3D visualized internet of things digital twin cloud platform construction method and system

Abstract

This invention provides a method and system for constructing a 3D visualized IoT digital twin cloud platform. The method acquires survey data and establishes a basic model based on the survey data. It then uses real-world images captured by a camera device to assist in rendering a first target object in the basic model, resulting in a first model. The first target object is a static object of a preset duration and a preset size. Based on the real-world images, it identifies a dynamically changing second target object and updates the first model accordingly, generating a second model to construct the digital twin cloud platform. Specifically, by updating and displaying dynamic data in real time, the user experience can be improved.

Description

Technical Field

[0001] This invention belongs to the field of digital twin technology, and specifically relates to a method and system for constructing a 3D visualized Internet of Things digital twin cloud platform. Background Technology

[0002] Digital twins create a digital model in virtual space that is highly similar to a physical entity through technologies such as data acquisition and transmission, data processing and analysis, model building and simulation. This model not only has the same appearance and structure as the physical entity, but more importantly, it can reflect the state, behavior and performance of the physical entity, ultimately enabling functions such as real-time monitoring, optimized control, and predictive evaluation of the physical entity.

[0003] The current digital twin technology is not perfect. Specifically, digital twin cities are mostly based on visualization and static analysis, with little application to dynamic data that requires real-time processing, resulting in a poor user experience. Summary of the Invention

[0004] Based on this, the present invention provides a method and system for constructing a 3D visualized IoT digital twin cloud platform, which aims to update dynamic data in real time and display it to improve user experience.

[0005] A first aspect of this invention provides a method for constructing a 3D visualized IoT digital twin cloud platform, applied to urban scenarios equipped with camera devices, the method comprising:

[0006] Acquire survey data and establish a basic model based on the survey data;

[0007] Based on the real-scene images captured by the camera device, the first target object in the basic model is rendered to obtain the first model. The first target object is an object that is stationary for a preset time and has a preset size.

[0008] Based on the real-scene image, a dynamically changing second target object is identified, and based on the second target object, the first model is updated to generate a second model, thereby constructing a digital twin cloud platform.

[0009] Furthermore, before the step of using real-scene images captured by a camera device to assist in rendering the first target object in the basic model to obtain the first model, the following steps are included:

[0010] Based on the aforementioned basic model, identify several first sub-target objects;

[0011] Analyze the first sub-target object, and determine the second sub-target object in the basic model based on the information of the first sub-target object, wherein the first target object includes the first sub-target object and the second sub-target object.

[0012] Furthermore, in the step of analyzing the first sub-target object and determining the second sub-target object in the basic model based on the information of the first sub-target object, at least the attributes and corresponding dimensions of the first sub-target object are analyzed, and the minimum dimensions corresponding to different attributes are determined according to the clustering analysis algorithm, wherein the minimum dimensions corresponding to different attributes are determined as the preset dimensions.

[0013] Furthermore, the step of using real-scene images captured by a camera device to assist in rendering the first target object in the basic model to obtain the first model includes:

[0014] The acquired real-scene images are preprocessed to obtain a preprocessed first image;

[0015] For any first target object in the basic model, determine the first image containing the first target object, and crop and stitch all the first images containing the first target object to generate a target image for describing the first target object;

[0016] Extract the first feature points of the target image and the corresponding second feature points of the first target object, and perform matching in three-dimensional space;

[0017] Based on the matching results, the texture information in the target image is mapped onto the first target object in the base model.

[0018] Furthermore, the step of cropping and stitching all the first images containing the first target object includes:

[0019] The first target object in the first image is cropped out, and the viewpoint and distance of the cropped image are marked.

[0020] Sort the corresponding cropping images according to their distance from closest to furthest to obtain the sorting result;

[0021] Obtain the first cropped image from the sorting results whose distance is less than a threshold, and obtain the second cropped image from the first cropped image with a preset viewpoint.

[0022] In the same 3D model, based on the viewpoint and distance of the second cropping image, it is scaled proportionally and projected onto the 3D space corresponding to the first target object. The overlapping parts of the projected second cropping image are deleted to obtain the first stitching result.

[0023] Determine whether the first splicing result is complete;

[0024] If the first stitching result is determined to be complete, then the first stitching result is used as the target image;

[0025] If the first stitching result is determined to be incomplete, the incomplete image portion is identified, and based on the sorting result, the third cropping image that contains the incomplete image portion and is closest to it is obtained.

