Ice and snow landscape optimization design system and method based on AR interaction technology

Abstract

The application relates to the field of AR technology and landscape design, and provides an ice and snow landscape optimization design system and method based on AR interaction technology.The method acquires material attributes and environmental data of an ice and snow landscape by scanning a three-dimensional data model of the ice and snow landscape, predicts ablation of the ice and snow landscape, and dynamically updates the three-dimensional data model of the ice and snow landscape; based on the dynamic three-dimensional data model, the material attributes and the environmental data, light tracing algorithm is used to generate dynamic distribution characteristics of reflection risk; based on the dynamic three-dimensional data model and the material attributes, finite element analysis is used to generate dynamic distribution characteristics of structure risk; based on all the risk distribution characteristics, an ice and snow landscape comprehensive risk assessment result is generated; based on the ice and snow landscape comprehensive risk assessment result, the comprehensive risk assessment result is visualized in an AR interaction interface, and ice and snow landscape design selection is performed.The application realizes real-time and visualization of risk analysis by combining AR interaction technology, and improves the safety and reliability of ice and snow landscape design.

Description

Technical Field

[0001] This application relates to the fields of AR technology and landscape design, and in particular to an ice and snow landscape optimization design system and method based on AR interactive technology. Background Technology

[0002] As a unique combination of art and engineering, ice and snow landscapes hold significant value in exhibitions, tourism, and urban landscapes. Ice and snow landscape design transforms the climatic disadvantage of "coldness" into a unique tourism resource and economic advantage. However, due to the special temperature sensitivity of ice and snow materials, their mechanical strength is easily affected by climate change. Furthermore, due to the translucent nature of ice and snow materials, they possess high reflectivity and unique scattering effects, producing distinctive light and shadow effects.

[0003] In traditional ice and snow landscape design, it is necessary to coordinate information from various aspects, including design drawings, quality control, and safety risks. This mainly relies on manual recording and on-site inspection. As an emerging technology, AR technology has been applied in many industries, especially in the construction industry. AR technology can combine virtual information with the real environment, providing real-time visual feedback, which greatly improves the efficiency and accuracy of information transmission and presents building information in real time.

[0004] Current AR technology based on 3D modeling is mainly applied to static architectural landscape design, but it lacks dynamic integrated analysis of the melting process, reflective properties, and structural risks of snow and ice landscapes. This affects the safety and reliability of snow and ice landscape design, and it also fails to integrate AR interactive technology to achieve real-time, visualized design optimization. Therefore, this paper proposes a snow and ice landscape optimization design system based on AR interactive technology. This system aims to provide intelligent support for snow and ice landscape design by collecting environmental data and material properties, predicting snow and ice melting, and calculating and assessing potential risks, thereby improving safety and reliability. Summary of the Invention

[0005] To address the aforementioned issues, a system and method for optimizing ice and snow landscape design based on AR interactive technology are provided, employing the following technical solutions:

[0006] In the first aspect, this application provides a method for optimizing the design of ice and snow landscapes based on AR interactive technology, including the following steps:

[0007] S1. Scan the ice and snow landscape to obtain a three-dimensional data model of the ice and snow landscape; at the same time, acquire the material properties and environmental data of the ice and snow landscape;

[0008] S2. Construct an ablation prediction model based on the snow and ice ablation dataset to predict the snow and ice landscape ablation and dynamically update the three-dimensional data model of the snow and ice landscape.

[0009] S3. Based on the dynamically updated three-dimensional data model of the ice and snow landscape, material properties and environmental data, the reflectivity of the ice and snow landscape is predicted by the ray tracing algorithm, and the dynamic distribution characteristics of reflectivity risk are generated.

[0010] S4. Based on the dynamically updated three-dimensional data model and material properties of the ice and snow landscape, predict the strain trend of the ice and snow landscape through finite element analysis and generate dynamic distribution characteristics of structural risks.

