KR102597704B1 - Automation device and method that handling clothing fabric - Google Patents

Abstract

As a clothing fabric handling automation device and method, the clothing fabric handling automation device according to an embodiment of the present application includes a vision camera for acquiring a target image by photographing a target fabric; a control unit that determines gripping coordinates and center point coordinates for the target fabric based on a gripping point determination algorithm applied to the target image; And the control unit includes a gripper jig that controls driving in response to the gripping coordinates and the center point coordinates to grip the target fabric, wherein the center point coordinates are at the center of a gripper unit having a plurality of grippers included in the gripper jig. It may be the corresponding coordinates

Description

Clothing fabric handling automation device and method {AUTOMATION DEVICE AND METHOD THAT HANDLING CLOTHING FABRIC}

This application relates to an apparatus and method for automating clothing fabric handling.

Due to the flexible nature of textile materials, the introduction of automation in the clothing manufacturing process has been delayed significantly compared to other businesses. In particular, handling technologies such as gripping and transporting clothing fabrics are very difficult to respond to numerous patterns and shapes as well as material characteristics, making them effective. No automation plan has been proposed.

Currently known representative fabric gripping methods include penetration and pneumatic methods. Among them, the pneumatic method is capable of efficiently gripping large quantities of fabric, but requires a precise flow rate to grasp only single sheets of fabric in order to link with other automated process systems such as cutting/sewing. There was a difficulty in controlling it.

On the other hand, in the case of the penetration type, if the penetration depth is adjusted, it is possible to grip a single piece of fabric, but the fabric may be damaged during the penetration process, and due to the very small fixation range of the fabric, there is a possibility that the fabric may fall off during transportation due to fabric phenomenon.

In addition, even if single-sheet gripping is possible, in order to link the fabric with other clothing manufacturing processes such as sewing, very high accuracy is required regarding the transfer position, angle, unfolding state, etc., whereas a fixed gripper device can be used to consistently capture different phenomena. There were significant limitations in transferring performance.

The technology behind this application is disclosed in Korean Patent Publication No. 10-1627114.

The purpose of this application is to solve the problems of the prior art described above, and to provide a clothing fabric handling automation device and method for determining the gripping point of the fabric according to the fabric shape recognized through vision in real time and gripping a single sheet of fabric. The purpose.

In addition, the present application is intended to solve the problems of the prior art described above, and includes a variable gripper jig device that corrects the positions of the four grippers according to the fabric shape recognized through vision in real time, fabric shape recognition based on clothing pattern CAD files, and optimal The purpose is to provide a clothing fabric handling automation device and method that aims to perform precise transport customized to the shape of the clothing fabric by linking a vision algorithm that performs the derivation of the gripping point location, etc.

However, the technical challenges sought to be achieved by the embodiments of the present application are not limited to those described above, and other technical challenges may exist.

As a technical means for achieving the above-described technical problem, an automated clothing fabric handling device according to an embodiment of the present application includes a vision camera for acquiring a target image by photographing a target fabric; a control unit that determines gripping coordinates and center point coordinates for the target fabric based on a gripping point determination algorithm applied to the target image; And the control unit includes a gripper jig that controls driving in response to the gripping coordinates and the center point coordinates to grip the target fabric, wherein the center point coordinates are at the center of a gripper unit having a plurality of grippers included in the gripper jig. It may be a corresponding coordinate.

In addition, the control unit may apply a real-time marker recognition algorithm to the target image and determine that a process for gripping the target fabric can be performed when the marker for the target image is recognized for a preset amount of time.

In addition, the holding point determination algorithm extracts a plurality of image key points corresponding to the corner outline of the image frame excluding the embroidery shape portion in the target image, and a mapping image in which a known fabric CAD shape is mapped to the plurality of image key points. may be generated, and the grip coordinates and the center point coordinates may be determined based on the mapping image.

Additionally, the mapping image may be created by matching the center coordinates and aspect ratio of the outline of the fabric CAD shape with the center coordinates and aspect ratio of the plurality of image key points.

