Image measurement device, image measurement method, and image measurement program

Abstract

To reduce errors when measuring a reinforcing steel.SOLUTION: An image measurement device (100) acquires an image of a small opening (21) of a columnar bar arrangement (200), receives the specification of a small opening region (301) including the small opening in the image from a user, calculates the three-dimensional coordinates of a plurality of feature points in the small opening region, calculates a small opening flat surface (302) on the basis of the three-dimensional coordinate, detects a small opening from a point group near the small opening flat surface, measures the columnar bar arrangement on the basis of the small opening, and outputs the result of the measurement.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an image measurement device, an image measurement method, and an image measurement program for measuring rebar at the end of column reinforcement by image processing. [Background technology]

[0002] Currently, technology is being developed to measure rebar diameter, spacing, etc. by analyzing photographed images of rebar arrangement. In addition, development is also underway on user support technology for photographing and measuring rebar arrangement, and technology to improve measurement accuracy.

[0003] For example, the notification device in Patent Document 1 acquires stereo images of reinforcing bars, generates three-dimensional point cloud coordinates based on the acquired stereo images, and identifies a plane formed by the reinforcing bars that make up the reinforcing bars based on the generated three-dimensional point cloud coordinates. Next, if the notification device determines that reinforcing bars cannot be measured when generating the three-dimensional point cloud coordinates or when identifying the plane, it notifies the device of this fact. If the notification device cannot generate three-dimensional point cloud coordinates or if the inclination angle of the identified plane or the distance to the plane does not satisfy a predetermined condition, it determines that reinforcing bars cannot be measured. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2018-173275 Summary of the Invention [Problem to be solved by the invention]

[0005] However, because there are other surfaces in the background of one side of a pillar or beam, a large number of rebars are densely packed in the photographed image. Therefore, when measuring pillars, beams, etc. where many rebars are arranged in a complex manner, there is a possibility that measurement errors will occur when measuring using image processing.

[0006] One aspect of the present invention aims to reduce errors when measuring reinforcing bars. [Means for solving the problem]

[0007] In order to solve the above problems, an image measuring device according to one aspect of the present invention is an image measuring device that measures column reinforcement using an image of the edge of the column reinforcement, and includes: an acquisition unit that acquires the image of the edge; a reception unit that receives from a user a specification of an edge area that includes the edge in the image acquired by the acquisition unit; a detection unit that calculates three-dimensional coordinates of a plurality of feature points present in the edge area, calculates an edge plane that is a three-dimensional plane based on the three-dimensional coordinates, and detects the edge from a point cloud that exists in the vicinity of the edge plane; a measurement unit that measures the column reinforcement based on the detected edge; and an output unit that outputs the measurement results.

[0008] Furthermore, in order to solve the above-mentioned problems, an image measurement device according to one aspect of the present invention is an image measurement method for measuring column reinforcement using an image of the edge of the column reinforcement, and includes: an acquisition step for acquiring an image of the edge; a reception step for receiving from a user specification of an edge area that is an area including the edge in the image acquired in the acquisition step; a detection step for calculating three-dimensional coordinates of a plurality of feature points present in the edge area, calculating an edge plane that is a three-dimensional plane based on the three-dimensional coordinates, and detecting the edge from a point cloud present in the vicinity of the edge plane; a measurement step for measuring the column reinforcement based on the detected edge; and an output step for outputting the measurement results. [Effects of the Invention]

[0009] According to one aspect of the present invention, errors when measuring reinforcing bars can be reduced. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a block diagram showing a configuration of an image measurement device according to a first embodiment of the present invention. [Figure 2] FIG. 1 is a perspective view showing a column reinforcement structure according to a first embodiment of the present invention. [Figure 3] FIG. 2 is a diagram showing an image of a column reinforcement edge according to the first embodiment of the present invention. [Figure 4] FIG. 10 is a diagram showing an example in which the designation of a fore-edge region is accepted and feature points of the fore-edge region are detected according to the first embodiment of the present invention. [Figure 5] FIG. 2 is a diagram showing an example of an image in which feature points in the vicinity of the fore-edge plane are drawn according to the first embodiment of the present invention. [Figure 6] FIG. 2 is a diagram showing an example of an image in which a point cloud is projected onto a fore-edge plane according to the first embodiment of the present invention. [Figure 7] FIG. 2 is a diagram showing a state in which the image measurement device according to the first embodiment of the present invention restricts the position of a point cloud. [Figure 8] 4 is a flowchart showing the processing of the image measurement device according to the first embodiment of the present invention. [Figure 9] FIG. 10 is a diagram showing an image of a column reinforcement edge according to the second embodiment of the present invention. [Figure 10] FIG. 10 is a diagram showing a point cloud in the vicinity of the fore-edge plane according to the second embodiment of the present invention. [Figure 11] FIG. 10 is a diagram showing an image of a column reinforcement edge according to the third embodiment of the present invention. [Figure 12] FIG. 10 is a diagram showing a point cloud within a predetermined range from the outer edge plane according to a third embodiment of the present invention. [Figure 13] FIG. 10 is a diagram showing a point cloud within a predetermined range from the inner edge plane according to a third embodiment of the present invention. [Figure 14] FIG. 10 is a diagram showing the result of projecting a point cloud onto an inner edge plane according to the third embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0011] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described in detail with reference to the drawings.

