JP7275983B2 - Work analysis device and work analysis program - Google Patents

Description

TECHNICAL FIELD The present invention relates to a work analysis device and a work analysis program that generate determination data for determining whether correct work is being performed.

Conventionally, by capturing a large number of videos of a worker performing a predetermined task such as the task of assembling a plurality of parts to a member to be assembled such as a substrate, and analyzing the video, it is possible to determine whether the task is being performed correctly. A system is employed that generates judgment data (annotation data) for judging whether or not, and uses the data thus generated to support work.

As a technique for generating such annotation data, for example, a work analysis device disclosed in Patent Literature 1 below is known. In the work analysis process performed by this work analysis device, the read work moving image to be analyzed is reproduced and displayed on the work analysis screen together with the measurement state display area and the like. Then, when the operator performs a delimiting operation by clicking a part of the playback screen with a mouse during playback of the moving image, a selection screen is displayed on the part of the playback screen. In this display state, when the operator performs a selection operation by clicking with a mouse on any of the attribute information displayed on the selection screen, the attribute information selected by the selection operation is displayed for the moving image range delimited by the delimitation operation. Analytical data including are associated and recorded.

JP 2017-134666 A

By the way, in the work analysis device disclosed in the above-mentioned Patent Literature 1, after the repetition of a predetermined work in which a plurality of unit works are performed in a predetermined order is captured as a video, a worker or the like who is watching the reproduced video may An operation such as clicking a portion of the playback screen with a mouse is required. For this reason, unless the entire moving image is viewed, the moving image range cannot be separated for each unit work, and there is a problem that the work becomes a heavy burden on the worker and the like. In particular, when the number of types of unit work increases and the number of repetitions of the predetermined work increases, the above problem becomes more pronounced. In addition, since it is necessary to perform an operation while watching the reproduced moving image after capturing the repetition of the predetermined work as a moving image, there is a problem that the annotation data cannot be generated while capturing the moving image of the predetermined work.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-described problems, and an object of the present invention is to provide judgment data for judging whether or not the correct work is being performed, to perform a predetermined work repeatedly. To provide a configuration capable of generating in real time based on a work moving image in which a is taken.

In order to achieve the above object, the invention described in claim 1 of the scope of claims includes:
A work analysis device (10) for generating determination data for determining whether correct work is being performed,
an imaging unit (13) for imaging repetition of a predetermined work in which a plurality of unit tasks are performed by a worker in a predetermined order;
A setting unit ( 11) and
a generation unit (11) for generating the determination data so as to include the work moving image captured by the imaging unit and the delimiter information set by the setting unit;
with
The generation unit generates the determination data so as to exclude a unit work immediately preceding the unit work performed in an order different from the predetermined order, based on the delimiter information set by the setting unit. characterized by generating
It should be noted that the symbols in parentheses above indicate the corresponding relationship with specific means described in the embodiments to be described later.

In the first aspect of the present invention, the setting unit includes delimiter information for delimiting the work moving image captured by the imaging unit into units of work at detection timings of predetermined motions based on predetermined motions set in advance for each unit of work. The generation unit generates determination data so as to include the work moving image captured by the imaging unit and the delimiter information set by the setting unit.

As a result, the work video can be automatically segmented for each unit work only by capturing the predetermined motions performed by the worker for each unit work. Therefore, the determination data for determining whether or not the correct work is being performed can be generated in real time based on the work video imaged of the predetermined work that is repeatedly performed.
In particular, the generation unit generates the determination data based on the delimiter information set by the setting unit so as to exclude the unit work immediately preceding the unit work performed in an order different from the predetermined order. . For example, when predetermined work is performed in the order of unit work A, unit work B, and unit work C, a predetermined action corresponding to unit work A is detected and then a predetermined action corresponding to unit work C is detected. Assume that the In this case, since the predetermined movement of unit work B that was actually performed after unit work A cannot be detected for some reason, the work video segmented as unit work A also includes the work video of unit work B. Therefore, unit work A immediately preceding unit work C, which was performed in an order different from the predetermined order, is excluded. In this way, since a moving image of a unit work that is not regarded as normal work is automatically excluded from the determination data, the reliability of the determination data can be improved.

In the invention of claim 2, the unit work is a work of assembling a part taken out of a parts box associated with the unit work into a member to be assembled, and the predetermined operation is an operation of taking out the part from the parts box. In this way, the work animation can be segmented at the detection timing of the work motions essential for the unit work, and motions unrelated to the original unit work are not forced. The burden can be reduced.

In the invention of claim 3, the unit work is a work of assembling a part associated with the unit work to the member to be assembled, and the predetermined operation moves the part to the planned assembly position of the member to be assembled. It is action. In this way, the work animation can be segmented at the detection timing of the work motions essential for the unit work, and motions unrelated to the original unit work are not forced. The burden can be reduced.

In the fourth aspect of the invention, the generation unit calculates a normal work time range for each unit work based on the delimiter information set by the setting unit. Work is generated as data for judgment. As a result, it is possible to automatically use a moving image of a unit work that is considered to be normal work in consideration of the work time as determination data, thereby improving the reliability of the determination data.

In the fifth aspect of the present invention, the generation unit generates determination data so as to exclude unit work whose work time is out of the normal work time range. As a result, it is possible to automatically exclude moving images of unit work that are not regarded as normal work from the determination data, and improve the reliability of the determination data.

According to the invention of claim 6 , it is possible to realize a work analysis program having the same effect as that of claim 1.

It is an explanatory view showing a schematic structure of a work analysis device concerning a 1st embodiment. It is explanatory drawing explaining the imaging state where each component box is imaged. 1 is a block diagram illustrating an electrical configuration of a work analysis device; FIG. 4A and 4B are explanatory diagrams for explaining the division operation in the first embodiment, FIG. 4A shows the division operation of unit work A, and FIG. 4B shows the division operation of unit work B; 5A and 5B are explanatory diagrams for explaining the division operation in the first embodiment, FIG. 5A shows the division operation of the unit work C, and FIG. 5B shows the division operation of the unit work D; 6 is a flowchart illustrating the flow of work analysis processing performed by a control unit; FIG. 9 is an explanatory diagram for explaining detection results of work breaks in which break information is set for each unit work; FIG. 11 is an explanatory diagram for explaining monitoring regions for detecting a break motion in the second embodiment; 9A and 9B are explanatory diagrams for explaining the division operation in the second embodiment, FIG. 9A shows the division operation of the unit work A, and FIG. 9B shows the division operation of the unit work B; 10A and 10B are explanatory diagrams for explaining the division operation in the second embodiment, FIG. 10A shows the division operation of unit work C, and FIG. 10B shows the division operation of unit work D; It is an explanatory view explaining a monitoring device of a work analysis device concerning a 3rd embodiment. FIG. 12 is an explanatory diagram illustrating a state in which a break motion is detected in the third embodiment; FIG. 13(A) is an explanatory diagram for explaining the monitoring device of the work analysis device according to the fourth embodiment, and FIG. 13(B) shows a state in which parts boxes are arranged in the monitoring area of FIG. 13(A). It is an explanatory view explaining. FIG. 14(A) is an explanatory diagram for explaining a monitoring device of a work analysis device according to a modification of the fourth embodiment, and FIG. 14(B) shows parts boxes arranged in the monitoring area of FIG. 14(A). FIG. 10 is an explanatory diagram for explaining a state in which FIG. 21 is an explanatory diagram for explaining a state of setting a monitoring area in the fifth embodiment; FIG. 21 is an explanatory diagram illustrating a height state in which the detection of a break motion is valid and a height state in which the detection of a break motion is invalid in the fifth embodiment; 17A and 17B are explanatory diagrams for explaining the monitoring device of the work analysis device according to the sixth embodiment, FIG. The state assembled to the work W is shown. 18 is a graph for explaining weight changes monitored by the monitoring device of FIG. 17; FIG. 21 is an explanatory diagram illustrating setting of a temporary monitoring area in a parts box in the seventh embodiment; FIG. 20 is an explanatory diagram for explaining setting of a temporary monitoring area in a work in the seventh embodiment; FIG. 21A is an explanatory diagram for explaining a monitor area set from a temporary monitor area with a weight of "3", and FIG. FIG. 4 is an explanatory diagram for explaining monitoring areas to be set; FIG. 20 is an explanatory diagram showing a schematic configuration of a work analysis device according to an eighth embodiment; FIG. 22 is a flowchart illustrating the flow of monitoring area setting processing performed by the control unit in the eighth embodiment; FIG. 24 is a flowchart illustrating the flow of a subroutine of parts box relative coordinate estimation processing in FIG. 23; 24 is a flowchart illustrating the flow of a subroutine of camera relative coordinate estimation processing in FIG. 23; FIG. 26A is an explanatory diagram for explaining the positional relationship between the second imaging section and the parts box, and FIG. 26B is an image captured by the second imaging section in the positional relationship shown in FIG. FIG. 10 is an explanatory diagram for explaining a captured image; It is explanatory drawing explaining the calculation method of the distance from a 2nd imaging part to a component box code|cord. FIG. 10 is an explanatory diagram illustrating a pasting position of a parts box code to a parts box; FIG. 29(A) is an explanatory diagram for explaining a state in which the parts box code is randomly assigned to the parts box, and FIG. 29(B) shows the positional relationship shown in FIG. It is an explanatory view explaining a captured image that has been captured. FIG. 21 is an explanatory diagram showing a main part of a work analysis device according to a first modified example of the eighth embodiment; FIG. 21 is an explanatory diagram showing a main part of a work analysis device according to a second modified example of the eighth embodiment; FIG. 32(A) is an explanatory diagram illustrating a state in which the parts box code is attached to the upper end of the peripheral wall of the parts box, and FIG. 32(B) illustrates a state in which the parts box code is attached to the upper lid. It is an explanatory diagram for. FIG. 22 is an explanatory diagram showing the main part of the work analysis device according to the ninth embodiment; FIG. 34(A) is an explanatory diagram showing a distance image in a state where the parts box is imaged near the imaging unit, and FIG. FIG. 10 is an explanatory diagram showing a distance image in a captured state; FIG. 16 is a flowchart illustrating the flow of monitoring area setting processing performed by a control unit in the ninth embodiment; FIG. FIG. 36A is an explanatory diagram showing the main part of the work analysis device according to the tenth embodiment, FIG. 36A shows a captured image of two component boxes placed on a shelf, and FIG. shows a state in which FIG. 36A is divided into blocks. FIG. 37 is a graph showing frequency feature quantities extracted from blocks B1 to B4 in FIG. 36; FIG. FIGS. 38A and 38B are explanatory diagrams showing the essential parts of the work analysis device according to the eleventh embodiment, FIG. 38(A) is taken to show a distance image. FIG. 39A is an explanatory diagram showing the main part of the work analysis device according to the twelfth embodiment, FIG. 39A shows a captured image of two parts boxes placed on the shelf, and FIG. shows a captured image in which the second color region is extracted, and FIG. 39C shows a captured image after performing the filtering process. FIG. 20 is an explanatory diagram for explaining a main part of monitoring area setting processing performed by the work analysis device according to the thirteenth embodiment; FIG. 22 is a flowchart illustrating the flow of monitoring area setting processing performed by a control unit in the thirteenth embodiment; FIG. FIG. 42 is a flow chart illustrating the flow of a subroutine of component area setting processing in FIG. 41; FIG. FIG. 10 is an explanatory diagram for explaining monitoring areas that are set based on component areas; FIG. 30 is an explanatory diagram for explaining a main part of monitoring area setting processing performed by the work analysis device according to the first modification of the thirteenth embodiment; FIG. 11 is an explanatory diagram illustrating detection results of line-scanning luminance values in the X-coordinate direction with respect to a predetermined Y-coordinate; FIG. 32 is an explanatory diagram for explaining a main part of monitoring area setting processing performed by the work analysis device according to the second modified example of the thirteenth embodiment; 7 is a graph for explaining the appearance frequency of angles of corners detected from an extracted image.

