A two-dimensional and three-dimensional integrated map display method and system

Abstract

The application belongs to the technical field of information geography, and discloses a two-three-dimensional integrated map display method and system. The method comprises the following steps: based on a cloud data center, according to two-three-dimensional geographic information data, using a three-dimensional reconstruction algorithm, an integrated map simulation model is constructed; according to real-time monitoring data of a physical entity, using an OPC UA communication scheme, data flow of a digital entity in the integrated map simulation model is generated, and an integrated map digital twin model is obtained; the data flow is subjected to abnormality detection, real-time abnormality detection results are obtained, and the integrated map digital twin model is used to visually display the data flow and the real-time abnormality detection results. The application solves the problems of the prior art, such as lack of depth integration of two-three-dimensional data, insufficient intuitive and efficient integration and display, large deviation of the three-dimensional model, and low automation degree.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of information geography, and particularly relates to a two-three-dimensional integrated map display method and system. BACKGROUND

[0002] Geographic information data refers to the general term of all data used to represent the spatial distribution of the earth's surface. It contains the attribute information of various natural and artificial features on the earth's surface, as well as their spatial position and mutual relationship. Geographic information data is the core component of geographic information system, and is mainly used in many fields such as city planning, resource management, environmental monitoring, disaster warning, transportation, market analysis, etc. The geographic information map constructed based on geographic information data is used to display and analyze geographic information. In the geographic information system, the geographic information map is not only a static visual representation, but also a dynamic and interactive analysis tool. The geographic information map can integrate multi-source data such as remote sensing images, terrain data, population statistics, etc. to provide a comprehensive spatial information view, which can help users understand and interpret spatial data, conduct geographic analysis, and support decision making.

[0003] The existing geographic information map display has the following defects:

[0004] 1) In the prior art, the fusion of two-dimensional and three-dimensional geographic information data is usually simple, lacking depth of spatial relationship and attribute information integration, and there are difficulties in conversion and synchronization between two-dimensional data and three-dimensional models, which leads to that users cannot obtain complete information view when analyzing and making decisions;

[0005] 2) In the prior art, there is often a lack of real-time monitoring and updating of physical entity state, which is a major defect for application scenarios that require real-time decision support. The integration and display of real-time data are usually not intuitive and efficient, and it is difficult to meet the rapid response requirements in emergency situations;

[0006] 3) In the prior art, the three-dimensional reconstruction technology may have insufficient accuracy, especially when dealing with complex terrain and building structures, the reconstructed three-dimensional model may have a large deviation from the actual situation, and the degree of automation in the three-dimensional reconstruction process is not high, often requiring a lot of manual intervention, increasing the possibility of errors. SUMMARY

[0007] In order to solve the problems of lack of depth integration of two-three-dimensional data, not intuitive and efficient integration and display, and three-dimensional model may have a large deviation and low degree of automation in the prior art, the present application aims to provide a two-three-dimensional integrated map display method and system.

[0008] The technical solution adopted by the present application is:

[0009] A two-three-dimensional integrated map display method, comprising the following steps:

[0010] Based on the cloud data center, according to the two-three-dimensional geographic information data, using a three-dimensional reconstruction algorithm, an integrated map simulation model is constructed;

[0011] According to the real-time monitoring data of the physical entity, using the OPC UA communication scheme, the data stream of the digital entity in the integrated map simulation model is generated, and the integrated map digital twin model is obtained;

[0012] The data stream is detected for abnormalities, and real-time abnormal detection results are obtained, and the integrated map digital twin model is used to visually display the data stream and the real-time abnormal detection results.

[0013] Further, the two-three-dimensional geographic information data includes two-dimensional geographic information data and three-dimensional geographic information data;

[0014] The two-dimensional geographic information data includes two-dimensional spatial data, two-dimensional attribute data and two-dimensional metadata;

[0015] The three-dimensional geographic information data includes three-dimensional spatial data, three-dimensional attribute data and three-dimensional metadata.

