Measurement system, measurement method and measurement program

Abstract

To provide a measurement system capable of accurately positioning a point group without a characteristic structure, a measurement method, and a measurement program.SOLUTION: A measurement system comprises an extraction unit and a positioning unit. The extraction unit extracts a point group of a first marker arranged in a known position with respect to an object to be measured from a measurement point group including a point group to be measured and the point group of the first marker. The positioning unit positions the point group to be measured and a known point group related to the object to be measured by positioning of the point group of the first marker and a point group of a second marker associated with the known position with respect to the known point group.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The embodiments relate to a measurement system, a measurement method, and a measurement program. [Background technology]

[0002] Conventionally, the alignment of two point clouds is performed by deriving point cloud correspondence information that indicates which points in one point cloud correspond to which points in the other point cloud, and by deriving geometric transformation information between the two point clouds. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-101987 Summary of the Invention [Problem to be solved by the invention]

[0004] If two point clouds have a distinctive structure, accurate alignment can be achieved by comparing the feature quantities between the two point clouds. On the other hand, if the two point clouds have few distinctive structures, the accuracy of alignment of the two point clouds is likely to decrease. For example, if the positions and orientations of the two point clouds are different and the shapes of the point clouds are symmetrical, matching the points that are closest to each other is likely to result in erroneous geometric transformation information.

[0005] The embodiments provide a measurement system, a measurement method, and a measurement program that can perform accurate alignment even for point clouds that do not have a distinctive structure. [Means for solving the problem]

[0006] The measurement system according to one aspect includes an extraction unit and a registration unit. The extraction unit is arranged at a known position relative to the point cloud of the measurement object and the measurement object. Plane markerThe point cloud of the first marker is extracted from the measurement point cloud including the point cloud of the first marker. The alignment unit aligns the point cloud of the first marker with a known position associated with the known point cloud related to the measurement object. Plane marker By aligning the point cloud of the second marker with the point cloud, the point cloud of the measurement target and the known point cloud are aligned. The extraction unit includes a first extraction unit that extracts a first point cloud having a color or brightness similar to that of the first marker from the measurement point cloud, a clustering unit that clusters the first point cloud, and a second extraction unit that extracts a second point cloud having a size corresponding to the size of the first marker from the clustered first point cloud as a point cloud of the first marker based on information on the size of the first marker. The alignment unit multilayers the point cloud of the second marker by duplicating the point cloud of the second marker along a normal direction of a plane of the second marker, and aligns the second point cloud with the multilayered point cloud of the second marker. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a block diagram showing an example of a configuration of a measurement system according to an embodiment. [Figure 2] FIG. 2 is a diagram showing a measurement marker. [Figure 3] FIG. 3 is a diagram showing the relationship between the known point cloud data and the point cloud data of the known markers. [Figure 4] FIG. 4 is a diagram illustrating an example of a hardware configuration of the measurement system. [Figure 5] FIG. 5 is a flowchart showing the operation of the measurement system. [Figure 6] FIG. 6 is a diagram illustrating clustering. [Figure 7] FIG. 7 is a diagram showing multi-layering of point cloud data of known markers. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, an embodiment will be described with reference to the drawings. FIG. 1 is a block diagram showing an example of the configuration of a measurement system according to an embodiment. The measurement system 1 shown in FIG. 1 can be used for measurement in a parts assembly system. The measurement target of the measurement system 1 is, for example, a part p placed on an assembly base plate B. The measurement system 1 in the embodiment compares the point cloud of the part p measured by the camera 2 with a known point cloud related to the part p that has been prepared in advance, and presents the comparison result to a user. The user is, for example, a worker who checks whether the assembly of the part p has been performed correctly.

[0009] The base plate B is a flat plate equipped with, for example, a holding portion for holding the component p at a predetermined position. A measurement marker M1 is disposed on the base plate B. The measurement marker M1 is a marker of a known size that is disposed at a predetermined position on the base plate B in a predetermined orientation. Information about the size of the measurement marker M1 may include, for example, information such as the length of each side and the length of the diagonal of the measurement marker M1. Here, in the embodiment, the component p is placed on the base plate B so that the positional relationship between the component p and the measurement marker M1 is a predetermined known positional relationship. In FIG. 1 , the horizontal distance x1 and the vertical distance y1 between the component p and the measurement marker M1 on the plane of the base plate B are on the plane of the base plate B. The base plate B may be a workbench on which the assembly work of the component p is performed. The base plate B may also be a circuit board on which an electronic circuit is mounted.

