Method and apparatus for analyzing iron scrap through image segmentation

Abstract

To provide a method for improving the accuracy of analysis results on a plurality of regions included in a loaded state image, and reducing the time required, and an iron scrap analysis apparatus.SOLUTION: A method includes the steps of: receiving, by a receiving unit of an iron scrap analysis device, a loaded state image of a loading device loaded with iron scraps; determining, by a processor, a target region including the iron scraps in the loaded state image; simplifying the target region to convert the simplified target region into a rectangular region; determining first and second lengths representing lengths of two different sides of the rectangular region, the second length greater than the first length; determining the number of segmentations of the target region based on a quotient obtained by dividing the second length by the first length; segmenting the loaded state image based on the number of segmentations to generate a plurality of segmented images; and providing a result of analyzing the iron scraps loaded on the loading device based on image analysis on the plurality of segmented images.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The technical field of the present disclosure relates to a method for providing an image analysis result for an article loaded on a loading equipment or the like, and more particularly to a technical field of a method for dividing a total area including the loaded article and providing an image analysis result for a plurality of divided areas.

Background Art

[0002] Recently, due to the increase in the logistics industry, it is a fact that many loading equipments for loading various articles or loading articles to move them from one place to another are widely used. However, although a plurality of articles loaded on the loading equipment can be managed or loaded according to the type of product or standard by the judgment of the operator, it may be difficult to check this every time. Therefore, a segmentation method may be used to monitor the image of each area by dividing the entire area of the loading equipment on which a plurality of articles are loaded. However, when the entire image is determined as an image analysis area and the image is analyzed during the segmentation process, there are limitations that the accuracy may be reduced or the time required for analysis may increase. In addition, when the image is divided into one or more areas and the image is analyzed, in the case of an article placed in each boundary area, there are limitations that the article may be included in duplicate in two areas or one article may be divided and analyzed. Therefore, it is necessary to provide a service that can provide a more accurate image analysis result by providing an image analysis method and system that can solve such limitations of analysis errors.

Prior Art Documents

Patent Documents

[0003] Korean Patent Publication No. 10-2011-0078566 (July 7, 2011), Efficient article loading position detection system using digital video recognition

Summary of the Invention

Problems to be Solved by the Invention

[0004] The problem to be solved by the present disclosure is to determine a method for dividing a loaded state image so that the accuracy of the analysis results for a plurality of regions included in the loaded state image can be improved in providing image analysis results, and to provide a service for providing analysis results for an image divided based on the determined division method.

[0005] The problem to be solved by the present disclosure is not limited to the above technical problems, and there can be other technical problems.

Means for Solving the Problem

[0006] As a technical means for achieving the above-described technical problem, a method for analyzing iron scrap through image division according to a first aspect of the present disclosure includes: a receiving unit obtaining a loaded state image captured in a state where iron scrap is loaded on loading equipment; a processor determining a target region including the iron scrap in the loaded state image; the processor simplifying the target region and converting it into a rectangular shape; the processor determining a first length indicating lengths of two different sides of the converted rectangle and a second length greater than the first length; the processor determining the number of divisions of the target region based on a quotient obtained by dividing the second length by the first length; the processor dividing the loaded state image based on the number of divisions to obtain a plurality of divided images; and the processor providing an analysis result for the iron scrap loaded on the loading equipment based on image analysis of the plurality of divided images.

[0007] Also, in the step of determining the number of divisions, when the value of the quotient is N, the processor can determine the number of divisions by a value that is 1 less than twice N.

[0008] In addition, the step of obtaining the plurality of divided images may include a step in which the processor obtains N divided images that are both horizontal and vertical and have the first length and do not overlap with each other, and a step in which the processor obtains N - 1 divided images that include the boundary lines of the N divided images and do not overlap with each other.

[0009] In addition, each of the N - 1 divided images may overlap with one or two of the N divided images.

[0010] In addition, among the boundary lines of the terminal divided image located at any one end of the N divided images, the boundary line of the side surface where there is an adjacent divided image may be included in the N - 1 divided images, and the boundary line of the side surface where there is no adjacent divided image may not be included in the N - 1 divided images.

[0011] In addition, the method may further include a step in which the processor determines the interval between the plurality of divided images based on the remainder obtained by dividing the second length by the first length.

[0012] In addition, the interval between the N divided images may be determined based on the value obtained by dividing the remainder by N - 1.

