JP7814237B2 - Reinforcement inspection device, reinforcement inspection method, and program - Google Patents

Description

This disclosure relates to a reinforcement inspection device, a reinforcement inspection method, and a program.

When constructing reinforced concrete structures, after the rebars have been assembled and laid, a rebar inspection is carried out to check whether they have been laid as designed. In a typical rebar inspection, the number of rebars, their diameter, and spacing on the rebar surface are determined based on images obtained by taking 3D photographs of the rebar surface being inspected. However, 3D photography requires large-scale equipment such as a twin-lens or triple-lens camera.

In contrast, for example, the reinforcement inspection system described in Patent Document 1 determines whether reinforcement is correct by using multiple images taken from different angles by a monocular camera of markers placed on a specific layer of reinforcement, overlaying the images so that the markers are aligned. Because only a monocular camera is used to photograph the reinforcement, a simpler configuration can be achieved than devices that perform three-dimensional photography.

Patent No. 6801055

However, the reinforcement inspection system described in Patent Document 1 had the problem that it was necessary to take multiple images from different angles using a monocular camera to obtain three-dimensional information about the reinforcement surface of the object being inspected.

The present disclosure aims to solve the above-mentioned problems by providing a reinforcement inspection device, a reinforcement inspection method, and a program that can perform reinforcement inspection without taking multiple photographs of the reinforcement surface.

The reinforcing bar inspection device according to the present disclosure includes a three-dimensional information acquisition unit that receives an image of an inspection area where reinforcing bars are arranged in a grid pattern, taken by a monocular camera, and three-dimensional point cloud data obtained by three-dimensionally measuring the inspection area by a lidar, and identifies an inspection sheet range determined by inspection sheets laid in the longitudinal direction of the reinforcing bars that intersect with each other from the image, and acquires three-dimensional point cloud data of the inspection sheet range; a plane identification unit that identifies the reinforcing bar surface of the inspection target based on the three-dimensional point cloud data of the inspection sheet range; an image conversion unit that converts the captured image into an orthogonal image; and a third unit that detects first position information of the reinforcing bars on the reinforcing bar surface of the inspection target in the orthogonal image based on pixel value distribution indicated by a first pixel value scanning line set in the longitudinal direction of the reinforcing bars laid by the inspection sheet, and detects second position information of the reinforcing bars arranged so that the inspection sheet intersects the reinforcing bars laid in the longitudinal direction . The inspection apparatus includes a first detection unit, a second detection unit that detects the number and spacing of reinforcing bars indicated by the second position information based on the pixel value distribution indicated by the second pixel value scanning line set for each pixel in the longitudinal direction of the inspection sheet, a first reinforcing bar diameter determination unit that determines the reinforcing bar diameter of the reinforcing bar indicated by the first position information based on the pixel value distribution indicated by the first pixel value scanning line set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information, a second reinforcing bar diameter determination unit that determines the reinforcing bar diameter of the reinforcing bar indicated by the second position information based on the pixel value distribution indicated by the second pixel value scanning line set for each pixel in the longitudinal direction of the reinforcing bar indicated by the first position information, and a measurement result information generation unit that generates and outputs measurement result information that indicates the reinforcing bar diameter , number, and spacing obtained in the longitudinal direction of the inspection sheet and in the direction intersecting the longitudinal direction of the inspection sheet within the inspection sheet range.

According to the present disclosure, a captured image of an inspection area where reinforcing bars are arranged in a grid pattern , captured with a monocular camera, and three-dimensional point cloud data obtained by three-dimensionally measuring the inspection area with a lidar are input. An inspection sheet range determined by an inspection sheet laid in the longitudinal direction of the intersecting reinforcing bars is identified from the captured image, and three-dimensional point cloud data of the inspection sheet range is obtained. The reinforcement surface of the inspection target is identified based on the three-dimensional point cloud data of the inspection sheet range. In the reinforcement surface of the inspection target in an orthogonal image converted from the captured image, first position information of the reinforcing bars is detected based on the pixel value distribution indicated by a first pixel value scanning line set in the longitudinal direction of the reinforcing bars laid in the longitudinal direction of the inspection sheet, and second position information of the reinforcing bars arranged so that the inspection sheet intersects the reinforcing bars laid in the longitudinal direction is detected . The reinforcing bar diameter of the reinforcing bar indicated by the first position information is determined based on the pixel value distribution indicated by each first pixel value scanning line set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information. The rebar diameter of the rebar indicated by the second position information is determined based on the pixel value distribution indicated by the second pixel value scanning line set for each pixel in the longitudinal direction of the rebar indicated by the first position information. Measurement result information indicating the rebar diameter , number, and spacing obtained in the longitudinal direction of the inspection sheet and in the direction intersecting the longitudinal direction of the inspection sheet within the inspection sheet range is generated and output. In this way, three-dimensional point cloud data measured in three dimensions by the LIDAR is used to interpolate three-dimensional information from the image captured by the monocular camera. As a result, the reinforcing bar inspection device according to the present disclosure can perform reinforcing bar inspection without multiple photographs of the reinforcing bar surface.

1 is a block diagram showing the configuration of a reinforcement bar arrangement inspection device according to a first embodiment. FIG. FIG. 10 is a front view showing a check sheet on which markers are printed. FIG. 10 is a screen diagram showing a reinforcement surface on which an inspection sheet is laid. 4A, 4B, and 4C are graphs showing the relationship between a function indicating the reinforcement surface in the inspection area and outliers and inliers. FIG. 10 is an explanatory diagram showing a process of converting a captured image into a normal image. FIG. 10 is an explanatory diagram showing an outline of a reinforcing bar detection process. 1 is a flowchart showing a reinforcement bar arrangement inspection method according to the first embodiment. 8A and 8B are block diagrams showing a hardware configuration for realizing the functions of the bar arrangement inspection device according to the first embodiment.

Embodiment 1.
1 is a block diagram showing the configuration of a reinforcement inspection device 1 according to a first embodiment. The reinforcement inspection device 1 inspects, for example, at least one of the diameter, number, and spacing of adjacent reinforcing bars on a reinforcement surface to be inspected. The reinforcement surface to be inspected is a surface on which reinforcing bars with inspection sheets laid longitudinally are present. Furthermore, the reinforcement surface may be, for example, a surface on which multiple reinforcing bars are arranged in a lattice pattern, and on which inspection sheets are laid longitudinally on each of a set of reinforcing bars that intersect (e.g., perpendicularly) with each other in the lattice pattern.

The reinforcement inspection device 1 is implemented as one function of a smartphone, tablet device, or laptop personal computer. As shown in FIG. 1, the reinforcement inspection device 1 is connected to a monocular camera 2, a lidar 3 (hereinafter referred to as LiDAR 3), and a display unit 4 via a wired or wireless connection. The reinforcement inspection device 1 is not limited to a device in which the monocular camera 2, LiDAR 3, and display unit 4 are externally attached, and may also be a device that incorporates the monocular camera 2, LiDAR 3, and display unit 4.

For example, a smartphone equipped with a monocular camera 2, LiDAR 3, and display unit 4 functions as the reinforcement inspection device 1 by executing a reinforcement inspection application that realizes the functions of the reinforcement inspection device 1 according to embodiment 1. The smartphone uses the three-dimensional point cloud data (distance information to the subject) of the reinforcement surface obtained by three-dimensional measurement by the LiDAR 3 for autofocus when photographing the reinforcement surface of the inspection target with the monocular camera 2.

The positions of the monocular camera 2 and the LiDAR 3 on the smartphone are correlated. For example, when photography is performed with the monocular camera 2 and three-dimensional measurement is performed with the LiDAR 3, the three-dimensional point cloud data obtained by the three-dimensional measurement using the LiDAR 2 is synchronized with the image captured by the monocular camera 2. This makes it possible to associate the pixels of the captured image with the three-dimensional point data. In other words, three-dimensional information can be added to the image captured by the monocular camera 2. This allows the reinforcement inspection device 1 to perform reinforcement inspection using the image captured in a single capture (one-shot capture) by the monocular camera 2.

