VIDEO MANAGEMENT SYSTEM, VIDEO MANAGEMENT METHOD, AND VIDEO MANAGEMENT PROGRAM

Abstract

A video management system according to the present invention comprises an acquisition unit, an identification unit, a determination unit, and an output unit. The acquisition unit acquires video captured of a work area. The identification unit identifies the state of the work area as shown in the video. The determination unit determines a storage standard for the video on the basis of a prescribed state for the work area and identification results for the state of the work area. The determination unit determines the storage reference of the video on the basis of the predetermined state of the work area and the identification result of the state of the work area. The output unit outputs the determined storage standard.

Description

Video management system, video management method, and recording medium

[0001] The present disclosure relates to a video management system and the like.

[0002] In factories, for example, analysis of work within a manufacturing process is performed to improve work efficiency, quality, and safety. The results of the work analysis are used, for example, by a manager who manages the manufacturing process to improve work procedures. The work analysis is performed, for example, by the manager viewing video footage of the work and confirming whether the work is being performed correctly in accordance with the work procedures. Furthermore, when analyzing work based on video footage of the work, for example, because the work is filmed over a long period of time, it may be necessary to appropriately manage the video data of the work.

[0003] When changing the storage device to which video is saved, the work monitoring system of Patent Document 1 deletes low-priority video saved in the new storage device depending on the capacity of the new storage device, and then saves high-priority video in the new storage device.

[0004] Japanese Patent Application Laid-Open No. 2020-194393

[0005] With the technology described in Patent Document 1, it may be difficult to reduce the storage capacity required to save the video.

[0006] In order to solve the above-mentioned problems, the present disclosure aims to provide a video management system and the like that can appropriately reduce the storage capacity required to store video.

[0007] In order to solve the above problems, the video management system of the present disclosure includes an acquisition means for acquiring video footage of a work area, an identification means for identifying the state of the work area shown in the video, a determination means for determining a storage standard for the video based on a predetermined state of the work area and the identification result of the state of the work area, and an output means for outputting the determined storage standard.

[0008] The video management method disclosed herein acquires video footage of a work area, identifies the state of the work area shown in the video, determines a storage standard for the video based on a predetermined state of the work area and the results of identifying the state of the work area, and outputs the determined storage standard.

[0009] The video management method disclosed herein non-temporarily records a video management program that causes a computer to execute the following processes: acquiring video of a work area; identifying the state of the work area shown in the video; determining a storage standard for the video based on a predetermined state of the work area and the results of identifying the state of the work area; and outputting the determined storage standard.

[0010] According to the present disclosure, it is possible to appropriately reduce the storage capacity required to save video.

[0011] FIG. 1 is a diagram illustrating an example of the configuration of a video management system according to an embodiment of the present disclosure. FIG. 2 is a diagram illustrating an example of a video captured of a work area according to an embodiment of the present disclosure. FIG. 3 is a diagram illustrating an example of a video captured of a work area according to an embodiment of the present disclosure. FIG. 4 is a diagram illustrating an example of a video captured of a work area according to an embodiment of the present disclosure. FIG. 5 is a diagram illustrating an example of a video captured of a work area according to an embodiment of the present disclosure. FIG. 6 is a diagram illustrating an example of an operation flow of a video management system according to an embodiment of the present disclosure. FIG. 7 is a diagram illustrating an example of the hardware configuration of a video management system according to an embodiment of the present disclosure.

[0012] An embodiment of the present disclosure will be described in detail with reference to the drawings. Fig. 1 is a diagram illustrating an example of the configuration of a video management system 10. The video management system 10 basically includes an acquisition unit 11, an identification unit 13, a determination unit 14, and an output unit 15. The video management system 10 also includes a work information acquisition unit 12 and a storage unit 16.

[0013] The video management system 10 is a system that determines storage standards for video captured of a work area. The video management system 10 determines, for example, at least one of the storage period for video captured of a work area and the code size of the video to be stored. The storage period for video is, for example, the length of time for which the video is stored after it is captured. After the storage period for video has elapsed, the stored video is, for example, deleted. After the storage period for video has elapsed, the stored video may be moved from the storage means in which it was stored during the storage period to another storage means.

[0014] The code amount of a video is, for example, the data volume of the video to be stored. The code amount of a video is, for example, an amount determined by at least one of the resolution, frame rate, and compression rate of the video. Determining the code amount of a video to be stored means, for example, determining the data volume of the video to be stored. For example, determining at least one of the resolution, frame rate, and compression rate of the video to be stored. For example, for video of the same duration, the larger the code amount, the higher the resolution and / or frame rate. For example, for video of the same duration, the larger the code amount, the lower the compression rate. In other words, for video of the same duration, the larger the code amount, the higher the image quality. For example, for video of the same duration, the smaller the code amount, the lower the resolution and / or frame rate. For example, for video of the same duration, the smaller the code amount, the higher the compression rate. In other words, for video of the same duration, the smaller the code amount, the lower the image quality. Determining the code amount of a video to be stored may also mean, for example, determining at least one of the parameters that determine the resolution, frame rate, and compression rate of the video. Furthermore, determining the code size of the video to be saved may also mean determining a conversion algorithm for the video. How the code size of the video to be saved is determined is not limited to the above.

