Building digital twinning method and device and readable storage medium

Abstract

The invention provides a building digital twinning method and device and a readable storage medium, and relates to the technical field of smart cities, and the method comprises the steps: generating a 3D simulation model of a building according to the collected image data of the exterior and interior of the building; converting a building information model BIM drawing of the installation position of the Internet of Things equipment into a vector diagram, and extracting a plane vector diagram of a corresponding floor in the 3D simulation model; matching the BIM drawing vector diagram with the plane vector diagram through an image automatic matching algorithm to obtain a matched image result; the matched image result is integrated to a digital twin platform, and the digital twin platform comprises the 3D simulation model. According to the method, the device and the readable storage medium, the problems that a traditional building modeling mode mostly depends on manual operation, time and labor are consumed, matching between a BIM drawing and a 3D model needs a large amount of manual intervention, precision is low, and Internet of Things equipment positioning is difficult to be accurate to the 3D model can be solved.

Description

Technical Field

[0001] The present invention relates to the field of smart city technology, and in particular to a building digital twin method, device and readable storage medium. Background Art

[0002] With the acceleration of urbanization, the design, construction and management of buildings have become increasingly complex. In order to improve the efficiency and effectiveness of building life cycle management, digital twin technology has gradually attracted attention. Digital twin is an emerging technology that connects physical entities with their virtual copies in real time. It is widely used in smart buildings, smart cities and other fields. However, the implementation of the digital twin method of buildings still faces some technical difficulties, which restricts its promotion in practical applications:

[0003] (1) Traditional building modeling methods mostly rely on manual operations, which is not only inefficient but also consumes a lot of manpower and time;

[0004] (2) At present, the matching between BIM (Building Information Modeling) drawings and 3D (three-dimensional) models still requires a lot of manual intervention, which can easily lead to reduced accuracy and thus affect the overall digital twin effect. This manual operation is not only time-consuming but also prone to errors, further increasing the workload;

[0005] (3) Accurate positioning of IoT devices is also a major challenge in digital twin technology. At present, many IoT devices are difficult to accurately locate in the three-dimensional model, resulting in the inability to effectively monitor the status and location of these devices in actual management, which in turn affects the operating efficiency and safety of the building. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide a building digital twin method, device and readable storage medium in response to the above-mentioned deficiencies in the prior art, so as to solve the problems that traditional building modeling methods mostly rely on manual operations, are time-consuming and labor-intensive, the matching between BIM drawings and 3D models requires a lot of manual intervention and has low precision, and the positioning of IoT devices is difficult to accurately locate in the 3D model.

[0007] In a first aspect, the present invention provides a building digital twin method, the method comprising:

[0008] Generate a 3D simulation model of the building based on the collected image data of the building's exterior and interior;

[0009] Convert the BIM drawing of the IoT device installation location into a vector diagram, and extract the plane vector diagram of the corresponding floor in the 3D simulation model;

[0010] By using an automatic image matching algorithm, the BIM drawing vector diagram is matched with the plane vector diagram to obtain a matched image result;

[0011] Integrate the matched image results into a digital twin platform, wherein the digital twin platform includes the 3D simulation model.

[0012] Furthermore, generating a 3D simulation model of a building based on the collected image data of the exterior and interior of the building specifically includes:

[0013] Use drones to collect image data of the building's exterior;

[0014] Use 360-degree camera equipment to collect image data inside the building;

[0015] A 3D simulation model of the building is generated according to the image data of the exterior and interior of the building using image automatic modeling technology.

[0016] Furthermore, the automatic image matching algorithm is used to match the BIM drawing vector image with the plane vector image to obtain a matched image result, which specifically includes:

[0017] Use a key point detection algorithm to detect key points in the BIM drawing vector diagram and the plane vector diagram, and obtain a descriptor corresponding to each key point;

[0018] Based on the key points and the corresponding descriptors, a feature matching algorithm is used to match the key points in the BIM drawing vector diagram with the plan vector diagram;

[0019] Calculate the transformation matrix from the BIM drawing vector diagram to the plane vector diagram according to the matched key point pairs;

[0020] Applying the transformation matrix to transform the BIM drawing vector diagram so that the BIM drawing vector diagram and the plane vector diagram are aligned in the same coordinate system;

[0021] A vertex matching algorithm is used to match and bind corresponding vertices in the transformed BIM drawing vector diagram and the plane vector diagram to obtain the matched image result.

