Method and apparatus for analyzing scrap iron, and recording medium for performing method

Abstract

The invention relates to a method and an apparatus for analyzing scrap iron and a recording medium for performing the method. A method for analyzing scrap iron, an apparatus for analyzing scrap iron for performing the method, and a recording medium are disclosed. The method includes: obtaining, by a receiving unit, a loading state image captured in a state in which scrap iron is loaded onto a loading device; determining, by the processor, a target area including scrap iron in the loading state image; simplifying, by the processor, the target region and converting the simplified target region into a rectangular region; determining, by the processor, a first length representing lengths of two different sides of the converted rectangular region and a second length greater than the first length; determining, by the processor, a number of divisions of the target region based on a quotient obtained by dividing the second length by the first length; segmenting, by the processor, the loading state image based on the number of segments and obtaining a plurality of segmented images; and providing, by the processor, an analysis result of the scrap iron loaded onto the loading device by image analysis of the plurality of segmented images.

Description

Technical Field

[0001] The technical field of the present disclosure relates to a method of providing an image analysis result for an object loaded on a loading device, etc., and relates to the technical field of a method for dividing an entire area including the loaded object and providing an image analysis result of a plurality of divided areas. Background Art

[0002] Recently, with the development of the logistics industry, loading devices are widely used to load various objects or move objects from one place to another. However, multiple objects loaded on a loading device can be managed or loaded at positions for each product or specification by workers, but it may be difficult to check the position each time. Therefore, a segmentation method can be used, in which the entire area of the loading device on which multiple objects are loaded is divided to monitor images of each area. However, there are limitations in that when performing segmentation, in the case where an entire image is determined as an image analysis area to analyze the image, the accuracy may be reduced or the time required for analysis may increase. In addition, there are limitations in that when analyzing an image by dividing the image into one or more areas, an object placed in each boundary area can be included in two areas, or a single object can be analyzed by dividing a single object. Therefore, there is a need to provide a service in which a more accurate image analysis result can be provided by providing an image analysis method and system capable of solving such limitations of analysis errors.

[0003] [Related Technical Literature]

[0004] [Patent Literature]

[0005] Korean Unexamined Patent Application Publication No. 10-2011-0078566 (published on July 7, 2011): Efficient Object Loading Location Detection System Using Digital Image Recognition Summary of the Invention

[0006] The present disclosure aims to provide a service for determining a method of segmenting a loaded state image, and provide an analysis result of an image segmented based on the determined segmentation method, so that when providing an image analysis result, the accuracy of the analysis results of multiple areas included in the loaded state image can be improved.

[0007] The object of the present disclosure is not limited to the above object, and there may be other technical objects.

[0008] According to one aspect of the present disclosure, a method for analyzing scrap iron through image segmentation is provided. The method includes the following steps: obtaining, by a receiving unit, a loading state image captured in a state where the scrap iron is loaded onto a loading device; determining, by a processor, a target area including the scrap iron in the loading state image; simplifying, by the processor, the target area and converting the simplified target area into a rectangular area; determining, by the processor, a first length representing the lengths of two different sides of the converted rectangular area and a second length greater than the first length; determining, by the processor, the number of segments of the target area based on the quotient obtained by dividing the second length by the first length; dividing, by the processor, the loading state image based on the number of segments and obtaining a plurality of segmented images; and providing, by the processor, an analysis result of the scrap iron loaded onto the loading device through image analysis of the plurality of segmented images.

[0009] The step of determining the number of segments may include the following steps: when the value of the quotient is N, determining, by the processor, the number of segments as a value that is 1 less than twice N.

[0010] The step of obtaining the plurality of segmented images may include the following steps: obtaining, by the processor, N segmented images, the horizontal length and vertical length of the N segmented images being the first length, and the N segmented images not overlapping each other; and obtaining, by the processor, N - 1 segmented images, the N - 1 segmented images including the boundary lines of the N segmented images and not overlapping each other.

[0011] Each of the N - 1 segmented images may overlap with one or two of the N segmented images.

[0012] Among the boundary lines of any end - portion segmented image in the N segmented images, the boundary line of the side where adjacent segmented images exist may be included in the N - 1 segmented images, and the boundary line of the side where adjacent segmented images do not exist may not be included in the N - 1 segmented images.

[0013] The method may further include the following step: determining, by the processor, the interval between the plurality of segmented images based on the remainder obtained by dividing the second length by the first length.

[0014] The interval between the N segmented images may be determined based on the value obtained by dividing the remainder by N - 1.

[0015] The step of obtaining the plurality of segmented images by the processor may include the following steps: obtaining, by the processor, one or more remaining segmented images obtained by dividing the remainder by N - 1; updating, by the processor, the region of each of the remaining segmented images in the remaining segmented images to the region between the N - 1 segmented images representing the intervals between the N segmented images; and obtaining, by the processor, N - 1 segmented images including the center lines of the remaining segmented images and not overlapping each other.

