JP2021196909A - Monitoring system - Google Patents

Abstract

To provide a monitoring system that allows accurate understanding of the movements of people and objects, that can accurately monitor a manufacturing process, and contribute to the improvement of work efficiency.SOLUTION: A monitoring system used in monitoring systems that monitor people, objects, or devices at a manufacturing site, comprises: a camera that monitors a person, an object, or a device; an analysis unit that analyzes video data obtained by the camera; and a display unit that displays the analysis results of the analysis unit. The analysis unit detects a change point in the video data and analyzes the state of the person, the object, and the device based on the change point.SELECTED DRAWING: Figure 1

Description

The present invention relates to a monitoring system for monitoring people, goods, and machines at a manufacturing site of goods.

At the manufacturing site of goods, a system for monitoring the people involved in manufacturing, the goods to be manufactured, and the machines (manufacturing equipment, inspection equipment, packing equipment, etc.) that execute the manufacturing process is known, and further improvement is possible. It is being advanced (see, for example, Patent Documents 1 to 3).

For example, at a manufacturing site in the assembly industry, a product is produced by aggregating a plurality of parts and combining them with work according to a predetermined assembly drawing, work procedure manual, etc. (for example, welding, cutting, assembly, etc.). .. In the case of a complicated product, predetermined work is carried out at a plurality of work sites, and each part (unit) is put together to create a more complicated product. In such work, when there are many types of parts (things) to be aggregated, the work procedure, site layout, parts aggregation work, etc. become complicated, waiting for work, retention of parts, and timing deviation of parts aggregation. , It is easy for workers (humans) to be misplaced, and there is a problem of reduced efficiency in assembly work. However, especially in the assembly industry, equipment and devices are rarely used, and assembly work is mainly performed by humans, so a logging environment using sensors is not in place. Therefore, there is a demand for a monitoring system that accurately grasps and monitors the state of people and things at the manufacturing site. In other words, it is desired to build a digital twin for the assembly industry and utilize it to improve and monitor management figures.

However, when quantifying and recording the human work state, the worker may stop the work and record the work state, or another worker may record while observing the worker's movement. There was a problem that it was necessary, laborious and costly.

Regarding the monitoring of the state of things, if the thing is inside the machine, it is possible to record and monitor the operation by the machine, but the thing is moved from the machine at one work site to the machine at another work site. In such cases, the condition cannot be sufficiently monitored.

Japanese Patent No. 5416322 Japanese Unexamined Patent Publication No. 2019-139570 Japanese Unexamined Patent Publication No. 2019-16226

The present invention provides a monitoring system capable of accurately grasping the movements of people and things, accurately monitoring the manufacturing process, and contributing to the improvement of work efficiency.

In order to solve the above problems, the monitoring system according to the present invention is a monitoring system for monitoring people, objects, and devices at a manufacturing site, and is obtained by a camera that monitors the people, objects, or devices, and the cameras. It includes an analysis unit that analyzes video data and a display unit that displays the analysis result by the analysis unit. The analysis unit detects a change point in the video data and analyzes the state of the person, the thing, or the device based on the change point.

According to the monitoring system according to the present invention, it is possible to provide a monitoring system that can accurately monitor the manufacturing process and contribute to the improvement of work efficiency.

It is a schematic diagram which shows an example of the structure of the monitoring system 1 which concerns on embodiment. It is a schematic diagram schematically explaining the operation of the human surveillance camera 11. It is a schematic diagram schematically explaining the operation of the thing surveillance camera 12 and the apparatus surveillance camera 13. It is a schematic diagram schematically explaining the operation of the thing surveillance camera 12 and the apparatus surveillance camera 13. It is a flowchart explaining the operation of the monitoring system 1 which concerns on embodiment. This is an example of a display screen on the display PC 17. This is an example of a display screen on the display PC 17. This is an example of a display screen on the display PC 17.

Hereinafter, the present embodiment will be described with reference to the accompanying drawings. In the attached drawings, functionally the same elements may be displayed with the same number. The accompanying drawings show embodiments and implementation examples in accordance with the principles of the present disclosure, but these are for the purpose of understanding the present disclosure and are never used for the limited interpretation of the present disclosure. is not it. The description of the present specification is merely a typical example, and does not limit the scope of claims or application examples of the present disclosure in any sense.