Additionally, the plurality of image keypoints are image keypoints from which noise has been removed, and the control unit may determine corner outlines that have not been repeatedly detected more than a preset number of times as noise.

Additionally, the gripping coordinates may be determined for each of the plurality of grippers by considering the positions and movable ranges of each of the plurality of grippers and the outline shape of the mapping image.

Additionally, the gripper jig may include: the gripper unit having the plurality of grippers; and an articulated robot that moves the gripper unit under the control of the control unit, and the plurality of grippers may be a needle gripper type provided to grip a single piece of clothing fabric.

In addition, the plurality of grippers include a first gripper, a second gripper positioned at intervals in a first horizontal direction with respect to the first gripper, and a second gripper positioned at a right angle to the first direction in the horizontal direction with respect to the first gripper. It includes a third gripper positioned at intervals in a second direction, and a fourth gripper positioned at intervals in a first horizontal direction with respect to the third gripper, wherein the gripper unit includes the first gripper and the a first linear driving unit that linearly moves the second gripper away from or closer to the third gripper and the fourth gripper along the second direction; The first gripper linearly moves away from or closer to the second gripper along the first direction, and the third gripper linearly moves away from or closer to the fourth gripper along the first direction. It may include a driving part.

In addition, the clothing fabric handling automation device may further include a communication unit that transmits the gripping coordinates and the center point coordinates determined by the control unit to the gripper jig.

In addition, as a method of automating clothing fabric handling using a clothing fabric handling automation device according to an embodiment of the present application, the method of automating clothing fabric handling according to an embodiment of the present application includes (a) photographing the target fabric using a vision camera; acquiring an image; (b) a control unit determining grip coordinates and center point coordinates for the target fabric based on a grip point determination algorithm applied to the target image; and (c) the control unit driving and controlling the gripper jig in response to the gripping coordinates and the center point coordinates in order to grip the target fabric, wherein the center point coordinates determine a plurality of grippers included in the gripper jig. It may be a coordinate corresponding to the center of the gripper unit.

In addition, in step (a), the control unit applies a real-time marker recognition algorithm to the target image and, when the marker for the target image is recognized for a preset time, can perform a process for gripping the target fabric. Step (b) above can be performed depending on the situation.

In addition, step (b) includes: (b1) extracting a plurality of image keypoints corresponding to corner outlines of the image frame excluding the embroidery shape portion in the target image; (b2) generating a mapping image in which a known fabric CAD shape is mapped to the plurality of image keypoints; (b3) may include determining the grip coordinates and the center point coordinates based on the mapping image.

Additionally, in step (b2), the mapping image may be created by matching the center coordinates and aspect ratio of the outline of the fabric CAD shape with the center coordinates and aspect ratio of the plurality of image key points.

Additionally, in step (b1), the plurality of image keypoints are image keypoints from which noise has been removed, and the control unit may determine corner outlines that have not been repeatedly detected a preset number of times as noise.

Additionally, the gripping coordinates may be determined for each of the plurality of grippers by considering the positions and movable ranges of each of the plurality of grippers and the outline shape of the mapping image.

The above-described means of solving the problem are merely illustrative and should not be construed as intended to limit the present application. In addition to the exemplary embodiments described above, additional embodiments may be present in the drawings and detailed description of the invention.

According to the means for solving the problem of the present application described above, the clothing fabric handling automation device includes a control unit including a gripping point determination algorithm applied to the target fabric recognized in real time, so that the fabric is processed according to the shape of the target fabric recognized using the algorithm. Since the gripping point can be determined, the process preparation process can be shortened.

In addition, according to the problem solving means of the present application described above, the control unit drives and controls the gripper jig in response to the gripping coordinates and the center point coordinates, so that the control unit controls the gripping target fabric without the need to manually adjust the position of the gripper according to the shape of the target fabric. The process preparation process can be shortened by driving the gripper jig in response to the shape and appropriate gripping point.

In addition, according to the problem solving means of the present application described above, the control unit generates a mapping image by extracting a plurality of image key points from which noise has been removed, thereby increasing accuracy by reducing errors or errors in determining the grip coordinates and center point coordinates for the target fabric. You can.