The reinforcement bar inspection device 1 may be a component included in a server capable of communicating with a terminal device equipped with the monocular camera 2, the LiDAR 3, and the display unit 4. For example, the terminal device can perform reinforcement bar inspection provided in the form of SaaS (Software as a Service). When performing reinforcement bar inspection in the form of SaaS, the terminal device does not need to have a reinforcement bar inspection application installed.
The bar arrangement inspection application is executed on the server, and the terminal device is provided with measurement result information on a general-purpose web browser. The bar arrangement inspection application is stored in a storage unit provided in the server.
Furthermore, an application for reinforcement inspection may be installed in the terminal device. When the application for reinforcement inspection is installed in the terminal device, the application can be executed to perform reinforcement inspection.

The monocular camera 2 is a cheaper camera than a stereo camera, and as mentioned above, may be a camera attached to a smartphone, tablet device, or laptop personal computer. Unlike a binocular camera (stereo camera) or trinocular camera, the monocular camera 2 does not require a large-scale device.

LiDAR3 is a lidar that measures distance by receiving reflected light from a laser pulse irradiated onto a target area at a predetermined measurement period (e.g., every 100 milliseconds), and detects three-dimensional point cloud data, which is a collection of three-dimensional points identified by the measured distances. The distance to an object in the target area is measured as the depth of the three-dimensional point.

Display unit 4 is a display device provided on a smartphone, tablet terminal, or laptop personal computer, and is, for example, a liquid crystal display (LCD) or organic electroluminescence (EL) display device. Display unit 4 displays rebar measurement result information.

Memory unit 5 is a memory unit that stores rebar characteristic information. The rebar characteristic information is a reference spectrum obtained by frequency converting pixel values in a scan line (hereinafter referred to as a pixel value scan line) consisting of multiple pixels lined up along the longitudinal direction of the rebar. For example, a fast Fourier transform (hereinafter referred to as an FFT) is used for the frequency conversion.

When a plurality of reinforcing bars are arranged in a grid pattern in the inspection area and an inspection sheet is laid in the longitudinal direction of the reinforcing bars that intersect with each other, a first reference spectrum is stored in the memory unit 5. The first reference spectrum is a reference spectrum obtained by frequency-converting a first pixel value scanning line set in the longitudinal direction of the reinforcing bars in a photographed image of the reinforcing bars on which the inspection sheet 6 is laid.
A second reference spectrum may also be stored in the storage unit 5. The second reference spectrum is a reference spectrum obtained by frequency-converting a second pixel value scanning line set in a direction intersecting the longitudinal direction of the rebar in a photographed image of the rebar on which the inspection sheet 6 is laid.

As shown in FIG. 1, the reinforcement bar inspection device 1 comprises a three-dimensional information acquisition unit 11, a plane identification unit 12, an image conversion unit 13, a first detection unit 14, a second detection unit 15, a first rebar diameter determination unit 16, a second rebar diameter determination unit 17, a correlation calculation unit 18, and a measurement result information generation unit 19. The three-dimensional information acquisition unit 11 inputs images of rebars laid in the longitudinal direction on an inspection sheet captured by a monocular camera 2, and three-dimensional point cloud data obtained by three-dimensionally measuring the rebars laid in the longitudinal direction on an inspection sheet using a LiDAR 3. The three-dimensional information acquisition unit 11 then identifies the inspection sheet range determined by the inspection sheet from the captured images and acquires three-dimensional point cloud data of the inspection sheet range.

Figure 2 is a front view of an inspection sheet 6 with markers 7. As shown in Figure 2, the inspection sheet 6 is a strip-shaped sheet with markers 7 at its ends. The inspection sheet 6 is laid in the longitudinal direction of the rebars. For example, when inspecting rebars before they are assembled into a grid (acceptance inspection), the rebars are aligned with the longitudinal direction of the inspection sheet 6, which is considered to be the reinforcement surface. The markers 7 on the inspection sheet 6 are, for example, identifiers with an identification shape 7B drawn on a square base 7A, and AR (augmented reality) markers may also be used.

The three-dimensional information acquisition unit 11 detects the marker 7 from the captured image captured by the monocular camera 2. For example, when the three-dimensional information acquisition unit 11 receives an image captured by the monocular camera 2, it detects the marker 7 from the captured image by using a learning model that outputs detection data for the marker 7. The learning model is machine-learned using captured images including the check sheet 6 as learning data, and is, for example, a neural network model. Note that the three-dimensional information acquisition unit 11 may also detect the marker 7 by performing pattern matching of the marker 7 in the captured image without using a learning model.

Next, the three-dimensional information acquisition unit 11 calculates the position information of the detected marker 7. For example, the three-dimensional information acquisition unit 11 binarizes the captured image input from the monocular camera 2, detects the contour of the base 7A of the marker 7, and calculates the position of the marker 7 when it is determined that the base 7A is a square based on the detected contour.

For example, as shown in Figure 2, if the shape formed by the line segment connecting vertices P1 and P2, the line segment connecting vertices P2 and P3, the line segment connecting vertices P3 and P4, and the line segment connecting vertices P4 and P1 is a rectangle (trapezoid), the captured image is an image obtained by monocular camera 2 photographing the reinforcement surface from the front. If any of the four vertices P1 to P4 of the shape of base 7A is not detected or the shape of base 7A is detected distorted, the captured image in this case is an image obtained by monocular camera 2 photographing the reinforcement surface from an oblique direction.

The three-dimensional information acquisition unit 11 calculates position information of the markers 7 in the image captured by the monocular camera 2 at a photographing position where the shape of the base 7A is trapezoidal. The three-dimensional information acquisition unit 11 uses the position information of the markers 7 to specify the inspection sheet range where the reinforcement inspection is to be performed.
3 is a screen image showing a photographed image 2A of a reinforcement surface on which an inspection sheet 6 has been laid, showing a reinforcement surface on which a plurality of reinforcing bars 8 are arranged in a grid pattern. In Fig. 3, in one of a plurality of sets of mutually intersecting reinforcing bars 8, an inspection sheet 6 is laid in the longitudinal direction of the reinforcing bars 8, and an inspection sheet 6 is laid in the longitudinal direction of the reinforcing bars 8 that intersect with the longitudinal direction of the reinforcing bars 8.

For example, the three-dimensional information acquisition unit 11 inputs a captured image 2A of the reinforcement surface shown in Figure 3 taken by a monocular camera 2 and three-dimensional point cloud data obtained by three-dimensionally measuring the reinforcement surface using LiDAR 3, identifies an inspection sheet range determined by inspection sheets 6 laid in the longitudinal direction of intersecting rebars 8 from the captured image 2A, and acquires three-dimensional point cloud data of the inspection sheet range. The inspection sheet range is a range identified by the positions of markers 7 placed on both ends of the intersecting inspection sheets 6. For example, the inspection sheet range is a rectangular range with one side consisting of a rebar 8 laid in the longitudinal direction of the inspection sheet 6 and a rebar 8 that intersects at the position of a marker 7 placed at the end of the inspection sheet 6.

The three-dimensional information acquisition unit 11 identifies the inspection sheet range of the captured image 2A based on the position of the marker 7, and then acquires three-dimensional point cloud data corresponding to the inspection sheet range from the three-dimensional point cloud data obtained by three-dimensional measurement using the LiDAR 3. The three-dimensional point cloud data corresponding to the inspection sheet range is distance information (depth information) of three-dimensional points on the rebar 8, inspection sheet 6, and marker 7 within the inspection sheet range.

The plane identification unit 12 identifies the reinforcement surface of the inspection target based on the three-dimensional point cloud data of the inspection sheet range. For example, the plane identification unit 12 detects plane candidates containing multiple three-dimensional points from the three-dimensional point cloud data of the inspection sheet range, and calculates, for each plane candidate, the number of three-dimensional points whose distance from the plane candidate is less than a threshold. The plane identification unit 12 then identifies the plane candidate with the largest number of three-dimensional points as the reinforcement surface of the inspection target. For example, the surface located at the forefront of a multi-story structure in which multiple reinforcing bars are arranged in a lattice pattern is the reinforcement surface of the inspection target.

