JP7794680B2 - Fixture spacing estimation device - Google Patents

Description

The present invention relates to an estimation device that estimates the spacing between adjacent fasteners among multiple fasteners driven into a rectangular plate material.

As shown in Patent Document 1, conventionally, board materials such as gypsum boards used for interior wall or ceiling materials are attached to a substrate using multiple fasteners such as screws. The multiple fasteners are driven into the board at specified intervals along at least the periphery of the board. After the board is installed, the spacing between the fasteners is inspected to ensure that it is within the specified intervals.

JP 2018-031241 A

While such inspections can be performed visually, it is also possible to photograph the plate material into which the fasteners have been driven and measure the spacing between the fasteners from the photographed image. However, if the plate materials are adjacent to each other, it is difficult to use image processing or other methods to identify the fasteners that have been driven along the boundary between the plate materials for each plate and then estimate the spacing between adjacent fasteners from the photographed image of the plate materials.

The present invention was made in light of these issues, and its purpose is to provide a fastener spacing estimation device that can easily and accurately estimate the spacing between fasteners driven into a plate material.

In consideration of the above-mentioned problems, the fastener spacing estimation device of the present invention is an estimation device that estimates the spacing between adjacent fasteners among multiple fasteners driven into each of multiple rectangular plate materials, and is characterized by including at least: an estimated line extraction unit that extracts images of the plate materials and images of each fastener from an overall image including the plate materials captured by an imaging device, and extracts estimated lines of the plate material's outline from the extracted image of the plate materials; a fastener group classification unit that classifies the images of the multiple fasteners into groups of images of fasteners driven along the estimated lines of adjacent plate materials based on the estimated lines; a boundary line estimation unit that sets coordinates of the classified multiple fasteners relative to the overall image, calculates an approximate line that divides each group of the classified multiple fasteners into two groups along the boundary between the adjacent plate materials based on the set coordinates, and estimates the calculated approximate line to be the boundary line of the plate materials at the boundary between the adjacent plate materials; and a spacing calculation unit that calculates the spacing between adjacent fasteners along the boundary line for each plate material.

According to the present invention, the estimated line extraction unit extracts an image of the plate and images of each fastener from an overall image including the plate captured by the imaging device, and extracts estimated lines of the plate's outline from the extracted image of the plate. This extraction can be performed, for example, using machine learning to extract images of the plate, or using image processing such as edge detection.

The fastener group classification unit can classify the images into groups of fasteners driven along the estimated line estimated by the estimated line extraction unit. The classified group of fastener images is a group of images of fasteners driven along the boundary between adjacent plate materials, and this group includes groups of images of fasteners driven into two plate materials. The boundary line estimation unit then sets the coordinates of the classified multiple fasteners relative to the overall image, and calculates an approximate line that divides each group of classified multiple fasteners into two groups along the boundary between adjacent plate materials based on the set coordinates. This approximate line can be estimated to be the boundary line of the plate materials at the boundary between the adjacent plate materials. As a result, the spacing calculation unit can easily and accurately calculate the spacing between adjacent fasteners in a group of fasteners that exist on either side of the estimated boundary line.

Here, during extraction by the estimated line extraction unit, a single contour line (boundary line) along the boundary between adjacent plate materials may be extracted as multiple, different, interrupted estimated lines. In such cases, the spacing between fasteners is calculated for each of the multiple, different, interrupted estimated lines, and it is possible that the calculated spacing between fasteners may differ slightly from the actual spacing between fasteners. From this perspective, in a more preferred embodiment, the fastener group classification unit performs cluster analysis on the estimated lines extracted by the estimated line extraction unit to group the estimated lines into estimated lines corresponding to the boundaries between the adjacent plate materials, and classifies the images of the fasteners into groups based on the grouped estimated lines.

However, according to this aspect, the estimated lines extracted by the estimated line extraction unit are grouped into estimated lines that face the boundaries of adjacent plate materials through cluster analysis using the coordinates of the pixels that make up the estimated lines, and the images of the fasteners are classified into groups based on these grouped estimated lines, allowing for more accurate classification of groups of images of fasteners that lie along boundary lines.