In addition, according to the above-described means of solving the problem of the present application, the gripper uses a penetrating needle gripper, which is effective in gripping only single sheets, unlike the pneumatic type, and overcomes the limitations due to the narrow gripping point through the gripping position response technology based on shape recognition. It can enable the gripping of strong fabric sheets.

In addition, according to the means for solving the problem of the present application described above, the gripper unit includes a first linear drive unit and a second linear drive unit, so that the plurality of grippers can linearly move even if the articulated robot is fixed at a position corresponding to the coordinates of the center point. , a plurality of grippers may be moved to a position corresponding to the gripping point coordinates.

1 is a diagram of an automated clothing fabric handling device according to an embodiment of the present application.
Figure 2 is a diagram for explaining the vision camera-based real-time trigger marker (embroidery shape) recognition function of the clothing fabric handling automation device according to an embodiment of the present application.
Figure 3 is a diagram for explaining the shape recognition process of clothing fabric in an automated clothing fabric handling device according to an embodiment of the present application.
Figure 4 is a diagram for explaining the gripper jig of the automated clothing fabric handling device according to an embodiment of the present application.
Figure 5 is a diagram for explaining a gripper unit of an automated clothing fabric handling device according to an embodiment of the present application.
Figure 6 is a diagram for explaining a gripper of an automated clothing fabric handling device according to an embodiment of the present application.
Figure 7 is a diagram for explaining the gripper position control system of the gripper jig of the automated clothing fabric handling device according to an embodiment of the present application.
Figure 8 is a network data flow diagram of an automated clothing fabric handling device according to an embodiment of the present application.
Figure 9 is a diagram for explaining an implementation example of an automated clothing fabric handling device according to an embodiment of the present application.
Figure 10 is a diagram showing the transfer accuracy evaluation process and results according to an implementation example of an automated clothing fabric handling device according to an embodiment of the present application.
Figure 11 is a flowchart of a method for automating clothing fabric handling according to an embodiment of the present application.
Figure 12 is a flow chart for determining the grip coordinates and center point coordinates of the target fabric in the clothing fabric handling automation method according to an embodiment of the present application.

Below, with reference to the attached drawings, embodiments of the present application will be described in detail so that those skilled in the art can easily implement them. However, the present application may be implemented in various different forms and is not limited to the embodiments described herein. In order to clearly explain the present application in the drawings, parts that are not related to the description are omitted, and similar reference numerals are assigned to similar parts throughout the specification.

Throughout this specification, when a part is said to be “connected” to another part, this includes not only the case where it is “directly connected,” but also the case where it is “electrically connected” with another element in between. do.

Throughout this specification, when a member is said to be located “on”, “above”, “at the top”, “below”, “at the bottom”, or “at the bottom” of another member, this means that a member is located on another member. This includes not only cases where they are in contact, but also cases where another member exists between two members.

Throughout the specification of the present application, when a part is said to “include” a certain element, this means that it may further include other elements rather than excluding other elements, unless specifically stated to the contrary.

Hereinafter, an automated clothing fabric handling device (hereinafter referred to as “this device”) according to an embodiment of the present application will be described.

1 is a diagram for explaining an automated clothing fabric handling device according to an embodiment of the present application, and FIG. 2 is a vision camera-based real-time trigger marker (embroidery shape) recognition function of the clothing fabric handling automation device according to an embodiment of the present application. 3 is a diagram for explaining the shape recognition process of clothing fabric by an automated clothing fabric handling device according to an embodiment of the present application.

Referring to FIG. 1 , the device 1000 includes a vision camera 100, a control unit 200, and a gripper jig 300. This device 1000 can be used in the clothing manufacturing process industry, but is not limited to this.

The vision camera 100 can obtain a target image by photographing the target fabric. For example, referring to (a) of FIGS. 1 and 2 , the vision camera 100 may be installed on the gripper jig 300 to bring the target fabric into the frame. Additionally, the target fabric may be a fabric that the device 1000 wants to grip or transfer, and the target image may be an image of the target fabric.