[0011] S5. Based on the dynamic distribution characteristics of reflective risk and structural risk of the ice and snow landscape, generate a comprehensive risk assessment result for the ice and snow landscape;

[0012] S6. Based on the comprehensive risk assessment results of the ice and snow landscape, visualize the comprehensive risk assessment results in the AR interactive interface and make selections for ice and snow landscape design.

[0013] According to the above technical solution, the scanning of the ice and snow landscape to obtain a three-dimensional data model of the ice and snow landscape; and the acquisition of material properties and environmental data of the ice and snow landscape, including:

[0014] The structural data of the ice and snow landscape is obtained through laser scanning. Combined with point cloud registration, the obtained structural data is registered and fused to construct a three-dimensional data model of the ice and snow landscape. Regions are then divided according to the equal area of ​​the ice and snow landscape structure. The laser scanning process involves using a 3D laser scanner to scan the ice and snow landscape at multiple time periods and angles to obtain high-precision point cloud data, including coordinate information, color information, laser return intensity, and the orientation of each point on its surface. Point cloud registration combines point cloud data from multiple locations at the same time period into a unified coordinate system. Constructing the three-dimensional data model of the ice and snow landscape involves converting the merged point cloud data from different time periods into multiple three-dimensional data models of the ice and snow landscape that change over time. The core purpose of this step is to establish a precise, time-varying three-dimensional data model of the ice and snow landscape that can be simulated, overcoming the uncertainty caused by subjective factors in manual measurement and providing an accurate geometric basis for continuous prediction of ice and snow melting.

[0015] Sublimation rate characteristic data were obtained by analyzing the variables affecting the sublimation rate of snow and ice using the Penman-Monteith equation. The Penman-Monteith equation was chosen because it clearly expresses the coupling of energy and mass transport. The process of obtaining sublimation rate characteristic data by analyzing the variables affecting the sublimation rate of snow and ice using the Penman-Monteith equation involves removing the constant λ from the parameters. s :Latent heat of sublimation of ice and snow, ρ a Air density, c p:Specific heat capacity of air at constant pressure, γ:wet and dry surface constants, G:surface heat flux, which has little impact on snow and ice landscape design; Snow and ice melting dataset is the parameter data that jointly affects the melting rate during the snow and ice melting process.

[0016] The data collected for the Microfacet model includes the reflectivity, refractive index, incident light direction, and incident light intensity of ice and snow materials, which are set as optical scene data. The refractive index of ice and snow materials can be obtained from commonly used tables. The reflectivity of ice and snow materials is calculated by measuring the ratio of incident light intensity to reflected light intensity using a spectrophotometer. The incident light direction of the sun is accurately calculated by inputting the time into a calculator for the sun's azimuth and altitude angles.

[0017] According to the above technical solution, the construction of the ablation prediction model to obtain the predicted ablation situation of the ice and snow landscape includes:

[0018] The snow and ice melting feature dataset was standardized. The input layer data included: snow and ice material density, radiation intensity, air temperature, snow and ice landscape surface temperature, air humidity, and wind speed. The output layer data was the melting rate, which was divided into training, testing, and validation sets to construct a melting prediction model. Standardization refers to transforming the data into a normal distribution with a mean of 0 and a standard deviation of 1.

[0019] Based on a neural network model, the loss is calculated and the ablation prediction model is updated using the training set; the ablation prediction model is periodically tested using the validation set; and the mean squared error is calculated using the test set to obtain the final ablation prediction model. Calculating the loss and updating the ablation prediction model using the training set allows the computer to automatically adjust the parameters within the neural network; periodically testing the ablation prediction model using the validation set monitors the training process to prevent overfitting and ensure the model's generalization ability.

[0020] Based on the final ablation prediction model, the ablation rate of each region is predicted by inputting thermodynamic data. This prediction is then combined with a three-dimensional data model of the snow and ice landscape, which is dynamically updated. This dynamic update calculates the displacement of each vertex on the model surface along its normal vector direction based on the predicted ablation rate and corresponding time for each region. The model's deformation is achieved by moving the vertex coordinates, resulting in three-dimensional data models for each predicted time period. This time-varying three-dimensional data model of the snow and ice landscape facilitates subsequent calculations based on the time-model variation, thereby enabling accurate risk prediction based on changes in snow and ice landscape ablation.