Some fasteners are driven into the plate material along a scribed line along the plate material's center line. Such scribed lines are also mistaken for estimated lines. Based on these estimated lines, the fastener group classification unit classifies the fastener images into groups. Even if the boundary line estimation unit estimates a boundary line, this boundary line is not a boundary line but the plate material's center line. Therefore, from this perspective, in a more preferred embodiment, the boundary line estimation unit calculates the distance between the coordinates of the classified multiple fasteners and the approximate line, and estimates whether the approximate line is the boundary line based on the calculated distance.

This aspect makes it possible to accurately estimate whether the calculated boundary line is the boundary line of the board material. For example, if the coordinates of the classified multiple fasteners are close to the approximation line, such as if an image of the fastener is on the approximation line, it can be estimated that the approximation line is not the boundary line between the board materials, but is some other line such as a scribe line.

Here, there is no particular problem if the overall image is captured from a position directly facing the plate. However, if the image is captured from an angle oblique to the plate, for example, it may not be possible to accurately calculate the spacing between the fasteners. For this reason, the estimation device further includes a contour line setting unit that sets, for each plate, a contour line of the plate that includes the boundary line estimated by the boundary line estimation unit, and a projection transformation unit that projectively transforms the image of the plate and the multiple fasteners driven into the plate into a front image viewed from the front, based on the contour line set by the contour line setting unit. The spacing calculation unit calculates the spacing between the fasteners for each plate in the front image.

This invention makes it possible to easily and accurately estimate the spacing between fasteners driven into a plate.

FIG. 1 is a schematic diagram of a screw pitch estimation device according to an embodiment of the present invention. FIG. 2 is a control block diagram of a calculation unit of the estimation device shown in FIG. 1 . FIG. 3 is a control block diagram of a projection transformation unit shown in FIG. 2 . 3 is a schematic diagram for explaining extraction of an estimated line of the outline of a gypsum board by the estimated line extraction unit shown in FIG. 2 . FIG. 3 is a schematic diagram for explaining classification of a group of images of screws driven along a boundary of a gypsum board by the screw group classification unit shown in FIG. 2. [0023] FIG. 3A to 3C are schematic diagrams illustrating classification of a group of images of screws driven into the periphery of a plasterboard by the boundary line estimation unit shown in FIG. 2 . FIG. 3 is a schematic diagram for explaining a contour line setting unit shown in FIG. 2 . FIG. 10 is a schematic diagram for explaining a projective transformation unit. FIG. 2 is an estimation flow diagram using the estimation device shown in FIG. 1 .

An estimation device 10 according to this embodiment will be described below with reference to FIGS.
1. Regarding Boards and Fasteners In this embodiment, the estimation device 10 is a device that estimates the spacing between adjacent fasteners among a plurality of fasteners driven into a rectangular board. Here, the fasteners are driven at predetermined intervals at least along the periphery of the board. Examples of combinations of boards 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.

In the following embodiment, gypsum board 5 is used as an example of the plate material, and screws 6 are used as an example of the fastener. Therefore, gypsum board 5 corresponds to the "plate material" defined in the present invention, screws 6 correspond to the "fastener" defined in the present invention, and the pitch of screws 6 (screw pitch), which will be described later, corresponds to the "spacing between fasteners" defined in the present invention.

The fasteners used to secure the gypsum board 5 may be nails or staples. The gypsum board 5 is used as an interior wall material or ceiling material, etc. The gypsum board 5 is secured with screws 6 along the long and short sides of the gypsum board 5 at a pitch equal to or less than that specified by law. The screw pitch here refers to the distance between adjacent screws 6, 6 along the long and short sides of the gypsum board 5.

Here, multiple screws 6, 6, ... are driven into the gypsum board 5 at a specified pitch along the periphery of the gypsum board 5, inside the periphery. Furthermore, in this embodiment, multiple screws 6, 6, ... are driven into the gypsum board 5 at a specified pitch in the center of the width of the gypsum board 5, along the long side of the gypsum board 5. After the gypsum board 5 is installed, the screw pitch is checked to ensure that it is within the specified pitch. The screw pitch is the center-to-center distance between adjacent screws 6 along the long side and short side when the gypsum board 5 is viewed from the front.