In this embodiment, the description is given in sufficient detail for those skilled in the art to implement the present disclosure, but other implementations and embodiments are also possible and do not deviate from the scope and spirit of the technical idea of the present disclosure. It is necessary to understand that it is possible to change the structure and structure and replace various elements. Therefore, the following description should not be construed as limited to this.

Hereinafter, embodiments relating to a process of assembling a product (a final product and a unit as an intermediate product) composed of a plurality of parts will be described. Parts ordered and delivered from the core system or ordering system are carried into and stored in the parts warehouse. On the other hand, when a manufacturing serial number is issued according to the manufacturing plan of the product, the parts are manufactured according to the manufacturing plan (including the assembly drawing and the assembly procedure manual created by the design department) defined in advance for each serial number. Is transported to the assembly shop. Assembly personnel, necessary equipment, and jigs will be assigned to this assembly shop according to the manufacturing plan. The assembly personnel carry out the prescribed assembly work according to the manufacturing plan, using the equipment and jigs required by the case.

Products that have undergone the prescribed assembly work are transported to the next assembly shop. Through this repetition and integration, the final product is completed, a predetermined shipping inspection is carried out, and it is stored in the shipping warehouse. The present embodiment provides means and a method for recording the above-mentioned assembly process and the progress of the work being carried out in the factory. Specifically, each warehouse, serving rack, and assembly shop records each part, each device / jig, identification information of each worker, start completion time, and takeoff / landing time. In the conventional technology, in order to detect the presence or absence of product parts, it is necessary to individually install sensors according to the work contents of each work, each shop, and the configuration of the shop. This is because, for example, it is necessary to change the installation position of the sensor every time the work content, the size and shape of the part change due to the change of the product or the like. According to the embodiment described below, it is not necessary to change the installation position of the camera as long as the parts, the jig, and the operator are present in the imaging range of the camera. As a result, the installation cost at the time of system introduction can be significantly reduced.

An example of the monitoring system 1 according to the embodiment will be described with reference to FIG. As an example, this surveillance system 1 is composed of a human surveillance camera 11, a mono surveillance camera 12, a device surveillance camera 13, a transfer computer (PC) 14, a collection / storage server 15, an analysis server 16, and a display computer (PC) 17. Can be done.

The human surveillance camera 11 is a camera for monitoring the movement of a person (worker) who executes work at a manufacturing site. For example, the human surveillance camera 11 stores information on the shape of a human and the characteristics of the movement in advance, and can be configured to be able to detect the movement of the human quickly and surely.

The object monitoring camera 12 is a camera for monitoring the movement of an object manufactured and moving at a manufacturing site. As an example, the object monitoring camera 12 captures identification information (one-dimensional code, two-dimensional code, color chart, etc.) attached to the cart in order to monitor the movement of the cart for loading and transporting the object. , Can be a camera to identify. By attaching different identification information to each of a plurality of carts, it is possible to identify the type of cart. However, this is only an example, and the mono surveillance camera 12 is not limited to the one that monitors the movement of the cart by the identification information. For example, the shape of the object itself may be recognized, or various identification information attached to the object may be identified. Further, instead of recognizing the cart, for example, the movement of the tray mounted on the belt conveyor may be monitored by the mono-surveillance camera 12. When the mono-surveillance camera 12 is configured to read a two-dimensional code, the mono-surveillance camera 12 can mount an application for two-dimensional code analysis inside the mono-surveillance camera 12. Of course, it goes without saying that the application for 2D code analysis is also good on the cloud.

The device monitoring camera 13 is a camera for monitoring the movement of various devices (manufacturing device, inspection device, packing device, etc.) installed at the manufacturing site. The device surveillance camera 13 can be different depending on the characteristics of the device to be imaged. For example, in the device monitoring camera 13 for a device in which the intervention of human operation is indispensable, the operation panel of the device can be imaged to be a camera for monitoring human operation. By taking an image of the operation panel, it is possible to determine whether the device is operating or stopped.

In recent equipment and devices, sensors arranged in the equipment can detect parameters indicating the state in the equipment. However, in the case of equipment that does not have these sensors, it is necessary to modify the equipment and install these sensors. However, in the case of a skilled person working with equipment and equipment, there is no abnormality in the process stage of the processing, assembly, and other processing of the equipment by visual inspection and listening to sound, and the condition of the equipment. Can be monitored. Therefore, even in the monitoring of equipment, the state can be monitored by utilizing the TV camera. By introducing monitoring with this TV camera, it is possible to eliminate the need to introduce a high-cost monitoring system such as modification for sensor installation and monitoring by a skilled person.

