3D Modeling Methods and Systems for High-Rise Curtain Walls

Abstract

This invention relates to the field of Building Information Modeling (BIM) technology, and particularly to a method and system for 3D modeling of high-rise curtain walls. It utilizes multispectral data, structured light scanning data, and thermal imaging data collected by drones, performs multidimensional analysis and fusion of the data, and employs a multimodal feature fusion algorithm for 3D modeling. Furthermore, it utilizes dynamic feedback and recursive optimization mechanisms to perform global and local geometric corrections, material feature optimization, and thermal feature correction on the model. Finally, a high-precision 3D model data is generated through a multi-channel fusion algorithm. This invention effectively solves the problems of insufficient geometric accuracy, limited material processing, and neglect of thermal features in existing technologies, significantly improving the accuracy and realism of the model. It is applicable to fields such as architectural design, structural analysis, and energy consumption assessment.

Description

Technical Field

[0001] This invention relates to the field of Building Information Modeling (BIM) technology, and in particular to a three-dimensional modeling method and system for high-rise curtain walls. Background Technology

[0002] High-rise curtain walls, as the exterior walls of modern high-rise buildings, play a vital role not only in aesthetics but also in the building's structural integrity. 3D modeling of high-rise curtain walls is significant in various aspects, including architectural design, structural analysis, and maintenance management. Through accurate 3D modeling, designers can simulate the curtain wall's lighting effects, structural strength, and thermodynamic behavior under different climatic conditions. Furthermore, 3D models play a crucial role in the construction, cleaning, and maintenance of buildings, enabling the early identification of potential structural problems and the development of effective solutions.

[0003] Currently, the 3D modeling method for high-altitude curtain walls (Chinese invention patent, publication number: CN117893681A, title: 3D Modeling and Image Transmission Method for High-altitude Curtain Walls) mainly relies on drones to acquire images and then remotely transmit them to an image processing system for modeling. Existing technologies employ image acquisition, remote transmission, contour modeling, local feature scanning, and 3D wireframe model generation. While this method can automatically generate 3D models, it suffers from the following main drawbacks:

[0004] Due to the limitations of image acquisition equipment in terms of resolution and angle, the geometric accuracy of the model is easily affected, especially in complex curved surfaces and connection point areas, where the error is relatively large.

[0005] Existing technologies mainly focus on texture rendering when processing materials, lacking fine processing of details such as the optical properties, reflection, and refraction of materials, resulting in the final model not being visually realistic enough.

[0006] Existing technologies hardly consider the thermal characteristics of curtain walls, which makes it impossible for models to simulate the behavior of curtain walls under different temperature conditions, thus limiting the application of models in energy consumption analysis and thermodynamic simulation.

[0007] Existing 3D modeling workflows are mostly linear processes, lacking coordinated optimization between steps, resulting in inconsistencies in geometry, materials, and thermal features in the final model. Summary of the Invention

[0008] To address the numerous problems existing in the prior art, this invention provides a 3D modeling method and system for high-altitude curtain walls. This invention utilizes unmanned aerial vehicles (UAVs) to collect multimodal data (including geometric, material, and thermal imaging data), and employs a multimodal feature fusion algorithm to deeply fuse and optimize this data. Through dynamic feedback and recursive optimization mechanisms, a high-precision 3D model is generated. This model is not only geometrically accurate but also realistically reproduces the material characteristics and thermal response of the curtain wall, making it suitable for applications such as architectural design, structural analysis, and energy consumption assessment.

[0009] A three-dimensional modeling method for high-altitude curtain walls includes the following steps:

[0010] Multispectral data, structured light scanning data, and thermal imaging data of the high-altitude curtain wall are collected by drones. The collected data are processed synchronously in time and space, and pre-processed fused data is generated through preliminary fusion.

[0011] The preprocessed fused data is subjected to multidimensional cross-analysis to extract geometric structure data, material feature data and thermal feature data in sequence, and fused feature data is generated through hierarchical feature fusion and dynamic feedback optimization.

[0012] Based on the fused feature data, a three-dimensional model is performed using a multimodal feature fusion algorithm, which deeply fuses the geometric structure data, the material feature data, and the thermal feature data, while generating optimized model data using real-time feedback and recursive optimization mechanisms.

[0013] The optimized model data is subjected to global geometric correction, local geometric refinement correction, material feature optimization and thermal feature correction, and the final corrected and optimized model data is generated through multi-dimensional collaborative optimization.

[0014] Based on the final corrected and optimized model data, geometric structure rendering, material feature rendering, and thermal feature rendering are performed, and the final three-dimensional model data is generated through a multi-channel fusion algorithm.

[0015] Preferably, the multidimensional cross-analysis includes the following steps:

[0016] The geometric structure data in the preprocessed fusion data is initially analyzed to generate preliminary geometric structure data. Combined with material feature data and thermal feature data, the boundary accuracy of the geometric structure data is optimized through multidimensional cross-analysis to generate geometric feature point data. The preliminary geometric structure data is further optimized using the geometric feature point data to generate optimized geometric structure data.

[0017] Preferably, the extraction of the material feature data includes the following steps:

[0018] The material information in the preprocessed fused data is subjected to light reflection analysis, refraction analysis and surface texture analysis to generate material optical feature data. The material optical feature data is then coupled with the optimized geometric structure data to further optimize the material feature data and generate optimized material feature data.

[0019] Preferably, the extraction of the thermal feature data includes the following steps:

[0020] Thermal gradient analysis is performed on the thermal imaging information in the preprocessed fused data. Combined with the optimized geometric structure data and optimized material optical feature data, thermal feature model data is generated through thermal feature modeling algorithm. The thermal feature model data is then corrected and optimized in real time using a dynamic feedback mechanism to generate optimized thermal feature data.

[0021] Preferably, the multimodal feature fusion algorithm includes the following steps:

[0022] The optimized geometric structure data, optimized material feature data, and optimized thermal feature data are weighted and fused, where:

[0023] Weighting coefficient W1 is used to represent the importance of geometric structure data; weighting coefficient W2 is used to represent the importance of material characteristic data; weighting coefficient W3 is used to represent the importance of thermal characteristic data.

[0024] The weight coefficients are dynamically adjusted through a recursive optimization mechanism to generate optimized model data.

[0025] Preferably, the specific expression for the weighted fusion calculation is:

[0026] M final =W1×G+W2×M+W3×T

[0027] Among them, M final G represents the optimized model data; M represents the optimized material feature data; T represents the optimized thermal feature data; W1, W2 and W3 represent the weight coefficients of the geometric structure data, material feature data and thermal feature data, respectively.

[0028] Preferably, the global geometric correction includes the following steps:

[0029] Based on the optimized model data, the macroscopic geometry of the 3D model is globally optimized. The global optimization algorithm is used to detect and eliminate macroscopic geometric errors. Global correction geometric model data is generated by adjusting the spatial position, scale and angle of the overall shape of the model.

[0030] Preferably, the local geometric refinement correction includes the following steps:

[0031] Local optimization is performed on the detailed regions in the global calibration geometric model data. The local geometric errors are corrected by the detail enhancement algorithm, and the key regions are refined by the micro-adjustment algorithm to generate the final geometric calibration model data.