[0026] Based on the third cropping image, the first stitching result is completed to obtain the target image.

[0027] Furthermore, in the step of identifying the dynamically changing second target object based on the real-scene image,

[0028] When a dynamically changing second target object is identified, it is determined whether the second target object satisfies the attributes and corresponding dimensions defined by the first sub-target object.

[0029] If it is determined that the second target object satisfies the attributes and corresponding size defined by the first sub-target object, then it is determined whether the second target object is stationary.

[0030] If it is determined that the second target object is stationary, the stationary time is obtained, and it is determined whether the stationary time is greater than the preset duration.

[0031] If the static time is determined to be greater than the preset duration, the second target object in the static state is determined as the first target object, and the step of using the real-scene image captured by the camera device to assist in rendering the first target object in the basic model to obtain the first model is executed.

[0032] Furthermore, the step of identifying a dynamically changing second target object based on the real-scene image, and updating the first model based on the second target object to generate a second model includes:

[0033] Based on the real-scene image, identify the second target object, determine the location of the second target object and the number of the second target objects, the second target objects including at least people and vehicles;

[0034] By comparing real-world images at preset time intervals, the stationary second target and the moving second target are determined, as well as the moving direction and speed of the moving second target.

[0035] Based on the location of the second target and the number of the second target, the corresponding number of physical models are invoked at the locations corresponding to the first model;

[0036] Based on the position of the stationary second target, arrange the physical models of the stationary second target and the moving second target, and control the physical model of the moving second target to run according to the direction and speed of movement to obtain the second model.

[0037] A second aspect of this invention provides a 3D visualization IoT digital twin cloud platform construction system for implementing the 3D visualization IoT digital twin cloud platform construction method provided in the first aspect, the system comprising:

[0038] The acquisition module is used to acquire surveying data and establish a basic model based on the surveying data.

[0039] The rendering module is used to assist in rendering the first target object in the basic model based on the real-scene image captured by the camera device, so as to obtain the first model. The first target object is an object that is stationary for a preset time and has a preset size.

[0040] The update module is used to identify a dynamically changing second target object based on the real-scene image, and update the first model based on the second target object to generate a second model, so as to build a digital twin cloud platform.

[0041] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the 3D visualization Internet of Things digital twin cloud platform construction method provided in the first aspect.

[0042] A fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the 3D visualization Internet of Things digital twin cloud platform construction method provided in the first aspect.

[0043] This invention provides a method and system for constructing a 3D visualized IoT digital twin cloud platform. The method acquires survey data and establishes a basic model based on the survey data. It then uses real-world images captured by a camera device to assist in rendering a first target object in the basic model, resulting in a first model. The first target object is a static object of a preset duration and a preset size. Based on the real-world images, it identifies a dynamically changing second target object and updates the first model accordingly, generating a second model to construct the digital twin cloud platform. Specifically, by updating and displaying dynamic data in real time, the user experience can be improved. Attached Figure Description

[0044] Figure 1 This is a flowchart illustrating the implementation of a 3D visualization IoT digital twin cloud platform construction method provided in Embodiment 1 of the present invention.

[0045] Figure 2 This is a structural block diagram of a 3D visualization IoT digital twin cloud platform construction system provided in Embodiment 2 of the present invention;

[0046] Figure 3 This is a structural block diagram of an electronic device provided in Embodiment 3 of the present invention. Detailed Implementation

[0047] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0048] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0050] Example 1

[0051] According to an embodiment of the present invention, a method for constructing a 3D visualized Internet of Things digital twin cloud platform is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0052] This first embodiment provides a method for constructing a 3D visualized IoT digital twin cloud platform, which can be used in electronic devices, such as computers. Please refer to... Figure 1 , Figure 1 The flowchart illustrates the implementation of a 3D visualization IoT digital twin cloud platform construction method provided in Embodiment 1 of the present invention, specifically including steps S01 to S03.

[0053] Step S01: Obtain survey data and establish a basic model based on the survey data.

[0054] Specifically, surveying data can be obtained through various methods such as manual surveying, satellite imagery, and drone surveying. Based on the surveying data, a three-dimensional basic model is established. Understandably, the basic model mainly includes streets, buildings, etc.

[0055] Step S02: Based on the real-scene image captured by the camera device, the first target object in the basic model is rendered to obtain the first model. The first target object is an object that is stationary for a preset duration and has a preset size.