[First embodiment]
Hereinafter, a first embodiment embodying a work analysis device and a work analysis program according to the present invention will be described with reference to the drawings.
As illustrated in FIG. 1, the work analysis device 10 according to the present embodiment is provided on a workbench 1 or the like. The apparatus is configured as a device that captures a work video taken from a worker and generates judgment data (annotation data) for judging whether or not the correct work is being performed for each unit work based on the work video. That is, the determination data is generated by setting delimiter information for delimiting the work moving image in which a predetermined work is repeated for each unit work. Therefore, it is possible to extract a large number of moving image ranges in which each unit work is imaged from the determination data.

A member to be assembled such as a printed circuit board (hereinafter also simply referred to as a work W) is transported and placed on the workbench 1 where the assembly work is performed. A plurality of component boxes 30 are arranged on the shelf 2 of the workbench 1 so as to be aligned left and right as seen from the worker M, and each component box 30 contains a plurality of types of components 20 to be assembled to the work W. are stored separately. In this embodiment, as can be seen from FIG. 2, four component boxes 30a to 30d are arranged side by side on the shelf 2, the component box 30a contains the component 20a, the component box 30b contains the component 20b, and the component box 30a contains the component 20b. The component 20c is stored in the box 30c, and the component 20d is stored in the component box 30d. In FIG. 2, the vicinity of the parts boxes 30a to 30d in the image captured by the imaging unit 13, which will be described later, is shown in an enlarged manner.

As shown in FIGS. 1 and 3, the work analysis device 10 includes a control unit 11, a storage unit 12, an imaging unit 13, a display unit 14, a light emitting unit 15, a speaker 16, an operation unit 17, a communication unit 18, and the like. there is The control unit 11 is composed mainly of a microcomputer, performs overall control of the work analysis device 10 and performs various calculations, and functions to execute, for example, work analysis processing to be described later. The storage unit 12 is configured by known storage media such as ROM, RAM, HDD, and nonvolatile memory, and stores an application program (hereinafter also referred to as a work analysis program) for executing work analysis processing, a predetermined database, and the like. are stored in advance so that they can be used by the control unit 11 .

The imaging unit 13 is configured as a camera having a light receiving sensor (eg, C-MOS area sensor, CCD area sensor, etc.). In this embodiment, the imaging unit 13 is configured separately from the apparatus main body 10a including the control unit 11, the display unit 14, etc., and in addition to the work status of the worker M, the parts boxes 30a to 30d and It is arranged on the upper part of the workbench 1 so as to capture the state of the work W as a moving image. In the present embodiment, the imaging unit 13 is configured to, for example, capture moving images (continuous still images) at 30 frames/second, and store the captured moving images in the storage unit 12 so that they can be analyzed by the control unit 11. there is

The display unit 14 is, for example, a liquid crystal display, and is configured to be controlled by the control unit 11 to display an image captured by the imaging unit 13, predetermined information, and the like. The device main body 10a is attached to the back plate of the workbench 1 or the like so that the display screen of the display unit 14 can be visually recognized by the operator M. As shown in FIG.

The light emitting unit 15 is, for example, an LED, and is configured to be controlled by the control unit 11 to control the color of emitted light and the lighting/blinking state. The speaker 16 is a known speaker or the like, and is controlled by the control unit 11 to emit various notification sounds such as preset sounds and alarm sounds.

The operation unit 17 is configured to output an operation signal corresponding to the input operation to the control unit 11, and the control unit 11 receives the operation signal and performs processing according to the input operation. there is The communication unit 18 is configured as a communication interface for performing data communication with an external device such as a host device, and is configured to perform communication processing in cooperation with the control unit 11 .

Next, a work analysis performed by the control unit 11 when the worker M performs a predetermined work of individually assembling the parts contained in the plurality of parts boxes into the work W according to a predetermined work procedure. Work analysis processing performed based on the program will be described.

In this embodiment, as the predetermined work to be analyzed, the unit work A that first assembles the part 20a of the parts box 30a, the second unit work B that assembles the part 20b of the parts box 30b, and 3 A unit work C for assembling the part 20c of the parts box 30c is performed first, and a unit work D for assembling the part 20d of the parts box 30d is performed fourth in this order.

In the work analysis process, based on a predetermined action (hereinafter also referred to as a break action) set in advance for each unit work, the work moving image captured by the imaging unit 13 is captured for each unit work at the detection timing of the break action. The determination data is generated so that delimiter information for delimiting is set. In the present embodiment, a range corresponding to the parts box 30a in the imaging range of the imaging unit 13 is set in advance as the monitoring area P1a, and as shown in FIG. is set as the delimiting motion for the unit work A. Similarly, the ranges corresponding to the component boxes 30b to 30d in the imaging range of the imaging unit 13 are set in advance as monitoring areas P1b to P1d, respectively. Then, as shown in FIG. 4(B), the movement of the worker M's hand entering the monitoring area P1b is set as the dividing movement for the unit work B. As shown in FIG. Further, as shown in FIG. 5(A), the action of the worker M's hand entering the monitoring area P1c is set as the dividing action for the unit work C. As shown in FIG. Further, as shown in FIG. 5(B), the movement of the worker M's hand entering the monitoring area P1d is set as the dividing movement for the unit work D. As shown in FIG. In FIGS. 4 and 5, the range corresponding to each of the parts boxes 30a to 30d out of the imaging range of the imaging unit 13 is shown enlarged.

Note that each of the monitoring areas P1a to P1d may be set as a specified range by, for example, arranging each of the component boxes 30a to 30d at a predetermined position, or by swinging each of the component boxes 30a to 30d individually. It may be set based on an image difference that is generated by continuously capturing images of the state in which the image is drawn.

The work analysis process performed by the control unit 11 will be specifically described below with reference to the flowchart of FIG.
When the work analysis process is started by the control unit 11 by performing a predetermined start operation on the operation unit 17, the imaging process shown in step S101 in FIG. 13 to be imaged. If any of the delimiting operations set as described above is detected during the shooting of the work moving image, the determination processing in step S103 is YES. Subsequently, in the delimiter information setting process of step S105, delimiter information for delimiting the work moving image at the detection timing is set. The break information can include the name of the unit work identified from the break motion, information about the detection time, and the like. Then, if the predetermined end operation or the like has not been performed (No in S107), the processing from step S103 is repeated again. Note that the control unit 11 that performs the delimiter information setting process can correspond to an example of a "setting unit".

By repeating the process from step S103, the division information is set for each unit work, and the work division detection result as shown in FIG. 7 can be obtained. For example, in the k-th cycle in FIG. 7, the operator M's hand entering the monitoring area P1a is detected at time t1, and this time t1 is set as the start timing of the unit work A. At time t2, the movement of the worker M's hand entering the monitoring area P1b is detected, and this time t2 is set as the start timing of the unit work B and the end timing of the unit work A. FIG. Similarly, when the operator M's hand is detected to enter the monitoring area P1c at time t3, this time t3 is set as the start timing of the unit work C and the end timing of the unit work B. . Further, when the movement of the operator M's hand entering the monitoring area P1d is detected at time t4, this time t4 is set as the start timing of the unit work D and the end timing of the unit work C. FIG. At time t5, the movement of the operator M's hand entering the monitoring area P1a is detected, and this time t5 is the start timing of the unit work A in the k+1 cycle and the start of the unit work D in the kth cycle. Set to end timing.

In this way, when the required work moving image is obtained with the delimiter information set and an end operation or the like is performed (Yes in S107), abnormal work exclusion processing shown in step S109 is performed. In this process, based on the delimiter information set as described above, a process for excluding unit work presumed to be abnormal work from the determination data is performed.

Specifically, for example, for each unit work, based on the average work time calculated based on the set delimiter information, a normal work time range that is regarded as normal work is calculated, and the work time is calculated as normal work time. Automatically exclude out-of-range unit operations. In the example of FIG. 7, the working time of the unit work B of the n1th cycle is out of the normal work time range, so the unit work B of the n1th cycle is excluded from the determination data.