[0032] Preferably, the multi-channel fusion algorithm includes the following steps:

[0033] The final geometric correction model data, optimized material feature data, and optimized thermal feature data are rendered independently. The geometric structure is rendered through the geometry channel, the material features are rendered through the material channel, and the thermal effects are rendered through the thermal feature channel. The rendering results of each channel are then fused together to generate the final 3D model data.

[0034] A system for implementing a three-dimensional modeling method for the high-altitude curtain wall includes:

[0035] The data acquisition module is used to collect multispectral data, structured light scanning data and thermal imaging data of the high-altitude curtain wall through drones, and to process the collected data synchronously in time and space to generate preprocessed fused data;

[0036] The data parsing and feature extraction module is used to perform multi-dimensional cross-analysis on the preprocessed fused data, sequentially extracting geometric structure data, material feature data and thermal feature data, and generating fused feature data through hierarchical feature fusion and dynamic feedback optimization.

[0037] The 3D modeling and feature fusion module is used to perform 3D modeling based on fused feature data and through multimodal feature fusion algorithms. It deeply fuses geometric structure data, material feature data and thermal feature data, and generates optimized model data using real-time feedback and recursive optimization mechanisms.

[0038] The calibration and optimization module is used to perform global geometric calibration, local geometric refinement calibration, material feature optimization, and thermal feature calibration on the optimized model data, and generates the final calibrated and optimized model data through multi-dimensional collaborative optimization.

[0039] The rendering and output module is used to perform geometric rendering, material feature rendering, and thermal feature rendering based on the final corrected and optimized model data, and to generate the final 3D model data through a multi-channel fusion algorithm.

[0040] Compared with the prior art, the advantages and beneficial effects of the present invention are as follows:

[0041] This invention achieves deep fusion of geometric structure, material features and thermal features through a multimodal feature fusion algorithm, generating a more accurate and realistic 3D model;

[0042] This invention achieves real-time correction and optimization of the model through dynamic feedback and recursive optimization mechanisms, ensuring the accuracy of the model in different application scenarios;

[0043] This invention achieves comprehensive and coordinated optimization of geometry, material properties, and thermal characteristics through multi-dimensional collaborative optimization technology, enabling the model to achieve optimal results in all dimensions. Attached Figure Description

[0044] Figure 1 This is a schematic flowchart of the method of the present invention;

[0045] Figure 2 This is a schematic diagram of the data collection process using a drone in this invention;

[0046] Figure 3 This is a schematic diagram of the multimodal feature fusion algorithm in this invention;

[0047] Figure 4 This is a schematic diagram of the multi-channel fusion algorithm in this invention;

[0048] Figure 5 This is a structural block diagram of the system of the present invention. Detailed Implementation

[0049] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0050] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0051] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0052] like Figure 1 As shown, a three-dimensional modeling method for high-altitude curtain walls includes the following steps:

[0053] like Figure 2As shown, multispectral data, structured light scanning data, and thermal imaging data of the high-altitude curtain wall are collected by drones, and the collected data are processed synchronously in time and space. Pre-processed fused data is generated through preliminary fusion.

[0054] A multispectral camera mounted on a drone is used to acquire multispectral data of the high-altitude curtain wall. Multispectral data covers multiple spectral ranges, including visible and non-visible light (such as near-infrared and ultraviolet light), revealing the reflection, absorption, and transmission characteristics of the curtain wall material at different wavelengths. These spectral characteristics are crucial for identifying and distinguishing different components of the curtain wall material, especially in detecting potential subtle differences and defects on the curtain wall surface. For example, by analyzing the near-infrared spectrum, the uniformity of the curtain wall surface coating and potential degradation areas can be identified, providing essential data support for subsequent material feature extraction and thermal feature analysis.

[0055] Structured light scanning technology, implemented using structured light scanning equipment mounted on a drone, works by projecting a beam of light with a known pattern, such as stripes or a grid, onto the surface of the curtain wall and capturing the deformation of the beam on the surface using a camera. Using these deformed patterns, high-precision 3D geometric data can be reconstructed, capturing details such as the complex geometry of the curtain wall, surface irregularities, and edge features. This is crucial for generating accurate geometric models, ensuring the accuracy of the model in shape, size, and spatial location. For example, in practice, structured light scanning can detect minute deformations and damaged areas on the curtain wall surface; this information is essential for subsequent global geometric correction and local refinement.

[0056] Thermal imaging technology uses drones equipped with thermal imaging cameras to collect thermal data and capture the temperature distribution on the surface of curtain walls. The principle of thermal imaging is based on the fact that objects emit different intensities of infrared radiation at different temperatures; thermal imaging cameras can convert this radiation difference into a visualized temperature distribution map. By analyzing this temperature data, areas of thermal anomaly in the curtain wall structure can be detected, such as insulation degradation or thermal bridging effects. This thermal characteristic information is very helpful in assessing the thermodynamic performance of curtain walls and potential structural problems. In practical applications, thermal imaging technology can identify material fatigue or cracks caused by temperature gradients, allowing for targeted corrections and optimizations during the modeling process.

[0057] After the aforementioned data acquisition is completed, temporal and spatial synchronization processing is required. The principle behind this step is that, since multispectral data, structured light scanning data, and thermal imaging data are acquired at different times and from different perspectives, these data must be aligned and corrected to ensure their consistency in the spatial coordinate system. This synchronization processing can be achieved through image registration techniques and sensor fusion algorithms, ensuring that all data matches the actual geometric position of the curtain wall, thereby avoiding model deviations or errors caused by data misalignment. In effect, temporal and spatial synchronization processing significantly improves the fusion quality of multi-source data, ensuring the accuracy of subsequent modeling processes.

[0058] Through a preliminary fusion step, the synchronously processed multispectral data, structured light scanning data, and thermal imaging data are initially fused to generate preprocessed fused data. This fusion process involves weighted summarization and feature extraction of information from different data sources to generate a preliminary multidimensional dataset. In principle, preliminary fusion combines key information such as geometry, material properties, and thermal characteristics to form a more complete description, which plays a fundamental role in subsequent multidimensional cross-analysis and feature extraction. In terms of effect, the preliminary fused data retains important features from each data source while removing redundant information, providing the necessary data foundation for subsequent high-precision modeling.

[0059] The preprocessed fused data is subjected to multidimensional cross-analysis to extract geometric structure data, material feature data and thermal feature data in sequence, and fused feature data is generated through hierarchical feature fusion and dynamic feedback optimization.

[0060] Multidimensional cross-analysis is a process of cross-validating and optimizing data sources from different sensors. Its core lies in improving the accuracy and reliability of the data by analyzing the interrelationships between geometric structure, material characteristics, and thermal characteristics in the preprocessed fused data. In the preprocessed fused data, geometric structure data, material characteristic data, and thermal characteristic data reflect the spatial morphology, material properties, and temperature distribution of the curtain wall, respectively, and these information are interconnected in physical space. Through multidimensional cross-analysis, one type of characteristic data (such as geometric data) can be used to correct and optimize other characteristic data (such as material and thermal characteristics), thereby eliminating biases caused by incomplete or inaccurate data. For example, during implementation, the precise boundaries of the geometric structure data can correct errors in the material characteristic data caused by uneven reflected light, thus improving the accuracy of the material characteristics.