[0012] [Embodiment 1] Fig. 1 is a block diagram showing the configuration of an image measurement device 100 according to a first embodiment of the present invention. The image measurement device 100 measures column reinforcement using an image of the edge of the column reinforcement taken from diagonally above. As shown in Fig. 1, the image measurement device 100 includes, as hardware, an imaging unit 101, an imaging unit 102, an image processing unit 103, a display unit 104, an input unit 105, and a storage unit 106.

[0013] The imaging units 101 and 102 are configured with solid-state imaging elements such as CCD (Charge Coupled Device) and CMOS (Complementary Metal Oxide Semiconductor) sensors, lenses, etc., and acquire images according to shooting conditions such as set exposure and focus position.

[0014] The image processing unit 103 performs image processing to measure the distance between a point and a plane, etc. The image processing unit 103 can be realized by software processing using a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), or by hardware processing using an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0015] The display unit 104 is a display for displaying images acquired by the imaging units 101 and 102, measurement results of the distance between a point and a plane, etc. The display unit 104 is configured by a display device such as a liquid crystal display or an organic EL (Electro Luminescence) display.

[0016] The input unit 105 is configured with a mouse, the touch panel of the display unit 104, etc. The storage unit 106 includes a storage medium such as a flash memory or a magnetic disk, and stores captured images, measurement results, etc.

[0017] The image processing unit 103 calculates the parallax from the images captured by the imaging units 101 and 102, and calculates three-dimensional information of the object in the image. The parallax is the amount of displacement of the object between two images, and is calculated using block matching or the like. In block matching, a reference window is set at a pixel of interest in a reference image, and reference windows are sequentially set in the reference image, and the similarity or difference between the pixels in the reference window and the reference window is evaluated. For the evaluation, SAD (Sum of Absolute Difference), SSD (Sum of Squared Difference), etc. are used.

[0018] The relationship between the distance Z to the photographed subject and the parallax D is expressed by D = f × B / Z, where f is the focal length of the image capturing units 101 and 102, and B is the distance between the two image capturing units. Furthermore, the three-dimensional coordinates (X, Y, Z) of the subject at the distance Z at the coordinates (x, y) on the image can be calculated by X = x × Z / f and Y = y × Z / f.

[0019] Here, with regard to the image measurement device 100 according to this embodiment, a method for calculating parallax from images acquired by the two image capturing units 101 and 102 when acquiring three-dimensional information (depth information) will be described. Note that other methods may also be used; for example, the field of view may be calculated from three or more image capturing units, or depth information may be acquired by TOF (Time Of Flight).

[0020] The column reinforcement in this embodiment shows reinforcement arranged in the shape of a square pillar. The reinforcement includes main reinforcement and ties. Main reinforcement is a steel bar that extends vertically and refers to a thick steel bar found in concrete such as a pillar. Ties are steel bars that extend horizontally and refer to thin steel bars used in pillars and surround the main reinforcement. The end is the cut edge at the top end of the main reinforcement that makes up the column reinforcement. The end plane is a three-dimensional plane in which the end exists nearby.

[0021] Measurements of rebar ends include the number of rebars, rebar diameter, and rebar spacing. The number of rebars is the number of main rebars among the rebars that make up the column reinforcement. The rebar diameter is the diameter of the main rebars among the rebars that make up the column reinforcement. Regarding rebar diameter, sometimes only the diameter of the main rebar is output, and sometimes the rebar standard of the measured main rebar is determined by comparing the measured diameter with the nominal diameter, node height, etc., and the name of that rebar standard is output. Regarding rebar spacing, there are cases where the distance between the rebar position lines that indicate the center position of the rebars is measured, and cases where the distance between the surfaces of opposing rebars is measured as the space between the rebars.

[0022] The object of the present invention is to measure the number of rebars, their diameters, and spacing. Measurements are made using the ends of the main reinforcement bars. Furthermore, when the user specifies several end areas, the image measurement device 100 identifies an end plane, which is a three-dimensional plane in which the ends are located nearby, and identifies the ends from the end plane. This allows all the ends to be identified based on the end plane, even if the user does not specify end areas for all the ends.