[0021] According to the above technical solution, the step of predicting the reflectivity of ice and snow landscapes using ray tracing algorithms and generating dynamic distribution characteristics of reflectivity risk includes:

[0022] Based on a dynamically updated 3D data model of ice and snow landscapes, a Microfacet model is constructed by assigning surface roughness, reflectivity, and refractive index characteristics to the 3D data model of ice and snow landscapes. The Microfacet model is a physically based local illumination model that assumes that the surface of an object is uneven, and that the macroscopic surface is composed of many micro-surfaces. Light undergoes ideal specular reflection or refraction on each micro-surface, making it suitable for simulating and calculating the surface reflection of ice and snow materials.

[0023] By inputting the incident light intensity and direction from the optical scene data, setting the light source parameters, and calculating the reflected light intensity using the Microfacet model, the reflected light intensity distribution of each ice and snow landscape area is obtained. The reflected light intensity distribution of each ice and snow landscape area is analyzed based on the simulated reflected light intensity distribution that may be received from the tourist's perspective, and its visual impact on tourists is analyzed.

[0024] The impact of reflective intensity distribution in various snow and ice landscape areas on human vision was assessed, yielding dynamic distribution characteristics of reflective risk in each area. The impact of reflective intensity distribution on human vision in each snow and ice landscape area was categorized based on the intensity of reflected light received from the simulated viewpoint of a visitor using a virtual camera: low intensity range was designated as the dim area, medium intensity range as the comfort area, high intensity range as the fatigue area, and extreme intensity range as the glare area. This process transforms lighting design, which previously relied on subjective perception, into quantifiable objective intensity values, providing a foundation for the accuracy and reliability of subsequent assessments and significantly reducing cognitive biases caused by subjective differences.

[0025] According to the above technical solution, the step of predicting the stress and strain distribution of the snow and ice landscape through finite element analysis and generating dynamic distribution characteristics of structural risks includes:

[0026] The dynamically updated 3D data model of the ice and snow landscape is imported into finite element analysis software. Geometric cleanup and simplification are performed, and regional meshing is implemented. Mesh refinement is applied to stress-concentrated areas, while sparser meshing is used in large, flat areas to construct the finite element model. The geometric cleanup, simplification, and meshing are performed to balance computational resource consumption, reducing computational resources allocated to large, flat areas with simple stress, while allocating more computational resources to areas with complex and concentrated stress, thereby improving computational efficiency.

[0027] In the finite element model, creep material properties of the ice and snow landscape are defined, gravitational acceleration is applied, and the bottom degrees of freedom are constrained. Since the stress-strain relationship of ice and snow materials is nonlinear from the outset, irreversible creep deformation will occur even under very small loads. The first stage is the initial creep stage, where the strain rate gradually decreases over time; the second stage is the steady-state creep stage, where the strain rate remains constant; the third stage is the accelerated creep stage, where the strain rate increases rapidly until the material fractures and fails. Since the first and third stages are relatively short, only the second stage is considered in the analysis; therefore, the Norton creep model is chosen for finite element analysis. The Norton creep model is as follows:

[0028] ;

[0029] in σ: creep strain rate, A: creep material constant, n: creep exponent. Creep material properties are the creep material constant A and creep exponent n in the Norton creep model. A constant axial force σ is applied to ice and snow materials in a temperature-controlled experimental chamber, and the axial strain ε occurring with time t is measured and recorded until the strain rate tends to stabilize or the ice and snow materials break. The experiment is repeated with different stresses σ to obtain a set of strain-time curves of ice and snow materials under different stresses. The steady-state creep rate is calculated from the data points where the strain rate is almost constant. Applying gravitational acceleration is the primary load calculated based on the model's own weight. Constraining the bottom degree of freedom prevents the entire model from shifting without internal deformation.

