Automatic steel pipe inventory count measurement system, automatic steel pipe inventory count measurement method, and automatic steel pipe inventory count measurement device

Abstract

The objective is to provide an automated steel pipe inventory counting system that allows for easy management of steel pipe inventory without having to attach identification marks to individual steel pipes. [Solution] The automatic steel pipe inventory count measurement system 100 includes an image acquisition means for acquiring an image including cross-sections of multiple steel pipes 50, an object identification means for identifying multiple objects included in the image as individual objects, a display means for displaying the image in a manner in which the identified individual objects are visible, a designation receiving means for receiving the designation of target objects from among the objects in the image to be measured in quantity, an identity determination means for performing an identity determination of whether objects in the image belong to the same range as the target object based on the shape of the target object, and a quantity measuring means for measuring the number of objects belonging to the same range.

Description

Technical Field

[0005] , , , , , ,

[0004] ,

[0001] The present invention relates to a steel pipe inventory quantity automatic measurement system, a steel pipe inventory quantity automatic measurement method, and a steel pipe inventory quantity automatic measurement device.

Background Art

[0002] Conventionally, as an inventory management system, a system has been proposed in which an identification mark is attached to a container of an item, and the inventory is managed by reading the identification mark in an image captured by a camera. (For example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, attaching an identification mark to each individual item or the container of the item can be extremely cumbersome. For example, in a steel pipe processing factory that processes steel pipes, steel pipes are purchased from a steel pipe manufacturing company, stored as inventory, and processed such as cutting the steel pipes to a predetermined length according to a specific order. Steel pipes are generally stacked and stored in a state where the cross section (end face) is visible. Therefore, if an identification mark is to be attached to each steel pipe, it will be attached to the visible cross section. However, since the cross section is annular and the area is extremely small compared to the outer peripheral surface in the length direction, it is not easy to attach an identification mark. In addition, attaching identification marks to the cross sections of a large number of steel pipes is also cumbersome.

[0005] It is possible to build a neural network capable of recognizing the type of steel pipe by performing machine learning on all types of stored steel pipes using images in various forms. However, performing machine learning on each of the many types of steel pipes individually would require a great deal of time and electricity. For example, even steel pipes with a circular cross-section have various specifications, and slight differences in diameter or wall thickness result in different types of steel pipes. In inventory management, it is necessary to identify not only cylindrical objects but also the type of steel pipe. For this reason, it is practically impossible to perform machine learning on many types of steel pipes completely automatically. The physical task of humans creating image data for each type of steel pipe and loading it into a computer is unavoidable, which takes a considerable amount of time and also consumes electricity for machine learning.

[0006] The present invention attempts to solve the aforementioned problems and aims to provide an automatic steel pipe inventory count measurement system, an automatic steel pipe inventory count measurement method, and an automatic steel pipe inventory count measurement device that can easily manage steel pipe inventory without having to attach identification marks to individual steel pipes. [Means for solving the problem]

[0007] This is an automatic steel pipe inventory count measurement system for measuring the number of multiple steel pipes that are placed on a surface, wherein the multiple steel pipes are placed in a state in which the cross-section of each steel pipe is visible from the outside, and the shape of the steel pipes is not pre-registered in the automatic steel pipe inventory count measurement system, and the automatic steel pipe inventory count measurement system comprises: an image acquisition means for acquiring an image including the cross-sections of the multiple steel pipes; an object identification means for identifying multiple objects included in the image acquired by the image acquisition means as individual objects; a display means for displaying the image in a manner in which the individual objects identified by the object identification means are visible; a designation receiving means for receiving the designation of a target object which is an object to be measured in quantity from among the objects in the image displayed by the display means; an identity determination means for performing an identity determination, which is a determination of whether or not the object in the image belongs to the same range as the target object based on the shape of the target object; and a quantity measuring means for measuring the number of objects belonging to the same range determined by the identity determination means.

[0008] According to the configuration of the first invention, individual objects in an image can be identified by the object identification means, and the object to be measured can be designated by the designation receiving means. Then, the identity determination means determines, based on shape, whether each object in the image belongs to the same range as the target object, and the quantity measurement means can measure the number of objects that belong to the same range as the target object. Thus, according to the configuration of the first invention, it is possible to determine whether objects belong to the same range as the target object based on their shape and to measure the number of objects that belong to the same range as the target object. For this reason, it is not necessary to attach identification marks to individual steel pipes, nor is it necessary for the shapes of the steel pipes to be pre-registered in the automatic steel pipe inventory count measurement system. Furthermore, since identity determination is performed based on shape by the identity determination means, the object identification means can be a general-purpose object identification program, and it is not necessary to perform machine learning for each type of steel pipe.

[0009] The second invention is an automatic steel pipe inventory counting system, wherein, in the configuration of the first invention, the display means displays the cross-section of the object in a manner that is easier to identify than other objects, and the identity determination means is configured to perform the identity determination based on the target object and the outer and inner contours of each object in the image.

[0010] Steel pipes are cylindrical objects, and their specifications are clearly evident in their cross-section (end face). In an image obtained by photographing a steel pipe, only one cross-section appears for each steel pipe. Therefore, the number of cross-sections in the image is equal to the number of steel pipes, and measuring the number of cross-sections is equivalent to measuring the number of steel pipes. The shape of the cross-section of a cylindrical object is defined by its outer and inner contours. The inventors of the present invention focused on the above facts and configured the display means in the configuration of the second invention to display the cross-section in a manner that is easier to identify than other objects, so that the user can easily specify the cross-section as the target object. Furthermore, the identity determination means performs identity determination based on the outer and inner contours that define the cross-section. This makes it possible to quickly measure the number of steel pipes in stock with relatively low power consumption, based on the minimum necessary information to identify individual steel pipes.

[0011] The third invention is an automatic steel pipe inventory count measurement system in which, in the configuration of the second invention, the identity determination means is configured to generate a modified object by removing portions of the outer contour and inner contour of the object that lack continuity, and to perform the identity determination based on the outer contour and inner contour of the target object and the modified object.

