Fastener spacing estimation apparatus

Abstract

To provide an estimation apparatus capable of accurately calculating the spacing between fasteners hammered into board material by accurately identifying the contour lines of the plurality of rectangular board materials attached by a plurality of fasteners.SOLUTION: An estimation apparatus 10 comprises: an image extraction unit 11 for extracting an image of board material and an image of a fastener; a projection transformation unit 12 for performing projection transformation on the extracted image of the board material together with the image of the fastener into a front image viewed from the front; a board number determination unit 13 for determining whether the extracted image of the board material is an image composed of the plurality of board materials based on the positions of the plurality of fasteners; a contour line generating unit 14 for generating contour lines dividing the image of the board material into images of the plurality of board materials if it is determined that the image is composed of the plurality of board materials; and a spacing calculation unit 15 for calculating the spacing between adjacent fasteners for each board material surrounded by the generated contour line.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to a plate contour estimation device that estimates the contour of a rectangular plate from a captured image that includes a plurality of fasteners driven into the plate. [Background technology]

[0002] Conventionally, as shown in Patent Document 1, board materials such as gypsum boards used for interior wall or ceiling materials are attached to a base via a plurality of fasteners such as screws. The fasteners are driven into the board within a prescribed interval along at least the periphery of the board. After the board is installed, the installation state of the board is inspected to see whether the intervals between fasteners in the same fastener row are within the prescribed interval.

[0003] Incidentally, such an inspection can be performed visually, but sometimes multiple plate materials attached with multiple fasteners are photographed to check the mounting state of the plate materials from the captured image. In this case, it is important to identify the contour line (i.e., the peripheral portion) of each plate material. However, since multiple fasteners exist in the vicinity along this contour line, it is expected that the contour line of the plate material cannot be accurately identified from the image of these fasteners. In view of this, for example, Patent Document 2 proposes an estimation device that estimates the contour line of the plate material and the distance between the fasteners by performing edge detection processing from a captured image including the plate material. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2018-031241 A [Patent Document 2] JP 2022-157018 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, when the contours of a plate are accurately detected from an image that includes the plate, an image recognized as one plate may be composed of images of multiple plate materials. As a result, it may be difficult to accurately measure the distance between the fasteners driven into each of the multiple plate materials.

[0006] The present invention has been made in consideration of the above points, and an object of the present invention is to provide an estimation device that can accurately calculate the distance between fasteners driven into a rectangular plate material by accurately identifying the contour line of the plate material, in which a plurality of fasteners are attached to the plate material. [Means for solving the problem]

[0007] In consideration of the above problems, a fastener spacing estimation device according to the present invention is an estimation device that estimates spacing between adjacent fasteners among a plurality of fasteners that are driven into each of a plurality of rectangular plate materials along a contour line of the plate material, and is characterized by having at least an image extraction unit that extracts an image of the plate material and an image of the fasteners from an overall image including the plate material captured by an imaging device, a projection transformation unit that projectively transforms the extracted image of the plate material together with images of the fasteners into a front image viewed from the front, a plate material number determination unit that determines whether the extracted image of the plate material is an image composed of a plurality of plate materials based on positions of the plurality of fasteners relative to the projection-transformed front image, a contour line generation unit that generates a contour line that divides the image of the plate material into images of the plurality of plate materials when it is determined that the image is composed of the plurality of plate materials, and a spacing calculation unit that calculates the spacing between adjacent fasteners for each plate material surrounded by the generated contour line.

[0008] According to the present invention, when an image of a plate is extracted in the image extraction step, the extracted image of the plate may be composed of images of a plurality of plates. Here, the projection transformation unit performs projection transformation on the extracted image of the plate to a front image, and the plate number determination unit can determine whether the image of the plate is composed of images of a plurality of plates based on the positions of the plurality of fasteners relative to the front image. As a result, the contour line generation unit can generate a contour line of the plate for each image of the plurality of plate materials, and calculate the interval between adjacent fasteners based on the images of the fasteners present within the contour line. In this way, the contour line of the plate can be accurately specified for a rectangular plate material attached to a plurality of plates by a plurality of fasteners, and the interval between the fasteners driven into the plate material can be accurately calculated.