[0016] The step of obtaining the plurality of segmented images may include the following steps: when the first length is more than twice as large as a third length representing the horizontal length of one or more remaining segmented images obtained by dividing the remainder by N - 1, determining, by the processor, one or more intervals between the N segmented images as twice the third length; obtaining, by the processor, one or more remaining combined images by combining two consecutive images from the leftmost segmented image to the rightmost segmented image of the one or more remaining segmented images; updating, by the processor, the region of each of the remaining combined images in the remaining combined images and the region of each of the remaining segmented images in the remaining segmented images to some of the regions of the N - 1 segmented images representing the intervals between the N segmented images; and obtaining, by the processor, less than N - 1 segmented images including the center line of the remaining combined images or the center line of the remaining segmented images and not overlapping each other, and updating the intervals between the segmented images corresponding to the regions excluded from the some of the regions between the N - 1 segmented images to have a value corresponding to 0.

[0017] The step of obtaining the remaining combined images may include the following steps: obtaining, by the processor, one or more remaining combined images by combining two consecutive images from the rightmost segmented image to the leftmost segmented image of the one or more remaining segmented images.

[0018] According to another aspect of the present disclosure, there is provided an apparatus for analyzing scrap iron by image segmentation, the apparatus including: a receiving unit configured to obtain a loading state image captured in a state where the scrap iron is loaded onto a loading device; and a processor configured to: determine a target region including the scrap iron in the loading state image; simplify the target region and convert the simplified target region into a rectangular region; determine a first length representing the length of two different sides of the converted rectangular region and a second length greater than the first length; determine the number of segments of the target region based on a quotient obtained by dividing the second length by the first length; divide the loading state image based on the number of segments and obtain a plurality of segmented images; and provide an analysis result of the scrap iron loaded onto the loading device through image analysis of the plurality of segmented images.

[0019] When the value of the quotient is N, the processor may determine the number of segments as a value that is 1 less than twice N.

[0020] The processor may obtain N segmented images, the horizontal length and vertical length of the N segmented images being the first length, and the N segmented images not overlapping each other, and obtain N - 1 segmented images, the N - 1 segmented images including the boundary lines of the N segmented images and not overlapping each other.

[0021] Each of the N - 1 segmented images may overlap with one or two of the N segmented images.

[0022] According to another aspect of the present disclosure, there is provided a computer-readable non-transitory recording medium on which a program for implementing the method of the first aspect is recorded. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] By referring to the drawings and describing in detail the exemplary embodiments of the present disclosure, the above and other objects, features, and advantages of the present disclosure will become more apparent to those of ordinary skill in the art, where:

[0024] Figure 1 is a block diagram schematically showing the configuration of an apparatus for analyzing scrap iron by image segmentation according to an embodiment of the present disclosure;

[0025] Figure 2 is a flowchart showing an operation in which an apparatus for analyzing scrap iron by image segmentation according to an embodiment of the present disclosure provides an image analysis result;

[0026] Figure 3A diagram for describing an example in which an apparatus for analyzing scrap iron according to an embodiment of the present disclosure obtains an incorrect image analysis result based on image segmentation;

[0027] Figure 4 A diagram for showing an example in which an apparatus for analyzing scrap iron according to an embodiment of the present disclosure re-obtains an image analysis result of a region corresponding to an incorrect image analysis result;

[0028] Figure 5 A diagram for describing an example in which an apparatus for analyzing scrap iron according to an embodiment of the present disclosure performs image analysis on a region of a remaining region excluding a rectangle obtained based on a loading state image based on image segmentation;

[0029] Figure 6 A diagram for describing an example in which an apparatus for analyzing scrap iron according to an embodiment of the present disclosure determines an interval between N-1 segmented images based on a remaining region;

[0030] Figure 7 A diagram for describing an example in which an apparatus for analyzing scrap iron according to an embodiment of the present disclosure performs image analysis based on image segmentation in the presence of a remaining rectangular region obtained based on a loading state image;

[0031] Figure 8 A diagram for describing an example in which an apparatus for analyzing scrap iron according to an embodiment of the present disclosure performs image analysis by updating an interval between segmented images according to a first method; and

[0032] Figure 9 A diagram for describing an example in which an apparatus for analyzing scrap iron according to an embodiment of the present disclosure performs image analysis by updating an interval between segmented images according to a second method. Detailed Description of the Embodiment

[0033] With reference to the accompanying drawings and embodiments described in detail below, the advantages and features of the present disclosure and the method for implementing the present disclosure will be clearly understood. However, the present disclosure is not limited to the embodiments to be disclosed below, but may be implemented in various different forms. The embodiments are provided to fully explain the present embodiments and to fully explain the scope of the present disclosure to those skilled in the art.

