KR102363763B1 - Method for upcycling waste leather and shredded leather scrap material based on edge detection and feature point extraction and matching of material images and system thereof - Google Patents

Abstract

A method and system for upcycling waste leather and fragmented leather scrap materials based on edge detection and feature point extraction and matching of material images are provided. The upcycling method of waste leather and fragmented leather scrap material based on edge detection and feature point extraction and matching of the material image according to some embodiments of the present disclosure analyzes the image taken of the target material to determine the upcycling suitability of the target material determining, in response to the suitability determination, determining a component of a product matching the target material, and controlling the processing equipment according to the determined specification of the component, wherein the photographed image is a first image and a second Including an image, the step of determining suitability for upcycling includes a raw image merging step of merging the first image and the second image through an image stitching technique, and analyzing the merged image to determine upcycling suitability of the target material and determining, wherein the raw image merging step is performed by matching feature points after edge detection in each of the first image and the second image. By doing so, the upcycling process can be performed in an automated manner, and a high-quality product can be manufactured.

Description

Method and system for upcycling waste leather and fragmented leather scrap material based on edge detection and feature point extraction and matching of material images AND SYSTEM THEREOF}

The present invention relates to a method for upcycling waste leather and fragmented leather scrap material and a system for performing the method, and more particularly, to various It relates to a method capable of automating a leather fabric upcycling process and a system for performing the method.

Upcycling is a compound word of upgrade and recycling, and it means to re-create a product with better value by recycling a given material. Upcycling is also called “upcycling,” meaning new use.

On the other hand, after mass production of clothing or leather products in factories, scrap fabrics or leather materials are left in large quantities, which become industrial waste when discarded. In addition, these industrial wastes incur significant costs to dispose of and can cause serious levels of environmental pollution during the treatment process. Accordingly, recently, interest in the upcycling process of scrap fabric or leather material is increasing, and attempts are being made to automate the upcycling process by introducing artificial intelligence technology or the like.

Korean Patent Publication No. 10-2018-0086164 (published on July 30, 2018)

A technical problem to be solved through some embodiments of the present disclosure is to provide a method capable of automating an upcycling process and a system for performing the method.

Another technical problem to be solved through some embodiments of the present disclosure is to provide a method for improving the efficiency of an upcycling process and a system for performing the method.

Another technical problem to be solved through some embodiments of the present disclosure is to provide a method capable of improving the quality of a product manufactured through an upcycling process, and a system for performing the method.

The technical problems of the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description.

In order to solve the above technical problem, the material upcycling method according to some embodiments of the present disclosure is a material upcycling method performed by a computing device that controls a process facility, and a target material is analyzed by analyzing the photographed image. determining suitability of a target material for upcycling, in response to the suitability determination, determining a component of a product that matches the target material, and comprising the steps of: may include controlling the processing equipment.

In some embodiments, the determining of the upcycling suitability includes extracting state information of the target material by analyzing the image, and determining the upcycling suitability of the target material based on the extracted state information Including the step, the state information may include at least one information of the degree of contamination, the presence of perforations, and the size.

In some embodiments, the process facility may further include a sorting facility, and in response to a nonconformity determination, further comprising controlling the sorting facility to discard the target material.

In some embodiments, the process equipment further includes a cutting equipment, and the controlling of the processing equipment includes: setting a cutting area for the target material according to the determined specification of the component; It may include generating a connected graph having a plurality of points as vertices, deriving a shortest path from the connected graph by applying a shortest path algorithm, and controlling the cutting equipment according to the derived shortest path. .

In some embodiments, the processing equipment further comprises a cutting equipment and a joining equipment, and the machining of the target material comprises deriving a cutting path and a joining path based on the determined specification of the component or the product; The method may include controlling the cutting equipment according to the derived cutting path and controlling the joining equipment according to the derived joining path.

In order to solve the above technical problem, the material upcycling system according to some embodiments of the present disclosure may include one or more process equipment including a processing equipment and a control device for controlling the one or more process equipment. At this time, the control device analyzes the image in which the target material is captured to determine the upcycling suitability of the target material, and in response to the suitability determination, determines a component of a product matching the target material, and The processing equipment may be controlled to process the target material according to specifications.

In order to solve the above technical problem, the computer program according to some embodiments of the present disclosure is combined with a computing device, analyzing the image taken of the target material to determine the upcycling suitability of the target material, suitability determination In response, to be stored in a computer-readable recording medium to execute the steps of determining the component of the product matching the target material and controlling the processing equipment to process the target material according to the determined specification of the component can

According to some embodiments of the present disclosure described above, by upcycling raw materials, material disposal costs may be reduced, and environmental pollution problems due to material disposal may be greatly alleviated.

