Three-dimensional model creation support system, program and recording medium

Abstract

To efficiently generate a three-dimensional model of a plant while reducing operations for adding or correcting a piping model and additionally generating a valve / device model.SOLUTION: A three-dimensional model generation support system includes: a piping center line generation apparatus which generates piping center line information indicating a piping center line from three-dimensional image data of a plant; a piping model generation apparatus which generates a piping model using the piping center line information; a valve / device recognition apparatus which recognizes a valve and a device from two-dimensional image data of the plant or the three-dimensional image data; and a valve / device CAD model arrangement apparatus which arranges a valve model and a device model in the piping model generated by the piping model generation apparatus.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a three-dimensional model creation support system, a program, and a recording medium. [Background technology]

[0002] In recent years, power plants and chemical plants have been managing their assets using three-dimensional computer-aided design (3D-CAD).

[0003] However, some of these plants are old, do not have 3D CAD models, and asset management is still carried out using paper documents.

[0004] In recent years, services have become common that use laser measurement to obtain three-dimensional point cloud data and use that data to create 3D models of plants. Note that in the following, three dimensions may be referred to as "3D" and two dimensions as "2D."

[0005] Current laser measurement devices are capable of acquiring highly accurate 3D point cloud data. Devices have also been developed that can acquire color information using a camera at the same time as acquiring coordinate data. This makes it possible to display colored 3D point cloud data. This makes it easier for the human eye to identify pipes, equipment, etc.

[0006] However, these point cloud data are not 3D models with attributes. Therefore, in order to use the point cloud data for asset management using tag information of equipment and piping, it is necessary to convert the point cloud data into a 3D model with attributes.

[0007] The general method for converting such data into a 3D model is for an operator to convert the data into a 3D model manually while displaying the point cloud data on a screen, which requires a great deal of effort.

[0008] On the other hand, in recent years, there is technology that uses software to recognize the shapes of pipes and other objects from point cloud data and convert them into attribute-free 3D models. In addition, technology has been developed to automatically assign attributes to attribute-free 3D models.

[0009] For example, Patent Document 1 discloses a layout design support device that compares end point connection information of logical connection data, which is a logical connection relationship between plant equipment, with end point connection information of geometric shape data, which is graphic shape information in three-dimensional space, and automatically generates a logical connection-geometric shape correspondence table composed of correspondence relationship data that associates logical connection data and geometric shape data whose end point connection information matches. [Prior art documents] [Patent documents]

[0010] [Patent Document 1] Patent No. 4940267 Summary of the Invention [Problem to be solved by the invention]

[0011] Conventional technology for converting point cloud data into 3D models is only capable of handling relatively simple shapes such as pipes and steel materials.

[0012] In addition, in Patent Document 1, it is difficult to convert all devices such as valves into 3D models. In addition, it is difficult to convert all piping into 3D models accurately, so it is necessary to correct the created piping model and to create additional piping models that could not be created automatically.

[0013] An object of the present invention is to reduce the work of adding and modifying piping models and the work of creating additional valve / equipment models, and to efficiently create a three-dimensional model of a plant. [Means for solving the problem]

[0014] The three-dimensional model creation support system of the present invention includes a piping centerline creation device that creates piping centerline information representing a piping centerline from three-dimensional image data of a plant, a piping model creation device that creates a piping model using the piping centerline information, a valve / equipment recognition device that recognizes valves and equipment from two-dimensional image data or three-dimensional image data of the plant, and a valve / equipment CAD model placement device that places valve models and equipment models in the piping model created by the piping model creation device. Effect of the Invention

[0015] According to the present invention, the work of adding and correcting piping models and the work of creating additional valve / equipment models can be reduced, and a three-dimensional model of a plant can be created efficiently. [Brief description of the drawings]

