Method and system for automatically extracting sewing track from visual edge and application

Abstract

The invention discloses a method and system for automatically extracting a sewing track from a visual edge and application, and belongs to the technical field of image recognition, and the method comprises the following steps: a CCD (Charge Coupled Device) is matched with a light source to obtain and store an original image of a first cutting piece; carrying out gray scale and binarization processing on the image; weighting pixel points of the original image by using Gaussian blur to obtain an output image; detecting the edge contour of the output image by using edge detection; after the contours are determined, a convex hull is obtained, and a final image containing two contours is obtained; the first piece, the second piece, the third piece and the like are sequentially overlaid on the first cutting piece, and the following cutting pieces of the first cutting piece are on the basis of the previous cutting piece, and the steps are repeated until the sample is completed. The air bag cutting piece sewing machine solves the problem that in the traditional air bag cutting piece sewing process, sewing routing is prone to being too large or too small.

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, and more specifically, to a method, system and application for automatically extracting sewing tracks using visual edges. Background Art

[0002] Automobile airbag is a passive safety protection system for automobiles. When an accident occurs, the airbag is deployed by electronic ejection to protect the passengers.

[0003] Airbags need to be sewn during production, and a lot of manpower and material resources are required in the process of sorting and identifying pieces, and the work quality and efficiency cannot be guaranteed, especially for the process of sewing multiple pieces in batches. Since the current manual sewing trajectory uses different pieces to sew at the same time, the efficiency of sewing trajectory extraction is poor, which can easily lead to the problem that the stitching trajectory is too large or too small, or the corners of different bottom pieces are not sewn during the sewing process. Therefore, how to use intelligent and reliable extraction of sewing trajectories to ensure the stability of sewing trajectories when the pieces are sewn in sequence has become a development trend. Based on this, it is of long-term significance to use visual inspection to extract the sewing trajectory of airbag pieces. Summary of the invention

[0004] In order to overcome the problems raised in the above-mentioned background technology, the present invention provides a method, system and application for automatically extracting sewing tracks by visual edges, so as to solve the problem that the sewing tracks of existing airbag panels are easily too large or too small, or there are leaks when they are sewn sequentially, thereby effectively reducing labor costs.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] A method for automatically extracting sewing tracks using visual edges comprises the following steps:

[0007] S1: CCD cooperates with light source to obtain the original image of the first cut piece and stores it;

[0008] S2: grayscale and binarization processing of the image;

[0009] S3: Use Gaussian blur to weight the pixels of the original image to obtain the output image;

[0010] S4: Detect edge contours of the output image using edge detection;

[0011] S5: After determining the contour, obtain the convex hull to obtain a final image containing two contours;

[0012] S6: The second piece, the third piece, ... are sequentially superimposed on the first piece, and the subsequent pieces of the first piece are based on the previous piece, and steps S1-S5 are repeated.

[0013] Preferably, in step S2, the image is gray-scaled using the cvtColor(src,dest,way) function, wherein:

[0014] src represents the initial mat object;

[0015] dest represents the converted mat object;

[0016] Way indicates the method of conversion.

[0017] Preferably, the Gaussian blur function in step S3 is

[0018] GaussianBlur(src,dest,size(m,n),sigma1,sigma2), where

[0019] size(m,n) means that the kernel size is defined as m*n; sigma1 and sigma2 are parameters of the blur degree and are defined as 0.

[0020] Preferably, the step S4 uses Canny (src, dest, low, high) to detect edge contours, wherein low and high represent a double threshold, low is a low threshold, and high is a high threshold;

[0021] Pixels with grayscale changes greater than high are set as strong edge pixels, and those below low are eliminated.

[0022] Preferably, the step S5 uses Cv2.ConvexHull(pt1) algorithm to obtain the convex hull.

[0023] The present invention also provides a system for automatically extracting sewing tracks through visual edges, comprising at least one processor and a memory for storing an execution system.