[0016] Further, based on the cloud data center, according to the two-three-dimensional geographic information data, using a three-dimensional reconstruction algorithm, an integrated map simulation model is constructed, comprising the following steps:

[0017] Based on the cloud data center, the two-three-dimensional geographic information data of the target area is collected and analyzed, and the two-dimensional geographic information data and the three-dimensional geographic information data of the target area are obtained;

[0018] According to the two-dimensional geographic information data, using a three-dimensional reconstruction model constructed based on a deep learning algorithm, three-dimensional reconstruction is performed to obtain an initial integrated map simulation model;

[0019] According to the three-dimensional geographic information data, the initial integrated map simulation model is corrected to obtain a final integrated map simulation model.

[0020] Further, the three-dimensional reconstruction model is constructed based on the CNN-Elman-GAN algorithm, and the three-dimensional reconstruction model includes a two-dimensional feature extraction module constructed based on the CNN algorithm, a target detection module constructed based on the Elman algorithm, and a three-dimensional reconstruction module constructed based on the GAN algorithm.

[0021] Further, according to the two-dimensional geographic information data, using a three-dimensional reconstruction model constructed based on a deep learning algorithm, three-dimensional reconstruction is performed to obtain an initial integrated map simulation model, comprising the following steps:

[0022] The two-dimensional feature extraction module is used to extract two-dimensional data features of the two-dimensional geographic information data, and the two-dimensional data features are input into the target detection module.

[0023] The target detection module is used to perform target detection according to the two-dimensional data features, obtain entity targets corresponding to the physical entities, extract entity target two-dimensional data features corresponding to the entity targets, and input the three-dimensional reconstruction module;

[0024] The three-dimensional reconstruction module is used to perform three-dimensional reconstruction according to the entity target two-dimensional data features, and obtain entity target three-dimensional models of digital entities corresponding to the entity targets;

[0025] The entity target three-dimensional models of all entity targets and the two-dimensional geographic information data are integrated to obtain an initial integrated map simulation model containing a plurality of digital entities.

[0026] Further, the initial integrated map simulation model is corrected according to the three-dimensional geographic information data to obtain a final integrated map simulation model, including the following steps:

[0027] The feature point extraction algorithm is used to extract a plurality of first feature points of the three-dimensional geographic information data and a plurality of second feature points of the initial integrated map simulation model;

[0028] The feature point matching algorithm is used to perform feature point matching on the plurality of first feature points and the plurality of second feature points to obtain a plurality of matching feature point pairs;

[0029] According to the plurality of matching feature point pairs, the three-dimensional geographic information data is used to correct a matching region of the initial integrated map simulation model to obtain the final integrated map simulation model.

[0030] Further, according to the real-time monitoring data of the physical entities, the OPC UA communication scheme is used to generate a data stream of the digital entities in the integrated map simulation model, and an integrated map digital twin model is obtained, including the following steps:

[0031] According to the entity targets output by the three-dimensional reconstruction model, real-time monitoring data of the corresponding physical entities is collected, and an OPC UA information model corresponding to the real-time monitoring data is constructed;

[0032] The OPC UA server is deployed in the cloud data center, and the corresponding OPC UA instance is created in the address space of the OPC UA server according to the OPC UA information model;

[0033] The real-time monitoring data is transmitted to the OPC UA server in the cloud data center, written into the corresponding OPC UA instance, and real-time information data of the OPC UA instance is extracted;

[0034] The real-time information data is converted into a data stream, the data stream is input into a digital entity corresponding to a physical entity, a visual interface is set for the digital entity, and an integrated map digital twin model is obtained.

[0035] Further, the data stream is subjected to abnormality detection to obtain real-time abnormality detection results, and the integrated map digital twin model is used to visually display the data stream and the real-time abnormality detection results, including the following steps:

[0036] The data stream of the digital entity is input into an abnormality detection model constructed based on a deep learning algorithm to perform abnormality detection on the data stream, and real-time abnormality detection results of the digital entity are obtained.

[0037] If the real-time abnormality detection results are abnormal, corresponding real-time alarm signals are generated according to the real-time abnormality detection results.

[0038] The data stream, the real-time abnormality detection results and the real-time alarm signals are displayed in the visual interface of the digital entity corresponding to the integrated map digital twin model.

[0039] Further, the abnormality detection model is constructed based on a GCN-RF algorithm, and the abnormality detection model includes a graph feature extraction module and an abnormality detection module connected in sequence, wherein the graph feature extraction module is constructed based on a GCN algorithm, and the abnormality detection module is constructed based on an RF algorithm.