The control unit 200 may determine the grip coordinates and center point coordinates for the target fabric based on a grip point determination algorithm applied to the target image. The gripping coordinates may be coordinates for the gripper 311 to be described later to grip the target fabric, and the center point coordinates may be at the center of the gripper unit 310 having a plurality of grippers 311 included in the gripper jig 300. It may be a corresponding coordinate. Additionally, for example, the control unit 200 may be a PLC-based integrated control system and may include an algorithm that enables detection of a fabric to be gripped, fabric shape recognition based on CAD image mapping, and determination of a fabric gripping point.

Additionally, the control unit 200 may apply a real-time marker recognition algorithm to the target image and determine that a process for gripping the target fabric can be performed when the marker for the target image is recognized for a set amount of time. For example, referring to (b) of Figure 2, when the target fabric enters the frame of the vision camera 100, the image feature extraction algorithm SURF (Speed-Up Robust Feature) and the feature point matching algorithm FLANN (Fast Library for Based on (Approximate Nearest Neighbor), it is possible to extract features for specific trigger markers (embroidered shapes) of target images recognized in real time and match them with existing registration markers.

At this time, for example, if the real-time marker recognition algorithm continuously recognizes 60 frames (about 2 seconds), it can be determined that the situation is possible for clothing to be gripped or transported, and after moving the gripper jig 300 through a trigger signal, the next Algorithm corner detection and CAD image mapping-based fabric shape recognition functions can be implemented.

Referring to FIG. 3, the holding point determination algorithm may extract a plurality of image keypoints corresponding to the corner outline of the image frame excluding the embroidery shape portion in the target image. For example, referring to (b) of FIG. 2 and (a) of FIG. 3, the device 1000 scans the clothing fabric with the vision camera 100 for 60 consecutive frames (about 2 seconds) to recognize the fabric shape. By taking a picture, 50 corners within the image frame excluding the embroidery shape can be extracted as image keypoints. Here, Figure 3(a) is a diagram showing the result of displaying all extracted corners.

Additionally, referring to (b) of FIG. 3, the plurality of image keypoints may be image keypoints from which noise has been removed. The control unit 200 may determine corner outlines that have not been repeatedly detected more than a preset number of times as noise.

Additionally, the control unit 200 may generate a mapping image in which a known fabric CAD shape is mapped to a plurality of image keypoints, and determine grip coordinates and center point coordinates based on the mapping image. For example, in order to map the fabric CAD shape to the image from which the noise has been removed (e.g., (b) in Figure 3), the outline (e.g., (c) in Figure 3) can first be extracted from the CAD image. there is.

For example, referring to (c) and (d) of FIGS. 3, the mapping image may be created by matching the center coordinates and aspect ratio of the outline of the fabric CAD shape with the center coordinates and aspect ratio of a plurality of image key points. Additionally, the mapping image can be created to match the actual fabric cutting shape.

Additionally, the gripping coordinates determined based on the mapping image may be determined for each of the plurality of grippers 311 by considering the positions and movable ranges of each of the plurality of grippers 311 and the outline shape of the mapping image.

FIG. 4 is a diagram for explaining a gripper jig of an automated clothing fabric handling device according to an embodiment of the present application, and FIG. 5 is a diagram for explaining a gripper unit of an automated clothing fabric handling device according to an embodiment of the present application. Figure 6 is a diagram for explaining a gripper of an automated clothing fabric handling device according to an embodiment of the present application. In addition, Figure 7 is a diagram for explaining a gripper position control system of a gripper jig of an automated clothing fabric handling device according to an embodiment of the present application.

The gripper jig 300 may be driven and controlled by the control unit 200 in response to the gripping coordinates and the center point coordinates in order to grip the target fabric. For example, the gripper jig 300 may be driven and controlled in response to the gripping coordinates and center point coordinates of the mapping image determined through the CAD image mapping-based fabric shape recognition algorithm of the control unit 200.