[0024] The present invention also provides a sewing device, comprising an image acquisition and processing unit, the image acquisition and processing unit comprising a CCD camera and a computer, wherein:

[0025] The system also includes a loading trolley, a rotating platform, a four-axis manipulator, a gripping mechanism, a rotating arm, a sewing jig, a feeding platform, a suction cup and a material tray. The pieces to be tested are stacked in sequence on the piece jig of the loading trolley. The four-axis manipulator drives the gripping mechanism to grip the pieces into the material tray on the rotating platform through the suction cup arranged at the bottom thereof. The piece jig is detachably mounted with a plurality of sewing molds on one side facing the adjacent material tray. The sewing molds are mounted on the sewing jig. The sewing jig is mounted on the pushing device through a plug-in lock. The pushing device pushes the sewing mold pushing device on the sewing jig into the interior of the material tray. The gripping mechanism places the sewn finished product into the feeding platform.

[0026] Preferably, the loading trolley is provided with a plurality of positioning needles installed thereon.

[0027] Preferably, the CCD camera is installed on the upper part of the cutting jig via a bracket, and a thickness sensor is installed at the bottom of the CCD camera bracket.

[0028] Preferably, a plurality of rotating arms are arranged around the top of the rotating platform, and anti-floating pressure pins are installed at the ends of the rotating arms.

[0029] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0030] The present invention provides a method, system and application for automatically extracting sewing trajectories by visual edges. When different mold pieces are sewn in sequence, the sewing trajectories can be extracted in sequence to keep the sewing trajectories within a preset value. Compared with manually stacking and placing the pieces, this method can ensure that each piece is sewn accurately. At the same time, the system has a high degree of intelligence, and both loading and unloading are intelligent, which can effectively reduce labor and save costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0033] Figure 2 It is a schematic diagram of the system structure of the present invention;

[0034] Figure 3 It is a schematic diagram of the three-dimensional structure of the sewing equipment of the present invention;

[0035] Figure 4 For the present invention Figure 3 Left view structural diagram;

[0036] Figure 5 For the present invention Figure 3 Rear view structure diagram;

[0037] Figure 6 It is a schematic diagram of the three-dimensional structure from another viewing angle of the present invention;

[0038] Figure 7 It is a schematic diagram of the structure of the gripping mechanism and the suction cup positioning method of the present invention;

[0039] Figure 8A schematic diagram of an original image of a cut piece of the present invention;

[0040] Fig. 9 It is a schematic diagram of an image after edge detection of a cut piece according to the present invention.

[0041] Explanation of the marks in the figure: 1. Loading trolley; 2. Rotating platform; 3. Four-axis manipulator; 4. Grasping mechanism; 5. Rotating arm; 6. Anti-floating pressure needle; 7. CCD camera; 8. Thickness sensor; 9. Plug-in lock; 10. Sewing jig; 11. Unloading platform; 12. Cutting jig; 13. Suction cup; 14. Material tray. DETAILED DESCRIPTION

[0042] In order to better understand the purpose, structure and function of the present invention, the technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings and specific preferred embodiments.

[0043] In the description of the present invention, it should be understood that the terms "left side", "right side", "upper part", "lower part", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. "First", "second", etc. do not indicate the importance of the parts, and therefore cannot be understood as a limitation on the present invention. The specific dimensions used in the embodiments are only for illustrating the technical solution and do not limit the scope of protection of the present invention. It is understandable to those skilled in the art that some well-known structures and their descriptions in the drawings may be omitted.

[0044] Unless otherwise clearly specified and limited, the terms "install", "set", "connect", "fix" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0045] Embodiment 1:

[0046] See also Figure 1 The present invention provides a method for automatically extracting sewing tracks by visual edge, comprising the following steps:

[0047] S1: CCD cooperates with light source to obtain the original image of the first cut piece and stores it;

[0048] S2: grayscale and binarization processing of the image;

[0049] S3: Use Gaussian blur to weight the pixels of the original image to obtain the output image;

[0050] S4: Detect edge contours of the output image using edge detection;

[0051] S5: After determining the contour, obtain the convex hull to obtain a final image containing two contours;

[0052] S6: The second piece, the third piece, ... are sequentially superimposed on the first piece, and the subsequent pieces of the first piece are based on the previous piece, and steps S1-S5 are repeated.

[0053] Based on the above embodiment, in step S2, the image is gray-scaled using the cvtColor(src, dest, way) function, where:

[0054] src represents the initial mat object;

[0055] dest represents the converted mat object;

[0056] Way indicates the method of conversion.

[0057] Based on the above embodiment, the Gaussian blur function in step S3 is:

[0058] GaussianBlur(src,dest,size(m,n),sigma1,sigma2), where

[0059] size(m,n) means that the kernel size is defined as m*n; sigma1 and sigma2 are parameters of the blur degree and are defined as 0.