[0023] The image measuring device 100 can inspect important inspection items such as the number of rebars based on an image of the edge 21 taken from diagonally above. The image measuring device 100 can also inspect whether rebars of the wrong diameter have been inserted.

[0024] Fig. 2 is a perspective view showing the structure of the column reinforcement 200 according to this embodiment. Fig. 2 also shows a state in which an image of the end 21 of the main reinforcement 20 constituting the column reinforcement 200 is being captured using the image measurement device 100. The image measurement device 100 acquires an image of the end 21 captured from diagonally above.

[0025] The column reinforcement 200 is composed of four vertical faces (not shown), and on the horizontal end plane 302, there are multiple ends 21 of the main reinforcement 20 that are erected vertically. The hoops 25 are laid horizontally so as to surround the main reinforcement 20. When photographing the end 21 of rectangular reinforcement such as a column or beam, if it is not possible to photograph the end 21 head-on, the image measuring device 100 photographs the end 21 from diagonally above.

[0026] 3 is a diagram showing an image of the end 21 of the column reinforcement 200 captured using the image measurement device 100 according to this embodiment. The end 21 of the main reinforcement 20 is actually approximately circular, but because the image was captured from diagonally above, the circular shape is distorted. In addition, the end 21 at the back is captured in such a way that it appears smaller than the end 21 at the front.

[0027] The image measurement device 100 receives from the user a designation of a fore-edge region 301 including the fore-edge 21 in the image displayed on the display unit 104. For example, in the image measurement device 100, the display unit 104 displays an image as shown in FIG. 3, and the user designates the fore-edge region 301 via the input unit 105. As a method for designating the fore-edge region 301 using the input unit 105, for example, the user may designate the region so as to surround the fore-edge 21 of the main reinforcement 20. Alternatively, the user may designate a point near the center of the fore-edge 21, and the image measurement device 100 may set a predetermined range based on the point (for example, a rectangular, circular, or other area centered on the point) as the fore-edge region 301. In the example shown in FIG. 3, the fore-edge region 301 is set to three locations surrounded by dashed lines.

[0028] Next, the image measurement device 100 calculates the three-dimensional coordinates of a plurality of feature points present in the specified fore-edge region 301. Conventional methods can be applied to detect the feature points, such as a Sobel filter or a Laplacian filter.

[0029] The image measurement device 100 then calculates a three-dimensional plane, the fore-edge plane 302, based on the three-dimensional coordinates of the calculated feature points. The fore-edge plane 302 is derived, for example, by calculating a least-squares plane based on the feature points. Here, if multiple feature points exist in one fore-edge region 301, it is possible to calculate the fore-edge plane 302 by setting one fore-edge region 301. However, due to the existence of calculation errors in the three-dimensional coordinates and individual differences in the inclination of the fore-edge 21 of each rebar, it is preferable to set multiple fore-edge regions 301 and calculate the three-dimensional plane based on the multiple three-dimensional coordinates calculated from each fore-edge region 301, as this reduces the effects of errors and individual differences. Figure 4 shows an example of accepting the designation of three fore-edge regions 301 according to this embodiment and detecting feature points 301' in the fore-edge regions 301.

[0030] Next, the image measurement device 100 detects the fore edge 21 from the point cloud existing near the fore edge plane 302. The fore edge 21 is detected based on feature points existing near the fore edge plane 302. "Existing near the fore edge plane 302" means that the distance from the fore edge plane 302 is within a predetermined threshold. The image measurement device 100, for example, calculates the three-dimensional coordinates of feature points within the image, calculates the distance between each feature point and the fore edge plane 302, and determines feature points whose distance is equal to or less than a predetermined threshold as feature points representing the fore edge 21.

[0031] Fig. 5 is a diagram showing an example of an image depicting feature points 302' near the edge plane 302 according to this embodiment. Since feature points 302' include a group of points that exist within a predetermined distance from the edge plane 302, the image shown in Fig. 5 also depicts the rebar area other than the cut end, which is the edge 21, i.e., the pillar portion.

[0032] Then, the image measurement device 100 projects the feature points present in the vicinity of the fore edge plane 302 onto the fore edge plane 302 and detects them as a circle on the fore edge plane 302.