Referring to FIG. 4 , the gripper jig 300 may include a gripper unit 310 and an articulated robot 320 . The gripper unit 310 may have a plurality of grippers 311. For example, a plurality of grippers 311 may be provided to grip the target fabric. Referring to FIGS. 4 and 5 , the number of grippers 311 may be four, but the number is not limited to this.

Hereinafter, a case where there are four plurality of grippers 311 according to an implementation example of the present application will be described.

Referring to FIG. 5, the plurality of grippers 311 may include a first gripper 311a, a second gripper 311b, a third gripper 311c, and a fourth gripper 311d. The second gripper 311b may be positioned at intervals from the first gripper 311a in a first horizontal direction (3 o'clock to 9 o'clock direction, based on FIG. 5). Additionally, the third gripper 311c may be positioned at intervals from the first gripper 311a in a second direction perpendicular to the first direction (12 o'clock to 6 o'clock direction, based on FIG. 5) with respect to the first gripper 311a. Additionally, the fourth gripper 311d may be positioned at intervals in the first horizontal direction with respect to the third gripper 311c.

Additionally, the gripper unit 310 may include a first linear drive unit 312a and a second linear drive unit 312b. For example, referring to FIG. 5, a linear driving unit 312 may be included to adjust the positions of the plurality of grippers 311 according to the gripping point determined through the vision algorithm of the vision camera 100 and the control unit 200. can

The first linear driving unit 312a can linearly move the first gripper 311a and the second gripper 311b so that they are away from or closer to the third gripper 311c and the fourth gripper 311d along the second direction. . In addition, the second linear driving unit 312b linearly moves the first gripper 311a away from or closer to the second gripper 311b in the first direction, and the third gripper 311c moves the fourth gripper 311d. It can be linearly moved away from or closer to the first direction. For example, the first linear drive unit 312a and the second linear drive unit 312b may be provided for each of the first to fourth grippers 311a to 311d, but are not limited thereto.

The first linear drive unit 312a and the second linear drive unit 312b may be motors that provide linear driving force, and more specifically, may be 5-axis AC servo motor-based linear guides. At this time, for example, referring to (b) of FIG. 5, the device 1000 may be designed to grip a target fabric with a size ranging from a minimum of 130 × 160 mm to a maximum of 450 × 410 mm.

Additionally, the plurality of grippers 311 may be a needle gripper type provided to enable gripping of single sheets of clothing fabric. Referring to (a) of Figure 6, the gripper 311 is a fabric electronic penetration depth control type that can discharge a needle within the range of, for example, 0.1 mm to 3.0 mm in order to perform a robust grip on the target fabric thickness. May include a gripper. At this time, referring to (b) of FIG. 6, the gripper 311, which includes a fabric electronic penetration depth control type gripper capable of discharging a needle, is used when observing whether the target fabric is damaged by needle penetration. , significant damage may not be found. However, it is not limited to this, and the gripper 311 may be provided with various types of grippers 311 that are known to those skilled in the art that can grip the target fabric without damaging it.

Additionally, the articulated robot 320 may move the gripper unit 310 under the control of the control unit 200. For example, the articulated robot 320 may be a six-axis robot, but is not limited to this. As another example, the articulated robot 320 may be a robot with various axes, which are obvious to those skilled in the art. Additionally, for example, the articulated robot 320 may be moved to a position corresponding to the center point coordinates determined by the control unit 200.

In other words, the gripper jig 300 converts the gripping coordinates determined through the algorithm of the control unit 200 into the moving distance of the gripper 311 and the coordinates of the center point of the target fabric into the position of the articulated robot 320, thereby converting the coordinates of the center point of the target fabric into the position of the articulated robot 320 and the position of the target fabric immediately after cutting. It is possible to respond according to the shape.

Figure 8 is a network data flow diagram of an automated clothing fabric handling device according to an embodiment of the present application.

Meanwhile, the device 1000 may include a communication unit. The communication unit may transmit the gripping coordinates and center point coordinates determined by the control unit 200 to the gripper jig 300.