[0060] Based on the above embodiment, the step S4 uses Canny (src, dest, low, high) to detect edge contours, where:

[0061] Low and high represent a double threshold, low is the low threshold and high is the high threshold;

[0062] Pixels with grayscale changes greater than high are set as strong edge pixels, and those below low are eliminated.

[0063] Based on the above embodiment, the step S5 adopts the Cv2.ConvexHull(pt1) algorithm to obtain the convex hull.

[0064] Take the first reverse sewing track as an example. Figure 8 and Fig. 9 As stated, Figure 8 is the original image, Fig. 9 is the image after edge detection.

[0065] It should be noted that the grayscale and binarization processing of the image, the weighting of the pixels of the original image by Gaussian blur, the edge detection of the edge contour of the output image, and the subsequent acquisition of the convex hull in Example 1 can all be programmed in OpenCV. The method of the present invention is designed for subsequent equipment, and the specific algorithms and steps are well-known technologies, which will not be repeated in this application.

[0066] Embodiment 2:

[0067] See also Figure 2 The present invention also provides a system for automatically extracting sewing trajectories by visual edges, comprising at least one processor and a memory for storing an execution system.

[0068] Embodiment 3:

[0069] See also Figure 3-7 The present invention also provides a sewing device, including an image acquisition and processing unit, the image acquisition and processing unit includes a CCD camera 7 and a computer, wherein:

[0070] The system also includes a loading trolley 1, a rotating platform 2, a four-axis manipulator 3, a gripping mechanism 4, a rotating arm 5, a sewing jig 10, a feeding platform 11, a suction cup 13 and a material tray 14. The pieces to be tested are stacked in sequence on the piece jig 12 of the loading trolley 1. The four-axis manipulator 3 drives the gripping mechanism 4 to grip the pieces into the material tray 14 on the rotating platform 2 through the suction cup 13 arranged at the bottom thereof. The piece jig 12 is detachably installed with multiple sewing molds on one side facing the material tray 14. The sewing molds are installed on the sewing jig 10. The sewing jig 10 is installed on the pushing device through the plug-in lock 9. The pushing device pushes the sewing mold pushing device on the sewing jig 10 into the inside of the material tray 14, and the gripping mechanism 4 places the sewn finished product into the feeding platform 11.

[0071] The specific working principle of the above embodiment is as follows: the pieces are stacked on the piece cutting jig 12 of the loading trolley 1, and the pieces are placed in the material tray 14 of the rotating platform 2 through the grasping mechanism 4 of the four-axis manipulator 3. The bottom of the grasping mechanism 4 is a plurality of suction cups 13, and the material is taken by high-pressure adsorption. This material taking method will not produce wrinkles, ensuring that the pieces remain original when sewing; a mold is installed on the piece cutting jig 12, and when the pieces enter the material tray 14, the three-axis moving mechanism at the bottom of the piece cutting jig 12 pushes the mold on the piece cutting jig 12 into the material tray, CC The D camera 7 extracts the first sewing track of the piece of cutting piece in combination with the mold, and the subsequent external sewing unit sews according to the sewing track. After sewing, the cutting piece fixture 12 moves driven by the three-axis moving mechanism at the bottom, and the movement method can be horizontal movement, so as to replace the next mold, repeat the visual inspection again, extract the second sewing track, and use the subsequent external sewing unit to sew according to the sewing track. The subsequent third piece and fourth batch can be sewn according to the above steps, and the sewn finished product is grabbed by the grabbing mechanism 4 and placed on the unloading platform 11.

[0072] It should be noted that the three-axis moving mechanism at the bottom of the cutting jig 12 is a prior art three-axis moving mechanism driven by a servo motor, and will not be described again in this application.

[0073] As a preferred embodiment of the above, the loading trolley 1 is provided with a plurality of positioning pins, and different cutting pieces can be stacked on the loading trolley 1 by the positioning pins according to different cutting pieces.

[0074] As a preferred embodiment of the above, the CCD camera 7 is installed on the upper part of the cutting jig 12 through a bracket, and a thickness sensor 8 is installed at the bottom of the CCD camera 7 bracket to perform thickness detection on the sewn samples to ensure the sample qualification rate.

