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 image analysis results for items loaded on loading equipment, and to a method for dividing a total area including loaded items and providing image analysis results for a plurality of divided areas. [Background technology]

[0002] Recently, with the expansion of the logistics industry, loading equipment for loading various items or transporting items from one location to another is increasingly used. However, multiple items loaded on the loading equipment may be managed and loaded according to product or size based on the operator's judgment. However, it can be difficult to check this every time. Therefore, a segmentation method can be used to monitor the image of each area by dividing the entire area of ​​the loading equipment on which multiple items are loaded. However, when segmentation is performed by determining the entire image as the image analysis area and analyzing the image, there are limitations such as reduced accuracy and increased analysis time. Furthermore, when an image is divided into one or more areas and then analyzed, there are limitations such as items placed in boundary areas being included in both areas and being analyzed separately. Therefore, there is a need for a service that can provide more accurate image analysis results by providing an image analysis method and system that can resolve these limitations of analysis errors. [Prior art documents] [Patent documents]

[0003] Korean Patent Publication No. 10-2011-0078566 (2011.07.07) Efficient item loading position detection system using digital image recognition Summary of the Invention [Problem to be solved by the invention]

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

[0005] The problems to be solved by the present disclosure are not limited to the above technical problems, and other technical problems may exist. [Means for solving the problem]

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

[0007] In the step of determining the number of divisions, when the value of the quotient is N, the processor may determine the number of divisions as a value that is 1 less than twice N.

[0008] The step of acquiring the plurality of divided images may further include the step of the processor acquiring N divided images whose width and height are both the first length and which do not overlap each other, and the step of the processor acquiring N-1 divided images whose width and height include boundaries of the N divided images and which do not overlap each other.

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

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

[0011] The method may further include the step of: determining intervals between the plurality of divided images based on a remainder obtained by dividing the second length by the first length.

[0012] Furthermore, the spacing between the N divided images can be determined based on the remainder divided by N-1.

[0013] Further, the step of the processor obtaining the plurality of divided images may include the steps of obtaining one or more remainder divided images by dividing the remainder by N-1; updating the area of ​​each of the remainder divided images with an inter-area between the N-1 divided images indicating the interval between the N divided images; and obtaining N-1 divided images that include the center line of the remainder divided image and do not overlap each other.

[0014] Further, the step of obtaining the plurality of divided images may include the steps of: if the first length is greater than twice a third length indicating the horizontal length of one or more remainder divided images obtained by dividing the remainder by N-1, the processor determining the spacing between at least one of the N divided images to be twice the third length; the processor obtaining one or more remainder combined images by combining two consecutive images from the left terminal divided image to the right terminal divided image of the one or more remainder divided images; the processor updating the area of ​​each remainder combined image and the remainder divided image area with a portion of the inter-areas between the N-1 divided images indicating the spacing between the N divided images; and the processor obtaining less than N-1 divided images that do not overlap each other and include the center line of the remainder combined image or the center line of the remainder divided image; and the spacing between the divided images corresponding to areas excluded from the portion of the inter-areas between the N-1 divided images may be updated to a value corresponding to 0.

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

[0016] An apparatus for analyzing scrap iron through image segmentation according to a second aspect of the present disclosure may include: a receiving unit that acquires a loaded state image captured while scrap iron is loaded on loading equipment; and a processor that determines a target area including the scrap iron in the loaded state image, simplifies the target area to convert 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 a number of divisions of the target area based on a quotient obtained by dividing the second length by the first length, acquires a plurality of divided images by dividing the loaded state image based on the number of divisions, and provides an analysis result for the scrap iron loaded on the loading equipment based on image analysis of the plurality of divided images.

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

[0018] The processor may also obtain N divided images whose width and height are both the first length and which do not overlap each other, and obtain N-1 divided images whose width and height include the boundaries of the N divided images and which do not overlap each other.

[0019] Also, each of the N-1 divided images may overlap one or two of the N divided images.

[0020] According to a third aspect of the present disclosure, there is provided a computer-readable non-transitory recording medium having a program recorded thereon for implementing the method of the first aspect. [Effects of the Invention]

[0021] According to one embodiment of the present disclosure, a general segmentation technique is used to perform image analysis by dividing the image into portions of a size that allows for efficient image analysis rather than extracting the area of ​​the loaded items from the entire image at once, thereby achieving highly accurate image analysis results and reducing the time required.