In the case of an automatic device that does not involve human operation, the device monitoring camera 13 for the device monitors the movement of, for example, a slot for an object (part) or a moving part (for example, a blade of a cutting device). Can be a camera for. Further, the device monitoring camera 13 can also be used for inspecting the contents of various operations inside the device. For example, in a device for harness connection, a harness connection confirmation inspection can be executed, it can be determined from the image whether or not a correct connection has been made, and if not, an error such as incorrect wiring can be detected.

Further, in this embodiment, the inspection target detecting means for detecting the inspection target and the defect detecting means for detecting the defect can be provided in the cameras 11 to 13 or in the external controller. The inspection target detecting means has a function of detecting an inspection target portion in a non-defective image. As an example, the inspection target detection means may be configured from a deep learning network in which the inspection target portion is learned in advance. By providing this means, it is possible to avoid erroneous detection of a portion having a large deformation but not regarded as an abnormality (for example, a part such as a cable) as a defect.

Then, by inputting the portion detected as the inspection target portion into the defect detection means, the defect to be inspected can be detected. As an example, this means may be configured by learning a plurality of normal parts (images of normal products) in advance from an autoencoder. By creating a difference image between the image reconstructed by the autoencoder and the input image, if there is an abnormal part, the image signal at that position becomes a large value, and it is detected as an abnormality by the threshold processing. The detected defect information (defect image, product information, etc.) can be stored in the defect information storage means.

When a new detection target is provided, the normal image can be learned by the inspection target detection means and the defect detection means (autoencoder). This learning may be performed using the information of the three-dimensional CAD generated at the time of designing the product.

Further, the information (network parameter) learned of the new detection target can be reflected by executing the weighted average with the corresponding parameter of the already learned network. With this method, it is possible to handle cases where each user does not want to upload information about a new detection target to the cloud. That is, by sending the parameters of the learned network shared on the cloud to the user's base and executing the weighted average at the base, a user-specific highly accurate defect detection means and inspection target detection means are configured.・ Can be provided.

The device monitoring camera 13 can use various lenses (ultra-close lens, fisheye lens, wide-angle lens, telephoto lens, etc.) depending on the characteristics of the image pickup target and the distance to the image pickup target.

The progress of the assembly work at the site of the assembly process can be identified and recorded by visual confirmation by a skilled person or a manager having a specific skill. From this point of view, the present embodiment is configured to perform appropriate data processing described below from only the information captured by the TV camera captured by visible light to calculate the takeoff and landing time to be recorded. ..

In addition, when the assembly work at each assembly shop during the assembly process is completed, not only the completion time is recorded, but also the start, completion time, and defects of the assembled intermediate product for each assembly process are detected. And record. The sampling time of this TV camera does not have to be the usual 30 fps or 60 fps, and can be thinned out to a numerical value such as 1 fps or 0.2 fps, if necessary. On the contrary, high-speed imaging such as 120 fps and 2000 fps may be used. The former has the effect of reducing the total amount of stored data, and the latter is necessary when collecting data accompanied by high-speed movement.

The transfer PC 14 has a function of reading video data (which may include both moving images and still images) captured by various cameras 11 to 13 and transferring the video data to the collection / storage server 15. The transfer PC 14 can also be configured to perform a data compression operation by a well-known method prior to the transfer operation. In addition to data compression operation, image processing and image processing (for example, leaving only the part of the image of the person or thing to be monitored, deleting unnecessary images, or increasing the resolution of the monitored image, etc. It is also possible to perform image processing (such as image processing) that reduces the resolution of the image of the object. The transfer PC 14 may be wirelessly connected to the collection / storage server 15 or may be connected by wire.

The collection / storage server 15 is a computer for collecting and storing video data transferred from the transfer PC 14 in a storage unit (not shown). Although the analysis of the collected video data is executed by the analysis server 16, the collection / storage server 15 may be in charge of a part of the analysis process, for example, a part of the analysis of the video data.