The screw pitch estimation device 10 according to this embodiment is a device that estimates the pitch (screw pitch) of the screws 6 driven into the gypsum board 5 after the gypsum board 5 has been installed. The estimation device 10 ultimately extracts images of the screws 6 from the image G1 containing the gypsum board 5 captured by the imaging device 20, and estimates the pitch of adjacent screws 6.

2. Hardware Configuration of the Estimation Device 10 The estimation device 10 is configured with hardware such as ROM and RAM, and includes a storage unit 10A that stores the conditions of the gypsum board 5, a screw pitch estimation program, and the like, and a calculation unit 10B that executes the screw pitch estimation program.

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. Data such as the specifications of the gypsum board 5 and a screw pitch estimation program is input to the input device 31. In this embodiment, image data captured by the imaging device 20 is input to the input device 31. The data input by the input device 31 is stored in the memory unit 10A. The output device 32 displays the image data captured by the imaging device 20, the calculation results calculated by the calculation unit 10B, etc.

In this embodiment, the estimation device 10 is composed of a memory unit 10A and a calculation unit 10B, but it may also include, for example, an input device 31 and an output device 32. In addition to the input device 31 and the output device 32, the estimation device 10 may also include an imaging device 20, and these may be integrated into a mobile terminal such as a smartphone or tablet.

3. Software Configuration of Estimation Device 10 In this embodiment, as shown in FIG. 2 , the estimation device 10 includes at least an estimation line extraction unit 11, a screw group classification unit (fixture group classification unit) 12, a boundary line estimation unit 13, a contour line setting unit 14, a projection transformation unit 15, and a pitch calculation unit 16.

3-1. Regarding the estimated line extraction unit 11 As shown in FIG. 4, the estimated line extraction unit 11 extracts an image of the gypsum board 5 and images of each screw (fixing device) 6 from the overall image G1 including the board material captured by the imaging device 20, and extracts estimated lines PA, PB, and EA to ED of the outline of the gypsum board 5 from the extracted image of the gypsum board 5.

The estimated line extraction unit 11 may use, for example, a support vector machine (SVM) or the like to learn the features of the gypsum board 5 from the captured image, using as training data an image of the gypsum board 5 captured by the imaging device 20 and feature values of the shape of the gypsum board 5 in this image (e.g., multiple points along the edge of the gypsum board). This makes it possible to extract an image of the gypsum board from any overall image G1 that includes an image of the gypsum board 5. Alternatively, after identifying the gypsum board itself using a cascade classifier that uses feature values such as Haar-like features, the image of the gypsum board 5 may be extracted from the image within the identification range using the machine learning results described above.

A similar method is used to identify the positions of multiple screws 6 relative to the overall image G1. For example, in this embodiment, it is sufficient to be able to calculate the screw pitch, and ultimately, it is sufficient to identify the center position of the screws 6. Therefore, since it is not necessary to accurately identify the image size of the screws 6 or the shape of the screws 6, the screws 6 may be identified using a cascade classifier or other machine-learned method to identify the screw shapes. Once the positions of the screws 6 are identified, as a result, as shown in Figure 8, the screws 6 can be identified from the front image of the gypsum board 5 after projective transformation. For example, a circular mark indicating the identified screw 6 may be added around the screw 6. This mark may be other than a circle, such as a square or diamond. Alternatively, the transformed front image may be binarized or grayscale processed, and the screws 6 may be identified based on the number of pixels that have a predetermined brightness difference from the surrounding pixels.

In addition, since the gypsum board 5 is rectangular, the contour line consisting of the four sides of the gypsum board 5 may be detected as an estimated line using edge detection (such as edge detection using the Canny method) and commonly known line detection (such as line detection using the Hough method).

