JP2021125131A - Management device - Google Patents

Abstract

To improve the utilization of an illumination device equipped with a camera.SOLUTION: A management device includes an acquisition section, a detection section and a tagging section. The acquisition section acquires photographic data photographed by a camera unit of an illumination device equipped with a camera, having an illumination unit and the camera unit. The detection section detects an error at a photographic site from the photographic data acquired by the acquisition section and specific information. The tagging section, when an error is detected by the detection section, tags error information concerning the error onto the photographic data with the detected error.SELECTED DRAWING: Figure 2

Description

Embodiments of the present invention relate to management devices.

In recent years, there is a lighting device with a camera including a lighting unit and a camera unit in one housing. Such camera-equipped lighting devices are also being introduced for applications such as monitoring production lines in factories and monitoring the status of employees in offices.

Japanese Unexamined Patent Publication No. 2019-204613

In the prior art, there was room for improvement in increasing the utility value of the lighting device with a camera. That is, the shooting data shot by the camera unit is only displayed or recorded.

An object of the present invention to be solved is to provide a management device capable of increasing the utility value of a lighting device with a camera.

The management device according to the embodiment includes an acquisition unit, a detection unit, and a tagging unit. The acquisition unit acquires shooting data obtained by shooting a work site by a camera unit of a camera-equipped lighting device having a lighting unit and a camera unit. The detection unit detects an error at the shooting site from the shooting data acquired by the acquisition unit and specific information. When an error is detected by the detection unit, the tagging unit tags the shooting data in which the error is detected with error information related to the error.

According to the present invention, the utility value of the lighting device with a camera can be increased.

FIG. 1A is a side view of the lighting device with a camera according to the first embodiment. FIG. 1B is a bottom view of the lighting device with a camera according to the first embodiment. FIG. 1C is a schematic view of the lighting system according to the first embodiment. FIG. 2 is a block diagram of the management device according to the first embodiment. FIG. 3 is a diagram showing an example of processing of the detection unit according to the first embodiment. FIG. 4 is a diagram showing an example of processing of the detection unit according to the first embodiment. FIG. 5 is a diagram showing an example of a measurement result of work efficiency. FIG. 6 is a flowchart showing a processing procedure executed by the management device according to the first embodiment. FIG. 7 is a block diagram of the management device according to the second embodiment. FIG. 8 is a flowchart showing a processing procedure executed by the management device according to the second embodiment.

The management device 100 according to the embodiment described below includes an acquisition unit 4a, a detection unit 4b, and a tagging unit 4c. The acquisition unit 4a acquires shooting data obtained by shooting the work site by the camera unit of the camera-equipped lighting device 10 having the lighting unit 20 and the camera unit 30. The detection unit 4b detects an error at the shooting site from the shooting data acquired by the acquisition unit 4a and the specific information. When an error is detected by the detection unit 4b, the tagging unit 4c tags the shooting data in which the error is detected with error information related to the error.

Further, in the management device 100 according to the embodiment described below, the tagging unit 4c tags the shooting data by changing the lighting mode of the lighting unit 20.

Further, the management device 100 according to the embodiment described below further includes a reproduction unit 4d that cuts out and reproduces the shooting data tagged with the error information by the tagging unit 4c.

Further, the management device 100a according to the embodiment described below includes an acquisition unit 4a, an input unit 4h, and a detection unit 4b. The acquisition unit 4a acquires shooting data obtained by shooting the work site by the camera unit of the camera-equipped lighting device 10 having the lighting unit 20 and the camera unit 30. The input unit 4h inputs specific information. The detection unit 4b detects an error at the shooting site from the shooting data acquired by the acquisition unit 4a and the specific information.

Further, in the management device 100 described below, the specific information is model data indicating the state of the product for each work process, and the detection unit 4b detects an error based on the state of the product and the model data reflected in the shooting data. do.

Further, in the management device 100 described below, the detection unit 4b detects an error based on the difference in the number of parts or accessories of each state of the product reflected in the model data and the photographing data.