[0061] After multi-dimensional cross-analysis, geometric structure data, material feature data, and thermal feature data are extracted sequentially. The purpose of extracting geometric structure data is to obtain the precise three-dimensional shape of the curtain wall, including key geometric information such as contours, edges, and surface details. This information forms the basis of 3D modeling, ensuring that the model is spatially consistent with the actual curtain wall. The extraction of material feature data focuses on the optical properties and texture features of the curtain wall surface, such as reflectivity, transparency, and surface roughness. These features directly affect the model's visual appearance and lighting effects. The extraction of thermal feature data is used to capture the temperature distribution and thermal effects of the curtain wall surface, helping to identify the material's thermal response and potential structural problems. In practical applications, the sequential extraction of these feature data ensures that each type of data is accurately extracted under the most suitable analytical conditions, thereby improving the overall realism of the model.

[0062] After extracting the feature data, hierarchical feature fusion and dynamic feedback optimization are used to generate the final fused feature data. Hierarchical feature fusion refers to fusing geometric structure, material features, and thermal features in a hierarchical manner according to the importance and priority of the feature data. Typically, geometric structure data serves as the base layer, initially establishing the skeleton of the model. Subsequently, material feature data and thermal feature data are superimposed on the geometric structure to form a multi-dimensional comprehensive feature model. This hierarchical fusion approach ensures that each type of feature data retains its unique attributes during the fusion process while forming a close collaborative relationship with other data.

[0063] Dynamic feedback optimization plays a crucial role in this process. In principle, dynamic feedback optimization monitors intermediate data generated during the fusion process in real time and adjusts the fusion process accordingly. For example, when fusing material feature data, if a material change due to thermal effects is detected, this information is immediately fed back to the fusion algorithm to adjust the weights of the material feature data and the fusion strategy, ensuring that the final fused feature data accurately reflects the curtain wall's performance under different conditions. Through this dynamic feedback mechanism, the system can adaptively optimize the fusion strategy, significantly improving the accuracy and consistency of the final model.

[0064] This step generates fused feature data that not only includes the curtain wall's complete geometric information, material properties, and thermal effect characteristics, but also eliminates contradictions and inconsistencies between various data sources through multi-dimensional cross-analysis and dynamic feedback optimization, forming a highly accurate and consistent 3D model foundation. This provides a solid foundation for subsequent modeling and rendering, ensuring that the final 3D model achieves optimal levels of visual effect and physical consistency.

[0065] Preferably, the multidimensional cross-analysis includes the following steps:

[0066] The geometric structure data in the preprocessed fusion data is initially analyzed to generate preliminary geometric structure data. Combined with material feature data and thermal feature data, the boundary accuracy of the geometric structure data is optimized through multidimensional cross-analysis to generate geometric feature point data. The preliminary geometric structure data is further optimized using the geometric feature point data to generate optimized geometric structure data.

[0067] Preliminary analysis is performed on the geometric structure data in the preprocessed fused data. The principle of this preliminary analysis lies in identifying the basic geometric shape and main structural features of the curtain wall through analytical algorithms. The preliminary geometric structure data generated in this step includes the approximate outline and key geometric elements of the curtain wall, such as panel edges, connection points, and surface curvature. However, due to noise, obstruction, or resolution limitations that may exist during data acquisition and preliminary processing, the preliminary geometric structure data often contains certain errors or incompleteness, thus requiring further optimization and correction.

[0068] By combining material and thermal feature data with preliminary geometric structure data, multidimensional cross-analysis is used to optimize the boundary accuracy of the geometric structure data. The principle of multidimensional cross-analysis lies in utilizing the inherent correlations between different feature data to further correct errors in the geometric structure data. For example, material feature data can provide information about the surface texture and material distribution of the curtain wall. By analyzing this information, boundary regions in the geometric structure data can be identified and refined. Similarly, thermal feature data, by reflecting the temperature distribution of the curtain wall surface, can reveal the influence of material thermal expansion or contraction on the geometry, thereby correcting the boundaries of the geometric structure data. For example, in practice, if thermal feature data shows that a certain part of the curtain wall has undergone slight deformation due to thermal expansion and contraction, this information can be used to correct the geometric data, making the model more accurate under thermodynamic conditions.

[0069] Geometric feature point data generated through multidimensional cross-analysis is crucial for optimizing geometric structure data. These feature points represent important nodes and boundaries in the curtain wall geometry, acting as the skeleton of the model and determining its overall shape and detailed representation. For example, feature points may include panel connection points, edge intersections, and key inflection points on curved surfaces. During model building, these geometric feature points serve as the basis for further optimization, ensuring the model's accuracy in these critical areas.

[0070] The preliminary geometric structure data is further optimized using geometric feature point data to generate optimized geometric structure data. The optimization process works by adjusting and refining the entire geometric model based on the feature points through interpolation, curve fitting, or feature point-based mesh refinement techniques. This optimization step effectively eliminates discontinuities and errors in the preliminary geometric structure data, resulting in clearer boundaries and more accurate shapes for the geometric model. For example, in practice, interpolation algorithms can be used to smooth the surface of the geometric structure, making edge transitions more natural, while mesh refinement techniques can add more mesh nodes around the feature points, improving the model's resolution and accuracy.

[0071] The optimized geometric data generated through the above steps possesses high accuracy and consistency, laying a solid foundation for subsequent 3D modeling and rendering. This process not only ensures the morphological accuracy of the geometric model but also, by combining material and thermal characteristic data, enables the model to reflect the realistic performance of the curtain wall under different environmental conditions, thereby enhancing the model's application value. In fields such as building structure analysis, thermodynamic research, and visual simulation, the optimized geometric data provides a more reliable reference, making subsequent analysis and decision-making more accurate.

[0072] Preferably, the extraction of the material feature data includes the following steps:

[0073] The material information in the preprocessed fused data is subjected to light reflection analysis, refraction analysis and surface texture analysis to generate material optical feature data. The material optical feature data is then coupled with the optimized geometric structure data to further optimize the material feature data and generate optimized material feature data.

[0074] Light reflection analysis is performed on the material information in the preprocessed and fused data. The principle of light reflection analysis is to determine the optical properties of the material, such as reflectivity, gloss, and specular reflection ratio, by calculating and measuring the reflection characteristics of the curtain wall surface to different light sources. These optical properties directly affect the visual effect of the model. For example, materials with high reflectivity will exhibit more obvious highlights and reflections under different lighting conditions, while materials with low reflectivity will appear matte or diffused. In practical applications, by performing light reflection analysis on the preprocessed and fused data, the reflection characteristics of curtain wall materials under different lighting conditions can be accurately extracted. For example, the reflection characteristics of glass curtain walls used on building facades can accurately reflect changes in ambient light, thus exhibiting a realistic reflection effect in the 3D model.

[0075] Refractive analysis studies the propagation path of light within a material to determine its refractive index and transmittance. The principle of refractive analysis is based on the phenomenon that light's propagation direction is deflected when it enters a medium of different densities. For transparent or translucent materials used in high-rise building facades, such as glass or polymers, refractive properties are a crucial factor determining their visual appearance. Through refractive analysis, the path of light within these materials can be accurately calculated, generating refractive index data. In practice, refractive analysis reveals the light transmission effect and internal refraction phenomena of glass facades, enabling the model to realistically reproduce the transmitted image of light passing through the glass, thereby enhancing the model's realism and visual impact.