Also, for example, based on the set delimiter information, the unit work immediately preceding the unit work performed in an order different from the predetermined order is automatically excluded. In the example of FIG. 7, the unit work C of the n2th cycle is performed after the unit work A and is in an order different from the predetermined order. Let A be excluded from the determination data. In this case, for some reason, the dividing motion of unit work B, which was actually performed after unit work A, cannot be detected. Therefore, unit work A immediately preceding unit work C, which was performed in an order different from the predetermined order, is excluded from the determination data.

After the unit work that is presumed to be abnormal work is excluded as described above, determination data generation processing is performed in step S111 to include the moving images of the remaining unit work that are considered to be normal work and the corresponding delimiter information. , the determination data (annotation data) is generated. The determination data generated in this manner is stored in the storage unit 12, and is transmitted to a host device or the like via the communication unit 18 as necessary. It should be noted that the data related to the unit work that is presumed to be an abnormal work may be stored separately in the storage unit 12 as abnormal data in order to use it as data for learning about actions in an abnormal situation. Also, the control unit 11 that performs the abnormal work exclusion process and the determination data generation process can correspond to an example of a "generation unit."

As described above, in the work analysis apparatus 10 according to the present embodiment, the dividing motion is detected from the work video imaged by the imaging unit 13 based on the dividing motion (predetermined motion) preset for each unit work. Delimitation information for delimiting each unit work at a timing is set, and determination data is generated so as to include the work moving image captured by the imaging unit 13 and the set delimitation information.

As a result, it is possible to automatically segment the work video for each unit work only by imaging the segmenting operation performed by the worker M for each unit work. Therefore, the determination data for determining whether or not the correct work is being performed can be generated in real time based on the work video imaged of the predetermined work that is repeatedly performed.

In particular, in this embodiment, the unit work is the work of assembling the parts 20 taken out from the parts box 30 associated with the unit work into the workpiece (to-be-assembled member) W. 20 is taken out. In this way, the work animation can be segmented at the detection timing of the work movement essential for the unit work, and the movement unrelated to the original unit work is not forced. Work load can be reduced.

In the abnormal work exclusion process and determination data generation process, a normal work time range that is regarded as normal work is calculated for each unit work based on the set delimiter information. A unit work is generated as determination data. As a result, it is possible to automatically use a moving image of a unit work that is considered to be normal work in consideration of the work time as determination data, thereby improving the reliability of the determination data. On the other hand, in the abnormal work exclusion process and determination data generation process, the determination data is generated so as to exclude the unit work whose work time is out of the normal work time range. As a result, it is possible to automatically exclude moving images of unit work that are not regarded as normal work from the determination data, and improve the reliability of the determination data.

Furthermore, in the abnormal work exclusion process and determination data generation process, based on the set delimiter information, it is determined that the unit work immediately preceding the unit work performed in an order different from the predetermined order is excluded. data is generated. Even in this way, videos of unit work that are not regarded as normal work are automatically excluded from the judgment data, so that the reliability of the judgment data can be improved.

[Second embodiment]
Next, a work analysis device and work analysis program according to the second embodiment will be described with reference to the drawings.
The second embodiment mainly differs from the first embodiment in that an operation of moving the component to the planned assembly position of the member to be assembled is adopted as the separating operation. Therefore, the same reference numerals are assigned to substantially the same components as in the first embodiment, and the description thereof will be omitted.

In this embodiment, as the predetermined work to be analyzed, as in the first embodiment, the unit work A for assembling the parts 20a in the parts box 30a is first, and the work for the parts box 30b is second. Unit work B for assembling part 20b, third unit work C for assembling part 20c of parts box 30c, and fourth unit work D for assembling part 20d of parts box 30d are employed in this order.

On the other hand, unlike the first embodiment, as shown in FIG. 8, a monitoring area P2a is a range corresponding to the planned assembly position where the part 20a is to be assembled with respect to the work W in the imaging range of the imaging unit 13. A range corresponding to the planned assembly position for assembling the part 20b is set as a monitoring area P2b, a range corresponding to the planned assembly position for assembling the part 20c is set as a monitoring area P2c, and a planned assembly position for assembling the part 20d is set. A range corresponding to the position is set as a monitoring area P2d.

Then, as shown in FIG. 9A, an action of moving the part 20a to the monitoring area P2a is set as the dividing action for the unit work A. As shown in FIG. Further, as shown in FIG. 9B, an action of moving the part 20b to the monitoring area P2b is set as the dividing action for the unit work B. As shown in FIG. Further, as shown in FIG. 10(A), an action of moving the part 20c to the monitoring area P2c is set as the dividing action for the unit work C. As shown in FIG. Further, as shown in FIG. 10(B), an action of moving the part 20d to the monitoring area P2d is set as the dividing action for the unit work D. As shown in FIG. In FIGS. 8 to 10, the range corresponding to the workpiece W in the imaging range of the imaging unit 13 is enlarged and illustrated, and FIGS. are omitted.

In the work analysis process performed by the control unit 11 in the present embodiment, when any of the delimiting actions set as described above is detected during shooting of the work moving image (Yes in S103), this detection Delimitation information for delimiting the work moving image at timing is set (S105), and the processing from step S103 is repeated until an end operation or the like is performed. If an end operation or the like is performed during such repeated processing (Yes in S107), determination data is generated so as to exclude unit work that is presumed to be abnormal work (S109, S111).

As described above, in the work analysis device 10 according to the present embodiment, the unit work is the work of assembling the part 20 associated with the unit work to the work (to-be-assembled member) W. operation) is an operation of moving the part 20 to the position where the workpiece W is to be assembled. Even in this way, the work animation can be segmented at the detection timing of the work movement essential for the unit work, and the worker M is not forced to perform a movement unrelated to the original unit work. etc. can be reduced.

[Third Embodiment]
Next, a work analysis device and work analysis program according to the third embodiment will be described with reference to the drawings.
The third embodiment is mainly different from the first embodiment in the process for detecting the break motion. Therefore, the same reference numerals are assigned to substantially the same components as in the first embodiment, and the description thereof will be omitted.

The work analysis device 10 according to the present embodiment includes a monitoring device 40 for detecting the movement of taking out the parts 20 from the parts box 30 as the dividing movement. The monitoring device 40 is a device for detecting the breaking operation by monitoring changes in capacitance, and as shown in FIG. It is configured to include six strip-shaped conductors 42y1 to 42y6 and a workbench 43. As shown in FIG. In addition, in FIG. 11 and FIG. 12 which will be described later, the workbench 43 is illustrated by a dashed line for convenience.

The sensor circuit 41 is a circuit for monitoring changes in capacitance (unit: F) of each of the conductors 42x1 to 42x6 and each of the conductors 42y1 to 42y6, and is controlled by the control unit 11 to display the monitoring results. It is configured to output to the control unit 11 .

As shown in FIG. 11, the conductors 42x1 to 42x6 and the conductors 42y1 to 42y6 are arranged in a grid pattern. 42y3 changes, and this change is detected by the sensor circuit 41. FIG. That is, the conductors 42x1 to 42x6 and the conductors 42y1 to 42y6 constitute 36 areas where changes in capacitance can be detected (hereinafter also referred to as work areas), and each work area arranged in a matrix. By monitoring changes in capacitance, it is possible to detect which work area a hand is approaching. In addition, each conductor is subjected to an insulation treatment or the like so as to reduce the influence of changes in capacitance of other overlapping conductors.

Therefore, in the present embodiment, when each component box 30 is placed on a workbench 43 provided to cover each work area, the sensor circuit 41 detects a change in capacitance exceeding a predetermined threshold. Based on the determined work area, it is possible to detect the operation of taking out the parts 20 from the parts box 30 (partitioning operation) and the position of the parts box 30 . In other words, it is possible to detect a breaking motion or the like by simply performing a normal work motion without performing a special motion or the like. In addition, the number of parts boxes 30 used for the work can also be detected according to the order of change of the work area where the capacitance changes.

In particular, by associating each work area with the type of the parts box 30 to be arranged, it is possible not only to detect the partitioning operation, but also to specify the extracted parts. For example, as shown in FIG. 12, in a state in which each of the component boxes 30a to 30d is arranged on the workbench 43, conductors 42x3, 42x4, 42y2, and 42y3 have a larger electrostatic charge than other conductors. When the change in capacitance is detected by the sensor circuit 41, it is possible not only to detect the partitioning operation, but also to detect removal of the component 20b from the component box 30b.

As described above, in this embodiment, by adopting a characteristic configuration for monitoring changes in the capacitance of each of the conductors 42x1 to 42x6 and each of the conductors 42y1 to 42y6, the division operation and the type of the extracted component 20 can be determined. can be detected, and this characteristic configuration can also be applied to other embodiments and the like. The work areas are not limited to being composed of the conductors 42x1 to 42x6 and the conductors 42y1 to 42y6, and may be composed of other members capable of monitoring changes in capacitance. For example, a configuration may be adopted in which one conductor capable of monitoring a change in capacitance is arranged for each work area. Also, the number of work areas is not limited to being set to 36 (6×6), and may be set to a different number depending on the arrangement of the component boxes 30 or the like. In addition, the configuration for detecting the above-described delimiting operation or the like by monitoring the change in the capacitance of each conductor is not limited to being applied to the detection of the delimiting operation for taking out the component 20 from the component box 30 as described above. For example, it may be applied to the detection of a delimiting operation for moving the component 20 to the planned assembly position of the member to be assembled.

[Fourth Embodiment]
Next, a work analysis device and work analysis program according to the fourth embodiment will be described with reference to the drawings.
The fourth embodiment is mainly different from the first embodiment in the process for setting the monitoring area. Therefore, the same reference numerals are assigned to substantially the same components as in the first embodiment, and the description thereof will be omitted.