Further, the management device 100 described below includes a learning unit 4f that learns model data from past shooting data.

Further, in the management device 100 described below, the specific information is information regarding the work cycle of the assembly line when the shooting site is the site of the assembly line.

Further, the management device 100 described below includes a notification unit 4g that notifies the operator when an error is detected by the detection unit 4b.

Further, the management device 100 described below includes a measurement unit 4e that measures the work efficiency per unit time from the shooting data.

(First Embodiment)
First, the camera-equipped lighting device 10 according to the first embodiment will be described with reference to FIGS. 1A and 1B. FIG. 1A is a side view of the camera-equipped lighting device 10 according to the first embodiment. FIG. 1B is a bottom view of the camera-equipped lighting device 10 according to the first embodiment.

As shown in FIG. 1A, the camera-equipped lighting device 10 according to the embodiment includes a lighting unit 20, a camera unit 30, and a power supply unit 40. Further, the lighting unit 20 and the camera unit 30 are screwed together via an L-shaped metal fitting, and the lighting unit 20 and the power supply unit 40 are connected via a connecting portion 12.

The connecting portion 12 is further joined to the mounting portion 11, and the lighting device 10 with a camera is mounted on an installation surface such as a ceiling via the mounting portion 11.

The lighting unit 20 includes a light source unit 21 and fins 25. The fins 25 are provided above the light source unit 21 and cool the heat generated by the light emission of the light source unit 21. As shown in FIG. 1B, the light source unit 21 is provided with a light emitting element 21b such as an LED (Light Emitting Diode) on the substrate 21a.

Further, the exit surface of the light source unit 21 is covered with the cover 22. The cover 22 is, for example, transparent glass or resin. The example shown in FIG. 1B shows a case where the light source unit 21 is composed of four substrates 21a, but the present invention is not limited to this.

Further, the camera unit 30 includes an imaging unit 31 and a lens 32. The imaging unit 31 includes an imaging sensor such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor), and various components necessary for capturing an image or video. Further, the lower surface of the imaging unit 31 is covered with the lens 32.

Further, as shown in FIG. 1B, the light source unit 21 and the image pickup unit 31 are oriented downward at the time of attachment. As a result, the area illuminated by the light source unit 21 can be imaged by the image pickup unit 31, so that the illuminance of the object to be photographed can be secured, and a clear image can be imaged.

Further, since the lighting device 10 with a camera is installed on the ceiling, it is possible to take a bird's-eye view of the space from the ceiling. The external shape of the camera-equipped lighting device 10 shown in FIGS. 1A and 1B is an example, and may have other shapes such as a base light and a ceiling light.

Next, the lighting system S according to the embodiment will be described with reference to FIG. 1C. FIG. 1C is a diagram showing an outline of the lighting system S according to the embodiment. In the following, a case where the lighting system S is introduced in a factory will be described as an example.

As shown in FIG. 1C, the lighting system S according to the embodiment includes a plurality of camera-equipped lighting devices 10 and a management device 100. Further, in the example shown in FIG. 1C, a case where each lighting device 10 with a camera is installed at a work site (for example, a production line) of a factory is shown.

The management device 100 is a device that manages each of the camera-equipped lighting devices 10 installed at the work site. For example, the management device 100 remotely controls the lighting mode of the lighting unit 20 of each camera-equipped lighting device 10, the imaging direction of the camera unit 30, the magnification, and the like via the network N.

In addition, the management device 100 collects and stores images or videos taken by each camera unit 30. For example, the image or video collected by the management device 100 is used for monitoring the work site or the like.

By the way, as described above, the management device 100 accumulates the shooting data taken by each camera unit 30. However, in the past, the shooting data accumulated in the management device was only stored and displayed to the manager. Therefore, there is room for improvement in increasing the utility value of the camera-equipped lighting device 10.