[0015] The video of the work area is used, for example, for work analysis. Therefore, the video storage standard is determined, for example, so that the more important an image is for work analysis, the longer the storage period. Also, the video storage standard is determined, for example, so that the more important an image is for work analysis, the larger the amount of code required when saving.

[0016] Whether or not video footage of a work area is important for analysis is determined, for example, based on the difference between the work captured in the video and the work under standard conditions. For example, if there is a large difference between the work captured in the video and the work under standard conditions, there is a high possibility that the work is not being performed correctly. If there is a small difference between the work captured in the video and the work under standard conditions, there is a high possibility that the work is being performed correctly. Therefore, for example, when analyzing a case where work is not being performed correctly, the greater the difference between the work captured in the video and the work under standard conditions, the more important the video is for analysis. For this reason, the code size of the video to be saved is determined to be larger the greater the difference between the work captured in the video and the work under standard conditions.

[0017] Furthermore, the standard state is, for example, a state in which work is being performed according to a procedure defined as a work procedure. For example, if the work captured in a video differs from the work in a standard state defined as a work procedure, the video can be important in analyzing the work. For example, analyzing the differences based on the video and improving the work content can improve work efficiency and quality. In this case, the greater the difference between the work captured in the video and the work in a standard state, the longer the storage period for the video may be set. Furthermore, the greater the difference between the work captured in the video and the work in a standard state, the greater the code size of the video may be determined.

[0018] Furthermore, for example, when analyzing a task captured on video with the aim of using correct tasks as a model, the storage period for the video may be determined to be longer the smaller the difference between the task captured on video and the task under standard conditions. Also, the code size of the video to be stored may be determined to be larger the smaller the difference between the task captured on video and the task under standard conditions. For example, increasing the code size of the video to be stored makes it possible to analyze the correct task in detail.

[0019] 2 and 3 show example images of frames included in a video of a work area. The example image in Fig. 2 shows a state in which a worker is waiting near a workbench. The example image in Fig. 3 shows a state in which a worker is assembling a product placed on the workbench.

[0020] In the example image of FIG. 2 , for example, the standard state during standby is when nothing is placed on the workbench. When the standard state is when nothing is placed on the workbench, for example, if assembly tools are placed on the workbench, the state of the work area will differ from the standard state. In this case, the video management system 10 determines the storage criteria so that the storage period is longer for sections showing the state where assembly tools are placed on the workbench than for sections showing the state where nothing is placed on the workbench. Furthermore, the video management system 10 determines the storage criteria so that the amount of code of the video to be stored is larger for sections showing the state where assembly tools are placed on the workbench than for sections showing the state where nothing is placed on the workbench.

[0021] In the example image of Figure 3, for example, it is assumed that assembling a product according to the procedure defined in the work procedure is the standard state. If assembling a product according to the procedure defined in the work procedure is the standard state, for example, a worker assembling the product using a procedure different from the work procedure is a state that differs from the standard state. In this case, the video management system 10 determines the storage criteria so that the storage period is longer for sections that show work performed using a procedure different from the work procedure than for sections that show work performed using a procedure that follows the work procedure. Furthermore, the video management system 10 determines the storage criteria so that the amount of code of the video to be stored is larger for sections that show work performed using a procedure different from the work procedure than for sections that show work performed using a procedure that follows the work procedure.

[0022] Furthermore, if the purpose of the analysis is to confirm the assembly procedure of a work, the section showing the image in the example of Fig. 3 is more important as a target for analysis than the section showing the image in the example of Fig. 2. In this case, the video management system 10 determines the storage criteria, for example, so that the storage period is longer for the section showing the image in the example of Fig. 3 than for the section showing the image in the example of Fig. 2. Furthermore, the video management system 10 determines the storage criteria, for example, so that the amount of code of the video to be stored is larger for the section showing the image in the example of Fig. 3 than for the section showing the image in the example of Fig. 2.

[0023] The video storage criteria determined by the video management system 10 are output to a system that manages the video of the work area or a system that analyzes the video. The video management system 10 may store the video of the work area in an internal storage means or a connected storage means based on the determined storage criteria.

[0024] Here, a specific example of the configuration of the video management system 10 will be described.

[0025] The acquisition unit 11 acquires video of a work area. The video of work is, for example, video captured to capture work performed by a worker in the work area. The work area is, for example, an area in a factory manufacturing process where one or more workers perform designated work. The work performed by the worker is, for example, work related to product manufacturing. Work related to product manufacturing includes, for example, product assembly, product processing, product inspection, product packaging, product transportation, equipment operation, and storage shelf organization. The work performed by the worker may also include equipment inspection, equipment repair, or equipment assembly. Work related to product manufacturing may also include food preparation. Work related to product manufacturing is not limited to the above. Work performed by the worker may also include cleaning, driving, exercise, instructing others, guiding, security, medical procedures, dispensing medicine, and equipment operation. The work performed by the worker is not limited to the above.

[0026] The video of the work area may be a video of items placed in the work area. For example, in the work area, parts and tools must be placed in designated locations. If the items are not placed in the designated locations, it may lead to a decrease in work efficiency, an incorrect selection of parts to be used, or an accident due to contact with the worker. Therefore, the presence or absence of items placed in the work area and how the items are placed may be the subject of analysis.

[0027] The acquisition unit 11 acquires, for example, video of the work area captured by a camera installed in a position where the work area can be captured. If a monitoring system is present that monitors the work area, the acquisition unit 11 may acquire the video of the work area via a server of the monitoring system. Alternatively, the acquisition unit 11 may acquire the video of the work area via a storage medium.