[0022] Furthermore, before using the key point detection algorithm to detect the key points in the BIM drawing vector diagram and the plane vector diagram, the method further includes:

[0023] Performing size normalization processing on the BIM drawing vector diagram and the plane vector diagram;

[0024] Edge detection is performed on the normalized BIM drawing vector image and the plane vector image to extract corresponding edge features.

[0025] Furthermore, the calculation of the transformation matrix from the BIM drawing vector image to the plane vector image according to the matched key point pairs specifically includes:

[0026] Eliminate incorrectly matched key point pairs from the matched key point pairs and retain correctly matched key point pairs;

[0027] The transformation matrix from the BIM drawing vector image to the plane vector image is calculated based on the correctly matched key point pairs.

[0028] Furthermore, after the BIM drawing vector diagram is transformed by applying the transformation matrix, the method further includes:

[0029] Superimpose the transformed BIM drawing vector diagram and the plane vector diagram to check the matching effect;

[0030] If the matching effect is not ideal, the parameters of the transformation matrix are adjusted.

[0031] Furthermore, after integrating the matched image results into the digital twin platform, the method further includes:

[0032] The alarm information and / or status information of the IoT device is displayed in a visual manner on the digital twin platform.

[0033] In a second aspect, the present invention provides a building digital twin device, the device comprising:

[0034] A simulation model generation module is used to generate a 3D simulation model of a building based on the collected image data of the exterior and interior of the building;

[0035] A vector diagram acquisition module, connected to the simulation model generation module, for converting the building information model (BIM) drawing of the IoT device installation location into a vector diagram, and extracting the plane vector diagram of the corresponding floor in the 3D simulation model;

[0036] An image automatic matching module is connected to the vector graphics acquisition module and is used to match the BIM drawing vector graphics with the plane vector graphics through an image automatic matching algorithm to obtain a matched image result;

[0037] The building digital twin module is connected to the image automatic matching module and is used to integrate the matched image results into the digital twin platform, wherein the digital twin platform includes the 3D simulation model.

[0038] In a third aspect, the present invention provides a building digital twin device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to implement the building digital twin method described in the first aspect.

[0039] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the building digital twin method described in the first aspect is implemented.

[0040] The present invention provides a building digital twin method, device and readable storage medium. First, a 3D simulation model of a building is generated according to the collected image data of the exterior and interior of the building; then the building information model BIM drawing of the installation location of the Internet of Things device is converted into a vector diagram, and the plane vector diagram of the corresponding floor in the 3D simulation model is extracted; then the BIM drawing vector diagram is matched with the plane vector diagram through an image automatic matching algorithm to obtain a matched image result; finally, the matched image result is integrated into a digital twin platform, wherein the digital twin platform includes the 3D simulation model. The present invention can realize automated modeling, save time and manpower, and at the same time, the matching accuracy can be improved and manual intervention can be reduced through the image automatic matching algorithm. In addition, by integrating the matched image results into the digital twin platform, the positioning of the Internet of Things device and the 3D model of the building can be accurately matched and monitored in real time. It solves the problems that the traditional building modeling method relies on manual operation, is time-consuming and labor-intensive, the matching between the BIM drawing and the 3D model requires a lot of manual intervention, low accuracy, and the positioning of the Internet of Things device is difficult to accurately locate in the 3D model. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a flow chart of a building digital twin method according to Embodiment 1 of the present invention;

[0042] Figure 2 This is a structural schematic diagram of a building digital twin device according to Embodiment 2 of the present invention;

[0043] Figure 3 This is a structural schematic diagram of a building digital twin device according to Example 3 of the present invention. DETAILED DESCRIPTION

[0044] In order to enable those skilled in the art to better understand the technical solution of the present invention, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0045] It should be understood that the specific embodiments and drawings described herein are only used to explain the present invention rather than to limit the present invention.

[0046] It can be understood that, in the absence of conflict, the various embodiments of the present invention and the various features in the embodiments can be combined with each other.

[0047] It can be understood that, for the convenience of description, the drawings of the present invention only show the parts related to the present invention, while the parts irrelevant to the present invention are not shown in the drawings.

[0048] It can be understood that each unit and module involved in the embodiments of the present invention may correspond to only one physical structure, or may be composed of multiple physical structures, or multiple units and modules may be integrated into one physical structure.

[0049] It can be understood that the terms "first", "second", etc. in the embodiments of the present invention are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0050] It can be understood that, without conflict, the functions and steps marked in the flowcharts and block diagrams of the present invention may occur in an order different from that marked in the drawings.