[0010] The measurement marker M1 is, for example, an AR (Augmented Reality) marker, and can be recognized from an image acquired by the camera 2. The measurement marker M1 is, for example, a rectangular, planar marker having a black and white pattern. FIG. 2 is a diagram showing the measurement marker M1. As shown in FIG. 2, it is desirable that the measurement marker M1 has an asymmetric pattern in the left-right and up-down directions. By having the measurement marker M1 have an asymmetric pattern, the orientation of the measurement marker M1 in the image can be recognized. Note that two or more measurement markers M1 may be arranged on the base plate B. Furthermore, the shape of the measurement marker M1 does not have to be rectangular.

[0011] As shown in FIG. 1, the measurement system 1 includes a first extraction unit 11, a plane detection unit 12, a clustering unit 13, a second extraction unit 14, an alignment unit 15, a shape database (DB) 16, and a display control unit 17. The measurement system 1 is configured to be able to communicate with a camera 2. The communication between the measurement system 1 and the camera 2 may be wireless or wired. The measurement system 1 is also configured to be able to communicate with a display device 3. The communication between the measurement system 1 and the display device 3 may be wireless or wired. Here, in FIG. 1, the first extraction unit 11, the plane detection unit 12, the clustering unit 13, and the second extraction unit 14 constitute an extraction unit for extracting a point cloud of a measurement marker M1.

[0012] The camera 2 is a camera that is held by, for example, a user and configured to measure measurement point cloud data including a point cloud of the part p that is the measurement target and the measurement marker M1, along with images of the part p that is the measurement target and the measurement marker M1. The camera 2 may be a depth camera or a 3D scanner. For example, an RGB-D camera may be used as the camera 2. The RGB-D camera is a camera configured to measure an RGB-D image. The RGB-D image includes a depth image and a color image (RGB color image). The depth image is an image that has the depth of each point of the measurement target as a pixel value. The color image is an image that has the RGB value of each point of the measurement target as a pixel value.

[0013] The display device 3 is a display device such as a liquid crystal display or an organic EL display, and displays various images based on the data transferred from the measurement system 1.

[0014] The first extraction unit 11 extracts point cloud data having a color similar to that of the measurement marker M1 from the measurement point cloud data measured by the camera 2. For example, if the measurement marker M1 is a marker having a black and white pattern, the first extraction unit 11 compares the RGB values ​​of each pixel in the color image measured by the camera 2 with an upper limit value corresponding to black, and identifies pixels whose RGB values ​​are equal to or less than the upper limit value as black pixels. Then, the first extraction unit 11 extracts point cloud data corresponding to the black pixels from the measurement point cloud data.

[0015] The plane detection unit 12 detects a plane spanned by the point cloud data extracted by the first extraction unit 11, and extracts point cloud data on the plane from the point cloud data extracted by the first extraction unit 11. The plane detection can be performed using, for example, RANSAC (Random Sample Consensus) Plate Fitting. RANSAC Plate Fitting uses RANSAC, which removes outliers based on a fundamental matrix calculated from points randomly sampled from the point cloud data. RANSAC Plate Fitting uses RANSAC to group each point of the point cloud data into two segments, an inlier set and an outlier set, and thereby detects a plane spanned by points belonging to the inlier set. The plane detection may be performed using any method other than RANSAC Plate Fitting, such as a method using a Hough transform. The point cloud data extracted by the first extraction unit 11 is narrowed down to point cloud data on the plane through plane detection.

[0016] The clustering unit 13 clusters the point cloud data on the plane detected by the plane detection unit 12. Clustering is performed using, for example, DBSCAN (Density-based spatial clustering of applications with noise). DBSCAN is a method of clustering point cloud data by repeatedly changing the evaluation point, determining that the evaluation point and the neighboring points belong to the same cluster if the number of points neighboring the evaluation point in the point cloud data exceeds a certain number, and determining that the evaluation point and the neighboring points do not belong to the same cluster if the number does not exceed the certain number. As in the embodiment, if the point cloud data of the part p and the point cloud data of the measurement marker M1 are separated from each other, there is a high possibility that the individual point cloud data of the measurement marker M1 belong to the same cluster. Clustering may be performed using any method other than DBSCAN, such as k-means.