[0030] The real-time strain of each region of the ice and snow landscape is calculated using a finite element method (FEM) solver, revealing the strain trends and generating strain cloud maps to show the dynamic distribution characteristics of structural risks in each region. The structural risk of each region is assessed by determining whether the strain rate of the corresponding region remains in a stable creep state without affecting the normal operation of the landscape.

[0031] Based on the above technical solution, and considering the dynamic distribution characteristics of reflective risk and structural risk of the ice and snow landscape, the comprehensive risk assessment results for the ice and snow landscape are generated, including:

[0032] Based on the dynamic distribution characteristics of reflective and structural risks, reflective and structural risks are quantified to the same scale. Weights are assigned to reflective and structural risk scores according to their impact, and a weighted calculation is used to obtain the comprehensive risk assessment results for each snow and ice landscape area. Since reflective intensity in reflective risk is not simply a matter of higher or lower values ​​being better, but rather a moderate indicator, with scores decreasing further from the optimal value and exhibiting a non-linear relationship, upper and lower limits for reflective intensity are defined using a quadratic function method.

[0033] S1=100-k·(BB ideal ) 2 ;

[0034] The reflection risk score is obtained, where S1: reflection risk score, k: penalty coefficient, determined by setting a score corresponding to the reflection intensity, and B: actual reflection intensity. ideal Optimal light intensity. In structural risk assessment, the longer the strain trend remains stable, the better. Structural risk score is set as follows:

[0035] S2=100*T / T i ;

[0036] Where T: the time to maintain a stable creep, T i Total exhibition time, S2 is the structural risk score and S2≤100.

[0037] Based on the above technical solution, visualizing the comprehensive risk assessment results in the AR interactive interface and updating the design scheme includes:

[0038] In the AR interactive interface, based on the comprehensive risk assessment results of each ice and snow landscape area, the optimal design scheme is recommended and displayed. Different colors are rendered to cover each ice and snow landscape area corresponding to its comprehensive risk level, and areas with high reflectivity and high structural risk are additionally marked. The real-time reflectivity and structural risk distribution of the interactive area is dynamically updated and displayed based on the user's interaction area. The optimal design scheme is the one with the highest comprehensive score and the smallest variance in each score across all time periods during the predicted exhibition time.

[0039] Secondly, this application provides an ice and snow landscape optimization design system based on AR interactive technology, including:

[0040] The multi-source data acquisition and analysis module is used to acquire three-dimensional data models, material properties, and environmental data of ice and snow landscapes through laser scanning, environmental sensing, and material testing.

[0041] The ablation prediction module is used to construct a neural network model based on the snow and ice ablation dataset to obtain the predicted ablation situation of the snow and ice landscape.

[0042] The reflectivity risk prediction module is used to predict the reflectivity of the ice and snow landscape based on dynamically updated 3D data models of ice and snow landscapes, material properties and environmental data, and to generate dynamic distribution characteristics of reflectivity risk.

[0043] The structural risk prediction module is used to dynamically update the three-dimensional data model and material properties of the ice and snow landscape, predict the stress and strain distribution of the ice and snow landscape through finite element analysis, and generate dynamic distribution characteristics of structural risks.

[0044] The comprehensive risk assessment module is used to generate comprehensive risk assessment results for the ice and snow landscape based on the dynamic distribution characteristics of reflective risk and structural risk of the ice and snow landscape.

[0045] The AR interaction and design update module is used to visualize the comprehensive risk assessment results in the AR interactive interface based on the comprehensive risk assessment results of the ice and snow landscape, and to update the design scheme.

[0046] Thirdly, this application provides an electronic device, including a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes an ice and snow landscape optimization design method based on AR interactive technology by calling the computer program stored in the memory.

[0047] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform an ice and snow landscape optimization design method based on AR interactive technology.