Referring to FIG. 7, the communication unit transmits a control command to the linear driving unit 312 of the gripper jig 300 based on the control unit 200, and connects the linear driving unit 312 of the gripper jig 300 and the control unit 200. You can build a signal control module by connecting them. For example, referring to FIG. 8, the communication unit uses data for controlling clothing fabric gripping (e.g., fabric thickness, grip center point coordinates, fabric size, etc.) generated through the vision algorithm of the control unit 200 to actually grip the target fabric and It may be provided to deliver to the gripper jig 300 that will perform the transfer.

Additionally, the communication unit may be equipped to enable relay control of the gripper jig 300 in order to transmit data for controlling clothing fabric gripping generated through the control unit 200. At this time, for example, if the control unit 200 is a PLC, the data generated by the vision camera 100 is combined into a single string and transmitted to the PLC, and then the string is converted into a gripper jig through the PLC Ladder development environment. It can be developed to be split and transmitted into data units to be transmitted to (300). Additionally, the communication unit may support different communication protocols for the articulated robot 320, gripper jig 300, and gripper 310. At this time, when transmitting data from the PLC, the communication unit can configure a network so that each protocol supported by the gripper jig 300 can be opened and transmitted. In addition, when transmitting data to the articulated robot 320, gripper jig 300, and gripper 310 based on the PLC, the communication unit can open and transmit data for each protocol supported.

For example, referring to FIG. 8, the communication unit may transmit center point coordinate data generated through the vision camera 100 and the control unit 200 to the articulated robot 310, and transmit the thickness data of the target fabric to the gripper 311. ) can be passed on. Additionally, the communication unit may transmit the grip coordinates generated through the vision camera 100 and the control unit 200 to the gripper unit 310. Accordingly, the gripper jig 300 can drive the articulated robot 320 with coordinates corresponding to the center point coordinates and discharge the needle within a range according to the thickness of the target fabric. Additionally, the gripper unit 310 may move the plurality of grippers 311 to coordinates corresponding to the gripping coordinates.

Figure 9 is a diagram for explaining an implementation example of an automated clothing fabric handling device according to an embodiment of the present application, and Figure 10 is a transfer accuracy evaluation process according to an implementation example of an automated clothing fabric handling device according to an embodiment of the present application, and This is a drawing showing the results.

Referring to FIG. 9, in order to verify the performance of this device 1000, an automation test of the cutting, transfer, and sewing clothing manufacturing process was performed on a test bed consisting of a 6-axis articulated robot, needle gripper, cutter, and sewing machine. It can be done. At this time, referring to FIG. 10, as a result of evaluating the accuracy (error area/actual area) of the fabric transfer position of this device 1000, precise transfer at 96.47% may be possible.

Meanwhile, the following will describe a clothing fabric handling automation method (hereinafter referred to as 'this automation method') using a clothing fabric handling automation device according to an embodiment of the present application. However, this automated method shares the same or corresponding technical features as the above-described device, and the same reference numerals are used for components that are the same or similar to those of the device 1000, and overlapping descriptions are simplified or omitted. Do this.

FIG. 11 is a flowchart of a method for automating clothing fabric handling according to an embodiment of the present application, and FIG. 12 is a flowchart for determining the grip coordinates and center point coordinates of a target fabric of the method for automating clothing fabric handling according to an embodiment of the present application.

Referring to FIG. 11 , this automated method may include a step of acquiring a target image by photographing the target fabric using the vision camera 100 (step S110). Additionally, in step S110, the vision camera 100 may acquire not only the target image but also data on the thickness of the target fabric.

In addition, in step S110, the control unit 200 applies a real-time marker recognition algorithm to the target image and, if the marker for the target image is recognized for a preset time, it may be determined that a process for gripping the target fabric can be performed. there is. The preset time may be 60 frames (about 2 seconds), but is not limited to this, and may be a time set by the user and previously input into the control unit 200.

In addition, referring to FIG. 11, the automated method includes a step (step S120) in which the control unit 200 determines the gripping coordinates and center point coordinates for the target fabric based on the gripping point determination algorithm applied to the target image. You can. Step S120 may be performed after the control unit 200 determines that a process for gripping the target fabric for the target image can be performed in step S110.