In addition, raw materials suitable for upcycling may be selected through the material inspection process, and thus the quality of manufactured products may be improved. In addition, the upcycling process can be automated by performing inspections through image analysis of raw materials without human intervention.

In addition, by merging a plurality of material images through an image stitching technique and extracting state information of raw materials from the merged images, the accuracy of the material inspection process can be improved.

In addition, by deriving a cutting path and/or a joining path based on the shortest path algorithm, the efficiency of the machining process can be greatly improved.

Effects according to the technical spirit of the present disclosure are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

Effects according to the technical spirit of the present disclosure are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is an exemplary diagram illustrating a material upcycling system according to some embodiments of the present disclosure.
2 is an exemplary flowchart schematically illustrating a material upcycling method according to some embodiments of the present disclosure.
3 is an exemplary flowchart illustrating a material inspection process according to some embodiments of the present disclosure.
4 is an exemplary view for further explaining a material inspection process according to some embodiments of the present disclosure.
5 is an exemplary view for explaining a method of measuring a material contamination level according to some embodiments of the present disclosure.
6 to 8 are exemplary views for explaining an image stitching method according to some embodiments of the present disclosure.
9 is an exemplary flowchart illustrating a machining process according to some embodiments of the present disclosure.
10 is an exemplary view for further explaining a cutting process according to some embodiments of the present disclosure.
11 is an exemplary view for further explaining a bonding process according to some embodiments of the present disclosure.
12 is an exemplary view for explaining a cutting path calculation method according to some embodiments of the present disclosure.
13 illustrates an exemplary computing device that may implement a control device according to some embodiments of the present disclosure.

Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Advantages and features of the present disclosure, and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the technical spirit of the present disclosure is not limited to the following embodiments, but may be implemented in various different forms, and only the following embodiments complete the technical spirit of the present disclosure, and in the technical field to which the present disclosure belongs It is provided to fully inform those of ordinary skill in the art of the scope of the present disclosure, and the technical spirit of the present disclosure is only defined by the scope of the claims.

In adding reference numerals to the components of each drawing, it should be noted that the same components are given the same reference numerals as much as possible even though they are indicated on different drawings. In addition, in describing the present disclosure, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present disclosure, the detailed description thereof will be omitted.

Unless otherwise defined, all terms (including technical and scientific terms) used herein may be used with the meaning commonly understood by those of ordinary skill in the art to which this disclosure belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless clearly defined in particular. The terminology used herein is for the purpose of describing the embodiments and is not intended to limit the present disclosure. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase.

In addition, in describing the components of the present disclosure, terms such as first, second, A, B, (a), (b), etc. may be used. These terms are only for distinguishing the elements from other elements, and the essence, order, or order of the elements are not limited by the terms. When a component is described as being “connected”, “coupled” or “connected” to another component, the component may be directly connected to or connected to the other component, but another component is between each component. It should be understood that elements may also be “connected,” “coupled,” or “connected.”

As used herein, “comprises” and/or “comprising” refers to a referenced component, step, operation, and/or component of one or more other components, steps, operations and/or components. The presence or addition is not excluded.

Hereinafter, various embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

1 is an exemplary diagram illustrating a material upcycling system 1 according to some embodiments of the present disclosure.

As shown in FIG. 1 , the material upcycling system 1 performs an up-cycling process on raw materials 21 to 24 in an automated or semi-automated manner to obtain a predetermined product 28 . It may be a system for manufacturing For example, the material upcycling system 1 may upcycle leather materials to manufacture leather products (eg wallets, bags, etc.), thereby reducing material disposal costs and greatly alleviating environmental pollution problems. . Hereinafter, for convenience of description, the material upcycling system 1 will be abbreviated as “upcycling system 1”.

The raw materials 21 to 24 are any material capable of upcycling, and may be, for example, leather, fiber, plastic, or the like, but is not limited thereto. However, in the following, in order to provide convenience of understanding, the description will be continued assuming that the raw materials 21 to 24 are leather materials.

As shown, the upcycling system 1 may be configured to include a plurality of process facilities 11 to 15 and a control device 10 for controlling them.

The process facilities 11 to 15 are various facilities used in the upcycling process, and for example, a photographing facility 11, a washing facility (eg 12), a drying facility (eg 13), a processing process such as cutting, bonding, etc. It may include a processing facility (eg 14) used for there is. However, the present invention is not limited thereto. Each of the process facilities 11 to 15 may be controlled by the control device 10 .