[0048] Compared with the prior art, this application has the following advantages and beneficial effects:

[0049] This application collects environmental data and material properties and constructs a snow and ice melting prediction model based on a three-dimensional data model. It achieves accurate prediction of snow and ice melting through artificial neural networks. Based on the three-dimensional data model of the snow and ice landscape under various melting states, it obtains the dynamic distribution characteristics of reflective risk through ray tracing algorithm and obtains the dynamic distribution characteristics of structural risk through finite element analysis, thus achieving accurate pre-identification of risks during the design stage. Finally, the comprehensive risk assessment results are visualized in an AR interactive interface to update the design scheme, significantly improving the safety and reliability of snow and ice landscape design. Attached Figure Description

[0050] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0051] Figure 1 This is a schematic diagram of the overall process of the ice and snow landscape optimization design method based on AR interactive technology provided in the embodiments of this application;

[0052] Figure 2 This is a schematic diagram of the structure of the ice and snow landscape optimization design system based on AR interactive technology provided in the embodiments of this application;

[0053] Figure 3 This is a schematic diagram of the creep-time curve of the ice and snow material under stress according to an embodiment of this application;

[0054] Figure 4This is a schematic diagram of the structure for training an artificial network model according to an embodiment of this application;

[0055] Figure 5 This is a schematic diagram of the comprehensive risk analysis process provided in the embodiments of this application. Detailed Implementation

[0056] The technical solution of this application will be described in detail below through specific embodiments. It should be understood that the embodiments of this application and the specific features in the embodiments are detailed descriptions of the technical solution of this application, rather than limitations on the technical solution of this application. Unless otherwise specified, the embodiments of this application and the technical features in the embodiments can be combined with each other.

[0057] Please see Figure 1 , Figure 1 This is a schematic diagram of the overall process of the ice and snow landscape optimization design method based on AR interactive technology provided in the embodiments of this application, which specifically includes the following steps:

[0058] S1. Scan the ice and snow landscape to obtain a three-dimensional data model of the ice and snow landscape; at the same time, obtain the material properties and environmental data of the ice and snow landscape.

[0059] The scanning of the snow and ice landscape includes: setting up four high-reflectivity target spheres next to the snow and ice landscape for subsequent automatic point cloud registration; using a laser scanner to scan every hour from multiple angles to obtain point cloud data with a coordinate accuracy of ±2mm, including 3D coordinates, reflection intensity, and scanning angle; importing the point cloud data into CloudCompare software to unify multiple sets of point clouds into a single coordinate system; importing the processed point cloud into MeshLab to generate a triangular mesh model, i.e., a 3D data model of the snow and ice landscape, and dividing it into equal-area regions, each approximately 2m in size. 2 .

[0060] The acquisition of material properties and environmental data for the ice and snow landscape includes: sampling the ice and snow materials used, obtaining the sample volume through laser scanning, measuring the sample weight to calculate the density of the ice and snow materials; and measuring the incident light intensity and reflected light intensity using a spectrophotometer, and calculating the reflectance using the formula...

[0061] R=(I r / I i )×100%;

[0062] Where I r : Reflected light intensity, I i : Incident light intensity; R: Reflectivity of ice and snow materials; The refractive index of ice and snow materials can be taken as 1.309 according to commonly used tables; Based on the thickness data of the three-dimensional data model of the ice and snow landscape, the melting rate of the ice and snow landscape is calculated and used to predict the melting thickness.

[0063] Sublimation rate characteristic data were obtained by analyzing the variables affecting the sublimation rate of ice and snow using the Penman-Monteith equation:

[0064] ;

[0065] λ s : Latent heat of sublimation of snow and ice (2.83x10 6 J / kg);

[0066] m: sublimation rate (kg / m²·s);

[0067] Δ: Slope of the saturated vapor pressure-temperature curve (Pa / K), determined by temperature;

[0068] R n Radiance intensity (W / m 2 );

[0069] G: Earth's surface heat flux (W / m²);

[0070] ρ a Air density (1.2 kg / m³) 3 );

[0071] c p Specific heat capacity of air at constant pressure (1004 J·kg / K);

[0072] e i (T s Ice surface temperature T s The saturated vapor pressure (Pa) at the ice surface is determined by the ice surface temperature;

[0073] e a The actual vapor pressure of air (Pa) is determined by air temperature and humidity.

