (step S16). The output unit 15 outputs the image data of the portion to which the abnormality detection information has been added, for example, to a terminal device (not shown) carried by the production line manager. The output unit 15 outputs, for example, image data of a length that spans the time going back the length of the work from the portion to which the abnormality detection information has been added, i.e., the image corresponding to the work start time, to the image of the portion to which the abnormality detection information has been added, i.e., the image corresponding to the work end time, to the terminal device.

When the terminal device requests image data of the area where an abnormality has occurred, the output unit 15 may output to the terminal device image data of the area to which the abnormality detection information has been added. The output unit 15 may also output to the terminal device image data of the area requested by an operation performed after checking the image data to which the abnormality detection information has been added.

When the image data of the portion to which the abnormality detection information is added is output, if the production line being monitored is still operating (Yes in step S17), the monitoring device 10 continues the operation of monitoring for abnormalities from step S11.

In step S17, if the operation of the production line has stopped (No in step S17), the monitoring device 10 ends the operation of monitoring the production line.

Figure 5 is a diagram that schematically illustrates an example of a graph generated using records of work time. The horizontal axis of Figure 5 indicates, for example, the end time of a task, and the vertical axis indicates the work time of the task completed at each time. The threshold value Th in Figure 5 is set as a criterion for determining abnormalities in work time, and when the work time is equal to or greater than Th, the abnormality detection unit 13 determines that an abnormality in work time has occurred. In the example of Figure 5, the lower limit of the normal range is not indicated, but the criterion for indicating the normal range may be set using thresholds that indicate lower and upper limits.

The output unit 15 may output display data showing a graph such as that shown in FIG. 5 to a terminal device. When a graph such as that shown in FIG. 5 is displayed, for example, when a black circle at the location of an abnormality is selected by the user of the terminal device, i.e., when any work time data is selected, the output unit 15 may output corresponding image data to the terminal device. Such a configuration makes it easier for the user of the monitoring system to determine the image data to be checked by referring to the work time.

The output unit 15 may output statistical data on working hours to a terminal device. The output unit 15 may, for example, calculate the number of abnormal working hours per specified period and the average number of abnormal working hours per specified period and output these to the terminal device. Furthermore, when outputting the statistical data on working hours, the output unit 15 may also output statistical data on abnormal working hours for each individual, group, and process to the terminal device. By outputting such statistical data, the production line manager can refer to trends in abnormal working hours and manage processes more efficiently by referring to image data.

When calculating statistical data on work times, the output unit 15 may output information indicating a large variation in work times to the terminal device if the variation in work times is equal to or greater than a preset standard. If the variation in work times is large, it is possible that the work performed by the workers is not stable. Therefore, by outputting information indicating a large variation in work times, the production line manager can verify the content of the work and improve work efficiency.

In the above example, the monitoring device 10 monitors the work time of the work captured by one camera device 20 and stores the image data, but the monitoring device 10 may also monitor the work time of each work captured by multiple camera devices 20.

Figure 6 shows an example in which work is being photographed using five camera devices 20. In the example of Figure 6, the work in each work section is photographed by a camera device 20 installed in each work section. An input device 30 is also installed for each work section. In the example of Figure 6, the work data acquisition unit 12 of the monitoring device 10 acquires work history data for each work section. The abnormality detection unit 13 monitors whether or not there is an abnormality in the work time, and if an abnormality is detected, adds abnormality detection information to the image data of the image of the work section in which the abnormality was detected. In the example of Figure 6, a camera device 20 is installed in each work section, but a single camera device 20 may be configured to photograph multiple work sections. In such a configuration, the monitoring device 10 may add information about the work section in which the abnormality was detected to the image data in addition to the abnormality detection information. The number of camera devices 20 may be other than five.

As explained above, when the monitoring system of this embodiment detects an abnormality in the work time per repetition of a task that is repeated according to a preset procedure, it adds anomaly detection information indicating the abnormality to the captured image of the task and saves the image. The work time per repetition, also known as cycle time, does not fluctuate significantly if the task is performed correctly according to the work procedure. If the work time fluctuates, the task was not performed according to the correct procedure, and there is a risk of an abnormality in the product. The monitoring system of this embodiment adds anomaly detection information to the image data of the work time and saves it. By referencing this information during verification, it is possible to check images of areas where there may be an abnormality in the product and confirm the actual work procedure. As a result, the monitoring system of this embodiment can be used to detect tasks that deviate from normal work and verify the content of the work.