[0075] As a preferred embodiment of the above, a plurality of rotating arms 5 are further arranged on the top of the rotating platform 2, and an anti-floating pressure needle 6 is installed at the end of the rotating arm 5. The anti-floating pressure needle 6 can fix the cut piece during sewing to ensure the stability during sewing. Specifically, the anti-floating pressure needle 6 can be driven to move by the rotating arm 5 on the rotating platform 2. Specifically, when the cut piece is sewn, the rotating arm 5 is rotated to allow the anti-floating pressure needle 6 to press the cut piece inside the material tray 14. After sewing, the rotating arm 5 is moved to remove the anti-floating pressure needle 6 to facilitate the subsequent grabbing of the cut piece.

[0076] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A method for automatically extracting sewing tracks using visual edges, characterized in that: The following steps are included: S1: CCD cooperates with light source to obtain the original image of the first cut piece and stores it; S2: grayscale and binarization processing of the image; S3: Use Gaussian blur to weight the pixels of the original image to obtain the output image; S4: Detect edge contours of the output image using edge detection; S5: After determining the contour, obtain the convex hull to obtain a final image containing two contours; S6: The second piece, the third piece, ... are sequentially superimposed on the first piece, and the subsequent pieces of the first piece are based on the previous piece, and steps S1-S5 are repeated.

2. The method for automatically extracting sewing tracks by visual edge according to claim 1, characterized in that: In step S2, the image is gray-scaled using the cvtColor(src, dest, way) function, where: src represents the initial mat object; dest represents the converted mat object; Way indicates the method of conversion.

3. The method for automatically extracting sewing tracks by visual edge according to claim 2, characterized in that: The Gaussian blur function in step S3 is GaussianBlur(src,dest,size(m,n),sigma1,sigma2), where: size(m,n) means that the kernel size is defined as m*n; sigma1 and sigma2 are parameters of the blur degree and are defined as 0.

4. The method for automatically extracting sewing tracks by visual edge according to claim 3, characterized in that: The step S4 uses Canny (src, dest, low, high) to detect edge contours, where: Low and high represent a double threshold, low is the low threshold and high is the high threshold; Pixels with grayscale changes greater than high are set as strong edge pixels, and those below low are eliminated.

5. The method for automatically extracting sewing tracks by visual edge according to claim 4, characterized in that: The step S5 uses the Cv2.ConvexHull(pt1) algorithm to obtain the convex hull.

6. A system for automatically extracting sewing tracks by visual edge, comprising the method for automatically extracting sewing tracks by visual edge as claimed in any one of claims 1 to 5, characterized in that: The system comprises at least one processor and a memory for storing an execution system.

7. A sewing device, comprising the method for automatically extracting sewing tracks by visual edge according to any one of claims 1 to 5, characterized in that: The image acquisition and processing unit comprises a CCD camera (7) and a computer, wherein: The system further comprises a loading trolley (1), a rotating platform (2), a four-axis manipulator (3), a grasping mechanism (4), a rotating arm (5), a sewing jig (10), a feeding platform (11), a suction cup (13) and a material tray (14). The cut pieces to be inspected are sequentially stacked on the cut piece jig (12) of the loading trolley (1), and the four-axis manipulator (3) drives the grasping mechanism (4) to grasp the cut pieces to the rotating platform (2) via the suction cup (13) arranged at the bottom thereof. ), a cutting jig (12) is detachably mounted with a plurality of sewing dies on one side facing the adjacent material tray (14), the sewing dies are mounted on the sewing jig (10), the sewing jig (10) is mounted on a pushing device via a plug-in lock (9), the pushing device pushes the sewing die on the sewing jig (10) into the material tray (14), and the grabbing mechanism (4) places the sewn finished product on the unloading platform (11).

8. The sewing device according to claim 7, characterized in that: The loading trolley (1) is provided with a plurality of positioning needles installed thereon.

9. The sewing device according to claim 8, characterized in that: The CCD camera (7) is installed on the upper part of the cutting jig (12) via a bracket, and a thickness sensor (8) is installed at the bottom of the CCD camera (7) bracket.

10. The sewing device according to claim 9, characterized in that: A plurality of rotating arms (5) are also arranged around the top of the rotating platform (2), and anti-floating pressure pins (6) are installed at the ends of the rotating arms (5).

Images