The work analysis device 10 according to this embodiment includes a monitoring device 40a for detecting the monitoring area, that is, the location where the parts box 30 is arranged. As shown in FIG. 13(A), this monitoring device 40a has a plurality of piezoelectric switches 44 arranged in a row at equal intervals with almost no gaps on the surface of the shelf 2 on which the parts box 30 is to be placed. configured to provide. Each piezoelectric switch 44 is configured to output a signal corresponding to the pressure to the control unit 11, and the control unit 11 can detect which piezoelectric switch 44 is in the pressed state.

That is, as shown in FIG. 13B, when the parts box 30 is arranged in a part of the monitoring area formed by the pressing surface side of each piezoelectric switch 44, the piezoelectric switch 44 (see FIG. 13(B), reference numeral 44a). Therefore, by monitoring the pressing state of each piezoelectric switch 44 by the control unit 11, it is possible to detect the place (monitoring area) where the parts box 30 is arranged in the monitoring area. In addition, in FIG.13(B), the parts box 30 is shown in figure by the broken line for convenience.

In place of the piezoelectric switch 44, a physical switch such as a contact switch capable of detecting that a part of the parts box is in contact with the detection surface can be used to detect where the parts box is placed in the monitoring area. (monitoring area) may be detected.

In addition, as long as it is not a non-use environment but a frequently used environment, instead of the above-described monitoring device 40a, a monitoring device 40b shown in FIG. . In this modification, each component box 30 is configured to have conductivity at least on the back side, and the monitoring device 40b detects a change in the conductive state within the monitoring area, thereby determining the arrangement of the component box 30. It is configured to detect a location (surveillance area). For this reason, the monitoring device 40b is provided with a plurality of first conductors 45 and the same number of second conductors 46 arranged parallel to each other on the plane on which each component box 30 is to be arranged. ), the range occupied by the detected conductors 45 and 46 (see symbols 45a and 46a in FIG. 14(B)) is detected by detecting the first conductor 45 and the second conductor 46 that are in a conducting state. can be detected as the place where the parts box 30 is arranged. In addition, in FIG.14(B), the parts box 30 is shown in figure by the broken line for convenience.

In particular, by changing the resistance value of the conductor provided on the back side of the component box 30 for each type of the component box 30, based on the resistance value detected during conduction through the first conductor 45 and the second conductor 46, The type of the parts box 30 to be arranged can be discriminated.

A characteristic configuration of this embodiment that detects each monitoring area using the piezoelectric switch 44 or the like described above, or a modification of this embodiment that detects each monitoring area using the above-described first conductor 45 and second conductor 46 or the like. The characteristic configuration of can also be applied to other embodiments.

[Fifth embodiment]
Next, a work analysis device and work analysis program according to the fifth embodiment will be described with reference to the drawings.
The fifth embodiment is different from the first embodiment mainly in the setting of the monitoring region and the detection of the break motion in consideration of the height of the hand. Therefore, the same reference numerals are assigned to substantially the same components as in the first embodiment, and the description thereof will be omitted.

In this embodiment, the control unit 11 performs a monitoring area setting process to set each monitoring area before the work analysis process is started. In this monitoring area setting process, the locus of a finger tracing the upper edge 31 of the peripheral wall of the parts box 30 is imaged by the imaging unit 13, thereby setting a monitoring area corresponding to the parts box. For example, as illustrated in FIG. 15, the monitoring area P1c corresponding to the parts box 30c is set by imaging the trajectory of a finger tracing the upper end 31 of the peripheral wall of the parts box 30c with the imaging unit 13.

In the above work analysis process, the height of the hand of the worker M is taken into account to detect a break motion in which the hand of the worker M enters the monitoring area. For example, when a hand trying to pick up a part stored in the parts box 30b passes over the adjacent parts box 30a, it is misidentified that the passing hand enters the monitoring area corresponding to the parts box 30a. This is because the break operation will be erroneously detected.

For this reason, in the present embodiment, a TOF (Time of Flight) camera capable of measuring the distance to the object to be imaged is employed as the imaging unit 13, and as shown in FIG. The height from the placement surface 2a of the hand entering the monitoring area is measured with reference to the placement surface 2a. When the height of the hand entering the monitoring area from the placement surface 2a exceeds a predetermined threshold value h1, the detection is invalidated and the division operation is not determined, and the height of the hand entering the monitoring area from the placement surface 2a is not determined. is less than or equal to a predetermined threshold value h1, it is determined that detection is valid, and the break motion is to be detected. It should be noted that a TOF camera may be prepared separately from the imaging unit 13 and used to measure the height from the placement surface 2a of the hand entering the monitoring area.

As a result, for example, even if a hand trying to pick up a component stored in the component box 30b enters the monitoring area corresponding to the component box 30a, the height of the hand from the mounting surface 2a is the predetermined threshold value h1. , the detection is invalidated, so erroneous detection of the break motion can be suppressed.

As described above, it is not limited to determining whether or not the detection is invalid based on the height of the hand from the placement surface 2a. It may be determined whether or not the detection is invalid based on the reference (see threshold value h2 in FIG. 16). In addition, the characteristic configuration of this embodiment, which determines whether or not detection is invalid based on the setting of the monitoring area using the trajectory of the traced finger and the height of the hand, can be applied to other embodiments. .

[Sixth Embodiment]
Next, a work analysis device and work analysis program according to the sixth embodiment will be described with reference to the drawings.
The sixth embodiment is mainly different from the first embodiment in that the break motion is detected using a change in weight. Therefore, the same reference numerals are assigned to substantially the same components as in the first embodiment, and the description thereof will be omitted.

The work analysis device 10 according to the present embodiment includes a monitoring device 40c for detecting the operation of taking out the part 20 from the parts box 30 and the operation of assembling the part 20 to the member to be assembled as the dividing operation. This monitoring device 40c is a device for detecting the above-described partitioning operation by monitoring changes in the weight of each component box 30 and the member to be assembled, and measures the weight of each component box 30 and the member to be assembled. It is configured with a possible weight sensor 47 . The weight sensor 47 is assembled to the shelf 2 with its weight measuring surface formed in a flat shape so that each component box 30 and the member to be assembled can be placed at the same time.

The work analysis process performed in this embodiment will be described below with reference to the drawings. In the following description, as shown in FIGS. 17A and 17B, four parts boxes 30a to 30d and a work W to which parts 20a to 20d are assembled are placed on the weight measuring surface of the weight sensor 47. A detailed description will be given of the case in which the In this embodiment, as the predetermined work to be analyzed, the unit work A to assemble the part 20a of the parts box 30a first and the unit work B to assemble the part 20b of the parts box 30b second to the work W are performed. , unit work C to assemble the part 20c of the parts box 30c third, and unit work D to assemble the part 20d of the parts box 30d fourth.

When the work W to which the parts 20a to 20d are not assembled is placed on the weight measurement surface, immediately after the work W is started to be assembled, the measurement value F measured by the weight sensor 47 is Fo. , when the part 20a is taken out from the parts box 30a to start the unit work A, the measured value of the weight sensor 47 decreases from Fo to Fa. The measured value Fa is obtained by subtracting the weight of the component 20a from the measured value Fo. Therefore, when the measured value measured by the weight sensor 47 decreases from Fo to Fa (see time t1 in FIG. 18), it is possible to detect the separation operation of taking out the component 20a from the component box 30a. After that, as shown in FIG. 17(B), by assembling the part 20a to the work W, the measured value of the weight sensor 47 increases from Fa to Fo. Therefore, when the measured value measured by the weight sensor 47 returns (increases) from Fa to Fo (see time t2 in FIG. 18), the division operation of assembling the part 20a to the workpiece W can be detected. After that, when the measured value of the weight sensor 47 decreases from Fo to Fb (the value obtained by subtracting the weight of the component 20b from the measured value Fo) (see time t3 in FIG. 18), the delimiting operation of taking out the component 20b from the component box 30b. is detected, and furthermore, the measurement value of the weight sensor 47 returns from Fb to Fo (see time t4 in FIG. 18), and the break operation of assembling the part 20b to the workpiece W is detected. After that, when the measured value of the weight sensor 47 decreases from Fo to Fc (the value obtained by subtracting the weight of the component 20c from the measured value Fo) (see time t5 in FIG. 18), the delimiting operation of taking out the component 20c from the component box 30c. is detected, and furthermore, the measurement value of the weight sensor 47 returns from Fc to Fo (see time t6 in FIG. 18), and the break operation of assembling the part 20c to the workpiece W is detected. After that, when the measured value of the weight sensor 47 decreases from Fo to Fd (the value obtained by subtracting the weight of the component 20d from the measured value Fo) (see time t7 in FIG. 18), the delimiting operation of taking out the component 20d from the component box 30d. is detected, and furthermore, the measurement value of the weight sensor 47 returns from Fd to Fo (see time t8 in FIG. 18), and the break operation of assembling the part 20d to the work W is detected.

As described above, in this embodiment, the change in weight measured by the weight sensor 47 can be used to accurately detect the dividing motion. Therefore, for example, even if an unintended part is taken from a different parts box by mistake, by returning the part to the parts box, a large weight change such as during assembly is not detected. It is possible to suppress the erroneous detection of the delimiting operation caused by this. Furthermore, even if a part drops onto the member to be assembled during assembly, the change in weight is different from that during assembly. can be distinguished.

As the weight sensor 47, a non-contact capacitance sensor, a capacitance weight sensor, a thin-film pressure sensor, or the like can be used. In addition, the monitoring device 40c is not limited to measuring the weight of each parts box 30 and the member to be assembled with one weight sensor 47, but also measures the weight of each parts box 30 and the parts to be assembled using two or more weight sensors or the like. The weight of the attached member may be measured. Further, the characteristic configuration of the present embodiment, in which the above-described break operation is detected using changes in weight measured by a weight sensor, can also be applied to other embodiments.

[Seventh embodiment]
Next, a work analysis device and work analysis program according to a seventh embodiment will be described with reference to the drawings.
The seventh embodiment is mainly different from the first embodiment in the process for setting the monitoring area. Therefore, the same reference numerals are assigned to substantially the same components as in the first embodiment, and descriptions thereof are omitted.