Therefore, in the management device 100 according to the first embodiment, it is decided to detect an error at the shooting site from the shooting data. In the following, a case where the shooting site is a work place will be described. Further, the error in the workplace indicates an error or error in the work performed on the line, or an error in the work of various processes performed in the workplace. That is, the management device 100 according to the embodiment detects an arbitrary error such as a work or a work error that occurs in the work place as an error in the work place.

FIG. 2 is a block diagram of the management device 100 according to the first embodiment. As shown in FIG. 2, the management device 100 includes a communication unit 2, a storage unit 3, and a control unit 4. The communication unit 2 is a communication module that performs data communication with each camera-equipped lighting device 10 via the network N.

The storage unit 3 is, for example, a semiconductor memory element such as a flash memory, or a storage device such as an HDD or an optical disk. In the example shown in FIG. 2, the storage unit 3 has a photographing data database 3a, a specific information database 3b, and a working data database 3c.

The shooting data database 3a is a database that stores shooting data taken by each camera-equipped lighting device 10. In this embodiment, in particular, the shooting data obtained by shooting each work process in the workplace is stored in the shooting data database 3a.

The specific information database 3b is a database that stores specific information for detecting an error in the workplace. As an example of the specific information, there is model data showing the state of the product for each work process in each work process. Such model data is generated, for example, by the learning unit 4f, which will be described later.

The work data database 3c is a database that stores information on the work efficiency of each production line. For example, information on work efficiency is generated by the measuring unit 4e, which will be described later.

Next, the control unit 4 will be described. The control unit 4 includes, for example, a microcomputer having a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), an input / output port, and various circuits.

In the example shown in FIG. 2, the control unit 4 includes an acquisition unit 4a, a detection unit 4b, a tagging unit 4c, a reproduction unit 4d, a measurement unit 4e, a learning unit 4f, and a notification unit 4g. The functions of the acquisition unit 4a, the detection unit 4b, the tagging unit 4c, the playback unit 4d, the measurement unit 4e, the learning unit 4f, and the notification unit 4g are, for example, such that the CPU of the control unit 4 stores the RAM, ROM, or storage of the control unit 4. It is realized by reading and executing the program stored in the part 3.

Part or all of the acquisition unit 4a, the detection unit 4b, the tagging unit 4c, the reproduction unit 4d, the measurement unit 4e, the learning unit 4f, and the notification unit 4g are ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable). It may be configured by hardware such as Gate Array).

The acquisition unit 4a acquires shooting data obtained by shooting the work site by the camera unit 30 of the camera-equipped lighting device 10 including the lighting unit 20 and the camera unit 30. For example, the acquisition unit 4a acquires shooting data from each camera unit 30 in real time, and stores the acquired shooting data in the shooting data database 3a each time the shooting data is acquired.

At this time, when there are a plurality of manufacturing lines, the shooting data for each work process is sequentially stored in the shooting data database 3a for each manufacturing line.

The detection unit 4b detects an error in the work place (shooting site) from the shooting data acquired by the acquisition unit 4a and the specific information. Here, as described above, the "error in the workplace" refers to an error or error in the work performed on the line, or an error in the work of various processes performed in the workplace.

In the following, for example, a case where a packing error of an accessory part is detected as an error in the workplace due to a human error will be described.

For example, the detection unit 4b performs image analysis and detects an error based on the model data indicating the state of the product for each work process and the state of the product reflected in the shooting data. More specifically, the detection unit 4b detects an error based on the difference in the number of parts or accessories between the model data and the state of the product reflected in the photographed data.

Here, a specific example of the detection process by the detection unit 4b will be described with reference to FIG. FIG. 3 is a diagram showing an example of processing of the detection unit 4b according to the first embodiment. Note that FIG. 4 shows a scene in which parts are sequentially packed in corrugated cardboard for each work process.

For example, in the model data Le shown on the left side of FIG. 3, a total of three parts P1 to P3 are packed in corrugated cardboard. On the other hand, the photographing data La shown on the right side of FIG. 3 shows a case where the parts P1 and P3 are packed in the corrugated cardboard, but the parts P2 are not packed.