[0012] Steel pipe manufacturers cut steel pipes to the appropriate lengths and deliver them to steel pipe processing plants. Because steel pipe manufacturers cut a large number of steel pipes within a set time, they tolerate a certain degree of irregularity in the cut surface. As a result, the cut surface of the steel pipe may differ from the original designed shape, and burrs may be present on the cut surface (end face). A burr is a residue on the outside of the geometric shape at the corner edge, and is a residue on the part from the machining or forming process. In steel pipe processing plants, if burrs are present, the area near the end face of the steel pipe is cut to remove the burr before the desired processing is carried out. As described above, steel pipe processing plants use steel pipes with burrs for processing, so it is necessary to keep track of the quantity in stock. Furthermore, when focusing on the inner and outer contours of the steel pipe, the burred portion deviates from the original contour and lacks continuity with the contour of the non-burred portion. In this regard, according to the configuration of the third invention, the identity determination means is configured to remove the burr portion as a part lacking continuity in shape to generate a modified object, and to perform identity determination based on the outer and inner contours of the target object and the modified object. As a result, even if the number of steel pipes in stock includes steel pipes with burrs, the number of stocked pipes can be accurately measured.

[0013] The fourth invention is an automatic steel pipe inventory count measurement system in which, in the configuration of the second invention, the identity determination means determines that the object belongs to the same range when the extent to which the outer contour of the object protrudes from the outer contour of the target object is within a predetermined range, and the difference between the area of ​​the object and the area of ​​the target object is within a predetermined range.

[0014] Steel pipes with a non-circular cross-section (hereinafter referred to as "irregularly shaped steel pipes") have the characteristic that, compared to steel pipes with a circular cross-section, distortion of the cross-section is more likely to occur when steel pipe manufacturers cut the steel pipes to the appropriate length. In steel pipe processing plants, if distortion of the cross-section occurs, the distorted portion is removed by cutting near the end face of the steel pipe before the desired processing is carried out. As described above, steel pipe processing plants use steel pipes with distorted cross-sections for processing, so it is necessary to keep track of the quantity in stock. A characteristic of irregularly shaped steel pipes is that even if distortion of the cross-section occurs, the outer contour is unlikely to protrude from the outer contour of the original cross-sectional shape. Also, even if distortion of the cross-section occurs, the thickness of the steel pipe (the distance between the inner contour and the outer contour) does not change, so the difference in area from the original cross-section is small, or is substantially the same. In this regard, according to the configuration of the fourth invention, if the extent to which the outer contour of the object protrudes from the outer contour of the target object is within a predetermined range, and the difference between the area of ​​the object and the area of ​​the target object is within a predetermined range, the object is determined to belong to the same range. Therefore, even if the cross-section of the steel pipe is distorted, the identity determination can be correctly made. Furthermore, the fourth invention is not limited to the quantity measurement of irregularly shaped steel pipes, but can also be applied to the quantity measurement of steel pipes with a circular cross-section.

[0015] The fifth invention is an automatic steel pipe inventory count measurement system according to claim 2, wherein, in the configuration of the first invention, the identity determination means determines that the object belongs to the same range when the outer contour of the object does not protrude from the outer contour of the target object and the difference between the area of ​​the object and the area of ​​the target object is within a predetermined range.

[0016] A characteristic of deformed steel pipes is that even if distortion occurs in the cross-section, the deformation usually occurs inward, and the possibility of the outer contour protruding from the outer contour of the original cross-sectional shape is low. In this respect, according to the configuration of the fifth invention, if the outer contour of the object does not protrude from the outer contour of the target object, and the difference between the area of ​​the object and the area of ​​the target object is within a predetermined range, the object is judged to belong to the same range. Therefore, even if distortion occurs in the cross-section of the steel pipe, the identity judgment can be correctly performed. Furthermore, the fifth invention is not limited to the quantity measurement of deformed steel pipes, but can also be applied to the quantity measurement of steel pipes with a circular cross-section.

[0017] The sixth invention is an automatic steel pipe inventory count measurement system in which, in the configuration of the first invention, the identity determination means performs the identity determination only on closed, annular objects.

[0018] Whether a steel pipe has a circular cross-section or a non-circular cross-section, its cross-section is a closed annular shape. In other words, the cross-section of a steel pipe in an image appears as a closed shape that encloses other objects or spaces. In this respect, according to the configuration of the sixth invention, since the identity determination means performs identity determination only on closed annular objects, it eliminates the possibility of mistakenly recognizing an object other than a steel pipe as a steel pipe, reduces the processing man-hours, and as a result, speeds up processing and reduces the amount of electricity consumed.

[0019] The seventh invention is an automatic steel pipe inventory count measurement system in which, in the configuration of the first invention, the identity determination means generates shape prediction information that predicts changes in the shape of the target object according to differences in position in the image, based on a plurality of objects recognized as belonging to the same range as the target object, and performs the identity determination based on the shape of the target object corrected by the shape prediction information.

[0020] In a steel pipe processing plant, if identical steel pipes are stored over a wide area, even if they have the same cross-section, the cross-sectional shape of a steel pipe located in the center of an image will differ from that of a steel pipe located at the edge of the image, even if the cross-section is the same. If the target object is a cross-section of a steel pipe located in the center of the image, objects near the center are likely to have differences in cross-sectional shape within a predetermined range, and are therefore judged to belong to the same range as the target object. In contrast, objects located far from the center may have significant differences in cross-sectional shape and may not be judged to belong to the same range. However, even if objects near the center and the target object are judged to belong to the same range, their shapes are not identical, and their different characteristics depend on the degree of positional deviation from the target object. This means that, for objects belonging to the same range as the target object, how the shape changes depending on the degree of deviation from the target object is known information, and based on this known information, shape prediction information can be generated to predict the shape of objects that are farther from the target object. In this regard, according to the configuration of the seventh invention, the identity determination means generates shape prediction information that predicts changes in the shape of the target object in accordance with differences in position in the image, based on a plurality of objects recognized as belonging to the same range as the target object, and performs identity determination based on the shape of the target object corrected by the shape prediction information. Therefore, even objects that are located at a position far from the target object and whose shapes appearing in the image are relatively large and different from those of the target object can be determined to be objects belonging to the same range.

[0021] The eighth invention is an automatic steel pipe inventory count measurement system according to claim 1, wherein, in the configuration of the first invention, the identity determination means generates shape prediction information that predicts changes in the shape of the target object according to differences in position in the image, based on a plurality of objects recognized as belonging to the same range as the target object, corrects the object subject to identity determination using the shape prediction information to generate a corrected object, and performs the identity determination based on the corrected object.