[0056] It should be noted that since there are a large number of cameras in the city, the real-world images captured by the cameras can be used to assist in rendering the basic model. Before this, it is necessary to mark the target objects to be rendered in the basic model, that is, to manually mark several first sub-target objects according to the basic model.

[0057] Analyze the first sub-target object, and automatically determine the second sub-target object in the base model based on the information of the first sub-target object. The first target object includes the first sub-target object and the second sub-target object. Specifically, at least the attributes and corresponding dimensions of the first sub-target object are analyzed, and the minimum dimensions corresponding to different attributes are determined according to the clustering analysis algorithm. The minimum dimensions corresponding to different attributes are determined as the preset dimensions. Through the above method, all target objects that need to be rendered in the base model can be quickly identified.

[0058] In this embodiment, the step of using real-scene images captured by a camera device to assist in rendering the first target object in the basic model to obtain the first model includes:

[0059] The acquired real-world images are preprocessed to obtain a preprocessed first image. Preprocessing may include operations such as noise removal, color balance adjustment, and contrast enhancement. This helps improve image quality, reduce errors in subsequent processing, and make the image's color and brightness more suitable for rendering requirements.

[0060] For any first target object in the basic model, a first image containing the first target object is determined, and all first images containing the first target object are cropped and stitched together to generate a target image describing the first target object. Specifically, the first target object in the first image is cropped out, and the viewpoint and distance of the cropped image are marked. It can be understood that the viewpoint and distance of the cropped image refer to the shooting viewpoint and shooting distance of the corresponding camera.

[0061] Sort the corresponding cropping images according to their distance from closest to furthest to obtain the sorting result;

[0062] The first cropped image with a distance less than a threshold is obtained from the sorting results, and a second cropped image with a preset viewing angle is obtained from the first cropped image. It should be noted that the closer the shooting distance, the clearer the image is and the more image features can be identified. In addition, the preset viewing angle refers to the viewing angle when the camera is facing the target object.

[0063] In the same 3D model, based on the viewpoint and distance of the second cropping image, it is scaled proportionally and projected onto the 3D space corresponding to the first target object. The overlapping parts of the projected second cropping image are deleted to obtain the first stitching result.

[0064] Determine whether the first splicing result is complete;

[0065] If the first stitching result is determined to be complete, then the first stitching result is used as the target image;

[0066] If the first stitching result is determined to be incomplete, the incomplete image portion is identified, and based on the sorting result, the third cropping image that contains the incomplete image portion and is closest to it is obtained.

[0067] Based on the third cropping image, the first stitching result is completed to obtain the target image;

[0068] The first feature points of the target image and the second feature points of the corresponding first target object are extracted and matched in three-dimensional space. Feature points can be extracted using feature extraction algorithms such as SIFT (Scale Invariant Feature Transform), SURF (Speed-Up Robust Feature Transform), and ORB (Oriented FAST and Rotated BRIEF). These feature points can represent key information in the image, such as the edges, corners, and textures of objects. In addition, the spatial correspondence between the image and the model can be determined by camera pose estimation and three-dimensional reconstruction techniques.

[0069] Based on the matching results, the texture information in the target image is mapped onto the first target object in the base model.

[0070] Step S03: Based on the real-scene image, identify the dynamically changing second target object, and based on the second target object, update the first model to generate a second model, so as to build a digital twin cloud platform.

[0071] Specifically, when a dynamically changing second target object is identified, it is determined whether the second target object satisfies the attributes and corresponding dimensions defined by the first sub-target object;

[0072] If it is determined that the second target object satisfies the attributes and corresponding size defined by the first sub-target object, then it is determined whether the second target object is stationary.

[0073] If it is determined that the second target object is stationary, the stationary time is obtained, and it is determined whether the stationary time is greater than the preset duration.

[0074] If the static time is determined to be greater than the preset duration, then the second target object in the static state is identified as the first target object, and the step of using the real-scene image captured by the camera device to assist in rendering the first target object in the basic model to obtain the first model is executed. The above method can be used to automatically construct and render new target objects.

[0075] It should be noted that the step of identifying a dynamically changing second target object based on the real-scene image, and updating the first model based on the second target object to generate a second model includes:

[0076] Based on the real-scene image, a second target object is identified using a deep learning-based image recognition algorithm, and the location of the second target object and the number of the second target objects are determined. The second target object includes at least people and vehicles, such as identifying a group of people in a park or identifying several vehicles on a road.