[0028] The work information acquisition unit 12 acquires, for example, information related to work content. The work information acquisition unit 12 acquires, for example, information related to work content from a production management server that manages the work area. The information related to work content is, for example, information that can identify the importance of video in the analysis of video captured of the work area. Identifying the importance means, for example, identifying whether each section of the video captured of the work area is important in the analysis. The importance serves as a criterion for determining the image quality or storage criteria of the video to be saved. For example, the storage criteria are determined so that the more important a section of the video captured of the work area is, the higher the image quality of the video. High-quality video is video with a large amount of code per unit time or per screen. Furthermore, for example, the storage criteria are determined so that the more important a section of the video captured of the work area is, the longer the storage period.

[0029] The information on the work content is, for example, information from which it is possible to extract what kind of video may be required when performing an analysis using video. The information on the work content is, for example, information from which it is possible to identify at least one of the work to be analyzed and the item to be analyzed. In other words, the information on the work content is, for example, information from which it is possible to identify the items that a person viewing the video wants to check from the video.

[0030] Information related to work content is, for example, information on at least one of the following items: the purpose of the work, the type of work, the product to be worked on, the person performing the work, the tools used in the work, and the work procedure. The purpose of the work is information that can identify at least one of the work and the item to be analyzed, such as preparing parts to prepare for the work, assembling parts to create an intermediate product, obtaining inspection results, or transporting and storing on a shelf. For example, the purpose of the work is not limited to the above. The type of work is information that can identify at least one of the work and the item to be analyzed from the work content, such as preparation, reporting, assembly, inspection, transport, cleaning, or repair. The type of work is not limited to the above.

[0031] The information about the work content may include at least one of the target of analysis and the purpose of the analysis to be performed using video footage of the work area. The target of analysis is information about at least one of the work and the item. The purpose of the analysis is, for example, information that indicates what type of work or posture of the worker is to be analyzed. The purpose of the analysis may be, for example, information that indicates what type of item placed in the work area is to be analyzed. The purpose of the analysis may also be, for example, information that indicates how the items are placed in the work area is to be analyzed. The information about the work content is not limited to the above.

[0032] The work information acquisition unit 12 may acquire information regarding the importance of each piece of information related to the work content in the analysis of the video. The information regarding the importance of each piece of information related to the work content in the analysis of the video is set by, for example, a person who analyzes the video, a manager of the manufacturing process, or an operator of the video management system 10.

[0033] The identification unit 13 identifies the state of the work area shown in the video acquired by the acquisition unit 11. For example, the identification unit 13 identifies the state of the work area shown in the video at each time point in the time series of the video acquired by the acquisition unit 11. For example, the identification unit 13 identifies the state of the work area shown in each frame included in the video acquired by the acquisition unit 11. The identification unit 13 may identify the state of the work area shown in each frame at a predetermined interval. The predetermined interval is set, for example, using the number of frames or time. The predetermined interval is set, for example, based on the frame rate of the video. The predetermined interval is set, for example, by a person analyzing the video, a manufacturing process manager, or an operator of the video management system 10. Furthermore, the identification unit 13 may identify the state of the work area shown in the video for a section of the video where work is being performed. For example, the identification unit 13 identifies the section where work is being performed in the video of the work area based on work history data acquired from a production management server.

[0034] The state of the work area is, for example, the state of the work being performed in the work area. The identification unit 13, for example, identifies the work being performed in the work area. The identification unit 13, for example, identifies the work performed by a worker, such as pressing a button, joining components, and tightening a screw with a screwdriver. The content of the work identified by the identification unit 13 is not limited to the above. The identification unit 13 may also identify the order of the work being performed in the work area. The identification unit 13 may also identify the tools used by the worker in the work. The identification unit 13 may also identify the product on which the worker is working.

[0035] The state of the work area may be the state of a worker in the work area. The identification unit 13, for example, identifies whether a worker is present in the work area. The identification unit 13 may, for example, identify who the worker is in the work area. The identification unit 13 may, for example, identify the posture of the worker in the work area. The identification unit 13 may also identify the attributes of the worker in the work area. The worker attributes may, for example, be at least one of the worker's affiliation, rank, qualifications, work responsibility, age, and gender. The worker attributes are not limited to the above. The identification unit 13 may also identify the clothing of the worker in the work area. The identification unit 13 may also identify clothing worn by the worker in the work area. The clothing may, for example, be at least one of safety equipment, badges, armbands, name tags, and accessories. The clothing is not limited to the above.

[0036] The state of the work area may be how an object is present in the work area. The identification unit 13, for example, identifies an object placed in the work area. The identification unit 13 may also identify whether an object to be analyzed is placed in the work area. The identification unit 13 may also identify the position of the object placed in the work area.

[0037] The identification unit 13 identifies, for example, sections in a video captured of a work area in which each task is captured. The unit of the identified sections corresponds, for example, to the range of sections that determines the video storage standards. For example, when three tasks are to be analyzed, namely, loading a product from a cart onto a workbench, attaching components to the product, and transferring the product from the workbench to the cart, the identification unit 13 identifies sections in which these three tasks are captured from the video captured of the work area. When tasks with the same procedure are performed repeatedly, the identification unit 13 may identify sections for each iteration of the repeated task. Furthermore, the identification unit 13 may identify the first to last iteration of the repeated task as one section.