[0022] The ninth invention is an automatic steel pipe inventory count measuring device for measuring the number of multiple steel pipes placed on a surface, wherein the multiple steel pipes are placed in a state in which the cross-section of each steel pipe is visible from the outside, and the shape of the steel pipes is not pre-registered in the automatic steel pipe inventory count measuring device, and the automatic steel pipe inventory count measuring device comprises: an image acquisition means for acquiring an image including the cross-sections of the multiple steel pipes; an object identification means for identifying multiple objects included in the image acquired by the image acquisition means as individual objects; a display means for displaying the image in a manner in which the individual objects identified by the object identification means are visible; a designation receiving means for receiving the designation of a target object which is an object to be measured in quantity from among the objects in the image displayed by the display means; an identity determination means for performing an identity determination, which is a determination of whether or not the object in the image belongs to the same range as the target object based on the shape of the target object; and a quantity measuring means for measuring the number of objects belonging to the same range determined by the identity determination means.

[0023] The tenth invention is an automatic method for measuring the number of steel pipes in stock, which measures the number of a plurality of placed steel pipes. The plurality of steel pipes are placed in a state where the cross-section of each steel pipe is visible from the outside, and the shape of the steel pipe is not registered in the automatic steel pipe inventory number measurement system in advance. The automatic steel pipe inventory number measurement method includes an image acquisition step for acquiring an image including the cross-sections of the plurality of steel pipes, an object identification step for identifying a plurality of objects included in the image acquired by the image acquisition means as individual objects, a display step for displaying an image in a manner where the individual objects identified by the object identification means are visible, a designation reception step for receiving a designation of a target object that is an object to be measured for quantity among the objects in the image displayed by the display means, an identity determination step for performing an identity determination that is a determination as to whether the objects in the image belong to the same range as the target object based on the shape of the target object, and a quantity measurement step for measuring the number of the objects belonging to the same range determined by the identity determination means. It is an automatic steel pipe inventory number measurement method including these steps.

Effects of the Invention

[0024] According to the present invention, it is possible to easily manage the inventory of steel pipes without attaching identification marks to individual steel pipes.

Brief Description of the Drawings

[0025] [Figure 1] It is an overall view showing an automatic steel pipe inventory number measurement system according to the first embodiment of the present invention. [Figure 2] It is a diagram showing the functional configuration of a measuring device in an automatic steel pipe inventory number measurement system. [Figure 3] It is a conceptual diagram showing a neural network. [Figure 4] It is a schematic diagram showing a cylindrical steel pipe. [Figure 5] It is a schematic diagram showing the state of steel pipe inventory and the appearance in an image. [Figure 6] It is a conceptual diagram showing a method for determining similarity. [Figure 7] This is a conceptual diagram illustrating a method for determining identity. [Figure 8] This is a mathematical formula that shows how to determine identity. [Figure 9] This is a schematic flowchart illustrating a method for measuring objects within the same range as the target object. [Figure 10] This flowchart shows how to recognize objects belonging to the same range. [Figure 11] This is a schematic diagram showing a cylindrical steel pipe with burrs, which is the subject of the second embodiment. [Figure 12] This is a conceptual diagram showing the separation of a steel pipe with burrs from the burrs themselves. [Figure 13] This is a conceptual diagram showing the target object, etc. [Figure 14] This is a conceptual diagram illustrating a method for determining identity. [Figure 15] This flowchart shows how to recognize objects belonging to the same range. [Figure 16] This is a schematic diagram showing a steel pipe with an irregularly shaped cross-section, which is the target of the third embodiment. [Figure 17] This is a schematic diagram showing the inventory status of irregularly shaped steel pipes. [Figure 18] This is a conceptual diagram illustrating a method for determining identity. [Figure 19] This flowchart shows how to recognize objects belonging to the same range. [Figure 20] This is a flowchart showing a method for recognizing objects belonging to the same range in the fourth embodiment. [Figure 21] This is a conceptual diagram showing an automatic steel pipe inventory count measurement system according to a fifth embodiment of the present invention. [Figure 22] This is a conceptual diagram illustrating a method for determining identity. [Figure 23] This is a flowchart showing a method for recognizing objects belonging to the same range in the fifth embodiment. [Modes for carrying out the invention]

[0026] The embodiments for carrying out the present invention will be described in detail below. In the following description, the same reference numerals will be used for similar components, and their descriptions will be omitted or simplified. Furthermore, descriptions of components that can be appropriately implemented by those skilled in the art will be omitted, and only the basic components of the present invention will be described.

[0027] <First Embodiment> Referring to Figure 1, the outline of the automatic steel pipe inventory count measurement system 100 (hereinafter referred to as "System 100") of this embodiment will be described. As shown in Figure 1, System 100 has a portable terminal 1 (hereinafter referred to as "Terminal 1"). Terminal 1 is a measuring device for measuring and recording the number of steel pipes 50 and 60. Terminal 1 is an example of an automatic steel pipe inventory count measurement device.

[0028] The steel pipes 50 and 60 are placed on the shelf 70, separated by type, so that the cross-section (end face) of each steel pipe 50 and 60 is visible from the outside. The steel pipe 50 is placed in area 110, which is a predetermined location, and the steel pipe 60 is placed in area 120, which is a predetermined location. The shapes of the steel pipes 50 and 60 are not pre-registered in terminal 1. Furthermore, different configurations of the steel pipes 50 and 60 are not learned by machine learning to generate a recognition program.

[0029] Terminal 1 uses a camera 2 built into Terminal 1 to photograph the steel pipes 50 and 60 and displays the images on the display screen 4 of the display device (hereinafter referred to as "screen 4"). The camera 2 is located on the front surface 1a of Terminal 1, and screen 4 is located on the back surface 1b of Terminal 1.

[0030] Terminal 1 is, for example, a smartphone. When the user specifies a single steel pipe 50 from the objects displayed on screen 4, terminal 1 measures the total number of steel pipes 50 included in the image, records that number internally, and displays it on screen 4. The displayed information includes the date, location, and quantity, as shown in Figure 1. If terminal 1 has data that associates the location with the type of steel pipe 50, it can also display the type and model number of the steel pipe 50 on screen 4. The quantity of steel pipes 50 includes the specified steel pipe 50 itself.

[0031] Figure 2 shows the functional configuration of terminal 1. As shown in Figure 2, terminal 1 has a CPU (Central Processing Unit) 10, a storage unit 12, a camera unit 14, an image display unit 16, and a satellite positioning unit 18.