[0017] The second extraction unit 14 extracts point cloud data of the measurement marker M1 from the clusters obtained by the clustering unit 13. If the size of the measurement marker M1 is known, the point cloud data of the measurement marker M1 can be identified, for example, from the length of the diagonal of the bounding box of the point cloud. The bounding box of the point cloud is an area formed by the boundaries of each cluster. In other words, the second extraction unit 14 extracts, as the point cloud data of the measurement marker M1, point cloud data belonging to a cluster whose diagonal length of the bounding box of the point cloud is closest to the length of the diagonal of the measurement marker M1. The point cloud data of the measurement marker M1 may be extracted based not only on the diagonal but also on the length of the side of the bounding box, etc.

[0018] The alignment unit 15 aligns the point cloud data of the measurement target with the known point cloud data stored in the shape DB 16 by aligning the point cloud data of the measurement marker M1 extracted by the second extraction unit 14 with the point cloud data of the known marker M2 stored in the shape DB 16. The alignment can be performed using an ICP (Iterative Closest Point) method, a BCPD (Bayesian Coherent Point Drift) method, or the like.

[0019] The shape DB 16 stores known point cloud data of the measurement target. The known point cloud data may be design drawing data of the measurement target part p created by 3D CAD (Computer Aided Design), etc. The known point cloud data is not limited to design drawing data, and may be any point cloud data or data that can be converted into point cloud data.

[0020] The shape DB 16 also stores point cloud data of the known marker M2 together with the known point cloud data. The point cloud data of the known marker M2 is point cloud data of a marker having the same black and white pattern as the measurement marker M1, and is associated with a predetermined position and a predetermined orientation with respect to the known point cloud data. If two or more measurement markers M1 are arranged on the base plate B, point cloud data of two or more known markers M2 may be prepared.

[0021] FIG. 3 is a diagram showing the relationship between the known point cloud data and the point cloud data of the known marker M2. In this embodiment, the known point cloud data d of the part p and the point cloud data of the known marker M2 are assumed to be arranged in a predetermined orientation on the same virtual plane. Data representing the positional relationship between the known point cloud data d and the point cloud data of the known marker M2 on the virtual plane is associated with the known point cloud data d and the point cloud data of the known marker M2. The data representing the positional relationship includes data on the horizontal distance x2 and the vertical distance y2 on the virtual plane on which the known point cloud data d of the part p and the point cloud data of the known marker M2 are arranged. Here, the horizontal distance x2 is k1 (k1 is a positive real number) times the horizontal distance x1, and the vertical distance y2 is k2 (k2 is a positive real number) times the vertical distance y1. k1 and k2 may or may not be equal. In other words, the positional relationship between the part p to be measured and the measurement marker M1 may differ from the positional relationship between the known point cloud data d and the known marker M2.

[0022] Furthermore, the number of points in the known point cloud data does not need to be the same as the number of points in the point cloud data of the measurement target. On the other hand, it is desirable that the number of points in the point cloud data of the known marker M2 be the same as the number of points in the point cloud data of the measurement marker M1. In other words, the densities of the known point cloud data and the point cloud data of the measurement target may be different, but it is desirable that the densities of the point cloud data of the known marker M2 and the point cloud data of the measurement marker M1 are the same. This is because, as will be explained in detail later, in this embodiment, the measurement point cloud data and the known point cloud data are aligned by aligning the measurement marker M1 and the known marker M2. To achieve accurate alignment between the measurement marker M1 and the known marker M2, it is desirable that the number of points in both markers be the same.

[0023] The known point cloud data and the point cloud data of the known markers may be configured as separate point cloud data. Even in this case, the horizontal distance x2 and the vertical distance y2 that represent the positional relationship between the known point cloud data and the point cloud data of the known markers are specified. Of course, the known point cloud data and the point cloud data of the known markers may be configured as a single point cloud data.

[0024] Furthermore, the shape DB 16 may be provided outside the measurement system 1. In this case, the alignment unit 15 of the measurement system 1 acquires information from the shape DB 16 as necessary.

[0025] The display control unit 17 displays information related to the alignment result by the alignment unit 15 on the display device 3. The information related to the shape comparison result is, for example, an image in which an image based on a point cloud measured by the camera 2 is superimposed with an image based on a known point cloud stored in the shape DB 16. The superimposition of the images can be performed by moving one image onto the other image based on geometric transformation information obtained by the alignment in the alignment unit 15.

[0026] Fig. 4 is a diagram showing an example of the hardware configuration of the measurement system 1. The measurement system 1 can be various types of terminal devices such as a personal computer (PC) or a tablet terminal. As shown in Fig. 2, the measurement system 1 has a processor 101, a ROM 102, a RAM 103, a storage 104, an input interface 105, and a communication device 106 as hardware.