[0034] The terms used in this disclosure are provided only for the purpose of describing the embodiments of the present disclosure and not for the purpose of limitation. In this specification, unless the context clearly indicates otherwise, the singular forms include the plural forms. It should be understood that the terms "comprising" and / or "including" used herein specify some of the stated components, but do not exclude the presence or addition of one or more other components. Throughout the specification, the same reference numerals represent the same components, and "and / or" includes each combination of one or more of the above components. It should be understood that although terms such as "first", "second", etc. may be used to describe various components, these components are not limited by these terms. These terms are only used to distinguish one component from another. Therefore, it should be understood that the first component to be described below may be the second component within the technical scope of the present disclosure.

[0035] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. In addition, it should be understood that terms should not be interpreted in an idealized or overly formal sense unless explicitly defined herein, such as terms defined in a common dictionary.

[0036] As shown in the drawings, spatial relative terms such as "below", "beneath", "lower", "above", "upper", etc. may be used to facilitate the description of the relationship between one component and other components. In addition to the directions shown in the drawings, spatial relative terms should be understood to include different directions during the use or operation of the element. For example, when the component shown in the figure is flipped, the component described as "below" or "beneath" may ultimately be placed "above" another component. Therefore, the exemplary term "below" may include both downward and upward directions. Components can be arranged in different directions, and thus the spatial relative terms can be interpreted according to this arrangement.

[0037] Hereinafter, embodiments will be described in detail with reference to the drawings.

[0038] Figure 1 is a block diagram schematically showing the configuration of a device 100 for analyzing scrap iron by image segmentation according to an embodiment of the present disclosure.

[0039] Referring to Figure 1 , the device 100 for analyzing scrap iron may include a receiving unit 110 and a processor 120.

[0040] According to an embodiment, the receiving unit 110 may obtain a loading state image captured in a state where scrap iron is loaded onto a loading device.

[0041] The processor 120 according to one embodiment may determine a target area including scrap iron in the loading state image. In addition, the processor 120 may simplify the target area and convert the simplified target area into a rectangular area. In addition, the processor 120 may determine a first length representing the lengths of two different sides of the converted rectangular area and a second length greater than the first length. In addition, the processor 120 may determine the number of divisions of the target area based on the quotient obtained by dividing the second length by the first length. In addition, the processor 120 may divide the loading state image based on the number of divisions and obtain a plurality of divided images. In addition, the processor 120 may provide an analysis result of the scrap iron loaded on the loading device through image analysis of the plurality of divided images.

[0042] In addition, in the process in which the receiving unit 110 obtains the loading state image and the processor 120 determines the target area, determines the number of divisions of the target area, obtains a plurality of divided images, and provides an image analysis result based on the divided images, the device 100 for analyzing scrap iron through image segmentation may be combined with various conventional networks such as the Internet, a mobile communication network, etc., and it should be noted that there is no particular limitation on the network.

[0043] In addition, those skilled in the art should understand that other general components other than those shown in Figure 1 may also be included in the device 100 for analyzing scrap iron through image segmentation. For example, the device 100 for analyzing scrap iron through image segmentation may further include a memory (not shown) for storing the loading state image, the target area, a plurality of divided images, etc., and may also include a transmission unit (not shown) for providing the image analysis result or a display unit (not shown) for displaying the image analysis result. Alternatively, those skilled in the art will understand that in another embodiment, some of the components shown in Figure 1 may be omitted.

[0044] The device 100 for analyzing scrap iron through image segmentation according to one embodiment may be used by a user and may be linked with any type of handheld wireless communication device equipped with a touch screen panel (e.g., a mobile phone, a smartphone, a personal digital assistant (PDA), a portable multimedia player (PMP), a tablet computer, etc.). In addition, it may be included in or linked with a device having a basis for installing and executing an application (e.g., a desktop personal computer (PC), a tablet computer, a laptop computer, an Internet protocol television (IPTV) including a set-top box).

[0045] The device 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 in this specification.

[0046] An apparatus 100 for analyzing scrap iron through image segmentation according to an embodiment may include a system (not shown) and a related server (not shown) that provide the image analysis result of the scrap iron, but the present disclosure is not limited thereto. A server according to an embodiment may support an application that provides a service that provides information on the image analysis result of the scrap iron.

[0047] Hereinafter, an example in which the apparatus 100 for analyzing scrap iron through image segmentation according to an embodiment independently obtains and provides an image analysis result according to a preset method of segmenting an image is mainly described. However, as described above, the apparatus 100 may perform the above functions in cooperation with a server. That is, the apparatus 100 for analyzing scrap iron and the server according to an embodiment may be implemented in an integrated manner in terms of their functions, and the server may be omitted. Thus, it can be seen that the present disclosure is not limited to any one embodiment.