[0016] [Figure 1] FIG. 1 is a configuration diagram illustrating an example of a three-dimensional model creation support system according to an embodiment. [Diagram 2] FIG. 2 is a diagram showing an example of the 2D / 3D image data of FIG. [Diagram 3] FIG. 1 is a flow diagram illustrating a method for creating a piping centerline. [Figure 4] FIG. 11 is a perspective view showing an example of a straight pipe model that is a created 3D-CAD model. [Diagram 5] FIG. 5 is a perspective view showing an example of a piping center line created from the straight pipe model of FIG. [Figure 6] FIG. 4 is a perspective view showing an example of a target region set in step S23 of FIG. [Figure 7] FIG. 7 is a perspective view showing an example in which an extended center line is added to the center line in FIG. 6. [Figure 8] FIG. 13 is a perspective view showing a state in which a virtual intersection is generated. [Figure 9] FIG. 13 is a perspective view showing piping center line information. [Figure 10] FIG. 13 is a diagram showing an example of output data of piping center line information. [Figure 11] FIG. 2 is a perspective view showing an example of a 3D piping model created by a piping model creation device. [Figure 12] FIG. 1 is a diagram showing an example of creating a 3D image from multiple 2D images. [Figure 13] FIG. 2 is a perspective view showing an area including a 3D image recognized as a valve. [Figure 14] FIG. 2 is a perspective view showing a state in which a valve is disposed in a pipe. [Figure 15] FIG. 2 is a perspective view showing an example of a created plant 3D model. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] A preferred embodiment of the present disclosure will now be described.

[0018] In the three-dimensional model creation support system, it is desirable for the piping centerline creation device to set a target area for creating piping centerline information, extend the centerline of the straight pipe model within the target area, determine a virtual intersection from the distance between the two centerlines obtained by extension, and create the piping centerline information from the end points of the piping centerline and the determined virtual intersection.

[0019] The valve / equipment recognition device creates three-dimensional image data from multiple two-dimensional image data, obtains a correspondence between the coordinates of the two-dimensional image data and the coordinates of the three-dimensional image data, and identifies the coordinates of the three-dimensional image data using the coordinates of the two-dimensional image data of the recognized valves and equipment and the correspondence. Valve / equipment CAD model placement device, It is desirable to place a valve model or equipment model selected from a model library at the coordinates of the identified three-dimensional image data.

[0020] It is desirable for the valve / equipment recognition device to accumulate two-dimensional or three-dimensional image data of valves and equipment through deep learning.

[0021] Hereinafter, the embodiments will be described with reference to the drawings. EXAMPLES

[0022] FIG. 1 is a configuration diagram showing an example of a three-dimensional model creation support system according to an embodiment.

[0023] As shown in this figure, the three-dimensional model creation support system includes a piping center line creation device 2, a piping model creation device 4, a valve / equipment recognition device 5, and a valve / equipment CAD model placement device 6. 2D / 3D image data 1 is used for predetermined processing by the piping center line creation device 2 and the valve / equipment recognition device 5. Pipe center line information 3 is created by the piping center line creation device 2 and is used for predetermined processing by the piping model creation device 4. The valve / equipment CAD model placement device 6 creates data regarding the placement of valves, equipment, etc., using data obtained by processing in the valve / equipment recognition device 5. A plant 3D model 7 is created using data obtained by the piping model creation device 4 and the valve / equipment CAD model placement device 6.

[0024] In the following, image data may be referred to simply as "image." Furthermore, "recognition" refers to identifying valves, equipment, etc., using numerical data such as two-dimensional or three-dimensional points, lines, and figures.

[0025] The above devices constituting the three-dimensional model creation support system may all be built into one computer device, or each device may be built into a separate computer device. Each of the above processes is implemented by processing a program recorded in one or more memories or other recording media built into the computer device by one or more central processing units (CPUs) built into the computer device. The program may also be recorded in a recording medium such as a memory stick that is detachable from the computer device. The program is for causing the computer device to execute a predetermined process. The recording medium is computer-readable and has the program recorded therein.

[0026] The 2D / 3D image data 1 is input and recorded in one or more recording media such as memories built into the computer device. The piping centerline information 3 created by a predetermined process from the 2D / 3D image data 1, the plant 3D model 7 finally created, and the like are recorded in one or more recording media such as memories built into the computer device. Note that input to the recording media may be performed via a communication means such as the Internet.

[0027] The 2D / 3D image data 1 includes a plurality of 2D images of a plant and a 3D image created from the 2D images.

[0028] The piping centerline creation device 2 is a device that recognizes piping in a 3D image of a plant and creates a line connecting the centers of the cross sections of the piping (hereinafter referred to as a "centerline" or "piping centerline"). The centerline is a line segment or a broken line that is not cut by valves installed in the middle of the piping and connects from one device that is an end point of the piping to another device that is an end point of the piping.