The analysis server 16 analyzes various video data stored in the collection / storage server 15, analyzes the movements of people, objects, and machines, and generates analysis data as the analysis result. The generated analysis data is output to the display PC 17, and is visualized and displayed in a form recognizable by the operator. The analysis server 16 can also be configured to compare the analysis data as a result of analyzing the movements of people, objects, and machines with the work plan data and analyze the difference.

The analysis items in the analysis server 16 can include, but are not limited to, items that can be discovered by a human being (for example, a field supervisor) performing daily supervision work. For example, the signal A included in the video data acquired and stored (learned) in the collection / storage server 15 over a long period of time is compared with the signal A'included in the newly acquired video data, and the comparison result is obtained. Can also be an analysis item. When there is a difference of a predetermined value or more between the signals A and A'obtained in this way, the analysis server 16 makes a significant change in the operation of a person, an object, or a machine at the place where the difference occurs. It is specified as a "change point" that indicates a point.

By identifying such change points, it becomes possible to detect the time when significant movements of humans, objects, and machines, which are often overlooked by human monitoring, occur, which is a factor that hinders the work efficiency of the manufacturing process. It can be used as an index. Also, in the case of human monitoring, it is necessary to separate the data when correct operation is performed and the data when abnormal operation is performed, but the positive data is easy to prepare, while it is easy to prepare. Preparing erroneous data is time-consuming. According to this system, it is not necessary to prepare erroneous data, and the system can be easily introduced in a short period of time. The analysis server 16 associates the time and place where such a change point occurs, and mathematically defines it as "working time at a specific working place".

In general, just because people and things are in place does not mean that the work is actually proceeding properly. However, by comparing and analyzing the work time data obtained as described above, for example,
(A) If the work currently being done deviates from the average work time
(B) When the variation in working time is large among multiple tasks
(C) When a person or an object is staying in a place other than a specific work place, these can be detected "mechanically". Although these are different from the "working time" defined or recognized by humans, it is possible to detect the factors that hinder the manufacturing lead time. That is, (a) has an obstructive factor of "deviation from the average time", and (b) has an obstructive factor of "large variation" in the work itself. In (c), there are obstacles such as "waiting for work" and "retention of goods".

The operation of the human surveillance camera 11 will be schematically described with reference to FIG. FIG. 2 shows how a human surveillance camera 11 captures a state in which a plurality of machines ((1) to (9)) are arranged at a manufacturing site and a human (worker) H moves along an arrow. There is. As an example, the human surveillance camera 11 stores information on the physique of human H, the properties of clothes normally worn by human H (color, shape, etc.), and movement characteristics (average walking speed, stride length). be able to. The human surveillance camera 11 can identify the image of human H included in the video data by comparing the information with the video data. The image of the identified human H is enclosed by the bounding box BB, and the video data can be recorded in a form including the bounding box BB.

In this way, when the video data is obtained by the human surveillance camera 11, the video data is analyzed by the analysis server 16, and the human H performs which work in which time zone (residence time) and in which time zone the work is performed. It is possible to analyze whether or not the user is moving (moving time) or is out of the shooting range according to the specified change point of the human movement. The point of change in human behavior can be identified according to the time when the human arrived in front of a given machine, the time when he left, and other information. The bar display at the lower right of FIG. 2 shows the work time (including the start time and the end time) related to the work (4) to (8). Such a bar display can also be displayed on the display screen of the display PC 17.

In the present embodiment, the worker detection means is configured by the human surveillance camera 11 or an external controller. The human surveillance camera 11 as a worker detecting means detects a worker in the acquired image, and may include a deep learning network in which the worker's image is learned in advance. The worker detection means detects the worker in the captured image. From the detected position, whether or not the worker is present at a predetermined position, that is, the entry time and the exit time to the work place are detected. In the present embodiment, captured images are acquired from a plurality of directions, the position of the worker in each two-dimensional image (direction of the viewpoint) can be known, and the intersection position in that direction is the worker in the three-dimensional space. Is detected as the existence position of. This method of detecting the presence position of a worker from a plurality of images is effective in a case where it is desired to improve the depth detection accuracy. It also has the effect of enabling detection by using a plurality of images in cases where the worker is in the shadow of equipment or other objects and does not move into the image.