[0009] In a more preferred embodiment, the plate number determination unit divides the image of the multiple fasteners into rows of fasteners along an edge of the extracted image of the plate, projects the center of the image of each fastener in the divided row of fasteners onto a virtual line along the edge, and determines that the extracted image of the plate is an image composed of the multiple plate materials if the center-to-center distance between adjacent ones of the projected centers is within a specific range, and when the contour generation unit determines that the image is composed of the multiple plate materials, it generates a contour line of the boundary of the images of the multiple plate materials between fasteners whose center-to-center distance is within a specific range.

[0010] According to this aspect, the rows of fasteners divided by the board number determination unit include one row (when there are no adjacent boards) or two rows (when there are adjacent boards). For each divided row of fasteners, when the center of the image of each fastener is projected onto a virtual line along the edge of the board, if the extracted image of the board is composed of images of multiple boards, the center-to-center distance of the images of the fastener falls within a predetermined range (specific range) at the boundary between adjacent boards. Therefore, when such a determination is made by the board number determination unit, the contour line generation unit can generate a contour line of the boundary of the determined images of the multiple boards between the fasteners that are within the predetermined center-to-center distance range.

[0011] In another preferred embodiment, the plate number determination unit divides the image of the multiple fasteners into fastener rows along edges of the extracted image of the plate, calculates the distance from the center of the projectively transformed image of the fasteners to the edge of the projectively transformed image of the plate, and if there is a fastener row for which the calculated distance exceeds a specific range, determines that the extracted image of the plate is an image composed of the multiple plate materials, and when it has determined that the image is composed of the multiple plate materials, the contour generation unit generates a contour of the boundary of the image of the multiple plate materials between the fastener rows for which the distance is within a certain level and the fastener rows for which the distance exceeds the certain level.

[0012] According to this aspect, when there is a fastener row whose distance to an edge of the projection-transformed image of the plate exceeds a specific range, the plate number determination unit can determine that the extracted image of the plate is an image composed of the plurality of plate materials. When such a determination is made by the plate number determination unit, the contour line generation unit can generate a contour line of the boundary of the images of the plurality of plate materials between the fastener row whose distance is within a certain range and the fastener row whose distance exceeds the certain range.

[0013] In a more preferred embodiment, the contour generation unit generates the contour along the fastener row for each of the plate materials by linear approximation based on central coordinates of the images of the plurality of fasteners constituting the fastener row from the positions of the images of the fastener row. According to this embodiment, the contour of the plate material can be generated by a plurality of linear approximations for each of the images of the plurality of plate materials. Effect of the Invention

[0014] According to the present invention, by accurately identifying the contour line of a rectangular plate material to which multiple fasteners are attached, the distance between the fasteners driven into the plate material can be accurately calculated. [Brief description of the drawings]

[0015] [Figure 1] FIG. 2 is a schematic diagram of a gypsum board into which a screw that is the subject of estimation in this embodiment is driven. [Diagram 2] 1 is a schematic diagram of a contour line estimation device according to an embodiment of the present invention. [Diagram 3] FIG. 2 is a block diagram of the estimation device shown in FIG. [Figure 4] 10 is a schematic diagram of a plaster board and screws extracted by an extraction unit from an overall image captured by an imaging device. FIG. [Diagram 5] 5 is a schematic diagram showing the image of the plaster board shown in FIG. 4 subjected to projective transformation by a projective transformation unit. [Figure 6] 6 is a schematic diagram for explaining a determination by a board number determination unit as to whether the image of the plaster board shown in FIG. 5 is made up of a plurality of images of plaster boards. FIG. [Figure 7] FIG. 7 is an enlarged view of part A shown in FIG. [Figure 8] 6 is a schematic diagram for explaining a determination by a board number determination unit according to a modified example as to whether the image of the plaster board shown in FIG. 5 is made up of a plurality of images of plaster boards. FIG. [Figure 9] FIG. 9 is an enlarged view of part B shown in FIG. [Figure 10] 6 is a schematic diagram showing contour lines of the plurality of gypsum boards shown in FIG. 5, generated by a contour line generating unit. FIG. [Figure 11] FIG. 2 is a calculation flow diagram of the estimation device according to the present embodiment. [Figure 12] FIG. 11 is a calculation flow diagram of an estimation device according to a modified example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] The fastener interval estimation device according to this embodiment will be described below with reference to FIGS. 1 to 12. FIG.