3-2. Regarding the screw group classification unit (fixture group classification unit) 12 Based on the estimated lines PA and PB shown in Fig. 4, the screw group classification unit 12 classifies a group of images of a plurality of screws 6 into groups 6A and 6B of images of screws 6 driven along the estimated lines PA and PB of adjacent gypsum boards 5, as shown in Fig. 5.

Here, during extraction by the estimated line extraction unit 11, a single contour line (boundary line) along the boundary between adjacent gypsum boards 5, 5 may be extracted as multiple, different, intermittent estimated lines. More specifically, in FIG. 4, the estimated line PA (PB) is extracted as a single line for each boundary line between adjacent gypsum boards 5, 5. However, as shown in FIG. 5, for example, the estimated lines PA, PB may not each be extracted as a single line, but may be extracted as multiple intermittent estimated lines PAa, PAb (PBa, PBb) along the vertical direction of FIG. 5. In such cases, the spacing between adjacent screws 6, 6 is calculated for each estimated line PAa, PAb (PBa, PBb), and it is expected that the calculated spacing between the screws 6, 6 will be slightly different from the actual spacing between the screws. From this perspective, the screw group classification unit 12 groups (classifies) the estimated lines according to the following before classifying the screw groups.

Specifically, the screw group classification unit 12 groups (classifies) the estimated lines PAa, PAb, PBa, and PBb extracted by the estimated line extraction unit 11 into estimated lines corresponding to the boundaries (boundary lines) between adjacent gypsum boards 5, 5 through cluster analysis using the coordinates of the pixels that make up the estimated lines PAa, PAb, PBa, and PBb (the X-Y Cartesian coordinates of each pixel relative to the overall image G1, as described below). In this embodiment, the estimated lines PAa, PAb and PBa are grouped (classified) through cluster analysis into a group of estimated lines PAa and PAb and a group of estimated lines PBa and PBb.

More specifically, the screw group classification unit 12 performs cluster analysis using a Bayesian Gaussian mixture model or the like on the coordinate values of the estimated lines PAa, PAb, PBa, and PBb of the gypsum board 5, and groups the estimated lines PAa, PAb, PBa, and PBb into a group of estimated lines PAa and PAb and a group of estimated lines PBa and PBb. As shown in Figure 4, when estimated lines PA and PB are properly extracted as estimated lines corresponding to the boundaries (boundary lines) between adjacent gypsum boards 5, they are classified (grouped) into estimated lines PA and PB by this cluster analysis.

The estimated line extraction unit 11 estimates the number of clusters based on the distribution of coordinate values for each pixel of the extracted estimated lines PAa, PAb, PBa, and PBb. Here, only clusters whose height (the difference between the minimum and maximum coordinate values in the Y direction) estimated from the estimated lines PAa, PAb, PBa, and PBb is equal to or greater than 1/2 to 1/3 of the height (length in the long side direction) of the entire image Gl or the gypsum board 5 are extracted.

Based on the grouped estimated lines PAa, PAb and the grouped estimated lines PBa, PBb, the screw group classification unit 12 classifies multiple images of screws 6 into groups 6A, 6B of images of screws 6 driven along the estimated lines of adjacent gypsum boards 5, 5. Specifically, as shown in FIG. 5, for the grouped estimated lines PAa, PAb, images of screws 6 within a range (area) located a predetermined distance from both sides of the estimated lines PAa, PAb are classified as group 6A of images of screws 6. A similar method is used to classify group 6B of images of screws 6 for the grouped estimated lines PBa, PBb. Note that in the case of the estimated lines PA, PB shown in FIG. 4, images of screws 6 located within a predetermined distance from both sides of the estimated lines PA, PB are classified as groups 6A, 6B.

The groups 6A and 6B of images of screws 6 classified here are groups of images of screws driven along the boundary between adjacent gypsum boards 5, and this group includes images of both screws 6 driven into the two gypsum boards 5. Therefore, in this embodiment, the boundary line estimation unit 13 divides these screws 6 into two.

6(a) and 6(b), the boundary line estimation unit 13 sets the coordinates (position coordinates) of the classified screws 6, 6, ... (groups 6A and 6B) in the overall image G1, and calculates approximation lines NA and NB that divide each group 6A and 6B of the classified screws 6, 6, ... into two groups along the boundary between adjacent gypsum boards 5 based on the set coordinates.