Second Embodiment
A second embodiment of the present invention will be described in detail with reference to the drawings. Fig. 7 is a diagram showing an outline of the configuration of a monitoring system of this embodiment. The monitoring system of this embodiment includes a monitoring device 40, an image capturing device 20, and an input device 30. The monitoring device 40 is connected to the image capturing device 20 via a network. The monitoring device 40 is also connected to the input device 30 via the network.

The monitoring system of the first embodiment calculates work time from input data on the start and end times of work and detects abnormalities in work time. In contrast to this configuration, the monitoring system of this embodiment calculates work time by detecting the movements of workers from image data capturing the work and identifying the start and end times of the work.

The configurations and functions of the imaging device 20 and input device 30 of this embodiment are similar to those of the imaging device 20 and input device 30 of the first embodiment, respectively.

The configuration of the monitoring device 40 will now be described. Figure 8 is a diagram showing an example of the configuration of the monitoring device 40. The monitoring device 40 includes an image acquisition unit 11, an image analysis unit 41, a data acquisition unit 42, an abnormality detection unit 13, a memory unit 14, and an output unit 15. The configurations and functions of the image acquisition unit 11, memory unit 14, and output unit 15 in this embodiment are the same as those of the parts with the same names in the first embodiment.

The image analysis unit 41 detects the worker's movements from the image data. For example, the image analysis unit 41 detects the color of the hand, the gloves worn by the worker, or whether or not the worker is moving using well-known image recognition technology. The image analysis unit 41 generates time-series data in which, for example, "1" indicates that the worker's movements are detected, and "0" indicates that no movements are detected.

The image analysis unit 41 identifies the start and end times of a task. The image analysis unit 41 identifies the time when movement is detected after a period of time during which no movement is detected continues for a predetermined period of time or longer as the start time of the task. Furthermore, after identifying the start time of a task, when a period of time during which no movement is detected continues for a predetermined period of time or longer, the image analysis unit 41 identifies the time when movement was last detected as the end time of the task.

The data acquisition unit 42 acquires the worker's identification information and the identification information of the work target as work history data. For example, the data acquisition unit 42 acquires the worker's identification information from the input device 30, which was entered into the input device 30 when the worker started work. The data acquisition unit 42 may also acquire the worker's identification information from a production management system (not shown). The worker's identification information may also be entered directly into the monitoring device 40.

The data acquisition unit 42 acquires the identification information of the work object from the input device 30, for example, at the start and end of the work. The identification information of the work object is read in the same manner as in the first embodiment. The data acquisition unit 42 associates the identification information of the worker and the identification information of the work object with the acquisition date and time of the information and stores them in the memory unit 14. Furthermore, the worker and the work object may be identified by image recognition in the image analysis unit 41.

The anomaly detection unit 13 calculates the work time from the start and end times of the work identified by the image analysis unit 41. The anomaly detection unit 13 identifies an abnormality in the work time when the work time is outside the standard range of normal work time. The anomaly detection unit 13 identifies the presence or absence of an abnormality using a method similar to that of the first embodiment. When the anomaly detection unit 13 detects an abnormality in the work time, it adds anomaly detection information, which is information indicating that an abnormality has been detected, to the image data. When an abnormality is detected, the anomaly detection unit 13 adds the anomaly detection information to the position of the image saved in the memory unit 14.

The image analysis unit 41 is performed, for example, by executing a computer program in a CPU. Each process in the image analysis unit 41 may be performed by a semiconductor device such as an FPGA or ASIC.

The operation of the monitoring system of this embodiment will now be described. Figure 9 is a diagram showing an example of the operation flow of the monitoring device 40.

The imaging device 20 captures images of workers working on the production line. The imaging device 20 sends image data of the captured images to the monitoring device 40. The input device 30 also acquires identification information for the worker and the work object, and sends this information to the monitoring device 40 as work history data.

In FIG. 9, the image acquisition unit 11 of the monitoring device 40 acquires image data of work on the production line from the imaging device 20 (step S21). Upon acquiring the image data, the image acquisition unit 11 stores the acquired image data in the storage unit 14. In addition, the data acquisition unit 42 acquires the worker's identification information and the work target's identification information as work history data.

When the image data is acquired, the image analysis unit 41 identifies the start and end times of the work from the image data (step S22). Once the start and end times of the work have been identified, the anomaly detection unit 13 calculates the work time from the start and end times of the work (step S23). After calculating the work time, the anomaly detection unit 13 compares the calculated work time with a standard for normal work time.