[0074] r a Aerodynamic drag (s / m) is inversely proportional to wind speed.

[0075] γ: Wet / dry surface constant (65 Pa / K);

[0076] Where λs, ρ a c p γ can be considered constants, G can be neglected in the structure of the ice and snow landscape, and the variables Δ and e are... i e a r aThe data varies with temperature, humidity, wind speed, and solar radiation intensity. Material density is obtained by calculating the volume from a 3D data model, measuring the corresponding weight, and then calculating it. Wind speed is obtained using an ultrasonic anemometer. Air temperature and humidity are obtained using an integrated temperature and humidity sensor protected by a radiation shield. The temperature of the ice and snow surface is obtained using an infrared thermometer, and solar radiation intensity is obtained by measuring it using a spectrophotometer. Environmental data from the same period and location over the past five years, including temperature, humidity, wind speed, and solar radiation intensity, were collected from local meteorological websites to construct a snow and ice melting characteristic dataset for building a snow and ice melting prediction model.

[0077] S2. Construct an ablation prediction model based on the snow and ice ablation dataset to predict the snow and ice landscape ablation situation and dynamically update the three-dimensional data model of the snow and ice landscape.

[0078] The construction of the ablation prediction model includes: standardizing all data, including material density, radiation intensity, air temperature, ice surface temperature, air humidity, wind speed, and ablation rate, and converting them into a normal distribution with a mean of 0 and a standard deviation of 1.

[0079] ;

[0080] : Standardized data, X: Original data, μ: Mean of the data, σ: Standard deviation of the data

[0081] ;

[0082] n: total number of samples, x i For the data of the i-th sample, standardization preprocessing can significantly improve the training efficiency and performance of the model. Input layer feature parameters: material density, radiation intensity, air temperature, ice surface temperature, air humidity, wind speed; output layer: ablation rate. The ReLU activation function is chosen to enable the neural network to fit complex function mappings, thereby solving nonlinear problems. For example... Figure 4 As shown, the dataset is randomly divided into a training set (80%), a validation set (10%), and a test set (10%). The training set is used to train the model and minimize the mean squared error.

[0083] ;

[0084] MSE: Mean Squared Error The predicted value of the i-th sample. : The true value of the i-th sample, i.e., (predicted rate - true rate) 2 The average value is used to input the validation set every 10% of the training set to check the model's generalization ability and prevent overfitting. After training, the mean squared error is calculated using the test set to finally evaluate the model's performance. The smaller the mean squared error, the closer the prediction result is to the true value, and the better the model performance.

[0085] The process of predicting the melting of snow and ice landscapes and dynamically updating the 3D data model of snow and ice landscapes includes: inputting environmental data into a trained melting prediction model based on historical environmental data from the past five years and recent weather forecasts to predict the melting rate of each region at a corresponding time in the future; and then, in the 3D modeling software Blender, shrinking and deforming the corresponding regions in the 3D data model based on the predicted melting rate to generate a dynamically updated 3D data model of the snow and ice landscape.

[0086] S3. Based on the dynamically updated three-dimensional data model of the ice and snow landscape, material properties and environmental data, the reflectivity of the ice and snow landscape is predicted by the ray tracing algorithm, and the dynamic distribution characteristics of reflectivity risk are generated.

[0087] The process of predicting the reflectivity of snow and ice landscapes using ray tracing algorithms includes: constructing a Microfacet model by assigning reflectivity, refractive index, and surface roughness to each region of the updated 3D snow and ice landscape data model; using Unity's HDRP high-definition rendering pipeline; and setting environmental optical data, including the angle of incidence of sunlight and the intensity of incident sunlight. The angle of incidence of sunlight was precisely calculated using a solar altitude and azimuth calculator. Ray tracing was then enabled to calculate the average reflectivity of each region at each time point along the main tourist routes.