[0033] FIG. 6 is a diagram showing an example of an image in which a point cloud is projected onto the edge plane 302 according to this embodiment. When the point cloud shown in FIG. 5 is projected onto the edge plane 302, it is projected directly onto the edge plane 302, as shown in FIG. 6. Conventional methods can be applied to detecting circular shapes. For example, using the center coordinates and radius of a circle as parameters, a circle is detected when the number of feature points present around the circumference of the circle is equal to or greater than a threshold value. Here, when projecting the point cloud around the edge plane 302 onto the edge plane 302, processing may be performed based on calculated three-dimensional coordinates, or the point cloud may be projected onto the edge plane 302 based on image coordinates, assuming that each point exists on the edge plane 302.

[0034] Next, the image measuring device 100 measures the column reinforcement 200 (particularly the main reinforcements 20) based on the detected end faces 21. The number of main reinforcements 20 is calculated from the number of circles that are end faces 21. The diameter of the main reinforcements 20 is calculated from the radius of the circles. The spacing between the main reinforcements 20 is calculated from the distance between the centers of adjacent circles. This makes it possible to measure the number of rebars, rebar diameter, and rebar spacing even in the reinforcement of columns, beams, etc. where a large number of rebars are arranged in a complex manner.

[0035] The image measurement device 100 outputs the measurement results by storing them in the storage unit 106 as a text file or displaying them on the display unit 104 as image information.

[0036] In the above, the image measurement device 100 detects the point cloud near the fore edge plane 302 from the entire image, but the user may limit the detection range. For example, the user specifies the area where the fore edge 21 exists as the measurement range. In particular, when specifying the fore edge area 301, it is preferable to specify an area that includes the fore edge 21 that exists at the corner of the column reinforcement 200 (i.e., near the vertex of the rectangle when the column reinforcement 200 is viewed from above). This allows the image measurement device 100 to appropriately set the range where the fore edge 21 exists.

[0037] Furthermore, the image measurement device 100 can reduce the influence of the foreground and background by using only the point cloud near the line segment connecting the positions of the corners of the set reinforcement (for example, the center position of the fore edge area 301) as feature points, thereby improving measurement accuracy. This is because, if an error occurs when calculating the parallax, the feature points may be included in the point cloud near the fore edge plane 302, but since only the point cloud near the line segment is used as the feature points, erroneous detection of the fore edge 21 is reduced. Note that "near the line segment" means that the distance from the line segment is within a predetermined value.

[0038] 7 is a diagram showing a state in which the image measurement device 100 according to this embodiment restricts the position of the point cloud. The image measurement device 100 receives from the user the specification of an edge region 301 including an edge 21 located at the corner of the column reinforcement 200. Next, the image measurement device 100 extracts a point cloud from the vicinity of the line segment connecting the edge regions 301.

[0039] For example, the four line segments 400 connecting the corner positions of the column reinforcement 200 are shown as dashed lines in Figure 7. On the image, the rebars within a predetermined distance from the line segments 400 are drawn. This makes it possible to limit the range in which the point cloud around the edge plane 302 is detected, thereby improving measurement accuracy.

[0040] FIG. 8 is a flowchart showing the processing of the image measuring device 100 according to this embodiment.

[0041] (Step S1: Acquisition step) In the image measurement device 100, the image processing unit (acquisition unit) 103 acquires an image of the end 21 of the main reinforcement 20, which is the measurement target, photographed from diagonally above by the imaging unit 101 and the imaging unit .

[0042] (Step S2: Reception step) In the acquisition step, the image processing unit (acquisition unit) 103 accepts the designation of the fore-edge area 301 for the image acquired by the image processing unit (acquisition unit) 103. The designation of the fore-edge area 301 is performed by the user via the input unit 105 on the image displayed on the display unit 104.

[0043] (Step S3) The image processing unit 103 calculates the three-dimensional coordinates of the user-specified fore-edge area 301. The calculation of the three-dimensional coordinates may be performed for all pixels included in the fore-edge area 301, but by performing the calculation for feature points whose edge strength is equal to or greater than a certain level, processing time can be reduced.

[0044] (Step S4) Based on the three-dimensional coordinates of each calculated point, the image processing unit 103 calculates the fore-edge plane 302. The three-dimensional plane representing the fore-edge plane 302 is calculated from the least-squares plane of each point, for example.

[0045] (Step S5: Detection step) The image processing unit (detection unit) 103 detects the fore edge 21 from a point cloud that exists within a predetermined distance from the fore edge plane 302. The point cloud is selected by calculating the distance between the three-dimensional coordinates of each point and a three-dimensional plane that represents the fore edge plane 302 and comparing this distance with a threshold. The selected point cloud is projected onto the fore edge plane 302, and the fore edge 21 is detected by detecting a circular shape on the fore edge plane 302. The projection onto the fore edge plane 302 may involve projecting the three-dimensional point cloud onto the fore edge plane 302, or it may involve projecting the image coordinates of the selected point cloud onto the fore edge plane 302, assuming that they are located there.