[0032] Terminal 1 controls the camera 2 built into Terminal 1 via the camera unit 14 to acquire image data of external objects. The image is then displayed on the screen 4 by the image display unit 16. The CPU 10 and camera unit 14 together constitute an example of an image acquisition means. The CPU 10 and camera unit 14 acquire an image including cross-sections of multiple steel pipes 50 and 60 placed in predetermined positions. Hereafter, when it is written that "an image is acquired by the camera unit 14," the CPU 10 is omitted, and it actually means "an image is acquired by the CPU 10 and the camera unit 14." The same applies to other parts and programs, and the "CPU 10" is omitted as appropriate.

[0033] Terminal 1 determines its current location using the satellite positioning unit 18. The satellite positioning unit 18 basically measures the position of Terminal 1 by receiving positioning radio waves from four or more navigation satellites.

[0034] The memory unit 12 stores various data and programs for controlling each part of the terminal 1. Furthermore, the memory unit 12 stores an object identification program 31, a display program 32, a designated receipt program 33, an identity determination program 34, a quantity measurement program 35, and a quantity recording program 36.

[0035] The object identification program 31 is a program for identifying multiple objects in image data acquired by the camera unit 14 of the terminal 1 as individual objects. The CPU 10 and the object identification program 31 together constitute an example of an object identification means. The object identification program 31 identifies individual objects included in the image acquired by the camera unit 14 from other objects.

[0036] The object recognition program 31 includes a neural network and uses the neural network to recognize objects. The neural network is generated by machine learning. When a large amount of image data is input as training data into the computer's neural network model (see Figure 3), learning is performed by the neural network's algorithm. The training data is, for example, data showing parts and components of various shapes.

[0037] The neural network model is, for example, the neural network conceptually shown in Figure 3. Since neural networks and deep learning are well-known, only a brief overview will be provided in this specification. A neural network consists of an input layer, one or more hidden layers, and an output layer. Although Figure 3 shows only one hidden layer, in reality, there are multiple hidden layers. That is, the learning in this embodiment is machine learning (deep learning) using a multi-layered neural network (deep neural network).

[0038] In machine learning, the output from the output layer is adjusted to approximate the correct answer by adjusting the input weights w1a, etc., of the input values ​​input to the hidden layer and the output layer, and the biases (thresholds in each layer) B1, etc., in the input layer, hidden layer, and output layer. As a result of learning, a neural network with adjusted weights and biases is generated as learning result data. Through this learning, for example, a neural network for accurately identifying objects in an image is generated. The memory unit 12 stores the neural network generated in this way.

[0039] The object recognition program 31 can use a general-purpose object recognition program, for example, Segment Anything, an image-based model provided by META Corporation. An image-based model refers to a model that has been pre-trained on a large amount of data and can be used generally. The technical feature of this embodiment is that it uses a general-purpose program for object recognition, and instead of using a neural network generated by machine learning to determine whether or not an object is a specific type of steel pipe, it identifies the characteristics of the steel pipes stored in the steel pipe processing plant and performs the determination using a program that takes those characteristics into account.

[0040] Figure 4 is a schematic diagram showing a cylindrical steel pipe 50. As shown in Figures 4(a) and (b), the steel pipe 50 is composed of a cross section (end face) 50a, an inner circumferential surface 50c, and an outer circumferential surface 50b. The cross section 50a is the cut surface obtained when the steel pipe is cut to an appropriate length at a steel pipe manufacturing company, and since it appears at the end, it is also the end face.

[0041] Terminal 1, using the object recognition program 31, can not only distinguish between individual steel pipes 50, but also recognize the cross-section 50a, inner surface 50c, and outer surface 50b of a single steel pipe 50 as different objects.

[0042] Terminal 1 displays individual objects identified by the object identification program 31 in a visible manner on screen 4 using the display program 32. The multiple steel pipes 50 are, for example, objectively stored as inventory in the manner shown in Figure 5(a). However, as shown in Figure 5(b), even steel pipes 50 of the same specifications are displayed on screen 4 in different manners, for example, at the center and at the ends, reflecting the distance and positional relationship between the lens of camera 2 and each steel pipe 50.

[0043] As shown in Figure 5(a), multiple steel pipes 50 are placed on the shelf 70 in an overlapping manner. The cross-section 50a of each steel pipe 50 is visible from the outside. In contrast, the inner circumferential surface 50c and outer circumferential surface 50b (see Figure 4) may not be visible from the outside depending on the position of each steel pipe 50a. Furthermore, even when the inner circumferential surface 50c and outer circumferential surface 50b are visible from the outside, the degree to which the visible shape differs depending on the position of each steel pipe 50 is greater than in the case of the cross-section 50a.

[0044] As shown in Figure 5(b), in the image acquired by the camera unit 14 of terminal 1, the shape of each steel pipe 50 differs depending on its position in the image. In Figure 5(b), the lens of camera 2 is positioned so that the central steel pipe 50 is centered in the image. For example, the closer to the edges of the image, the more elongated the shape of the steel pipe 50 in the image appears.

[0045] On screen 4, the multiple cross-sections 50a, inner circumferential surfaces 50c, outer circumferential surfaces 50b, and shelves 70 of Figure 5(b) are displayed in a manner that allows them to be distinguished and viewed as separate objects, for example, by being colored in different colors. On screen 4, the cross-section 50a is displayed in a manner that makes it easier to identify than the other objects. For example, the cross-section 50a is displayed in a color with higher brightness than the other objects.

[0046] Terminal 1 receives, via the designation receiving program 33, the designation of a target object from among the objects displayed on screen 4 by the display program 32, which is the object whose quantity will be measured. The CPU 10 and the designation receiving program 33 together constitute an example of a designation receiving means.

[0047] The display screen 4 of terminal 1 shows the image shown in Figure 5(b). The cross section 50a, outer surface 50b, and inner surface 50c are displayed in a distinguishable manner, and the user designates the cross section 50a as the target object by, for example, touching the cross section 50a with a finger or pen. As a result, terminal 1 receives the designation of the target object.

[0048] Terminal 1, using the identity determination program 34, performs identity determination based on the shape of the target object, determining whether an object included in the image belongs to the same range as the target object. The CPU 10 and the identity determination program 34 together constitute an example of identity determination means.

[0049] The identity determination program 34 will be explained with reference to Figures 5 to 8. When the image of Figure 5(b) is displayed on the display screen 4 (see Figure 1) and the cross section 50a is specified as the target object, terminal 1 performs an identity determination to determine whether the objects present in the image belong to the same area as the cross section 50a. Terminal 1 performs an identity determination for each object in the image.