[0038] The identification model is, for example, a machine learning model using a neural network. The identification model is generated, for example, by learning the relationship between an image of a work area and information indicating the area in which the worker or item to be identified is captured. The identification model may be generated by learning the relationship between an image of a work area, the area in which the worker to be identified is captured, and the type of work the worker is performing. The identification model may be generated by learning the relationship between an image of a work area, the area in which the item to be identified is captured, and the name of the item captured in the image. The training data used to generate the identification model may be selected as appropriate depending on the identification target of the identification model. The identification model is generated, for example, in a system external to the video management system 10.

[0039] The identification unit 13 may use multiple identification models to identify at least one of the work and the object shown in the video. For example, the identification unit 13 may use an identification model that identifies an area in the video where the worker's body is shown to identify the area in the frame image where the worker is shown. Then, for example, the identification unit 13 may use an identification model that identifies the position of the worker's body part in the video to identify the position of the worker's hand in the frame image. Furthermore, the identification unit 13 may identify the object held by the worker at the identified position using an identification model that identifies the type of object. In this way, by identifying the work and the object using multiple identification models, the identification unit 13 can identify the procedure of the work, for example. Furthermore, the identification unit 13 may use a different identification model for each work included in the workflow to identify at least one of the work performed by the worker and the object shown in the video.

[0040] The determination unit 14 determines a storage standard for the video based on a predetermined state of the work area and the identification result of the state of the work area. The determination unit 14 determines a storage standard for each time-series section of the video based on, for example, the predetermined state of the work area and the identification result of the state of the work area. The storage standard is a standard related to at least one of the code amount of the video when storing the video and the length of the period for storing the video.

[0041] For example, the determination unit 14 estimates a difference between the identification result of the work area state and a predetermined state of the work area. Then, the determination unit 14 determines a storage standard for the video based on the estimated difference. The determination unit 14 may determine a storage standard for the video for each time-series section of the video based on the estimated difference. For example, the determination unit 14 determines a storage standard for each section where there is a difference between the identification result of the work area state and the predetermined state of the work area and a section where there is no difference. The determination unit 14 may determine a storage standard for the video for each section based on the degree of difference between the identification result of the work area state and the predetermined state of the work area.

[0042] The predetermined state is, for example, a standard state or a normal state. The standard state is, for example, the state of the work area when steady work is being performed. The standard state may be the steady state of the work area outside of working hours or during breaks. The standard state may be the position or state of an item placed in the work area during steady state.

[0043] A normal state is, for example, a state that does not differ from a predetermined state. A normal state is, for example, a state in which work is being performed correctly in accordance with a predetermined work procedure. For example, if the work procedure specifies that work A, work B, and work C should be performed in that order, then a state in which work A, work B, and work C are being performed in that order is a normal state. On the other hand, if the work procedure specifies that work A, work B, and work C should be performed in that order, then a state in which work A, work C, and work B are being performed in that order is a state that differs from normal. A normal state may be a state in which a predetermined worker or a predetermined number of workers are present in the work area. A normal state may be a state in which a worker is in a predetermined position. A normal state may be a state in which a worker is in a predetermined posture. A normal state may be a state in which a predetermined item is placed in the work area. The predetermined state is set, for example, by a person who analyzes the video, a manufacturing process manager, or an operator of the video management system 10.

[0044] For example, the determination unit 14 determines a storage standard such that, when there is a difference between a predetermined state and the identification result, the amount of code for the video is larger than when there is no difference. For example, when there is a difference between a predetermined state and the identification result, the determination unit 14 determines a storage standard such that the amount of code for the video to be stored is larger than the standard value. For example, assume that the video of the work area is 3840 pixels x 2160 pixels, and the standard value for saving the video is 1920 pixels x 1080 pixels. In this case, for example, the determination unit 14 determines that the saving standard is to save the section of the video of the work area where there is a difference between the predetermined state and the identification result as 3840 pixels x 2160 pixels. Furthermore, assume that the video of the work area is 60 frames per second, and the standard value for saving the video is 30 frames per second. In this case, the determination unit 14 determines, as a storage standard, that a section of the video of the work area where there is a difference between the predetermined state and the identification result be stored as video at 60 frames per second. How to determine the code amount for storing video is not limited to the above. The determination unit 14 may also determine the storage standard such that the code amount for video increases as the difference between the predetermined state and the identification result increases.

[0045] For example, the determination unit 14 determines the storage criteria so that, when there is a difference between a predetermined state and the identification result, the video is stored for a longer period of time than when there is no difference. For example, the determination unit 14 determines, for example, a storage period of one month for a section of a video captured of a work area where there is a difference between the predetermined state and the identification result, and a storage period of one week for a section where there is no difference. How the video is stored is determined is not limited to the above. The determination unit 14 may also determine the storage criteria so that the greater the difference between the predetermined state and the identification result, the longer the video is stored.