[0013] In addition, the step in which the processor obtains the plurality of divided images may include a step in which the processor obtains one or more remainder divided images obtained by dividing the remainder by N - 1; a step in which the processor updates the area of each of the remainder divided images in the intermediate area between the N - 1 divided images indicating the interval between the N divided images; and a step in which the processor obtains N - 1 divided images that include the center line of the remainder divided images and do not overlap with each other.

[0014] Also, when the length of the first one is greater than twice the third length indicating the horizontal length of one or more remaining divided images obtained by dividing the remainder by N - 1 in the step of obtaining the plurality of divided images, the step of determining the interval between at least one of the N divided images to be twice the third length; the step of obtaining one or more remaining combined images by combining two consecutive images from the left terminal divided image to the right terminal divided image of the one or more remaining divided images by the processor; the step of the processor updating the region of each of the remaining combined images and the region of the remaining divided images with a part of the regions between the N - 1 divided images indicating the interval between the N divided images; and the step of the processor obtaining less than N - 1 non - overlapping divided images including the center line of the remaining combined image or the center line of the remaining divided image; are included, and the interval between the divided images corresponding to the regions excluded from the part of the regions between the N - 1 divided images can be updated to a value corresponding to 0.

[0015] Also, the step of obtaining the remaining combined images may include the step of the processor obtaining one or more remaining combined images by combining two consecutive images from the right terminal divided image to the left terminal divided image of the one or more remaining divided images.

[0016] An iron scrap analysis apparatus through image segmentation according to a second aspect of the present disclosure includes: a receiving unit that acquires a loaded state image captured in a state where iron scrap is loaded on loading equipment; and a processor that determines a target region including the iron scrap in the loaded state image, simplifies the target region, converts it into a rectangular shape, determines a first length indicating lengths of two different sides of the converted rectangle, and a second length greater than the first length, determines the number of divisions of the target region based on a quotient obtained by dividing the second length by the first length, divides the loaded state image based on the number of divisions to obtain a plurality of divided images, and provides an analysis result for the iron scrap loaded on the loading equipment based on image analysis of the plurality of divided images.

[0017] Further, when the value of the quotient is N, the processor can determine the number of divisions with a value that is 1 less than twice N.

[0018] Further, the processor can obtain N divided images where both the horizontal and vertical sides are the first length and do not overlap with each other, and can obtain N - 1 divided images that include the boundary lines of the N divided images and do not overlap with each other.

[0019] Further, each of the N - 1 divided images can overlap with one or two of the N divided images.

[0020] According to a third aspect of the present disclosure, a computer-readable non-transitory recording medium on which a program for implementing the method of the first aspect is recorded can be provided.

Advantages of the Invention

[0021] According to an embodiment of the present disclosure, by using a general segmentation technique, instead of extracting the area of the loaded articles in the entire image at once, the image is divided into images of a size with high image analysis efficiency and image analysis is performed, so that highly accurate image analysis results can be obtained, and the required time is reduced.

[0022] In addition, when performing image analysis through image segmentation according to the present invention, since highly accurate analysis is possible even for the loaded articles included in the segmentation boundary, there is an advantage that the problem of misjudgment of grades / items due to segmentation can be solved.

[0023] In addition, when performing image analysis through a certain segmentation size, even if there is a remaining area, the efficiency of image analysis can be improved in that image analysis can be performed by updating the position of the image of the blank area.

[0024] The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

Brief Description of the Drawings

[0025]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Embodiments for Carrying Out the Invention

[0026] Advantages, features, and methods for achieving them in the present disclosure will become clear by referring to the embodiments described in detail below together with the attached drawings. However, the present disclosure is not limited to the embodiments disclosed below and can be embodied in various different forms, provided that these embodiments make the disclosure complete and are provided to fully inform those of ordinary skill in the relevant technical field of the scope of the present disclosure.

[0027] The terms used in this specification are for the purpose of describing examples and are not intended to limit the present disclosure. In this specification, the singular form also includes the plural form unless otherwise specified in the context. The terms "comprises" and / or "comprising" used in the specification do not exclude the presence or addition of one or more other components in addition to the recited components. Throughout the specification, the same reference numerals refer to the same components, and "and / or" includes each and all combinations of the recited components. Although terms such as "first", "second", etc. are used to describe various components, these components are of course not limited by these terms. These terms are merely used to distinguish one component from another. Therefore, it is of course possible that the first component referred to below may be the second component within the technical concept of the present disclosure.