[0050] For example, as shown in Figure 6, terminal 1 compares the shapes of cross-section 50a and cross-section 50ac. Terminal 1 determines the identity of the shapes of cross-sections 50a and 50ac based on the pixels of camera 2. In Figure 6(a), each pixel is shown as a coordinate by rows of numbers 1 to 14 and columns of letters A to N. In reality, as shown in Figure 6(b), pixels in the image are even more finely spaced. The identity determination is performed based on these finely spaced pixels.

[0051] Terminal 1 acquires pixel information for cross-section 50a. Pixel information includes the coordinates (positions) of the pixels of each individual object and the display content for each pixel. Similarly, Terminal 1 acquires pixel information for each individual object in the image.

[0052] Identity determination is performed using pixel information. Specifically, terminal 1 compares the outer contour 50ao of cross section 50a with the outer contour 50aco of cross section 50ac when cross section 50a and cross section 50ac are placed at the same coordinates, and determines the degree of pixel overlap. Similarly, terminal 1 compares the inner contour 50ai of cross section 50a with the inner contour 50aci of cross section 50ac when cross section 50a and cross section 50ac are placed at the same coordinates, and determines the degree of pixel overlap.

[0053] In other words, the pixels used in identity determination are only the outer and inner contours of the target object, and the outer and inner pixels of each object. Therefore, compared to using all the pixels of the target object and each object, the processing burden on terminal 1 is smaller, and power consumption is also lower.

[0054] For example, as shown in Figures 7(a) to (d), terminal 1 compares cross section 50a and cross section 50ac. As shown in Figure 7(d), terminal 1 determines the degree of pixel overlap in the comparison between the outer contour 50ao of cross section 50a and the outer contour 50aco of cross section 50ac, and the degree of pixel overlap in the comparison between the inner contour 50ai of cross section 50a and the inner contour 50aci of cross section 50ac, when the cross sections 50a and cross section 50ac are arranged to overlap as much as possible, that is, when the number of overlapping pixels is maximized.

[0055] Equation 1, shown in Figure 8, defines "Sim out" as the degree of pixel overlap in the outer contour. The number of pixels in the outer contour of the target object, cross section 50a, is defined as "number of all pixels of target object". The degree of overlap (Sim out) is defined as the ratio of the number of overlapping pixels in the outer contour 50ao and contour 50aco to the total number of pixels in the outer contour 50a.

[0056] Similarly, equation 2 defines "Sim in" as the degree of pixel overlap in the inner contour, and defines the degree of overlap (Sim in) as the ratio of the number of overlapping pixels in the inner contour 50ai and contour 50aci to the number of pixels in the inner contour of the target object, which is cross section 50a.

[0057] As shown in Equation 3, terminal 1 determines that sections 50a and 50ac belong to the same range when the overlap degree "Sim out" is equal to or greater than the reference value ratio a1, and as shown in Equation 4, the overlap degree "Sim in" is equal to or greater than the reference value ratio b1. Ratio a1 is, for example, 0.8. Similarly, ratio b1 is, for example, 0.8.

[0058] Terminal 1 measures the number of objects belonging to the same range as the target object using the quantity measurement program 35. The CPU 10 and the quantity measurement program 35 together constitute an example of a quantity measurement means. As described above, Terminal 1 measures the number of objects belonging to the same range, where both ratio a1 and ratio b1 are 0.8 or higher, which is the reference value. The target object itself is also included in the number of objects belonging to the same range.

[0059] Terminal 1 stores the number of objects belonging to the same range as the target object in the storage unit 12 using the quantity recording program 36. The CPU 10 and the quantity recording program 36 together constitute an example of a quantity recording means.

[0060] Terminal 1 displays the number of objects belonging to the same range as the target object on screen 4 (see Figure 1) using the display program 32.

[0061] Next, with reference to Figures 9 and 10, the method for measuring inventory quantities using terminal 1 described above will be briefly explained again.

[0062] When terminal 1 acquires an image including the steel pipe 50 (see Figure 1) using camera 2 (step ST1, image acquisition step in Figure 9), it identifies the object in the image (step ST2, object identification step) and displays the object on screen 4 (see Figure 1) in a manner that can be specified by the user (step ST3, display step). When terminal 1 receives the user's specification of a target object (step ST4, specification receipt step), it determines the objects in the image that belong to the same range as the target object (step ST5, identity determination step), measures the number of objects that belong to the same range as the target object (step ST6, quantity measurement step), records the number of objects that belong to the same range as the target object (recording step), and displays it on screen 4 (step ST7, result display step). In step ST7, the image used to measure the number of objects is also recorded in association with the number of objects. This allows the number of objects to be measured again at a later date, and also allows for the recording and management of fluctuations in inventory quantities.

[0063] In the identity determination step (step ST5) described above, as shown in Figure 10, pixel information of the target object is acquired (step ST51), and pixel information of each object in the image is also acquired (step ST52). The process is then limited to objects where the overlap ratio of pixels of the outer contour of the target object and the pixels of the outer contour of the object is greater than or equal to a predetermined value (step ST53). Furthermore, the process is limited to objects where the overlap ratio of pixels of the inner contour of the target object and the pixels of the inner contour of the object is greater than or equal to a predetermined value (step ST54). The objects remaining after the limitation in steps ST53 and ST54 are determined to be objects belonging to the same range as the target object. Note that, unlike this embodiment, the order in which steps ST53 and ST54 are performed may be reversed, or steps ST53 and ST54 may be performed simultaneously.

[0064] <Second Embodiment> The second embodiment will be described with reference to Figures 11 to 15. The explanation will omit details common to the first embodiment and focus on the differences.

[0065] As shown in Figure 11, the inventory of steel pipes may include steel pipes 50A that have burrs. Steel pipe 50A is originally a steel pipe with a circular cross-section (end face). When steel pipes are cut to a predetermined length at a steel pipe manufacturing plant, steel pipes with a circular cross-section do not deform in principle because they have strong mechanical strength against external forces. However, burrs may form on the cross-section of steel pipes with a circular cross-section. When burrs form, the contour of the cross-section deviates from the original shape. This embodiment relates to measuring the inventory quantity when the inventory includes steel pipes with burrs on the cross-section.

[0066] As shown in Figures 11(a) and (b), burrs 50c are present in steel pipe 50A. The cross section 50ac of steel pipe 50A, excluding the burrs 50c, is within the same range as the cross section 50a of steel pipe 50 (see Figure 4).