[0029] The piping centerline information 3 is information that represents a piping centerline, and is data expressed by the three-dimensional coordinates of the end points and vertices of the piping centerline.

[0030] The piping model creation device 4 creates a 3D-CAD model of the piping from the piping center line information 3 using an API (Application Programming Interface) of the 3D-CAD system.

[0031] The valve / equipment recognition device 5 recognizes valves and equipment from 2D or 3D images of the plant, and obtains position information of the recognized valves and equipment.

[0032] The valve / equipment CAD model placement device 6 places the valve model on the piping model using the API of the 3D-CAD system based on the valve position information acquired by the valve / equipment recognition device 5. Similarly, it also places the equipment model using the equipment position information.

[0033] The plant 3D model 7 is a 3D model including models of equipment, piping, and valves, and is the main model of the plant excluding structures such as piping supports that support the piping.

[0034] The details of each component and the operation of this embodiment will be described below.

[0035] FIG. 2 shows an example of the 2D / 3D image data 1 of FIG.

[0036] 2 shows three-dimensional point cloud data created from a plurality of images of a plant taken by a drone. In addition to the piping 11, images of a tank 12a, a pump 12b, and a valve 13 are included. The piping in the 3D image of such a plant is recognized by a piping centerline creation device 2 (FIG. 1), and a centerline (piping centerline) of the cross section of the piping is created. Then, a piping model creation device 4 creates a piping model using piping centerline information 3 obtained by the piping centerline creation device 2.

[0037] Here, a method for creating a piping centerline and creating a piping model will be described.

[0038] FIG. 3 is a flow diagram illustrating a method for creating a piping centerline.

[0039] As shown in the figure, first, in step S21, a straight pipe part is extracted from the entire image of the pipe by a CAD conversion tool, which is a program of the pipe center line creation device 2, and a straight pipe model is created. In addition to the straight pipe, parts such as bends may also be modeled. In this case, point cloud data constituting the image of the pipe is used.

[0040] In step S22, a center line is created for the created piping model of the straight pipe. Since the model of the straight pipe is a cylinder, the piping center line can be created by connecting the centers of the circles of the cross sections.

[0041] In step S23, a target region to which the center line is extended is set.

[0042] In step S24, the center line is extended to find a virtual intersection point (hereinafter referred to as a "virtual intersection point.") The center line is extended to both ends of the target area set in step S23.

[0043] In step S25, a piping model is created by connecting vertices using the virtual intersections obtained in step S24.

[0044] In step S26, it is determined whether or not the creation of the piping model has been completed for all regions. If there are regions for which the creation of the piping model has not been completed, the process returns to step S23, where the target region is set and the same process is repeated.

[0045] FIG. 4 is a perspective view showing an example of a straight pipe model, which is a 3D-CAD model created by the CAD conversion tool in step S21 of FIG.

[0046] In FIG. 4, a pipe 41, a branch pipe 42 connected to the pipe 41, and a pipe 43 perpendicular to the pipe 41 are each created as a straight pipe model.

[0047] Since the point cloud data created from images taken by a drone is less accurate than the point cloud data obtained by laser measurement, it is rare that all pipes are modeled correctly. For this reason, models cannot be generated for some pipes and they remain as point cloud data. Even if the pipes are modeled, there may be discrepancies in the connections of each pipe model.

[0048] FIG. 5 is a perspective view showing an example of a piping center line created from the straight pipe model of FIG.

[0049] This process is carried out in step S22 in FIG.

[0050] FIG. 5 shows center lines P1, P2, and P3 created from the straight pipe models of the pipe 41, the branch pipe 42, and the pipe 43 in FIG.

[0051] FIG. 6 shows an example of the target region set in step S23 of FIG.

[0052] In FIG. 6, the shape of the target region is a rectangular parallelepiped 60.

[0053] The setting method involves specifying two points A1 and A2, which are diagonal corners of the rectangular parallelepiped 60, by using a mouse on the operation screen of the software that processes the center line of the piping. Instead of using a mouse, a method of inputting coordinate values ​​may also be used. The target area may be set automatically by a computer device constituting the three-dimensional model creation support system. In this case, the processing by the computer device may be displayed on the screen as appropriate.

[0054] FIG. 7 shows the same with a line extending from the center line of FIG.