The photographing facility 11 may photograph the raw materials 21 to 24 , the processed materials 25 to 27 , the product 28 , and the like, and provide (transmit) the photographed image to the control device 10 . there is. Also, the imaging facility 11 may photograph the process facilities 12 to 15 in order to monitor the upcycling process.

In addition, the processing facility (e.g. 14) may include a cutting facility used for cutting the materials 21 to 27, a bonding facility used for bonding the materials 21 to 27, and the like. However, the present invention is not limited thereto.

Next, the control device 10 may be a computing device that generally controls the process facilities 11 to 15 . In other words, the control device 10 may control the upcycling process as a whole.

More specifically, the control device 10 acquires (receives) images in which the raw materials 21 to 24 are photographed from the photographing facility 11, and analyzes the acquired images to obtain the raw materials 21 to 24 You can check the quality. In addition, the control device 10 may process the inspected raw materials 21 to 24 by controlling the process facilities 12 to 15 , and as a result, the raw materials 21 to 24 are converted into products 28 . ) can be reborn as A more detailed description of the operation of the control device 10 will be described later with reference to the drawings below in FIG. 2 .

The control device 10 may be implemented as one or more computing devices. For example, the control device 10 may be implemented as one computing device. Alternatively, the control device 10 may be implemented with a plurality of computing devices, and a first function of the control device 10 may be implemented in a first computing device and a second function may be implemented in a second computing device. Alternatively, a specific function of the control device 10 may be implemented in a plurality of computing devices. The computing device may include any type of device having a computing function. For an example of the computing device, refer to FIG. 13 .

As shown, the control device 10 and the process facilities 11 to 15 may communicate through a network. Here, the network may be implemented as various types of wired/wireless networks.

So far, an upcycling system 1 according to some embodiments of the present disclosure has been schematically described with reference to FIG. 1 . Hereinafter, a material upcycling method that can be performed in the upcycling system 1 as illustrated in FIG. 1 will be described in detail with reference to FIG. 2 and the following drawings.

Each step of the method to be described below may be performed by a computing device or a material upcycling system having the computing device. In other words, at least some of the methods to be described below may be implemented as one or more instructions executed by a processor of a computing device. Hereinafter, for convenience of understanding, it is assumed that each step of the method to be described below is performed by the control device 10 or the upcycling system 1 illustrated in FIG. 1 to continue the description. Accordingly, when the subject of a specific operation is omitted, it may be understood as being performed by the control device 10 or the upcycling system 1 .

2 is an exemplary flowchart illustrating a material upcycling method according to some embodiments of the present disclosure. However, this is only a preferred embodiment for achieving the purpose of the present disclosure, and it goes without saying that some steps may be added or deleted as needed.

As shown in FIG. 2 , the method according to the present embodiments may start in step S1 of performing a material inspection process. The material inspection process can be understood as a process of inspecting the upcycling suitability of raw materials (e.g. 21). For example, the control device 10 may analyze an image taken of the raw material (e.g. 21) to extract state information of the material, and determine upcycling suitability based on the extracted state information. If it is determined to be unsuitable for upcycling, the raw material (e.g. 21) may be discarded. The material inspection process will be described in detail later with reference to FIGS. 3 to 8 .

In step S2, a machining process may be performed, and a product may be manufactured as a result. The machining process may include, for example, cutting and bonding, but is not limited thereto. For example, the control device 10 can manufacture the product (e.g. 28) by cutting the material (e.g. 22) by controlling the cutting equipment and/or the joining equipment or by joining a plurality of materials (e.g. 22, 23). The cutting process and the joining process may be repeatedly or non-repetitively performed regardless of the order. The processing process will be described in detail later with reference to FIGS. 9 to 12 .

For reference, the product (eg 28) may be a generic term for all articles manufactured from raw materials through the processing process, and not only the finished article but also the unfinished article (eg, it does not have the shape of the finished article and is simply cut / bonded material) may also be included in the scope of the product (eg 28).

In step S3, a product inspection process may be performed. The product inspection process may be performed in a manner similar to the above-described material inspection process S1. For example, the control device 10 may extract state information of the product by analyzing an image obtained by photographing the manufactured product (e.g. 28), and may inspect the quality of the product based on the extracted state information.

As a more specific example, the control device 10 measures the contamination level of the product (eg 28) from the image of the product (eg 28) using a deep learning model (eg, a CNN-based model such as YOLO) that detects a contamination object. can

As another example, the control device 10 may extract product specification information (eg type/type, size, color, shape, etc.) from the image of the product (eg 28) by applying a deep learning model or image analysis technique. . In addition, the control device 10 may determine whether the product (e.g. 28) meets the standard specification by comparing the reference specification information of the product DB with the extracted specification information. When there are a plurality of images of the product (eg 28), the control device 10 merges the plurality of images through the image stitching technique, and analyzes the merged image to more accurately extract the specification information of the product (eg 28). there is. The image stitching technique will be described in more detail later with reference to FIGS. 6 to 8 .