The operation of the mono surveillance camera 12 and the machine surveillance camera 13 will be schematically described with reference to FIG. FIG. 2 describes an example in which three mono-surveillance cameras 12 (12A to 12C) and three mechanical surveillance cameras 13 (13A to 13C) are arranged as an example, but this is just an example. The number of the mono surveillance camera 12 and the machine surveillance camera 13 is not limited to a specific number. Further, the mono-surveillance camera 12 is not limited to a specific type, but is preferably a two-dimensional code 22 attached to a cart 21 on which an object (parts or the like) is placed, as is schematically shown in FIG. Can be a camera that shoots.

The cart 21 moves between the plurality of machines (11) to (13), for example, as shown in FIG. For example, when the cart 21 finishes the process prior to the machine (11) and moves to the front of the machine (11), the two-dimensional code 22 attached to the cart 21 is imaged by the mono-surveillance camera 12A. As a result, the arrival of the cart 21 at the machine (11) is detected.

When the work on the machine (11) is completed, the cart 21 moves away from the machine (11) and moves toward the next machine (12), the monosurveillance camera 12A detects that the two-dimensional code 22 is no longer imaged. By doing so, the detachment of the cart 21 from the machine (11) is detected. When the cart 21 arrives in front of the machine (12), the two-dimensional code 22 attached to the cart 21 is imaged by the monosurveillance camera 12B. As a result, the arrival of the cart 21 at the machine (12) is detected. By repeating such an operation, it is possible to detect the movement of the cart 21, that is, the object (parts or the like) based on the video data of the object monitoring camera 12.

The change point of the movement of the object can be specified by the start time and the departure time of a certain machine (see FIG. 4). The travel time (waiting time) from the upper machine (process) to the lower machine (process) can be calculated by the difference between the departure time from the upper machine and the arrival time to the lower machine. Similarly, the change point of the operation of the machine can be specified by the time when a certain machine starts a specific operation and the time when a specific operation ends.

Further, the parts intermediate product placed on the cart 21 corresponds to the product serial number or the like associated with the cart number, the part number, the part number, etc. when the parts are placed on the cart 21 on the serving shelf. Given a relationship. The correspondence relationship is also given to the two-dimensional code 22 as information, and when the two-dimensional code 22 is read, the information on these correspondence relationships is automatically collected. By this series of automatic collection, the cart 21, parts, workers, shops, and change times are linked. This link is also made between other shops, other products, and other workers. As a result, at a specific time, the position of the part, the worker, the equipment / equipment / jig is recognized, and the vector data is stored in the storage means. Further, the detection of the time of the state change does not necessarily have to be based on the image captured by the TV camera, and may be combined with information from another sensor, an already installed sensor, or the like.

The operation of the monitoring system 1 according to the embodiment will be described with reference to the flowchart of FIG. In this system, the human surveillance camera 11, the mono surveillance camera 12, and the machine surveillance camera 13 operate independently to monitor the movements of people, objects, and machines. The obtained video data is transferred to the transfer PC 14 and read, and the transfer PC 14 performs a predetermined data compression operation on the video data and then transfers the video data to the collection / storage server 15. The collection / storage server 15 receives and stores the transferred data. The data stored in the collection / storage server 15 is appropriately transmitted to the analysis server 16 and targeted for analysis.

The analysis server 16 identifies the change points of humans, objects, and machines as described above based on the stored data, specifies the time when the change points occur, and further specifies the place where the change points occur, and is not shown. Stores such information in the storage unit. By specifying a plurality of change points, it is possible to specify a significant operation start time and operation end time in each machine of human and thing.

When the change point and the time and place where the change point occurred are specified, the state of people and things in each process can be known, thereby knowing the time required for each process and among a plurality of processes. In which process, it can be determined whether there is room (margin) for shortening the lead time. That is, the analysis server 16 can function as a margin determination means for determining a margin in each process based on the specified change point and the data at the time when a significant operation occurs. The marginal portion can be visually displayed on the display PC 17.

FIG. 6 is an example of a display screen when the analysis result in the analysis server 16 is displayed on the display of the display PC 17. In the display example of FIG. 6, the horizontal axis is the time axis, and the timeline of the manufacturing plan and the timeline of each process (processes 1 to 3) in the actual work (actual results) are displayed as bars for each different production number. It is a Gantt chart that contrasts by display. According to this display, the difference between the manufacturing plan and the actual work on each work day is visualized. According to this screen display, it is possible to visualize which production number is in which process, and to grasp the progress in the large process executed over many days for each small process.