[0067] Incidentally, burrs are formed when long steel pipes are cut to the appropriate length at steel pipe manufacturing companies, and are parts that lack continuity from the cross-sectional contour shape. In images, they are parts where the pattern of continuous pixels changes abruptly. Furthermore, burrs on steel pipes do not occupy a large area of ​​more than 50% of the outer or inner contour of the steel pipe, but rather occupy a relatively small area.

[0068] In a cylindrical steel pipe 50, the outer and inner contours have a predetermined radius of curvature. In the image, the pixels constituting these contours are continuous and have a predetermined radius of curvature. The portion that deviates from the predetermined radius of curvature is a burr. Alternatively, in the original cross-sectional shape without burrs, the distance between the outer and inner contours is substantially the same in all parts, so a portion where this distance differs from other parts may be judged as a burr. For this reason, for example, as shown in Figure 12(a), in the cross-section 50ac of the steel pipe 50A, it is possible to recognize the original inner contour 50a2p, separate the burr 50c, and generate the original contour cross-section 50acr, as shown in Figure 12(b).

[0069] As shown in Figure 13, when the cross section 50a of the steel pipe 50 is designated as the target object, terminal 1 also performs identity verification with the cross section 50ac where burrs have formed. Terminal 1 uses the identity determination program 34 (see Figure 2) to remove the burrs 50c that lack continuity with the shape of the inner contour 50a2 of the cross section 50ac, as shown in Figures 14(a) and (b), and generates the cross section 50acr as a modified object in the memory unit 12 of terminal 1.

[0070] As shown in Figures 14(c) and (d), terminal 1 determines whether cross-section 50acr belongs to the same range as cross-section 50a based on the outer and inner contours of cross-section 50a, which is the target object, and cross-section 50acr, which is the modified object.

[0071] Referring to Figure 15, the method for measuring the quantity of inventory using terminal 1 described above when burrs are present on a steel pipe with a circular cross-section will be briefly explained. In the identity determination step (step ST5 in Figure 9), as shown in Figure 15, a corrected object is generated by removing parts that lack continuity in the outer and inner contours of the object in the image (step ST521), and the objects are limited to those in which the overlap ratio of pixels of the outer contour of the target object and the outer contour of the corrected object is greater than or equal to a predetermined value (step ST53), and further limited to those in which the overlap ratio of pixels of the inner contour of the target object and the inner contour of the corrected object is greater than or equal to a predetermined value (step ST54). The objects remaining after the limitation in steps ST53 and ST54 are determined to be objects belonging to the same range as the target object.

[0072] In the case of steel pipes with irregular cross-sections rather than circular ones, the outer and inner contours of the cross-section cannot be said to have a predetermined radius of curvature. However, even if the cross-section is distorted, the distance between the outer and inner contours, i.e., the thickness of the steel pipe, is substantially the same in all parts. Therefore, for example, the parts where the thickness of the steel pipe changes can be removed as burrs, and the identity can be recognized as described above.

[0073] <Third Embodiment> A third embodiment will be described with reference to Figures 16 to 19. The explanation will omit details common to the first and second embodiments, and will focus on the differences.

[0074] As shown in Figure 16, the cross-section 52a of a steel pipe may not be circular. In this specification, a steel pipe with a non-circular cross-section is referred to as a "deformed steel pipe." Deformed steel pipes have the characteristic that, when cut to a predetermined length at a steel pipe manufacturing plant, their cross-section is more likely to be distorted compared to steel pipes with a circular cross-section. Furthermore, even if distortion occurs in the cross-section, the thickness, which is the distance between the outer and inner surfaces, does not change, so the area of ​​the cross-section is substantially the same as the original. This embodiment focuses on the characteristics of deformed steel pipes described above and relates to the measurement of inventory quantities of deformed steel pipes.

[0075] Figure 17 is a schematic diagram showing the inventory status of deformed steel pipes 52. As shown in Figure 17(a), in the inventory area of ​​steel pipes 52 with the original cross-sectional shape, there are deformed steel pipes 52A and 52B with distorted cross-sectional shapes.

[0076] As shown in Figure 17(b), the cross-sections of the deformed steel pipes 52A and 52B are distorted compared to the cross-section 52a of the steel pipe 52, as shown in cross-sections 52Aa and 52Ba. However, there is no significant difference in the cross-sectional area between cross-section 52a and 52Aa and 52Ba, and they are substantially the same.

[0077] Terminal 1 uses the identity determination program 34 (see Figure 2) to determine whether the degree to which the outer contour of cross section 52Ba protrudes from the outer contour of cross section 52a (hereinafter referred to as "degree of protrusion") is within a predetermined range.

[0078] In Figure 18(a), the outer contour of cross section 50a is X1 in the horizontal direction and Y1 in the vertical direction. The outer contour of cross section 52Ba is X2 in the horizontal direction and Y2 in the vertical direction. In this embodiment, X1 and X2 are equal, and Y1 and Y2 are equal. Therefore, it is determined that the outer contour of the object does not protrude from the outer contour of the target object. The predetermined range of protrusion is, for example, when S2 is the difference in the number of pixels between the target object and the outer contour of the object, the ratio (S2 / S1) of the difference S2 to the total number of pixels (S1) of the outer contour of the target object is within the range of plus or minus 5% (±5%).

[0079] Furthermore, terminal 1 determines that an object belongs to the same area as the target object if the difference between the area of ​​the object and the area of ​​the target object (hereinafter referred to as "area difference") is within a predetermined range. In Figure 18(b), the number of pixels occupied by cross section 50a is c1, and the number of pixels occupied by cross section 52Ba is c2. Terminal 1 compares c1 and c2 to determine whether the area difference is within a predetermined range. The predetermined range of the area difference is, for example, when S3 is the difference in the number of pixels between the target object and the object, the ratio (S3 / S4) of the difference S3 to the total number of pixels of the target object (S4) is within plus or minus 3% (±3%). In this embodiment, S3 is the difference between c1 and c2, and S4 is c1.

[0080] Note that in Figure 18(a), for convenience, one pixel is displayed larger, so the difference between the number of pixels in the outer contour and the number of pixels in the area is small. However, in reality, the number of pixels that make up cross-sections 50a and 50Ba is extremely large, and it is clear that the number of pixels that make up the outer contour is less than the number of pixels that make up the area.