[0076] Surface texture analysis involves analyzing the microstructure of a curtain wall surface to obtain information about the material's surface roughness, texture direction, and detailed features. The principle behind surface texture analysis is to reconstruct the material's texture pattern and details through scanning and data processing of the material's surface microstructure. Different surface textures significantly affect the material's visual appearance; for example, rough surfaces produce more diffuse reflection, while smooth surfaces produce stronger specular reflection. In practice, surface texture analysis can generate texture pattern data for the curtain wall surface and apply it to the model, ensuring realistic reproduction of surface details. For instance, the subtle brushed texture of a metal curtain wall can be accurately simulated through this process, enhancing the model's texture and visual appeal.

[0077] Through the above light reflection analysis, refraction analysis, and surface texture analysis, material optical characteristic data is generated. This data contains the complete optical properties of the material, reflecting the performance of the curtain wall under different lighting and viewing angles. However, to ensure a perfect match between the material characteristic data and the geometric model, the material optical characteristic data must be coupled with the optimized geometric structure data for calculation. The principle of coupling calculation is that by tightly combining material features with geometry, the material properties can be represented in a precise geometric coordinate system. This process can eliminate material performance deviations caused by geometric errors or misalignments. For example, by coupling the refractive index data with the geometric model of the glass curtain wall, it can be ensured that light exhibits accurate refraction effects when passing through glass of different thicknesses, thereby enhancing the realism of the model.

[0078] Through coupled computation and further optimization, optimized material feature data is generated. This optimization process ensures a high degree of consistency between the material feature data and the geometric structure data, and eliminates any potential discontinuities or errors by adjusting the spatial distribution of the material features. In effect, the optimized material feature data not only improves the model's visual appeal but also ensures its accuracy in physical simulations. For example, in thermodynamic analysis, accurate material feature data can precisely reflect the material's thermal response, thereby improving the reliability of the analysis.

[0079] Preferably, the extraction of the thermal feature data includes the following steps:

[0080] Thermal gradient analysis is performed on the thermal imaging information in the preprocessed fused data. Combined with the optimized geometric structure data and optimized material optical feature data, thermal feature model data is generated through thermal feature modeling algorithm. The thermal feature model data is then corrected and optimized in real time using a dynamic feedback mechanism to generate optimized thermal feature data.

[0081] Thermal gradient analysis is a preliminary step in thermal feature data extraction. The principle of thermal gradient analysis is based on temperature distribution data from thermal imaging to calculate the temperature gradient across different areas of the curtain wall surface. The temperature gradient refers to the rate of temperature change in space, revealing the thermal conductivity and thermal stress distribution of the curtain wall in different areas. Through thermal gradient analysis, potential thermal anomaly areas on the curtain wall surface can be identified, such as thermal bridges, insulation defects, or material fatigue points. During implementation, thermal gradient analysis can accurately locate these anomaly areas, providing crucial input data for subsequent thermal feature modeling. For example, on a high-rise building curtain wall in winter, thermal imaging may show thermal bridging effects caused by indoor and outdoor temperature differences; thermal gradient analysis can accurately locate these areas, thus reflecting the true thermal response of the curtain wall in the model.

[0082] Thermal feature modeling is performed by combining optimized geometric data and optimized material optical characteristic data. The principle of thermal feature modeling lies in generating a thermal feature model that accurately reflects the characteristics of heat conduction, heat radiation, and heat convection by tightly integrating thermal imaging data with geometric and material features. Geometric data provides information on the spatial shape and structure of the curtain wall, which is crucial for determining how heat propagates on and within the curtain wall surface. Material optical characteristic data reflects the absorptivity, reflectivity, and transmittance of the material, properties that affect heat absorption and dissipation. During thermal feature modeling, these data are integrated into a unified physical model capable of simulating the thermal behavior of the curtain wall under different environmental conditions. For example, thermal feature modeling can simulate temperature changes on the curtain wall surface under sunlight and predict potential areas of thermal stress concentration, which is significant for building safety assessment and energy consumption optimization.

[0083] After generating the thermal characteristic model data, a dynamic feedback mechanism is used to correct and optimize the data in real time. The principle of this dynamic feedback mechanism is to monitor and analyze the performance of the thermal characteristic model under different simulation conditions in real time, and adjust the model parameters promptly to ensure the accuracy and consistency of the model. This mechanism can dynamically correct the thermal characteristic model based on new input data or deviations during model operation, avoiding errors caused by initial settings or incomplete data. For example, if the thermal conductivity coefficient of a certain material is found to be inconsistent with reality during modeling, the dynamic feedback mechanism can automatically adjust this parameter, thereby correcting the overall thermal characteristic performance of the model. In practical implementation, this mechanism can significantly improve the robustness and accuracy of the thermal characteristic model, ensuring that the generated thermal characteristic data can truly reflect the thermodynamic behavior of the curtain wall.

[0084] After correction and optimization through a dynamic feedback mechanism, optimized thermal characteristic data is generated. This optimized thermal characteristic data not only includes the accurate temperature distribution and heat conduction paths of the curtain wall under different temperature conditions, but also integrates the influence of geometric structure and material characteristics, forming a highly accurate thermal characteristic model. In practice, this data can be used to simulate the thermal stress distribution of the curtain wall under different climatic conditions, predict potential thermal fatigue zones, and optimize the building's thermal insulation performance and energy efficiency. For example, under tropical climate conditions, the optimized thermal characteristic data can be used to analyze the thermal deformation risk of the curtain wall under prolonged high-temperature exposure, thus providing important reference data for building design and maintenance.

[0085] Based on the fused feature data, a three-dimensional model is performed using a multimodal feature fusion algorithm, which deeply fuses the geometric structure data, the material feature data, and the thermal feature data, while generating optimized model data using real-time feedback and recursive optimization mechanisms.

[0086] like Figure 3 As shown, preferably, the multimodal feature fusion algorithm includes the following steps:

[0087] The optimized geometric structure data, optimized material feature data, and optimized thermal feature data are weighted and fused, where:

[0088] Weighting coefficient W1 is used to represent the importance of geometric structure data; weighting coefficient W2 is used to represent the importance of material characteristic data; weighting coefficient W3 is used to represent the importance of thermal characteristic data.

[0089] The weight coefficients are dynamically adjusted through a recursive optimization mechanism to generate optimized model data.

[0090] Multimodal feature fusion is a core algorithm that deeply integrates feature information from different data sources, such as geometric structure data, material feature data, and thermal feature data. Its principle lies in the fact that while each feature data is important in describing different aspects of a curtain wall, a single data source is insufficient to comprehensively reflect the overall state and performance of the curtain wall. Through multimodal feature fusion, these different data sources can be integrated into a unified model, forming a more comprehensive and accurate 3D model. For example, geometric structure data describes the shape and size of the curtain wall, but without combining it with material feature data, it is difficult to realistically reproduce the surface optical effects of the curtain wall; similarly, thermal feature data provides thermodynamic information, but without the support of geometric structure data, its spatial positioning may be insufficiently accurate. Therefore, multimodal feature fusion is a necessary process for 3D modeling of high-rise curtain walls, ensuring the integrity and consistency of the model by coordinating the interrelationships between different data sources.