The detection unit 4b recognizes that the component P2 is not packed from the difference between the model data Le and the shooting data La, and detects it as an error. In this way, by detecting the error based on the difference, the error can be easily detected. The presence or absence of passage of corrugated cardboard may be detected by a microwave sensor. That is, the error may be detected based on the combination of the detection results of other sensors other than the shooting data.

Further, the detection unit 4b may detect each of the parts P1 to P3 from the photographed data La by image recognition, and may recognize that the unrecognized parts P2 are not packed as a result of the image recognition.

That is, in this case, each component P1 to P3 is recognized from the shooting data La, and if the number of recognized components P1 to P3 does not match the number of components P1 to P3 in the model data, it is detected as an error. do.

In this case, each component may be recognized from the color of each component reflected in the shooting data. For example, each component may be recognized based on the degree of coincidence between the RGB of each pixel of the shooting data and the RGB of each component in the model data.

Further, assuming that the part is an instruction manual, characters are usually printed in the instruction manual. Therefore, the presence or absence of characters may be recognized from the contrast difference of RGB from the shooting data, and it may be determined whether or not the characters are packed in the instruction manual. In this case, the illuminance, color temperature, frequency, and the like of the lighting unit 20 may be adjusted so that the RGB values of the components in the shooting data approach the RGB of the model data.

The detection unit 4b may detect the error from the difference between the shooting data before and after the work process instead of the model data. For example, when the part P2 is packed in one work process, it is detected as an error when there is no change in the corrugated cardboard before and after the work process, that is, when the part P2 is not packed. do. Needless to say, the detection unit 4b can also detect an error even when a specific part is packed in a larger number than usual.

Further, as another example, the detection unit 4b can detect the above error based on, for example, the work interval of the operator. FIG. 4 describes a specific example of the detection process by the detection unit 4b.

The operation timing shown in A of FIG. 4 indicates the operation timing of the packing work of the operator, and the operation cycle shown in B of FIG. 4 indicates the flow cycle of the corrugated cardboard. That is, here, the specific information becomes the work cycle, and if the parts P2 are packed in all the corrugated cardboard, the operation timing and the work cycle coincide with each other.

On the other hand, when the operation timing is small in the work timing, the component P2 is not packed. In this case, the detection unit 4b tracks the movement of the worker by image recognition and detects an error based on the work interval of the worker.

As described above, the camera-equipped lighting device 10 is installed on the ceiling. Therefore, for example, it can be assumed that the corrugated cardboard is blocked from the camera unit 30 by the head of an operator or the like. On the other hand, by detecting the error based on the operator, it is possible to detect the error even when the part or the like cannot be directly recognized from the shooting data.

Returning to the description of FIG. 2, the tagging unit 4c will be described. When an error is detected by the detection unit 4b, the tagging unit 4c tags the shooting data in which the error is detected with error information related to the error.

For example, the error information is a flag, the flag of the shooting data in which no error is detected is "0", and the flag of the shooting data in which no error is detected is "1".

Further, the tagging unit 4c may tag the shooting data by changing the lighting mode of the lighting unit 20 when an error is detected. Specifically, for example, the tagging unit 4c changes the lighting mode of the camera-equipped lighting device 10 that captures the photographing data in which the error is detected.

For example, the illumination mode includes frequency and illuminance. Further, in this case, if the work is stopped by changing the lighting mode, the work efficiency is lowered. Therefore, it is preferable to change the lighting mode within a range that does not hinder the work.

In this case, the lighting mode reflected in the shooting data changes before and after the error is detected, and the time when the error occurs can be detected from the change point of the lighting mode.

The reproduction unit 4d cuts and reproduces the shooting data tagged with the error information by the tagging unit 4c. That is, the playback unit 4d extracts the shooting data tagged with the error information from the shooting data database 3a and reproduces the shooting data.