[0022] In addition, when performing image analysis through image division according to the present invention, highly accurate analysis is possible even for loaded items included in the division boundary, which has the advantage of solving the problem of incorrect classification / item determination due to division.

[0023] Furthermore, when performing image analysis through a certain division size, even if there is a residual area, the image analysis can be performed by updating the image position of the blank area, which can improve the efficiency of image analysis.

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

[0025] [Figure 1] 1 is a block diagram illustrating a schematic configuration of an apparatus for analyzing iron scrap through image segmentation according to an embodiment of the present disclosure. [Figure 2] 1 is a flowchart illustrating steps for providing image analysis results through an apparatus for analyzing scrap iron through image segmentation according to an embodiment of the present disclosure. [Figure 3] 1 is a diagram illustrating an example in which an erroneous image analysis result is obtained based on image segmentation in an iron scrap analyzing apparatus according to an embodiment of the present disclosure; [Figure 4] 10 is a diagram illustrating an example in which the scrap iron analyzing apparatus according to the embodiment of the present disclosure reacquires image analysis results for an area corresponding to an erroneous image analysis result. [Figure 5]10 is a diagram illustrating an example in which an iron scrap analyzing apparatus according to an embodiment of the present disclosure performs image analysis by image division on an area excluding a remaining area of ​​a rectangle acquired based on a loading state image. [Figure 6] 10 is a diagram illustrating an example in which an apparatus for analyzing scrap iron according to an embodiment of the present disclosure determines intervals between N-1 divided images based on a remaining area. [Figure 7] 10 is a diagram illustrating an example in which an iron scrap analyzing apparatus according to an embodiment of the present disclosure performs image analysis by image division when a rectangular residual area is obtained based on a loading state image; [Figure 8] 1 is a diagram illustrating an example in which an apparatus for analyzing scrap iron according to an embodiment of the present disclosure performs image analysis by updating intervals between divided images using a first method. [Figure 9] 10 is a diagram illustrating an example in which the scrap iron analyzing apparatus according to the embodiment of the present disclosure performs image analysis by updating intervals between divided images using a second method. DETAILED DESCRIPTION OF THE INVENTION

[0026] The advantages and features of the present disclosure, and methods for achieving them, will become apparent from the following detailed description of the embodiments in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below, and may be embodied in various different forms. However, the embodiments are provided so that the disclosure will be complete and will fully convey the scope of the present disclosure to those skilled in the art.

[0027] The terms used in this specification are for the purpose of describing the embodiments and are not intended to limit the present disclosure. In this specification, the singular includes the plural unless otherwise specified in the context. The terms "comprises" and / or "comprising" used in this specification do not exclude the presence or addition of one or more other elements in addition to the elements referenced. The same reference numerals refer to the same elements throughout this specification, and "and / or" includes each and every combination of one or more of the referenced elements. Although terms such as "first," "second," etc. are used to describe various elements, these elements are not limited by these terms. These terms are used merely to distinguish one element from another. Therefore, a first element referred to below may of course be a second element within the technical spirit of this disclosure.

[0028] Unless otherwise defined, all terms (including technical and scientific terms) used herein may be used in the sense commonly understood by those of ordinary skill in the art, and terms defined in commonly used dictionaries should not be interpreted ideally or excessively unless expressly defined otherwise.

[0029] Spatially relative terms such as "below," "beneath," "lower," "above," and "upper" may be used to easily describe the relationship of one component to another, as illustrated in the drawings. Spatially relative terms should be understood to include different orientations of components in use or operation in addition to the orientations illustrated in the drawings. For example, if a component illustrated in the drawings were turned over, a component described as "below" or "beneath" another component would be positioned "above" the other component. Thus, the exemplary term "below" can encompass both an orientation of below and above. Components may be oriented in other directions, and the spatially relative terms should be interpreted accordingly.

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

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

[0032] Referring to FIG. 1, a scrap iron analysis device 100 may include a receiver 110 and a processor 120 .

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

[0034] According to an embodiment, the processor 120 may determine a target area including iron scrap in the loading state image. The processor 120 may also simplify the target area and convert it into a rectangular shape. The processor 120 may also determine a first length indicating the lengths of two different sides of the converted rectangle and a second length greater than the first length. The processor 120 may also determine the number of divisions of the target area based on a quotient obtained by dividing the second length by the first length. The processor 120 may also obtain a plurality of divided images by dividing the loading state image based on the number of divisions. The processor 120 may also provide an analysis result of the iron scrap loaded on the loading equipment based on image analysis of the plurality of divided images.