As shown here, the monitoring system of the present embodiment is very effective in monitoring the progress of the manufacturing plan. If the progress of the manufacturing plan is delayed, labor costs, depreciation costs of equipment, etc. will be added, which will lead to an increase in manufacturing costs. This is the reason why the progress management is very effective. Further, when a large delay occurs, an appropriate manufacturing output can be obtained by reviewing the manufacturing plan (manufacturing schedule) again. This is the reason why replanning (rescheduling) of the manufacturing plan is necessary. At this time, the magnitude of the delay can be set in advance, for example, 20% or 30% increase of the initially set lead time. Alternatively, for example, the tact of a specific process that is a bottleneck can be set in advance to increase by 20% or 30%. That is, the monitoring system of this embodiment plays an important role in determining the time when replanning is necessary. In other words, by using the monitoring system of the present invention in combination with the scheduler, a larger effect can be produced. At this time, a certain effect can be expected regardless of whether the scheduler to be tried is a stacked automatic scheduler or a scheduler equipped with some optimization algorithm.

FIG. 7 is another example of the display screen when the analysis result in the analysis server 16 is displayed on the display of the display PC. In the display example on the upper side of FIG. 7, the horizontal axis is the elapsed time, and the breakdown of the working time of each process (processes 1 to 3) for each different production number is displayed as the length of the bar. According to this display, the variation in the total working time in each production is visualized, and the variation in the required time in each process is also visualized. This makes it easy to grasp the production number that required a long working time and investigate the cause.

Further, in the display example on the lower side of FIG. 7, the horizontal axis is the elapsed time, but the movement time between different processes is displayed by the length of the bar for each of a plurality of carts. According to this display, it is possible to visualize which process of which cart the movement time is long, and it is possible to easily investigate the cause.

FIG. 8 is a graph showing the operating time and the operating time in each process (processes 1 to 3). Focusing only on a single process, the higher the ratio of operating time to the whole (operating rate), the higher the work efficiency. However, if the operating rate is high in a certain process and the operating rate is low in an adjacent process, the work efficiency of the entire process cannot be improved. In this way, when there is a difference in the operating rate between adjacent processes, it can be determined that a bottleneck has occurred in the work. If a bottleneck occurs, work efficiency can be improved by changing the manufacturing plan including staffing.

In addition, in the embodiment described above, for security reasons, the user can perform information in the venue (processing of imaging data after acquisition of this embodiment, time detection of state change of people, objects, and devices, and subsequent data processing). There are cases where you want to avoid uploading processing result information) to the cloud. In this case, the change time, product information, and other information can be encoded and decoded with a password set by the user in advance. As a result, these pieces of information can be treated as text information whose contents are more meaningful to people in the hall, and as meaningless information without a password on the cloud.

Further, by performing identification using a hash function before and after using the data on the cloud, it is possible to guarantee that the data on the cloud has not been tampered with, and it is possible to provide security of the user data. This technique adds a pre-hash value to the stored data to generate the next hash value, which means that the tampering work takes a lot of time, providing a situation where tampering is virtually impossible, resulting in security. It may be the one using the blockchain technology which can further improve.

Further, in a system using an image of a TV camera, the worker may feel resistance to the image taken by the worker itself, or may be concerned about leakage of personal information. On the other hand, at the initial stage, the controller or the like can be provided with a means for performing image conversion such as Fourier transform on the captured image and converting it into information that cannot be determined by the human eye. By using such a converted image in a subsequent step such as learning, it is possible to execute the same image conversion in a subsequent step such as worker detection.

By acquiring various time data including the work completion time detected in this way for each product, the lead time from the start to the completion of the product can be analyzed as the work time for each work. Further, for example, at the end of a day's work time, a report can be created by summarizing the progress of the work, the arrangement position of parts, and the like.

The system and method for utilizing various time data such as the takeoff / landing time and the start completion time detected in this way will be described below. According to this system, it is possible to describe the progress time of each work by focusing on a specific product. When the variation in the progress time shown on the left is calculated for a specific product or a specific shop, it can be determined that the work is not mature if the variation is large due to the operator or other disturbance. In that case, for example
・ Change the worker of a specific work to a member with a high degree of work skill. ・ Analyze the cause of variation and take countermeasures such as preparing a jig to separate the work.

Further, in the above case, the deterioration of the work quality can be known in real time by monitoring the variation state of the start completion time.