[0048] In one embodiment, the apparatus 100 for analyzing scrap iron and the server may be linked to each other, and by performing a process for segmenting an image and a process for providing an analysis result, a configuration for providing an analysis result may be performed by the server or the apparatus 100 for analyzing scrap iron. For example, the apparatus 100 for analyzing scrap iron may operate as a server, and the apparatus 100 for analyzing scrap iron and the server are hereinafter collectively referred to as the apparatus 100 for analyzing scrap iron.

[0049] Figure 2 FIG. is a flowchart showing an operation of an apparatus 100 for analyzing scrap iron through image segmentation according to an embodiment of the present disclosure to provide an image analysis result.

[0050] Referring to operation S210, an apparatus 100 for analyzing scrap iron according to an embodiment may obtain a loading state image captured in a state where scrap iron is loaded onto a loading device. For example, the apparatus 100 for analyzing scrap iron may obtain a loading state image by looking down at the loading device from above through a camera.

[0051] Referring to operation S220, an apparatus 100 for analyzing scrap iron according to an embodiment may determine a target region including the scrap iron in the loading state image. The target region may include a region in the loading state image captured by the camera excluding the loading device and a region excluding the region not including the scrap iron. That is, the apparatus 100 for analyzing scrap iron may determine a region for performing image analysis including the scrap iron as the target region.

[0052] Referring to operation S230, the scrap iron analyzing device 100 according to one embodiment may simplify the target area and convert the simplified target area into a rectangular area. Generally, the loading device may correspond to a rectangular area whose horizontal length is longer than its vertical length. Therefore, the scrap iron analyzing device 100 may convert the area to be analyzed as an image analysis into a rectangular area by including the target area containing the scrap iron.

[0053] Referring to operation S240, the scrap iron analyzing device 100 according to one embodiment may determine a first length representing the lengths of two different sides of the converted rectangular area and a second length greater than the first length. In one embodiment, the scrap iron analyzing device 100 may determine the vertical length of the converted rectangular area as the first length and the horizontal length of the converted rectangular area as the second length.

[0054] Referring to operation S250, the scrap iron analyzing device 100 according to one embodiment may determine the number of divisions of the target area based on the quotient obtained by dividing the second length by the first length. The scrap iron analyzing device 100 may determine the number of divisions as a number greater than the value corresponding to the quotient obtained by dividing the second length representing the horizontal length of the converted rectangular area by the first length representing the vertical length. For example, the scrap iron analyzing device 100 may obtain the number of divisions corresponding to the quotient obtained by dividing the second length by the first length, and may also obtain the number of divisions corresponding to a value less than the quotient.

[0055] Referring to operation S260, the scrap iron analyzing device 100 according to one embodiment may divide the loading state image based on the number of divisions and obtain a plurality of divided images. For example, when the value of the quotient is N, the scrap iron analyzing device 100 according to one embodiment may determine the number of divisions as a value one less than twice N. That is, the formula 2N - 1 may be applied to the number of divisions and may be a formula derived from N+(N - 1). In addition, this formula may be a formula corresponding to when there is no remainder. For example, when there is no remainder and the value of the quotient is N, the loading state image may preferably be divided into N images according to the value of the quotient. That is, according to the value of the quotient, N divided images may be obtained, the N divided images each have the first length in width and height, and the N divided images do not overlap. In addition, after the scrap iron analyzing device 100 obtains N images, the scrap iron analyzing device 100 may obtain N - 1 divided images, the N - 1 divided images include the boundary lines of the N divided images and do not overlap with each other. Therefore, the number of divisions of the target area may be determined as 2N - 1. In addition, when there is a remainder according to the quotient obtained by dividing the second length by the first length, a process for obtaining the divided images of the remaining area may also be performed. This will be described in more detail Figures 3 to 9 below.

[0056] Referring to operation S270, the scrap iron analysis device 100 according to one embodiment can provide an analysis result of the scrap iron loaded onto the loading device through image analysis of a plurality of segmented images. The scrap iron analysis device 100 can perform image analysis on each of the plurality of segmented images obtained in operations S210 to S260, and can provide the image analysis results obtained for each of the plurality of segmented images. The scrap iron analysis device 100 can provide information about the image analysis results to the user terminal and can display each of the plurality of segmented images.

[0057] Figure 3 It is a diagram for describing an example in which the scrap iron analysis device 100 according to one embodiment of the present disclosure obtains an incorrect image analysis result based on image segmentation.

[0058] Referring to Figure 3 , the scrap iron analysis device 100 according to one embodiment can obtain one or more segmented images segmented according to one or more boundary lines. However, as shown in the figure, when obtaining one or more segmented images separated by a boundary line, there is a limitation that undetected scrap iron may exist in the area around the boundary line, or one scrap iron can be detected by being separated.