[0028] Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used in a meaning commonly understood by those of ordinary skill in the relevant technical field. Also, terms defined in commonly used dictionaries are not ideally or overly interpreted unless specifically defined otherwise.

[0029] Spatially relative terms such as "below", "beneath", "lower", "above", "upper", etc. can be used to easily describe the correlation between one component and another as shown in the drawings. Spatially relative terms should be understood to include terms in different directions of the components in addition to the directions shown in the drawings during use or operation. For example, when the components shown in the drawings are turned over, the components described as "below" or "beneath" another component may be placed "above" the other component. Therefore, the exemplary term "below" can include all directions of below and above. The components can also be oriented in other directions, and accordingly, the spatially relative terms can be interpreted according to the orientation.

[0030] Hereinafter, embodiments will be described in detail with reference to the drawings.

[0031] FIG. 1 is a block diagram schematically illustrating the configuration of an iron scrap analysis apparatus 100 through image segmentation according to an embodiment of the present disclosure.

[0032] Referring to FIG. 1, the iron scrap analysis apparatus 100 can include a receiving unit 110 and a processor 120.

[0033] According to one embodiment, the receiving unit 110 can acquire a loaded state image captured in a state where iron scrap is loaded on the loading equipment.

[0034] The processor 120 according to one embodiment can determine a target region including iron scrap in the loaded state image. Further, the processor 120 can simplify the target region and convert it into a rectangular shape. Further, the processor 120 can determine a first length indicating the lengths of two different sides of the converted rectangle and a second length larger than the first length. Further, the processor 120 can determine the number of divided parts of the target region based on the quotient obtained by dividing the second length by the first length. Further, the processor 120 can divide the loaded state image based on the number of divided parts to obtain a plurality of divided images. Further, the processor 120 can provide an analysis result for the iron scrap loaded on the loading equipment based on image analysis for the plurality of divided images.

[0035] Also, it should be noted that the iron scrap analysis apparatus 100 through image segmentation can be combined by various conventional network combinations such as the Internet or a mobile communication network in the process of acquiring a loaded state image by the receiving unit 110, determining a target region by the processor 120, determining the number of divided parts of the target region to obtain a plurality of divided images, and providing an image analysis result based on the divided images, and there is no special restriction on this.

[0036] In addition to this, those with ordinary knowledge in the relevant technical field can understand that in addition to the components illustrated in FIG. 1, other general-purpose components can be further included in the iron scrap analysis apparatus 100 through image segmentation. For example, the iron scrap analysis apparatus 100 through image segmentation can further include a memory (not shown) for storing a loaded state image, a target area, a plurality of divided image information, etc., and can further include a transmission unit (not shown) for providing an image analysis result or a display unit (not shown) for displaying the image analysis result. Or when following other embodiments, those with ordinary knowledge in the relevant technical field can understand that some of the components illustrated in FIG. 1 can be omitted.

[0037] The iron scrap analysis apparatus 100 through image segmentation according to an embodiment can be used by a user and can be linked with all types of handheld wireless communication devices equipped with a touch screen panel, such as a mobile phone, a smartphone, a PDA (Personal Digital Assistant), a PMP (Portable Multimedia Player), a tablet PC, etc. In addition to this, it can also be included in or linked with devices provided with a base on which an application can be installed and executed, such as a desktop PC, a tablet PC, a laptop PC, and an IPTV including a set-top box.

[0038] The iron scrap analysis apparatus 100 through image segmentation can be implemented on a terminal such as a computer that operates through a computer program for implementing the functions described in this specification.

[0039] The iron scrap analysis apparatus 100 through image segmentation according to an embodiment can include, but is not limited to, a system (not shown) and a related server (not shown) that provide an image analysis result for the iron scrap. A server according to an embodiment can assist an application that provides a service for providing image analysis result information for the iron scrap.

[0040] Hereinafter, an example will be mainly described in which the iron scrap analyzer 100 through image segmentation according to an embodiment independently obtains and provides an image analysis result by a preset image segmentation method. However, as described above, it may be performed through cooperation with a server. That is, the iron scrap analyzer 100 through image segmentation according to an embodiment and the server can be integrally implemented in terms of their functions, and the server may be omitted, and it can be understood that it is not limited to any one embodiment.