Further, by preparing an environment having the monitoring system, the production planning system, and the display system shown in FIGS. 6 to 8 on the cloud of the present embodiment, the following new value can be created. For example, when an algorithm that can detect human change points more accurately and with high time resolution is developed, the value of the entire system can be improved by changing only this algorithm. For example, since the process at the time of process change can be decomposed into smaller pieces, the lead time can be shortened by redesigning the process with higher accuracy by changing the combination thereof. In this way, by having a monitoring system, a production planning system, or a display system, new technologies and programs can be easily and quickly applied to the site. In other words, the present invention has an aspect of providing a "base; platform" for improving the efficiency of the production site.

Furthermore, by counting the usage time of each of the technologies and programs applied in the field in this way, it is possible to measure the total utilization time of those technologies. The reward for the system provider can be automatically calculated by the machine according to this utilization time. This is the mechanization of paperwork, but even at the manufacturing site, such mechanization and efficiency improvement of paperwork is important in terms of cost reduction. In addition, by having this type of utilization time measurement system and paying a reward according to the utilization time, the temporary cash payment amount will be reduced compared to introducing the system with a lump sum payment, so-called. The effect of improving cash flow can be expected.

Further, according to this monitoring system, it is possible to detect and issue a deviation from the average work time and the assumed work completion time. In a remote monitoring system using a mere surveillance camera, the observer needs to continue to monitor the image being shot, but the effect is that the system can receive a report only when the image deviates from the assumption. Can be expected.

[effect]
As described above, according to the system of the present embodiment, the movements of people, things, and machines are monitored by the cameras 11 to 13, and the movements of people, things, and machines change significantly according to the change points in the video data. Can be detected, analyzed by the analysis server 16, and the result can be visualized and presented. Therefore, the operator can visually monitor the movements of people, objects, and machines, and can execute the monitoring without inputting one by one and without taking time to set the conditions, and the manufacturing process can be accurately and low. It can be monitored by cost and work efficiency can be improved. In other words, it is possible to take the same measures only by imaging with the cameras 11 to 13 for the matters that are judged sensuously by the eyes of the management supervisor. As a result, it is possible to efficiently monitor the manufacturing site with this system without assigning a dedicated system person in charge. By visualizing the manufacturing site, visualization will be realized, and it will be possible to provide one-stop solutions to management issues beyond that.

The cameras 11 to 13 used can be appropriately changed in the installation location, the type of the camera, or the number of cameras can be increased, and it is easy to respond to the change in the manufacturing site. Specifically, with this system, it is not easy to keep a record of the state or result of assembly work by human, visual inspection by human, transportation of goods by human, operation state of machine by human, etc. Can be recorded. As a result, it is possible to record the state of the work site by a human, as in the case of a factory site composed of an automatic machine having a mechanism for recording data indicating the state.

[others]
The present invention is not limited to the above-mentioned examples, and includes various modifications. For example, the above-described embodiment has been described in detail in order to explain the present invention in an easy-to-understand manner, and is not necessarily limited to the one including all the described configurations. Further, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. Further, it is possible to add / delete / replace a part of the configuration of each embodiment with another configuration.

1 ... Surveillance system, 11 ... Human surveillance camera, 12 ... Mono surveillance camera, 13 ... Device surveillance camera, 14 ... Transfer computer (PC), 15 ... Collection / storage server, 16 ... Analysis server, 17 ... Display computer (PC) , 21 ... Cart, 22 ... Two-dimensional code.

Claims (3)

In a monitoring system that monitors people, goods, or equipment at the manufacturing site
A camera that monitors the person, thing, or device,
An analysis unit that analyzes the video data obtained by the camera,
It is provided with a display unit that displays the analysis result by the analysis unit.
The analysis unit is a monitoring system characterized in that it detects a change point in the video data and analyzes the state of the person, an object, or a device based on the change point. The analysis unit
A change point detecting means for detecting the change point of the person, the thing, and the apparatus from the video data obtained by the camera.
The monitoring system according to claim 1, further comprising a motion detecting means for identifying a time point at which a significant motion of the person, the object, or the device occurs from the time data of the plurality of change points. The monitoring system according to claim 2, further comprising a margin portion determining means for determining a margin portion as a room for shortening the lead time in each process based on the detection result of the operation detecting means.

Images