[0046] (Step S6: Measurement step) The image processing unit (measurement unit) 103 measures the reinforcing bars based on the detected edges 21.

[0047] (Step S7: Output step) The image processing unit (output unit) 103 outputs the measurement results as output information. The image processing unit 103 stores the output information in the storage unit 106 as a text file or image data, or displays it on the display unit 104.

[0048] According to the above, since rebars are measured based on an image of the ends 21 of columns, beams, etc. taken from diagonally above, it is possible to obtain stable measurement results regardless of the number of rebars, the rebar arrangement configuration, etc. In other words, since the ends 21 of the column reinforcement 200 can be accurately detected from an image taken from diagonally above, errors when measuring rebars can be reduced. Furthermore, since the ends 21 are used, it is possible to measure not only the number of rebars but also the rebar diameter and rebar spacing, which is useful.

[0049] In this embodiment, a method has been described in which the image processing unit 103 directly acquires images captured by the imaging units 101 and 102, but the same effect can be achieved by acquiring images stored in the memory unit 106.

[0050] [Embodiment 2] A second embodiment of the present invention will be described below. For ease of explanation, the same reference numerals will be used to designate components having the same functions as those described in the first embodiment, and the description thereof will not be repeated.

[0051] In the second embodiment of the present invention, we will explain the measurement of reinforcing bars when the reinforcing bars to be measured have a two-layer structure. The layer here refers to the outer layer or the inner layer, with the outer layer being the first layer and the inner layer being the second layer.

[0052] FIG. 9 is a diagram showing an image of the end 21 of column reinforcement 201 photographed from diagonally above using the image measurement device 100 according to this embodiment. FIG. 9 shows an image of the end 21 of column reinforcement 201 arranged in two layers. Compared to FIG. 3, reinforcing bars have been added to the inside of the outer face of the column reinforcement 201. Of the column reinforcement 201, the main reinforcement 20 on the outside of the frame 500 is considered to be the first layer, and the main reinforcement 20 on the inside of the frame 500 is considered to be the second layer. Reinforcing bar measurement results can also be obtained from such an image of the end 21 of the main reinforcement 20 using the method described in embodiment 1. Note that the frame 500 is set for convenience of explanation and is unrelated to the present invention itself and is not a constituent element of the present invention.

[0053] The image measurement device 100 receives a user's specification of a fore-edge area 301 in the image shown in Figure 9, calculates the three-dimensional coordinates of the fore-edge area 301 specified by the user, calculates a fore-edge plane 302 based on the calculated three-dimensional coordinates, and extracts a point cloud around the fore-edge plane 302.

[0054] Fig. 10 is a diagram showing a point cloud near the edge plane 302 extracted from Fig. 9. The image measurement device 100 projects the point cloud shown in Fig. 10 onto the edge plane 302, detects a circular shape on the edge plane 302 to detect the edge 21, and performs measurement processing of the reinforcing bars based on the detected edge 21. In other words, by using a method similar to that of the first embodiment, it is possible to detect the second layer edge (additional edge) 21 present inside the column reinforcement 201.

[0055] Here, in a method in which the user specifies the edge area 301 at the corner of a rectangular reinforcement and only the point cloud around the line segment connecting the positions of the set corners is used as the feature point, the detection range of the feature points is limited, so it is not possible to simultaneously detect the edge 21 that exists on the first and second layers of the column reinforcement 201.

[0056] Therefore, in a method in which only point clouds near line segments connecting the positions of corners of reinforcement are used as feature points, processing of the second layer is added after completing processing of the first layer of column reinforcement 201. In processing of the first layer, the image measurement device 100 accepts from the user a specification of a corner of reinforcement in the first layer of the fore edge area 301, and executes processing up to detecting the fore edge 21 as explained in the first embodiment.

[0057] After completing the processing of the first layer, the image measuring device 100 starts processing the second layer and receives from the user the specification of the corner of the reinforcement of the second layer for the edge area (additional edge area) 301. The additional edge area here is an area including the additional edge that is arranged in the second layer different from the first layer where the edge is arranged. However, in FIG. 9, the additional edge and additional edge area are the edge 21 and edge area 301, as in the first layer.

[0058] Next, the image measuring device 100 calculates the three-dimensional coordinates of multiple feature points present in the fore-edge region 301 of the second layer, calculates a three-dimensional fore-edge plane (additional fore-edge plane) 302 based on the three-dimensional coordinates, and detects the additional fore-edge from the point cloud present in the vicinity of the additional fore-edge plane. However, in Figure 9, the additional fore-edge plane is the fore-edge plane 302, just like in the first layer.