[0051] It is understood that the flowcharts and block diagrams of the present invention illustrate the possible architectures, functions, and operations of the systems, devices, equipment, and methods according to the various embodiments of the present invention. Each box in the flowchart or block diagram may represent a unit, module, program segment, or code, which contains executable instructions for implementing the specified functions. Moreover, each box or combination of boxes in the block diagram and flowchart may be implemented by a hardware-based system that implements the specified functions, or may be implemented by a combination of hardware and computer instructions.

[0052] It can be understood that the units and modules involved in the embodiments of the present invention can be implemented by software or hardware. For example, the units and modules can be located in a processor.

[0053] Embodiment 1:

[0054] This embodiment provides a building digital twin method, such as Figure 1 As shown, the method includes:

[0055] Step S101: Generate a 3D simulation model of a building based on the collected image data of the exterior and interior of the building.

[0056] Specifically, drones can be used to collect image data of the exterior of the building; 360-degree camera equipment can be used to collect image data of the interior of the building; and automatic image modeling technology can be used to generate a 3D simulation model of the building based on the image data of the exterior and interior of the building.

[0057] In this embodiment, in addition to using drones and 360-degree camera equipment, a 3D simulation model of the building can also be generated through laser scanning and other high-precision measurement technologies.

[0058] Step S102: converting the building information model (BIM) drawing of the IoT device installation location into a vector diagram, and extracting the plan vector diagram of the corresponding floor in the 3D simulation model.

[0059] In this embodiment, the BIM drawings of the installation location of the IoT device are converted into vector graphics (such as PDF, DWG or SVG format). There are two situations at this time. If this BIM drawing is in a raster image format (such as JPG, PNG or BMP), or needs to be reproduced from a paper drawing into an electronic photo, then we can use image editing software (such as Adobe Illustrator, Inkscape, etc.) to convert it into a vector graphics; if the BIM drawing is created in a professional BIM software (such as Autodesk Revit, ArchiCAD, Bentley Systems, etc.), we can directly export it to a vector graphics format such as PDF, DWG or SVG in the software. These formats support lossless scaling, so the image can be enlarged or reduced without distortion.

[0060] Step S103: Match the BIM drawing vector image with the plane vector image through an automatic image matching algorithm to obtain a matched image result.

[0061] In this embodiment, the automatic image matching algorithm is used to match and bind the BIM drawing vector diagram of the installation location of the Internet of Things device with the corresponding plane vector diagram in the 3D simulation model.

[0062] Optionally, the step of matching the BIM drawing vector image with the plane vector image by an automatic image matching algorithm to obtain a matched image result specifically includes:

[0063] Use a key point detection algorithm to detect key points in the BIM drawing vector diagram and the plane vector diagram, and obtain a descriptor corresponding to each key point;

[0064] Based on the key points and the corresponding descriptors, a feature matching algorithm is used to match the key points in the BIM drawing vector diagram with the plan vector diagram;

[0065] Calculate the transformation matrix from the BIM drawing vector diagram to the plane vector diagram according to the matched key point pairs;

[0066] Applying the transformation matrix to transform the BIM drawing vector diagram so that the BIM drawing vector diagram and the plane vector diagram are aligned in the same coordinate system;

[0067] A vertex matching algorithm is used to match and bind corresponding vertices in the transformed BIM drawing vector diagram and the plane vector diagram to obtain the matched image result.

[0068] In this embodiment, key point detection algorithms such as SIFT (Scale-invariant feature transform), SURF (Speeded Up Robust Features), ORB, etc., for BIM drawing vector graphics, the detected key points include outer contour vertices and the installation positions of each IoT device, and for plane vector graphics, the detected key points include outer contour vertices. Descriptors are used to describe local features around key points. For BIM drawing vector graphics, descriptors include the distance and angle between each outer contour vertex, and the distance and angle from each IoT device to these vertices; for plane vector graphics, descriptors include the connection relationship and angle between each outer contour vertex.

[0069] In this embodiment, feature matching algorithms such as BFMatcher (brute force matcher), FLANN (fast nearest neighbor search library), etc., use feature matching algorithms to match the key points in the BIM drawing vector map with the plane vector map to find potential corresponding key point pairs.

[0070] In this embodiment, commonly used transformation matrices include affine transformation, homography transformation, etc., and vertex matching algorithms such as distance-based matching algorithms are used to match and bind corresponding vertices in the transformed BIM drawing vector map and the plane vector map to obtain the matched image result.