[0046] The determination unit 14 may determine the storage criteria so that the amount of video code is larger when the predetermined state and the identification result are identical than when there is a difference. The term "the predetermined state and the identification result are identical" refers to, for example, whether the predetermined state is identical within a criterion for determining whether the state is identical. The term "the predetermined state and the identification result are identical" refers to, for example, whether the predetermined state is identical within a predetermined range. For example, if the predetermined state is that an assembly tool is placed in a tool shed, the assembly tool can be identical regardless of the angle at which it is placed in the tool shed. Furthermore, if the predetermined state is that an operator performs work according to a procedure, the operator can be identical even if the operator's movements in each task are different as long as the work procedure and the operator's work procedure in the identification result match. Furthermore, the term "the predetermined state and the identification result are identical" may refer to, for example, whether the predetermined state and the identification result are identical within a range in which the identification model identifies the two as identical. Furthermore, the determination unit 14 may determine the storage criteria so that the video is stored for a longer period when the predetermined state and the identification result are identical than when there is a difference. Furthermore, "identical" may include "similar." It is possible to set as appropriate whether to increase the code amount when there is a difference between the predetermined state and the identification result or when there is no difference and they are the same. Also, it is possible to set as appropriate whether to increase the storage period when there is a difference between the predetermined state and the identification result or when there is no difference and they are the same.

[0047] The determination unit 14 determines a storage standard for the video based on, for example, the worker's work in the work area identified by the identification unit 13 and the worker's work in a predetermined state. The determination unit 14 determines a storage standard for each time-series section of the video based on, for example, the worker's work in the work area identified by the identification unit 13 and the worker's work in a predetermined state. The determination unit 14 determines the storage standard such that the larger the difference between the worker's work in the work area identified by the identification unit 13 and the worker's work in a predetermined state, the larger the code size of the video. For example, in the case of a five-step task, the determination unit 14 determines the storage standard such that the code size of the video is larger when the performed task differs from the work procedure in four steps than when the performed task differs from the work procedure in two steps. The determination unit 14 may determine the storage standard such that the larger the difference between the worker's work in the work area identified by the identification unit 13 and the worker's work in a predetermined state, the longer the period for storing the video. For example, when a five-step work is performed, the determination unit 14 determines the storage standard so that the period for storing the video is longer when the work performed differs from the work procedure in four steps than when the work differs from the work procedure in two steps.

[0048] The determination unit 14 determines a storage standard for the video based on, for example, the number of workers present in the work area identified by the identification unit 13 and the number of workers present in the work area in a predetermined state. The determination unit 14 determines a storage standard for each time-series section of the video based on, for example, the number of workers present in the work area identified by the identification unit 13 and the number of workers present in the work area in a predetermined state. The determination unit 14 determines the storage standard such that the larger the difference between the number of workers present in the work area identified by the identification unit 13 and the number of workers present in the work area in a predetermined state, the larger the code size of the video. For example, the determination unit 14 determines the storage standard such that the code size of the video is larger when a single person is performing a task that is specified to be performed by two people than when two people are performing the task. The determination unit 14 may determine the storage standard such that the longer the period for storing the video is, the larger the difference between the number of workers present in the work area identified by the identification unit 13 and the number of workers present in the work area in a predetermined state. For example, when a task is to be performed by two people and the task is performed by one person, the determination unit 14 determines the storage standard so that the video is stored for a longer period than when the task is performed by two people.

[0049] For example, when the number of workers present in the work area identified by the identification unit 13 is greater than the number of workers present in the work area in a predetermined state, the determination unit 14 may not need to change the video storage period and the code size of the stored video from the standard values. This is because, for example, a large number of workers means that an instructor is likely to be present in the work area. Furthermore, for example, when the number of workers present in the work area identified by the identification unit 13 is greater than the number of workers present in the work area in a predetermined state, the determination unit 14 may change the video storage period and the code size of the stored video from the standard values.

[0050] The determination unit 14 determines a storage standard for the video based on, for example, the task time required to perform the task in the task area identified by the identification unit 13 and the task time in a predetermined state. The determination unit 14 determines a storage standard for each time-series section of the video based on, for example, the task time required to perform the task in the task area identified by the identification unit 13 and the task time in a predetermined state. The determination unit 14 determines the storage standard such that the larger the difference between the task time required to perform the task in the task area identified by the identification unit 13 and the task time in a predetermined state, the larger the code size of the video. For example, if a task that normally takes an average of 90 seconds to perform according to a task procedure is performed in 180 seconds, the determination unit 14 determines the storage standard such that the code size of the video is larger when the task is performed in 180 seconds than when the task is performed in 90 seconds. The determination unit 14 may also determine the storage standard such that the larger the difference between the task time required to perform the task in the task area identified by the identification unit 13 and the task time in a predetermined state, the longer the period for storing the video. For example, when a task that normally takes an average of 90 seconds to complete according to a work procedure is completed in 180 seconds, the determination unit 14 determines the storage standard so that the video is stored for a longer period when the task is completed in 180 seconds than when the task is completed in 90 seconds.