[0059] Figure 4 It is a diagram showing an example in which the scrap iron analysis device 100 according to one embodiment of the present disclosure re-obtains an image analysis result of an area corresponding to an incorrect image analysis result.

[0060] Referring to Figure 4 , to overcome the limitation that undetected scrap iron may exist in the area around the boundary line or one scrap iron can be detected by being separated, the scrap iron analysis device 100 according to one embodiment can re-obtain an image analysis result centered on the boundary line in order to re-perform image analysis on the area around the boundary line. For example, by also performing image segmentation of the image into a quadrilateral including the area around the boundary line, an image of the corresponding area can be obtained, and the image analysis result of the corresponding area can be re-obtained. This will be described in more detail with reference to Figure 5 in more detail.

[0061] Figure 5 It is a diagram for describing an example in which the scrap iron analysis device 100 according to one embodiment of the present disclosure performs image analysis on an area of the remaining area excluding the rectangle obtained based on the loading state image based on image segmentation.

[0062] Referring to Figure 5, in the case where there is no remainder when the second length is divided by the first length, the scrap iron analyzing apparatus 100 according to an embodiment can obtain N divided images, the horizontal length and the vertical length of the N divided images corresponding to the quotient being the first length, and obtain N-1 divided images including the boundary lines of the N divided images. That is, as shown in the upper part of the figure, N divided images (in Figure 5 in which N corresponds to an example of 4) can be obtained, and as shown in the lower part of the figure, N-1 divided images (in Figure 5In the example where N corresponds to 3). Referring to the accompanying drawings, each of the N - 1 divided images may overlap with one or two of the N divided images. That is, the N - 1 divided images may include some of the divided images on both sides of the boundary line. In addition, among the boundary lines of the end divided images located at one end of the N divided images, the N - 1 divided images may include the boundary lines at the side where the adjacent divided images are located, and the N - 1 divided images may not include the boundary lines at the side where there are no adjacent divided images. That is, referring to the N divided images shown in the upper part of the accompanying drawings, among the boundary lines included in the leftmost divided image or the rightmost divided image, the boundary lines without adjacent divided images beside them may not be included in the N - 1 divided images, and the boundary lines with adjacent divided images beside them may be included in the N - 1 divided images. Referring to the N - 1 divided images shown in the lower part of the accompanying drawings, it can be confirmed that among the boundary lines of the end divided images, the N - 1 divided images only include the boundary lines at the side where there are adjacent divided images, and do not include the boundary lines at the side where there are no adjacent divided images. In one embodiment, the N - 1 divided images may correspond to the divided image whose horizontal length and vertical length including the boundary line are the first length. In one embodiment, when obtaining the divided image, the horizontal length and the vertical length are usually determined to be the first length corresponding to the vertical length of the converted rectangular area, so that the divided image can be obtained as an image corresponding to a square. However, according to specific situations, the divided image can be obtained as an image corresponding to a rectangle whose horizontal length is less than the first length instead of an image corresponding to a square whose horizontal length and vertical length correspond to the first length. For example, in another embodiment, the device 100 for analyzing scrap iron may determine a scrap iron located at the outermost side in two directions centered on the boundary line among the positions of one or more undetected scrap irons included in the area around one or more boundary lines and the positions of one or more scrap irons across the boundary line, obtain the length between the endpoint of the scrap iron located at the outermost side of the boundary line and the boundary line based on the positions of one or more scrap irons to determine the length twice the obtained length as the horizontal length, and obtain a rectangular image with different horizontal length and vertical length as the divided image. That is, the device 100 for analyzing scrap iron may obtain the positions of the scrap iron, so that a rectangular image excluding the areas other than the unnecessary areas can be obtained as the divided image.

[0063] Figure 6 FIG. is an example for describing the interval between N - 1 divided images determined by the device 100 for analyzing scrap iron according to an embodiment of the present disclosure based on the remaining area.

[0064] Referring to Figure 6, the device 100 for analyzing scrap iron according to an embodiment may determine the interval between multiple 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 may be the interval between N divided images. In one embodiment, the interval between N divided images may be determined based on the value obtained by dividing the remainder by N - 1. For example, the remainder may be a region whose horizontal length is shorter than the first length. As Figure 6 shown, when obtaining multiple divided images according to the quotient obtained by dividing the second length by the first length, the interval between N divided images may be determined based on the horizontal length S corresponding to the remaining remainder. By determining the horizontal length S corresponding to the remainder divided 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 device 100 for analyzing scrap iron may obtain one or more remaining divided images obtained by dividing the remainder by N - 1. That is, the device 100 for analyzing scrap iron may obtain N - 1 remaining divided images obtained by dividing the horizontal length S corresponding to the remainder by N - 1. The device 100 for analyzing scrap iron may update the region of each of the remaining divided images to the region between N - 1 divided images representing the interval between the divided images. As Figure 6 shown, the device 100 for analyzing scrap iron may update the position of each region such that the N - 1 remaining divided images obtained by dividing the remainder by N - 1 are located in the region between N - 1 divided images.