[0040] A two-three-dimensional integrated map display system is used to implement a two-three-dimensional integrated map display method, and the system includes a cloud data center and a plurality of data acquisition devices.

[0041] The cloud data center is provided with a three-dimensional reconstruction unit, a digital twin construction unit and a map display unit connected in sequence.

[0042] The present application has the following advantages:

[0043] The application discloses a two-three-dimensional integrated map display method and system, and realizes conversion from two-dimensional data to accurate three-dimensional models by means of an integrated map simulation model constructed by a three-dimensional reconstruction algorithm combined with two-three-dimensional data fusion, effectively integrates rich information of two-dimensional data and stereoscopic perception of three-dimensional models, and provides a comprehensive spatial information view; the integrated map digital twin model realizes real-time digital twin monitoring and display, collects data of physical entities in real time through an OPC UA information model, integrates the data into the digital twin model, realizes real-time synchronization of the physical world and the digital copy, realizes intuitive and efficient integration and display, and greatly improves the efficiency of monitoring and decision support; when the integrated map simulation model is constructed, a high-precision three-dimensional reconstruction and correction algorithm is introduced, real three-dimensional data is used to accurately correct the initial three-dimensional model, the high consistency of the digital twin model and the actual physical entity is ensured, the deviation from the actual situation is reduced, the degree of automation is improved, a large amount of manual intervention is avoided, and the possibility of errors is reduced.

[0044] Other beneficial effects of the application will be further described in the specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 It is a flow chart of the two-three-dimensional integrated map display method in the application.

[0046] Figure 2 It is a structural block diagram of the two-three-dimensional integrated map display system in the application. DETAILED DESCRIPTION

[0047] The application will be further explained in combination with the drawings and specific embodiments.

[0048] Embodiment 1:

[0049] As shown in the drawings, Figure 1 The embodiment provides a two-three-dimensional integrated map display method, which comprises the following steps:

[0050] S1: based on a cloud data center, according to two-three-dimensional geographic information data, using a three-dimensional reconstruction algorithm, constructing an integrated map simulation model, comprising the following steps:

[0051] S1-1: based on the cloud data center, collecting two-three-dimensional geographic information data of a target area, and performing analysis to obtain two-dimensional geographic information data and three-dimensional geographic information data of the target area;

[0052] The two-three-dimensional geographic information data comprises two-dimensional geographic information data and three-dimensional geographic information data;

[0053] Two-dimensional geographic information data is usually used to represent information about the surface of a target area, including points, lines, and areas on a map. It can be satellite imagery, aerial photographs, or maps. For example, roads, administrative boundaries, and land use types in a target area are all two-dimensional geographic information data. Two-dimensional geographic information data is usually represented on a plane and does not consider height or three-dimensional information.

[0054] Three-dimensional geographic information data not only includes the information in three-dimensional geographic information data, but also adds the vertical dimension, namely height information. Three-dimensional geographic information data more realistically represents the information of physical entities such as terrain, buildings, underground facilities, etc. in three dimensions.

[0055] Two-dimensional geographic information data includes two-dimensional spatial data, two-dimensional attribute data, and two-dimensional metadata;

[0056] Two-dimensional spatial data describes the location and shape of surface features of a target area, usually represented by points, lines, and surfaces. Two-dimensional attribute data provides descriptive information about two-dimensional spatial elements and is associated with the two-dimensional spatial data. For example, the physical entity corresponding to a two-dimensional spatial data point may represent a building, and its two-dimensional attribute data may include information such as the building's name, purpose, year of construction, and ownership. Two-dimensional attribute data usually exists in tabular form and corresponds to each element of the two-dimensional spatial data. It is associated with spatial elements through a unique identifier (such as ID). Two-dimensional metadata is data element information about two-dimensional geographic information data. In a geographic information system, two-dimensional metadata provides detailed information about spatial datasets, such as the source, creation date, data accuracy, data format, coordinate system, data collection method, and responsible unit of the two-dimensional geographic information data. Two-dimensional metadata is crucial for the management, sharing, and reuse of two-dimensional geographic information data, helping users understand and use the two-dimensional geographic information data.