[0088] The dynamic distribution characteristics of the risk of generating reflection include: the reflection intensity area is divided into the following regions according to the reflection intensity and human eye comfort standards: below 200 lux is the dim area, 200-2000 lux is the comfortable area, 2000-4000 lux is the fatigue area, and above 4000 lux is the glare area.

[0089] S4. Based on the dynamically updated three-dimensional data model and material properties of the ice and snow landscape, the strain trend of the ice and snow landscape is predicted by finite element analysis, and the dynamic distribution characteristics of structural risk are generated.

[0090] The finite element analysis method for predicting the strain trend of ice and snow landscapes includes: importing dynamically updated 3D data models of ice and snow landscapes into ANSYS Workbench; searching for and deleting duplicate surfaces; creating surfaces using the surfaces panel for larger missing surfaces; adjusting smaller missing surfaces using replace; performing automatic mesh generation; applying a 1:5 to 1:10 gradient refinement in key areas such as hole edges and structural connections; and defining the measured ice density. Figure 3 As shown, the first and third stages of creep are relatively short in duration. Therefore, the Norton creep model is chosen to describe the second stage of creep in ice and snow materials for finite element calculation:

[0091] ;

[0092] σ: creep strain rate, A: creep material constant, n: creep exponent. Creep material properties are the creep material constant A and creep exponent n in the Norton creep model. A constant axial force σ is applied to ice and snow materials in a temperature-controlled experimental chamber, and the axial strain ε occurring with time t is measured and recorded until the strain rate tends to stabilize or the ice and snow materials break. The experiment is repeated with different stresses σ to obtain a set of strain-time curves of ice and snow materials under different stresses. The steady-state creep rate is calculated from the data points where the strain rate is almost constant. ,Depend on get On the coordinate graph, with ln(σ) as the abscissa, Data points are plotted on the ordinate. A straight line is fitted using linear regression. The fitted line represents the stress exponent n, and the intercept is ln(A). The parameter A is obtained by taking the inverse. Gravitational acceleration is applied to calculate the self-weight as a load. The bottom degrees of freedom are constrained to prevent the entire model from shifting without internal deformation. Static structural analysis is performed using a finite element method (FEM).

[0093] The dynamic distribution characteristics of generated structural risks include: displaying stress concentration areas and strain trends in various regions of the ice and snow landscape based on analysis results, and automatically determining whether the landscape is stable or affects normal operation based on settings.

[0094] S5. For example Figure 5 As shown, a comprehensive risk assessment result for the ice and snow landscape is generated based on the dynamic distribution characteristics of reflective risk and structural risk of the ice and snow landscape.

[0095] The comprehensive risk assessment results for generating snow and ice landscapes include: setting upper and lower limits for reflectivity intensity and establishing a reflectivity analysis score S1 using the quadratic function method.

[0096] S1=100-k·(BB ideal ) 2 ;

[0097] S1: Reflection risk score, k: Penalty coefficient, B: Actual reflective intensity, B ideal Optimal light intensity: Since the effect of reflective intensity on the human eye in a range smaller or larger than the comfort zone is not linear and is asymmetrical, two intervals were set: one with reflective intensity greater than 1000 lux and the other with reflective intensity less than 1000 lux. Furthermore, 2000 lux was assigned a score of 60 points for reflective intensity greater than 1000 lux, and 200 lux was assigned a score of 60 points for reflective intensity less than 1000 lux. The optimal light intensity of 1000 lux was assigned a score of 100 points. This determined the penalty coefficient k for different reflective intensity intervals, resulting in a reflective risk score for each area.