Specifically, as shown in FIG. 6(b), a Cartesian coordinate system (X-Y coordinate system) is set for the image of the gypsum board 5, and the equation of a line through which each screw 6, 6 passes is determined using the least squares method or the like for the center coordinates (center position coordinates) of each screw 6 in the image groups 6A, 6B of the screws 6, and the line of this equation is designated as the approximate lines NA, NB. The center coordinate of the screw 6 is determined by the coordinate of the pixel corresponding to the center of the pixels constituting the image of the screw 6. It is also possible to perform principal component analysis on the center coordinates of each of the image groups 6A, 6B of the screws 6, and determine the approximate lines NA, NB as the lines (principal component axis) that pass through the center of the screw group and are in the direction of the first principal component. The boundary line estimation unit 13 estimates that the calculated approximate lines NA, NB are the boundary lines BA, BB of the gypsum board 5 at the boundary between adjacent gypsum boards 5.

Here, some of the screws 6 driven into the gypsum board 5 are driven along a scribed line drawn on the center line of the gypsum board 5. Such scribed lines may also be mistaken for an estimated line by the estimated line extraction unit 11. Even if the screw group classification unit 12 classifies the images of the screws 6 into groups based on these estimated lines and the boundary line estimation unit 13 estimates a boundary line, this boundary line is not a boundary line but the center line of the gypsum board 5. Therefore, from this point of view, the boundary line estimation unit 13 may calculate the distance between the coordinates of the classified multiple screws 6 and the approximation line N, and estimate whether the approximation line N is a boundary line based on the calculated distance.

For example, as shown in Figure 6(c), if the coordinates of the classified multiple screws 6 are close to the approximation line N, for example, if the distance is such that an image of the screw 6 is on the approximation line N, it is estimated that this approximation line N is not the boundary line BA, BB between the gypsum boards 5, but some other line such as a scribe line. In this way, the contour line setting unit 14 can accurately estimate whether the calculated approximation lines NA, NB are the boundary lines BA, BB of the gypsum boards 5.

3-4. Contour Line Setting Unit 14 The contour line setting unit 14 sets, for each gypsum board 5, a contour line (specifically, the straight lines of the four sides) of the gypsum board 5 including the boundary lines BA and BB estimated by the boundary line estimation unit 13. Here, as shown in FIG. 4 , the contour line of each gypsum board 5 may be set using the overall contour lines (estimated lines) EA, EB, EC, and ED of the multiple gypsum boards 5 estimated by the estimated line extraction unit 11. Approximate straight lines NEA to NED may be created for the contour lines EA to ED by the least squares method, principal component analysis, or the like based on the coordinates (coordinates in an X-Y Cartesian coordinate system) of the pixels that make up the contour line, and contour lines c1 to c4 of the gypsum board 5 may be set using these approximate straight lines.

In this case, similar to what was shown in the screw group classification unit 12, the contour lines EA-ED can be grouped (classified) using cluster analysis using the coordinates of the pixels of the contour lines EA-ED extracted by the estimated line extraction unit 11, and for each grouped contour line EA-ED, the above-mentioned approximate lines NEA-NED can be created for the coordinates of the pixels that make up each contour line, and these can be used to set the contour lines c1-c4 of the gypsum board 5. In this way, even if at least one of the contour lines EA-ED extracted by the estimated line extraction unit 11 is an intermittent line, grouping it makes it possible to calculate a more accurate approximate line NEA-NED.

In addition, cluster analysis may be used to classify groups 6C, 6D, 6E, and 6F of screw 6 images based on the contour lines EA, EB, EC, and ED. As with the approximation lines described above, for the group 6C, 6D, 6E, and 6F of screw 6 images classified in this way, approximate straight lines NEA-NED passing through the planar coordinates (coordinates in an X-Y Cartesian coordinate system) of multiple screws 6 belonging to that group may be calculated using the least squares method or the like, and these calculated approximate lines NEA-NED may be offset by a predetermined number of pixels outside the gypsum board 5 and set as the contour lines of the gypsum board 5. In this way, contour lines c1-c4 of the gypsum board 5 can be set as shown in Figure 7.