Referring to FIG. 12, step S120 may include extracting a plurality of image keypoints corresponding to corner outlines of the image frame excluding the embroidery shape portion in the target image (step S121). In step S121, the plurality of image keypoints may be image keypoints from which noise has been removed. Additionally, the control unit 200 may determine corner outlines that have not been repeatedly detected more than a preset number of times as noise. That is, image keypoints from which corner outlines that have not been repeatedly detected more than a preset number of times through the control unit 200 are removed may be a plurality of image keypoints.

Additionally, referring to FIG. 12 , step S120 may include generating a mapping image in which a known fabric CAD shape is mapped to a plurality of image keypoints (step S122). In step S122, the mapping image may be created by matching the center coordinates and aspect ratio of the outline of the fabric CAD shape with the center coordinates and aspect ratio of a plurality of image key points.

Additionally, referring to FIG. 12 , step S120 may include determining grip coordinates and center point coordinates based on the mapping image (step S123). The gripping coordinates may be determined for each of the plurality of grippers 311 by considering the positions and movable ranges of each of the plurality of grippers 311 and the outline shape of the mapping image.

Referring to FIG. 11, this automated method may include a step (step S130) in which the control unit 200 drives and controls the gripper jig 300 in response to the gripping coordinates and the center point coordinates to grip the target fabric. The center point coordinates may be coordinates corresponding to the center of the gripper unit 310 having a plurality of grippers 311 included in the gripper jig 300.

In step S130, a communication unit may be included in order for the control unit 200 to transmit data of the gripping coordinates and center point coordinates determined for gripping the target fabric to the gripper jig 300. In addition, the communication unit transmits control commands to the linear driving unit 312 of the gripper jig 300 based on the control unit 200, and controls the signal by connecting the linear driving unit 312 of the gripper jig 300 and the control unit 200. You can build modules.

In step S130, the gripper jig 300 may drive the articulated robot 320 with coordinates corresponding to the center point coordinates determined in step S120, and discharge the needle within a range according to the thickness of the target fabric created in step S110. You can do it. Additionally, the gripper unit 310 may move the plurality of grippers 311 to coordinates corresponding to the gripping coordinates determined through step S120.

In this device 1000 and this automation method, accurate transfer customized to the shape of the fabric can be performed, so the clothing manufacturing automation line can be expanded by connecting with already commercialized automation equipment such as cutting and sewing.

This device (1000) and this automation method are linked with a variable gripper jig device capable of responding to various fabric shapes and real-time image processing technology to perform precise fabric handling, which is a core automation technology in the clothing manufacturing process, and automatically customized gripping and A transfer method may have been developed.

The description of the present application described above is for illustrative purposes, and those skilled in the art will understand that the present application can be easily modified into other specific forms without changing its technical idea or essential features. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present application is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present application.

1000: Clothing fabric handling automation device
100: Vision camera
200: control unit
300: Gripper jig
310: Gripper unit
311: Gripper
311a: first gripper
311b: second gripper
311c: third gripper
311d: fourth gripper
312: linear driving unit
312a: first linear drive unit
312b: second linear drive unit
320: Jointed robot

Claims (15)