[0041] In one embodiment, the iron scrap analyzer 100 and the server can be linked, and the configuration for providing an analysis result by performing an image segmentation process and an analysis result providing process can be performed by the server or by the iron scrap analyzer 100. For example, the iron scrap analyzer 100 can operate as a server, and hereinafter, it will be uniformly described by the iron scrap analyzer 100.

[0042] FIG. 2 is a flowchart showing each stage in which an image analysis result is provided through the iron scrap analyzer 100 through image segmentation according to an embodiment of the present disclosure.

[0043] Referring to step S210, the iron scrap analyzer 100 according to an embodiment can obtain a loaded state image that is imaged while iron scrap is loaded on the loading equipment. For example, the iron scrap analyzer 100 can obtain a loaded state image that is photographed in a state of looking down on the loading equipment from above through a camera.

[0044] Referring to step S220, the iron scrap analyzer 100 according to an embodiment can determine a target area including the iron scrap in the loaded state image. The target area can include an area other than the loading equipment and an area not including the iron scrap in the loaded state image photographed by the camera. That is, the iron scrap analyzer 100 can determine the area including the iron scrap for performing image analysis as the target area.

[0045] Referring to step S230, the iron scrap analyzer 100 according to an embodiment can simplify the target area and convert it into a rectangular shape. Generally, the loading equipment can correspond to a rectangular shape whose horizontal length is longer than its vertical length. Therefore, the iron scrap analyzer 100 can convert the area to be image-analyzed into a rectangular shape by including the target area including the iron scrap.

[0046] Referring to step S240, the iron scrap analyzer 100 according to an embodiment can determine a first length indicating the lengths of two different sides of the converted rectangle and a second length greater than the first length. In one embodiment, the iron scrap analyzer 100 can determine the vertical length of the converted rectangle as the first length and the horizontal length as the second length.

[0047] Referring to step S250, the iron scrap analyzer 100 according to an embodiment can determine the number of divisions of the target area based on the quotient obtained by dividing the second length by the first length. The iron scrap analyzer 100 can determine the number of divisions to be a number greater than the value corresponding to the quotient obtained by dividing the second length (indicating the horizontal length of the converted rectangle) by the first length (indicating the vertical length). For example, the iron scrap analyzer 100 can obtain the number of divisions corresponding to the quotient obtained by dividing the second length by the first length, and can further obtain the number of divisions corresponding to a value smaller than the quotient.

[0048] Referring to step S260, the iron scrap analysis apparatus 100 according to an embodiment can divide the loaded state image based on the number of divisions to obtain a plurality of divided images. For example, when the quotient value of the iron scrap analysis apparatus 100 according to an embodiment is N, the number of divisions can be determined by a value that is 1 less than twice N. That is, the formula 2N - 1 can be applied to the number of divisions, which can be a formula derived from N+(N - 1). Also, this can be a formula corresponding to the case where there is no remainder. For example, when there is no remainder and the quotient value is N, the loaded state image can be preferentially divided into N images according to the quotient value. That is, both the horizontal and vertical lengths are the first length according to the quotient value, and N non-overlapping divided images can be obtained. Also, after the iron scrap analysis apparatus 100 obtains N images, it can obtain N - 1 non-overlapping divided images including the boundary lines of the N divided images. Therefore, the number of divisions of the target area can be determined to be 2N - 1. Also, when there is a remainder based on the quotient obtained by dividing the second length by the first length, the divided image acquisition process for the remainder area can be further performed. This will be described in more detail through FIGS. 3 to 9.

[0049] Referring to step S270, the iron scrap analysis apparatus 100 according to an embodiment can provide an analysis result for the iron scrap loaded on the loading equipment based on image analysis of a plurality of divided images. The iron scrap analysis apparatus 100 can perform image analysis on each of the plurality of divided images obtained in steps S210 to S260, and can provide the image analysis results obtained for each of the plurality of divided images. The iron scrap analysis apparatus 100 can provide the image analysis result information to the user terminal, and may display each of the plurality of divided images.

[0050] FIG. 3 is a drawing for explaining an example in which an incorrect image analysis result is obtained based on image division by the iron scrap analysis apparatus 100 according to an embodiment of the present disclosure.

[0051] Referring to FIG. 3, the iron scrap analyzer 100 according to an embodiment can obtain one or more divided images divided by one or more boundary lines. However, as shown in the drawings, when obtaining one or more divided images separated by the boundary line as a boundary, there are limitations that undetected iron scraps may exist in the peripheral area of the boundary line, or one iron scrap may be separated and detected.