As described above, when the error information is a flag, shooting data related to the error can be extracted based on the presence or absence of the flag. Further, when the error information is a change in the illumination mode, the presence or absence of the error information can be detected by the change in the spectrum of the shooting data.

Then, the reproduction unit 4d reproduces the shooting data while displaying the shooting time. As a result, only the shooting data indicating the error status is reproduced, so that the work manager can easily grasp the error status.

In this case, for example, it is preferable to play back a predetermined period before and after (for example, 1 minute before and after) based on the time when the error is detected.

The measuring unit 4e measures the work efficiency per unit time from the shooting data. For example, as shown in FIG. 4, the measuring unit 4e can measure the work efficiency per unit time based on the operation timing.

For example, the measurement unit 4e measures the work efficiency for each production line and stores the measurement result in the work data database 3c. FIG. 5 is a diagram showing an example of a measurement result of work efficiency. In the example of FIG. 5, the transition of work efficiency is shown for each production line.

As shown in FIG. 5, for example, in the production line w1, the work efficiency is not uneven, and the production line w2 once faces the peak P at which the production efficiency is maximized, but the other work efficiencies are higher than those of the production line w1. Indicates inferior.

Further, the production line w3 shows that the work efficiency is inferior to that of the production lines w1 and w2. Here, the case where the work efficiency of the peak P is continuously performed on all the production lines w1 to w3 is the upper limit of the production capacity of the production lines w1 to w3.

That is, by measuring the work efficiency, it can be used for grasping the upper limit of the production capacity of the production line, reviewing the efficiency improvement of the production line, and the like. The measuring unit 4e may tag the imaging data at the singular point (for example, peak P) of the work efficiency. Further, at this time, the worker for each production line may be recognized from the shooting data, and the worker may be tagged with the measurement result of the work efficiency or the shooting data.

This makes it easier for the work manager to consider reviewing the staffing. In the above example, the case where the work efficiency is measured for each production line has been described, but the present invention is not limited to this. That is, the work efficiency of each work process may be measured.

Returning to the explanation of FIG. 2, the learning unit 4f will be described. The learning unit 4f learns the above model data from the past shooting data. For example, the learning unit 4f can learn the model data by machine learning using the shooting data as the model for each work process as the teacher data.

The model data may include each part, as shown in FIG. 3, or may be the part itself for each work process. The configuration of the learning unit 4f may be provided in a device (for example, a cloud) different from the management device 100.

The notification unit 4g notifies the operator when an error is detected by the detection unit 4b. That is, the management device 100a immediately notifies the occurrence of an error. For example, the notification unit 4g notifies the operator of an error by changing the lighting mode of the lighting unit 20 of the corresponding lighting device 10 with a camera or outputting a voice from a microphone in the work place. The lighting mode here indicates blinking, change in color temperature, and the like.

Next, the processing procedure executed by the management device 100 according to the embodiment will be described with reference to FIG. FIG. 6 is a flowchart showing a processing procedure executed by the management device 100 according to the embodiment. The processing procedure shown below is repeatedly executed by the control unit 4 of the management device 100.

As shown in FIG. 6, when the management device 100 acquires the shooting data (step S101), the management device 100 performs image analysis of the shooting data (step S102). Subsequently, the management device 100 determines whether or not an error has been detected as a result of image analysis (step S103), and if an error is detected (step S103, Yes), tags the shooting data (step S104). , End the process.

If the management device 100 does not detect an error in the determination in step S103 (steps S103, No), the management device 100 omits the process in step S104 and ends the process.

(Second Embodiment)
In the above-described embodiment, the case where an error is detected based on the specific information registered in advance has been described, but the present invention is not limited to this. That is, the error may be detected based on the specific information input later.

Here, the management device 100a according to the second embodiment will be described with reference to FIGS. 7 and 8. FIG. 7 is a block diagram of the management device 100a according to the second embodiment. In the example shown in FIG. 7, the management device 100a includes an input unit 4h instead of the learning unit 4f of the management device 100 already described.