As another example, the control device 10 may perform the product inspection in the same manner as the material inspection process.

As another example, the control device 10 may perform defect inspection on the product (e.g. 28) by understanding the deep learning model of the autoencoder structure. Specifically, the control device 10 may train the deep learning model of the autoencoder structure by using the image of a normal product without defects. The deep learning model trained in this way can restore images of normal products well, but may not restore images of defective products well. Accordingly, the control device 10 may determine whether a defect exists in the product (e.g. 28) based on whether the image of the product (e.g. 28) input to the deep learning model is well restored. For example, the control device 10 may determine that the product (e.g. 28) is defective when the reconstruction loss of the deep learning model is greater than or equal to the reference value. Alternatively, if the difference between the latent vector of the image of the corresponding product (eg 28) output by the encoder of the deep learning model and the latent vector of the normal product image is greater than the reference value, the control device 10 is applied to the product (eg 28). may be judged to be defective.

So far, a material upcycling method according to some embodiments of the present disclosure has been described with reference to FIG. 2 . According to the above-described method, by upcycling the raw materials, the cost of material disposal can be reduced, and the environmental pollution problem caused by the material disposal can be greatly alleviated.

Hereinafter, detailed processes of the above-described material upcycling method will be described in more detail. First, a material inspection process according to some embodiments of the present disclosure will be described with reference to FIGS. 3 to 8 .

3 is an exemplary flowchart illustrating a material inspection process according to some embodiments of the present disclosure. However, this is only a preferred embodiment for achieving the purpose of the present disclosure, and it goes without saying that some steps may be added or deleted as needed.

As shown in FIG. 3 , the material inspection process according to the present embodiment may be started in step S11 of acquiring an image of the raw material. For example, as shown in FIG. 4 , the control device 10 may acquire (receive) images in which raw materials 21 to 24 are photographed from the photographing facility 11 .

In step S12, by analyzing the acquired image, suitability for upcycling of the raw material may be determined. For example, as shown in FIG. 4 , the control device 10 analyzes the acquired image to extract state information of each raw material 21 to 24 , and determines upcycling suitability based on the extracted state information. can

The state information of the raw material (eg 21) may include, for example, information on the quality of the material such as turbidity, contamination level, abrasion level, presence of perforations, etc., and specification information such as type (type), shape, color, size, etc. However, the present invention is not limited thereto, and may further include possible information extracted through image analysis.

Specific methods of determining suitability for upcycling may vary.

For example, when the contamination level (or turbidity, wear level) of the raw material (e.g. 21) is equal to or greater than a reference value, the control device 10 may determine that the raw material (e.g. 21) is unsuitable for upcycling.

As another example, when perforations exist in the raw material e.g. 21 , the control device 10 may determine that the raw material e.g. 21 is unsuitable for upcycling.

As another example, when the size of the raw material e.g. 21 is less than or equal to the reference value, the control device 10 may determine that the raw material e.g. 21 is unsuitable for upcycling.

As another example, if the size of the first raw material is less than or equal to the reference value, but there is a second raw material that can be joined, and when the size of the first raw material and the second raw material is greater than the reference value, the control device 10 controls the two raw materials It can be determined that the material is suitable for upcycling.

A specific method of extracting state information may also vary according to embodiments.

In some embodiments, the control device 10 may extract information on the shape (or shape, size) of the raw material eg 21 by applying an edge detection technique to the image of the raw material eg 21 . there is. For example, the control device 10 may determine the shape of the raw material eg 21 from the shape of the edge detected in the material image, and may calculate the size of the raw material eg 21 from the size of the area within the edge. .

Also, in some embodiments, the control device 10 may extract type information (or size information) of the raw material (e.g. 21) using a deep learning model. For example, the control device 10 uses a deep learning model trained to predict the type (class) of the material (eg a CNN-based model trained to predict the class label of the material) from the material image to the raw material (eg 21) type can be predicted. As another example, the control device 10 uses a deep learning model (eg, a CNN-based model such as YOLO, etc., a CNN-based semantic segmentation model that performs class prediction in units of pixels) trained to detect a raw object image of a raw material. can detect the raw material object, and calculate the size of the raw material eg 21 based on the size of the area occupied by the raw material object. As a more specific example, as shown in FIG. 5 , the control device 10 uses a Convolutional Neural Network (CNN)-based deep learning model 32 such as You Only Look Once (YOLO) to obtain a raw image 31. can detect the raw material object 311 in the form of a bounding box 312 . Then, the control device 10 may calculate the size of the raw material 311 based on the size of the bounding box 312 . Also, the control device 10 may determine the shape of the raw material 311 by applying an edge detection technique to the bounding box image 312 . Alternatively, the control device 10 counts the number of pixels occupied by the raw material object eg 311 in the raw image using the semantic segmentation model, and calculates the size of the raw material eg 311 based on the counted number of pixels You may.