[0052] FIG. 4 is a drawing showing an example in which the iron scrap analyzer 100 according to an embodiment of the present disclosure re-obtains an image analysis result for a region corresponding to an incorrect image analysis result.

[0053] Referring to FIG. 4, the iron scrap analyzer 100 according to an embodiment can re-obtain the image analysis result centered on the boundary line in order to re-perform the image analysis for the peripheral area of the boundary line in order to overcome the limitation points where undetected iron scraps may exist in the peripheral area of the boundary line or one iron scrap may be separated and detected. For example, by further performing image division with a rectangle including the peripheral area of the boundary line, the image of the corresponding area can be obtained and the image analysis result for the corresponding area can be re-obtained. This can be described in more detail through FIG. 5.

[0054] FIG. 5 is a drawing for explaining an example of performing image analysis by image division on an area excluding the rectangular remaining area obtained based on the loaded state image by the iron scrap analyzer 100 according to an embodiment of the present disclosure.

[0055] Referring to FIG. 5, when the second length is divided by the first length and there is no remainder, N divided images with horizontal and vertical lengths corresponding to the quotient being the first length can be obtained, and N - 1 divided images including the boundary lines of the N divided images can be obtained. That is, as shown at the upper end of the drawing, N divided images (in FIG. 5, N corresponds to an example situation of 4) can be obtained, and as shown at the lower end of the drawing, N - 1 divided images (in FIG. 5, N - 1 corresponds to 3) can be obtained. Referring to the drawing, each of the N - 1 divided images can overlap with one or two of the N divided images. That is, the N - 1 divided images can include a part of the divided images on both sides centered on the boundary line. Also, among the boundary lines of the terminal divided image located at any one end of the N divided images, the boundary line on the side where there is an adjacent divided image is included in the N - 1 divided images, and the boundary line on the side where there is no adjacent divided image may not be included in the N - 1 divided images. That is, referring to the N divided images shown at the upper end with reference to the drawing, in the case of a boundary line where there is no horizontally adjacent divided image among the boundary lines included in the leftmost or rightmost divided image, it is not included in the N - 1 divided images, and in the case of a boundary line where there is a horizontally adjacent divided image, it may be included in the N - 1 divided images. Referring to the N - 1 divided images shown at the lower end with reference to the drawing, it can be confirmed that only the boundary lines on the side where there is an adjacent divided image excluding the boundary lines on the side where there is no adjacent divided image among the boundary lines of the terminal divided image are included in the N - 1 divided images. In one embodiment, the N - 1 divided images can correspond to divided images with horizontal and vertical lengths including the boundary line being the first length. In one embodiment, when obtaining the divided image, generally the horizontal and vertical lengths are determined to be the first length corresponding to the vertical length of the converted rectangle and can be obtained with an image corresponding to a square. However, depending on multiple situations, it may also be obtained with an image corresponding to a rectangle with a horizontal length less than the first length other than an image corresponding to a square with horizontal and vertical lengths corresponding to the first length.For example, in another embodiment, the iron scrap analyzer 100 can determine one iron scrap located outermost in both lateral directions centered on the boundary line among the positions of at least one undetected iron scrap included in one or more boundary line peripheral regions and the positions of at least one iron scrap existing across the boundary line. By obtaining the length between the end point of the iron scrap located outermost centered on the boundary line and the boundary line based on the positions of one or more iron scraps and determining a length twice the obtained length as the horizontal length, a rectangular image with different horizontal and vertical lengths may be obtained as a divided image. That is, the iron scrap analyzer 100 may obtain a rectangular image excluding regions other than unnecessary regions by obtaining the positions of the iron scraps as a divided image.

[0056] FIG. 6 is a drawing for explaining an example in which the iron scrap analyzer 100 according to an embodiment of the present disclosure determines the intervals between N-1 divided images based on the surplus regions.