[0071] Optionally, before using a key point detection algorithm to detect key points in the BIM drawing vector diagram and the plane vector diagram, the method further includes:

[0072] Performing size normalization processing on the BIM drawing vector diagram and the plane vector diagram;

[0073] Edge detection is performed on the normalized BIM drawing vector image and the plane vector image to extract corresponding edge features.

[0074] In this embodiment, the size of the BIM drawing vector image and the plane vector image is normalized so that the two images are matched at the same scale. At the same time, edge detection (such as Canny edge detection) is performed on the normalized BIM drawing vector image and the plane vector image to extract the edge features of the image.

[0075] Optionally, calculating the transformation matrix from the BIM drawing vector image to the plane vector image according to the matched key point pairs specifically includes:

[0076] Eliminate incorrectly matched key point pairs from the matched key point pairs and retain correctly matched key point pairs;

[0077] The transformation matrix from the BIM drawing vector image to the plane vector image is calculated based on the correctly matched key point pairs.

[0078] In this embodiment, an algorithm such as RANSAC (Random Sampling Consensus Algorithm) can be used to remove incorrectly matched key point pairs and retain correctly matched key point pairs.

[0079] Optionally, after applying the transformation matrix to transform the BIM drawing vector diagram, the method further includes:

[0080] Superimpose the transformed BIM drawing vector diagram and the plane vector diagram to check the matching effect;

[0081] If the matching effect is not ideal, the parameters of the transformation matrix are adjusted.

[0082] In this embodiment, if the initial superposition effect is not ideal, the transformation matrix parameters are adjusted and the calculation is repeated until a satisfactory matching effect is achieved.

[0083] Step S104: Integrate the matched image results into a digital twin platform, wherein the digital twin platform includes the 3D simulation model.

[0084] In this embodiment, integrating the matched image results into the digital twin platform means reflecting the installation location of the IoT device in the matched image results in the 3D simulation model of the digital twin platform to achieve real-time monitoring and management of the IoT device. The digital twin platform includes 3D simulation models and various operating indicator monitoring of IoT devices.

[0085] Optionally, after integrating the matched image results into the digital twin platform, the method further includes:

[0086] The alarm information and / or status information of the IoT device is displayed in a visual manner on the digital twin platform.

[0087] Specifically, in the digital twin platform, each level of the 3D simulation model of the building can be scaled freely. If an IoT device at any level sounds an alarm, it can be intuitively displayed in the building model.

[0088] In a specific embodiment, the building digital twin method may include the following steps:

[0089] S1. Data collection:

[0090] Use drones to collect external image data of the building.

[0091] Use 360° camera equipment to collect image data inside the building.

[0092] S2. 3D modeling:

[0093] Use image automatic modeling technology to generate 3D simulation models of the interior and exterior of the building.

[0094] S3. BIM drawing vectorization:

[0095] Convert the BIM drawings of the IoT device installation locations into vector graphics (such as PDF, DWG or SVG format). There are two situations. If the BIM drawing is in a raster image format (such as JPG, PNG or BMP), or needs to be reprinted from a paper drawing into an electronic photo, we can use image editing software (such as Adobe Illustrator, Inkscape, etc.) to convert it into a vector graphics; if the BIM drawing is created in professional BIM software (such as Autodesk Revit, ArchiCAD, BentleySystems, etc.), we can directly export it to a vector graphics format such as PDF, DWG or SVG in the software. These formats support lossless scaling, so the image can be enlarged or reduced without distortion.

[0096] S4. Image matching:

[0097] Extract the plane vector diagram of the corresponding floor in the 3D simulation model of the building.

[0098] Through the automatic image matching algorithm, the BIM drawing vector diagram is matched and bound with the plane vector diagram of the 3D simulation model.

[0099] Specifically, automatic image matching is the core method of this solution, which is used to match and bind the BIM drawings of the IoT device installation location with the floor plan in the 3D simulation model. The implementation steps of the algorithm are described in detail below:

[0100] 1. Image preprocessing

[0101] (1) Image reading:

[0102] Read the BIM drawing vector diagram (Figure A) and the floor plan vector diagram (Figure B) of the corresponding floor in the 3D simulation model.

[0103] (2) Image normalization:

[0104] Figure A and Figure B are resized to make the two images match at the same scale.

[0105] a) Read image: For example, use OpenCV to read image files.

[0106] b) Get target size: Calculate or set a uniform target size (eg, width and height).