In addition, in some embodiments, the control device 10 may extract information on the degree of contamination (or the degree of wear, perforation, etc.) of the raw material (e.g. 21) using a deep learning model. For example, as shown in FIG. 5 , the control device 10 uses the deep learning model 34 trained to predict (measure) the degree of contamination, and use the raw image (31 or 33; eg a cropped image of the bounding box 312) It is possible to predict (measure) the contamination level 35 of the raw material 311 from Alternatively, the control device 10 uses a deep learning model (eg 34; a CNN-based model such as YOLO, etc., a CNN-based semantic segmentation model that performs class prediction in units of pixels) trained to detect a contamination object. In (eg 33), a contaminated object may be detected, and the contamination level of the raw material (eg 311) may be determined based on the number and size of the contaminated object (ie, the entire area occupied by the contaminated object).

Meanwhile, in some embodiments, a determination as to whether to wash may be further performed. For example, as shown in FIG. 4 , when the contamination level (or turbidity, etc.) of a specific raw material 23 is greater than or equal to a reference value, the control device 10 may determine that cleaning is necessary for the corresponding raw material 23 . . Also, the control device 10 may control the cleaning intensity of the cleaning equipment 162 based on the contamination level of the specific raw material 23 . In addition, the control device 10 may measure the contamination level of the washed raw material 23 again and repeatedly perform the washing process based on the measured contamination level.

It will be described again with reference to FIG. 3 .

In step S13, processing according to the suitability determination result may be performed. For example, as shown in FIG. 4 , in response to determining that a specific raw material 21 is unsuitable for upcycling, the control device 10 controls the sorting facility 161 to discard the raw material 21 . can Alternatively, in response to determining that a particular raw material 24 is suitable for upcycling, the control device 10 controls the sorting equipment 161 and/or the conveyor equipment so that the next process can be performed on the raw raw material 24 . (15) can be controlled. In addition, in response to the determination that the specific raw material 23 needs washing, the control device 10 may control the washing equipment 162 and the drying equipment 163 so that the corresponding raw material 23 is washed.

On the other hand, a case in which the entire raw material (e.g. 21) is not included in a single image, or the raw material (e.g. 21) is photographed at various angles and included in a plurality of images may occur. In this case, the control device 10 may merge a plurality of images by applying an image stitching technique, and extract state information of the raw material (e.g. 21) from the merged image. By doing so, the state information (e.g. shape, size, contamination level, etc.) of the raw material (e.g. 21) can be accurately extracted. Hereinafter, image stitching methods according to embodiments will be described in detail. The image stitching method, which will be described later, may be utilized in various cases of merging images (eg, merging product images in a product inspection process, etc.).

6 to 8 are exemplary views for explaining an image stitching method according to some embodiments of the present disclosure.

As shown in FIG. 6 , the control device 10 may merge a plurality of images 41 and 42 in which raw materials are photographed through an image stitching technique. Specifically, the control device 10 matches the feature points 411 and 413 extracted from the first image 41 with the feature points 421 and 422 extracted from the second image 42 , and the matched feature points A merged image 43 may be generated by stitching the two images 41 and 42 based on (411 and 421 and 412 and 422).

On the other hand, in order for the two images 41 and 42 to be stitched (merged) accurately, it is important that the key point extraction and the key point matching be performed accurately. Hereinafter, a keypoint extraction method and a keypoint matching method according to embodiments of the present disclosure will be described in detail.

As shown in FIG. 7 , the control device 10 may detect an edge in the raw image 44 and determine a reference pixel 451 in a pixel area (e.g. 45) constituting the edge. For example, the reference pixel 451 may be determined as a pixel positioned at the leftmost and uppermost positions (or the rightmost and uppermost, leftmost and lowermost, etc.), but is not limited thereto. The number of reference pixels 451 may be one or plural. For reference, a dotted line on the right side of FIG. 7 means a pixel.