For example, the plane identification unit 12 identifies the foreground reinforcement plane using the RANSAC (RANdom Sample Consensus) method. The plane identification unit 12 repeatedly estimates a function indicating plane candidates using three-dimensional point cloud data within the inspection sheet range. Figures 4A, 4B, and 4C are graphs showing the relationship between functions P(1), P(2), and P(3), which indicate the planes of each layer, and outliers 31 and inliers 32, respectively, and show three-dimensional points on the XY coordinate plane. Outliers 31 are three-dimensional points that are not within the allowable range, and inliers 32 are three-dimensional points that are within the allowable range.

In the RANSAC method, the number of 3D points that are inliers 32 is counted for each parameter representing the functions P(1), P(2), and P(3), and the parameter with the highest count is determined to be the optimal parameter. In other words, the plane candidate represented by the function to which the determined parameters are applied is determined to be the estimated foreground plane. As is clear from Figures 4A, 4B, and 4C, the parameters representing function P(3) have the largest number of 3D points that are inliers 32, so the plane identification unit 12 identifies the plane candidate represented by function P(3) as the reinforcement surface to be inspected.

The image conversion unit 13 converts the captured image into a normalized image. A normalized image is an image in which the distance between the monocular camera 2 and the reinforcement surface of the inspection target is constant, and the reinforcement surface of the inspection target is directly facing the monocular camera 2. Note that all pixels in the normalized image are scaled so that the distance from the monocular camera 2 is constant. As a result, the normalized image corrects for differences in the size of the rebar depending on the distance between the monocular camera 2 and the reinforcement surface of the inspection target.

Figure 5 is an explanatory diagram showing the process of converting the captured image 2A into the oriented image 2B, showing only the foreground reinforcement surface that appears in both the captured image 2A and the oriented image 2B. The image conversion unit 13 specifies four points at the four corners of any rectangle among the reinforcing bars 8 arranged in a grid pattern on the reinforcement surface to be inspected in the captured image 2A, and estimates a homography transformation matrix that gives the rectangle the shape it appears as viewed from the front of the monocular camera 2. The image conversion unit 13 converts the captured image 2A into the oriented image 2B based on the homography transformation matrix.

For example, if the reinforcing bar inspection device 1 is used to perform incoming inspections of reinforcing bars, and the inspection target is reinforcing bars with the inspection sheet 6 laid longitudinally before they are assembled in a grid pattern, the reinforcing bar inspection device 1 may not need to include the second detection unit 15, the second reinforcing bar diameter determination unit 17, and the correlation calculation unit 18. In this case, the first detection unit 14 functions as a detection unit that detects the positional information of the reinforcing bar based on the pixel value distribution indicated by a pixel value scanning line set longitudinally on the inspection sheet 6 on the reinforcing bar surface of the inspection target in the orthogonal image. Note that the pixel value scanning line is a scanning line composed of the pixel values of multiple pixels lined up longitudinally of the reinforcing bar in the orthogonal image. In the following description, pixel values are assumed to be luminance values, and the pixel value scanning line is referred to as the luminance value scanning line.

For example, note that the brightness value distribution differs between the brightness value scanning lines on the inspection sheet 6 laid in the longitudinal direction of the rebar in the orthogonal image and the brightness value scanning lines on the rebar. The detection unit takes note of this and sequentially sets brightness value scanning lines along the longitudinal direction of the rebar in a direction that intersects (e.g., perpendicular to) the longitudinal direction of the rebar. The detection unit then identifies scanning lines where the brightness value distribution indicated by the brightness value scanning lines set sequentially on the inspection sheet 6 has changed significantly, and detects the position information of these scanning lines as the position information of the rebar in the orthogonal image.

Figure 6 is an explanatory diagram outlining the rebar detection process, showing a case in which an inspection sheet 6 is laid in the longitudinal direction of each of a set of rebars 8 that intersect with each other among multiple rebars 8 arranged in a grid pattern on a reinforcement surface. In this case, the rebar arrangement inspection device 1 shown in Figure 1 is used to measure the diameter, number, and spacing of the multiple rebars 8 arranged in a grid pattern. As shown in Figure 6, the first detection unit 14 detects first position information of the rebars based on the brightness value distribution indicated by the first brightness value scanning line i set in the longitudinal direction of the rebars 8 laid in the longitudinal direction by the inspection sheet 6, and detects second position information of the rebars 8 that are arranged so as to intersect with the rebars 8 laid in the longitudinal direction by the inspection sheet 6.

For example, in the orthogonal image, the brightness value distribution differs between the brightness value scanning line i on the inspection sheet 6 and the brightness value scanning line i on the rebar 8. The first detection unit 14 takes note of this and sequentially sets first brightness value scanning lines i along the longitudinal direction of the rebar 8 in a direction perpendicular to the longitudinal direction of the rebar 8, as shown in FIG. 6 . The first detection unit 14 then identifies brightness value scanning lines i where the brightness value distribution indicated by the brightness value scanning lines i set sequentially on the inspection sheet 6 changes significantly, and detects the position information of the identified brightness value scanning line i as first position information of the rebar 8. This results in the detection of first position information indicating the horizontal position of the rebar 8 in FIG. 6 .

In the brightness value distribution indicated by brightness value scanning line i on inspection sheet 6 in the orthogonalized image, the brightness value of the rebar 8 (vertical rebar 8 in Figure 6) arranged perpendicular to the rebar 8 indicated by the first position information differs from the brightness value on inspection sheet 6. The first detection unit 14 focuses on this and identifies the position where there is a change in brightness value corresponding to the vertical rebar 8 in the brightness value distribution indicated by brightness value scanning line i on inspection sheet 6, and detects the identified position as second position information for the rebar 8 in the orthogonalized image. This results in the detection of second position information indicating the position of the vertical rebar 8 in Figure 6.

The second detection unit 15 detects the number and spacing of the rebars 8 indicated by the second position information based on the brightness value distribution indicated by each second brightness value scanning line j set for each pixel in the longitudinal direction (horizontal direction in Figure 6) of the rebars 8 indicated by the first position information. For example, in the normalized image, the brightness value distribution differs between the brightness value scanning line j on the inspection sheet 6 and the brightness value scanning line j on the rebars 8. Taking this into consideration, the second detection unit 15 sets second brightness value scanning lines j perpendicular to the longitudinal direction of the rebars 8 in order along the longitudinal direction of the rebars 8, as shown in Figure 6. The second detection unit 15 then determines that the brightness value scanning lines j set sequentially from the top of the inspection sheet 6, whose brightness value distribution has changed, are the brightness value scanning lines j at the boundary between the inspection sheet 6 and the rebars 8. The second detection unit 15 uses the position information of the boundary brightness value scanning lines j to detect the number of rebars 8 perpendicular to the longitudinal direction of the rebars 8 and the spacing between adjacent rebars 8. This allows the number of rebars 8 perpendicular to the horizontal rebars 8 in Figure 6 and the spacing between the vertical rebars 8 to be detected.

When the reinforcing bar inspection device 1 performs an acceptance inspection of reinforcing bars and the inspection target is reinforcing bars with the inspection sheet 6 laid longitudinally before being assembled into a grid, the first reinforcing bar diameter determination unit 16 functions as a reinforcing bar diameter determination unit that determines the reinforcing bar diameter of the reinforcing bar 8 indicated by the position information detected by the detection unit, based on the pixel value distribution indicated by the brightness value scanning line i set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar 8 indicated by the position information detected by the detection unit.

For example, the rebar diameter determination unit sequentially sets brightness value scanning lines i along the longitudinal direction of the rebar 8 in a direction intersecting (e.g., perpendicular to) the longitudinal direction of the rebar 8. Among the brightness value scanning lines i set sequentially from the top of the inspection sheet 6, the rebar diameter determination unit determines a scanning line where the brightness value distribution changes to be the first scanning line at the boundary where the rebar 8 changes from the top of the inspection sheet 6 to the top of the rebar 8, and identifies the position information of the first scanning line. Furthermore, the rebar diameter determination unit scans in a direction intersecting the longitudinal direction of the rebar 8, and determines a scanning line where the brightness value distribution changes to be the second scanning line at the boundary where the rebar 8 changes to the top of the inspection sheet 6, and identifies the position information of the second scanning line. The rebar diameter determination unit can determine the diameter of the rebar indicated by the position information detected by the detection unit by converting the difference value between the position information of the first scanning line and the position information of the second scanning line in the orthogonal image into a distance in real space.