[0051] The determination unit 14 determines a storage standard for the video based on, for example, the objects present in the work area identified by the identification unit 13 and the objects present in the work area in a predetermined state. The determination unit 14 determines a storage standard for each time-series section of the video based on, for example, the objects present in the work area identified by the identification unit 13 and the objects present in the work area in a predetermined state. For example, when the objects present in the work area identified by the identification unit 13 are different from the objects present in the work area in a predetermined state, the determination unit 14 determines the storage standard so that the amount of code for the video is larger than when the objects are the same. Furthermore, for example, when the identification result of the identification unit 13 does not identify an object present in the work area in a predetermined state, the determination unit 14 determines the storage standard so that the amount of code for the video is larger than when the object is identified. For example, when it is specified that a display indicating that adjustment work is in progress be displayed during device adjustment work, and the display cannot be identified in the identification result, the determination unit 14 determines the storage standard so that the amount of code for the video is larger than when the display is displayed. The determination unit 14 may determine the storage criteria so that, when an object present in the work area identified by the identification unit 13 is different from an object present in the work area in a predetermined state, the video will be stored for a longer period of time than when the objects are the same. Furthermore, the determination unit 14 may determine the storage criteria so that, when an object present in the work area in a predetermined state cannot be identified in the identification result of the identification unit 13, the video will be stored for a longer period of time than when the object can be identified. For example, when it is specified that a display indicating that adjustment work is in progress should be displayed during device adjustment work, if the display cannot be identified in the identification result, the determination unit 14 determines the storage criteria so that the video will be stored for a longer period of time than when the display is displayed.

[0052] The determination unit 14 may determine a storage standard for the video based on the worker's clothing identified by the identification unit 13 and the clothing worn by the worker in a predetermined state. The determination unit 14 determines a storage standard for each time-series section of the video, for example, based on the worker's clothing identified by the identification unit 13 and the clothing worn by the worker in a predetermined state. For example, the determination unit 14 determines a storage standard such that the code amount of the video is larger when the identification result of the identification unit 13 shows that a worker present in the work area is not wearing the specified safety equipment than when the worker is wearing the correct safety equipment. Furthermore, the determination unit 14 may determine a storage standard such that the video is stored for a longer period when the identification result of the identification unit 13 shows that a worker present in the work area is not wearing the specified safety equipment than when the worker is wearing the correct safety equipment.

[0053] The determination unit 14 may determine the video storage standard based on a predetermined state of the work area and the identification result of the work area state when the same work area is photographed multiple times. The determination unit 14, for example, determines the storage standard for each time-series section of the video based on a predetermined state of the work area and the identification result of the work area state when the same work area is photographed multiple times. The determination unit 14 may also determine the video storage standard based on a predetermined state and the identification result when the same work performed in the work area is photographed multiple times. The determination unit 14 determines the storage standard for each time-series section of the video based on a predetermined state and the identification result when the same work performed in the work area is photographed multiple times. The same work may be performed by different workers. The same work may also be performed in different areas.

[0054] The determination unit 14 estimates the frequency of anomalies using, for example, the identification results of each of the videos captured multiple times. Then, the determination unit 14 determines a storage standard for each time-series section of the video, for example, based on the frequency of anomalies. An anomaly refers to, for example, a state in which the difference between a predetermined state and the identification result is equal to or greater than a standard. When the cause of a frequently occurring anomaly is the subject of analysis, the determination unit 14 determines the storage standard, for example, such that the higher the frequency of the anomaly, the larger the amount of code for the video. Furthermore, when the cause of a frequently occurring anomaly is the subject of analysis, the determination unit 14 may determine the storage standard such that the higher the frequency of the anomaly, the longer the period for storing the video. Furthermore, when the occurrence situation of a rarely occurring anomaly is the subject of analysis, the determination unit 14 determines the storage standard such that, for example, the lower the frequency of the anomaly, the larger the amount of code for the video. When the occurrence situation of a rarely occurring anomaly is the subject of analysis, the determination unit 14 may determine the storage standard such that the lower the frequency of the anomaly, the longer the period for storing the video.

[0055] The determination unit 14 may determine the storage criteria for each time-series section of the video based on whether the analysis target is captured in the video of the work area. For example, if the purpose of the analysis is to confirm the assembly procedure of the work, the storage criteria may be determined so that the storage period is longer for sections that capture images of workers performing assembly work than for sections that capture images of waiting workers. Furthermore, if the purpose of the analysis is to confirm the assembly procedure of the work, the storage criteria may be determined so that the amount of code of the video to be stored is larger for sections that capture images of workers performing assembly work than for sections that capture images of waiting workers.

[0056] 4 and 5 show example images included in video captured of a work area. The example image in FIG. 4 shows a state in which no workers are near the work bench. The example image in FIG. 5 shows a state in which a worker is standing near the work bench with cleaning tools in hand. If the purpose of the analysis is to determine the time periods during which people are present in the work area, the section showing the image in FIG. 5 is of higher importance as a target for analysis than the section showing the image in FIG. 4. In this case, the video management system 10 determines the storage criteria, for example, so that the section showing the image in FIG. 5 is stored for a longer period than the section showing the image in FIG. 4. The video management system 10 determines the storage criteria, for example, so that the amount of code of the video to be stored is larger for the section showing the image in FIG. 5 than the section showing the image in FIG. 4.

[0057] 6 and 7 show other examples of images included in video captured of a work area. The example image in FIG. 6 shows a state in which a worker stands behind a cart in the direction of travel and pushes the cart forward. The example image in FIG. 7 shows a state in which a worker stands in front of the cart in the direction of travel and pulls the cart. For example, for the purpose of personal protection and safety, pushing the cart forward as in the example image in FIG. 6 is designated as normal work, while pulling the cart is prohibited as in the example image in FIG. 7. In this case, the video management system 10 determines the storage criteria so that the storage period is longer for the section in which the image in FIG. 7 is shown than for the section in which the image in FIG. 6 is shown. The video management system 10 determines the storage criteria so that the amount of code of the video to be saved is larger for the section in which the image in FIG. 7 is shown than for the section in which the image in FIG. 6 is shown.