[0059] Then, the image measurement device 100 measures the column reinforcement 201 based on the detected ends and additional ends and outputs the measurement results. This makes it possible to execute the processing of the first and second layers by using only the point clouds around the line segments connecting the corner positions of the reinforcement as feature points.

[0060] Furthermore, in a method in which only the point cloud around the line segments connecting the positions of the corners of the reinforcement are used as feature points, it is sufficient to extract feature points from the area where the fore edges 21 are arranged, so calculation of the fore edge plane 302 can be performed simultaneously. For example, the image measurement device 100 accepts the designation of the fore edge area 301 of the first layer and then accepts the designation of the fore edge area 301 of the second layer, calculates the three-dimensional coordinates of the fore edge areas 301 of both layers, and calculates the fore edge plane 302 including the fore edge area 301 of the first layer and the fore edge area 301 of the second layer. On the other hand, the image measurement device 100 may process the first layer and the second layer completely separately.

[0061] The above explanation has been given for two layers of reinforcement, but the same processing can be applied to three or more layers of reinforcement as long as the image includes the edge 21 to be measured.

[0062] As explained above, it is possible to measure the number of rebars, their diameters, and spacing even in reinforcement consisting of multiple layers. In particular, by setting the edge area 301 for each layer at the corners of the reinforcement on each layer, it is possible to use only the point cloud around the line segments connecting the corners of the rectangular reinforcement as feature points, and measurement processing can be performed appropriately.

[0063] The image measuring device 100 may display the measured edge 21 in a different color, or may issue a warning that the edge has been measured when the user specifies it as the edge area 301. This makes it possible to prevent double measurements of rebars or erroneous specification of rebars in different layers.

[0064] [Embodiment 3] A third embodiment of the present invention will be described below. For ease of explanation, the same reference numerals will be used to designate components having the same functions as those described in the first and second embodiments, and the description thereof will not be repeated.

[0065] In the third embodiment of the present invention, measurement of reinforcing bars when the heights of the ends 21 of the reinforcing bars to be measured are different will be described.

[0066] Fig. 11 is a diagram showing an image of the edge 21 of the column reinforcement 202 photographed from diagonally above using the image measurement device 100 according to this embodiment. Fig. 11 shows an image of the edge 21 photographed when there are two types of height of the main reinforcement 20 of the column reinforcement 202. When there are multiple edge planes 302 like this, by processing each edge plane 302, the edge 21 can be detected and measurement results can be obtained.

[0067] First, the image measuring device 100 receives from the user a designation of a fore-edge region 301 for the fore-edge 21 of the reinforcing bar located on the outside of the reinforcement (the side where the height of the main reinforcement 20 is higher). Next, the image measuring device 100 calculates the three-dimensional coordinates of the feature points present in the fore-edge region 301 for which the user designation has been received, and calculates the outer fore-edge plane (fore-edge plane) 3021 based on the calculated three-dimensional coordinates.

[0068] Fig. 12 is a diagram showing a point cloud within a predetermined range from the outer edge plane 3021 according to this embodiment. As shown in Fig. 12, the point cloud existing within a predetermined distance from the calculated outer edge plane 3021 corresponds to the edges 21 of the reinforcing bars located outside the reinforcement. The image measuring device 100 projects the point cloud onto the outer edge plane 3021 to detect the edges 21 of the reinforcing bars located outside the reinforcement, and measures the reinforcing bars.

[0069] Then, the image measuring device 100 receives from the user the specification of an edge region (additional edge region) 301 for the edge (additional edge) 21 of the reinforcing bar located on the inside of the reinforcement (the side where the height of the main reinforcement 20 is lower), as in the first embodiment. The additional edge region here is a region that includes additional edges of a different height from the edge. However, in FIG. 9, the additional edge and additional edge region are the edge 21 and edge region 301, as in the first layer.

[0070] Next, the image measurement device 100 calculates the three-dimensional coordinates of multiple feature points present in the user-specified fore-edge area 301, calculates an inner fore-edge plane (additional fore-edge plane) 3022, which is a three-dimensional plane, based on the three-dimensional coordinates, and detects the additional fore-edge from the point cloud present in the vicinity of the inner fore-edge plane 3022.

[0071] Then, the image measurement device 100 measures the column reinforcement 201 based on the detected end and additional end, and outputs the measurement results.

[0072] Fig. 13 is a diagram showing a point cloud within a predetermined range from the inner edge plane 3022 according to this embodiment. Fig. 14 is a diagram showing the result of projecting the point cloud onto the inner edge plane 3022.