Next, the control device 10 may search for edge pixels adjacent to each other in different directions from the reference pixel 451 . For example, as shown, a search is performed from the reference pixel 451 in a first direction (refer to sub-edge 452), a search is also performed in a second direction (refer to sub-edge 453), and in a third direction. A figure search may also be performed (see sub-edge 454). Accordingly, the edge detected in the raw image 44 may be divided into a plurality of sub-edges 452 to 454 .

The search for adjacent edge pixels may be continuously performed for each sub-edge 452 to 454 . For example, as shown in FIG. 8 , the control device 10 may search for edge pixels (e.g. 455 to 458) constituting the sub-edge 454 in the illustrated numerical order. Then, the control device 10 determines the location information of the pixel 456 in which branching occurs, the end pixel (eg 457) of the sub-edge 454, and the pixel 458 in which the search direction is changed, and the corresponding pixels 456 to 458. The search direction of may be stored as search information of the corresponding sub-edge 454 .

Next, the control device 10 may select a feature point of the corresponding raw image 44 from the pixels stored in the search information of the sub-edges 452 to 454 . For example, the branch pixel 456 and the end pixel 457 may be selected as feature points of the corresponding raw image 44 .

Matching between the feature points may be performed based on search information of the sub-edges (e.g. 452 to 454). Specifically, the control device 10 may perform keypoint matching by comparing search information of sub-edges (e.g. 452 to 454) to which the keypoint of the two images belongs. In other words, the control device 10 compares the location information of the feature point stored in the search information, the search direction, the distance between the feature points, etc. to determine whether the two sub-edges (ie, the sub-edges of the two images) match or the feature points on the two sub-edges. It can be determined whether these match.

So far, the material inspection process according to some embodiments of the present disclosure has been described with reference to FIGS. 3 to 8 . As described above, a raw material suitable for upcycling may be selected through the material inspection process, and thus the quality of the manufactured product may be improved. In addition, the upcycling process can be automated by performing material inspection through image analysis of raw materials without human intervention. In addition, by merging a plurality of material images through the image stitching technique and extracting state information of raw materials from the merged images, the accuracy of the material inspection process can be improved.

Hereinafter, a machining process according to some embodiments of the present disclosure will be described with reference to FIGS. 9 to 11 .

9 is an exemplary flowchart illustrating a machining process according to some embodiments of the present disclosure. However, this is only a preferred embodiment for achieving the purpose of the present disclosure, and it goes without saying that some steps may be added or deleted as needed.

As shown in FIG. 9 , the processing process according to the present embodiment may start in step S21 of determining a component matching a raw material by inquiring a product DB. Here, the component may mean a part constituting the product. For example, the control device 10 may determine a component to be matched for each raw material by comparing the specification information of the component stored in the product DB and the state information (e.g. quality information, specification information) of the raw material. As a more specific example, when the material type of the specific component is the same as the raw material and the size of the specific component is smaller than or equal to the raw material, the control device 10 may determine the specific component as a matching component of the raw material. As another example, even if the size of a specific component is larger than the raw material, when the corresponding raw material is bonded to another raw material, the control device 10 may determine the specific component as the matching component if it can be equal to or larger than the specific component. there is.

In step S22, it is determined whether processing is necessary. For example, the control device 10 may compare the specifications of the raw material and the matching component to determine whether the raw material requires processing such as cutting or bonding.

In step S23, in response to determining that machining is necessary, machining may be performed according to the specification of the matching component. For example, as shown in FIG. 10 , the control device 10 may process the raw materials 22 to 24 according to the specifications of the matching component by controlling the cutting equipment 17 . Also, as shown in FIG. 11 , the control device 10 may join the processed materials 25 to 27 by controlling the bonding facility 18 , and as a result, the product 28 can be manufactured. there is. As described above, the cutting process and the bonding process may be repeatedly performed regardless of the order. For example, the control device 10 may repeatedly perform the cutting process and the joining process until the manufactured product 28 satisfies the reference specification information of the product DB (eg, reference specification information of a component or product).

Meanwhile, according to some embodiments of the present disclosure, the control device 10 derives a cutting path and/or splicing path based on the shortest path algorithm, and the cutting equipment 17 according to the derived cutting path and/or splicing path. ) and/or the bonding facility 18 . Accordingly, equipment control can be performed more efficiently, and costs for processing equipment (eg, power consumption and time costs caused by inefficient path movement of the cutting edge, etc.) can be reduced. It will be described in more detail with reference to the example shown in FIG. 12 .