[0091] In its implementation, the multimodal feature fusion algorithm involves weighted fusion of optimized geometric structure data, optimized material feature data, and optimized thermal feature data. The principle of weighted fusion is that, considering the varying degrees of impact of different feature data on model accuracy, a weight coefficient is assigned to each feature data to reflect its importance in the overall model. These weight coefficients are W1, W2, and W3, where W1 represents the importance of geometric structure data, W2 represents the importance of material feature data, and W3 represents the importance of thermal feature data. The weight coefficients can be adjusted according to the specific modeling requirements. For example, in an application that emphasizes geometric accuracy, the weight of W1 can be increased, while in a scenario that focuses more on material performance or thermal effects, the weights of W2 or W3 can be higher.

[0092] It's important to note that these weight coefficients are not static but dynamically adjusted through a recursive optimization mechanism. The principle of this mechanism is to iteratively adjust each weight coefficient, gradually adjusting it to achieve an optimal balance across multiple dimensions in the final model. In each iteration, the algorithm compares the expected results with the actual results based on the current model performance, and then adjusts the weight coefficients accordingly. For example, in the early iterations, if the simulation accuracy of thermal features is insufficient, the algorithm can increase the weight of W3, giving thermal feature data a more significant role in subsequent fusion. As the number of iterations increases, the various aspects of the model will tend towards balance, resulting in highly accurate and consistent optimized model data.

[0093] Through this recursive optimization mechanism, the final optimized model data not only achieves optimal performance in terms of geometry, material properties, and thermal response, but also adapts to the needs of different application scenarios. For example, in the architectural design process, the optimized model data can be used to simulate the effects of sunlight at different times, thereby helping designers optimize the building's appearance and energy efficiency; in structural safety assessments, this data can be used to predict the performance of curtain walls under extreme temperature conditions, thus providing a scientific basis for maintenance decisions.

[0094] In summary, 3D modeling using multimodal feature fusion algorithms, and the optimized model data generated through weighted fusion and recursive optimization mechanisms, plays a crucial role in the 3D modeling of high-altitude curtain walls. It not only integrates geometric, material, and thermal feature data to generate a comprehensive and accurate 3D model, but also ensures the model's efficiency and reliability in practical applications through dynamic adjustment and optimization. This approach provides strong technical support for fields such as architectural design, structural analysis, and thermodynamics research, ensuring that the model achieves optimal performance in all aspects.

[0095] Preferably, the specific expression for the weighted fusion calculation is:

[0096] M final =W1×G+W2×M+W3×T

[0097] Among them, M final G represents the optimized model data; M represents the optimized material feature data; T represents the optimized thermal feature data; W1, W2 and W3 represent the weight coefficients of the geometric structure data, material feature data and thermal feature data, respectively.

[0098] M in the formula final This refers to the final optimized model data, which is the result of weighted fusion of geometric structure data (G), material feature data (M), and thermal feature data (T). In the 3D modeling process, geometry, material, and thermal features represent the spatial morphology, surface optical properties, and thermodynamic behavior of the curtain wall, respectively. These three types of data jointly determine the accuracy and realism of the model.

[0099] G represents the optimized geometric data. Geometric data provides basic structural information about the curtain wall, including its three-dimensional shape, boundary lines, and surface curvature; this information forms the basis of modeling. Without accurate geometric data, the spatial layout and shape of the model will be inaccurate.

[0100] M represents the optimized material feature data. Material feature data includes optical properties such as reflectivity, refractive index, and surface roughness of the curtain wall surface; these attributes determine the model's visual appearance. The accuracy of the material data directly affects the model's realism and visual effects, such as the light and shadow effects under sunlight.

[0101] T represents the optimized thermal characteristic data. This data reflects the thermal response of the curtain wall material at different temperatures, such as the coefficient of thermal expansion, thermal conductivity, and temperature distribution. These characteristics are crucial for simulating the thermodynamic behavior of the curtain wall, especially under extreme environmental conditions.

[0102] The core idea of ​​weighted fusion is to assign appropriate weights to these three types of data based on their importance in different modeling tasks. In the formula, W1, W2, and W3 correspond to the weight coefficients for geometric structure, material features, and thermal features, respectively. These weight coefficients are set to balance the influence of different feature data according to specific needs when generating the final model. For example, in a modeling task focused on visual effects, the weight of material features might be higher; while in a scenario focusing on thermodynamic analysis, the weight of thermal features might increase.

[0103] In practice, weighted fusion computation is a dynamic process. A recursive optimization mechanism is used to adjust the values ​​of W1, W2, and W3, allowing the model to gradually approach its optimal state. The principle of the recursive optimization mechanism is to iteratively adjust the weight coefficients through repeated iterations and error correction, ensuring that the final model achieves the expected accuracy and performance in all aspects. For example, during initial modeling, a higher weight might be set for geometric data to ensure the accuracy of the model's basic structure; subsequently, by correcting the model's material properties and thermal response, the weights of W2 and W3 are gradually increased until the final generated model achieves a balance in terms of geometry, material properties, and thermodynamic performance.

[0104] In terms of effectiveness, weighted fusion computation ensures that the integration of multimodal data is not only physically accurate but also visually and functionally realistic. For example, in the solar radiation simulation of high-rise curtain walls, the optimized model data M... final It can accurately reproduce the light and shadow effects of the curtain wall at different times and under different lighting conditions, while taking into account the influence of thermal expansion on geometric shape and the optical properties of materials, thus providing a more accurate reference for architectural design.

[0105] In summary, weighted fusion computation, by integrating geometric structure data, material feature data, and thermal feature data, generates highly optimized 3D model data M. finalThis process, through the reasonable setting and dynamic adjustment of weight coefficients, ensures the accuracy and practicality of the model in different application scenarios. This method not only improves the physical accuracy of the 3D model but also enhances its overall performance in architectural design, structural analysis, and thermodynamic simulation, providing a powerful technical support platform for the 3D modeling of high-rise curtain walls.

[0106] The optimized model data is subjected to global geometric correction, local geometric refinement correction, material feature optimization and thermal feature correction, and the final corrected and optimized model data is generated through multi-dimensional collaborative optimization.

[0107] Global geometric correction involves macroscopically adjusting the entire 3D model to ensure consistency between the model's overall structure and the actual curtain wall. Its principle lies in analyzing and optimizing potential global geometric errors in the model data, such as overall shape deformation, scale inconsistencies, or posture deviations, and then using global optimization algorithms to correct these errors. For example, due to limitations in sensor viewing angles during data acquisition, the overall shape of the model may be slightly distorted. Global geometric correction can adjust the model's coordinate system and shape parameters to correct these deviations to a more accurate shape that conforms to the actual curtain wall structure. In effect, global geometric correction ensures that the 3D model conforms to the actual shape of the curtain wall as a whole, enabling the model to accurately reflect the actual situation in large-scale building structures.

[0108] After completing global geometric correction, local geometric refinement correction is performed. The principle of local geometric refinement correction is to make more precise geometric adjustments to key areas or details in the model, especially correcting minor errors in complex structures, connection points, or curved surfaces. Through refinement correction, the model's resolution and detail can be further improved, ensuring that these key areas will not cause functional or visual defects in subsequent applications due to geometric inaccuracies. For example, in the connection point area of ​​a curtain wall, problems such as uneven edges or misalignment at connections may occur due to initial data resolution limitations. Through local refinement correction, these subtle geometric errors can be corrected, resulting in a more accurate and smoother 3D model. In effect, this process makes the key details of the model more realistic, especially important in high-resolution visualization or fine structural analysis.