[0055] The extended portion is indicated by a dashed line in Figure 7. Hereinafter, this dashed line will be referred to as the "extended center line."

[0056] An extension of the centerline P2 extends from an end point P21 of the centerline P2 to an intersection point T12 with the boundary surface of the target area. Similarly, an extension of the centerline P2 extends from the end point P22 to an intersection point T22.

[0057] As for the center line P3, the end point P31 is extended to the intersection point T32, and the end point P32 is extended to the intersection point T31.

[0058] Next, in step S24 of FIG. 3, a virtual intersection point is obtained using the extended center line.

[0059] The virtual intersection point was determined as follows.

[0060] Two extended center lines are selected and the distance is calculated (step S241).

[0061] If the distance is equal to or less than the threshold, a virtual intersection is created at the midpoint of the line segment that has the shortest distance (step S242).

[0062] Steps S241 and S242 are performed for all combinations of center lines (step S243).

[0063] The coordinates of the end points and virtual intersections of the center line are adjusted in the x-, y-, and z-axis directions (step S244). Specifically, if the deviation of each coordinate is equal to or less than a separately set threshold, the average value is used.

[0064] Through the above steps, the virtual intersection point is obtained.

[0065] FIG. 8 shows the state in which the virtual intersections have been generated.

[0066] In this figure, virtual intersections V1 and V2 are generated.

[0067] The virtual intersection point V1 is generated at a position away from the end points P11 and P21 of the center line, while the virtual intersection point V2 has almost the same coordinates as P31.

[0068] In this figure, all z coordinates have the same value due to the coordinate correction process in step S244. The x coordinates of the end points P12 and P11 and the virtual intersection point V1, which have close x coordinate values, are also the same.

[0069] Next, in step S25 of FIG. 3, a piping model is created in which the vertices are connected using the virtual intersections obtained in step S24.

[0070] The piping model was created as follows.

[0071] One virtual intersection is selected (step S251). In the example of Fig. 8, two virtual intersections V1 and V2 have been generated, so V1 and V2 are processed in that order.

[0072] It is determined whether the virtual intersection is on at least one of the two intersecting center lines or outside both center lines (step S252). In the example of Fig. 8, V1 is on the outside and V2 is on the inside.

[0073] If it is on a line segment, it is classified as an endpoint, and the coordinates of the nearby endpoints are deleted (step S253). If it is on the outside, it is classified as a vertex, and the coordinates of the endpoints near the center line are deleted, and then both center lines are classified into the same group. In the example of FIG. 8, V1 is on the outside, so it is classified as a vertex, and the nearby endpoints P21 and P11 are deleted. Furthermore, center lines P1 and P2 are classified into the same group. On the other hand, V2 is on the line segment of P2, so it is classified as an endpoint, and endpoint P31 is deleted.

[0074] Steps S251 to S253 are repeated for all virtual intersections (step S254).

[0075] The center lines classified into the same group are stored as piping center line information of one piping line (step S255).

[0076] FIG. 9 is a perspective view showing piping center line information.

[0077] In this figure, the remaining end points and vertices from the example of FIG. 8 are shown along with the centerline.

[0078] The centerline information for one piping line is P22, V1 and P12, and the other is P32 and V2.

[0079] FIG. 10 shows an example of output data of piping centerline information.

[0080] In this diagram, the format is such that the first line shows the piping line name and the second line shows the piping line coordinates.

[0081] Specifically, for the piping line named Line01, the coordinates of the piping line are arranged in order from the end point (x11, y11, z11) to the end point (x1n, y1n, z1n), and for Line02, the coordinates of the piping line are arranged in order from the end point (x21, y21, z21) to the end point (x2n, y2n, z2n).

[0082] Next, the piping model creating device 4 (FIG. 1) will be described.

[0083] In the piping model creation device 4, a 3D-CAD model of the piping is created from the piping centerline information 3 using the API of the 3D-CAD system.

[0084] In general, in 3D-CAD systems for plants, a piping model can be created by inputting the coordinates of the center line of the piping. Here, the piping model is not only a straight pipe model, but also a model of the bent pipes that connect the straight pipes is automatically generated. In addition, for branch piping, a model connected to the parent pipe is created by inputting the connecting coordinates.

[0085] Figure 11 shows the created piping model.

[0086] The piping model shown in this figure can be created by giving the coordinates of P22, V1, and P12 and the coordinates of P32 and V2 in the format of FIG. 10, as shown in the example of FIG.