[0035] In addition, the scrap iron analysis device 100 through image segmentation acquires a loading state image through the receiving unit 110, determines a target area through the processor 120, determines the number of divisions of the target area to acquire a plurality of divided images, and provides image analysis results based on the divided images. In this process, the device can be connected to a combination of various conventional networks such as the Internet network or a mobile communication network, and there is no particular limitation thereon.

[0036] In addition, it will be understood by those skilled in the art that other general components may be included in the apparatus for analyzing scrap iron through image segmentation 100 in addition to the components shown in Figure 1. For example, the apparatus for analyzing scrap iron through image segmentation 100 may further include a memory (not shown) for storing a loading state image, a target area, information on a plurality of segmented images, etc., and may further include a transmitter (not shown) for providing image analysis results or a display (not shown) for displaying image analysis results. It will be understood by those skilled in the art that some of the components shown in Figure 1 may be omitted in other embodiments.

[0037] The scrap iron analysis device 100 through image segmentation according to one embodiment can be used by a user and can be connected to all kinds of handheld-based 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., and can also be included in or connected to devices equipped with a platform 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 apparatus 100 for analyzing scrap iron through image segmentation may be implemented as a terminal such as a computer that operates through a computer program to implement the functions described herein.

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

[0040] The following description will be focused on an embodiment in which the apparatus 100 for analyzing scrap iron through image division according to an embodiment independently acquires and provides image analysis results using a preset image division method, but as mentioned above, this may be performed in conjunction with a server. That is, the apparatus 100 for analyzing scrap iron through image division according to an embodiment and the server may be integrated in terms of their functions, or the server may be omitted, and it is understood that the present invention is not limited to any one embodiment.

[0041] In one embodiment, the scrap iron analyzing device 100 and a server may be linked together, and the configuration of providing analysis results by performing an image segmentation process and an analysis result providing process may be performed by the server, or may be performed by the scrap iron analyzing device 100. For example, the scrap iron analyzing device 100 may operate as a server, and hereinafter, the scrap iron analyzing device 100 will be referred to as the scrap iron analyzing device 100.

[0042] FIG. 2 is a flowchart illustrating steps for providing image analysis results through the apparatus 100 for analyzing scrap iron through image segmentation according to an embodiment of the present disclosure.

[0043] Referring to step S210, the iron scrap analyzing apparatus 100 according to an embodiment may acquire a loading state image captured while iron scrap is loaded on the loading equipment. For example, the iron scrap analyzing apparatus 100 may acquire a loading state image captured while looking down on the loading equipment through a camera.

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

[0045] Referring to step S230, the iron scrap analyzing device 100 according to an embodiment can simplify and convert the target area into a rectangular shape. Generally, loading equipment can correspond to a rectangular shape in which the horizontal length is longer than the vertical length. Therefore, the iron scrap analyzing device 100 can convert the target area of ​​the image analysis into a rectangular shape so that the target area includes iron scrap.

[0046] Referring to step S240, the iron scrap analyzing apparatus 100 according to an embodiment may 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 an embodiment, the iron scrap analyzing apparatus 100 may 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 scrap iron analyzing apparatus 100 according to an embodiment may determine the number of divisions of the target region based on a quotient obtained by dividing the second length by the first length. The scrap iron analyzing apparatus 100 may determine the number of divisions to be a number greater than a value corresponding to a quotient obtained by dividing the second length, which indicates the horizontal length of the converted rectangle, by the first length, which indicates the vertical length. For example, the scrap iron analyzing apparatus 100 may obtain the number of divisions corresponding to the quotient obtained by dividing the second length by the first length, and may further obtain the number of divisions corresponding to a value smaller than the quotient.