[0065] Figure 7 is a diagram for describing an example in which the device 100 for analyzing scrap iron according to an embodiment of the present disclosure performs image analysis based on image segmentation in the case where there is a remaining rectangular region obtained based on the loading state image.

[0066] Referring to Figure 7 , the device 100 for analyzing scrap iron may update the positions of the N - 1 remaining divided images, and then obtain N - 1 divided images that include the center lines of the remaining divided images and do not overlap each other. That is, the device 100 for analyzing scrap iron may perform image analysis on the image corresponding to the remainder by obtaining N - 1 divided images of a region corresponding to a square with a horizontal length and a vertical length of the first length with the remaining divided images as the center lines, and provide the image analysis result of the region corresponding to the remainder. In one embodiment, the device 100 for analyzing scrap iron may determine by updating the interval between N divided images differently because even when the horizontal length of the remainder is divided by N - 1 to obtain N - 1 remaining divided images, there may be undetected scrap iron around the divided boundary lines, and the scrap iron can be detected by being separated.

[0067] Figure 8FIG. is an example of a diagram for describing an image analysis performed by an apparatus 100 for analyzing scrap iron according to an embodiment of the present disclosure by updating an interval between divided images according to a first method.

[0068] Referring to Figure 8 , according to an embodiment, the apparatus 100 for analyzing scrap iron may determine one or more intervals between N divided images as twice the third length when the first length ratio is greater than twice the third length representing the horizontal length of one or more remaining divided images obtained by dividing the remainder by N−1. Further, according to the first method, the apparatus 100 for analyzing scrap iron may obtain one or more remaining combined images by combining two consecutive images from the leftmost divided image to the rightmost divided image of the one or more remaining divided images. Referring to Figure 8 , according to an embodiment, the apparatus 100 for analyzing scrap iron may, when the first length is greater than twice the third length, obtain two consecutive images from the left among N−1 remaining divided images obtained by dividing S, which represents the horizontal length corresponding to the remainder in Figure 6 , by N−1 as remaining combined images, obtain one or more remaining combined images in which two images are combined according to the number of N−1, and obtain one remaining divided image and two non-consecutive images. The apparatus 100 for analyzing scrap iron may update the area of each of the remaining combined images and the area of each of the remaining divided images to some areas among the areas between N−1 divided images representing the intervals between N divided images. As shown in Figure 8 , the apparatus 100 for analyzing scrap iron may update the remaining combined images including two consecutive remaining divided images to some areas among the areas between N−1 divided images, and update one remaining divided image in which two remaining divided images are non-consecutive to some areas among the areas between N−1 divided images other than the areas where the remaining combined images are located. Accordingly, the apparatus 100 for analyzing scrap iron may obtain less than N−1 divided images including the center lines of the remaining combined images or the remaining divided images and not overlapping each other. In one embodiment, since the remaining combined images include consecutive remaining divided images, less than N−1 divided images may be obtained by obtaining divided images corresponding to some areas among the areas between N−1 divided images. Further, the apparatus 100 for analyzing scrap iron may update the intervals between the divided images corresponding to the areas excluded from some areas among the areas between N−1 divided images to values corresponding to 0. Accordingly, the apparatus 100 for analyzing scrap iron may determine the intervals between the divided images in the areas other than the updated positions of the remaining divided images as 0, and also obtain less than N−1 divided images corresponding to the updated positions of the remaining divided images excluding the areas where the intervals between the divided images are 0. InFigure 8 In this case, the number of remaining combined images is described as being determined to be one, but the present disclosure is not limited thereto, and a plurality of remaining combined images may be determined according to the number of N. Therefore, as shown in Figure 7 N - 1 divided images corresponding to the updated positions of the remaining divided images are obtained as shown in, and as shown in Figure 8 less than N - 1 divided images corresponding to the updated positions of the remaining combined images including two consecutive remaining divided images are also obtained, having the effect that in the case where undetected scrap iron exists or one piece of scrap iron is detected by being separated in the remaining area, more accurate images are obtained. This may be a process that can be further performed in the case where undetected scrap iron exists or one piece of scrap iron is detected by being separated when the remainder is divided into one or more remaining divided images and the divided images are obtained.

[0069] Figure 9 FIG. is an example for describing an image analysis performed by the scrap iron analysis device 100 according to an embodiment of the present disclosure by updating the intervals between divided images according to a second method.