The work analysis device 10 according to the present embodiment monitors the trajectory of the hand of the worker M when taking out the part 20 from the parts box 30 and the trajectory of the hand of the worker M when assembling the part 20 to the member to be assembled. , based on the monitoring result, sets the monitoring area.

Specifically, the hand of the worker M is recognized from the moving image captured by the imaging unit 13, and the direction and amount of movement of the captured hand are detected at predetermined time intervals (for example, frame intervals). . Then, when the state in which the amount of movement is equal to or less than a predetermined value continues for a predetermined period of time or longer, it is assumed that the hand is in a staying state (hereinafter also referred to as a staying state), and the hand captured in this staying state is provisionally taken as a reference. A monitoring area is set. This is because the movement of the hand when taking out the part 20 from the parts box 30 and the movement of the hand when assembling the part 20 to the member to be assembled are likely to cause the above-described retention state.

For example, as illustrated in FIG. 19, when the hand that has finished assembling the part 20a to the workpiece W goes to pick up the part 20b from the parts box 30b, the hand is in the above-described staying state when taking out the part 20b from the parts box 30b. Therefore, a temporary monitoring area (refer to symbol Po1b in FIG. 19) for the parts box 30b is set based on the hand in this staying state. After that, as shown in FIG. 20, when the hand that has taken out the part 20b moves toward the planned assembly position of the work W, the hand stays in the above-described staying state when the part 20b is assembled to the planned assembly position of the work W. , a provisional monitoring area (refer to symbol Po2b in FIG. 20) for the assembly planned position of the part 20b is set on the basis of this retained hand.

Note that in the present embodiment, the temporary monitoring area is set according to a rectangular area inside the imaging range occupied by the hand in the staying state, such as the temporary monitoring area Po1b in FIG. 19 and the temporary monitoring area Po2b in FIG. However, it is not limited to this. good too.

Then, by repeating each unit work, the temporary monitoring area for each parts box 30 and the temporary monitoring area for each planned assembly position are sequentially accumulated and stored in the storage unit 12 . After that, in order to improve the estimation accuracy of the monitoring area and optimize the monitoring area, the overlapped range for each temporary monitoring area is obtained and weighted, and the monitoring area can be set according to the weighting.

For example, if the temporary monitoring area is set 100 times for one monitoring area, the weight of the area that overlaps 50 times or more is "3", the weight of the area that overlaps 20 times or more is "2", and the weight of the area that overlaps 20 times or more is "2". Set the weight of the overlapped region to '1'. When the monitor area is set so as to include all temporary monitor areas with a weight of "3", the monitor area (see hatched area) can be set as shown in FIG. 21(A). Also, when setting the monitoring area so as to include all the temporary monitoring areas whose weight is "2" or more, the monitoring area (see the hatched area) can be set as shown in FIG. 21(B).

Note that the temporary monitoring area has a predetermined shape, such as a rectangular shape, centered on an intermediate position between the center position of the hand in the previous retained state and the center position of the hand in the current retained state for one monitoring region. It may be set based on the area. Further, the characteristic configuration of this embodiment in which one monitoring area is set using a plurality of temporary monitoring areas described above can also be applied to other embodiments.

[Eighth Embodiment]
Next, a work analysis device and work analysis program according to an eighth embodiment will be described with reference to the drawings.
In the eighth embodiment, the information code attached to each parts box is used to set the monitoring area corresponding to each parts box, but this is mainly different from the first embodiment. Therefore, the same reference numerals are assigned to substantially the same components as in the first embodiment, and the description thereof will be omitted.

In this embodiment, as shown in FIG. 22, each parts box 30 is provided with an information code for position detection (hereinafter also referred to as parts box code Ca). A second imaging unit 13a for imaging Ca is newly provided. The second imaging unit 13a functions as a camera for setting a monitoring area, and has the same function as the imaging unit 13. The captured image is stored in the storage unit 12 so that it can be analyzed by the control unit 11. It is configured. The second image capturing unit 13a is positioned within the image capturing range of the image capturing unit 13 so that the component box code Ca of each component box 30 arranged on the shelf 2 can be imaged from the front side when viewed from the worker M. are placed. An information code (hereinafter also referred to as a camera code Cb) for calculating the relative positional relationship between the second imaging unit 13a and the imaging unit 13 is provided on the outer surface (upper surface) of the second imaging unit 13a on the imaging unit 13 side. attached. In this embodiment, the parts box code Ca and the camera code Cb are configured as QR codes (registered trademark), but are not limited to this. It may be configured as a dimension code.

In this embodiment, before the work analysis process is started, a monitoring area setting process is performed by the control unit 11 in order to set each monitoring area. In this monitoring area setting process, the relative coordinates of the parts box 30 with respect to the second imaging section 13a are calculated from the captured image of the parts box code Ca captured by the second imaging section 13a. Then, by calculating the relative coordinates of the second imaging unit 13a with the imaging unit 13 as the reference from the imaged image of the camera code Cb with the imaging unit 13, the relative coordinates of the parts box 30 with the imaging unit 13 as the reference are calculated. Coordinates are estimated, and a monitoring area for each parts box 30 is set based on the estimation result.

For this reason, in addition to the information of the parts 20 housed in the attached parts box 30, the parts box code Ca has a size indicating the height, width, depth, etc. of the parts box 30 (hereinafter also referred to as box size). and the size and shape of the component box code Ca, the size indicating the number of cells (hereinafter also referred to as code size), the pasting position of the component box code Ca to the component box 30 (hereinafter also referred to as code position), etc. Recorded.

In addition, the camera code Cb includes information such as the pasting position of the camera code Cb with respect to the second imaging unit 13a, the code size, etc., and the relative positional relationship between the imaging unit 13 and the second imaging unit 13a based on the captured image of the camera code Cb. Information for calculating is recorded.

The monitor area setting process in this embodiment will be specifically described below with reference to the drawings. In the following description, the case where one parts box 30 with the parts box code Ca is arranged on the shelf 2 will be described in detail.

Before starting the work analysis process, when the monitoring area setting process is started by the control unit 11 in response to a predetermined operation, the second imaging unit 13a A process for estimating the relative coordinates of the parts box 30 with reference to is performed. In the subroutine of this process, first, the second imaging unit 13a becomes ready to take an image of the parts box code Ca (S211 in FIG. 24), and decode processing for reading the imaged parts box code Ca is performed (S213). .

Since the component boxes 30 are arranged on the shelf 2, the component box code Ca is successfully read (Yes in S215), and the box size, code size, code position, etc. are acquired. A reading angle calculation process shown in S217 is performed. In this process, the angle of the parts box code Ca with respect to the second imaging unit 13a is calculated as the reading angle α based on the range of the parts box code Ca occupied in the captured image of the second imaging unit 13a.

For example, as shown in FIG. 26(A), since the parts box 30 is tilted with respect to the second imaging section 13a, the parts box code Ca is picked up as shown in the image shown in FIG. 26(B). If so, the reading angle α (see FIG. 25A) of the parts box code Ca with respect to the second imaging unit 13a is determined based on the length ratio of the four sides obtained from the positions of the four corners of the parts box code Ca. Calculated.

Subsequently, reading distance calculation processing shown in step S219 is performed. In this process, the distance from the second imaging unit 13a to the parts box code Ca is calculated as the reading distance y based on the number of pixels of the parts box code Ca in the image captured by the second imaging unit 13a. The reading distance y can be calculated based on the image corrected so that the angles of the four corners of the parts box code Ca are 90° using the reading angle α calculated as described above.

For example, for the parts box code Ca imaged as shown in FIG. is x2, the actual size in the x direction corresponding to the entire captured image at the position of the parts box code Ca is x3, and the actual size in the x direction of the actual parts box code Ca is x4, the relationship of formula (1) holds. Also, with respect to the reading distance y, the formula (2) is obtained from the x-direction size x3 corresponding to the entire captured image at the position of the parts box code Ca and the angle θ obtained from the angle of view and resolution of the second imaging unit 13a. relationship is established.
x1:x2=x3:x4 (1)
y=x3/2×tan θ (2)

Since x1, x4, and θ are known, the reading distance y is calculated based on the number of pixels x2 in the x direction of the parts box code Ca by the following equation (3) obtained from equations (1) and (2). be able to.
y=(x1×x4/x2)/2×tan θ (3)

After the reading angle α and the reading distance y are calculated as described above, relative coordinate estimation processing shown in step S221 is performed. In this process, first, based on the reading angle α and the reading distance y calculated as described above, the relative coordinates of the parts box code Ca with respect to the second imaging unit 13a are calculated. Based on the relative coordinates of the parts box code Ca and the code position, code size, box size, etc. read from the parts box code Ca, the relative coordinates of the parts box 30 with respect to the second imaging unit 13a are estimated. This makes it possible to estimate how the parts box 30 is arranged with respect to the second imaging section 13a.

By estimating the relative coordinates of the parts box 30 with reference to the second imaging unit 13a as described above, when the parts box relative coordinate estimation process in step S201 ends, camera relative coordinate estimation process shown in step S203 , a process for estimating the relative coordinates of the second imaging section 13a with the imaging section 13 as a reference. In the subroutine of this process, first, the imaging unit 13 becomes capable of imaging the camera code Cb (S231 in FIG. 25), and decode processing for reading the imaged camera code Cb is performed (S233).

When the camera code Cb is successfully read (Yes in S235), the reading angle calculation process shown in step S237 is performed, and the camera code Cb for the imaging unit 13 is read by the same calculation method as the reading angle calculation process in step S217. The angle is calculated as the reading angle. Subsequently, reading distance calculation processing shown in step S239 is performed, and the imaging unit 13 calculates the number of pixels of the camera code Cb in the image captured by the imaging unit 13 by the same calculation method as the reading distance calculation processing in step S219. to the camera code Cb is calculated as the reading distance.