[0048] Referring to step S260, the iron scrap analyzing apparatus 100 according to an embodiment may obtain a plurality of divided images by dividing the loaded state image based on the division number. For example, when the quotient value is N, the iron scrap analyzing apparatus 100 according to an embodiment may determine the division number as a value that is 1 less than twice N. That is, the division number may be determined by the formula 2N-1, which may be a formula derived from N + (N-1). This may also 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 may be preferentially divided into N images based on the quotient value. That is, N divided images that have a first length in both the horizontal and vertical directions and do not overlap each other may be obtained based on the quotient value. Furthermore, after obtaining N images, the iron scrap analyzing apparatus 100 may obtain N-1 divided images that include the boundaries of the N divided images and do not overlap each other. Therefore, the number of divisions of the target area may be determined to be 2N-1. Also, if there is a remainder from the quotient obtained by dividing the second length by the first length, a divided image acquisition process for the remainder region may be further performed, which will be described in more detail with reference to FIGS.

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

[0050] FIG. 3 is a diagram illustrating an example in which the scrap iron analyzing apparatus 100 according to an embodiment of the present disclosure obtains an erroneous image analysis result based on image segmentation.

[0051] 3, the scrap iron analyzing apparatus 100 according to an embodiment can acquire one or more divided images divided by one or more boundary lines. However, as shown in the drawing, when acquiring one or more divided images separated by boundary lines, there are limitations in that undetected scrap iron may exist in the area around the boundary lines or one scrap iron may be detected separately.

[0052] FIG. 4 is a diagram illustrating an example in which the scrap iron analyzing device 100 according to an embodiment of the present disclosure reacquires image analysis results for an area corresponding to an erroneous image analysis result.

[0053] 4, the scrap iron analyzing device 100 according to an embodiment can reacquire image analysis results around the boundary line to re-perform image analysis on the area around the boundary line in order to overcome the limit point where undetected scrap iron exists in the area around the boundary line or where a single scrap iron may be detected separately. For example, an image of the area can be acquired by further dividing the image into a rectangle including the area around the boundary line, and image analysis results for the area can be re-acquired. This can be described in more detail with reference to FIG. 5.

[0054] FIG. 5 is a diagram illustrating an example in which the scrap iron analyzing apparatus 100 according to an embodiment of the present disclosure performs image analysis by image division on an area excluding a remaining area of ​​a rectangle acquired based on a loading state image.

[0055] Referring to FIG. 5, when the scrap iron analyzing apparatus 100 according to an embodiment divides the second length by the first length and there is no remainder, it obtains N divided images whose horizontal and vertical lengths corresponding to the quotient are the first length, and it can obtain N-1 divided images including the boundaries of the N divided images. That is, as shown at the top of the drawing, N divided images (an example situation in which N corresponds to 4 in FIG. 5) can be obtained, and as shown at the bottom of the drawing, N-1 divided images (N-1 corresponds to 3 in FIG. 5) can be obtained. Referring to the drawing, each of the N-1 divided images may overlap one or two of the N divided images. That is, the N-1 divided images may include portions of the divided images on both sides of the boundary line. In addition, among the boundaries of a terminal divided image located at one end of the N divided images, the boundary line on a side where an adjacent divided image is located may be included in the N-1 divided images, but the boundary line on a side where no adjacent divided image is located may not be included in the N-1 divided images. That is, with reference to the N divided images shown at the top of the drawing, if a boundary in the leftmost or rightmost divided image has no horizontally adjacent divided image, it is not included in the N-1 divided images, whereas if a boundary has a horizontally adjacent divided image, it is included in the N-1 divided images. With reference to the N-1 divided images shown at the bottom of the drawing, it can be seen that, among the boundaries of the terminal divided image, only the side boundaries with adjacent divided images are included in the N-1 divided images, excluding the side boundaries with no horizontally adjacent divided images. In one embodiment, the N-1 divided images may correspond to divided images whose horizontal and vertical lengths, including the boundaries, are first lengths. In one embodiment, when acquiring divided images, the horizontal and vertical lengths are generally determined to be the first length corresponding to the vertical length of the converted rectangle, and an image corresponding to a regular rectangle may be acquired. However, depending on various circumstances, an image corresponding to a rectangle whose horizontal length is less than the first length may be acquired, other than an image corresponding to a regular rectangle whose horizontal and vertical lengths correspond to the first length.For example, in another embodiment, the iron scrap analyzing device 100 may determine one iron scrap located at the outermost position on both sides of the boundary line from among the positions of at least one undetected iron scrap included in one or more boundary line peripheral areas and the positions of at least one iron scrap located across the boundary line, and may obtain the length between the boundary line and the end point of the iron scrap located at the outermost position based on the one or more positions of the iron scrap, and may determine the width to be twice the obtained length, thereby obtaining a rectangular image with different horizontal and vertical lengths as the divided image. In other words, the iron scrap analyzing device 100 may obtain a rectangular image as the divided image by obtaining the position of the iron scrap and excluding areas other than the unnecessary area.