[0073] 13, the point cloud existing within a predetermined distance from the calculated inner edge plane 3022 corresponds to the edge 21 of the reinforcing bar located inside the reinforcement. The image measuring device 100 projects the point cloud onto the inner edge plane 3022 to detect the edge 21 of the reinforcing bar located inside the reinforcement, and measures the reinforcing bar.

[0074] As shown in FIG. 13 , the point cloud within a predetermined distance from the inner edge plane 3022 includes a point cloud of the area of ​​the reinforcing bars located on the outside that is not the edge 21. Specifically, assume that the column reinforcement 202 includes tall reinforcing bars and short reinforcing bars. If the edge 21 of the tall reinforcing bar is near the outer edge plane 3021 and the edge 21 of the short reinforcing bar is near the inner edge plane 3022, the area near the inner edge plane 3022 will include not only the point cloud of the edge 21 of the low reinforcing bar but also the point cloud of the column portion of the tall reinforcing bar. The point cloud of the column portion of the tall reinforcing bar is within the range visible from the imaging position, and therefore becomes the point cloud of the half of the side surface on the side of the imaging units 101 and 102 (i.e., a semi-cylindrical point cloud). When these point clouds are projected onto the inner edge plane 3022, a semi-circular shape is formed, as shown in FIG. 14 , which can be excluded as not being the target edge.

[0075] As described above, it is possible to measure the number of rebars, the diameter of the rebars, and the spacing between the rebars even in a case where there are multiple end planes 302 with the end 21 in close proximity.

[0076] The image measuring device 100 may display the measured edge 21 in a different color, or may issue a warning that the edge has been measured when the user designates it as the edge area 301. This makes it possible to prevent the rebar from being measured twice.

[0077] [Software implementation example] The functions of the image measurement device 100 (hereinafter referred to as the "device") are realized by a program that causes a computer to function as the device, and by a program that causes a computer to function as each block of the device (particularly, the image processing unit 103).

[0078] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., a memory) as hardware for executing the program. The control device and storage device execute the program, thereby realizing the functions described in each of the above embodiments.

[0079] The program may be non-transitory and may be recorded on one or more computer-readable recording media. The recording media may or may not be included in the device. In the latter case, the program may be supplied to the device via any wired or wireless transmission medium.

[0080] Furthermore, some or all of the functions of the control blocks can be realized by logic circuits. For example, an integrated circuit in which a logic circuit that functions as each of the control blocks is formed is also included in the scope of the present invention. In addition, the functions of the control blocks can also be realized by, for example, a quantum computer.

[0081] Furthermore, each process described in each of the above embodiments may be executed by AI (Artificial Intelligence). In this case, the AI ​​may run on the control device or on another device (for example, an edge computer or a cloud server).

[0082] 〔summary〕 The image measuring device according to aspect 1 of the present invention is an image measuring device that measures column reinforcement using an image of the edge of the column reinforcement, and includes an acquisition unit that acquires the image of the edge, a reception unit that receives from a user a specification of an edge area that includes the edge in the image acquired by the acquisition unit, a detection unit that calculates three-dimensional coordinates of a plurality of feature points present in the edge area, calculates an edge plane that is a three-dimensional plane based on the three-dimensional coordinates, and detects the edge from a point cloud that exists in the vicinity of the edge plane, a measurement unit that measures the column reinforcement based on the detected edge, and an output unit that outputs the measurement results.

[0083] In the image measuring device according to aspect 2 of the present invention, in the above-mentioned aspect 1, the receiving unit may receive from the user a designation of the fore-edge region including the fore-edge located at a corner of the column reinforcement.

[0084] The image measuring device according to aspect 3 of the present invention is in the above-mentioned aspect 2, wherein the detection unit may extract the point cloud from the vicinity of a line segment connecting the fore-edge regions.

[0085] An image measuring device according to aspect 4 of the present invention may be configured such that, in aspect 1 above, the receiving unit receives from the user a specification of an additional edge area including an additional edge to be located on a layer different from the layer on which the edge is located, the detection unit calculates three-dimensional coordinates of a plurality of feature points present in the additional edge area, calculates an additional edge plane which is a three-dimensional plane based on the three-dimensional coordinates, and detects the additional edge from a point cloud present in the vicinity of the additional edge plane, the measurement unit measures the column reinforcement based on the edge and the additional edge, and the output unit outputs the measurement results.

[0086] An image measuring device according to aspect 5 of the present invention may be configured such that, in aspect 1 above, the receiving unit receives from the user a specification of an additional edge area including an additional edge of a different height from the edge, the detection unit calculates three-dimensional coordinates of a plurality of feature points present in the additional edge area, calculates an additional edge plane which is a three-dimensional plane based on the three-dimensional coordinates, detects the additional edge from a point cloud present in the vicinity of the additional edge plane, the measurement unit measures the column reinforcement based on the edge and the additional edge, and the output unit outputs the measurement results.