When the reading angle and the reading distance are calculated as described above, the relative coordinate estimation process shown in step S241 is performed, and the camera code based on the imaging unit 13 is calculated by the same calculation method as the relative coordinate estimation process in step S221. When the relative coordinates of Cb are calculated, the relative coordinates of the second imaging section 13a with the imaging section 13 as a reference are calculated based on the calculated relative coordinates of the camera code Cb and the reading result read from the camera code Cb. Presumed. This makes it possible to estimate in what state the second imaging unit 13 a is arranged with respect to the imaging unit 13 . Note that when the second imaging unit 13a is arranged at a predetermined position with respect to the imaging unit 13, the relative coordinates of the second imaging unit 13a with respect to the imaging unit 13 are identified. The estimation process may be eliminated.

By estimating the relative coordinates of the second imaging unit 13a based on the imaging unit 13 as described above, when the camera relative coordinate estimation processing in step S203 ends, the parts box position calculation processing shown in step S205 is performed. . In this process, the imaging unit 13 , the position (relative coordinates) of the parts box 30 is calculated.

As a result, the area occupied by the parts box 30 in the image captured by the imaging unit 13 can be estimated. Therefore, in the setting process shown in step S207, the area of the captured image estimated as the parts box 30 as described above is set as the monitoring area. Then, the monitoring area setting process ends. When a plurality of component box codes Ca are captured by the second imaging unit 13a in a decodable manner, the monitoring area can be set for each component box code Ca according to the flow described above. In particular, since the information of the parts 20 is also recorded in the parts box code Ca, it is possible to specify the type of the parts 20 corresponding to the monitoring area.

In this embodiment, the parts box code Ca has a size as large as possible near one edge of the side surface of the parts box 30 on the side of the second imaging unit 13a, as shown in FIG. 28(A). However, it is not limited to this, and may be attached to other parts as long as the positions match the recorded code positions. For example, the parts box code Ca may be attached to the center of the side surface of the parts box 30 facing the second imaging unit 13a as shown in FIG. , may be applied in a relatively small size near one edge.

In addition, assuming that it is not possible to specify the position of the parts box 30 where the parts box code Ca is attached, the parts box code Ca and the parts to which this parts box code Ca is attached are obtained from the captured image of the second imaging unit 13a. The coordinates relative to the surface of the box 30 may be calculated, and the calculation results, the box size, and the code size may be used to estimate the relative coordinates of the parts box 30 with respect to the second imaging section 13a. In this case, the code position is not recorded in the parts box code Ca.

For example, since the parts box code Ca is attached to the parts box 30 as shown in FIG. 29A, the parts box code Ca and the parts box 30 are imaged as shown in FIG. , image processing such as edge search is used to detect at what position on the surface of the parts box 30 and in what kind of inclination the parts box code Ca is attached, and the relative coordinates can be calculated. For example, the length (known) and the angle of the upper edge of the parts box 30 and the length (known) of one side of the parts box code Ca and the angle of the one side are shown using the thick line part in FIG. 29(B). By comparing with , it is possible to detect at what position on the surface of the parts box 30 and in what kind of inclination the parts box code Ca is attached.

Further, the second imaging unit 13a is not limited to being arranged at a position where the component box code Ca of each component box 30 arranged on the shelf 2 can be captured from the front side when viewed from the worker M. For example, , may be arranged at a position where an image can be captured from the rear side as seen from the worker M.

Further, for example, as a first modified example of the present embodiment, the second imaging unit 13a is arranged such that each component box 30 having a component box code Ca attached to each bottom surface is placed on a transparent shelf 2, as shown in FIG. On the premise that it is placed, it may be arranged at a position where the component box code Ca can be imaged from below through the transparent portion of the shelf 2 . In this case, for example, an information code Cc is attached to a predetermined position surrounding the transparent portion of the shelf 2 within the imaging range of the second imaging unit 13a, and information about the position of the shelf 2 to which the information code Cc is attached is displayed. By recording such as in the information code Cc, the relative coordinates of the shelf 2 with the second imaging unit 13a as a reference can be estimated from the captured image of the second imaging unit 13a. Therefore, by estimating the relative coordinates of the shelf 2 with the imaging unit 13 as a reference using another information code or the like, it is possible to estimate the relative coordinates of the second imaging unit 13a with the imaging unit 13 as a reference. can. As a result, based on the relative coordinates of the parts box 30 with the second imaging unit 13a as a reference and the relative coordinates of the second imaging unit 13a with the imaging unit 13 as a reference, the parts box 30 with the imaging unit 13 as a reference By calculating the position, the area occupied by the parts box 30 in the image captured by the imaging unit 13 can be set as the monitoring area.

In particular, since the parts box code Ca is attached to the bottom surface of the parts box 30, the parts box code Ca can be made larger than when the parts box code Ca is attached to the side surface of the parts box 30. Therefore, the parts box code Ca can be read. It is possible to improve the accuracy of coordinate estimation by In addition, since the parts box code Ca and the information code Cc are simultaneously imaged by the second imaging unit 13a, the positional relationship between the parts box code Ca and the information code Cc can also be accurately calculated. In addition, since the second imaging unit 13a can be arranged on the lower side of the shelf 2, even when the second imaging unit 13a is provided, the space saving of the work analysis device 10 can be realized. Also, a parts box code Ca can be attached to a parts box such as a pallet that has no space for attaching an information code to its side or top surface. In addition, in the configuration in which the second imaging unit 13a captures images from the front side and the rear side of the worker M, when the component boxes 30 are arranged in a line, each component box code Ca can be captured, but the second imaging unit 13a By capturing an image from the lower side at 13a, each component box code Ca can be captured even when the component boxes 30 are arranged in two or more rows, and convenience can be improved. Moreover, the transparent portion of the shelf 2 is not limited to being formed in a rectangular shape, and may be formed in a circular shape, for example, as in the second modification shown in FIG. 31 . Also, as shown in FIG. 31, a marker Cm attached to a specific position may be employed instead of the information code Cc. Note that when the second imaging unit 13a is arranged at a predetermined position with respect to the shelf 2, since the relative coordinates of the shelf 2 are specified with respect to the second imaging unit 13a, the information code Cc is omitted. good too.

In addition, the parts box code Ca is not limited to being attached to the side or bottom surface of the parts box 30. For example, as shown in FIG. It may be attached to the four corners or the like. Also, the parts box code Ca attached to the upper end of the peripheral wall may be configured as a one-dimensional code in consideration of readability. Further, for example, the parts box code Ca may be attached to the upper lid portion 32 of the parts box 30 having the upper lid portion 32 as shown in FIG. 32(B).

Note that the characteristic configuration of this embodiment, in which the monitoring areas corresponding to the component boxes 30 are respectively set using the component box code Ca attached to each component box 30, is also applicable to other embodiments. can do.

[Ninth Embodiment]
Next, a work analysis device and work analysis program according to a ninth embodiment will be described with reference to the drawings.
The ninth embodiment mainly differs from the first embodiment in the process for setting the monitoring area. Therefore, the same reference numerals are assigned to substantially the same components as in the first embodiment, and the description thereof will be omitted.

In this embodiment, the control unit 11 performs a monitoring area setting process to set each monitoring area before the work analysis process is started. In this monitoring area setting process, a monitoring area corresponding to the parts box 30 is set by detecting the movement of the parts box 30 when the parts box 30 is placed on the shelf 2 . Specifically, as shown in FIG. 33 , after bringing the parts box 30 closer to the imaging unit 13 , the component box 30 is placed on the shelf 2 so as to gradually move away from the imaging unit 13 . A range in which the distance gradually changes at is set as a monitoring area corresponding to the parts box 30 .

For this reason, in this embodiment, a TOF camera capable of measuring the distance to the imaging target is employed as the imaging unit 13 . As a result, for example, if a TOF camera is used as the imaging unit 13 , and the image of the component box 30 is captured at a position relatively close to the imaging unit 13 , the image becomes whiter as it gets closer, and becomes darker as it gets further away. , the parts box 30 is imaged in a whitish color like the distance image shown in FIG. 34(A). Then, by moving the parts box 30 away from the imaging unit 13, the parts box 30 changes to a blackish color so as to be close to the color of the shelf 2, as shown in the distance image shown in FIG. 34(B). be done. Note that a TOF camera may be prepared separately from the imaging unit 13, and the monitoring area corresponding to the parts box 30 may be set using the imaging result of this TOF camera.

The monitoring area setting process performed by the control unit 11 in this embodiment will be specifically described below with reference to the drawings.
Before starting the work analysis process, when the monitoring area setting process is started by the control unit 11 in response to a predetermined operation, the imaging process shown in step S301 of FIG. The box 30 can be imaged. Subsequently, the distance monitoring process shown in step S303 is performed, and the distance from the imaging unit 13 can be measured according to the captured image in the imaging range of the part of the shelf 2 where the parts box 30 is to be placed. .

Subsequently, in the determination processing in step S305, it is determined whether or not there is an area (hereinafter also referred to as a distance difference area) in which a distance difference occurs due to movement of the object in the imaging range of the imaging unit 13 . Here, if the parts box 30 is not brought close to the shelf 2 and there is no movement in the imaging range of the imaging unit 13, the determination of No is repeated in step S305.

Then, when the operator M moves the parts box 30 closer to the imaging unit 13 and enters the imaging range of the imaging unit 13, and a distance difference area is generated, a determination of Yes is made in step S305, and determination processing in step S307 is performed. , it is determined whether or not the distance difference area is caused by movement to a long distance. Here, when the distance between the imaging unit 13 and the parts box 30 is increased by arranging the parts box 30 placed within the imaging range of the imaging unit 13 by the worker M on the shelf 2, the distance difference area changes to black and becomes smaller, it is determined that the distance difference area is caused by the movement to the far side (Yes in S307).