[0056] FIG. 6 is a diagram illustrating an example in which the scrap iron analyzing apparatus 100 according to an embodiment of the present disclosure determines intervals between N-1 divided images based on the remaining area.

[0057] Referring to FIG. 6 , the scrap iron analyzing apparatus 100 according to one embodiment may determine the spacing between multiple divided images based on the remainder obtained by dividing the second length by the first length. In one embodiment, the spacing between the divided images may refer to the spacing between N divided images. In one embodiment, the spacing between the N divided images may be determined based on the value obtained by dividing the remainder by N-1. For example, the remainder may refer to an area whose horizontal length is shorter than the first length. As shown in FIG. 6 , when multiple divided images are obtained by dividing the second length by the first length, the spacing between the N divided images may be determined based on the horizontal length S corresponding to the remaining remainder. The position of the image corresponding to the remainder can be updated by determining the length obtained by dividing the horizontal length S corresponding to the remainder by N-1 as the spacing between the N divided images. For example, the scrap iron analyzing apparatus 100 may obtain one or more remainder divided images by dividing the remainder by N-1. That is, the scrap iron analyzing apparatus 100 may obtain N-1 remainder divided images by dividing the horizontal length S corresponding to the remainder by N-1. The scrap iron analyzing device 100 can update the position of each region of the remainder divided image with the interval region between N-1 divided images, which indicates the interval between the divided images. As shown in Fig. 6, the scrap iron analyzing device 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 interval region between the N-1 divided images.

[0058] FIG. 7 is a diagram illustrating an example in which the scrap iron analyzing apparatus 100 according to an embodiment of the present disclosure performs image analysis by image division when there is a rectangular remaining area acquired based on a loading state image.

[0059] 7, after updating the positions of the N-1 remainder divided images, the iron scrap analyzing device 100 can acquire N-1 divided images that include the center lines of the remainder divided images and do not overlap each other. That is, the iron scrap analyzing device 100 can perform image analysis on the images corresponding to the remainder by acquiring N-1 divided images of areas corresponding to a regular rectangle with the center line of the remainder divided image and a first length in horizontal and vertical lengths, and can provide analysis results for the images corresponding to the remainder. In one embodiment, even when the iron scrap analyzing device 100 divides the horizontal length of the remainder by N-1 to acquire N-1 remainder divided images, undetected iron scrap may exist in the areas around the separated boundary lines, and the iron scrap may be detected separately, so the spacing between the N divided images may be updated and determined differently.

[0060] FIG. 8 is a diagram illustrating an example in which the scrap iron analyzing apparatus 100 according to an embodiment of the present disclosure performs image analysis by updating the intervals between divided images using a first method.

[0061] 8, when the first length is greater than twice the third length, which indicates the horizontal length of one or more remainder divided images obtained by dividing the remainder by N-1, the scrap iron analyzing apparatus 100 according to an embodiment may determine the spacing between at least one N divided image to be twice the third length. Furthermore, the scrap iron analyzing apparatus 100 may obtain one or more remainder combined images by combining two consecutive images from the left end divided image to the right end divided image of one or more remainder divided images according to the first method. Referring to FIG. 8, when the first length is greater than twice the third length, the scrap iron analyzing apparatus 100 according to an embodiment may obtain two consecutive images from the left side of the N-1 remainder divided images obtained by dividing S, which indicates the horizontal length corresponding to the remainder in FIG. 6, by N-1. At least one remainder combined image in which two images are combined by N-1 may be obtained, and one remainder divided image in which two images are not consecutive may also be obtained. The iron scrap analyzing device 100 can update each region of the remainder combined image and the remainder divided image region in a portion of the space between N-1 divided images, which indicates the spacing between N divided images. As shown in FIG. 8, the iron scrap analyzing device 100 can update a remainder combined image including two consecutive remainder divided images in a portion of the space between N-1 divided images, and update a remainder divided image where two consecutive remainder divided images are not consecutive in a portion of the space between N-1 divided images other than the space where the remainder combined image is located. Thus, the iron scrap analyzing device 100 can acquire less than N-1 divided images that do not overlap each other and include 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 acquired by acquiring divided images corresponding to a portion of the space between N-1 divided images.In addition, the iron scrap analyzing device 100 may update the spacing between divided images corresponding to areas excluded from some of the intervening areas between the N-1 divided images to a value corresponding to 0. Therefore, the iron scrap analyzing device 100 may set the spacing between divided images in areas that are not update positions of the remainder divided images to 0, and may further acquire less than N-1 divided images corresponding to the update positions of the remainder divided images excluding the areas where the spacing between the divided images is 0. Although the number of remainder combined images is determined to be one in FIG. 8, this is not limited thereto and a plurality of images may be determined depending on the number N. Therefore, by acquiring N-1 divided images corresponding to the update positions of each remainder divided image as in FIG. 7 and further acquiring less than N-1 divided images corresponding to the update positions of each remainder combined image including two consecutive remainder divided images as in FIG. 8, it is possible to obtain more accurate images when undetected or one iron scrap is detected separately in the remainder area. This may be a process that can be further performed when the remainder is divided into one or more remainder divided images and the divided images are obtained, so that undetected or one iron scrap is separated and detected.