If the calculated work time is within the standard range (Yes in step S24) and the production line being monitored is continuing to operate (Yes in step S27), the monitoring device 40 continues monitoring for abnormalities from step S21.

When the calculated work time is outside the reference range (No in step S24), the abnormality detection unit 13 adds abnormality detection information to the image data (step S25). The abnormality detection unit 13 adds the abnormality detection information to the image data acquired when an abnormality in the work time is detected, and stores the image data in the storage unit 14. The abnormality detection information may also include identification information for the worker who was performing the work when the abnormality was detected and identification information for the work target.

Once the abnormality detection information is added to the image data, the output unit 15 outputs the image data of the portion to which the abnormality detection information has been added (step S26). If the production line being monitored is still operating when the image data of the portion to which the abnormality detection information has been added is output (Yes in step S27), the monitoring device 40 continues monitoring for abnormalities, as in step S21.

In step S27, if the operation of the production line has stopped (No in step S27), the monitoring device 40 ends the operation of monitoring the production line.

The monitoring system of this embodiment determines the start and end times of work that is repeated according to a preset procedure by analyzing image data that captures the work. As a result, the monitoring system of this embodiment can accurately calculate work time because the worker does not need to input information about the start and end times of the work. This allows the monitoring system of this embodiment to more accurately detect abnormalities in work time. By improving the accuracy of detecting abnormalities in work time, the monitoring system of this embodiment can more efficiently check image data that may contain abnormalities.

(Third embodiment)
A third embodiment of the present invention will be described in detail with reference to the drawings. Fig. 10 is a diagram showing an outline of the configuration of a monitoring device 100 of this embodiment.

The monitoring device 100 of this embodiment comprises an image acquisition unit 101, an abnormality detection unit 102, and an output unit 103. The image acquisition unit 101 acquires image data of work performed in a predetermined order. The abnormality detection unit 102 monitors abnormalities in the work time, which is the time required for the work, and, if an abnormality is detected, adds information indicating that an abnormality has been detected to the image data acquired at the time the abnormality was detected. The information indicating that an abnormality has been detected is also referred to as abnormality detection information. The output unit 103 outputs the image data to which the information indicating that an abnormality has been detected has been added.

The image acquisition unit 11 in the first and second embodiments is an example of the image acquisition unit 101. The image acquisition unit 101 is also an aspect of image acquisition means. The abnormality detection unit 13 in the first and second embodiments is an example of the abnormality detection unit 102. The abnormality detection unit 102 is also an aspect of abnormality detection means. The output unit 15 in the first and second embodiments is an example of the output unit 103. The output unit 103 is also an aspect of output means.

The operation of the monitoring device 100 will now be described. Figure 11 is a diagram showing an example of the operational flow of the monitoring device 100. The image acquisition unit 101 acquires image data of work performed in a predetermined order (step S101). Once the image data has been acquired, the anomaly detection unit 102 monitors for abnormalities in the work time, which is the time required for the work (step S102). If an abnormality is detected, the anomaly detection unit 102 adds information indicating that an abnormality has been detected to the image data acquired when the abnormality was detected (step S103). Once the information indicating that an abnormality has been detected has been added, the output unit 103 outputs the image data to which the information indicating that an abnormality has been detected has been added (step S104).

The monitoring device 100 of this embodiment monitors abnormalities in the work time of tasks that are performed repeatedly in a predetermined order, and when an abnormality is detected, adds information indicating the detection of the abnormality to the image data. When tasks are performed in a predetermined order, abnormalities in the work time occur when tasks that differ from normal are performed. Therefore, by detecting abnormalities in work time, it is possible to detect that work that differs from normal work has been performed. Therefore, by using the monitoring device 100 of this embodiment, it is possible to detect tasks that differ from normal work and verify the content of the work.

The processes in the monitoring device 10 of the first embodiment, the monitoring device 40 of the second embodiment, and the monitoring device 100 of the third embodiment can be performed by executing a computer program on a computer. Figure 12 shows an example of the configuration of a computer 200 that executes a computer program that performs the processes in the monitoring device 10 of the first embodiment, the monitoring device 40 of the second embodiment, and the monitoring device 100 of the third embodiment. The computer 200 includes a CPU 201, memory 202, a storage device 203, an input/output I/F (Interface) 204, and a communication I/F 205.