[0058] The output unit 15 outputs the determined video storage criteria. The output unit 15 outputs the determined video storage criteria, for example, to a storage means for storing video of the work area. The output unit 15 may output the video of the work area and the storage criteria for the video to the storage means for storing the video of the work area.

[0059] The storage unit 16 stores, for example, video footage of the work area. The storage unit 16 also stores an identification model. The identification model may be stored in a storage means external to the video management system 10. The storage unit 16 may also store the determined criteria. The storage unit 16 may also store video footage of the work area based on the determined criteria.

[0060] An example of the operation of the video management system 10 to convert a video of a work area into a video in which body parts that can identify a worker have been processed will be described below. Fig. 8 shows an example of the operation flow when the video management system 10 converts a video of a work area into a video in which body parts that can identify a worker have been processed.

[0061] The acquisition unit 11 acquires a video of the work area (step S11). For example, the acquisition unit 11 acquires a video of the work area captured by a camera installed so as to be able to capture the work area.

[0062] When the video of the work area is acquired, the identification unit 13 identifies the state of the work area shown in the video at each time point in the time series of the video (step S12).

[0063] Once the state of the work area shown in the video has been identified, the determination unit 14 determines the storage criteria for each time-series section of the video based on the standard state of the work area and the identification result of the work area state (step S13).

[0064] When the storage criteria have been determined for all sections (No in step S14), the output unit 15 outputs the storage criteria determined by the determination unit 14 (step S15).

[0065] When the storage criteria are determined, if there is a section for which the storage criteria have not been determined (Yes in step S14), the process returns to step S12, and the identification unit 13 identifies the state of the work area shown in the video at each point in the video timeline for the section for which the storage criteria have not been determined.

[0066] The video management system 10 identifies the state of the work area captured in the video at each time point in the time series of the video of the work area. The video management system 10 then determines a storage standard for the video based on the predetermined state of the work area and the identification result of the work area state. For example, when the order of tasks performed by workers in the work area differs from the order of tasks defined in the work procedure, the video management system 10 determines the storage standard so that the amount of code for the video to be stored is larger than when the tasks are performed according to the work procedure. Determining the storage standard so that the amount of code for the video is larger means, for example, determining the storage standard so that the video will have high image quality. Furthermore, for example, when the order of tasks performed by workers in the work area differs from the order of tasks defined in the work procedure, the video management system 10 determines the storage standard so that the video will be stored for a longer period than when the tasks are performed according to the work procedure. In this way, for example, if work being done in a work area is performed in a different order than specified in the work procedure, the image quality of the video that shows that work can be improved and the storage period can be extended, thereby reducing the storage capacity required to store the video while preserving the video in a state necessary for analysis. Therefore, by using the video management system 10, the storage capacity required to store the video can be appropriately reduced.

[0067] Furthermore, the video management system 10 can efficiently reduce the storage capacity required to store the video while retaining the video in the state required for analysis by determining video storage criteria for each section of the video time series, for example, based on a predetermined state of the work area and the identification result of the state of the work area.

[0068] Each process in the video management system 10 can be realized by executing a computer program on a computer. Fig. 9 shows an example of the configuration of a computer 100 that executes a computer program that performs each process in the video management system 10. The computer 100 includes a CPU (Central Processing Unit) 101, a memory 102, a storage device 103, an input / output I / F (Interface) 104, and a communication I / F 105.

[0069] The CPU 101 reads and executes computer programs for performing each process from the storage device 103. The CPU 101 may be configured as a combination of multiple CPUs. The CPU 101 may also be configured as a combination of a CPU and another type of processor. For example, the CPU 101 may be configured as a combination of a CPU and a graphics processing unit (GPU). The memory 102 is configured with a dynamic random access memory (DRAM) or the like, and temporarily stores computer programs executed by the CPU 101 and data being processed. The storage device 103 stores computer programs executed by the CPU 101. The storage device 103 is configured with, 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 103. The input / output I / F 104 is an interface that receives input from an operator and outputs display data, etc. The communication I / F 105 is an interface that transmits and receives data to and from other information processing devices.

[0070] The computer program used to execute each process can also be stored and distributed on a computer-readable recording medium that non-temporarily stores data. Examples of recording media that can be used include magnetic tapes 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.

[0071] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes.

[0072] [Supplementary Note 1] A video management system comprising: an acquisition means for acquiring video of a work area; an identification means for identifying the state of the work area shown in the video; a determination means for determining a storage standard for the video based on a predetermined state of the work area and the identification result of the state of the work area; and an output means for outputting the determined storage standard.

[0073] [Supplementary Note 2] The video management system according to Supplementary Note 1, wherein the storage criteria are criteria related to at least one of a code amount of the video when the video is stored and a length of time for which the video is stored.

[0074] [Supplementary Note 3] The video management system according to Supplementary Note 2, wherein the determining means determines the storage criteria so that, when there is a difference between the predetermined state and the identification result, the amount of code for the video is larger than when there is no difference.

[0075] [Supplementary Note 4] The video management system described in Supplementary Note 3, wherein the predetermined state is a state in which work is being performed according to a work procedure, and the determining means determines the storage standard so that the amount of code for the video is increased when the identification result indicates that the worker's work procedure differs from the prescribed procedure.