[0017] 1. About the boards and fixtures In this embodiment, the estimation device 10 (hereinafter referred to as "estimation device 10") is a device that estimates the contour line of a board material and the intervals between fasteners driven into the board material. Here, fasteners are driven into the board material at a predetermined interval at least along the periphery of the board material. Examples of combinations of board material and fasteners include eaves soffit material (decorative material under the eaves) and nails that secure it, structural plywood in wooden houses and nails that secure it, and floor underlayment and nails / screws that secure it.

[0018] In the following embodiment, as shown in Fig. 1, a gypsum board 5A is exemplified as a plate material, and a screw 6A is exemplified as a fastener. Therefore, the gypsum board 5A corresponds to the "plate material" in the present invention, and the screw 6A corresponds to the "fastener" in the present invention. The contour lines 7H and 7V of the gypsum board 5A correspond to the "contour lines of the plate material."

[0019] The fasteners for fixing the gypsum board 5A may be nails or staples. The gypsum board 5A is used as an interior wall material or ceiling material. The gypsum board 5A is fixed with screws 6A along the long and short sides of the gypsum board 5A at a pitch equal to or less than that specified by laws and regulations. The screw pitch here refers to the distance between adjacent screws 6A, 6A along the long and short sides of the gypsum board 5A.

[0020] Here, the multiple screws 6A, 6A, ... are driven into the gypsum board 5A at a specified pitch along the periphery of the gypsum board 5A, inside the periphery of the gypsum board 5A. Furthermore, in this embodiment, the multiple screws 6A, 6A, ... are driven into the gypsum board 5A at a specified interval (pitch) P along the long side direction of the gypsum board 5A at the center of the width direction of the gypsum board 5A. After the gypsum board 5A is installed, the screw pitch is checked to see if it is within the specified pitch. The screw pitch is the center-to-center distance between adjacent screws 6A along the long side direction and the short side direction when the gypsum board 5A is viewed from the front.

[0021] The contour line estimation device 10 according to this embodiment is a device that estimates the interval between screws 6A driven into a plaster board 5A after the plaster board 5A has been installed. The estimation device 10 performs projective transformation of the image of the plaster board 5A together with the image of the screws 6A from contour lines 7H, 7V of an overall image GT including the plaster board 5A captured by an imaging device 20 into a front-facing image viewed from the front, extracts the image 6 of the projected screws 6A, and estimates the pitch of adjacent screws 6A.

[0022] 2. Hardware configuration of the estimation device 10 As shown in FIG. 2, the estimation device 10 is configured as hardware including a ROM, a RAM, etc., and is equipped with a memory device 10A in which the conditions of the gypsum board 5A, a screw pitch estimation program, etc. are recorded, and a calculation device 10B that executes a contour line estimation program.

[0023] 3-1. About the image extraction unit 11 An input device 31 and an output device 32 are connected to the estimation device 10. In this embodiment, the input device 31 and the output device 32 may be integrated into a touch panel display. The input device 31 receives data such as the specification conditions of the gypsum board 5A and a program for estimating the screw pitch. In this embodiment, the input device 31 receives image data captured by the imaging device 20. The data input by the input device 31 is stored in the storage device 10A. The output device 32 displays image data captured by the imaging device 20, calculation results calculated by the calculation device 10B, and the like.