[0109] Material feature optimization involves further adjustments to the material representation of the model. The principle behind material feature optimization is to readjust the mapping method of material feature data based on the model's shape after global and local geometric corrections, ensuring the consistency and accuracy of material properties across the entire model surface. For example, during geometric correction, the model surface may experience stretching or compression of material textures due to shape adjustments. Material feature optimization can correct these inconsistencies by readjusting texture mapping parameters, allowing the material texture to still be naturally distributed across the adjusted geometry. Furthermore, material feature optimization can also include further adjustments to the material's optical properties to address changes in lighting conditions or the needs of specific scenarios. For example, in practical applications, adjusting reflectivity and roughness parameters can make the model appear more realistic under different lighting conditions. In effect, material feature optimization ensures that the 3D model visually matches the material effect of a real curtain wall, giving the model not only accurate geometric shape but also optical properties consistent with the actual material.

[0110] Thermal characteristic correction adjusts the thermodynamic performance of a model. Its principle is to ensure the model accurately reflects the thermal response of the curtain wall under different temperature conditions by correcting the thermal characteristic data within the model. Thermal characteristic correction includes adjustments to heat conduction paths, thermal expansion effects, and temperature distribution. Especially after geometric and material adjustments, thermal characteristic data may need recalibration to ensure accuracy in the new geometry and material mapping. For example, during geometric correction, if some parts of the model undergo slight deformation, this may affect the heat conduction path in that area, thus affecting the thermal effect. Thermal characteristic correction allows for the recalculation of thermodynamic parameters in these areas, ensuring the model's accuracy in thermal analysis. In effect, thermal characteristic correction ensures the accuracy of the model in simulating thermodynamic behavior, making the model more practical and reliable in applications such as energy consumption analysis and thermal stress assessment.

[0111] The entire process utilizes multidimensional collaborative optimization, combining the correction and optimization of three dimensions: geometry, material, and thermal features, to generate the final corrected and optimized model data. The principle of multidimensional collaborative optimization lies in simultaneously considering the mutual influence and synergistic effects between different feature data, performing global optimization in a systematic way to ensure consistency across all aspects of the model during the correction and optimization process. For example, geometric correction may affect the distribution of material textures, and material optimization may affect the performance of thermal features. By comprehensively considering these factors, multidimensional collaborative optimization ensures that each optimization step is carried out in a coordinated manner, resulting in model data that is both accurate and consistent, avoiding conflicts or inconsistencies between different optimization processes.

[0112] The final calibrated and optimized model data exhibits extremely high accuracy and consistency, accurately reflecting the geometric shape, material characteristics, and thermodynamic behavior of high-rise curtain walls under various environmental conditions. This makes the model widely applicable in multiple fields such as architectural design, structural analysis, and energy consumption assessment. It not only improves the accuracy of modeling but also enhances the model's practical application effects, providing strong technical support for the construction industry.

[0113] Preferably, the global geometric correction includes the following steps:

[0114] Based on the optimized model data, the macroscopic geometry of the 3D model is globally optimized. The global optimization algorithm is used to detect and eliminate macroscopic geometric errors. Global correction geometric model data is generated by adjusting the spatial position, scale and angle of the overall shape of the model.

[0115] The core of global geometric correction is to globally optimize the macroscopic geometric structure of a 3D model based on optimized model data. Macroscopic geometric structure refers to the overall shape of the model, including its spatial position, scale, and angles. During data acquisition and initial modeling, errors in sensors, viewing angle limitations, or environmental factors may cause macroscopic deviations in the model. For example, the overall shape of the model may be slightly distorted, or the model's spatial position may not perfectly match its actual position. If these macroscopic geometric errors are not corrected, they will lead to inaccuracies in subsequent applications, affecting the overall reliability of the modeling.

[0116] To eliminate these macroscopic geometric errors, global geometric correction utilizes a global optimization algorithm for comprehensive analysis and adjustment. The principle of the global optimization algorithm lies in identifying deviations in the model through mathematical analysis of its overall shape, and then eliminating these deviations by adjusting parameters such as the model's spatial position, scale, and angles. This process typically involves repositioning the model's overall coordinate system and correcting its scale and rotation. For example, if a slight rotational deviation occurs during the initial modeling process, the global optimization algorithm can calculate the model's overall angular offset and adjust its rotation angle to match the actual curtain wall's orientation. Similarly, if the model exhibits stretching or compression in a certain direction, the algorithm can adjust the model's scale factor to restore it to the correct dimensions.

[0117] In practice, global geometric correction typically involves several key steps: First, by scanning and analyzing the optimized model data as a whole, macroscopic geometric errors in the model are identified; then, based on these errors, the spatial position, scale, and angles of the model are adjusted; finally, globally corrected geometric model data is generated. These steps ensure that the model's overall shape is completely consistent with the actual building structure. For example, when dealing with a curtain wall model of a high-rise building, global geometric correction can ensure that the model's overall height, width, and depth are consistent with the actual building, and that the model's position and orientation in three-dimensional space also match the actual structure.

[0118] Global geometric correction significantly improves the overall accuracy of 3D models, making them not only accurate in detail but also highly consistent with reality in overall form. This is crucial for applications such as structural analysis, architectural design, and visualization of high-rise curtain walls. For example, in architectural design, a globally geometrically corrected 3D model can be used to accurately simulate the overall appearance and structure of a building, helping designers evaluate the building's visual effects and spatial layout from different perspectives. In structural analysis, the corrected model can be used to accurately calculate the building's stress and stability, ensuring the building's safety in actual use.

[0119] Preferably, the local geometric refinement correction includes the following steps:

[0120] Local optimization is performed on the detailed regions in the global calibration geometric model data. The local geometric errors are corrected by the detail enhancement algorithm, and the key regions are refined by the micro-adjustment algorithm to generate the final geometric calibration model data.

[0121] The starting point for local geometric refinement correction is the identification and optimization of detailed areas in the globally corrected geometric model data. While global geometric correction eliminates macroscopic errors in the model, minor geometric errors may still exist in some key detailed areas, such as curtain wall connection points, edge treatments, complex surfaces, and decorative details. These errors are usually caused by resolution limitations in the initial data acquisition or by neglecting details during global optimization. However, in 3D modeling, these detailed areas often determine the final quality and accuracy of the model, thus requiring local refinement.

[0122] To correct these local geometric errors, a detail enhancement algorithm is first applied. The principle of this algorithm is to increase the resolution of detailed regions in the model, capturing more geometric features and correcting errors in these areas. For example, at the edges of a curtain wall, the detail enhancement algorithm can increase the point density of the edges through interpolation or subdivision algorithms, making the edge lines smoother and more precise. Furthermore, for curved surfaces, the algorithm can further optimize the curvature and smoothness of the surface, making the transitions more natural and avoiding surface unevenness caused by insufficient resolution. In implementation, the detail enhancement algorithm typically includes multi-level subdivision and curve fitting techniques to ensure that every detailed region is fully optimized.

[0123] Building upon detail enhancement algorithms, micro-adjustment algorithms are used for refined processing of critical areas. The principle of micro-adjustment algorithms is to precisely fine-tune the most critical areas of the model, ensuring that the geometric features of these areas are completely consistent with the actual physical structure. Critical areas typically include curtain wall seams, fixing points, corners, and any parts with complex geometries. In these areas, micro-adjustment algorithms correct for any minor errors introduced during data acquisition or modeling by precisely fitting curves and surfaces to the local geometry. For example, at the connection points of the curtain wall, micro-adjustment algorithms can ensure the precise position and shape of each connection point, resulting in a high degree of visual and structural consistency throughout the structure.