[0027] The processor 101 controls the overall operation of the measurement system 1. The processor 101 operates as a first extraction unit 11, a plane detection unit 12, a clustering unit 13, a second extraction unit 14, an alignment unit 15, and a display control unit 17 by executing a program stored in the storage 104, for example. The processor 101 is, for example, a central processing unit (CPU). The processor 101 may be a micro-processing unit (MPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or the like. The processor 101 may be a single CPU or the like, or multiple CPUs or the like.

[0028] The ROM (Read Only Memory) 102 is a non-volatile memory. The ROM 102 stores a startup program and the like for the measurement system 1. The RAM (Random Access Memory) 103 is a volatile memory. The RAM 103 is used as a working memory for processing in the processor 101, for example.

[0029] The storage 104 is, for example, a storage such as a hard disk drive or a solid state drive. The storage 104 stores various programs executed by the processor 101, such as a measurement program. The storage 104 may also store a shape DB 16. The shape DB 16 does not necessarily have to be stored in the storage 104.

[0030] The input interface 105 includes input devices such as a touch panel, a keyboard, a mouse, etc. When an input device of the input interface 105 is operated, a signal corresponding to the operation content is input to the processor 101. The processor 101 performs various processes according to this signal.

[0031] The communication device 106 is a communication device that enables the measurement system 1 to communicate with external devices such as the camera 2 and the display device 3. The communication device 106 may be a communication device for wired communication or a communication device for wireless communication.

[0032] Next, a description will be given of the operation of the measurement system 1. Fig. 5 is a flowchart showing the operation of the measurement system 1. The processing of Fig. 5 is executed by the processor 101.

[0033] In step S1, the processor 101 acquires measurement point cloud data including point cloud data of the part p to be measured and the measurement marker M1 from the camera 2. Here, when the camera 2 measures the measurement point cloud data, the measurement is performed so that both the part p to be measured and the measurement marker M1 are within the field of view of the camera 2.

[0034] In step S2, the processor 101 extracts, for example, black measurement point cloud data from the measurement point cloud data acquired from the camera 2. If the part p does not include black parts and the measurement marker M1 is a marker with a black and white pattern, only the point cloud data of the measurement marker M1 is extracted by this processing. However, if the part p includes black parts or low-brightness parts that are considered to be black parts, the point cloud data of the black parts or low-brightness parts of the part p may also be extracted. The following processing is performed taking into account the case where the part p includes black or low-brightness parts.

[0035] In step S3, the processor 101 detects a plane spanned by the extracted point cloud and extracts point cloud data on the plane. The plane is detected to take into account the tilt of the point cloud data due to, for example, the shooting orientation of the camera 2. The subsequent processing is performed on the point cloud data on the extracted plane.

[0036] In step S4, the processor 101 clusters the point cloud data on each of the detected planes. As a result of the clustering, the black measurement point cloud data extracted in step S2 is divided into a plurality of clusters C1, C2, ..., Cn (n = 13 in FIG. 6) as shown in FIG. 6. In FIG. 6, for example, cluster C10 is the cluster of point cloud data of measurement marker M1. Note that FIG. 6 shows the result of clustering for point cloud data on one plane. In practice, clustering is performed on the point cloud data on each of the planes detected in step S3.

[0037] In step S5, the processor 101 extracts the point cloud data of the measurement marker M1 from the size of the bounding box of each point cloud data. For example, point cloud data whose bounding box shape is the same as the shape of the measurement marker M1 and whose diagonal length is closest to the diagonal length of the measurement marker M1 is extracted as the point cloud data of the measurement marker M1. It is also assumed that a part whose bounding box shape is the same as the marker M1 will be placed on the base plate B. Taking this into consideration, the diagonal length of the measurement marker M1 needs to be different from the diagonal lengths of any parts that are expected to be placed on the base plate B. By making the diagonal length of the measurement marker M1 different from the diagonal lengths of the respective parts, only the point cloud data of the measurement marker M1 can be correctly extracted.

[0038] In step S6, the processor 101 virtually multi-layers the point cloud data of the known marker M2 stored in the shape DB 16. The multi-layering is performed, for example, by generating multiple pieces of duplicate point cloud data M21 and M22 of the point cloud data of the known marker M2 at positions moved a certain distance along a normal direction based on the surface of the point cloud data of the original known marker M2 stored in the shape DB 16, as shown in Fig. 7. Here, the number of duplicate point cloud data is not limited to two. In other words, three or more point cloud data may be generated.