delete As a clothing fabric handling automation device,
A vision camera that acquires a target image by photographing the target fabric;
a control unit that determines grip coordinates and center point coordinates for the target fabric based on a grip point determination algorithm applied to the target image; and
The control unit includes a gripper jig that controls driving in response to the gripping coordinates and the center point coordinates to grip the target fabric,
The center point coordinates are coordinates corresponding to the center of a gripper unit having a plurality of grippers included in the gripper jig,
The control unit,
A clothing fabric handling automation device that applies a real-time marker recognition algorithm to the target image and determines that a process for gripping the target fabric can be performed when the marker for the target image is recognized for a preset time. As a clothing fabric handling automation device,
A vision camera that acquires a target image by photographing the target fabric;
a control unit that determines grip coordinates and center point coordinates for the target fabric based on a grip point determination algorithm applied to the target image; and
The control unit includes a gripper jig that controls driving in response to the gripping coordinates and the center point coordinates to grip the target fabric,
The center point coordinates are coordinates corresponding to the center of a gripper unit having a plurality of grippers included in the gripper jig,
The gripping point determination algorithm is,
Extracting a plurality of image keypoints corresponding to the corner outline of the image frame excluding the embroidery shape portion from the target image,
Generate a mapping image in which a known fabric CAD shape is mapped to the plurality of image key points,
An automated clothing fabric handling device that determines the grip coordinates and the center point coordinates based on the mapping image. According to paragraph 3,
The mapping image is generated by matching the center coordinates and aspect ratio of the outline of the fabric CAD shape with the center coordinates and aspect ratio of the plurality of image key points. According to paragraph 3,
The plurality of image keypoints are image keypoints from which noise has been removed,
The control unit determines a corner outline that has not been repeatedly detected more than a preset number of times as noise. According to paragraph 3,
The gripping coordinates are determined for each of the plurality of grippers by considering the position and movable range of each of the plurality of grippers and the outline shape of the mapping image. According to paragraph 3,
The gripper jig is,
the gripper unit having the plurality of grippers; and
It includes an articulated robot that moves the gripper unit under the control of the control unit,
The plurality of grippers are needle gripper types provided to enable gripping of single sheets of clothing fabric. In clause 7,
The plurality of grippers include a first gripper, a second gripper positioned at intervals in a first horizontal direction with respect to the first gripper, and a second gripper orthogonal to the first direction in the horizontal direction with respect to the first gripper. It includes a third gripper positioned at intervals in one direction, and a fourth gripper positioned at intervals in a first horizontal direction with respect to the third gripper,
The gripper unit is,
a first linear driving unit that linearly moves the first gripper and the second gripper away from or closer to the third gripper and the fourth gripper along the second direction;
The first gripper linearly moves away from or closer to the second gripper along the first direction, and the third gripper linearly moves away from or closer to the fourth gripper along the first direction. A clothing fabric handling automation device comprising a driving unit. In clause 7,
The clothing fabric handling automation device,
The clothing fabric handling automation device further includes a communication unit that transmits the gripping coordinates and the center point coordinates determined by the control unit to the gripper jig. delete A method of automating clothing fabric handling using a clothing fabric handling automation device,
(a) acquiring a target image by photographing the target fabric using a vision camera;
(b) a control unit determining grip coordinates and center point coordinates for the target fabric based on a grip point determination algorithm applied to the target image; and
(c) the control unit driving and controlling the gripper jig in response to the gripping coordinates and the center point coordinates to grip the target fabric,
The center point coordinates are coordinates corresponding to the center of a gripper unit having a plurality of grippers included in the gripper jig,
The control unit,
In step (a), if the marker for the target image is recognized for a preset time by applying a real-time marker recognition algorithm to the target image, it is determined that a process for gripping the target fabric can be performed, and the ( b) A method of automating garment fabric handling, wherein the step is performed. According to clause 11,
In step (b),
(b1) extracting a plurality of image keypoints corresponding to corner outlines of the image frame excluding the embroidery shape portion from the target image;
(b2) generating a mapping image in which a known fabric CAD shape is mapped to the plurality of image keypoints;
(b3) A method for automating clothing fabric handling, including the step of determining the grip coordinates and the center point coordinates based on the mapping image. According to clause 12,
In step (b2) above,
The mapping image is generated by matching the center coordinates and aspect ratio of the outline of the fabric CAD shape with the center coordinates and aspect ratio of the plurality of image key points. According to clause 12,
In step (b1) above,
The plurality of image keypoints are image keypoints from which noise has been removed,
The control unit determines a corner outline that has not been repeatedly detected more than a preset number of times as noise. According to clause 12,
The gripping coordinates are determined for each of the plurality of grippers by considering the position and movable range of each of the plurality of grippers and the outline shape of the mapping image.

Images