The first rebar diameter determination unit 16 determines the rebar diameter of the rebar 8 indicated by the first position information based on the brightness value distribution indicated by each first brightness value scanning line i set for each pixel in a direction perpendicular to the longitudinal direction of the rebar 8 indicated by the first position information.
For example, as shown in Figure 6, the first rebar diameter determination unit 16 sets brightness value scanning lines i along the longitudinal direction of the rebar 8 in sequence in a direction perpendicular to the longitudinal direction of the rebar 8 (the vertical direction in Figure 6).
Next, the first rebar diameter determination unit 16 determines that the scanning line where the brightness value distribution has changed among the brightness value scanning lines i set in order from the top of the inspection sheet 6 is the first scanning line at the boundary where the inspection sheet 6 changes to the top of the rebar 8, and identifies the position information of the first scanning line.
Furthermore, the first rebar diameter determination unit 16 proceeds with scanning in a direction perpendicular to the longitudinal direction of the rebar 8, and determines that the scanning line where the brightness value distribution has changed is the second scanning line at the boundary where the rebar 8 changes to the inspection sheet 6, and identifies the position information of the second scanning line.
The first rebar diameter determination unit 16 determines the rebar diameter of the rebar 8 indicated by the first position information detected by the first detection unit 14 by converting the difference value between the position information of the first scanning line and the position information of the second scanning line in the facing image into a distance in real space.

Furthermore, the first reinforcing bar diameter determination unit 16 may determine the reinforcing bar diameter of the reinforcing bar 8 indicated by the first position information based on the correlation value calculated by the correlation calculation unit 18 .
For example, a spectrum obtained by frequency-converting luminance-value scanning lines set in the longitudinal direction of the rebar on the image is obtained in advance by experiment, and this spectrum is stored as a first reference spectrum in the storage unit 5. The first rebar diameter determination unit 16 frequency-converts each of the luminance-value scanning lines i set in order in a direction perpendicular to the longitudinal direction of the rebar 8 to generate a spectrum indicating changes in luminance values, and outputs the spectrum to the correlation calculation unit 18.

The correlation calculation unit 18 calculates a correlation value between the frequency conversion spectrum generated by the first rebar diameter determination unit 16 and the first reference spectrum stored in the memory unit 5, and outputs the correlation value to the first rebar diameter determination unit 16. For example, the correlation calculation unit 18 compares the peak positions and peak intensities of the spectra, and quantifies (scores) the degree of similarity between the two spectra to calculate the correlation value.
If the correlation value calculated by the correlation calculation unit 18 is less than a threshold value, the first rebar diameter determination unit 16 determines that the luminance value scanning line i corresponding to the spectrum from which this correlation value was obtained represents the luminance value distribution on the inspection sheet 6 in the normalized image.

On the other hand, if the correlation value calculated by the correlation calculation unit 18 is equal to or greater than a threshold value, the first rebar diameter determination unit 16 determines that the luminance value scanning line i corresponding to the spectrum from which this correlation value was obtained indicates the luminance value distribution on the rebar 8 in the facing image.
The first rebar diameter determination unit 16 uses the above correlation value to detect the position information of the first scanning line and the position information of the second scanning line, and determines the rebar diameter of the rebar 8 indicated by the first position information using the difference value between the position information of the first scanning line and the position information of the second scanning line.

The second rebar diameter determination unit 17 determines the rebar diameter of the rebar 8 indicated by the second position information based on the brightness value distribution indicated by each second brightness value scanning line j set for each pixel in the longitudinal direction of the rebar 8 indicated by the first position information.
6 , the second rebar diameter determination unit 17 sets brightness value scanning lines j that are perpendicular to the longitudinal direction of the rebar 8 indicated by the first position information in order along the longitudinal direction of the rebar 8. Of the brightness value scanning lines j set in order from the top of the inspection sheet 6, the second rebar diameter determination unit 17 determines that the scanning line where the brightness value distribution has changed is the first scanning line at the boundary where the top of the inspection sheet 6 changes to the top of the rebar 8, and specifies the position information of the third scanning line.

Furthermore, the second rebar diameter determination unit 17 scans in the longitudinal direction of the rebar 8, and determines that the scan line where the brightness value distribution changes significantly is the fourth scan line, which is the boundary where the rebar 8 changes to the inspection sheet 6, and identifies the position information of the fourth scan line.
The second rebar diameter determination unit 17 determines the rebar diameter of the rebar 8 indicated by the second position information detected by the first detection unit 14 by converting the difference value between the position information of the third scanning line and the position information of the fourth scanning line in the facing image into a distance in real space.

The second rebar diameter determination unit 17 may also determine the rebar diameter of the rebar 8 indicated by the second position information based on the correlation value calculated by the correlation calculation unit 18. For example, the first rebar diameter determination unit 16 stores, in the memory unit 5 as a second reference spectrum, a spectrum obtained by frequency-converting the first pixel value scanning line i set for each vertical pixel in FIG. 6 . The correlation calculation unit 18 calculates a correlation value between the spectrum obtained by frequency-converting the second luminance value scanning line j by the second rebar diameter determination unit 17 and the second reference spectrum stored in the memory unit 5.

In Figure 6, the position of the vertical rebar 8 is identified by the second position information, so in the brightness value distribution indicated by the horizontal brightness scanning line i, changes in brightness values of the vertical rebar 8 appear at the position indicated by the second position information. However, changes in brightness values of the vertical rebar 8 do not appear in the brightness scanning line i set on the horizontal rebar 8, but appear strongly in the brightness scanning line i set on the inspection sheet 6.

The correlation calculation unit 18 calculates a correlation value between the change in brightness value indicated by the spectrum obtained by frequency converting the second brightness-place scanning line j set vertically by the second rebar diameter determination unit 17 and the change in brightness value at the position indicated by the second position information in the spectrum obtained by frequency converting the horizontal brightness-place scanning line i.
The second rebar diameter determination unit 17 uses the above correlation value to detect the position information of the third scanning line and the position information of the fourth scanning line, and determines the rebar diameter of the rebar 8 indicated by the second position information using the difference value between the position information of the third scanning line and the position information of the fourth scanning line.

Alternatively, a spectrum obtained by frequency-converting the luminance scanning lines j set in a direction perpendicular to the longitudinal direction of the rebar on the image may be obtained in advance through experiments, and this spectrum may be stored in the memory unit 5 as a second reference spectrum. In this case, the second rebar diameter determination unit 17 frequency-converts each of the luminance scanning lines j set in sequence in the longitudinal direction of the rebar 8 indicated by the first position information to generate a spectrum indicating changes in luminance values, and outputs this spectrum to the correlation calculation unit 18.

The correlation calculation unit 18 calculates a correlation value between the frequency conversion spectrum generated by the second rebar diameter determination unit 17 and the second reference spectrum stored in the memory unit 5, and outputs the correlation value to the second rebar diameter determination unit 17. For example, the correlation calculation unit 18 compares the peak positions and peak intensities of the spectra, and quantifies (scores) the degree of similarity between the two spectra to calculate the correlation value.
If the correlation value calculated by the correlation calculation unit 18 is less than a threshold value, the second rebar diameter determination unit 17 determines that the luminance value scanning line j corresponding to the spectrum from which this correlation value was obtained indicates the luminance value distribution on the inspection sheet 6 in the normalized image.

On the other hand, if the correlation value calculated by the correlation calculation unit 18 is greater than or equal to a threshold value, the second rebar diameter determination unit 17 determines that the luminance value scanning line j corresponding to the spectrum from which this correlation value was obtained indicates the luminance value distribution on the rebar 8 in the facing image.
The second rebar diameter determination unit 17 uses the above correlation value to detect the position information of the third scanning line and the position information of the fourth scanning line, and determines the rebar diameter of the rebar 8 indicated by the second position information using the difference value between the position information of the third scanning line and the position information of the fourth scanning line.