[0024] In the present embodiment, the estimation device 10 is configured with the storage device 10A and the calculation device 10B, but may also include, for example, an input device 31 and an output device 32. The estimation device 10 may further include an imaging device 20 in addition to the input device 31 and the output device 32, and may be a mobile terminal such as a smartphone or tablet in which these are integrated.

[0025] 3-2. Software configuration of the estimation device 10 In this embodiment, as shown in FIG. 3, the estimation device 10 includes at least an image extraction unit 11, a projection transformation unit 12, a board number determination unit (plate material number determination unit) 13, a contour line generation unit 14, and a spacing calculation unit 15.

[0026] As a pre-processing step, the image extraction unit 11 may equalize the brightness difference of each pixel constituting the captured image captured by the imaging device 20. For example, the image extraction unit 11 may equalize the brightness of each pixel so that the brightness of each pixel falls within a predetermined range. Specifically, the image extraction unit 11 may multiply the brightness of each pixel by a correction coefficient corresponding to the difference between the maximum and minimum brightness values ​​of the pixel of the imaging device 20. By using the captured image with the brightness equalized, the image extraction unit 11 can equalize the pixels of the image of the screw, which changes depending on the imaging conditions.

[0027] The image extraction unit 11 extracts an image 5T of the plaster board 5A and an image 6 of the screws 6A from a whole image GT including (an image of) the plaster board 5A captured by the imaging device 20. As shown in Fig. 4, the image 5T of the plaster board 5A is an image of a region surrounded by images 7A and 7B of edges corresponding to images 7h and 7v of contour lines 7H and 7V.

[0028] The image extraction unit 11 may extract the image 5T of the plaster board 5A and the image 6 of the screw 6A by any method as long as the image extraction unit 11 can extract the image 5T of the plaster board 5A and the image 6 of the screw 6A. For example, the image 5T of the plaster board 5A and the image 6 of the screw 6A may be extracted from the whole image GT by a learning model machine-learned using the contour lines 7H and 7V (images 7h and 7v) of the plaster board 5A as feature quantities.

[0029] The learning model of the image extraction unit 11 is, for example, a model that uses a support vector machine (SVM) or the like to learn images 7h and 7v of the contour lines 7H and 7V from the captured images, using a plurality of captured images captured by the imaging device 20 and feature values ​​of the shape of the gypsum board 5A in these images (for example, images 7h and 7v of the contour lines 7H and 7V, which are the outer edges of the gypsum board 5A) as teacher data. This makes it possible to extract images 7A and 7B of the edge of the gypsum board from any overall image including the image of the gypsum board 5A. The shape of the gypsum board 5A itself may be identified using a cascade classifier that uses feature values ​​such as Haar-like features. Similarly, the image 6 of the screw 6A may be extracted using a learning model that has machine-learned the shape of the screw 6A.

[0030] Furthermore, a CNN (Convolutional Neural Network) may be used to create a learning model for the image extraction unit 11. Specifically, preprocessing of data normalization and resizing to an appropriate size are performed from the captured image as necessary. Next, annotation data obtained by labeling the background image, the image 5T of the gypsum board 5A, the image 7v of the contour line 7V along the vertical direction of the gypsum board 5A, and the image 7h of the contour line 7H along the horizontal direction of the gypsum board 5A for each pixel of the captured image are used as training data, and a learning model is created by machine learning using a CNN. From this learning model, an image 5T including the edge of the gypsum board is extracted from the captured image. When extracting this image 5T, for example, an image that has been subjected to binarization processing such as adaptive binarization processing and edge detection processing may be used as a filter image to detect a part of the image of the edge of the gypsum board, and the edge of the gypsum board may be calculated from the extracted image using linear approximation such as the least squares method.