Here, there is no particular problem if the overall image G1 is captured from a position directly facing the plasterboard 5. However, if the overall image G1 is captured from an angle oblique to the plasterboard 5, the image of the plasterboard 5 will look like the image on the left in Figure 8. Therefore, in this case, it may not be possible to accurately calculate the spacing between the screws. For this reason, the estimation device 10 may be provided with a projective transformation unit 15.

3-5. Projection transformation unit 15 The projection transformation unit 15 performs projection transformation on the gypsum board 5 and the screws 6 driven into the gypsum board 5 into a front image G3 viewed from the front. The method of projection transformation by the projection transformation unit 15 is not particularly limited as long as it can perform projection transformation on the extracted image G2 of the gypsum board 5 into a front image G3 viewed from the front.

For example, the pre-entered lengths of the short and long sides of a rectangular gypsum board 5 can be input, and the corresponding contour lines c1-c4 of the image G1 of the gypsum board 5 can be determined to be the short or long sides. The extracted image G2 of the gypsum board 5 can then be converted into a front image G3 so that the aspect ratio of the contour lines c1-c4 of the image G1 of the gypsum board 5 matches the ratio of the short side to the long side. In this case, the intersection points g1-g4 of the contour lines c1-c4 are calculated, and the lengths of the contour lines c1-c4 are calculated from the coordinates of these intersection points. Note that the projection transformation shown in Figure 8 may also involve expansion/contraction of the contour pixels. The method of converting to the front image G3 is a commonly known method, and detailed description will be omitted.

3-6. Pitch calculation unit (spacing calculation unit) 16 The pitch calculation unit 16 calculates the screw pitch P between adjacent screws 6, 6 along the vertical direction (lengthwise direction) of the front image G3 and the screw pitch P between adjacent screws 6, 6 along the horizontal direction (lengthwise direction) of the front image G3 based on the positions of the plurality of screws 6, 6 relative to the front image G3 after projection transformation. The pitch calculation unit 16 corresponds to the "spacing calculation unit" in this invention.

Specifically, the distance between the centers of the screws 6 is calculated as the number of pixels. If the length of the long or short side of the gypsum board 5 is input in advance, the actual length and width of each pixel can be calculated from these long and short sides, and the screw pitch P can be calculated from these actual lengths. In addition, if the entire image G1 is acquired by the imaging device 20 along with an actual length scale or a corresponding mark, the actual length and width of each pixel can be calculated.

The pitch calculation unit 16 determines whether the calculated screw pitch P falls within a specified range. Specifically, if the measured screw pitch falls within the specified range, each screw is surrounded by a solid circle, and if it does not fall within the specified range, it is surrounded by a dashed circle.

According to this embodiment, the image G2 of the gypsum board 5 extracted by the estimated line extraction unit 11 is projectively transformed by the projection transformation unit into a front image G3 viewed from the front. As a result, even when the gypsum board 5 is imaged from an oblique direction, the image G2 of the gypsum board 5 is transformed into a front image G3 together with the screws 6. Therefore, the position (position coordinates) of the screws 6 in the front image G3 of the gypsum board 5 after projection transformation can also be identified from the position (position coordinates) of the screws 6 before projection transformation.

Rather than directly identifying the positions of the multiple screws 6, 6, ... from the projectively transformed front image G3, the positions of the screws 6 are identified from the image G2 of the gypsum board 5 before projective transformation, in which the images of the screws 6 are easy to identify, and then the positions of the multiple screws 6, 6, ... in the projectively transformed front image G3 can be identified based on these positions. As a result, the pitch calculation unit 16 can accurately calculate the spacing between the screws 6, 6 regardless of the imaging conditions.

An estimation flow diagram using the estimation device 10 will be described below with reference to FIG.
First, in step S1, the imaging device 20 captures an image of an area to be inspected, including the gypsum board 5, and acquires an entire image G1.