The measurement result information generation unit 19 generates and outputs measurement result information indicating the rebar diameter of the rebars 8 within the inspection sheet range. For example, the measurement result information generation unit 19 generates display control information for displaying the measurement results on an electronic whiteboard as measurement result information and outputs it to the display unit 4. The display unit 4 displays the electronic whiteboard on which the rebar diameter of the measurement results is written based on the display control information.

Furthermore, when the reinforcement surface is a reinforcement surface in which inspection sheets 6 are laid in the longitudinal direction of each set of rebars 8 that intersect each other among multiple rebars 8 arranged in a grid pattern, as shown in FIG. 3, the reinforcement inspection device 1 measures the diameter, number, and spacing of the rebars 8 in the longitudinal direction of the inspection sheet 6 within the inspection sheet area (the horizontal direction in FIG. 3) and in the direction intersecting the longitudinal direction of the inspection sheet 6 (the vertical direction in FIG. 3). This measures the diameter, number, and spacing of the rebars 8 within the inspection sheet area. In this case, the measurement result information generation unit 19 generates display control information as measurement result information for displaying the diameter, number, and spacing of the rebars 8 within the inspection sheet area on an electronic whiteboard, and outputs this information to the display unit 4. Based on the display control information, the display unit 4 displays an electronic whiteboard that lists the diameter, number, and spacing of the rebars 8 within the inspection sheet area.

Next, a reinforcement bar arrangement inspection method according to the first embodiment will be described.
FIG. 7 is a flowchart showing the reinforcement bar arrangement inspection method according to the first embodiment.
The three-dimensional information acquisition unit 11 inputs an image of an inspection area in which multiple reinforcing bars 8 are arranged in a grid pattern, taken by a monocular camera 2, and three-dimensional point cloud data obtained by three-dimensionally measuring this inspection area using a LiDAR 3, and identifies the inspection sheet range determined by the inspection sheets 6 laid in the longitudinal direction of the reinforcing bars 8 that intersect with each other from the image, and acquires three-dimensional point cloud data of the inspection sheet range (step ST1).

The plane identification unit 12 identifies the reinforcement surface to be inspected within the inspection sheet range based on the three-dimensional point cloud data of the inspection sheet range (step ST2). The image conversion unit 13 converts the captured image into a normalized image (step ST3).

The first detection unit 14 detects first position information of the reinforcing bars 8 based on the brightness value distribution indicated by the first brightness value scanning line i set in the longitudinal direction of the reinforcing bars 8 on the reinforcement surface of the inspection target in the front-facing image, and detects second position information of the reinforcing bars 8 on the inspection sheet 6 that are arranged so as to cross the reinforcing bars 8 laid in the longitudinal direction (step ST4-1).
In addition, the second detection unit 15 detects the number and spacing of the reinforcing bars indicated by the second position information based on the brightness value distribution indicated by the second brightness value scanning line j set for each pixel in the longitudinal direction of the reinforcing bars 8 indicated by the first position information (step ST4-2).

The first rebar diameter determination unit 16 determines the rebar diameter of the rebar 8 indicated by the first position information based on the brightness value distribution indicated by each first brightness value scanning line i set for each pixel in a direction intersecting the longitudinal direction of the rebar 8 indicated by the first position information (step ST5-1). This process is the first rebar diameter determination process. Furthermore, the second rebar diameter determination unit 17 determines the rebar diameter of the rebar 8 indicated by the second position information based on the brightness value distribution indicated by each second brightness value scanning line set for each pixel in the longitudinal direction of the rebar 8 indicated by the first position information (step ST5-2). This process is the second rebar diameter determination process.

The measurement result information generation unit 19 generates measurement result information indicating the diameter, number, and spacing of the rebars 8 obtained in the longitudinal direction of the inspection sheet 6 within the inspection sheet range and in a direction intersecting the longitudinal direction of the inspection sheet 6 (step ST6). For example, the measurement result information is display control information for displaying the measurement results, and the display unit 4 displays the measurement results based on the display control information.

Note that while the pixel values making up the pixel value scan line are brightness values, they are not limited to brightness values as long as there is a difference between the pixel values in the rebar 8 and the pixel values in the inspection sheet 6. For example, pixel color information may also be used.

Next, a hardware configuration for realizing the functions of the bar arrangement inspection device 1 will be described.
The functions of the three-dimensional information acquisition unit 11, plane identification unit 12, image conversion unit 13, first detection unit 14, second detection unit 15, first rebar diameter determination unit 16, second rebar diameter determination unit 17, correlation calculation unit 18, and measurement result information generation unit 19 included in the reinforcement bar inspection device 1 are realized by a processing circuit. That is, the reinforcement bar inspection device 1 includes a processing circuit for executing the processes of steps ST1 to ST6 shown in Fig. 7. The processing circuit may be dedicated hardware, or may be a CPU (Central Processing Unit) that executes a program stored in a memory.

Figure 8A is a block diagram showing the hardware configuration that realizes the functions of the reinforcement inspection device 1. Figure 8B is a block diagram showing the hardware configuration that executes software that realizes the functions of the reinforcement inspection device 1. In Figures 8A and 8B, the input interface 100 is an interface that relays the captured images input by the reinforcement inspection device 1 from the monocular camera 2, the three-dimensional point cloud data input by the LiDAR 3, and the rebar characteristic information input by the memory unit 5. The output interface 101 is an interface that relays the measurement result information output from the reinforcement inspection device 1 to the display unit 4.

When the processing circuit is the dedicated hardware processing circuit 102 shown in FIG. 8A, the processing circuit 102 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel-programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination of these. The functions of the three-dimensional information acquisition unit 11, plane identification unit 12, image conversion unit 13, first detection unit 14, second detection unit 15, first rebar diameter determination unit 16, second rebar diameter determination unit 17, correlation calculation unit 18, and measurement result information generation unit 19 provided in the reinforcement inspection device 1 may be realized by separate processing circuits, or these functions may be realized together by a single processing circuit.

When the processing circuit is the processor 103 shown in FIG. 8B, the functions of the three-dimensional information acquisition unit 11, plane identification unit 12, image conversion unit 13, first detection unit 14, second detection unit 15, first rebar diameter determination unit 16, second rebar diameter determination unit 17, correlation calculation unit 18, and measurement result information generation unit 19 provided in the reinforcement bar inspection device 1 are realized by software, firmware, or a combination of software and firmware. The software or firmware is written as a program and stored in the memory 104.

The processor 103 reads and executes the programs stored in the memory 104 to realize the functions of the three-dimensional information acquisition unit 11, plane identification unit 12, image conversion unit 13, first detection unit 14, second detection unit 15, first rebar diameter determination unit 16, second rebar diameter determination unit 17, correlation calculation unit 18 and measurement result information generation unit 19 that are provided in the reinforcement inspection device 1.
For example, the bar arrangement inspection device 1 includes a memory 104 for storing a program that, when executed by the processor 103, results in the processing of steps ST1 to ST6 shown in FIG.

These programs cause the computer to execute the processing procedures or methods performed by the three-dimensional information acquisition unit 11, plane identification unit 12, image conversion unit 13, first detection unit 14, second detection unit 15, first rebar diameter determination unit 16, second rebar diameter determination unit 17, correlation calculation unit 18, and measurement result information generation unit 19. The memory 104 may be a computer-readable storage medium that stores programs that cause the computer to function as the three-dimensional information acquisition unit 11, plane identification unit 12, image conversion unit 13, first detection unit 14, second detection unit 15, first rebar diameter determination unit 16, second rebar diameter determination unit 17, correlation calculation unit 18, and measurement result information generation unit 19.

Memory 104 may be, for example, non-volatile or volatile semiconductor memory such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable Read Only Memory), or EEPROM (Electrically-EPROM), as well as magnetic disks, flexible disks, optical disks, compact disks, minidisks, and DVDs.