[0039] In step S7, the processor 101 aligns the point cloud data of the part p with the known point cloud data by aligning the point cloud data of the measurement marker M1 extracted in step S5 with the point cloud data of the known marker M2 layered in step S6. The measurement point cloud data may be rotated around the normal direction due to factors such as the tilt of the camera 2 when capturing the image. The measurement point cloud data may also be tilted due to factors such as the tilt of the camera 2 when capturing the image. In these cases, simply aligning the point cloud data of the measurement marker M1 with the point cloud data of the known marker M2 may result in insufficient information in the three-dimensional direction, resulting in inaccurate alignment. As shown in FIG. 7, aligning the point cloud data of the layered known marker M2 with the point cloud data of the measurement marker M1 can compensate for the lack of information in the three-dimensional direction during alignment. Therefore, the point cloud data of the measurement marker M1 and the point cloud data of the known marker M2 are correctly aligned. Here, the positional relationship between the measurement marker M1 and the part p to be measured and the positional relationship between the point cloud data of the known marker M2 and the known point cloud data are specified in advance. Therefore, by aligning the point cloud data of the measurement marker M1 with the point cloud data of the known marker M2, the point cloud data of the part p and the known point cloud data are also correctly aligned. Note that if the positional relationship between the measurement target part p and the measurement marker M1 and the positional relationship between the known point cloud data d and the known marker M2 differ, the point cloud data of the part p is aligned with the known point cloud data in accordance with the difference in positional relationship.

[0040] In step S8, the processor 101 displays on the display device 3 a three-dimensional image of the measurement target based on the measurement point cloud data measured by the camera 2 and a three-dimensional image of the measurement target based on the known point cloud data, superimposed on each other. Thereafter, the processor 101 ends the processing of Fig. 5. When superimposing the images, differences between the measurement point cloud data and the known point cloud data may be emphasized. The emphasis may be performed by any method, such as changing the color of the differences or changing the density of the differences.

[0041] As described above, according to the embodiment, a measurement marker M1 is provided at a known position from the measurement object, and a point cloud of known markers M2 is provided at a known position from the known point cloud related to the measurement object. Then, the point cloud data of the measurement object and the known point cloud data are aligned by aligning the point cloud data of the measurement marker M1 extracted from the measurement point cloud data with the point cloud data of the known marker M2. In other words, feature information of the measurement object is not used to align the point cloud data of the measurement object with the known point cloud data. Therefore, accurate alignment can be achieved even if the measurement object does not have a distinctive structure.

[0042] Furthermore, according to the embodiment, in order to extract the point cloud data of the measurement marker M1 from the measurement point cloud data, extraction of point cloud data of a color similar to that of the measurement marker M1, plane detection, clustering, and extraction of point cloud data based on the size of the diagonal of the bounding box are performed. This allows only the point cloud data of the measurement marker M1 to be correctly extracted. Therefore, in the embodiment, even if the performance of the camera 2 does not allow an image of the measurement marker M1 with sufficient resolution to be obtained, the point cloud data of the measurement marker M1 can be accurately extracted.

[0043] Furthermore, during alignment, the point cloud data of the known markers M2 is multi-layered, which allows for accurate alignment including three-dimensional orientation.

[0044] [Variations] A modified example will be described. In the embodiment, the measurement system 1 is used for measurement in a parts assembly system. However, the measurement system according to the embodiment can be applied to any measurement system.

[0045] In the embodiment, the camera 2 may be configured integrally with the measurement system 1. In this case, the position and orientation of the camera 2 may be controlled by the measurement system 1.

[0046] In the embodiment, the measurement marker M1 is a marker with a black and white pattern. However, the measurement marker M1 does not necessarily have to be a marker with a black and white pattern. For example, the measurement marker M1 may be a marker with a predetermined color pattern. In this case, the first extraction unit 11 compares the RGB values ​​of each pixel in the color image measured by the camera 2 with upper and lower limit values ​​corresponding to the color of the marker M1, thereby identifying pixels whose RGB values ​​are in a range greater than or equal to the lower limit value and less than or equal to the upper limit value. Then, the first extraction unit 11 extracts point cloud data corresponding to the identified pixels from the measurement point cloud data.