[0062] FIG. 9 is a diagram illustrating an example in which the scrap iron analyzing apparatus 100 according to an embodiment of the present disclosure performs image analysis by updating the intervals between divided images using a second method.

[0063] Referring to FIG. 9, the scrap iron analyzing apparatus 100 according to an embodiment can obtain one or more remainder combined images by combining two consecutive images from the right end of one or more remainder divided images to the left end of the left end of the leftover divided image using the second method. While the remainder combined image was obtained by combining two consecutive images from the left side of the remainder divided image using the first method in FIG. 8, the remainder combined image can be obtained by combining two consecutive images from the right side of the remainder divided image using the second method in FIG. 9. Therefore, it is possible to obtain a divided image that allows for the identification of undetected or single iron scrap that may occur on the left or right side between multiple remainder divided images. As shown in FIG. 9, it is possible to obtain less than N-1 divided images including remainder combined images that are combined in the opposite direction to FIG. 8, and the spacing between the divided images corresponding to the areas excluded from some of the areas between the N-1 divided images can be updated to a value corresponding to 0. In one embodiment, an example has been described in which multiple divided images are obtained by obtaining a regular square image including one or more remaining divided images or one or more remaining combined images through Figures 7 to 9, but this is not limited to this, and multiple divided images may also be obtained by obtaining a rectangular image by determining the horizontal length to be shorter than the first length as described above.

[0064] According to one embodiment, by performing image analysis by dividing an image into images of a size that is highly efficient for image analysis rather than extracting the area of ​​the loaded items from the entire image at once using a general segmentation technique, it is possible to obtain highly accurate image analysis results and reduce the time required. Furthermore, when performing image analysis through image division according to the present invention, it is possible to perform highly accurate analysis even on loaded items included in the division boundary, which has the advantage of solving the problem of incorrect classification / item determination due to division. Furthermore, when performing image analysis through a certain division size, even if there is a remaining area, the image analysis can be performed by updating the image position of the blank area, which improves the efficiency of image analysis.

[0065] Various embodiments of the present disclosure may be embodied as software including one or more instructions stored in a storage medium (e.g., memory) readable by a machine (e.g., a display device or a computer). For example, a processor (e.g., processor 220) of the machine can retrieve and execute at least one of the one or more instructions stored in the storage medium. This allows the machine to operate to perform at least one function according to the retrieved at least one 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" simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves). This term does not distinguish between data being stored semi-permanently and data being stored temporarily on the storage medium.

[0066] According to one embodiment, methods according to various embodiments disclosed in this disclosure may be provided in a computer program product. Computer program products may be traded as merchandise between sellers and buyers. Computer program products may be distributed in the form of a machine-readable storage medium (e.g., a compact disc read-only memory (CD-ROM)) or distributed online (e.g., downloaded or uploaded) through an application store (e.g., Play Store™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion 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 server, or an intermediary server.