[0057] Referring to FIG. 6, the iron scrap analyzer 100 according to an embodiment can determine the interval between a plurality of divided images based on the remainder obtained by dividing the second length by the first length. In one embodiment, the interval between the divided images can mean the interval between N divided images. In one embodiment, the interval between N divided images can be determined based on the value obtained by dividing the remainder by N - 1. For example, the remainder can mean a region whose horizontal length is shorter than the first length. As shown in FIG. 6, when obtaining a plurality of divided images by the quotient of dividing the second length by the first length, the interval between N divided images can be determined based on the horizontal length S corresponding to the remaining remainder. By determining the length obtained by dividing the horizontal length S corresponding to the remainder by N - 1 as the interval between N divided images, the position of the image corresponding to the remainder can be updated. For example, the iron scrap analyzer 100 can obtain one or more remainder divided images obtained by dividing the remainder by N - 1. That is, the iron scrap analyzer 100 can obtain N - 1 remainder divided images by dividing the horizontal length S corresponding to the remainder by N - 1. The iron scrap analyzer 100 can update the region of each remainder divided image in the region between N - 1 divided images indicating the interval between the divided images. As shown in FIG. 6, the iron scrap analyzer 100 can update the position of each region so that the N - 1 remainder divided images obtained by dividing the remainder by N - 1 are located in the region between N - 1 divided images.

[0058] FIG. 7 is a drawing for explaining an example of performing image analysis by image division when there is a rectangular remainder region obtained by the iron scrap analyzer 100 according to an embodiment of the present disclosure based on a loaded state image.

[0059] Referring to FIG. 7, after the iron scrap analyzer 100 updates the positions of N - 1 remaining divided images, it can obtain N - 1 divided images that include the center lines of the remaining divided images and do not overlap with each other. That is, the iron scrap analyzer 100 can perform image analysis on the images corresponding to the remainders by obtaining N - 1 divided images of the regions corresponding to squares with the horizontal and vertical lengths being the first length with the center lines of the remaining divided images, and can provide the analysis results for the images of the regions corresponding to the remainders. In one embodiment, when the iron scrap analyzer 100 obtains N - 1 remaining divided images by dividing the horizontal length of the remainder by N - 1, undetected iron scraps may exist in the peripheral region of the boundary line where they are divided. Since the iron scraps are separated and detected, the intervals between the N divided images may be updated and determined differently.

[0060] FIG. 8 is a drawing for explaining an example in which the iron scrap analyzer 100 according to an embodiment of the present disclosure performs image analysis by updating the intervals between divided images by a first method.

[0061] Referring to FIG. 8, when the first length is greater than twice the third length indicating the horizontal length of one or more remainder divided images obtained by dividing the remainder by N - 1, the iron scrap analyzer 100 according to an embodiment can determine the interval between at least one or more of the N divided images to be twice the third length. Also, the iron scrap analyzer 100 can obtain one or more remainder combined images by combining two consecutive images from the left - hand terminal divided image to the right - hand terminal divided image of the one or more remainder divided images by the first method. Referring to FIG. 8, when the first length is greater than twice the third length, the iron scrap analyzer 100 according to an embodiment is N - 1 remainder divided images obtained by dividing S, which represents the horizontal length corresponding to the remainder in FIG. 6, by N - 1. Two consecutive images from the left can be obtained as remainder combined images, and at least one or more remainder combined images in which two images are combined according to the number N - 1 can be obtained. One single remainder divided image in which two images are not consecutive may also be obtained together. The iron scrap analyzer 100 can update the region of each remainder combined image and the remainder divided image region in a part of the intermediate region between N - 1 divided images indicating the interval between N divided images. As shown in FIG. 8, the iron scrap analyzer 100 updates a remainder combined image including two consecutive remainder divided images in a part of the intermediate region between N - 1 divided images, and can update one remainder divided image in which two remainder divided images are not consecutive in a part of the intermediate region between N - 1 divided images other than the region where the remainder combined image is located. Therefore, the iron scrap analyzer 100 can obtain less than N - 1 non - overlapping divided images including the center line of the remainder combined image or the center line of the remainder divided image. In one embodiment, since the remainder combined image includes consecutive remainder divided images, less than N - 1 divided images can be obtained by obtaining the divided images corresponding to a part of the intermediate region between N - 1 divided images.In addition, the iron scrap analyzer 100 can update the interval between divided images corresponding to the area excluded from a part of the area between N-1 divided images with a value corresponding to 0. Therefore, the iron scrap analyzer 100 can determine the interval between divided images in an area that is not the update position of the divided images to be 0, and can further obtain less than N-1 divided images corresponding to the update positions of the remaining divided images excluding the area where the interval between the divided images is 0. In FIG. 8, the remaining combined image is determined to be one, but it is not limited thereto, and it may be determined to be a plurality according to the number of N. Therefore, as in FIG. 7, N-1 divided images corresponding to the update positions of each of the remaining divided images are obtained, and as in FIG. 8, less than N-1 divided images corresponding to the update positions of each of the remaining combined images including two consecutive remaining divided images are further obtained. In the case where an undetected or one iron scrap is separated and detected in the remaining area, there is an effect that an image with higher accuracy can be obtained. This can be a process that can be further performed when an undetected or one iron scrap is separated and detected by dividing the remaining into one or more remaining divided images and obtaining the divided images.