[0057] Three-dimensional geographic information data includes three-dimensional spatial data, three-dimensional attribute data, and three-dimensional metadata;

[0058] In addition to the information contained in two-dimensional spatial data, three-dimensional spatial data also contains height or depth information, which can more accurately represent the three-dimensional features in the real world. Three-dimensional attribute data and three-dimensional metadata are the same as two-dimensional attribute data and two-dimensional metadata, are related to the corresponding three-dimensional spatial data, and are used to understand and use three-dimensional geographic information data.

[0059] S1-2: Based on two-dimensional geographic information data, a three-dimensional reconstruction model constructed using a deep learning algorithm is used to perform three-dimensional reconstruction and obtain an initial integrated map simulation model.

[0060] The 3D reconstruction model is built based on the CNN-Elman-GAN algorithm, and includes a 2D feature extraction module built based on the Convolutional Neural Networks (CNN) algorithm, an object detection module built based on the Elman algorithm, and a 3D reconstruction module built based on the Generative Adversarial Networks (GAN) algorithm, which are connected in sequence.

[0061] The 2D feature extraction module is used to extract advanced features from 2D geographic information data. These features include edges, textures, shapes, etc., and can capture the details and structural information of 2D geographic information data, which is crucial for subsequent 3D reconstruction.

[0062] The target detection module is used to detect and locate the target location and region of entity targets in two-dimensional geographic information data based on the characteristics of two-dimensional data. It can use time dynamic information for target detection, which helps to locate entity targets more accurately. The output will be used to guide the three-dimensional reconstruction process to ensure that the reconstructed three-dimensional model is aligned with the two-dimensional entity targets in the two-dimensional geographic information data.

[0063] The 3D reconstruction module consists of a generator and a discriminator. The generator's task is to generate a 3D model using 2D features and object detection information, while the discriminator's task is to distinguish between the generated 3D model and the real 3D model. Through this adversarial process, the generator can generate increasingly realistic 3D models. The generator is usually a deep neural network that takes 2D features and object detection information as input and outputs a 3D model. The discriminator is another deep neural network that takes the 3D model as input and outputs a score representing the model's realism. The discriminator receives the 3D model output by the generator and tries to distinguish whether it is real or generated. Through multiple iterations of training, the generator gradually learns to generate more realistic 3D models.

[0064] Based on two-dimensional geographic information data, a three-dimensional reconstruction model constructed using a deep learning algorithm is used to perform three-dimensional reconstruction, resulting in an initial integrated map simulation model. The process includes the following steps:

[0065] S1-2-1: Use the two-dimensional feature extraction module to extract the two-dimensional data features of the two-dimensional geographic information data, and input the two-dimensional data features into the target detection module;

[0066] S1-2-2: Using the target detection module, target detection is performed based on the two-dimensional data features to obtain the physical target corresponding to the physical entity, extract the two-dimensional data features of the corresponding physical target, and input them into the three-dimensional reconstruction module;

[0067] S1-2-3: Using the 3D reconstruction module, based on the 2D data features of the entity target, perform 3D reconstruction to obtain the 3D model of the entity target corresponding to the digital entity.

[0068] S1-2-4: Integrate the 3D models of all entity targets and the 2D geographic information data to obtain an initial integrated map simulation model containing several digital entities.

[0069] S1-3: Based on the 3D geographic information data, the initial integrated map simulation model is corrected to obtain the final integrated map simulation model, including the following steps:

[0070] S1-3-1: Using a feature point extraction algorithm, extract several first feature points from the 3D geographic information data and several second feature points from the initial integrated map simulation model;

[0071] Feature point extraction algorithms include Scale-Invariant Feature Transform (SIFT), Speeded Up Robust Features (SURF), and Oriented Fast and Rotated BRIEF (ORB) algorithms.

[0072] S1-3-2: Use a feature point matching algorithm to perform feature point matching on a number of first feature points and a number of second feature points to obtain a number of matching feature point pairs;

[0073] Feature point matching algorithms include Brute-Force Matcher (BFM), Fast Library for Approximate Nearest Neighbors (FLANN) matching, and Random Sample Consensus (RANSAC) algorithms.