It is assumed that cutting areas 51 to 53 as shown in FIG. 12 are set in the raw material 50 . The cutting areas 51 to 53 may be set according to specifications (e.g. shape, size, etc.) of the matching component. As shown, each of the cutting areas 51 to 53 may be a line area 51 , 52 or a face area 53 . In this case, the control device 10 may generate the connection graph 60 having points 511 to 531 (e.g. vertices) on each of the cutting regions 51 to 53 as vertices. If the connected graph cannot be generated (ie, the cutting areas are not connected), the control device 10 connects the points 511 to 531 on the cutting areas 51 to 53 (see trunk line 61 ). ) to create the connection graph 60 . Next, the control device 60 derives the shortest path from the connection graph 60 according to the shortest path algorithm (eg Dijkstra's algorithm, Bellman-Ford's algorithm, etc.), and sets the derived shortest path as a cutting path to cut equipment (17) can be controlled. In this case, the weights of the trunk lines constituting the connection graph 60 may be the same as or different from each other. For example, edges within the cutting areas 51 to 53 may have relatively small (or high) weights, and edges outside the cutting areas (eg, 61 ) may have relatively high (or low) weights.

The joining path can also be derived in a similar way to the cutting path. In other words, the control device 10 may generate a connection graph having points (e.g. vertices) on the junction region as vertices, derive a shortest path from the generated connection graph, and use it as a junction path.

So far, the machining process according to some embodiments of the present disclosure has been described with reference to FIGS. 9 to 12 . As described above, by deriving a cutting path and/or a joining path based on the shortest path algorithm, the efficiency of the machining process may be greatly improved.

Hereinafter, an exemplary computing device 70 capable of implementing the control device 10 according to some embodiments of the present disclosure will be described.

13 is an exemplary hardware configuration diagram illustrating the computing device 70 .

As shown in FIG. 13 , the computing device 70 loads one or more processors 71 , a bus 73 , a communication interface 74 , and a computer program 76 executed by the processor 71 . It may include a memory 72 and a storage 75 for storing the computer program (76). However, only the components related to the embodiment of the present disclosure are illustrated in FIG. 13 . Accordingly, those skilled in the art to which the present disclosure pertains can see that other general-purpose components other than the components shown in FIG. 13 may be further included. That is, the computing device 70 may further include various components in addition to the components shown in FIG. 13 . Also, in some cases, the computing device 70 may be configured in a form in which some of the components illustrated in FIG. 13 are omitted. Hereinafter, each component of the computing device 70 will be described.

The processor 71 may control the overall operation of each component of the computing device 70 . The processor 71 includes at least one of a central processing unit (CPU), a micro processor unit (MPU), a micro controller unit (MCU), a graphic processing unit (GPU), or any type of processor well known in the art of the present disclosure. may be included. In addition, the processor 71 may perform an operation on at least one application or program for executing the operation/method according to the embodiments of the present disclosure. Computing device 70 may include one or more processors.

Next, the memory 72 may store various data, commands and/or information. Memory 72 may load one or more computer programs 76 from storage 75 to execute operations/methods according to embodiments of the present disclosure. The memory 72 may be implemented as a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

Next, the bus 73 may provide a communication function between the components of the computing device 70 . The bus 73 may be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

Next, the communication interface 74 may support wired/wireless Internet communication of the computing device 70 . In addition, the communication interface 74 may support various communication methods other than Internet communication. To this end, the communication interface 74 may be configured to include a communication module well known in the art to which the present disclosure pertains.

In turn, the storage 75 may non-temporarily store one or more computer programs 76 . The storage 75 is a non-volatile memory, such as a read only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, a hard disk, a removable disk, or well in the art to which the present disclosure pertains. It may be configured to include any known computer-readable recording medium.

Next, the computer program 76 may include one or more instructions that, when loaded into the memory 72 , cause the processor 71 to perform an operation/method according to embodiments of the present disclosure. That is, the processor 71 may perform the operation/method according to the embodiments of the present disclosure by executing the one or more instructions.

For example, the computer program 76 analyzes an image in which the target material is photographed to determine the suitability for upcycling of the target material, and in response to the suitability determination, determines the component of the product matching the target material and the determined It may include instructions to perform an operation of controlling the processing equipment so that the target material is processed according to the specification of the component. In this case, the control device 10 according to some embodiments of the present disclosure may be implemented through the computing device 70 .

The technical idea of the present disclosure described with reference to FIGS. 1 to 13 may be implemented as computer-readable codes on a computer-readable medium. The computer-readable recording medium may be, for example, a removable recording medium (CD, DVD, Blu-ray disk, USB storage device, removable hard disk) or a fixed recording medium (ROM, RAM, computer-equipped hard disk). can The computer program recorded on the computer-readable recording medium may be transmitted to another computing device through a network such as the Internet and installed in the other computing device, thereby being used in the other computing device.