In this case, a follow-up area monitoring process shown in step S309 is performed, the distance difference area is set as a follow-up area corresponding to the parts box 30, and the change in the follow-up area is monitored. be. Subsequently, in the determination processing of step S311, it is determined whether or not there is no change in the tracking area set as described above. Here, when the operator M is in the process of placing the parts box 30 on the shelf 2 and the parts box 30 is separated from the imaging unit 13, the follow-up area continues to change. determination is repeated.

Then, when the component box 30 is placed on the shelf 2 by the operator M, the distance of the component box 30 to the imaging unit 13 does not change, and the follow-up area does not change. In this case, in the setting shown in step S313, the follow-up area that has not changed is set as the monitoring area, and the monitoring area setting process ends. It should be noted that, when performing work using a plurality of component boxes 30, each component box 30 can be monitored by executing the monitoring area setting process each time one component box 30 is placed on the shelf 2. A monitoring area can be set.

As described above, in this embodiment, since the operator M can set the monitoring area by the general operation of placing the parts box 30 on the shelf 2 from above, it is not necessary to prepare a device for setting the monitoring area. This eliminates the need for prior setting work, complicated terminal operations, etc., and reduces the work required by the operator M to set the monitoring area. Then, the monitoring area can be set at the timing when the parts box 30 is placed on the shelf 2 . In particular, since the worker M does not specify the monitoring area, it is possible to suppress setting deviation of the monitoring area. In addition, in the monitoring area setting process, even if a different object in the parts box 30 is within the imaging area of the imaging unit 13, it is not set as a monitoring area unless the object stops after moving far away. , the setting accuracy of the monitoring area can be improved. Also, even if the parts box 30 changes in terms of image or shape, the monitoring area is set so that the following area does not change after setting the following area. A monitoring area can be set for

It should be noted that not only the TOF camera is employed as the imaging unit 13, but also a general RGB camera or the like is employed, and the follow-up area is set by detecting a state in which the parts box 30 is moving away from the captured image. You may In this configuration, it is possible to pseudo-recognize that the parts box 30 moves away from the imaging unit 13 by utilizing the fact that the area of the parts box 30 occupied in the captured image becomes smaller as the distance from the imaging unit 13 increases.

Further, the monitoring area process is not limited to being started in response to a predetermined operation by the worker M. It may be started by the operator M performing a predetermined gesture.

Note that the characteristic configuration of this embodiment, in which the movement of the parts box 30 is detected when the parts box 30 is placed on the shelf 2 and the monitoring area corresponding to the parts box 30 is set, is the same as that of other embodiments. etc. can also be applied.

[Tenth embodiment]
Next, a work analysis device and work analysis program according to a tenth embodiment will be described with reference to the drawings.
The tenth embodiment is mainly different from the first embodiment in the process for setting the monitoring area. Therefore, the same reference numerals are assigned to substantially the same components as in the first embodiment, and the description thereof will be omitted.

As for the storage state of each component 20 in the component box 30, various storage states are conceivable, such as a case where each component 20 is neatly arranged and a case where each component 20 is placed randomly. The parts 20 of the same kind are put together in the . In other words, it is considered that similar aggregates are accommodated in the parts box 30 respectively.

Therefore, in the present embodiment, the picked-up image of the parts box 30 is divided into blocks, the feature amount of each block is calculated, and the part 20 is located in the portion where the blocks having similar feature amounts are gathered. Determine that there is. Here, as the feature amount, for example, edge feature amounts such as a color histogram and HoG (Histogram Of Gradient), and various things such as frequency can be used.

For example, when two parts boxes 30e and 30f are arranged on the shelf 2 as shown in FIG. As shown, it is divided into blocks and a predetermined feature amount is extracted for each block. In this embodiment, frequency-based feature amounts are extracted. For example, in blocks B1 to B4 in FIG. 36B, frequency feature amounts as shown in FIG. 37 are extracted.

After the feature amount of each block is extracted, the blocks are grouped into blocks having similar feature amounts. As this grouping method, for example, a method of grouping similar parameters such as k-means and x-means into clusters and dividing them can be adopted.

If there is a group gathered in a rectangular area like the parts box 30 in the grouping, the range of the grouped blocks can be set as a monitoring area corresponding to the parts box 30. - 特許庁

It should be noted that the characteristic configuration of this embodiment, in which the monitoring regions corresponding to the component boxes 30 are respectively set using the feature amount extracted for each block, can also be applied to other embodiments.

[Eleventh embodiment]
Next, a work analysis device and work analysis program according to an eleventh embodiment will be described with reference to the drawings.
The eleventh embodiment is mainly different from the first embodiment in the process for setting the monitoring area. Therefore, the same reference numerals are assigned to substantially the same components as in the first embodiment, and the description thereof will be omitted.

Normally, the parts box 30 has a box shape with a rectangular opening at the top, and as a feature of this box shape, the upper ends of the peripheral walls are at the same height. Therefore, in this embodiment, a TOF camera is used as the imaging unit 13, and the distance is measured with respect to the area where the parts box 30 is planned to be arranged. Then, an area at the same height is extracted, and a monitoring area corresponding to the parts box 30 is set according to its shape. That is, when an area at the same height is extracted as a square ring, the parts box 30 is detected so that the square ring area becomes the peripheral wall, and the monitoring area is set so as to include this area. In this embodiment, it is assumed that the mounting surface of the shelf 2 on which each component box 30 is mounted is positioned horizontally with respect to the imaging section 13 .

Specifically, for example, when two parts boxes 30e and 30f are arranged on the shelf 2 as shown in FIG. The upper end of the peripheral wall of 30 is extracted as a quadrangular annular area with the same height.

In this manner, since the monitoring area corresponding to the parts box 30 can be set based on the area at the same height in the distance image, there is no need to prepare a device for setting the monitoring area, and the setting work and complicated operation in advance can be eliminated. Terminal operations and the like become unnecessary, and the operations of the worker M required for setting the monitoring area can be reduced.

It should be noted that a TOF camera may be prepared separately from the imaging unit 13, and regions at the same height may be extracted using this camera. When the mounting surface of the shelf 2 on which each component box 30 is mounted is inclined with respect to the imaging unit 13, the tilt angle is measured in advance, and the distance image is obtained by considering the tilt angle. You can correct the height at Further, the characteristic configuration of this embodiment, in which the monitoring area corresponding to the parts box 30 is set based on the area at the same height in the distance image, can also be applied to other embodiments.

[Twelfth Embodiment]
Next, a work analysis device and work analysis program according to a twelfth embodiment will be described with reference to the drawings.
The twelfth embodiment is mainly different from the first embodiment in the process for setting the monitoring area. Therefore, the same reference numerals are assigned to substantially the same components as in the first embodiment, and the description thereof will be omitted.

In the present embodiment, the color of each component box 30 is given a characteristic to make it easier to extract the area occupied by each component box 30 from the captured image as the monitoring area. As the color of each component box 30, it is possible to adopt a color that is individual and can be easily distinguished from the color of the surroundings of the shelf 2 and the like, the color of the hand of the worker M, and the like.

For example, the parts box 30e is set to a first color (eg, green), the parts box 30f is set to a second color (eg, blue), and as shown in FIG. is used to set the monitoring area of the parts box 30f, the area of the second color is extracted from the captured image as shown in FIG. 39(B). After that, filtering processing such as dilation/contraction including noise removal is performed on the image from which the second color region is extracted, thereby extracting a quadrangular ring region as shown in FIG. 39(C). . As a result, an area including the extracted rectangular annular area can be set as the monitoring area. In addition, in FIG. 39, only the second color is shown with hatching.

In particular, by distinguishing the color for each parts box 30, it is possible to easily grasp the type of the parts box 30 corresponding to the extracted monitoring area. In this way, by associating the colors with the types of the component boxes 30, it is possible to detect in which order the component boxes 30 are placed. By comparing with the order of the parts box 30 or the like, it is possible to exclude them. In addition, depending on the environment in which the work analysis device 10 is placed, it may be affected by external lighting, etc. Therefore, by viewing in a color space such as HSV that is robust against changes in brightness, misrecognition can be suppressed.

[Thirteenth Embodiment]
Next, a work analysis device and work analysis program according to a thirteenth embodiment will be described with reference to the drawings.
The thirteenth embodiment is mainly different from the first embodiment in the process for setting the monitoring area. Therefore, the same reference numerals are assigned to substantially the same components as in the first embodiment, and the description thereof will be omitted.

In this embodiment, the control unit 11 performs a monitoring area setting process to set each monitoring area before the work analysis process is started. In this monitoring area setting process, an area in which an image that can be assumed to be the component 20 is imaged in the captured image captured by the imaging unit 13 is set as a component area Pn, and the parts box 30 is monitored based on this component area Pn. , that is, the monitoring area is set.

Specifically, one component image of the target component 20 or two or more component images (templates) captured at different angles are prepared in advance, and as illustrated in FIG. In an extracted image obtained by extracting a range in which the parts box 30 may be placed from the image, a search is made for a range having a high degree of similarity with respect to the parts image (template matching). In this embodiment, a detection window Sw, which is set based on the size of the component 20 to be imaged, is slid in the extracted image to search for a range in which the degree of similarity is high.

The monitoring area setting process performed by the control unit 11 in this embodiment will be specifically described below with reference to the drawings.
Before starting the work analysis process, when the control unit 11 starts the monitoring area setting process in response to a predetermined operation with the parts box 30 placed on the shelf 2, the process is shown in step S401 in FIG. An initial setting process is performed, the type of the parts box 30 to which the monitoring area is to be set is specified, and the parts images of the parts 20 contained in the parts box 30 are acquired. Note that the component images may be obtained from the storage unit 12 stored in advance, or may be obtained from the outside each time the monitoring area setting process is performed.

If all the monitoring areas have not been set (No in S403), after the imaging unit 13 becomes capable of imaging (S405), the component area setting process shown in step S407 is performed. In the subroutine of this process, first, a similar range search process shown in step S501 of FIG. 42 is performed. In this process, as described above, the detection window Sw is slid in the extracted image at predetermined intervals (for example, in units of one or several pixels) to search for a range in which the degree of similarity is high. Processing is performed (see FIG. 40).