[0074] S1-3-3: Based on several matching feature point pairs, use 3D geographic information data to correct the matching area of ​​the initial integrated map simulation model to obtain the final integrated map simulation model.

[0075] S2: Based on real-time monitoring data of physical entities, using the Object Linking and Embedding for Process Control Unified Architecture (OPCUA) communication scheme, generate the data flow of digital entities in the integrated map simulation model, and obtain the integrated map digital twin model, including the following steps:

[0076] S2-1: Based on the entity targets output by the 3D reconstruction model, collect real-time monitoring data of the corresponding physical entities, and construct the corresponding OPC UA information model based on the real-time monitoring data, including the following steps:

[0077] S2-1-1: Based on the entity targets output by the 3D reconstruction model, use a data acquisition device to collect real-time monitoring data of the corresponding physical entities, and preprocess the real-time monitoring data to obtain preprocessed real-time monitoring data.

[0078] S2-1-2: Perform data parsing on the preprocessed real-time monitoring data to obtain several physical parameters and their relationships, and set corresponding nodes, node attributes, and node relationships based on the physical parameters and their relationships;

[0079] Nodes are building blocks in the OPC UA information model, including but not limited to:

[0080] Object nodes: Represent physical entities in the real world, such as terrain, buildings, underground facilities, etc., corresponding to the entity target;

[0081] Variable nodes: Represent data values, such as monitored temperature, monitored humidity, monitored pressure, etc. for terrain, buildings, and underground facilities;

[0082] Method node: Represents a function or operation that can be invoked;

[0083] View nodes: Represent a subset of the OPC UA information model, which can be used to organize nodes or provide a specific perspective;

[0084] Node attributes are descriptive properties that every node possesses. These attributes define the characteristics of the node, including but not limited to:

[0085] NodeId: A unique identifier;

[0086] NodeClass: The type of the node (such as object, variable, method, etc.);

[0087] BrowseName: The name used for browsing;

[0088] DisplayName: The name used for display;

[0089] Description: Text describing the purpose of the node;

[0090] References: A list of references pointing to other nodes;

[0091] Value: For variable nodes, this attribute contains the current value of the variable;

[0092] DataType: For variable nodes, this attribute defines the type of the value;

[0093] Node relationship references are associations between nodes. They define the structure and relationships between nodes, and references have type and direction. References allow the construction of hierarchical structures and define how nodes are related to each other in the address space.

[0094] S2-1-3: Based on nodes, node attributes, and node relationships, construct the OPC UA information model of the physical entity, extract the model metadata of the OPC UA information model, which defines the structure of the information model, including objects, variables, methods, references, etc., and send it to the OPC UA server.

[0095] S2-2: Deploy an OPC UA server in the cloud data center, and create a corresponding OPC UA instance in the address space of the OPC UA server according to the OPC UA information model, including the following steps:

[0096] S2-2-1: Deploy an OPC UA server in the cloud data center and collect model metadata of all OPC UA information models during initialization;

[0097] S2-2-2: Based on the model metadata, create the corresponding OPC UA instance in the address space of the OPC UA server;

[0098] S2-3: Transmit the real-time monitoring data to the OPC UA server in the cloud data center, write it to the corresponding OPC UA instance, and extract the real-time information data from the OPC UA instance, including the following steps:

[0099] S2-3-1: Using a data acquisition device, real-time monitoring data is uploaded to the OPC UA server in the cloud data center according to the OPC UA protocol;

[0100] S2-3-2: Encapsulate the real-time node values ​​and real-time node attribute values ​​in the real-time monitoring data to obtain the corresponding real-time node encapsulated data;

[0101] S2-3-3: Write service using OPC UA protocol to write real-time node encapsulated data to the node of OPC UA instance;

[0102] S2-3-4: When the preset data collection period arrives, extract the graph structure data of the OPC UA instance according to the preset subscription service, including the real-time node values ​​and real-time node attribute values ​​of the nodes and the node relationships between the nodes, to obtain real-time information data in Extensible Markup Language (XML) format;

[0103] S2-4: Convert real-time information data into a data stream, input the data stream into the digital entity corresponding to the physical entity, and set up a visualization interface for the digital entity to obtain an integrated map digital twin model;

[0104] By constructing a unified OPC UA information model, standardized conversion between different data sources is achieved, simplifying the data processing flow and improving processing efficiency. Through the data interaction processing flow between the data acquisition device and the OPC UA server, it is possible to quickly respond to the writing and querying of real-time data and meet real-time requirements.