[0107] c) Resize the image: For example, use OpenCV's `resize` function to resize the image to the target size.

[0108] (3) Edge detection:

[0109] Perform edge detection (such as Canny edge detection) on Figure A and Figure B to extract the edge features of the images.

[0110] a) Read image: Use OpenCV to read image files.

[0111] b) Grayscale processing: convert the image into a grayscale image.

[0112] c) Gaussian blur: Gaussian blur is performed on the image to reduce noise.

[0113] d) Edge detection: Use Canny edge detection algorithm to extract image edges.

[0114] 2. Feature extraction

[0115] (1) Key point detection:

[0116] Use key point detection algorithms (such as SIFT, SURF, ORB, etc.) to detect the key points in Figure A and Figure B.

[0117] It should be noted that since the two images have been normalized, the key points here are the outer contour vertices of the drawing and the installation positions of each IoT device for Figure A, and the outer contour vertices of the drawing for Figure B. You can select one from SIFT, SURF, or ORB for key point detection.

[0118] (2) Descriptor calculation:

[0119] Descriptors are computed for each keypoint, which are used to describe the local features around the keypoint.

[0120] It should be noted that for Figure A, since it is a drawing with dimensions, the descriptor includes the distance and angle between each outer contour vertex, as well as the distance and angle from each IoT device to these vertices; for Figure B, since it is a vector diagram and can be scalable, it is only necessary to describe the connection relationship and angle between each outer contour vertex, which can then be automatically matched by the key point matching algorithm.

[0121] 3. Feature matching

[0122] (1) Matching key points:

[0123] Use a feature matching algorithm (such as BFMatcher, FLANN, etc.) to match the key points in Figure A and Figure B to find potential corresponding key point pairs.

[0124] It should be noted that the key point and its corresponding descriptor are used together.

[0125] (2) Eliminate incorrect matches:

[0126] The incorrectly matched key point pairs are removed through algorithms (such as RANSAC) and the correctly matched key point pairs are retained.

[0127] 4. Transformation calculation

[0128] (1) Calculate the transformation matrix:

[0129] Based on the matching point pairs, the transformation matrix from image A to image B is calculated. Commonly used transformation matrices include affine transformation, homography transformation, etc.

[0130] (2) Apply the transformation matrix:

[0131] Apply the transformation matrix to transform image A so that it is aligned with image B in the same coordinate system.

[0132] It should be noted that Figure A is a dimensioned drawing and Figure B is a vector diagram. However, for the algorithm, it is very likely that Figure A and Figure B will have inconsistent angles, inconsistent front and back, etc. before alignment. They need to be rotated, flipped left and right, and adjusted up and down to align the outer contour vertices in the same coordinate system.

[0133] 5. Image Fusion

[0134] (1) Image overlay:

[0135] Overlay the transformed image A with image B to check the matching effect.

[0136] (2) Adjustment and optimization:

[0137] If the initial superposition effect is not ideal, adjust the transformation matrix parameters and repeat the calculation until a satisfactory matching effect is achieved.

[0138] 6. Vertex Binding

[0139] (1) Vertex extraction:

[0140] Extract the vertex coordinates of graph A and graph B.

[0141] (2) Vertex matching:

[0142] Use a vertex matching algorithm (such as a distance-based matching algorithm) to match and bind corresponding vertices of graph A and graph B.

[0143] It should be noted that when the two images are superimposed in the same coordinate system through operations such as rotation and flipping, some vertices of image B will not overlap with those of image A due to errors in the automatic generation of image B. At this time, the vertex matching algorithm can be used to match the two different vertices of image B and image A that are closer, and then adjust the vertices of image B to obey the outer contour of image A, thereby binding the outer contour vertices of the two images.

[0144] (3)Vertex update:

[0145] After binding, update the vertex coordinates of graph A and graph B so that they change synchronously in the same coordinate system.

[0146] It should be noted that the update is based on Figure A, and the vertices of Figure B are bound to it, so that when a certain floor of the building is scaled in the subsequent digital twin building platform, the two figures can be scaled synchronously.

[0147] 7. Final Output

[0148] (1) Output matching results:

[0149] Output the matched image results and save them in vector format (such as SVG, PDF, etc.).

[0150] It should be noted that, through the above steps, the external vertices of the two images are unified and superimposed into a scalable vector image.

[0151] (2) Integration into the digital twin platform:

[0152] Integrate the matched image results into the digital twin platform to achieve real-time monitoring and management of IoT devices.