[0062] FIG. 9 is a drawing for explaining an example in which the iron scrap analyzer 100 according to an embodiment of the present disclosure performs image analysis by updating the interval between divided images by a second method.

[0063] Referring to FIG. 9, an iron scrap analyzer 100 according to an embodiment can obtain one or more remaining combined images by combining two images that are continuous from the right - hand terminal divided image to the left - hand terminal divided image of one or more remaining divided images by a second method. In FIG. 8, if the remaining combined image is obtained by combining two images that are continuous from the left by the first method, then as in FIG. 9, the remaining combined image can be obtained by combining two images that are continuous from the right of the remaining divided images by the second method. Therefore, when undetected or one iron scrap is separated and detected horizontally on the left or right between a plurality of remaining divided images, there is an effect that divided images can be obtained so that all can be confirmed. As shown in FIG. 9, less than N - 1 divided images including the remaining combined images combined in the opposite direction to FIG. 8 can be obtained, and the interval between the divided images corresponding to the regions excluded from some of the intermediate regions between the N - 1 divided images can be updated to a value corresponding to 0. In one embodiment, through FIGS. 7 - 9, an example of obtaining a plurality of divided images by obtaining a square image including one or more remaining divided images or one or more remaining combined images has been described, but it is not limited thereto. As described above, a rectangular image may be obtained by determining the horizontal length to be shorter than the first length to obtain a plurality of divided images.

[0064] According to one embodiment, instead of extracting the area of the loaded articles in the overall image at once using general segmentation techniques, the image is divided into images of a size with high image analysis efficiency and image analysis is performed, thereby obtaining highly accurate image analysis results and having the effect of reducing the required time. Further, when performing image analysis through the image segmentation according to the present invention, since it is possible to perform highly accurate analysis even on the loaded articles included in the division boundary, there is an advantage that the problem of misjudgment of grades / items due to division can be solved. Even when there is a remaining area when performing image analysis through a certain division size, the efficiency of image analysis can be improved in that image analysis can be performed by updating the position of the image of the blank area.

[0065] Various embodiments of the present disclosure may be embodied in software including one or more instructions stored in a machine (e.g., a display device or a computer)-readable storage medium (e.g., a memory). For example, a processor (e.g., processor 220) of the machine may call and execute at least one of the one or more instructions stored from the storage medium. This enables the machine to be operated to perform at least one function by the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, "non-transitory" only means that the storage medium is a tangible device and does not include a signal (e.g., an electromagnetic wave), and this term does not distinguish between the case where data is stored semi-permanently in the storage medium and the case where it is stored temporarily.

[0066] According to one embodiment, the methods according to the various embodiments disclosed in the present disclosure may be provided included in a computer program product. The computer program product may be traded as a commodity between a seller and a purchaser. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) through an application store (e.g., Play StoreTM), or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a part of the computer program product may be at least temporarily stored or temporarily generated in a machine-readable storage medium such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0067] Although the present invention has been described with reference to the drawings illustrating the examples, it is not limited by the disclosed examples and the drawings. It will be understood that those having ordinary knowledge in the technical field related to this example can be embodied in a modified form without departing from the essential characteristics of the above description. Therefore, the disclosed method should be considered from an explanatory perspective rather than a limiting perspective. Even if the effects related to the configuration of the present invention are not explicitly described when explaining the examples, the effects that can be predicted by the corresponding configuration may also be recognized. The scope of the present invention is shown not in the above description but in the claims, and all differences within the equivalent scope should be construed as being included in the present invention.