[0105] S3: Perform anomaly detection on the data stream, obtain real-time anomaly detection results, and use an integrated map digital twin model to visualize the data stream and real-time anomaly detection results, including the following steps:

[0106] S3-1: Input the data stream of digital entities into an anomaly detection model built based on deep learning algorithms, perform anomaly detection on the data stream, and obtain real-time anomaly detection results of digital entities;

[0107] The anomaly detection model is built based on the Graph Convolutional Network (GCN)-Random Forest (RF) algorithm, and the anomaly detection model includes a graph feature extraction module built based on the GCN algorithm and an anomaly detection module built based on the RF algorithm, which are connected in sequence.

[0108] The graph feature extraction module is used to extract real-time graph features corresponding to real-time information data in XML format. Real-time information data in XML format can be used to characterize the graph structure information of OPC UA instance. A graph is a mathematical structure composed of nodes (or vertices) and edges. XML files can define custom tags to represent nodes and edges in the graph. In this embodiment, in order to accurately characterize the graph structure information of OPC UA instance, graph structure restoration is required first.

[0109] The anomaly detection module filters the input graph features through its internal Classification and Regression Tree (CART), which can process a large number of features and select the most stable and discriminative graph feature components, and perform anomaly detection based on the graph feature components.

[0110] The process involves inputting the data stream of digital entities into an anomaly detection model built based on a deep learning algorithm, performing anomaly detection on the data stream, and obtaining real-time anomaly detection results for the digital entities. This includes the following steps:

[0111] S3-1-1: Based on real-time information data, the graph structure is restored to obtain the corresponding real-time OPC UA information graph, and the real-time OPC UA information graph is input into the graph feature extraction module of the anomaly detection model;

[0112] S3-1-2: Use the graph feature extraction module to extract real-time graph features from the real-time OPC UA information graph, and input the real-time graph features into the anomaly detection module of the anomaly detection model;

[0113] S3-1-3: Using the anomaly detection module, extract several real-time key graph feature components from the real-time graph features, and perform anomaly detection based on these real-time key graph feature components to obtain the real-time anomaly detection results for digital entities. This includes the following steps:

[0114] S3-1-3-1: Using the RF structure trained in the anomaly detection module, extract the feature contribution of M real-time candidate graph feature components from the real-time graph features, where M is the number of key graph feature components.

[0115] The formula is:

[0116]

[0117] In the formula, For the first Feature contribution of feature components in real-time candidate images; For the first Real-time candidate graph feature components in random forest The feature contribution of each tree; For CART tree indicators; This is a real-time indicator of the feature components of the candidate image; Total number of CARTs;

[0118]

[0119] In the formula, CART tree nodes in a random forest m ,node and nodes The Gini index; CART tree node m Medium category The proportion; Total number of categories; m , , For node indication; For category indicators;

[0120] S3-1-3-2: Normalize the feature contribution of the M real-time candidate image feature components to obtain several normalized feature contribution values.

[0121] The formula is:

[0122]

[0123] In the formula, The feature contribution after normalization; J This represents the total number of feature components in the real-time candidate image.

[0124] S3-1-3-3: Generate feature selection criteria values ​​for several real-time candidate image feature components based on the normalized feature contribution.

[0125] The formula is:

[0126]

[0127] In the formula, For the first Feature selection criteria values ​​for feature components in real-time candidate images; For the first Feature contribution of real-time candidate image feature components after normalization; This is a real-time indicator of the feature components of the candidate image;

[0128] S3-1-3-4: Based on the feature selection standard value, sort the real-time candidate map feature components in descending order of power, and select the top M real-time candidate map feature components as real-time key map feature components to obtain M real-time key map feature components.

[0129] S3-1-3-5: Based on several real-time key map feature components, perform anomaly detection to obtain real-time anomaly detection results for digital entities;

[0130] S3-2: If the real-time anomaly detection result indicates the presence of an anomaly, then generate a corresponding real-time alarm signal based on the real-time anomaly detection result;

[0131] S3-3: Display the data stream, real-time anomaly detection results, and real-time alarm signals in the visualization interface of the digital entity corresponding to the integrated map digital twin model;

[0132] The anomaly detection model can effectively identify anomalies in the data stream and visualize them through an integrated map digital twin model, providing strong technical support for real-time monitoring and early warning.