[0087] Next, the valve / equipment recognition device 5 (FIG. 1) will be described.

[0088] The valve / equipment recognition device 5 recognizes valves and equipment from 2D or 3D images of the plant, and acquires position information of the recognized valves and equipment. In this embodiment, the valves are recognized using 2D images.

[0089] The method of creating a 3D image (point cloud) from a 2D image involves determining the depth of an object from multiple 2D images taken of the same object from different angles, and then converting the object into a 3D image.

[0090] A specific procedure in the valve / equipment recognition device 5 will be described below.

[0091] FIG. 12 shows an example of creating a 3D image from multiple 2D images.

[0092] In this figure, a 3D image is created from N 2D images.

[0093] When creating a 3D image (point cloud) from multiple 2D images, multiple 2D image data used to create each point of the 3D image are associated (step S51). Information on the 2D image data is saved in the form of an image file name and two-dimensional coordinates on the image file.

[0094] The valves and equipment are recognized from the 2D images used (step S52). The widely used deep learning method is used to recognize objects in the images. By learning images of valves, equipment, etc. in advance, images of valves and equipment can be identified from all 2D images.

[0095] Using the correspondence of the coordinates obtained in step S51, a 3D image corresponding to the image of the valve and the equipment identified on the 2D image is identified (step S53). Note that the 2D image corresponding to the 3D image of a certain valve spans multiple image files. Also, the points of the 3D image and the points of the 2D image do not correspond one-to-one. Therefore, among the pixels of the valve image recognized on a certain 2D image file, the pixels corresponding to the 3D image are limited to a part. However, by recognizing the valve and the equipment in all 2D images used to create the 3D image and identifying the corresponding 3D image, the 3D image of the valve in the 3D image can be identified. Note that, as a method of finding the corresponding 3D image, a method of determining whether the corresponding 2D image is in the area identified in step S52 for all the points of the 3D image may be used.

[0096] Position information of the valves and equipment is obtained from the coordinate data of the valves and equipment identified on the 3D image (step S54).

[0097] FIG. 13 shows an area containing 3D images that were recognized as valves.

[0098] In this figure, the valves are arranged in the area indicated by a rectangular parallelepiped 130 drawn with a dashed line.

[0099] Since the 3D image includes multiple valves and devices, it is necessary to separate the 3D image identified in step S53 into units of individual valves and devices.

[0100] In this embodiment, the identified points that are continuous and have an interval within a threshold are separated as one valve or equipment. In addition, if the volume of a rectangular parallelepiped created by this process is smaller than a predetermined threshold, it is excluded from the position information of the valve or equipment. This process makes it possible to delete data that was erroneously recognized as a valve or equipment in step S53.

[0101] Through the above steps, three-dimensional position information of the valves and devices can be obtained.

[0102] In this embodiment, the valves and equipment are recognized using 2D images, but they may be recognized using only 3D images. That is, the process of step S52 may be performed using 3D images as multiple 2D images with various viewpoints. In addition, if there is sufficient 3D data of the valves and equipment as training data, the valves and equipment may be identified by three-dimensional shape recognition.

[0103] Next, the valve / equipment CAD model placement device 6 places the valve model on the piping model based on the valve position information acquired by the valve / equipment recognition device 5, using the API of the 3D-CAD system.

[0104] The specific method will be described below.

[0105] As mentioned above, the valve position information is acquired as a rectangular parallelepiped. On the other hand, to place the valve model using the API of the 3D-CAD system, it is necessary to specify the coordinates on the center line of the piping model.

[0106] Figure 14 shows the valves installed in the piping.

[0107] In this diagram, the overlapping portion between a rectangular parallelepiped 141 representing the valve position information and the center line of the pipe 140 is extracted as a line segment 142, and its midpoint 143 is the valve placement position. The valve model is selected from a model library registered in advance in the 3D-CAD system. If the valve / equipment recognition device 5 is able to identify the type of valve, a valve model of the identified type is placed. If the type cannot be identified, a standard valve model is placed.

[0108] Next, the case of the equipment model will be described.

[0109] When placing an equipment model, the orientation and position of the equipment model are adjusted so that the pipe connection port of the equipment model matches the end point of the pipe. If there is an equipment model that has the same pipe connection port as the actual equipment, it is possible to match the pipe connection port and the end point of the pipe, but in reality, it is difficult to prepare all equipment models.