Then, when the search is completed for all of the extracted images, it is determined in the determination processing in step S503 whether or not a range in which the degree of similarity is equal to or greater than the fixed threshold has been searched. In the present embodiment, for example, the fixed threshold is set to 0.8, and if even one range in which the similarity is equal to or higher than the fixed threshold is found in the search results, the answer is Yes in step S503. be judged. In addition, even if the range in which the similarity is equal to or higher than the fixed threshold value is not searched in the search result (No in S503), the range in which the similarity is equal to or higher than the partial threshold value (for example, 0.2) is a predetermined number ( For example, if 10 items have been searched, the decision processing in step S505 is determined to be Yes.

As described above, if it is determined Yes in step S503 or if it is determined Yes in step S505, the setting process shown in step S507 is performed, and the component region Pn is set based on the searched range. . Specifically, as shown in FIG. 43, a rectangular area including all ranges whose similarities are greater than or equal to the partial threshold value is set as the component area Pn, and the subroutine of the component area setting process ends. In addition, in FIG. 43, part of the range in which the degree of similarity is equal to or higher than the partial threshold value is indicated by a rectangular dashed line.

On the other hand, in the search result, if the range in which the similarity is equal to or higher than the fixed threshold has not been searched (No in S503), and the predetermined number of ranges in which the similarity is equal to or higher than the partial threshold has not been searched (No in S505). ), the subroutine of the part area setting process ends without setting the part area Pn.

When the subroutine of the component area setting process ends as described above, it is determined whether or not the component area Pn is set in the determination process of step S409. Here, if the component area Pn is not set, it is determined as No in step S409, and the notification process shown in step S411 is performed. In this process, the fact that the part 20 to be searched cannot be found from the captured image is notified using the display on the display unit 14, etc., and this monitoring area setting process ends.

On the other hand, if the component area Pn is set (Yes in S409), the straight line search process shown in step S413 is performed. In this process, a straight line is searched outward from a point on the edge of the component region Pn in the extracted image. In this embodiment, as shown in FIG. 43, processing is performed to search for a straight line from the minimum X and Y coordinates in the component region Pn toward the negative side in the X direction (see symbol L1 in FIG. 43). ). Since the parts area Pn is set within the area corresponding to the parts box 30, a straight line corresponding to the inner surface of the peripheral wall of the parts box 30 is searched by the straight line search process. The search for a straight line is not limited to searching from the minimum X and Y coordinates in the component area Pn toward the negative side in the X direction, and the search for a straight line is performed outward from an arbitrary point on the edge of the component area Pn. You may do so.

After the straight line is searched as described above, an intersection point search process is performed in step S415 to search the extracted image for an intersection that is the tip of the searched straight line and intersects with another straight line. When intersections are searched by searching the straight line clockwise or counterclockwise, first, the number k of intersections searched is initialized to 0 (S417), and if the intersection is outside the part area Pn, If so (Yes in S419), the number k of intersection points searched is incremented (S421). Immediately after the number k of intersections is set to 0 as described above, the number k of intersections is set to 1.

Then, if the number of intersections k is not 4 (No in S423), processing is performed to search for the next intersection that will be the tip of another straight line connected to the intersection (S425). If the searched intersection point is outside the component area Pn (Yes at S419) and the incremented number k of intersection points is not 4 (No at S423), the processing from step S425 onward is performed again. If the searched intersection point is within the component area Pn (No in S419), it is determined that an incorrect intersection point has been searched, and the process for searching for the intersection point of the straight line is continued (S427).

Then, when the next intersection point is searched (S425) and the incremented number k of intersection points becomes 4 (Yes in S423), the setting process shown in step S429 is performed. In this process, since the rectangular area having the four corners of the searched four intersections corresponds to the rectangular area surrounded by the peripheral wall of the parts box 30, this rectangular area is set as the monitoring area. is processed. After that, in order to set the monitoring area of the next parts box 30, the processes after step S403 are performed. Then, when the monitoring areas for all the component boxes 30 are set, the judgment processing in step S403 returns Yes, and this monitoring area setting process ends.

As described above, in the monitoring area setting process in the present embodiment, an area in which an image that can be assumed to be the part 20 is imaged is set as the parts area Pn, and based on this parts area Pn, the area of the parts box 30, that is, the , a monitoring area is set. As a result, there is no need to prepare a device or the like for setting the monitoring area, and there is no need for prior setting work or complicated terminal operations, etc., and it is possible to reduce the operation of the worker M necessary for setting the monitoring area. can.

Note that the component region Pn is not limited to being set using the degree of similarity to the component image, and may be set using another method. For example, as a first modified example of the present embodiment, the component region Pn may be set based on the detection result using an edge detection algorithm (for example, the Canny method).

Specifically, the luminance value is line-scanned in the X-coordinate direction with respect to the grayscale of the extracted image (see FIG. 44), and the number of amplitudes within a certain interval (for example, within 10 pixels) is a predetermined threshold value (for example, 4 times). ) Store the Y coordinates of the start and end of the continuously detected section. Similarly, the luminance values are line-scanned in the Y coordinate direction (see FIG. 44), and the X coordinates of the start and end of the detected section are stored. Note that FIG. 45 conceptually exemplifies detection results obtained by line-scanning luminance values in the X-coordinate direction with respect to a predetermined Y-coordinate. Then, the coordinates closest to the origin in the stored X and Y coordinates are defined as the points through which two of the four straight lines forming the outer edge of the component area Pn pass, and the coordinates farthest from the origin are the points through which the remaining two straight lines pass. A part area Pn is set by making a point. The above effect can be obtained even when the monitoring area is set based on the component area Pn set in this way.

Further, as a second modified example of the present embodiment, the component region Pn may be set based on the detection result using a corner detection algorithm (for example, Harris corner detection).

Specifically, in the extracted image, the corners of each object are detected, and the angle of the smaller angle (less than 180 degrees) consisting of two straight lines that intersect at the detected corner and the coordinates of those corners are obtained (Fig. 46 hatched area), and a histogram for each rough corner angle is calculated (see FIG. 47). Then, the X coordinate and Y coordinate that are closest to the origin and the X coordinate that is farthest from the origin are selected from among the predetermined number of angles (depending on the shape of the part, for example, the top three angles for a triangle) in which the appearance frequency of the histogram is the highest. and the Y coordinate are set so as to coincide with the area surrounded by the parts area Pn. The above effect can be obtained even when the monitoring area is set based on the component area Pn set in this way.

It should be noted that the characteristic configuration of this embodiment, in which a component area Pn is set and a monitoring area is set from this component area Pn, can also be applied to other embodiments.

It should be noted that the present invention is not limited to the above-described embodiments and modifications thereof, and may be embodied as follows, for example.
(1) The predetermined work to be analyzed in the present invention is not limited to adopting an assembly work consisting of four unit works A to D. For example, an assembly work consisting of one to three unit works is adopted. Alternatively, an assembly operation consisting of five or more unit operations may be adopted.

(2) The delimiting operation (predetermined operation) described above includes the operation of taking out the component 20 from the component box 30 (first embodiment) and the operation of moving the component 20 to the planned assembly position of the workpiece W (second embodiment). form), but may be set to other work motions that are essential in the unit work, or may be set to motions that are easy to recognize images that are unrelated to the unit work.

(3) The present invention is not limited to being employed for work analysis when assembling parts to a work W such as a printed circuit board according to a predetermined work procedure. It may be employed for work analysis when assembling parts according to a predetermined work procedure for a product.

(4) By displaying information about the unit work determined to be abnormal work in the work analysis process, division information, etc., on the display unit 14 or the like, an opportunity to manually correct the division information may be provided as necessary. .

10 Work analysis device 11 Control unit (setting unit, generation unit)
13... Imaging unit 20, 20a to 20d... Parts 30, 30a to 30d... Parts box P1a to P1d, P2a to P2d... Monitoring area W... Work (member to be assembled)

Claims (6)

A work analysis device that generates determination data for determining whether correct work is being performed,
an imaging unit that captures repetition of a predetermined work in which a plurality of unit tasks are performed by a worker in a predetermined order;
a setting unit that sets delimiter information for delimiting the work moving image captured by the imaging unit into each unit work based on a predetermined motion set in advance for each unit work, at the detection timing of the predetermined motion; ,
a generation unit that generates the determination data so as to include the work moving image captured by the imaging unit and the delimiter information set by the setting unit;
with
The generation unit generates the determination data so as to exclude a unit work immediately preceding the unit work performed in an order different from the predetermined order, based on the delimiter information set by the setting unit. A work analysis device characterized by generating The unit work is a work of assembling a part taken out from a parts box associated with the unit work into a member to be assembled,
2. The work analysis apparatus according to claim 1, wherein the predetermined action is an action of taking out the part from the parts box. the unit work is a work of assembling a part associated with the unit work to a member to be assembled;
2. The work analysis apparatus according to claim 1, wherein the predetermined motion is a motion of moving the part to a predetermined assembly position of the member to be assembled. The generation unit calculates a normal work time range that is considered to be normal work for each unit work based on the delimiter information set by the setting unit. is generated as the judgment data. 5. The work analysis apparatus according to claim 4, wherein the generation unit generates the determination data so as to exclude the unit work whose work time is out of the normal work time range. In the control unit of the work analysis device that generates judgment data for judging whether or not the correct work is being done,
an imaging process of capturing an image of repetition of a predetermined work in which a plurality of unit tasks are performed by a worker in a predetermined order, using an imaging unit;
a setting process for setting delimiter information for delimiting the work moving image captured by the image capturing process for each unit work based on a predetermined motion set in advance for each unit work, at the detection timing of the predetermined motion; ,
a generation process for generating the determination data so as to include the work moving image captured by the imaging process and the delimiter information set by the setting process;
and
In the generating process, based on the delimiter information set in the setting process, the determination data is generated so as to exclude a unit work immediately preceding the unit work performed in an order different from the predetermined order. A work analysis program characterized by generating

Images