[0133] Example 2:

[0134] like Figure 2 As shown, this embodiment provides a two-dimensional and three-dimensional integrated map display system for realizing a two-dimensional and three-dimensional integrated map display method. The system includes a cloud data center and several data acquisition devices, and the cloud data center is communicatively connected to the several data acquisition devices.

[0135] The data acquisition device is used to collect real-time monitoring data of physical entities and send the real-time monitoring data of physical entities to the cloud data center according to the OPC UA protocol.

[0136] The cloud data center is equipped with sequentially connected 3D reconstruction units, digital twin construction units, and map display units;

[0137] The 3D reconstruction unit is used to construct an integrated map simulation model based on 2D and 3D geographic information data and using 3D reconstruction algorithms.

[0138] The digital twin building unit is used to generate the data stream of digital entities in the integrated map simulation model based on the real-time monitoring data of physical entities and using the OPC UA communication scheme, and obtain the integrated map digital twin model.

[0139] The map display unit is used to detect anomalies in the data stream, obtain real-time anomaly detection results, and use an integrated map digital twin model to visualize the data stream and real-time anomaly detection results.

[0140] This invention discloses a method and system for integrated 2D and 3D map display. By constructing an integrated map simulation model using a 3D reconstruction algorithm that combines 2D and 3D data fusion, it achieves the conversion from 2D data to a precise 3D model, effectively integrating the rich information of 2D data with the stereoscopic perception of the 3D model, providing a comprehensive spatial information view. The integrated map digital twin model enables real-time digital twin monitoring and display. Data from physical entities is collected in real time through the OPC UA information model and integrated into the digital twin model, achieving real-time synchronization between the physical world and the digital copy. This provides intuitive and efficient integration and display while significantly improving the efficiency of monitoring and decision support. In constructing the integrated map simulation model, a high-precision 3D reconstruction and correction algorithm is introduced. Real 3D data is used to accurately correct the initial 3D model, ensuring a high degree of consistency between the digital twin model and the actual physical entities, reducing deviations from reality, improving automation, avoiding extensive manual intervention, and reducing the possibility of errors.

[0141] This invention is not limited to the optional embodiments described above, and anyone can derive other various forms of products based on the teachings of this invention. The specific embodiments described above should not be construed as limiting the scope of protection of this invention; the scope of protection of this invention should be determined by the claims, and the specification can be used to interpret the claims.

Claims

1. A method for displaying integrated 2D and 3D maps, characterized in that: Includes the following steps: Based on cloud data centers, and using 2D and 3D geographic information data, an integrated map simulation model is constructed using 3D reconstruction algorithms. The aforementioned two-dimensional and three-dimensional geographic information data includes two-dimensional geographic information data and three-dimensional geographic information data; The two-dimensional geographic information data includes two-dimensional spatial data, two-dimensional attribute data, and two-dimensional metadata; The aforementioned three-dimensional geographic information data includes three-dimensional spatial data, three-dimensional attribute data, and three-dimensional metadata; Based on cloud data centers and using 2D and 3D geographic information data, an integrated map simulation model is constructed using 3D reconstruction algorithms, including the following steps: Based on the cloud data center, the two-dimensional and three-dimensional geographic information data of the target area are collected and analyzed to obtain the two-dimensional and three-dimensional geographic information data of the target area. Based on two-dimensional geographic information data, a three-dimensional reconstruction model built using a deep learning algorithm is used to perform three-dimensional reconstruction, resulting in an initial integrated map simulation model. The three-dimensional reconstruction model is constructed based on the CNN-Elman-GAN algorithm, and the three-dimensional reconstruction model includes a two-dimensional feature extraction module based on the CNN algorithm, an object detection module based on the Elman algorithm, and a three-dimensional reconstruction module based on the GAN algorithm, which are connected in sequence. Based on two-dimensional geographic information data, a three-dimensional reconstruction model constructed using a deep learning algorithm is used to perform three-dimensional reconstruction, resulting in an initial integrated map simulation model. The process includes the following steps: The two-dimensional feature extraction module is used to extract the two-dimensional data features of the two-dimensional geographic information data, and the two-dimensional data features are then input into the target detection module. The target detection module is used to detect targets based on two-dimensional data features, obtain the physical targets corresponding to the physical entities, extract the two-dimensional data features of the corresponding physical targets, and input them into the three-dimensional reconstruction module. Using the 3D reconstruction module, based on the 2D data features of the entity target, 3D reconstruction is performed to obtain the 3D model of the entity target corresponding to the digital entity. By integrating the 3D models of all entity targets and the 2D geographic information data, an initial integrated map simulation model containing several digital entities is obtained. Based on the three-dimensional geographic information data, the initial integrated map simulation model is corrected to obtain the final integrated map simulation model. Based on real-time monitoring data of physical entities, the OPC UA communication scheme is used to generate data streams of digital entities in the integrated map simulation model, and an integrated map digital twin model is obtained. Anomaly detection is performed on the data stream to obtain real-time anomaly detection results, and an integrated map digital twin model is used to visualize the data stream and the real-time anomaly detection results.