[0067] Although the present invention has been described with reference to illustrative drawings, it is not limited by the disclosed embodiments and drawings. Those skilled in the art will understand that the present invention may be embodied in various modified forms without departing from the essential characteristics of the above description. Therefore, the disclosed methods should be considered from an illustrative rather than a restrictive perspective. Even if the effects of the configurations of the present invention are not explicitly described in the description of the embodiments, predictable effects of the configurations may be recognized. The scope of the present invention is defined by the claims, not the above description, and all differences within the scope of equivalents thereto should be construed as being included in the present invention. [Explanation of symbols]

[0068] 100: Iron scrap analyzer 110: Receiving unit 120: Processor

Claims

1. In the method of analyzing iron scrap through image segmentation, acquiring a loading state image captured by the receiving unit in a state where the iron scrap is loaded on the loading equipment; a processor determining an area of ​​interest in the loaded image that includes the ferrous scrap; the processor simplifying the region of interest into a rectangular shape; the processor determining a first length indicating the lengths of two different sides of the transformed rectangle and a second length greater than the first length; the processor determining the number of divisions of the region of interest based on a quotient obtained by dividing the second length by the first length; the processor dividing the loaded state image based on the division number to obtain a plurality of divided images; and the processor providing an analysis result for the ferrous scrap loaded on the loading equipment based on image analysis of the plurality of segmented images.

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

3. The step of obtaining a plurality of divided images includes: the processor obtaining N divided images each having the first length in both width and height and not overlapping with one another; 3. The method of claim 2, further comprising the step of: said processor obtaining N-1 non-overlapping divided images that include the boundaries of said N divided images.

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

5. The method of claim 3, wherein, among the boundaries of a terminal divided image located at one end of the N divided images, the boundary on a side where an adjacent divided image is located is included in the N-1 divided images, and the boundary on a side where no adjacent divided image is located is not included in the N-1 divided images.

6. 3. The method of claim 2, further comprising the step of: said processor determining spacing between a plurality of divided images based on a remainder obtained by dividing said second length by said first length.

7. 7. The method of claim 6, wherein the spacing between the N sub-images is determined based on the remainder divided by N-1.

8. The step of obtaining a plurality of divided images includes: the processor dividing the remainder by N-1 to obtain one or more remainder divided images; updating the area of ​​each of the remaining divided images with an interval area between N-1 divided images indicating an interval between the N divided images; and 8. The method of claim 7, further comprising the step of: said processor acquiring N-1 non-overlapping divided images that include the center line of said remaining divided image.

9. The step of obtaining a plurality of divided images includes: determining, by the processor, when the first length is greater than twice a third length indicating a horizontal length of one or more remainder divided images obtained by dividing the remainder by N-1, that an interval between at least one of the N divided images is twice the third length; obtaining one or more remainder combined images by the processor combining two consecutive images from a left end divided image to a right end divided image of the one or more remainder combined images; updating the areas of each of the remaining combined images and the remaining divided image areas with a portion of the inter-area between the N-1 divided images that indicates the intervals between the N divided images; and The processor acquires less than N-1 divided images that do not overlap each other and include a center line of the remainder combined image or a center line of the remainder divided image; The method of claim 6, wherein the intervals between the N-1 divided images corresponding to areas excluded from the partial area are updated to a value corresponding to 0.

10. The step of obtaining the remaining combined image includes:

10. The method of claim 9, further comprising: the processor obtaining one or more remainder combined images by combining two consecutive images from a right terminal divided image to a left terminal divided image of the one or more remainder combined images.

11. In the iron scrap analysis device through image division, a receiving unit for acquiring a loaded state image captured in a state in which the iron scrap is loaded on the loading equipment; and determining a target area including the iron scrap in the loading state image; simplifying the region of interest into a rectangular shape; determining a first length indicating two different side lengths of the transformed rectangle and a second length greater than the first length; determining the number of divisions of the target region based on a quotient obtained by dividing the second length by the first length; Dividing the loading state image based on the division number 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 an image analysis of the plurality of divided images.

12. The processor The iron scrap analyzing device according to claim 11, wherein when the value of the quotient is N, the number of divisions is determined to be a value that is one less than twice N.

13. The processor obtaining N divided images each having a width and a length equal to the first length and not overlapping with each other; The iron scrap analyzing apparatus according to claim 12, wherein N-1 divided images that include boundary lines of the N divided images and do not overlap each other are acquired.

14. The iron scrap analyzing apparatus of claim 13, wherein each of the N-1 divided images overlaps with one or two of the N divided images.

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

Images