[0087] The image measurement method according to aspect 6 of the present invention is an image measurement method for measuring column reinforcement using an image of a fore edge of the column reinforcement, and includes: an acquisition step for acquiring an image of the fore edge; a reception step for receiving from a user specification of a fore edge area that is an area including the fore edge in the image acquired in the acquisition step; a detection step for calculating three-dimensional coordinates of a plurality of feature points present in the fore edge area, calculating a fore edge plane that is a three-dimensional plane based on the three-dimensional coordinates, and detecting the fore edge from a point cloud present in the vicinity of the fore edge plane; a measurement step for measuring the column reinforcement based on the detected fore edge; and an output step for outputting the measurement results.

[0088] The image measuring device 100 according to each aspect of the present invention may be realized by a computer. In this case, the control program for the image measuring device 100, which causes the computer to operate as each part (software element) of the image measuring device, thereby realizing the image measuring device 100 on the computer, and the computer-readable recording medium on which the program is recorded, also fall within the scope of the present invention.

[0089] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. Furthermore, new technical features can be created by combining the technical means disclosed in each embodiment. For example, column reinforcement includes concepts such as beams and bridges. [Explanation of symbols]

[0090] 21 Small lot (additional small lot) 100 Image measurement device 101 Imaging unit 102 Imaging unit 103 Image processing unit (acquisition unit, reception unit, detection unit, measurement unit, output unit) 104 Display section 105 Input section 106 Storage section 200, 201, 202 Column reinforcement 301 Fore-edge area (additional fore-edge area) 302 Edge plane (additional edge plane) 3021 Outer edge plane (edge ​​plane) 3022 Inner edge plane (additional edge plane)

Claims

1. An image measurement device that measures column reinforcement using an image of the edge of the column reinforcement, an acquisition unit that acquires an image of the edge; a receiving unit that receives, from a user, designation of a fore-edge region including the fore-edge in the image acquired by the acquiring unit; a detection unit that calculates three-dimensional coordinates of a plurality of feature points present in the fore-edge area, calculates a fore-edge plane that is a three-dimensional plane based on the three-dimensional coordinates, and detects the fore-edge from a point cloud that exists in the vicinity of the fore-edge plane; a measuring unit that measures the column reinforcement based on the detected end; an output unit that outputs the measurement results; An image measurement device comprising:

2. The reception unit Accepting designation of the edge region including the edge located at the corner of the column reinforcement from the user 2. The image measurement device according to claim 1.

3. The detection unit The point cloud is extracted from the vicinity of the line segment connecting the fore-edge regions.

3. The image measuring device according to claim 2.

4. The reception unit receiving, from the user, a designation of an additional edge area including an additional edge to be disposed on a layer different from the layer on which the edge is disposed; The detection unit calculating three-dimensional coordinates of a plurality of feature points present in the additional fore-edge area, calculating an additional fore-edge plane, which is a three-dimensional plane, based on the three-dimensional coordinates, and detecting the additional fore-edge from a point cloud present in the vicinity of the additional fore-edge plane; The measurement unit Measure the column reinforcement based on the end and the additional end, The output unit Output the measurement results 2. The image measurement device according to claim 1.

5. The reception unit receiving, from the user, a designation of an additional edge region including an additional edge having a height different from that of the edge; The detection unit calculating three-dimensional coordinates of a plurality of feature points present in the additional fore-edge area, calculating an additional fore-edge plane, which is a three-dimensional plane, based on the three-dimensional coordinates, and detecting the additional fore-edge from a point cloud present in the vicinity of the additional fore-edge plane; The measurement unit Measure the column reinforcement based on the end and the additional end, The output unit Output the measurement results 2. The image measurement device according to claim 1.

6. An image measurement method for measuring column reinforcement using an image of a column reinforcement edge, an acquisition step of acquiring an image of the edge; a receiving step of receiving, from a user, designation of a fore-edge region that is a region including the fore-edge in the image acquired in the acquiring step; a detection step of calculating three-dimensional coordinates of a plurality of feature points present in the fore-edge area, calculating a fore-edge plane, which is a three-dimensional plane, based on the three-dimensional coordinates, and detecting the fore-edge from a group of points present in the vicinity of the fore-edge plane; a measuring step of measuring the column reinforcement based on the detected end; an output step of outputting the measurement result; An image measurement method comprising:

7. 2. An image measurement program for causing a computer to function as the image measurement device according to claim 1, the image measurement program causing a computer to function as the acquisition unit, the acceptance unit, the detection unit, the measurement unit, and the output unit.

Images