[0110] Therefore, in this embodiment, the pipe connection port and the end point of the pipe are arranged as close as possible. Also, if the type of equipment cannot be identified, a simple shape such as a rectangular parallelepiped or cylinder is arranged as the equipment model. Even if automatic recognition is not possible, by arranging it as an equipment model, the position to place the model can be known, thereby reducing the man-hours required for creating the equipment model.

[0111] Figure 15 shows an example of the created plant 3D model.

[0112] As shown in this figure, the main parts of a plant, excluding structures such as pipe supports that support the pipes, can be made into a 3D model. This makes it possible to create 3D models more efficiently and in a shorter time than with the conventional manual correction method. [Explanation of symbols]

[0113] 1: 2D / 3D image data, 2: Pipe centerline creation device, 3: Pipe centerline information, 4: Pipe model creation device, 5: Valve / equipment recognition device, 6: Valve / equipment CAD model placement device, 7: Plant 3D model, 11: Pipe, 12a: Tank, 12b: Pump, 13: Valve, 41, 43: Pipe, 42: Branch pipe.

Claims

1. a piping centerline creating device that creates piping centerline information representing a piping centerline from three-dimensional image data of a plant; a piping model creation device that creates a piping model using the piping center line information; a valve / equipment recognition device for recognizing valves and equipment from the two-dimensional image data or the three-dimensional image data of the plant; a valve / equipment CAD model arrangement device that arranges a valve model and an equipment model in the piping model created by the piping model creation device, The valve / equipment recognition device creates three-dimensional image data from a plurality of two-dimensional image data, and at that time, obtains a correspondence relationship between coordinates of the two-dimensional image data and coordinates of the three-dimensional image data, and identifies the coordinates of the three-dimensional image data using the coordinates of the two-dimensional image data of the recognized valve and the recognized equipment and the correspondence relationship; The valve / equipment CAD model placement device is a three-dimensional model creation support system that places a valve model or equipment model selected from a model library at the specified coordinates of the three-dimensional image data.

2. 2. The three-dimensional model creation support system according to claim 1, wherein the piping centerline creation device sets a target area for creating the piping centerline information, extends a centerline of a straight pipe model within the target area, determines a virtual intersection from a distance between two centerlines obtained by extension, and creates the piping centerline information from an end point of the piping centerline and the determined virtual intersection.

3. The three-dimensional model creation support system as described in claim 1, wherein the valve / equipment recognition device accumulates the two-dimensional image data or the three-dimensional image data of the valve and the equipment through deep learning.

4. On the computer, A procedure for creating piping centerline information representing a piping centerline from three-dimensional image data of a plant; creating a piping model using the piping centerline information; Recognizing valves and equipment from the two-dimensional image data or the three-dimensional image data of the plant; A procedure for arranging a valve model and an equipment model in the piping model; and a program for executing the procedure, The procedure of recognizing the valve and the device includes creating three-dimensional image data from a plurality of two-dimensional image data, acquiring a correspondence between coordinates of the two-dimensional image data and coordinates of the three-dimensional image data, and identifying the coordinates of the three-dimensional image data using the coordinates of the two-dimensional image data of the recognized valve and the device and the correspondence, The program, wherein the step of placing the valve model and the equipment model is to place a valve model or an equipment model selected from a model library at the identified coordinates of the three-dimensional image data.

5. On the computer, A procedure for creating piping centerline information representing a piping centerline from three-dimensional image data of a plant; creating a piping model using the piping centerline information; Recognizing valves and equipment from the two-dimensional image data or the three-dimensional image data of the plant; A computer-readable recording medium having recorded thereon a procedure for arranging a valve model and an equipment model in the piping model and a program for executing the procedure, The procedure of recognizing the valve and the device includes creating three-dimensional image data from a plurality of two-dimensional image data, acquiring a correspondence between coordinates of the two-dimensional image data and coordinates of the three-dimensional image data, and identifying the coordinates of the three-dimensional image data using the coordinates of the two-dimensional image data of the recognized valve and the device and the correspondence, a recording medium, wherein the step of placing the valve model and the equipment model is to place a valve model or an equipment model selected from a model library at the specified coordinates of the three-dimensional image data.

Images