[0031] Even if images 7A and 7B of the edge of the gypsum board 5A are obtained in this way, for example, if the horizontal edge of the gypsum board 5A cannot be detected, the extracted image 5T of the gypsum board may be composed of multiple (for example, two in Figs. 4 and 5) images 5T of the gypsum board. In such a case, the screw 6A may be present on the images 7A and 7B of the estimated or calculated edge, or the image 6 of the screw 6A present in the image 5T of the gypsum board 5A may be identified as the image 6 of the screw 6A of the adjacent gypsum board. In particular, since the horizontal edge of the gypsum board 5A is unlikely to be shaded, the image 7B of the horizontal edge of the gypsum board 5A may be difficult to detect. From this point of view, the following process is performed in this embodiment.

[0032] 3-3. About the Projection Transformation Unit 12 As shown in FIG. 5, the projection transformation unit 12 performs projection transformation on the extracted image 5T of the gypsum board 5A into a front image viewed from the front. Specifically, projection transformation is performed so that the area surrounded by the images 7A and 7B of the edges, which are the four sides of the image 5T of the gypsum board 5A, becomes rectangular. As long as the extracted image 5T of the gypsum board 5A can be projected into a front image viewed from the front, the method of projection transformation by the projection transformation unit 12 is not particularly limited. In this embodiment, the projection transformation unit 12 converts the image 5T of the gypsum board 5A together with the image 6 of the screw 6A into a front image viewed from the front by the projection transformation described in JP 2022-158835 A disclosed by the inventor.

[0033] 3-4. About the board number determination unit 13 The board number determination unit 13 determines whether the extracted image 5T of the plaster board 5A is an image 5 composed of a plurality of plaster boards 5A, based on the positions of the plurality of screws 6A relative to the front image 5C of the plaster board 5A subjected to projection transformation.

[0034] As shown in Fig. 6, the board number determination unit 13 divides the image 6 of the multiple screws 6A into screw rows (fastener rows) 6C, 6D along the image 7A of the edge of the long side of the extracted image 5T of the gypsum board 5A. Each screw row 6C, 6D is made up of multiple screws 6A, 6A at a predetermined distance on either side of the edge image 7A.

[0035] As shown in Fig. 7, the center of the image 6 of each screw 6A in the divided screw rows 6C, 6D is projected onto an imaginary line L along the image 7A of the long edge. If the center-to-center distances d1, d2, ... between adjacent centers of the projected images 6 of the screws 6A are within a specific range, the extracted image 5T of the gypsum board 5A is determined to be an image 5 composed of a plurality of gypsum boards 5A.

[0036] Specifically, the screws 6A are driven into the adjacent gypsum boards 5A, 5A at relatively close positions, so that the center-to-center distances d1, d3, d5, d7, and d9 are extremely narrow. On the other hand, the screws 6A are driven into the gypsum board 5A at a fixed pitch along the long side direction, so that the center-to-center distances d2, d4, and d8 are a predetermined screw pitch (screw interval) and are relatively long. The center-to-center distance d6 shown in FIG. 7 is the distance (specific distance) between the centers of the screws 6A driven into the corners of the gypsum board 5A. Therefore, since the center-to-center distance d6 is different from the above-mentioned distance, it is determined that the extracted image 5T of the gypsum board 5A is an image 5 composed of two gypsum boards 5A. Specifically, the boundary 7R between the images 5 of the two gypsum boards exists at the center position of the center-to-center distance d6, and the images are divided by this boundary 7R.

[0037] As shown in Fig. 9, in a modified example of the board number determination unit 13, distances D1 to D10 are calculated from the center of the image 6 of the projectively transformed screw 6A to the image 7A of the edge of the image 5 of the projectively transformed plaster board 5A. If there is a screw row 6D for which the calculated distance D1 exceeds a specific range (distance D), it is determined that the extracted image 5T of the plaster board 5A is an image 5, 5... made up of (for example, two) plaster boards 5A according to the number of screw rows. Specifically, as shown in Fig. 8, a boundary 7R between the two plaster board images 5 exists at the center position of the screw row 6E and the screw row 6F within the range, and the images are divided by this boundary 7R.