[0070] Referring to Figure 9 , according to an embodiment, the scrap iron analysis device 100 may obtain one or more remaining combined images by combining two consecutive images from the right - end divided image to the left - end divided image of one or more remaining divided images according to a second method. In Figure 8 , the remaining combined images may be obtained by combining two consecutive images from the left side of the remaining divided images according to a first method, while in Figure 9 , the remaining combined images may be obtained by combining two consecutive images from the right side of the remaining divided images according to a second method. Therefore, the effect is that divided images can be obtained such that all cases where undetected scrap iron may occur between the left and right sides among a plurality of remaining divided images or one piece of scrap iron is detected by being separated can be recognized. As shown in Figure 9 , less than N - 1 divided images including remaining combined images combined in a direction opposite to Figure 8 may be obtained, and the intervals of the divided images corresponding to the regions excluded from some regions among the regions between the N - 1 divided images are updated to values corresponding to 0. In one embodiment, referring to Figures 7 to 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 is described, but the present disclosure is not limited thereto, and 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.

[0071] According to one embodiment, image analysis can be performed by dividing the area of the loaded object into images of a certain size instead of extracting the area of the loaded object from the entire image at once using a general segmentation technique. Therefore, highly accurate image analysis results can be obtained and the required time can be reduced. In addition, when image analysis is performed by image segmentation according to the present disclosure, the advantage is that highly accurate analysis can be performed on the loaded object included in the segmentation boundary, thereby solving the problem of incorrect determination of grades / items due to segmentation. And when image analysis is performed with a certain segmentation size, the efficiency of image analysis can be improved because even in the presence of a remaining area, image analysis can be performed by updating the position of the image in the blank area.

[0072] Various embodiments of the present disclosure can be implemented as software, which includes one or more instructions stored in a storage medium (e.g., a memory) readable by a machine (e.g., a display device or a computer). For example, a processor of the machine (e.g., processor 120) can call at least one stored instruction from the storage medium and execute the instruction. This enables the device to operate according to at least one called instruction to perform at least one function. The one or more instructions can include code generated by a compiler or code executable by an interpreter. The storage medium readable by the device can be provided in the form of a non-transitory storage medium. Here, the term "non-transitory" only means that the storage medium is a tangible device and does not include signals (e.g., electromagnetic waves), and this term does not distinguish between the case where data is stored semi-permanently and the case where data is temporarily stored in the storage medium.

[0073] According to one embodiment, the methods according to the various embodiments disclosed in the present disclosure can be included in and provided in a computer program product. The computer program product can be traded between a seller and a buyer as a commodity. The computer program product can be distributed in the form of a machine-readable storage medium (e.g., a compact disc read-only memory (CD-ROM)), or can be distributed online (e.g., by downloading or uploading) through an application store (e.g., Play Store TM), or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a part of the computer program product can be temporarily stored or temporarily generated in a machine-readable storage medium (e.g., the memory of a manufacturer's server, an application store's server, or an intermediate server).

[0074] According to one embodiment of the present disclosure, image analysis can be performed by dividing the area of the loaded object into areas of images of a certain size instead of extracting the area of the loaded object from the entire image at once using a general segmentation technique. Therefore, highly accurate image analysis results can be obtained and the required time can be reduced.

[0075] In addition, when performing image analysis through image segmentation according to the present disclosure, there is an advantage that highly accurate analysis can be performed on the loading object included in the segmentation boundary, thereby solving the problem of incorrect determination of grades / items due to segmentation.

[0076] In addition, when performing image analysis through a specific segmentation size, the efficiency of image analysis can be improved because even when there are remaining areas, image analysis can be performed by updating the position of the image in the blank area.

[0077] The effects of the present disclosure are not limited to the above effects, and those skilled in the art can clearly understand other effects not described from the above detailed description.

[0078] Although the present disclosure has been described with reference to the accompanying drawings, the present disclosure is not limited to the disclosed embodiments and drawings, and those skilled in the art will understand that various changes can be made in form and detail without departing from the spirit and scope of the present disclosure. Therefore, the disclosed method should be described from an exemplary rather than a restrictive perspective. Even when an embodiment is described and the effects of the configuration according to the present disclosure are not explicitly described, the effects predictable from the configuration can be identified. The scope of the present disclosure is not limited by the detailed description of the present disclosure, but is defined by the appended claims, and includes all modifications and equivalents falling within the scope of the appended claims, and will be interpreted as being included in the present disclosure.

[0079] Cross - reference to related applications

[0080] This application claims the priority and benefits of Korean Patent Application No. 10 - 2023 - 0188833, filed on December 21, 2023, the entire content of which is incorporated herein by reference in its entirety.

Claims

1. A method for analyzing scrap iron by image segmentation, the method for analyzing scrap iron comprising the following steps: obtaining, by the receiving unit, a loading state image captured when the scrap iron is loaded on the loading device; Determining, by a processor, a target area in the loading state image that includes the scrap metal; simplifying the target area and converting the simplified target area into a rectangular area by the processor; Determining, by the processor, a first length representing lengths of two different sides of the transformed rectangular area and a second length greater than the first length; determining, by the processor, a number of divisions of the target area based on a quotient obtained by dividing the second length by the first length; segmenting the loading state image based on the segmentation number by the processor and obtaining a plurality of segmented images; as well as The processor provides an analysis result of the scrap metal loaded on the loading device through image analysis of the plurality of segmented images.