2. The method for displaying a two-dimensional and three-dimensional integrated map according to claim 1, characterized in that: Based on 3D geographic information data, the initial integrated map simulation model is revised to obtain the final integrated map simulation model, including the following steps: Using a feature point extraction algorithm, several first feature points from the 3D geographic information data and several second feature points from the initial integrated map simulation model are extracted. Using a feature point matching algorithm, feature point matching is performed on several first feature points and several second feature points to obtain several matching feature point pairs; Based on several matching feature point pairs, the matching area of ​​the initial integrated map simulation model is corrected using 3D geographic information data to obtain the final integrated map simulation model.

3. The method for displaying a two-dimensional and three-dimensional integrated map according to claim 1, characterized in that: Based on real-time monitoring data of physical entities, the OPC UA communication scheme is used to generate data streams of digital entities in the integrated map simulation model, resulting in an integrated map digital twin model. This process includes the following steps: Based on the entity targets output by the 3D reconstruction model, collect real-time monitoring data of the corresponding physical entities, and construct the corresponding OPC UA information model based on the real-time monitoring data. Deploy an OPC UA server in the cloud data center and create a corresponding OPC UA instance in the address space of the OPC UA server according to the OPC UA information model; The real-time monitoring data is transmitted to the OPC UA server in the cloud data center, written to the corresponding OPC UA instance, and the real-time information data of the OPC UA instance is extracted. Real-time information data is converted into a data stream, the data stream is input into the digital entity corresponding to the physical entity, and a visualization interface is set for the digital entity to obtain an integrated map digital twin model.

4. The method for displaying a two-dimensional and three-dimensional integrated map according to claim 3, characterized in that: Anomaly detection is performed on the data stream to obtain real-time anomaly detection results. An integrated map digital twin model is then used to visualize the data stream and the real-time anomaly detection results. This process includes the following steps: The data stream of digital entities is input into an anomaly detection model built based on deep learning algorithms to perform anomaly detection on the data stream and obtain real-time anomaly detection results for digital entities. If the real-time anomaly detection result indicates the presence of an anomaly, a corresponding real-time alarm signal will be generated based on the real-time anomaly detection result. The data stream, real-time anomaly detection results, and real-time alarm signals are displayed in the visualization interface of the digital entity corresponding to the integrated map digital twin model.

5. The method for displaying a two-dimensional and three-dimensional integrated map according to claim 4, characterized in that: The anomaly detection model is constructed based on the GCN-RF algorithm, and the anomaly detection model includes a graph feature extraction module constructed based on the GCN algorithm and an anomaly detection module constructed based on the RF algorithm, which are connected in sequence.

6. A two-dimensional and three-dimensional integrated map display system, used to implement the two-dimensional and three-dimensional integrated map display method as described in any one of claims 1-5, characterized in that: The system includes a cloud data center and several data acquisition devices, with the cloud data center being communicatively connected to each of the several data acquisition devices. The cloud data center is equipped with sequentially connected 3D reconstruction units, digital twin construction units, and map display units.

Images