[0038] 3-5. Contour Line Generation Unit 14 When it is determined that the image 5 is composed of a plurality of gypsum boards 5A, the contour line generating unit 14 generates a contour line that divides the image 5T of the gypsum board 5A into images 5 of the plurality of gypsum boards 5A. Specifically, as shown in FIG. 6 and the like, a horizontal contour line 7H is generated at the boundary 7R. As shown in FIG. 6 and FIG. 7, when it is determined that the image 5 is composed of a plurality of gypsum boards 5A, the contour line generating unit 14 generates a contour line 7V of the boundary 7R of the image 5 of the plurality of gypsum boards 5A between the images of the screws 6A whose center-to-center distance d6 is within a specific range (at the center of the center-to-center distance d6).

[0039] In the modified example, as shown in Fig. 8 and Fig. 9, when the contour line generating unit 14 determines that the image 5 is composed of a plurality of gypsum boards 5A, it generates a contour line 7H of the boundary 7R of the image 5 of the plurality of gypsum boards 5A between the screw row 6F within a certain distance and the screw row 6E whose distance d exceeds a certain distance. Using the contour line 7H as a reference, the contour line generating unit 14 generates contour lines 7H, 7V along the screw rows 6E, 6F... for each gypsum board 5A by linear approximation based on the central coordinates of the image 6 of the plurality of screws 6A that compose the screw rows 6E, 6F from the positions of the images of the screw rows 6E, 6F. As a result, a contour line 7A' is also generated as shown in Fig. 10.

[0040] 3-6. Regarding the interval calculation unit 15 The interval calculation unit 15 calculates the interval P between adjacent screws 6A for each plaster board 5A surrounded by the generated contour lines 7H, 7V. Here, the distance between the centers of the images 6 of adjacent screws 6A is calculated for each plaster board 5A shown in Fig. 10. In this way, by accurately identifying the contour lines 7H, 7V of the plaster board 5A for a plurality of rectangular plaster boards 5A attached by a plurality of fasteners, the interval between the screws 6A driven into the plaster board 5A can be accurately calculated.

[0041] A flow diagram using the estimation device 10 will be described below with reference to Figs. 11 and 12. First, as shown in Fig. 11, in step S1, the imaging device 20 captures an image of an area including the gypsum board 5A as an inspection area, and acquires an overall image. In step S2, the image extraction unit 11 extracts images 5T of a plurality of gypsum boards 5A (see Fig. 4). In the flow from step S3 onwards, it is verified whether the extracted images 5T of the gypsum board 5A constitute the images 5, 5, ... of a plurality of gypsum boards 5A.

[0042] In step S3, the projection transformation unit 12 projectively transforms the extracted image 5 of the plaster board 5A into a front image 5C. Next, the process proceeds to step S4, where the board number determination unit 13 divides the images 6 of the multiple screws 6A into screw rows (fixture rows) 6C, 6D along the image 7A of the edge of the long side of the extracted image 5T of the plaster board 5A (see FIG. 6). In step S5, the board number determination unit 13 projects the centers of the images 6 of the screws 6A, such as the screw rows 6C, 6D, onto a virtual line L, and in step S6, the center-to-center distances d1, d2, ... on the virtual line L are calculated (see FIG. 7).

[0043] In step S7, if the calculated center-to-center distance is within a specific range (specifically, if a distance such as center-to-center distance d6 exists), the board number determination unit 13 determines that the image 5T of the extracted gypsum board 5A is an image 5, 5... composed of a number of gypsum boards 5A (for example, two) that falls within that specific range.

[0044] In step S8, if the screw row is composed of two screw rows of adjacent gypsum boards, contour line generation unit 14 generates contour lines 7V and 7H based on the positions of the images of the screws in these screw rows using the least squares method or the like in accordance with the arrangement of the screws in these screw rows. Contour line 7H, which becomes boundary 7R, is also generated.