[0153] S5. Model integration:

[0154] Integrate the matched drawings with the 3D simulation model to realize real-time monitoring and management of IoT devices on the digital twin platform.

[0155] It should be noted that integrating the matched drawings with the 3D simulation model means reflecting the installation location of the IoT device in the transformed image A in the 3D simulation model. The digital twin platform includes a 3D building model (i.e., a 3D simulation model of the building) and various operating indicator monitoring. Each level of the 3D building model can be freely scaled. If an IoT device at any level gives an alarm, it can be intuitively displayed in the building model.

[0156] S6. Equipment connection:

[0157] Connect IoT devices at all levels to the IoT platform to complete the integration and testing of the overall system.

[0158] In a specific embodiment, the solution is implemented in an office building. First, drones and 360° camera equipment are used to collect internal and external data of the building and generate a 3D simulation model. Then, the BIM drawings of the installation locations of the IoT devices on each floor are converted into vector graphics, which are matched with the corresponding floor plans in the 3D model through an image matching algorithm. After the matching is completed, the IoT devices are connected to the IoT platform to achieve real-time monitoring and management.

[0159] Among them, the image automatic matching algorithm can be implemented through the following Python code example:

[0160]

[0161]

[0162]

[0163] It should be noted that the fault alarm function of IoT devices is a prior art, but the alarm of the prior art is not visualized on the IoT platform, for example: the alarm of the P01 device flooded; at this time, the maintenance personnel have two ways to find out which device it is, one is to look up the table, and find the device location on the installation record table corresponding to P01. The other is to manually change the name on the IoT platform, add a text description of the installation location to the name of the P01 device, and the next time the alarm is triggered, it will display the flooded P01 device-B1 garage southwest corner-alarm; after the digital twin platform of the present invention is associated with the IoT installation location, when P01 alarms, it will display the visualized alarm information on the corresponding floor and the corresponding location, for example: in the southwest corner of the B1 floor of the building model, a flashing cursor is displayed, and the name is still: flooded P01 device, which greatly reduces the difficulty of fault location work for maintenance personnel.

[0164] It should be noted that the digital twin method of a building provided by the present invention collects image data of the exterior and interior of the building through drones and 360° camera equipment, and generates a 3D vector model using image automatic modeling technology. After converting the BIM drawings of the installation location of the IoT device into vector graphics, the BIM drawings are matched and bound to the floor plan of the corresponding floor of the 3D simulation model through an automatic image matching algorithm. In this way, precise positioning and real-time monitoring of IoT devices can be achieved on the digital twin platform. Specifically, it has the following beneficial effects:

[0165] a)Automated modeling saves time and manpower.

[0166] b) Lossless scaling of vector images ensures model accuracy and avoids the problem of existing raster images being easily distorted when enlarged.

[0167] c) Automatic image matching algorithm improves matching accuracy and reduces manual intervention.

[0168] d) Realize accurate matching and real-time monitoring of IoT device positioning and building 3D models.

[0169] e) Through the building digital twin platform, the faulty IoT equipment can be quickly located and warned.

[0170] The digital twin method of a building provided by an embodiment of the present invention first generates a 3D simulation model of the building according to the collected image data of the exterior and interior of the building; then converts the BIM drawing of the installation location of the Internet of Things device into a vector diagram, and extracts the plane vector diagram of the corresponding floor in the 3D simulation model; then matches the BIM drawing vector diagram with the plane vector diagram through an image automatic matching algorithm to obtain a matched image result; finally, the matched image result is integrated into a digital twin platform, wherein the digital twin platform includes the 3D simulation model. The present invention can realize automated modeling, save time and manpower, and at the same time, the matching accuracy can be improved and manual intervention can be reduced through the image automatic matching algorithm. In addition, by integrating the matched image results into the digital twin platform, the accurate matching and real-time monitoring of the Internet of Things device positioning and the building 3D model can be realized. It solves the problems that the traditional building modeling method relies on manual operation, is time-consuming and labor-intensive, the matching between BIM drawings and 3D models requires a lot of manual intervention, low accuracy, and the positioning of the Internet of Things device is difficult to accurately locate in the 3D model.