2. The method for analyzing scrap iron according to claim 1, wherein: The step of determining the number of divisions includes the following steps: when the value of the quotient is N, the processor determines the number of divisions to be a value that is 1 less than twice N.

3. The method for analyzing scrap iron according to claim 2, wherein: The step of obtaining the plurality of segmented images comprises the following steps: obtaining, by the processor, N segmented images, the horizontal lengths and vertical lengths of the N segmented images being the first lengths, and the N segmented images not overlapping each other; and The processor obtains N-1 segmented images, which include boundary lines of the N segmented images and do not overlap with each other.

4. The method for analyzing scrap iron according to claim 3, wherein: Each of the N-1 segmented images overlaps with one or two segmented images of the N segmented images.

5. The method for analyzing scrap iron according to claim 3, wherein: Among the boundary lines of any end segmented image in the N segmented images, the boundary line of the side where the adjacent segmented image exists is included in the N-1 segmented images, and the boundary line of the side where the adjacent segmented image does not exist is not included in the N-1 segmented images.

6. The method for analyzing scrap iron according to claim 2, further comprising the following steps: The intervals between the plurality of segmented images are determined, by the processor, based on a remainder obtained by dividing the second length by the first length.

7. The method for analyzing scrap iron according to claim 6, wherein: The intervals between the N divided images are determined based on a value obtained by dividing the remainder by N-1.

8. The method for analyzing scrap iron according to claim 7, wherein: The step of obtaining the plurality of segmented images comprises the following steps: obtaining, by the processor, one or more residual segmented images obtained by dividing the remainder by N-1; updating, by the processor, the area of ​​each of the remaining segmented images to an area between the N-1 segmented images representing an interval between the N segmented images; and The processor obtains N-1 segmented images that include the center line of the remaining segmented image and do not overlap with each other.

9. The method for analyzing scrap iron according to claim 6, wherein: The step of obtaining the plurality of segmented images comprises the following steps: when the first length is greater than twice a third length representing a horizontal length of one or more remaining segmented images obtained by dividing the remainder by N-1, determining, by the processor, one or more intervals between the N segmented images as twice the third length; obtaining, by the processor, one or more remaining combined images by combining two consecutive images from a left end segmented image to a right end segmented image of the one or more remaining segmented images; updating, by the processor, the area of ​​each of the remaining combined images and the area of ​​each of the remaining segmented images to some areas among the areas of the N-1 segmented images representing the intervals between the N segmented images; and less than N-1 segmented images that include the center line of the remaining combined image or the center line of the remaining segmented images and do not overlap with each other are obtained by the processor, and The intervals between the segmented images corresponding to the areas excluded from the some areas among the areas between the N-1 segmented images are updated to have a value corresponding to 0.

10. The method for analyzing scrap iron according to claim 9, wherein: The step of obtaining the remaining combined image includes the step of obtaining, by the processor, one or more remaining combined images by combining two consecutive images from the right end segmented image to the left end segmented image of the one or more remaining segmented images.

11. A device for analyzing scrap iron by image segmentation, the device for analyzing scrap iron comprising: a receiving unit configured to obtain a loading state image captured in a state where scrap iron is loaded on the loading device; as well as A processor configured to: determining a target area including the scrap iron in the loading state image; Simplifying the target area and converting the simplified target area into a rectangular area; Determine a first length representing lengths of two different sides of the converted rectangular area and a second length greater than the first length; determining the number of divisions of the target area based on a quotient obtained by dividing the second length by the first length; segmenting the loading state image based on the segmentation number and obtaining a plurality of segmented images; and An analysis result of the scrap metal loaded on the loading device is provided by image analysis of the plurality of segmented images.

12. The apparatus for analyzing scrap iron according to claim 11, wherein: When the value of the quotient is N, the processor determines the number of divisions to be a value smaller than two times N by 1.

13. The apparatus for analyzing scrap iron according to claim 12, wherein: The processor is configured to: obtaining N segmented images, wherein the horizontal length and the vertical length of the N segmented images are the first lengths, and the N segmented images do not overlap with each other; and N-1 segmented images are obtained, the N-1 segmented images including boundary lines of the N segmented images and not overlapping each other.

14. The apparatus for analyzing scrap iron according to claim 13, wherein: Each of the N-1 segmented images overlaps with one or two segmented images of the N segmented images.

15. A recording medium for executing the method for analyzing scrap iron according to any one of claims 1 to 10, the recording medium being a computer-readable recording medium on which a program for executing the method for analyzing scrap iron on a computer is recorded.

Images