[0076] [Supplementary Note 5] The video management system according to Supplementary Note 2 or 3, wherein the determining means determines the storage criteria so that, when there is a difference between the predetermined state and the identification result, the video is stored for a longer period of time than when there is no difference.

[0077] [Supplementary Note 6] The video management system described in Supplementary Note 5, wherein the predetermined state is a state in which work is being performed according to a work procedure, and the determining means determines the storage criteria so that the video is stored for a longer period of time when the identification result shows that the worker's work procedure differs from the specified procedure.

[0078] [Supplementary Note 7] The video management system described in any one of Supplementary Notes 1 to 6, wherein the determination means determines the storage criteria for the video based on the work of the worker in the work area identified by the identification means and the work of the worker in the specified state.

[0079] [Supplementary Note 8] The video management system described in any one of Supplementary Notes 1 to 6, wherein the determination means determines the storage criteria for the video based on the number of workers present in the work area identified by the identification means and the number of workers present in the work area in the specified state.

[0080] [Supplementary Note 9] The video management system described in any one of Supplementary Notes 1 to 6, wherein the determination means determines the storage criteria for the video based on the work time required to perform the work in the work area identified by the identification means and the work time for the work in the specified state.

[0081] [Supplementary Note 10] The video management system described in any one of Supplementary Notes 1 to 6, wherein the determination means determines the storage criteria for the video based on the objects present in the work area identified by the identification means and the objects present in the work area in the specified state.

[0082] [Supplementary Note 11] The video management system described in any one of Supplementary Notes 1 to 6, wherein the determination means determines the storage criteria for the video based on a predetermined state of the work area and an identification result of the state of the work area when the same work area or a work area where the same work has been performed is photographed multiple times.

[0083] [Supplementary Note 12] The video management system according to any one of Supplementary Notes 1 to 11, wherein the determination means determines a storage standard for each section of the time series of the video based on a predetermined state of the work area and an identification result of the state of the work area at each point in time on the time series of the video. [Supplementary Note 13] The video management system according to Supplementary Note 12, wherein the determination means determines the storage standard for each section of the time series of the video based on whether an analysis target is captured in the video taken of the work area.

[0084] [Supplementary Note 14] A video management method comprising: acquiring video of a work area; identifying the state of the work area shown in the video; determining a storage standard for the video based on a predetermined state of the work area and the identification result of the state of the work area; and outputting the determined storage standard.

[0085] [Supplementary Note 15] A recording medium that non-temporarily records a video management program that causes a computer to execute the following processes: acquiring video of a work area; identifying the state of the work area shown in the video; determining a storage standard for the video based on a predetermined state of the work area and the identification result of the state of the work area; and outputting the determined storage standard.

[0086] The present disclosure has been described above using the above-described embodiments as examples. However, the present disclosure is not limited to the above-described embodiments. That is, the present disclosure can be applied in various aspects that can be understood by a person skilled in the art within the scope of the present disclosure.

[0087] REFERENCE SIGNS LIST 10 Video management system 11 Acquisition unit 12 Work information acquisition unit 13 Identification unit 14 Determination unit 15 Output unit 16 Storage unit 100 Computer 101 CPU 102 Memory 103 Storage device 104 Input / output I / F 105 Communication I / F

Claims

1. An acquisition means for acquiring an image of a work area; an identification means for identifying the state of the work area shown in the image; a determination means for determining a standard for storing the video based on a predetermined state of the work area and the result of identifying the state of the work area; an output means for outputting the determined storage criteria; A video management system comprising:

2. the storage standard is a standard regarding at least one of a standard regarding the amount of code of the video when the video is stored and a standard regarding the length of a period for storing the video; The video management system according to claim 1 .

3. the determining means determines the storage standard so that, when there is a difference between the predetermined state and the identification result, the amount of code of the video is larger than when there is no difference. The video management system according to claim 2 .

4. The predetermined state is a state in which the work is being performed as defined in the work procedure, the determining means determines the storage standard so as to increase the code amount of the video when the work procedure of the worker differs from a predetermined procedure in the identification result. The video management system according to claim 3 .

5. the determining means determines the storage standard so that, when there is a difference between the predetermined state and the identification result, the period for storing the video is longer than when there is no difference. The video management system according to claim 2 .

6. The predetermined state is a state in which the work is being performed as defined in the work procedure, the determining means determines the storage criteria so that the video is stored for a longer period if the identification result indicates that the worker's work procedure differs from a predetermined procedure. The video management system according to claim 5 .

7. the determining means determines the storage standard for the video based on the work of the worker in the work area identified by the identifying means and the work of the worker in the predetermined state.

7. The video management system according to claim 1.

8. the determining means determines the storage criteria for the video based on the number of workers present in the work area identified by the identifying means and the number of workers present in the work area in the predetermined state.

7. The video management system according to claim 1.

9. Obtain footage of the work area, Identifying the condition of the work area shown in said image; determining a storage standard for the video based on the predetermined state of the work area and the identification result of the state of the work area; outputting the determined preservation criteria; Video management methods.

10. Acquiring video of the work area; identifying the state of the work area shown in the video; determining a storage standard for the video based on a predetermined state of the work area and the identification result of the state of the work area; A process of outputting the determined storage criteria; A video management program that runs on a computer.