[0171] Embodiment 2:

[0172] like Figure 2 As shown, this embodiment provides a building digital twin device, which is used to execute the above-mentioned building digital twin method, including:

[0173] A simulation model generation module 11 is used to generate a 3D simulation model of the building based on the collected image data of the exterior and interior of the building;

[0174] A vector diagram acquisition module 12, connected to the simulation model generation module 11, is used to convert the building information model BIM drawing of the IoT device installation location into a vector diagram, and extract the plane vector diagram of the corresponding floor in the 3D simulation model;

[0175] The image automatic matching module 13 is connected to the vector diagram acquisition module 12 and is used to match the BIM drawing vector diagram with the plane vector diagram through an image automatic matching algorithm to obtain a matched image result;

[0176] The building digital twin module 14 is connected to the image automatic matching module 13, and is used to integrate the matched image results into the digital twin platform, wherein the digital twin platform includes the 3D simulation model.

[0177] Optionally, the simulation model generating module 11 includes:

[0178] The first acquisition unit is used to use a drone to collect image data of the exterior of the building;

[0179] The second acquisition unit is used to use a 360-degree camera to collect image data inside the building;

[0180] The automatic modeling unit is used to generate a 3D simulation model of the building according to the image data of the exterior and interior of the building using the image automatic modeling technology.

[0181] Optionally, the image automatic matching module 13 includes:

[0182] A key point detection unit, used to detect key points in the BIM drawing vector diagram and the plane vector diagram using a key point detection algorithm, and obtain a descriptor corresponding to each key point;

[0183] A feature matching unit, configured to match the key points in the BIM drawing vector diagram with the key points in the plane vector diagram using a feature matching algorithm based on the key points and the corresponding descriptors;

[0184] A transformation matrix calculation unit, used for calculating the transformation matrix from the BIM drawing vector image to the plane vector image according to the matched key point pairs;

[0185] A transformation alignment unit, used for applying the transformation matrix to transform the BIM drawing vector diagram so as to align the BIM drawing vector diagram with the plane vector diagram in the same coordinate system;

[0186] The matching and binding unit is used to match and bind the corresponding vertices in the transformed BIM drawing vector image and the plane vector image using a vertex matching algorithm to obtain the matched image result.

[0187] Optionally, the image automatic matching module 13 further includes:

[0188] A normalization unit, used for performing size normalization processing on the BIM drawing vector diagram and the plane vector diagram;

[0189] The edge detection unit is used to perform edge detection on the normalized BIM drawing vector image and the plane vector image to extract corresponding edge features.

[0190] Optionally, the transformation matrix calculation unit includes:

[0191] An error elimination unit is used to eliminate the incorrectly matched key point pairs from the matched key point pairs and retain the correctly matched key point pairs;

[0192] A calculation unit is used to calculate the transformation matrix from the BIM drawing vector image to the plane vector image according to the correctly matched key point pairs.

[0193] Optionally, the image automatic matching module 13 further includes:

[0194] A superposition unit, used for superimposing the transformed BIM drawing vector diagram and the plane vector diagram to check the matching effect;

[0195] A parameter adjustment unit is used to adjust the parameters of the transformation matrix if the matching effect is not ideal.

[0196] Optionally, the device further comprises:

[0197] A visualization module is used to display the alarm information and / or status information of the Internet of Things device in a visual manner in the digital twin platform.

[0198] Embodiment 3:

[0199] refer to Figure 3 This embodiment provides a building digital twin device, including a memory 21 and a processor 22, the memory 21 stores a computer program, and the processor 22 is configured to run the computer program to execute the building digital twin method in Example 1.

[0200] The memory 21 is connected to the processor 22. The memory 21 may be a flash memory, a read-only memory or other memory. The processor 22 may be a central processing unit or a single-chip microcomputer.

[0201] Embodiment 4:

[0202] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the building digital twin method in the above-mentioned embodiment 1 is implemented.

[0203] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, computer program modules or other data). Computer-readable storage media include, but are not limited to, RAM (Random Access Memory), ROM (Read Only Memory), EEPROM (Electrically Erasable Programmable read only memory), flash memory or other memory technology, CDROM (Compact Disc Read Only Memory), digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer.