[0077] By comparing real-world images at preset time intervals, the stationary second target and the moving second target are determined, as well as the moving direction and speed of the moving second target.

[0078] Based on the location of the second target object and the number of the second target objects, the corresponding number of physical models are called at the location corresponding to the first model. It can be understood that a physical model library is built in advance, and when a need arises, the corresponding physical model is directly called from the physical model library, such as a physical model of a person or a physical model of a vehicle. Specifically, physical models of different types of people and vehicles can be created.

[0079] Based on the position of the immovable second target, arrange the physical models of the immovable second target and the moving second target, and control the physical model of the moving second target to run according to the moving direction and speed to obtain the second model. Specifically, call the physical model of the immovable second target, place it in the field according to the relative position, and use the physical model of the immovable second target as a reference to call the physical model of the corresponding moving second target, and drive it according to the moving direction and speed.

[0080] The second model is generated only when selected by the user to avoid generating too much data in real time. Understandably, when a user logs into the digital twin cloud platform and switches to a certain road or venue, the corresponding camera image will be retrieved, and a corresponding physical model will be generated based on the image and displayed in the digital twin cloud platform to enhance the user experience. When closed, the generation of the physical model in the digital twin cloud platform will be canceled.

[0081] In summary, the 3D visualization IoT digital twin cloud platform construction method in the above embodiments of the present invention acquires surveying data, establishes a basic model based on the surveying data, and uses real-scene images acquired by a camera device to assist in rendering a first target object in the basic model to obtain a first model. The first target object is a static object with a preset duration and a preset size. Based on the real-scene images, a dynamically changing second target object is identified, and the first model is updated based on the second target object to generate a second model, thereby constructing a digital twin cloud platform. Specifically, by updating and displaying dynamic data in real time, the user experience can be improved.

[0082] Example 2

[0083] Please see Figure 2 , Figure 2 This is a structural block diagram of a 3D visualization IoT digital twin cloud platform construction system provided in Embodiment 2 of the present invention. This 3D visualization IoT digital twin cloud platform construction system 200 is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0084] Specifically, the 3D visualization IoT digital twin cloud platform construction system 200 includes: an acquisition module 21, a rendering module 22, and an update module 23, wherein:

[0085] The acquisition module 21 is used to acquire surveying data and establish a basic model based on the surveying data;

[0086] The rendering module 22 is used to assist in rendering the first target object in the basic model based on the real-scene image captured by the camera device, so as to obtain the first model. The first target object is an object that is stationary for a preset time and has a preset size.

[0087] The update module 23 is used to identify a dynamically changing second target object based on the real scene image, and update the first model based on the second target object to generate a second model in order to build a digital twin cloud platform. When a dynamically changing second target object is identified, it is determined whether the second target object meets the attributes and corresponding size defined by the first sub-target object.

[0088] If it is determined that the second target object satisfies the attributes and corresponding size defined by the first sub-target object, then it is determined whether the second target object is stationary.

[0089] If it is determined that the second target object is stationary, the stationary time is obtained, and it is determined whether the stationary time is greater than the preset duration.

[0090] If the static time is determined to be greater than the preset duration, the second target object in the static state is determined as the first target object, and the step of using the real-scene image captured by the camera device to assist in rendering the first target object in the basic model to obtain the first model is executed.

[0091] Furthermore, in some optional embodiments of the present invention, the 3D visualization IoT digital twin cloud platform construction system 200 further includes:

[0092] The identification module is used to identify several first sub-target objects based on the basic model;

[0093] The analysis module is used to analyze the first sub-target object, determine the second sub-target object in the basic model based on the information of the first sub-target object, wherein the first target object includes the first sub-target object and the second sub-target object, analyze at least the attributes and corresponding dimensions of the first sub-target object, and determine the minimum dimensions corresponding to different attributes according to the clustering analysis algorithm, wherein the minimum dimensions corresponding to different attributes are determined as the preset dimensions.

[0094] Furthermore, in some optional embodiments of the present invention, the rendering module 22 includes:

[0095] The preprocessing unit is used to preprocess the acquired real-scene images to obtain a preprocessed first image;

[0096] The first determining unit is configured to determine, for any first target object in the basic model, a first image containing the first target object, and to crop and stitch together all first images containing the first target object to generate a target image for describing the first target object.