[0081] Referring to Figure 19, the method for measuring the inventory quantity of deformed steel pipes using terminal 1 will be briefly explained. In the identity determination step (step ST5 in Figure 9), as shown in Figure 19, the method is limited to objects whose degree of protrusion is within a predetermined range (step ST55), and further limited to objects whose area difference is within a predetermined range (step ST56). The objects remaining after the limitation in steps ST55 and ST56 are determined to be objects belonging to the same range as the target object.

[0082] Unlike Figures 17 and 18, it is also possible that the deformed steel pipe may be crushed laterally. In this case, X2 will be larger than X1 in Figure 18(a). Even in this case, if the ratio of the difference S2 to the total number of pixels (S1) of the outer contour of the object (S2 / S1) is within a predetermined range, and the difference between the area of ​​the object and the area of ​​the object (hereinafter referred to as "area difference") is within a predetermined range, the object is judged to belong to the same range as the object. Unlike this embodiment, in determining identity, instead of "the degree of protrusion is within a predetermined range," it may be stated that "the outer contour of the object does not protrude from the outer contour of the object." This is because when the cross-section of a deformed steel pipe is distorted, it usually deforms inward.

[0083] <Fourth Embodiment> The fourth embodiment will be described primarily with reference to Figure 20. Matters common to the first to third embodiments will be omitted from the explanation, and the focus will be on the differences.

[0084] Whether a steel pipe has a circular cross-section or a non-circular cross-section, its cross-section is a closed annular shape. In other words, the cross-section of a steel pipe in an image appears as a closed shape that encloses other objects or spaces. "Closed" means that the walls between the outer and inner surfaces form a continuous cylindrical shape with no gaps. For example, the steel pipes 50 and 60 shown in Figure 1 have circular cross-sections and are closed annular shapes. Also, the non-circular cross-section of the non-circular steel pipe 52 shown in Figure 16 is not a circular cross-section, but it is a closed annular shape that encloses a space. In contrast, the shelf 70 in Figure 1 is neither annular nor has a closed shape that encloses other objects or spaces. In the fourth embodiment, terminal 1 focuses on the above-mentioned characteristics of steel pipes and limits the object of identity determination to closed annular objects using the identity determination program 34 (see Figure 2).

[0085] Referring to Figure 20, the method for measuring the quantity of inventory by terminal 1 in the fourth embodiment will be briefly explained. In the identity determination step (step ST5 in Figure 9), as shown in Figure 20, the selection is limited to objects that are closed rings (step ST522 in Figure 20). Subsequently, the selection is limited to objects where the overlap ratio of pixels of the outer contour of the target object and the pixels of the outer contour of the object is greater than or equal to a predetermined value (step ST53). Furthermore, the selection is limited to objects where the overlap ratio of pixels of the inner contour of the target object and the pixels of the inner contour of the object is greater than or equal to a predetermined value (step ST54). The objects remaining after the limitation in steps ST522, ST53, and ST54 are determined to be objects belonging to the same range as the target object.

[0086] <Fifth Embodiment> The fifth embodiment will be described primarily with reference to Figures 21, 22, and 23. Matters common to the first to fourth embodiments will be omitted from the explanation, and the differences will be the focus of the description. Even for cross-sections of the same type and type of steel pipe 50, the shape represented will differ depending on the position in the image. Even objects judged to belong to the same range as the target object will have a different shape. However, there is a certain regularity in the manner in which the shape differs from the target object. This embodiment aims to correctly determine identity even for objects with significant shape differences from the target object, by focusing on the regularity in the manner of shape differences among objects belonging to the same range as the target object.

[0087] Figure 21(a) shows an example of an image when the steel pipes 50 are stored over a wide area. In Figures 21(a) and (b), the central position of the effect 50 located in the center is designated as horizontal position 0, and the positions are shown from 0 to 20. As shown in Figure 21(a), in the image acquired by the camera unit 14 (see Figure 2), the diameter of the cross-sectional shape of the steel pipe 50 located in the central part of the image is φ1, and the diameter of the steel pipe 50 located at the edge of the image is φ5, with φ5 being smaller than φ1. The object in question is a cross-section 50a with a diameter of φ1. Note that in Figure 21(a), the steel pipes 50 in the center are ellipses, and φ2 to φ5 are the minor axes of the ellipse, but in this specification, for convenience, even the minor axes are simply referred to as diameters.

[0088] As shown in Figure 21(b), objects with diameters φ2 and φ3 satisfy equation 3 (see Figure 8) for their outer contours and equation 4 (see Figure 8) for their inner contours, and are determined to belong to the same range as the target object. However, objects with diameters φ4 and φ5 do not satisfy either or both of equations 3 or 4, and are not determined to belong to the same range as the target object.

[0089] Incidentally, objects with diameters φ2 and φ3 belong to the same range as the target object with diameter φ1, but their diameters are not identical. As shown in Figure 21(b), their different characteristics depend on the degree of positional deviation from the target object with diameter φ1. For this reason, for objects belonging to the same range as the target object, a curve F1 can be calculated that shows how the shape changes depending on the degree of deviation from the target object, and curve F1r can also be calculated by extending curve F1. Curve F1r is shape prediction information that shows how the shape changes depending on the degree of deviation from the target object. Curve F1r allows us to calculate how the shape changes depending on the degree of deviation from the target object.

[0090] As shown in Figures 22(a) and (b), when terminal 1 performs identity determination, the identity determination program 34 (see Figure 2) calculates a curve F1 based on the pixel information of the object determined to be identical, and further calculates a curve F1r. For example, when the target object is cross section 50a and identity determination is performed on cross section 50ac located at position 6.9 in Figure 21(a), the curve F1r is used to calculate the shape when the center of cross section 50a is located at position 6.9, and cross section 50ar is obtained. Then, cross section 50a (Figure 22(a)) is corrected to cross section 50ar. Cross section 50ar is also called the corrected object.

[0091] Then, as shown in Figures 22(c) and (d), terminal 1 determines the degree of pixel overlap in the comparison between the outer contour 50ao of section 50ar and the outer contour 50aco of section 50ac, and the degree of pixel overlap in the comparison between the inner contour 50ai of section 50a and the inner contour 50aci of section 50ac, when the terminal 1 is arranged so that the sections 50ar and 50ac overlap the most, that is, when the terminal 1 is arranged in the manner in which the number of overlapping pixels is greatest.