[0204] In summary, the digital twin method, device and readable storage medium of a building provided by the embodiment of the present invention first generate a 3D simulation model of a building according to the collected image data of the exterior and interior of the building; then convert the BIM drawing of the building information model at the installation location of the Internet of Things device into a vector diagram, and extract the plane vector diagram of the corresponding floor in the 3D simulation model; then match the BIM drawing vector diagram with the plane vector diagram through the image automatic matching algorithm to obtain the matched image result; finally, integrate the matched image result into the digital twin platform, wherein the digital twin platform includes the 3D simulation model. The present invention can realize automated modeling, save time and manpower, and at the same time, can improve the matching accuracy and reduce manual intervention through the image automatic matching algorithm. In addition, by integrating the matched image results into the digital twin platform, the accurate matching and real-time monitoring of the positioning of the Internet of Things device and the 3D model of the building can be realized. It solves the problems that the traditional building modeling method relies on manual operation, is time-consuming and labor-intensive, the matching between the BIM drawing and the 3D model requires a lot of manual intervention, low accuracy, and the positioning of the Internet of Things device is difficult to accurately locate in the 3D model.

[0205] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present invention, but the present invention is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also considered to be within the scope of protection of the present invention.

Claims

1. A building digital twin method, characterized in that: The method comprises: Generate a 3D simulation model of the building based on the collected image data of the building's exterior and interior; Convert the BIM drawing of the IoT device installation location into a vector diagram, and extract the plane vector diagram of the corresponding floor in the 3D simulation model; By using an automatic image matching algorithm, the BIM drawing vector diagram is matched with the plane vector diagram to obtain a matched image result; Integrate the matched image results into a digital twin platform, wherein the digital twin platform includes the 3D simulation model.

2. The method according to claim 1, characterized in that The step of generating a 3D simulation model of a building according to the collected image data of the exterior and interior of the building specifically includes: Use drones to collect image data of the building's exterior; Use 360-degree camera equipment to collect image data inside the building; A 3D simulation model of the building is generated according to the image data of the exterior and interior of the building using image automatic modeling technology.

3. The method according to claim 1, characterized in that The automatic image matching algorithm is used to match the BIM drawing vector diagram with the plane vector diagram to obtain a matched image result, specifically including: Use a key point detection algorithm to detect key points in the BIM drawing vector diagram and the plane vector diagram, and obtain a descriptor corresponding to each key point; Based on the key points and the corresponding descriptors, a feature matching algorithm is used to match the key points in the BIM drawing vector diagram with the plan vector diagram; Calculate the transformation matrix from the BIM drawing vector diagram to the plane vector diagram according to the matched key point pairs; Applying the transformation matrix to transform the BIM drawing vector diagram so that the BIM drawing vector diagram and the plane vector diagram are aligned in the same coordinate system; A vertex matching algorithm is used to match and bind corresponding vertices in the transformed BIM drawing vector diagram and the plane vector diagram to obtain the matched image result.

4. The method according to claim 3, characterized in that Before using the key point detection algorithm to detect the key points in the BIM drawing vector diagram and the plane vector diagram, the method further includes: Performing size normalization processing on the BIM drawing vector diagram and the plane vector diagram; Edge detection is performed on the normalized BIM drawing vector image and the plane vector image to extract corresponding edge features.

5. The method according to claim 3, characterized in that: The step of calculating the transformation matrix from the BIM drawing vector diagram to the plane vector diagram according to the matched key point pairs specifically includes: Eliminate incorrectly matched key point pairs from the matched key point pairs and retain correctly matched key point pairs; The transformation matrix from the BIM drawing vector image to the plane vector image is calculated based on the correctly matched key point pairs.

6. The method according to claim 3, characterized in that After the BIM drawing vector diagram is transformed by applying the transformation matrix, the method further includes: Superimpose the transformed BIM drawing vector diagram and the plane vector diagram to check the matching effect; If the matching effect is not ideal, the parameters of the transformation matrix are adjusted.

7. The method according to claim 1, characterized in that After integrating the matched image results into the digital twin platform, the method further includes: The alarm information and / or status information of the IoT device is displayed in a visual manner on the digital twin platform.

8. A building digital twin device, characterized in that: The device comprises: A simulation model generation module is used to generate a 3D simulation model of a building based on the collected image data of the exterior and interior of the building; A vector diagram acquisition module, connected to the simulation model generation module, for converting the building information model (BIM) drawing of the IoT device installation location into a vector diagram, and extracting the plane vector diagram of the corresponding floor in the 3D simulation model; An image automatic matching module is connected to the vector graphics acquisition module and is used to match the BIM drawing vector graphics with the plane vector graphics through an image automatic matching algorithm to obtain a matched image result; The building digital twin module is connected to the image automatic matching module and is used to integrate the matched image results into the digital twin platform, wherein the digital twin platform includes the 3D simulation model.

9. A building digital twin device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to implement the building digital twin method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the building digital twin method according to any one of claims 1 to 7 is implemented.

Images