[0097] An extraction unit is used to extract the first feature points of the target image and the corresponding second feature points of the first target object, and to perform matching in three-dimensional space;

[0098] The mapping unit is used to map the texture information in the target image onto the first target object in the base model according to the matching result.

[0099] Furthermore, in some optional embodiments of the present invention, the first determining unit includes:

[0100] The cropping subunit is used to crop out the first target object from the first image and mark the viewpoint and distance of the cropped image;

[0101] The sorting sub-unit is used to sort the corresponding cropping images according to the order of distance from nearest to farthest, and obtain the sorting result;

[0102] The sub-unit is used to obtain a first cropping image from the sorting result whose distance is less than a threshold, and to obtain a second cropping image from the first cropping image whose viewpoint is a preset viewpoint.

[0103] The projection subunit is used to scale the second cropping image proportionally within the same 3D model, project it onto the 3D space corresponding to the first target object, and delete the overlapping parts of the projected second cropping image to obtain the first stitching result.

[0104] The judgment subunit is used to determine whether the first splicing result is complete;

[0105] The first determining subunit is used to take the first stitching result as the target image if it is determined that the first stitching result is complete.

[0106] The second determining subunit is used to determine the image portion at the incomplete location if the first stitching result is determined to be incomplete, and to obtain the third cropping image that contains the image portion at the incomplete location and is closest to it according to the sorting result.

[0107] The supplementary subunit is used to complete the first stitching result based on the third cropping image to obtain the target image.

[0108] Furthermore, in some optional embodiments of the present invention, the updating module 23 includes:

[0109] The second determining unit is used to identify a second target object based on the real-scene image, and to determine the location of the second target object and the number of the second target objects, wherein the second target objects include at least people and vehicles;

[0110] The third determining unit is used to compare real-scene images at preset time intervals to determine the immobile second target and the moving second target, as well as the moving direction and speed of the moving second target.

[0111] The calling unit is used to call the corresponding number of physical models at the location corresponding to the first model, based on the location of the second target object and the number of the second target objects.

[0112] The control unit is used to arrange the physical models of the immobile second target and the moving second target based on the position of the immobile second target, and to control the physical model of the moving second target to run in the direction and speed of movement to obtain the second model.

[0113] Example 3

[0114] In another aspect, the present invention also proposes an electronic device, please refer to [link to relevant documentation]. Figure 3 The image shows an electronic device according to Embodiment 3 of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor. When the processor 10 executes the computer program 30, it implements the 3D visualization Internet of Things digital twin cloud platform construction method described above.

[0115] In some embodiments, the processor 10 may be a central processing unit (CPU), controller, microcontroller, microprocessor or other data processing chip, used to run program code stored in memory 20 or process data, such as executing access restriction programs.

[0116] The memory 20 includes at least one type of readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 20 can be an internal storage unit of an electronic device, such as the hard disk of the electronic device. In other embodiments, the memory 20 can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. Furthermore, the memory 20 can include both internal and external storage units of the electronic device. The memory 20 can be used not only to store application software and various types of data of the electronic device, but also to temporarily store data that has been output or will be output.

[0117] It should be pointed out that, Figure 3 The structure shown does not constitute a limitation on the electronic device. In other embodiments, the electronic device may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0118] This invention also proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the 3D visualization IoT digital twin cloud platform construction method described above.

[0119] Those skilled in the art will understand that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0120] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0121] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0122] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0123] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this patent should be determined by the appended claims.