The functions of the three-dimensional information acquisition unit 11, plane identification unit 12, image conversion unit 13, first detection unit 14, second detection unit 15, first rebar diameter determination unit 16, second rebar diameter determination unit 17, correlation calculation unit 18, and measurement result information generation unit 19 included in the reinforcement bar inspection device 1 may be partially implemented by dedicated hardware, and partially implemented by software or firmware. For example, the three-dimensional information acquisition unit 11 and plane identification unit 12 are implemented by the processing circuit 102, which is dedicated hardware, and the image conversion unit 13, first detection unit 14, second detection unit 15, first rebar diameter determination unit 16, second rebar diameter determination unit 17, correlation calculation unit 18, and measurement result information generation unit 19 are implemented by the processor 103 reading and executing programs stored in memory 104. In this way, the processing circuit can implement the above functions using hardware, software, firmware, or a combination of these.

As described above, the reinforcing bar arrangement inspection device 1 according to the first embodiment includes a three-dimensional information acquisition unit 11 that receives an image of an inspection area photographed by the monocular camera 2 and three-dimensional point cloud data obtained by three-dimensionally measuring the inspection area by the LiDAR 3, identifies an inspection sheet range determined by the inspection sheet 6 laid in the longitudinal direction of the reinforcing bars that intersect with each other from the photographed image, and acquires three-dimensional point cloud data of the inspection sheet range, a plane identification unit 12 that identifies the reinforcing bar arrangement surface of the inspection target, an image conversion unit 13 that converts the photographed image into an orthogonal image, a first detection unit 14 that detects first position information of the reinforcing bar based on the pixel value distribution indicated by the first pixel value scanning line set in the longitudinal direction of the reinforcing bars laid in the longitudinal direction of the inspection sheet 6, and detects second position information of the reinforcing bar that intersects with the reinforcing bar, and a plane identification unit 12 that identifies the reinforcing bar arrangement surface of the inspection target from the photographed image and acquires three-dimensional point cloud data of the inspection sheet range, an image conversion unit 13 that converts the photographed image into an orthogonal image, and a first detection unit 14 that detects second position information of the reinforcing bar that intersects with the reinforcing bar based on the pixel value distribution indicated by the first pixel value scanning line set in the longitudinal direction of the reinforcing bar that intersects with the reinforcing bar, and The inspection apparatus is provided with a second detection unit 15 that detects the number and spacing of reinforcing bars indicated by the second position information based on the pixel value distribution indicated by the second pixel value scanning line set for each pixel in the longitudinal direction of the bars; a first reinforcing bar diameter determination unit 16 that determines the reinforcing bar diameter of the reinforcing bar indicated by the first position information based on the pixel value distribution indicated by the first pixel value scanning line set for each pixel in the direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information; a second reinforcing bar diameter determination unit 17 that determines the reinforcing bar diameter of the reinforcing bar indicated by the second position information based on the pixel value distribution indicated by the second pixel value scanning line set for each pixel in the longitudinal direction of the reinforcing bar indicated by the first position information; and a measurement result information generation unit 19 that generates and outputs the measurement result information that indicates the reinforcing bar diameter, number, and spacing obtained in the longitudinal direction of the inspection sheet 6 and the direction intersecting the longitudinal direction of the inspection sheet 6 within the inspection sheet range.
Using the three-dimensional point cloud data obtained by three-dimensional measurement using the LiDAR 3, three-dimensional information about the images captured by the monocular camera 2 is interpolated. This allows the reinforcement inspection device 1 to perform reinforcement inspection without taking multiple images of the reinforcement surface.

In the reinforcement bar inspection device 1 according to embodiment 1, measurement result information is output to a terminal device equipped with a monocular camera 2, LiDAR 3, and display unit 4, and displayed on the display unit 4. This enables reinforcement bar inspection using the terminal device.

In the reinforcement bar inspection device 1 according to embodiment 1, the first rebar diameter determination unit 16 determines the rebar diameter of the rebar indicated by the first position information based on a spectrum obtained by frequency-converting a first pixel value scanning line set for each pixel in a direction intersecting the longitudinal direction of the rebar indicated by the first position information. By using the spectrum obtained by frequency-converting the first pixel value scanning line set for each pixel, the reinforcement bar inspection device 1 can accurately determine the rebar diameter of the rebar indicated by the first position information.

In the reinforcing bar inspection device 1 according to embodiment 1, the first reinforcing bar diameter determination unit 16 determines the reinforcing bar diameter based on a spectrum obtained by frequency-converting a first pixel value scanning line set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information. The second reinforcing bar diameter determination unit 17 determines the reinforcing bar diameter of the reinforcing bar indicated by the second position information based on a spectrum obtained by frequency-converting a second pixel value scanning line set for each pixel in the longitudinal direction of the reinforcing bar indicated by the first position information. By using the spectrum obtained by frequency-converting the pixel value scanning line set for each pixel, the reinforcing bar inspection device 1 can accurately determine the reinforcing bar diameter of the reinforcing bar indicated by the first position information and the reinforcing bar diameter of the reinforcing bar indicated by the second position information.

In the reinforcement bar inspection device 1 according to embodiment 1, the correlation calculation unit 18 calculates a correlation value between a first reference spectrum obtained by frequency-converting the first pixel value scanning line and a spectrum obtained by frequency-converting the first pixel value scanning line set for each pixel in a direction intersecting the longitudinal direction of the rebar indicated by the first position information. The first rebar diameter determination unit 16 determines the rebar diameter of the rebar indicated by the first position information based on the correlation value. By using the correlation value between the first reference spectrum and the spectrum obtained by frequency-converting the first pixel value scanning line, the reinforcement bar inspection device 1 can accurately determine the rebar diameter of the rebar indicated by the first position information.

In the reinforcement bar inspection device 1 according to embodiment 1, the correlation calculation unit 18 calculates a correlation value between a second reference spectrum obtained by frequency-converting the second pixel value scanning line and a spectrum obtained by frequency-converting the second pixel value scanning line set for each pixel in the longitudinal direction of the rebar indicated by the first position information. The second rebar diameter determination unit 17 determines the rebar diameter of the rebar indicated by the second position information based on the correlation value. By using the correlation value between the second reference spectrum and the spectrum obtained by frequency-converting the second pixel value scanning line, the reinforcement bar inspection device 1 can accurately determine the rebar diameter of the rebar indicated by the second position information.

In the reinforcing bar inspection device 1 according to embodiment 1, the first reinforcing bar diameter determination unit 16 stores in the memory unit 5 a spectrum obtained by frequency-converting a first pixel value scanning line set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information. The correlation calculation unit 18 calculates a correlation value between the spectrum stored in the memory unit 5 and a spectrum obtained by frequency-converting a second pixel value scanning line set for each pixel in the longitudinal direction of the reinforcing bar indicated by the first position information. The second reinforcing bar diameter determination unit 17 determines the reinforcing bar diameter of the reinforcing bar indicated by the second position information based on the correlation value. This enables the reinforcing bar inspection device 1 to accurately determine the reinforcing bar diameter of the reinforcing bar indicated by the second position information.

In the reinforcement bar arrangement inspection method according to the first embodiment, a three-dimensional information acquisition unit 11 inputs an image of an inspection area where reinforcing bars are arranged in a grid pattern, taken by a monocular camera 2, and three-dimensional point cloud data obtained by three-dimensionally measuring the inspection area by a LiDAR 3, identifies an inspection sheet range determined by an inspection sheet 6 laid in the longitudinal direction of the reinforcing bars that intersect with each other from the image, and acquires three-dimensional point cloud data of the inspection sheet range, a plane identification unit 12 identifies the reinforcement surface of the inspection target within the inspection sheet range based on the three-dimensional point cloud data of the inspection sheet range, an image conversion unit 13 converts the captured image into an orthogonal image, and a first detection unit 14 detects first position information of the reinforcing bars on the reinforcement surface of the inspection target in the orthogonal image based on pixel value distribution indicated by a first pixel value scanning line set in the longitudinal direction of the reinforcing bars where the inspection sheet 6 is laid in the longitudinal direction, and The second position information is detected, and the second detection unit 15 detects the number and spacing of the reinforcing bars indicated by the second position information based on the pixel value distribution indicated by the second pixel value scanning lines set for each pixel in the longitudinal direction of the reinforcing bars indicated by the first position information, the first reinforcing bar diameter determination unit 16 determines the reinforcing bar diameter of the reinforcing bars indicated by the first position information based on the pixel value distribution indicated by the first pixel value scanning lines set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bars indicated by the first position information, the second reinforcing bar diameter determination unit 17 determines the reinforcing bar diameter of the reinforcing bars indicated by the second position information based on the pixel value distribution indicated by the second pixel value scanning lines set for each pixel in the longitudinal direction of the reinforcing bars indicated by the first position information, and the measurement result information generation unit 19 generates and outputs measurement result information indicating the reinforcing bar diameter, number and spacing of the reinforcing bars obtained in the longitudinal direction of the inspection sheet 6 and in the direction intersecting the longitudinal direction of the inspection sheet 6 within the inspection sheet range, respectively.
By executing this reinforcement bar arrangement inspection method using the reinforcement bar arrangement inspection device 1, reinforcement bar arrangement inspection can be performed without taking multiple photographs of the reinforcement bar arrangement surface.