In the above, even though all components constituting the embodiment of the present disclosure are described as being combined or operated in combination, the technical spirit of the present disclosure is not necessarily limited to this embodiment. That is, within the scope of the present disclosure, all of the components may operate by selectively combining one or more.

Although acts are shown in a particular order in the drawings, it should not be understood that the acts must be performed in the specific order or sequential order shown, or that all illustrated acts must be performed to obtain a desired result. In certain circumstances, multitasking and parallel processing may be advantageous. Moreover, the separation of the various components in the embodiments described above should not be construed as necessarily requiring such separation, and the described program components and systems may generally be integrated together into a single software product or packaged into multiple software products. It should be understood that there is

Although embodiments of the present disclosure have been described above with reference to the accompanying drawings, those of ordinary skill in the art to which the present disclosure pertains may practice the present disclosure in other specific forms without changing the technical spirit or essential features. can understand that there is Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. The protection scope of the present disclosure should be interpreted by the following claims, and all technical ideas within the equivalent range should be interpreted as being included in the scope of the technical ideas defined by the present disclosure.

Claims (11)

A method of upcycling waste leather and fragmented leather scrap material based on edge detection and feature point extraction and matching of material images performed by a computing device that controls process equipment, comprising:
analyzing the photographed image of the target material to determine suitability for upcycling of the target material;
in response to the conformance determination, determining a component of the product that matches the target material; and
Controlling the process equipment so that the target material is processed according to the determined specification of the component,
The photographed image includes a first image in which at least a partial area of the target material is photographed and a second image in which at least another partial area of the target material is photographed,
The step of determining suitability for upcycling includes:
a material image merging step of merging the first image and the second image through an image stitching technique so that the entire area of the target material is included in the merged image; and
Including; a merged image analysis step of analyzing the merged image;
The raw image merging step is performed by matching feature points after edge detection in each of the first image and the second image,
The material image merging step is:
dividing the edge of the first image into a plurality of first sub-edges by detecting an edge in the first image and searching pixel areas constituting the edge of the first image in different directions from a reference pixel;
dividing an edge of the second image into a plurality of second sub-edges by detecting an edge in the second image and searching pixel regions constituting the edge of the second image in different directions from a reference pixel;
matching the feature points on the first plurality of sub-edges with the feature points on the second plurality of sub-edges by comparing search directions; and
Comprising the step of merging the first image and the second image based on the matched feature point,
The feature points on the first plurality of sub-edges include pixels in which branching occurs during search,
The process equipment includes a cutting equipment,
The step of controlling the process equipment includes controlling the cutting equipment,
The step of controlling the cutting equipment comprises:
setting a plurality of cutting areas for the target material according to the determined specification of the component;
generating a connection graph having a plurality of points on the set cutting regions as vertices;
deriving a shortest path from the connected graph by applying a shortest path algorithm; and
Cutting the target material according to the derived shortest path; Upcycling method of waste leather and fragmented leather scrap material based on edge detection and feature point extraction and matching of the material image, characterized in that it comprises.
According to claim 1,
The step of determining suitability for upcycling includes extracting the state information of the target material and then determining the upcycling suitability of the target material based on the extracted state information,
The state information is an upcycling method of waste leather and fragmented leather scrap material based on edge detection and feature point extraction and matching of the material image, including information on at least one of contamination level, perforation presence, and size.
3. The method of claim 2,
The pollution degree is measured through a CNN (Convolutional Neural Network)-based deep learning model trained to detect a contaminated object, and an upcycling method of waste leather and fragmented leather scrap material based on edge detection and feature point extraction and matching of the material image.
3. The method of claim 2,
The process equipment further comprises a washing equipment,
The step of controlling the process equipment further comprises the step of controlling the washing equipment based on the degree of contamination, an upcycling method of waste leather and fragmented leather scrap material based on edge detection and feature point extraction and matching of a material image.
According to claim 1,
The process equipment further comprises a sorting equipment,
The controlling of the process equipment further comprises controlling the classification equipment so that the target material is discarded in response to the non-conformity determination, waste leather and fragmented leather scraps based on edge detection and feature point extraction and matching of the material image How to upcycle materials.
delete delete delete According to claim 1,
The process equipment further comprises a bonding equipment,
Controlling the process equipment comprises:
Lung based on edge detection and feature point extraction and matching of the material image, further comprising; after deriving a bonding path based on the determined specification of the component or the product, controlling the bonding facility according to the derived bonding path A method of upcycling leather and shredded leather scrap materials.
delete delete

Images