Claims

1. A 3D visualized IoT digital twin cloud platform construction method, characterized in that, The method is applied to a city scene provided with a camera device, and comprises: obtaining surveying and mapping data, and establishing a basic model according to the surveying and mapping data; assisting in rendering a first target object in the basic model according to a real scene image collected by the camera device to obtain a first model, the first target object being an object that is static for a preset time length and has a preset size; identifying a second target object that dynamically changes according to the real scene image, and updating the first model on the basis of the second target object to generate a second model to construct a digital twin cloud platform; the step of assisting in rendering the first target object in the basic model according to the real scene image collected by the camera device to obtain the first model comprises: preprocessing the collected real scene image to obtain a first image after preprocessing; for any first target object in the basic model, determining a first image containing the first target object, and performing cropping and splicing on all first images containing the first target object to generate a target image for describing the first target object; extracting a first feature point of the target image and a second feature point of the corresponding first target object, and matching in a three-dimensional space; mapping texture information in the target image to the first target object in the basic model according to a matching result; in the step of identifying the second target object that dynamically changes according to the real scene image, when the second target object that dynamically changes is identified, judging whether the second target object satisfies attributes and corresponding sizes defined by a first sub-target object; if it is judged that the second target object satisfies the attributes and corresponding sizes defined by the first sub-target object, judging whether the second target object has a static condition; if it is judged that the second target object has the static condition, obtaining a static time, and judging whether the static time is greater than the preset time length; if it is judged that the static time is greater than the preset time length, determining the second target object in the static state as the first target object, and performing the step of assisting in rendering the first target object in the basic model according to the real scene image collected by the camera device to obtain the first model; the step of identifying the second target object that dynamically changes according to the real scene image, and updating the first model on the basis of the second target object to generate the second model comprises: identifying the second target object according to the real scene image, and determining a site where the second target object is located and a number of the second target objects, the second target objects at least including people and vehicles; comparing real scene images at intervals of a preset time to determine second target objects that are not moving and second target objects that are moving, and a moving direction and speed of the second target objects that are moving; according to the site where the second target object is located and the number of the second target objects, calling a corresponding number of physical models at positions corresponding to the first model; arranging the physical models of the second target objects that are not moving and the second target objects that are moving according to positions of the second target objects that are not moving, and controlling the physical models of the second target objects that are moving to run according to the moving direction and speed to obtain the second model.

2. The 3D visualized IoT digital twin cloud platform building method of claim 1, wherein, The step of assisting in rendering the first target object in the base model according to the real scene image collected by the camera to obtain the first model comprises the following steps: Identifying a plurality of first sub-target objects according to the base model; Analyzing the first sub-target objects, and determining a second sub-target object in the base model according to information of the first sub-target objects, wherein the first target object comprises the first sub-target objects and the second sub-target object.

3. The 3D visualized IoT digital twin cloud platform building method of claim 2, wherein, In the step of analyzing the first sub-target objects, and determining a second sub-target object in the base model according to information of the first sub-target objects, at least the attributes and corresponding sizes of the first sub-target objects are analyzed, and the minimum size corresponding to different attributes is respectively determined according to a clustering analysis algorithm, wherein the minimum size corresponding to different attributes is determined as the preset size.

4. The 3D visualized IoT digital twin cloud platform building method of claim 3, wherein, The step of cropping and splicing all first images containing the first target object comprises the following steps: cropping the first target object in the first image, and marking the perspective and distance of the cropped image; sorting the corresponding cropped images according to the distance from near to far to obtain a sorting result; obtaining a first cropped image with a distance less than a threshold value in the sorting result, and obtaining a second cropped image with a preset perspective from the first cropped image; in the same three-dimensional model, performing proportional scaling based on the perspective and distance of the second cropped image, projecting onto the three-dimensional space corresponding to the first target object, and deleting the overlapping part of the projected second cropped image to obtain a first splicing result; judging whether the first splicing result is complete; if it is judged that the first splicing result is complete, taking the first splicing result as the target image; if it is judged that the first splicing result is not complete, determining the image part of the incomplete part, and obtaining a third cropped image containing the image part of the incomplete part and closest to the distance according to the sorting result; complementing the first splicing result to complete according to the third cropped image to obtain the target image.

5. A 3D visualized IoT digital twin cloud platform construction system, characterized in that, The system for implementing the 3D visualization Internet of Things digital twin cloud platform construction method according to any one of claims 1-4, the system comprises: an acquisition module configured to acquire surveying and mapping data, and establish a base model according to the surveying and mapping data; a rendering module configured to assist in rendering a first target object in the base model according to a real scene image collected by a camera to obtain a first model, the first target object being an object that is static for a preset time length and has a preset size; an update module configured to identify a second target object that dynamically changes according to the real scene image, and generate a second model by updating the first model based on the second target object to construct a digital twin cloud platform.

6. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by a processor to implement the 3D visualization Internet of Things digital twin cloud platform construction method according to any one of claims 1-4.

7. An electronic device, comprising: The computer program is stored in the memory and executable on the processor, and the processor implements the 3D visualization Internet of Things digital twin cloud platform construction method according to any one of claims 1-4 when executing the program.

Images