[0045] Finally, in step S9, the interval calculation unit 15 calculates the interval P between adjacent screws 6A for each plaster board 5A surrounded by the generated contour lines 7H, 7V.

[0046] In the flow according to the modified example shown in FIG. 12, steps S5 to S7 in the flow shown in FIG. 11 are replaced with steps S11 and S12, and the other steps are given the same reference numerals and detailed description is omitted. In step S11, distances D1 to D10 from the center of the image 6 of the projectively transformed screw 6A to the image 7A of the edge of the image 5 of the projectively transformed plaster board 5A are calculated (see FIG. 9). In step S12, if the board number determination unit 13 determines that the calculated distance exceeds a specific range, the process proceeds to step S9. In step S8, when the contour line generation unit 14 determines that the image 5 is composed of multiple plaster boards 5A, it generates a contour line 7H of the boundary 7R of the image 5 of multiple plaster boards 5A between the screw row 6F, whose distance is within a certain range, and the screw row 6E, whose distance d exceeds a certain range. Similarly, the other contour lines 7H and 7V are also generated by linear approximation.

[0047] Although the embodiments of the present invention have been described in detail above, the present invention is not limited to the above-described embodiments, and various design modifications can be made without departing from the spirit of the present invention as described in the claims. [Explanation of symbols]

[0048] 5A: board material (gypsum board), 6A: fastener (screw), 10: estimation device, 11: image extraction unit, 12: projective transformation unit, 13: board material number determination unit (board number determination unit), 14: contour line generation unit, 15: interval calculation unit

Claims

1. An estimation device that estimates a distance between adjacent fasteners among a plurality of fasteners that are driven into each of a plurality of rectangular plate materials along a contour line of the plate materials, the estimation device comprising: an image extraction unit that extracts an image of the plate material and an image of the fastener from an overall image including the plate material captured by an imaging device; a projection transformation unit that performs projection transformation on the extracted image of the plate material together with the image of the fixture into a front image viewed from the front; a plate number determination unit that determines whether the extracted image of the plate is an image composed of a plurality of plate materials based on positions of the plurality of fasteners with respect to the projectively transformed front image; a contour line generating unit that generates a contour line dividing the image of the plate into images of the plurality of plate materials when it is determined that the image is composed of the plurality of plate materials; a spacing calculation unit that calculates the spacing between adjacent fasteners for each plate material surrounded by the generated contour line.

2. The plate number determination unit divides the images of the plurality of fasteners into fastener rows along edges of the extracted plate images, a center of an image of each fastener in the divided fastener row is projected onto a virtual line along the edge, and if a center-to-center distance between adjacent centers of the projected centers is within a specific range, it is determined that the extracted image of the plate is an image composed of the plurality of plate materials; 2. The fastener spacing estimation device according to claim 1, wherein when it is determined that the image is composed of the plurality of plate materials, the contour line generation unit generates a contour line of a boundary of the image of the plurality of plate materials between fasteners whose center-to-center distance is within a specific range.

3. The plate number determination unit divides the images of the plurality of fasteners into fastener rows along edges of the extracted plate images, calculating a distance from a center of the projectively transformed image of the fastener to an edge of the projectively transformed image of the plate, and if there is a fastener row for which the calculated distance exceeds a specific range, determining that the extracted image of the plate is an image composed of the plurality of plate materials; 2. The fastener spacing estimation device according to claim 1, wherein, when it is determined that the image is composed of the plurality of plate materials, the contour line generation unit generates a contour line of a boundary of the image of the plurality of plate materials between a fastener row where the distance is within a certain level and a fastener row where the distance exceeds the certain level.

4. 4. The fastener spacing estimation device according to claim 2 or 3, wherein the contour generation unit generates the contour along the fastener row for each of the plate materials by linear approximation based on central coordinates of images of the plurality of fasteners that constitute the fastener row, from positions of the images of the fastener row.

Images