[0124] This series of local optimizations and micro-adjustments ultimately generated the final geometric correction model data. This data not only closely matches the actual curtain wall structure as a whole, but also achieves extremely high accuracy in detail, ensuring that the model can truly reflect the complex structure and fine features of the curtain wall.

[0125] Local geometric refinement correction significantly improves the detail representation of 3D models, making them accurate not only in overall structure but also in every minute area, achieving high resolution and precision. For example, in architectural visualization, the refined model can clearly display every detail of the curtain wall, from connection points to decorative elements, leaving nothing out. In structural analysis, refinement correction ensures that the model's geometric data accurately reflects the actual structure, thereby improving the reliability of the analysis.

[0126] Based on the final corrected and optimized model data, geometric structure rendering, material feature rendering, and thermal feature rendering are performed, and the final three-dimensional model data is generated through a multi-channel fusion algorithm.

[0127] like Figure 4 As shown, preferably, the multi-channel fusion algorithm includes the following steps:

[0128] The final geometric correction model data, optimized material feature data, and optimized thermal feature data are rendered independently. The geometric structure is rendered through the geometry channel, the material features are rendered through the material channel, and the thermal effects are rendered through the thermal feature channel. The rendering results of each channel are then fused together to generate the final 3D model data.

[0129] Geometric rendering is the most fundamental rendering step in 3D modeling. The principle behind geometric rendering lies in accurately visualizing the 3D geometry of the curtain wall based on the final corrected and optimized model data. This includes rendering the model's vertices, edges, and faces, as well as presenting the model's spatial layout and shape. The key to geometric rendering is accurately reproducing the macroscopic form and detailed structure of the curtain wall, ensuring that the final model faithfully reflects the geometric features of the actual building. For example, in practice, geometric rendering utilizes lighting models and shadow algorithms to realistically reproduce the appearance of the building's curtain wall, ensuring consistent shape and lighting effects under different lighting conditions. In terms of effect, geometric rendering lays the foundation for the overall appearance of the model, ensuring its accuracy and visual integrity in 3D space.

[0130] Next is material feature rendering, which maps the optical properties of materials onto the geometric structure. The principle of material feature rendering lies in accurately rendering the reflection, refraction, texture, and color characteristics of the curtain wall surface based on optimized material feature data. The goal of material feature rendering is to make the model not only realistic in form but also highly realistic in visual effect. For example, in building curtain walls, material feature rendering can accurately represent the transparency and reflectivity of glass, the gloss of metal, and the surface texture and feel of other materials. In practice, material feature rendering is usually achieved through advanced rendering techniques such as PBR (Physically Based Rendering), which can simulate optical phenomena in the real world, making the model visually closer to the actual physical materials. In terms of effect, material feature rendering gives the model visual realism, making the model not only accurate in geometric form but also highly realistic in material representation.

[0131] Thermal feature rendering is a unique and crucial part of 3D modeling, simulating the thermal response of curtain wall materials under different temperature conditions. The principle of thermal feature rendering lies in using optimized thermal feature data to present the material's behavior when heated or cooled, such as temperature distribution, thermal radiation, and thermal conductivity effects. Thermal feature rendering is essential for building energy consumption analysis and thermodynamic simulation. For example, in practical applications, thermal feature rendering can depict the temperature changes of a curtain wall under direct sunlight or the thermal radiation effects during nighttime cooling. Through the visualization of these thermal features, designers and engineers can intuitively understand the building's thermal behavior under different environmental conditions, thereby making corresponding design or maintenance decisions. In terms of effect, thermal feature rendering makes the 3D model not only accurate statically but also dynamically reflects the building's true response to temperature changes, enhancing the model's application value in energy consumption analysis and thermodynamic research.

[0132] Multi-channel fusion algorithms are a crucial step in integrating the rendering results of geometry, material features, and thermal features into a unified 3D model. The principle involves rendering each channel independently (geometry, material, and thermal features), then using a fusion algorithm to overlay the rendering results of these channels into a final model. This multi-channel fusion ensures consistency across all dimensions of the model, eliminating contradictions or inconsistencies between geometry, material representation, and thermal response. For example, the shadow effects generated in geometry rendering need to be consistent with the gloss and reflectivity in material feature rendering, while also considering the thermal radiation effects in thermal feature rendering. By balancing and integrating information from these different dimensions, multi-channel fusion algorithms ensure a high degree of consistency and accuracy in both visual representation and physical simulation of the final model.

[0133] In practice, multi-channel fusion algorithms typically include the following steps: First, the geometric structure, material features, and thermal features are rendered independently; then, the rendering results of each channel are preprocessed to ensure consistency in spatial location and data format; finally, these preprocessed rendering results are combined using weighted overlay or other fusion techniques to generate the final 3D model data. For example, in the visualization process of architectural design, the fused 3D model can not only accurately display the shape and material of the curtain wall, but also simulate its thermal response in real time, providing a comprehensive reference for design and decision-making.

[0134] By fusing geometric structure rendering, material feature rendering, and thermal feature rendering across multiple channels, the 3D modeling of high-rise curtain walls can not only realistically reproduce the building's appearance in terms of form and visuals, but also simulate the building's dynamic performance under different environmental conditions. The multi-channel fusion algorithm ensures the comprehensiveness and consistency of the final model data, making the model widely applicable in fields such as architectural design, structural analysis, and thermodynamics research, providing comprehensive technical support for the construction industry.

[0135] like Figure 5 As shown, a system for implementing a three-dimensional modeling method for the high-altitude curtain wall includes:

[0136] The data acquisition module is used to collect multispectral, structured light scanning, and thermal imaging data of the high-altitude curtain wall via drones. It then processes the acquired data synchronously in time and space to generate pre-processed fused data. Multispectral data captures the optical properties of the curtain wall, structured light scanning data acquires its geometry, and thermal imaging data records the temperature distribution on the curtain wall surface. To ensure spatiotemporal consistency, the acquired data undergoes synchronous processing to generate pre-processed fused data. The key to this step is the accurate acquisition and synchronous processing of multi-source data to ensure the accuracy and consistency of subsequent modeling.

[0137] The data parsing and feature extraction module performs multi-dimensional cross-analysis on the preprocessed fused data, sequentially extracting geometric structure data, material feature data, and thermal feature data. It then generates fused feature data through hierarchical feature fusion and dynamic feedback optimization. The core of this module lies in multi-dimensional data parsing; through layer-by-layer analysis, it extracts key features from different dimensions and optimizes the data accordingly, providing high-quality input for subsequent modeling processes.

[0138] The 3D modeling and feature fusion module performs 3D modeling based on fused feature data using a multimodal feature fusion algorithm. It deeply fuses geometric structure data, material feature data, and thermal feature data, and generates optimized model data using real-time feedback and recursive optimization mechanisms. Based on the fused feature data, this module performs 3D modeling using a multimodal feature fusion algorithm, deeply fusing geometric structure data, material feature data, and thermal feature data. Utilizing real-time feedback and recursive optimization mechanisms, it continuously corrects and optimizes the model data, ultimately generating a highly accurate optimized model. This process ensures a high degree of consistency and accuracy in the 3D model's geometry, material representation, and thermal effects.