A computer executing the program according to embodiment 1 functions as a reinforcement inspection device 1. It is possible to provide a reinforcement inspection device 1 that can perform reinforcement inspection without taking multiple images of the reinforcement surface.

Various aspects of the present disclosure are summarized below as appendices.
(Appendix 1)
a three-dimensional information acquisition unit that inputs a photographed image of a reinforcing bar with an inspection sheet laid in the longitudinal direction, taken by a monocular camera, and three-dimensional point cloud data obtained by three-dimensionally measuring the reinforcing bar with the inspection sheet laid in the longitudinal direction using a lidar, identifies an inspection sheet range determined by the inspection sheet from the photographed image, and acquires the three-dimensional point cloud data of the inspection sheet range;
a plane specifying unit that specifies a reinforcement plane to be inspected based on the three-dimensional point cloud data of the inspection sheet range;
an image conversion unit that converts the captured image into a normal image;
a detection unit that detects position information of the reinforcing bar based on a pixel value distribution indicated by a pixel value scanning line set in the longitudinal direction of the reinforcing bar on the reinforcing bar arrangement surface of the inspection target in the orthogonal image;
a reinforcing bar diameter determination unit that determines the reinforcing bar diameter of the reinforcing bar indicated by the position information based on the pixel value distribution indicated by each of the pixel value scanning lines set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar;
a measurement result information generating unit that generates and outputs measurement result information indicating the diameters of reinforcing bars in the inspection sheet range.
(Appendix 2)
a three-dimensional information acquisition unit that inputs an image of an inspection area where reinforcing bars are arranged in a grid pattern, taken with a monocular camera, and three-dimensional point cloud data obtained by three-dimensionally measuring the inspection area with a lidar, identifies an inspection sheet range determined by an inspection sheet laid in the longitudinal direction of the reinforcing bars that intersect with each other from the image, and acquires the three-dimensional point cloud data of the inspection sheet range;
a plane specifying unit that specifies a reinforcement plane to be inspected based on the three-dimensional point cloud data of the inspection sheet range;
an image conversion unit that converts the captured image into a normal image;
a first detection unit that detects first position information of the reinforcing bars on the reinforcing bar arrangement surface of the inspection target in the orthogonal image based on a pixel value distribution indicated by a first pixel value scanning line set in the longitudinal direction of the reinforcing bars laid in the longitudinal direction of the inspection sheet, and detects second position information of the reinforcing bars arranged so that the inspection sheet crosses the reinforcing bars laid in the longitudinal direction;
a second detection unit that detects the number and spacing of the reinforcing bars indicated by the second position information based on pixel value distributions indicated by second pixel value scanning lines set for each pixel in the longitudinal direction of the inspection sheet;
a first reinforcing bar diameter determination unit that determines the reinforcing bar diameter of the reinforcing bar indicated by the first position information based on the pixel value distribution indicated by each of the first pixel value scanning lines set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information;
a second reinforcing bar diameter determination unit that determines the reinforcing bar diameter of the reinforcing bar indicated by the second position information based on the pixel value distribution indicated by the second pixel value scanning line set for each pixel in the longitudinal direction of the reinforcing bar indicated by the first position information;
a measurement result information generating unit that generates and outputs measurement result information indicating the diameter, number, and spacing of reinforcing bars obtained in the longitudinal direction of the inspection sheet and in a direction intersecting the longitudinal direction of the inspection sheet within the inspection sheet range.
(Appendix 3)
The bar arrangement inspection device according to claim 1 or 2, wherein the measurement result information is output to a terminal device including the monocular camera, the lidar, and a display unit, and is displayed on the display unit.
(Appendix 4)
The reinforcing bar inspection device according to claim 2, wherein the first reinforcing bar diameter determination unit determines the reinforcing bar diameter of the reinforcing bar indicated by the first position information based on a spectrum obtained by frequency-converting the first pixel value scanning line set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information.
(Appendix 5)
The first reinforcing bar diameter determination unit determines the reinforcing bar diameter of the reinforcing bar indicated by the first position information based on a spectrum obtained by frequency-converting the first pixel value scanning line set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information,
The second reinforcing bar diameter determination unit determines the reinforcing bar diameter of the reinforcing bar indicated by the second position information based on a spectrum obtained by frequency-converting the second pixel value scanning line set for each pixel in the longitudinal direction of the reinforcing bar indicated by the first position information.
(Appendix 6)
a correlation calculation unit that calculates a correlation value between a first reference spectrum obtained by frequency-converting the first pixel value scanning line and a spectrum obtained by frequency-converting the first pixel value scanning line set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information,
The reinforcing bar inspection device according to claim 4 or 5, wherein the first reinforcing bar diameter determination unit determines the reinforcing bar diameter of the reinforcing bar indicated by the first position information based on the correlation value.
(Appendix 7)
a correlation calculation unit that calculates a correlation value between a second reference spectrum obtained by frequency-converting the second pixel value scanning line and a spectrum obtained by frequency-converting the second pixel value scanning line set for each pixel in the longitudinal direction of the reinforcing bar indicated by the first position information;
The reinforcing bar inspection device according to claim 5, wherein the second reinforcing bar diameter determination unit determines the reinforcing bar diameter of the reinforcing bar indicated by the second position information based on the correlation value.
(Appendix 8)
The first reinforcing bar diameter determination unit stores in a storage unit a spectrum obtained by frequency-converting the first pixel value scanning line set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information,
a correlation calculation unit that calculates a correlation value between the spectrum stored in the storage unit and a spectrum obtained by frequency-converting the second pixel value scanning line set for each pixel in the longitudinal direction of the reinforcing bar indicated by the first position information,
The reinforcing bar inspection device according to claim 5, wherein the second reinforcing bar diameter determination unit determines the reinforcing bar diameter of the reinforcing bar indicated by the second position information based on the correlation value.
(Appendix 9)
A reinforcement inspection method using a reinforcement inspection device,
a three-dimensional information acquisition unit inputs a photographed image of an inspection area where reinforcing bars are arranged in a grid pattern, taken by a monocular camera, and three-dimensional point cloud data obtained by three-dimensionally measuring the inspection area by a lidar, identifies an inspection sheet range determined by inspection sheets laid in the longitudinal direction of the reinforcing bars that intersect with each other from the photographed image, and acquires the three-dimensional point cloud data of the inspection sheet range;
a step in which a plane specifying unit specifies a reinforcement surface to be inspected in the inspection sheet range based on the three-dimensional point cloud data of the inspection sheet range;
an image conversion unit converting the captured image into a normal image;
a step in which a first detection unit detects first position information of a reinforcing bar on the reinforcing bar arrangement surface of the inspection target in the orthogonal image based on a pixel value distribution indicated by a first pixel value scanning line set in the longitudinal direction of the reinforcing bar by the inspection sheet, and detects second position information of a reinforcing bar arranged so as to cross the reinforcing bar laid in the longitudinal direction by the inspection sheet;
a step in which a second detection unit detects the number and spacing of the reinforcing bars indicated by the second position information based on pixel value distributions indicated by second pixel value scanning lines set for each pixel in the longitudinal direction of the reinforcing bars indicated by the first position information;
A step in which a first reinforcing bar diameter determination unit determines the reinforcing bar diameter of the reinforcing bar indicated by the first position information based on the pixel value distribution indicated by each of the first pixel value scanning lines set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information;
A step in which a second reinforcing bar diameter determination unit determines the reinforcing bar diameter of the reinforcing bar indicated by the second position information based on the pixel value distribution indicated by each of the second pixel value scanning lines set for each pixel in the longitudinal direction of the reinforcing bar indicated by the first position information;
a step of the measurement result information generating unit generating and outputting measurement result information indicating the diameter, number and spacing of reinforcing bars obtained in the longitudinal direction of the inspection sheet and in a direction intersecting the longitudinal direction of the inspection sheet within the inspection sheet range.
(Appendix 10)
A program for causing a computer to function as the reinforcement inspection device according to any one of Supplementary Note 1 to Supplementary Note 8.