The CPU 201 reads and executes computer programs that perform each process from the storage device 203. The CPU 201 may be configured as a combination of a CPU and a GPU (Graphics Processing Unit). The memory 202 is configured from DRAM (Dynamic Random Access Memory) or the like, and temporarily stores the computer programs executed by the CPU 201 and data being processed. The storage device 203 stores the computer programs executed by the CPU 201. The storage device 203 is configured from, for example, a non-volatile semiconductor storage device. Other storage devices such as a hard disk drive may also be used for the storage device 203. The input/output I/F 204 is an interface that accepts input from operators and outputs display data, etc. The communication I/F 205 is an interface that sends and receives data to and from each device that makes up the monitoring system.

The computer programs used to execute each process can also be stored on a recording medium and distributed. Examples of recording media that can be used include magnetic tape for recording data and magnetic disks such as hard disks. Optical disks such as CD-ROMs (Compact Disc Read Only Memory) can also be used as recording media. Non-volatile semiconductor storage devices can also be used as recording media.

REFERENCE SIGNS LIST 10 Monitoring device 11 Image acquisition unit 12 Work data acquisition unit 13 Abnormality detection unit 14 Storage unit 15 Output unit 20 Imaging device 30 Input device 40 Monitoring device 41 Image analysis unit 42 Data acquisition unit 100 Monitoring device 101 Image acquisition unit 102 Abnormality detection unit 103 Output unit 200 Computer 201 CPU
202 Memory 203 Storage device 204 Input/output I/F
205 Communication I/F

Claims (9)

image acquisition means for acquiring image data of work that is repeatedly performed by a worker in a predetermined order;
an image analysis means for identifying a start time and an end time of the work from the image data;
an anomaly detection means for monitoring a work time, which is the time required for each repetition of the work that is repeatedly performed by the worker in a predetermined order, based on the start time and the end time, and for detecting an abnormality in the variation in the work time by the worker when the variation in the work time that the worker repeatedly performs in the predetermined order is equal to or exceeds a standard, and for adding information indicating the detection of the abnormality to image data acquired when the abnormality is detected in the work time;
and an output means for outputting the image data to which the information is added. The monitoring device described in claim 1, wherein the image analysis means determines the start time and end time based on the time at which movement is detected when a period of time during which no movement is detected continues for a predetermined period of time or longer. The monitoring device described in claim 1 or 2, wherein the output means outputs image data for a period of time corresponding to the work period during which the abnormality was detected. A monitoring device according to any one of claims 1 to 3, wherein the output means outputs display data that displays the work time as a graph, and outputs the image data corresponding to selected data. a plurality of photographing devices that photograph images of work that is repeatedly performed in a predetermined order and output image data of the photographed images;
The monitoring device according to any one of claims 1 to 4,
The image acquisition means acquires the image data from each of the photographing devices, and the abnormality detection means monitors abnormalities in the work time of the image data for each of the photographing devices, and when an abnormality is detected, adds information indicating that an abnormality has been detected to the image data acquired at the time the abnormality was detected. The system captures image data of the workers repeatedly performing tasks in a set order,
Identifying the start time and end time of the work from the image data;
Based on the start time and the end time, a work time, which is the time required for each repetition of the work performed repeatedly in a predetermined order by the worker, is monitored; if the variation in the work time performed repeatedly in a predetermined order by the worker is equal to or exceeds a standard, an abnormality in the variation in the work time by the worker is detected; and if an abnormality in the work time is detected, information indicating the detection of the abnormality is added to image data acquired when the abnormality is detected;
A monitoring method that outputs image data to which the information is added. The monitoring method described in claim 6, wherein if a period of time during which no motion is detected continues for a predetermined period of time or longer, the start time and end time are determined based on the time at which motion is detected. A process of acquiring image data of work that is repeatedly performed by a worker in a predetermined order;
A process of identifying a start time and an end time of the work from the image data;
a process of monitoring a work time, which is the time required for each repetition of the work that is repeatedly performed by the worker in a predetermined order, based on the start time and the end time, detecting an abnormality in the variation in the work time by the worker when the variation in the work time that the worker repeatedly performs in the predetermined order is equal to or exceeds a standard, and when an abnormality in the work time is detected, adding information indicating the detection of the abnormality to image data acquired when the abnormality is detected;
and a monitoring program that causes a computer to execute a process of outputting the image data to which the information has been added. The monitoring program of claim 8 causes a computer to execute a process for determining the start time and end time based on the time at which motion is detected when a period of time during which no motion is detected continues for a predetermined period of time or longer.