[0139] The calibration and optimization module performs global geometric calibration, local geometric refinement calibration, material feature optimization, and thermal feature calibration on the optimized model data. Through multi-dimensional collaborative optimization, it generates the final calibrated and optimized model data. The key here is to fine-tune the model to ensure that it is accurate not only in its overall form but also highly consistent with the actual curtain wall structure in detail.

[0140] The rendering and output module is used to perform geometric structure rendering, material feature rendering, and thermal feature rendering based on the final corrected and optimized model data, and to generate the final 3D model data through a multi-channel fusion algorithm. Based on the final corrected and optimized model data, this module is responsible for geometric structure rendering, material feature rendering, and thermal feature rendering. Through a multi-channel fusion algorithm, these rendering results are integrated to generate the final 3D model data. This process not only ensures the visual realism of the model but also enables the model to accurately simulate the optical and thermodynamic properties of actual curtain walls, resulting in a final 3D model with a high degree of visual and functional consistency.

[0141] In practical applications, after extracting construction drawing information, the extracted information is categorized and summarized, and a preliminary 3D model is generated using modeling tools. This model, through multi-user collaboration, supports the overall modeling needs of the project via a cloud platform sharing service. The modeling tools first generate a wireframe model, then convert it into a controlled model, and assign facade information to the controlled model. Further, the facade information is used to generate unit panel types and stored in a database, with each unit panel assigned a corresponding building address. After the aluminum profile mold drawings are transferred to the database, they are optimized, ultimately generating a parametric 3D machining model for precise factory processing. Subsequently, through a series of modular processes in this invention system, multimodal data of the high-altitude curtain wall is gradually collected, analyzed, modeled, corrected, and rendered, ultimately generating a highly accurate 3D model with realistic physical properties. This model can be applied to architectural design, structural analysis, and thermodynamic research, providing comprehensive curtain wall representation.

[0142] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects.

[0143] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A three-dimensional modeling method of a high-altitude curtain wall, characterized by, The method comprises the following steps: Collecting multispectral data, structured light scanning data and thermal imaging data of the high-altitude curtain wall by a UAV, synchronously processing the collected data in time and space, and generating preprocessed fusion data by preliminary fusion; Performing multi-dimensional cross analysis on the preprocessed fusion data, sequentially extracting geometric structure data, material feature data and thermal feature data, and generating fusion feature data by hierarchical feature fusion and dynamic feedback optimization; The multi-dimensional cross analysis comprises the following steps: performing preliminary analysis on the geometric structure data in the preprocessed fusion data to generate preliminary geometric structure data, combining the material feature data and the thermal feature data, optimizing the boundary accuracy of the geometric structure data by multi-dimensional cross analysis, generating geometric feature point data, further optimizing the preliminary geometric structure data by using the geometric feature point data, and generating optimized geometric structure data; The extraction of the material feature data comprises the following steps: performing light reflection analysis, refraction analysis and surface texture analysis on the material information in the preprocessed fusion data to generate material optical feature data, and coupling the material optical feature data and the optimized geometric structure data for further optimization of the material feature data to generate optimized material feature data; The extraction of the thermal feature data comprises the following steps: performing thermal gradient analysis on the thermal imaging information in the preprocessed fusion data, combining the optimized geometric structure data and the optimized material optical feature data, generating thermal feature model data by a thermal feature modeling algorithm, and performing real-time correction and optimization on the thermal feature model data by a dynamic feedback mechanism to generate optimized thermal feature data; Based on the fusion feature data, a multi-modal feature fusion algorithm is used for three-dimensional modeling, the geometric structure data, the material feature data and the thermal feature data are deeply fused, and an optimized model data is generated by using a real-time feedback and recursive optimization mechanism; Global geometric correction, local geometric fine correction, material feature optimization and thermal feature correction are performed on the optimized model data to generate final correction and optimization model data by multi-dimensional collaborative optimization; Based on the final correction and optimization model data, geometric structure rendering, material feature rendering and thermal feature rendering are performed, and a final three-dimensional model data is generated by a multi-channel fusion algorithm.

2. The high-rise facade three-dimensional modeling method according to claim 1, wherein, The multi-modal feature fusion algorithm comprises the following steps: The optimized geometric structure data, the optimized material feature data and the optimized thermal feature data are weighted and fused, wherein: weighting factor for indicating the importance of the geometry data; weighting factor for indicating the importance of the material characteristic data; weighting factor for indicating the importance of the thermal characteristic data; The weight coefficients are dynamically adjusted by a recursive optimization mechanism to generate the optimized model data.

3. The high-rise facade three-dimensional modeling method according to claim 2, wherein, The specific expression of the weighted fusion calculation is: wherein, represents the optimized model data; represents the optimized geometry data; represents the optimized material feature data; represents the optimized thermal feature data; , and represent the weight coefficients of the geometry data, the material feature data, and the thermal feature data, respectively.

4. The high-rise facade three-dimensional modeling method according to claim 1, wherein, The global geometric correction comprises the following steps: Based on the optimized model data, the macroscopic geometric structure of the three-dimensional model is globally optimized, global optimization algorithm is used to detect and eliminate macroscopic geometric errors, and global correction geometric model data is generated by adjusting the spatial position, scale and angle of the overall shape of the model.

5. The high-rise facade three-dimensional modeling method according to claim 4, characterized in that, The local geometric fine correction comprises the following steps: The detail area in the global correction geometric model data is locally optimized, the local geometric error is corrected through a detail enhancement algorithm, and a micro adjustment algorithm is used for fine processing of key areas to generate final geometric correction model data.

6. The high-rise facade three-dimensional modeling method according to claim 1, wherein, The multi-channel fusion algorithm comprises the following steps: The final geometric correction model data, the optimized material feature data and the optimized thermal feature data are independently rendered respectively, the geometric structure is rendered through a geometric channel, the material feature is rendered through a material channel, the thermal effect is rendered through a thermal feature channel, and the rendering results of the channels are subjected to multi-channel fusion processing to generate final three-dimensional model data.

7. A system for implementing the three-dimensional modeling method of the high-altitude curtain according to any one of claims 1 to 6, characterized in that, Comprise: The data acquisition module is used for collecting multispectral data, structure light scanning data and thermal imaging data of the high-altitude curtain respectively by the unmanned aerial vehicle, and synchronously processing the collected data in time and space to generate preprocessed fusion data; The data analysis and feature extraction module is used for multi-dimensional cross analysis of the preprocessed fusion data, sequentially extracting geometric structure data, material feature data and thermal feature data, and generating fusion feature data through hierarchical feature fusion and dynamic feedback optimization; The three-dimensional modeling and feature fusion module is used for three-dimensional modeling based on the fusion feature data, deep fusion of the geometric structure data, material feature data and thermal feature data through a multi-modal feature fusion algorithm, and generation of optimized model data by using real-time feedback and recursive optimization mechanism; The correction and optimization module is used for global geometric correction, local geometric fine correction, material feature optimization and thermal feature correction of the optimized model data, and generation of final correction and optimization model data through multi-dimensional collaborative optimization; The rendering and output module is used for geometric structure rendering, material feature rendering and thermal feature rendering based on the final correction and optimization model data, and generation of final three-dimensional model data through a multi-channel fusion algorithm.

Images