In addition, any of the components of the embodiments may be modified or omitted.

1 Reinforcement inspection device, 2 Monocular camera, 2A Captured image, 2B Oriented image, 3 LiDAR, 4 Display unit, 5 Memory unit, 6 Inspection sheet, 7 Marker, 7A Base, 7B Identification shape, 8 Reinforcement bar, 11 Three-dimensional information acquisition unit, 12 Plane identification unit, 13 Image conversion unit, 14 First detection unit, 15 Second detection unit, 16 First reinforcement bar diameter determination unit, 17 Second reinforcement bar diameter determination unit, 18 Correlation calculation unit, 19 Measurement result information generation unit, 31 Outlier, 32 Inlier, 100 Input interface, 101 Output interface, 102 Processing circuit, 103 Processor, 104 Memory.

Claims (9)

a three-dimensional information acquisition unit that inputs an image of an inspection area where reinforcing bars are arranged in a grid pattern, taken with a monocular camera, and three-dimensional point cloud data obtained by three-dimensionally measuring the inspection area with a lidar, identifies an inspection sheet range determined by an inspection sheet laid in the longitudinal direction of the reinforcing bars that intersect with each other from the image, and acquires the three-dimensional point cloud data of the inspection sheet range;
a plane specifying unit that specifies a reinforcement plane to be inspected based on the three-dimensional point cloud data of the inspection sheet range;
an image conversion unit that converts the captured image into a normal image;
a first detection unit that detects first position information of the reinforcing bars on the reinforcing bar arrangement surface of the inspection target in the orthogonal image based on a pixel value distribution indicated by a first pixel value scanning line set in the longitudinal direction of the reinforcing bars laid in the longitudinal direction of the inspection sheet, and detects second position information of the reinforcing bars arranged so that the inspection sheet crosses the reinforcing bars laid in the longitudinal direction;
a second detection unit that detects the number and spacing of the reinforcing bars indicated by the second position information based on pixel value distributions indicated by second pixel value scanning lines set for each pixel in the longitudinal direction of the inspection sheet;
a first reinforcing bar diameter determination unit that determines the reinforcing bar diameter of the reinforcing bar indicated by the first position information based on the pixel value distribution indicated by each of the first pixel value scanning lines set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information;
a second reinforcing bar diameter determination unit that determines the reinforcing bar diameter of the reinforcing bar indicated by the second position information based on the pixel value distribution indicated by the second pixel value scanning line set for each pixel in the longitudinal direction of the reinforcing bar indicated by the first position information;
a measurement result information generating unit that generates and outputs measurement result information indicating the diameter, number, and spacing of reinforcing bars obtained in the longitudinal direction of the inspection sheet and in a direction intersecting the longitudinal direction of the inspection sheet within the inspection sheet range. The bar arrangement inspection device according to claim 1 , wherein the measurement result information is output to a terminal device including the monocular camera, the lidar, and a display unit, and is displayed on the display unit. The reinforcing bar inspection device according to claim 1, characterized in that the first reinforcing bar diameter determination unit determines the reinforcing bar diameter of the reinforcing bar indicated by the first position information based on a spectrum obtained by frequency-converting the first pixel value scanning line set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information. The first reinforcing bar diameter determination unit determines the reinforcing bar diameter of the reinforcing bar indicated by the first position information based on a spectrum obtained by frequency-converting the first pixel value scanning line set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information,
The reinforcing bar inspection device according to claim 1, characterized in that the second reinforcing bar diameter determination unit determines the reinforcing bar diameter of the reinforcing bar indicated by the second position information based on a spectrum obtained by frequency-converting the second pixel value scanning line set for each pixel in the longitudinal direction of the reinforcing bar indicated by the first position information. a correlation calculation unit that calculates a correlation value between a first reference spectrum obtained by frequency-converting the first pixel value scanning line and a spectrum obtained by frequency-converting the first pixel value scanning line set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information,
The bar arrangement inspection device according to claim 4 , wherein the first reinforcing bar diameter determination unit determines the reinforcing bar diameter of the reinforcing bar indicated by the first position information based on the correlation value. a correlation calculation unit that calculates a correlation value between a second reference spectrum obtained by frequency-converting the second pixel value scanning line and a spectrum obtained by frequency-converting the second pixel value scanning line set for each pixel in the longitudinal direction of the reinforcing bar indicated by the first position information;
The bar arrangement inspection device according to claim 5 , wherein the second reinforcing bar diameter determination unit determines the reinforcing bar diameter of the reinforcing bar indicated by the second position information based on the correlation value. The first reinforcing bar diameter determination unit stores in a storage unit a spectrum obtained by frequency-converting the first pixel value scanning line set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information,
a correlation calculation unit that calculates a correlation value between the spectrum stored in the storage unit and a spectrum obtained by frequency-converting the second pixel value scanning line set for each pixel in the longitudinal direction of the reinforcing bar indicated by the first position information,
The bar arrangement inspection device according to claim 4 , wherein the second reinforcing bar diameter determination unit determines the reinforcing bar diameter of the reinforcing bar indicated by the second position information based on the correlation value. A reinforcement inspection method using a reinforcement inspection device,
a three-dimensional information acquisition unit inputs a photographed image of an inspection area where reinforcing bars are arranged in a grid pattern, taken by a monocular camera, and three-dimensional point cloud data obtained by three-dimensionally measuring the inspection area by a lidar, identifies an inspection sheet range determined by inspection sheets laid in the longitudinal direction of the reinforcing bars that intersect with each other from the photographed image, and acquires the three-dimensional point cloud data of the inspection sheet range;
a step in which a plane specifying unit specifies a reinforcement surface to be inspected in the inspection sheet range based on the three-dimensional point cloud data of the inspection sheet range;
an image conversion unit converting the captured image into a normal image;
a step in which a first detection unit detects first position information of a reinforcing bar on the reinforcing bar arrangement surface of the inspection target in the orthogonal image based on a pixel value distribution indicated by a first pixel value scanning line set in the longitudinal direction of the reinforcing bar by the inspection sheet, and detects second position information of a reinforcing bar arranged so as to cross the reinforcing bar laid in the longitudinal direction by the inspection sheet;
a step in which a second detection unit detects the number and spacing of the reinforcing bars indicated by the second position information based on pixel value distributions indicated by second pixel value scanning lines set for each pixel in the longitudinal direction of the reinforcing bars indicated by the first position information;
A step in which a first reinforcing bar diameter determination unit determines the reinforcing bar diameter of the reinforcing bar indicated by the first position information based on the pixel value distribution indicated by each of the first pixel value scanning lines set for each pixel in a direction intersecting the longitudinal direction of the reinforcing bar indicated by the first position information;
A step in which a second reinforcing bar diameter determination unit determines the reinforcing bar diameter of the reinforcing bar indicated by the second position information based on the pixel value distribution indicated by each of the second pixel value scanning lines set for each pixel in the longitudinal direction of the reinforcing bar indicated by the first position information;
a step of the measurement result information generating unit generating and outputting measurement result information indicating the diameter, number and spacing of reinforcing bars obtained in the longitudinal direction of the inspection sheet and in a direction intersecting the longitudinal direction of the inspection sheet within the inspection sheet range. A program for causing a computer to function as the bar arrangement inspection device according to any one of claims 1 to 7 .