Explanation of Reference Numerals

[0068] 100: Iron Scrap Analyzer 110: Receiver 120: Processor

Claims

1. In a method for analyzing iron scrap through image segmentation, a step of a receiving unit obtaining a loaded state image captured when iron scrap is loaded on a loading equipment; a step of a processor determining a target area including the iron scrap in the loaded state image; a step of the processor simplifying the target area and converting it into a rectangular shape; a step of the processor determining a first length indicating lengths of two different sides of the converted rectangle and a second length greater than the first length; a step of the processor determining the number of divisions of the target area based on a quotient obtained by dividing the second length by the first length; a step of the processor dividing the loaded state image based on the number of divisions to obtain a plurality of divided images; and a step of the processor providing an analysis result for the iron scrap loaded on the loading equipment based on image analysis for the plurality of divided images; A method comprising.

2. The step of determining the number of divisions is The method according to claim 1, wherein the processor determines the number of divisions by a value that is 1 less than twice N when the value of the quotient is N.

3. The step of obtaining the plurality of divided images is a step of the processor obtaining N divided images that are both horizontal and vertical and are the first length and do not overlap each other, and a step of the processor obtaining N−1 divided images that include the boundary lines of the N divided images and do not overlap each other; The method according to claim 2, comprising.

4. The method according to claim 3, wherein each of the N−1 divided images overlaps one or two of the N divided images.

5. Among the boundary lines of the terminal divided image located at any one end of the N divided images, the boundary line of the side where there is an adjacent divided image is included in the N−1 divided images, and the boundary line of the side where there is no adjacent divided image is not included in the N−1 divided images. The method according to claim 3.

6. The method according to claim 2, further comprising a step of the processor determining an interval between the plurality of divided images based on a remainder obtained by dividing the second length by the first length.

7. The method according to claim 6, wherein the interval between the N divided images is determined based on a value obtained by dividing the remainder by N−1.

8. The step of obtaining the plurality of divided images is the step in which the processor obtains one or more remainder divided images obtained by dividing the remainder by N - 1; the step in which the processor updates the area of each of the remainder divided images in an intermediate area between N - 1 divided images indicating the interval between the N divided images; and the step in which the processor obtains N - 1 divided images that include the center line of the remainder divided images and do not overlap with each other; The method according to claim 7, comprising:

9. The step of obtaining the plurality of divided images is the step in which the processor determines the interval between at least one of the N divided images to be twice the third length when the first length is greater than twice the third length indicating the horizontal length of one or more remainder divided images obtained by dividing the remainder by N - 1; the step in which the processor obtains one or more remainder combined images by combining two consecutive images from the left end divided image to the right end divided image of the one or more remainder divided images; the step in which the processor updates the area of each of the remainder combined images and the area of the remainder divided images in a partial area of the intermediate area between N - 1 divided images indicating the interval between the N divided images; and the step in which the processor obtains less than N - 1 divided images that include the center line of the remainder combined images or the center line of the remainder divided images and do not overlap with each other; including The interval between the divided images corresponding to the area excluded from the partial area of the intermediate area between the N - 1 divided images is updated to a value corresponding to 0. The method according to claim 6.

10. The step of obtaining the remainder combined image is the step in which the processor obtains one or more remainder combined images by combining two consecutive images from the right end divided image to the left end divided image of the one or more remainder divided images; The method according to claim 9, comprising:

11. In an iron scrap analyzer through image segmentation, a receiving unit that obtains a loaded state image captured in a state where iron scrap is loaded on a loading device; and determining a target area including the iron scrap in the loaded state image, simplifying the target area and converting it into a rectangular shape, Determine a first length indicating the lengths of two different sides of the transformed rectangle and a second length greater than the first length, Determine the number of divisions of the target area based on the quotient obtained by dividing the second length by the first length, Divide the loading state image based on the number of divisions to obtain a plurality of divided images, A processor that provides an analysis result for the iron scrap loaded on the loading equipment based on image analysis of the plurality of divided images; An iron scrap analysis device including.

12. The processor is When the value of the quotient is N, the iron scrap analysis device according to claim 11, wherein the number of divisions is determined by a value that is 1 less than twice N.

13. The processor is Both the horizontal and vertical directions are the first length, and N non-overlapping divided images are obtained, The iron scrap analysis device according to claim 12, wherein N - 1 non-overlapping divided images are obtained, including the boundary lines of the N divided images.

14. The iron scrap analysis device according to claim 13, wherein each of the N - 1 divided images overlaps one or two of the N divided images.

15. A computer-readable recording medium recording a program for causing a computer to execute the method according to any one of claims 1 to 10.

Images