[0047] Furthermore, the measurement marker M1 may be a marker that is recognized by its brightness. For example, the measurement marker M1 may be a marker with a black and white pattern drawn with retroreflective paint. In this case, a LiDAR (Light Detecting and Ranging) camera may be used as the camera 2. The first extraction unit 11 extracts measurement point cloud data of the measurement marker M1 from the measurement point cloud data using information on the infrared brightness of the measurement target measured by the camera 2. Specifically, the first extraction unit 11 extracts point cloud data having a brightness value higher than a predetermined value. This is because high-brightness infrared light returns from a marker drawn with retroreflective paint due to retroreflection. Note that the measurement marker M1 drawn with retroreflective paint can also be measured with a camera other than a LiDAR camera, such as an RGB-D camera.

[0048] In the embodiment, it is assumed that the measurement target has a three-dimensional structure. On the other hand, when the measurement target is a plane, for example, and three-dimensional information is not required for alignment, processes such as plane detection and multi-layering of point cloud data of known markers M2 may be omitted.

[0049] Although several embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, and are also included in the scope of the invention and its equivalents as defined in the claims. [Explanation of symbols]

[0050] 1 Measurement system, 2 Camera, 3 Display device, 11 First extraction unit, 12 Plane detection unit, 13 Clustering unit, 14 Second extraction unit, 15 Alignment unit, 16 Shape database (DB), 17 Display control unit, 101 Processor, 102 ROM, 103 RAM, 104 Storage, 105 Input interface, 106 Communication device.

Claims

1. an extracting unit that extracts a point cloud of a first marker from a measurement point cloud that includes a point cloud of a measurement object and a point cloud of a first marker that is a planar marker arranged at a known position with respect to the measurement object; an alignment unit that aligns the point cloud of the measurement object with the known point cloud by aligning the point cloud of the first marker with the point cloud of a second marker, the second marker being a planar marker associated with a known position with respect to the known point cloud related to the measurement object; Equipped with The extraction unit a first extraction unit that extracts a first point cloud having a color or brightness similar to that of the first marker from the measurement point cloud; a clustering unit that clusters the first point cloud; a second extraction unit that extracts, based on size information of the first marker, a second point cloud having a size corresponding to the size of the first marker from the clustered first point cloud as a point cloud of the first marker; and The alignment unit is The point cloud of the second marker is multi-layered by duplicating the point cloud of the second marker along a normal direction of a plane of the second marker; aligning the second point cloud with the multilayered point cloud of the second marker; Measurement system.

2. further comprising a plane detection unit that detects at least one plane corresponding to the first point cloud; The measurement system according to claim 1 , wherein the clustering unit clusters the first point cloud on each of the planes.

3. The measurement system according to claim 1 , wherein the size information is a length of a diagonal of the first marker.

4. The measurement system according to claim 1 , wherein the first marker is a marker drawn with retroreflective paint.

5. extracting a point cloud of the first marker from a measurement point cloud including a point cloud of a measurement object and a point cloud of a first marker which is a planar marker arranged at a known position with respect to the measurement object; aligning the point cloud of the measurement object with the known point cloud by aligning the point cloud of the first marker with the point cloud of a second marker, which is a planar marker associated with a known position with respect to the known point cloud of the measurement object; Equipped with The extracting step comprises: extracting a first point cloud having a color or brightness similar to that of the first marker from the measurement point cloud; clustering the first point cloud; extracting, from the clustered first point cloud, a second point cloud having a size corresponding to the size of the first marker as a point cloud of the first marker, based on information about the size of the first marker; Including, The aligning step comprises: multi-layering the point cloud of the second marker by duplicating the point cloud of the second marker along a normal direction of a plane of the second marker; Aligning the second point cloud with the multilayered point cloud of the second marker; Including, Measurement method.

6. extracting a point cloud of the first marker from a measurement point cloud including a point cloud of a measurement object and a point cloud of a first marker which is a planar marker arranged at a known position with respect to the measurement object; aligning the point cloud of the measurement object with the known point cloud by aligning the point cloud of the first marker with the point cloud of a second marker, which is a planar marker associated with a known position with respect to the known point cloud of the measurement object; A measurement program for causing a computer to execute the above, The extracting step comprises: extracting a first point cloud having a color or brightness similar to that of the first marker from the measurement point cloud; clustering the first point cloud; extracting, from the clustered first point cloud, a second point cloud having a size corresponding to the size of the first marker as a point cloud of the first marker, based on information about the size of the first marker; causing the computer to execute The aligning step comprises: multi-layering the point cloud of the second marker by duplicating the point cloud of the second marker along a normal direction of a plane of the second marker; Aligning the second point cloud with the multilayered point cloud of the second marker; causing the computer to execute Measurement program.

Images