[0092] Referring to Figure 23, the method for measuring the quantity of inventory by terminal 1 in the fifth embodiment will be briefly explained. In the identity determination step (step ST5 in Figure 9), as shown in Figure 23, shape prediction information F1r is generated from multiple objects belonging to the same range (step ST57), the target object is corrected based on the shape prediction information F1r, and a corrected object is generated (step ST58). Then, the objects are limited to those in which the overlap ratio of pixels of the outer contour of the corrected object and the pixels of the outer contour of the object is greater than or equal to a predetermined value (step ST59). Furthermore, the objects are limited to those in which the overlap ratio of pixels of the inner contour of the corrected object and the pixels of the inner contour of the object is greater than or equal to a predetermined value (step ST60). The objects remaining after the limitation in steps ST59 and ST60 are also determined to be objects belonging to the same range as the target object, similar to the objects remaining after the limitation in steps ST53 and ST54.

[0093] Unlike this embodiment, a corrected object may be generated by calculating the shape of the object if it were at the same position as the target object, based on the shape prediction information F1r and its position in the image of the object to be identified. The target object and the corrected object may then be used as the objects to be identified.

[0094] It should be noted that the present invention is not limited to these embodiments, and any modifications, improvements, etc., that can achieve the objectives of the present invention are included in the present invention. For example, the configurations of the first to fifth embodiments described above may be combined as appropriate. [Explanation of Symbols]

[0095] 1. Mobile device 31 Object Identification Program 32 Display Programs 33 Designated Receipt Program 34 Identity Determination Program 35 Quantity Measurement Program 36 Quantity Recording Program 50,52 Steel pipe 50a, 50ac, 52a cross-section 50b Outer surface 50c Inner surface 100 Steel Pipe Inventory Quantity Automatic Measurement System

Claims

1. This is an automated steel pipe inventory counting system that measures the number of steel pipes that are placed on a surface. The multiple steel pipes are placed in a manner that allows the cross-section of each steel pipe to be visible from the outside, and the shape of the steel pipes is not pre-registered in the automatic steel pipe inventory count measurement system. The aforementioned automatic steel pipe inventory count measurement system is: Image acquisition means for acquiring an image including the cross-sections of multiple steel pipes, Object identification means for identifying multiple objects included in the image acquired by the image acquisition means as individual objects, Display means for displaying an image in which individual objects identified by the object identification means are visible, A designation receiving means for receiving the designation of a target object, which is one of the objects in the image displayed by the display means that is to be measured in quantity, Identity determination means that performs identity determination, which is to determine whether the object in the image belongs to the same range as the target object, based on the shape of the target object, A quantity measuring means for measuring the number of objects belonging to the same range as determined by the identity determination means, An automatic steel pipe inventory count measurement system.

2. The display means displays the cross-section of the object in a manner that makes it easier to identify than other objects. The automatic steel pipe inventory count measurement system according to claim 1, wherein the identity determination means is configured to perform the identity determination based on the target object and the outer and inner contours of each of the objects in the image.

3. The aforementioned identity determination means is, A modified object is generated by removing portions of the outer and inner contours of the object that lack continuity. The automatic steel pipe inventory count measurement system according to claim 2, configured to perform the identity determination based on the outer and inner contours of the target object and the modified object.

4. The aforementioned identity determination means is, The automatic steel pipe inventory count measurement system according to claim 2, wherein the extent to which the outer contour of the object protrudes from the outer contour of the target object is within a predetermined range, and the difference between the area of ​​the object and the area of ​​the target object is within a predetermined range, determines that the object belongs to the same range.

5. The aforementioned identity determination means is, The automatic steel pipe inventory count measurement system according to claim 2, wherein the outer contour of the object does not protrude from the outer contour of the target object, and the difference between the area of ​​the object and the area of ​​the target object is within a predetermined range, and the object is determined to belong to the same range.

6. The identity determination means performs the identity determination only on the closed, annular object. The automatic steel pipe inventory count measurement system according to claim 1.

7. The identity determination means generates shape prediction information that predicts changes in the shape of the target object in accordance with differences in position in the image, based on a plurality of objects that are recognized as belonging to the same range as the target object. The identity determination is performed based on the shape of the target object corrected by the shape prediction information. The automatic steel pipe inventory count measurement system according to claim 1.

8. The identity determination means generates shape prediction information that predicts changes in the shape of the target object in accordance with differences in position in the image, based on a plurality of objects that are recognized as belonging to the same range as the target object. The object subject to the identity determination is corrected using the shape prediction information. Generate a correction object, The identity determination is performed based on the corrected object. The automatic steel pipe inventory count measurement system according to claim 1.

9. This is an automatic steel pipe inventory counting device that measures the number of steel pipes that are placed on a surface. The multiple steel pipes are placed in a manner that allows the cross-section of each steel pipe to be visible from the outside, and the shape of the steel pipes is not pre-registered in the automatic steel pipe inventory count measurement system. The aforementioned automatic steel pipe inventory count measuring device is: Image acquisition means for acquiring an image including the cross-sections of multiple steel pipes, Object identification means for identifying multiple objects included in the image acquired by the image acquisition means as individual objects, Display means for displaying an image in which individual objects identified by the object identification means are visible, A designation receiving means for receiving the designation of a target object, which is one of the objects in the image displayed by the display means that is to be measured in quantity, Identity determination means that performs identity determination, which is to determine whether the object in the image belongs to the same range as the target object, based on the shape of the target object, A quantity measuring means for measuring the number of objects belonging to the same range as determined by the identity determination means, An automatic steel pipe inventory count measuring device.

10. This is an automatic method for measuring the number of steel pipes in stock, which measures the number of steel pipes that are placed on a surface. The multiple steel pipes are placed in a manner that allows the cross-section of each steel pipe to be visible from the outside, and the shape of the steel pipes is not pre-registered in the automatic steel pipe inventory count measurement system. The aforementioned automatic measurement method for the number of steel pipes in stock is: An image acquisition step for obtaining an image including the cross-sections of multiple steel pipes, An object identification step of identifying multiple objects included in the image acquired by the image acquisition means as individual objects, A display step in which an image is displayed in an embodiment in which individual objects identified by the object identification means are visible, A designation receiving step of receiving the designation of a target object, which is one of the objects in the image displayed by the display means that is to be measured in quantity, A step of identity determination, in which an identity determination is performed based on the shape of the target object, which is a determination of whether or not the object in the image belongs to the same range as the target object, A quantity measurement step of measuring the number of objects belonging to the same range as determined by the identity determination means, An automatic method for measuring the number of steel pipes in stock, including those included.

Images