The input unit 4h inputs specific information. For example, the input unit 4h inputs information to be detected for an error as specific information. For example, suppose that after all the packing work by the worker is completed, the instruction manual that should have been packed is left over.

In this case, the input unit 4h inputs data for specifying the instruction manual from the shooting data as specific information, for example, based on the operation of the operator. The detection unit 4b performs error detection processing from the shooting data recorded in the shooting data database 3a based on the specific information.

In this way, the management device 100a can detect an error that was not initially expected by accepting the input of the specific information by the input unit 4h.

Next, the processing procedure executed by the management device 100a according to the second embodiment will be described with reference to FIG. FIG. 8 is a flowchart showing a processing procedure executed by the management device 100a according to the second embodiment.

As shown in FIG. 8, when the management device 100a inputs the specific information (step S201), the management device 100a performs image analysis of the shooting data stored in the shooting data database 3a based on the specific information (step S202). Subsequently, the management device 100a determines whether or not an error has been detected as a result of the image analysis (step S203), and if an error is detected (step S203, Yes), reproduces the shooting data of the corresponding portion of the error. (Step S204), the process ends.

If the management device 100a does not detect an error in the determination in step S203 (steps S203, No), the management device 100a shifts to the process in step S202.

By the way, in the above-described embodiment, the case where the learning unit 4f and the input unit 4h are provided in separate management devices 100 has been described, but the present invention is not limited to this. That is, the learning unit 4f and the input unit 4h may be provided in the same management device 100, respectively.

Further, some or all the functions of the management device 100 may be provided in each camera-equipped lighting device 10. That is, each camera-equipped lighting device 10 may detect an error.

Further, in the above-described embodiment, the case where the lighting system S is installed in the factory has been described, but the present invention is not limited to this. That is, the lighting system S may be installed in another place such as an office or a hospital.

Although embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. This embodiment can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. This embodiment and its modifications are included in the scope and gist of the invention, as well as in the scope of the invention described in the claims and the equivalent scope thereof.

4a Acquisition unit 4b Detection unit 4c Tagging unit 4d Playback unit 4e Measurement unit 4f Learning unit 4g Notification unit 4h Input unit 10 Camera-equipped lighting device 20 Lighting unit 30 Camera unit 40 Power supply unit 100, 100a Management device

Claims (10)

An acquisition unit that acquires shooting data taken by the camera unit of a camera-equipped lighting device including a lighting unit and a camera unit;
A detection unit that detects an error at the shooting site from the shooting data and specific information acquired by the acquisition unit;
When an error is detected by the detection unit, a tagging unit that tags the shooting data in which the error is detected with error information related to the error;
A management device equipped with. The tagging part is
By changing the lighting mode of the lighting unit, the shooting data is tagged.
The management device according to claim 1. A playback unit that cuts and reproduces the shooting data tagged with the error information by the tagging unit;
The management device according to claim 1 or 2, further comprising. An acquisition unit that acquires shooting data taken by the camera unit of a camera-equipped lighting device including a lighting unit and a camera unit;
With an input section for entering specific information;
A detection unit that detects an error at the shooting site from the shooting data acquired by the acquisition unit and the specific information;
A management device equipped with. The specific information is model data indicating the state of the product for each work process.
The detection unit detects the error based on the state of the product and the model data reflected in the shooting data.
The management device according to any one of claims 1 to 4. The detection unit
The error is detected based on the difference in the number of parts or accessories for each state of the product reflected in the model data and the shooting data.
The management device according to claim 5. Learning unit that learns the model data from past shooting data;
The management device according to claim 5 or 6, further comprising. The specific information is
Information on the work cycle of the assembly line when the shooting site is an assembly line site.
The management device according to any one of claims 1 to 7. A notification unit that notifies the operator when an error is detected by the detection unit;
The management device according to any one of claims 1 to 8, further comprising. A measuring unit that measures work efficiency per unit time from the shooting data;
The management device according to any one of claims 1 to 9, further comprising.

Images