Next, in step S2, the estimated line extraction unit 11 extracts an image of the gypsum board 5 and an image of the screw 6 from the overall image G1 including the gypsum board 5 captured by the imaging device 20, and extracts an estimated line of the outline of the gypsum board 5 from the extracted image of the gypsum board 5. Here, the position of the screw 6 relative to the overall image G is identified.

Next, in step S3, the screw group classification unit 12 classifies groups of images of screws 6 driven along the estimated lines PA and PB into groups 6A and 6B of screw 6 images. In step S4, the boundary line estimation unit 13 sets the coordinates of the classified screws 6, 6, ... relative to the overall image G1, and calculates approximate lines NA and NB that divide each group of classified screws 6, 6, ... into two groups along the boundaries of adjacent gypsum boards 5 based on the set coordinates. In step S6, the boundary line estimation unit 13 estimates whether the approximate lines NA and NB are boundary lines BA and BB. In step S7, the image G2 of the gypsum board 5 is projectively transformed into a front image G3.

Next, in step S8, the positions (center positions) of multiple screws 6 are identified from the front image G3 of the gypsum board 5, and in step S9, the pitch calculation unit 16 calculates the screw pitch P of adjacent screws from the image of the identified screws 6. Finally, in step S10, the pitch calculation unit 16 determines whether the screw pitch falls within a specified range.

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 set forth in the claims.

In this embodiment, the screw group classification unit performs cluster analysis based on the coordinates of the estimated lines to classify the estimated lines into groups. However, for example, it may also be possible to classify a group of images of multiple screws into a group of images of screws driven along the estimated lines of adjacent gypsum boards using cluster analysis based on the coordinates of the estimated lines.

5: Plasterboard (board material), 6: Screws (fixtures), 10: Estimation device, 11: Estimation line extraction unit, 12: Fixture group classification unit (screw group classification unit), 13: Boundary line estimation unit, 14: Contour line setting unit, 15: Projection transformation unit, 16: Pitch calculation unit (spacing calculation unit), 20: Image capture device, G1: Overall image, G2: Plasterboard image, G3: Front image

Claims (4)

An estimation device that estimates the spacing between adjacent fasteners among a plurality of fasteners driven into a plurality of rectangular plate materials,
an estimated line extraction unit that extracts an image of the plate and an image of each fixing device from an overall image including the plate captured by an imaging device, and extracts an estimated line of the outline of the plate from the extracted image of the plate;
a fastener group classification unit that classifies the images of the plurality of fasteners into groups of images of fasteners driven along the estimated line of adjacent plate materials based on the estimated line;
a boundary line estimation unit that sets coordinates of the classified plurality of fasteners relative to the entire image, calculates an approximation line that divides each group of the classified plurality of fasteners into two groups along the boundary between the adjacent plate materials based on the set coordinates, and estimates that the calculated approximation line is the boundary line of the plate materials at the boundary between the adjacent plate materials;
a spacing calculation unit that calculates the spacing between the adjacent fasteners along the boundary line for each of the plate materials;
A fastener spacing estimation device comprising at least: The fastener spacing estimation device described in claim 1, characterized in that the fastener group classification unit groups the estimated lines extracted by the estimated line extraction unit into estimated lines corresponding to the boundaries of the adjacent plate materials through cluster analysis using the coordinates of the pixels that make up the estimated lines, and classifies the images of the fasteners into groups based on the grouped estimated lines. The fixture spacing estimation device according to claim 1 or 2, characterized in that the boundary line estimation unit calculates the distance between the coordinates of the classified multiple fixtures and the approximation line, and estimates whether the approximation line is the boundary line based on the calculated distance. The estimation device includes:
a contour line setting unit that sets, for each of the plate materials, a contour line of the plate material that includes the boundary line estimated by the boundary line estimation unit;
a projection transformation unit that performs projection transformation on an image of the plate material and a plurality of fasteners driven into the plate material based on the contour line set by the contour line setting unit, into a front image viewed from the front,
4. The fastener spacing estimation device according to claim 1, wherein the spacing calculation unit calculates the spacing between the fasteners for each of the plate materials in the front image.