[0098] S1 = 100 - 6.25 × 10 -5 ×(B-1000) 2 (0 < B < 1000);

[0099] S1=100-4×10 -5 ×(B-1000) 2 (B>1000);

[0100] In structural risk assessment, the longer the strain trend remains stable, the better. A simple way to set the structural risk score S2 is as follows:

[0101] S2=100*T / T i ;

[0102] Where T: the time to maintain stable strain, T i Total exhibition time; S2: Structural risk score S2≤100. Since structural risk has a direct impact on safety, a corresponding weight of 0.6 is set, and the weight for reflectivity risk is set to 0.4. Comprehensive risk assessment results for the ice and snow landscape area:

[0103] S = 0.4S1 + 0.6S2.

[0104] S6. Based on the comprehensive risk assessment results of the ice and snow landscape, visualize the comprehensive risk assessment results in the AR interactive interface and make selections for ice and snow landscape design.

[0105] The visualization of the comprehensive risk assessment results in the AR interactive interface includes: uploading the comprehensive risk assessment results to the AR device; when the user wears the AR device to observe the physical 3D model, a semi-transparent color heat map will be overlaid. Low-risk areas with S>90 and S1 and S2 both greater than 60 are overlaid in green; medium-risk areas with 90>S>75 and S1 and S2 both greater than 60 are overlaid in orange; and high-risk areas with S<75 are overlaid in red. When S1 or S2 is less than 60, it is highlighted to indicate structural instability or abnormal reflection.

[0106] The snow and ice landscape design selection process involves the user interacting with high-risk areas via gestures or voice. The AR interface immediately displays the risk status: "High Risk: Structural instability. Internal steel support is recommended," and suggests the optimal design: pre-embedding a 30mm diameter steel pipe within the area. Once the user agrees, the AR system renders a semi-transparent steel pipe model at the corresponding location in real time and updates the risk calculation. The simulation results show the area's color changing from red to yellow and the highlighting removed, indicating a reduced risk level to medium. The construction team then implants the steel pipe in the corresponding area based on the AR system's markings. Scanning the updated landscape begins a new cycle of prediction and assessment.

[0107] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of the ice and snow landscape optimization design system based on AR interactive technology provided in this application embodiment. This embodiment provides an ice and snow landscape optimization design system based on AR interactive technology, including:

[0108] The multi-source data acquisition and analysis module is used to acquire three-dimensional data models, material properties, and environmental data of ice and snow landscapes through laser scanning, environmental sensing, and material testing.

[0109] The ablation prediction module is used to construct a neural network model based on the snow and ice ablation dataset to obtain the predicted ablation situation of the snow and ice landscape.

[0110] The reflectivity risk prediction module takes the incident light intensity and direction from the optical scene data as input, sets the light source parameters, and calculates the reflectivity intensity using a Microfacet model to obtain the reflectivity intensity distribution for each ice and snow landscape area. This reflectivity intensity distribution for each ice and snow landscape area is generated by analyzing the visual impact on tourists based on the simulated reflectivity intensity distribution that might be received from their perspective, thus creating a dynamic reflectivity risk distribution characteristic.

[0111] The structural risk prediction module is used to generate dynamic distribution characteristics of structural risks based on the dynamically updated 3D data model of the snow and ice landscape and material properties, using finite element analysis software and selecting the Norton creep model. The Norton creep model is as follows:

[0112] ;

[0113] Let σ be the creep strain rate, σ be the stress, A be the creep material constant, and n be the creep exponent. The creep material properties are the creep material constant A and the creep exponent n in the Norton creep model. A and n reflect the strain trend of the creep material under stress.

[0114] The comprehensive risk assessment module is used to generate comprehensive risk assessment results for the ice and snow landscape based on the dynamic distribution characteristics of reflective risk and structural risk of the ice and snow landscape.

[0115] The AR interaction and design update module is used to visualize the comprehensive risk assessment results in the AR interactive interface based on the comprehensive risk assessment results of the ice and snow landscape, and to update the design scheme.

[0116] Embodiments of the present invention also provide an electronic device, including a memory, a processor, and a communication bus; the memory and the processor are connected via the communication bus. The memory stores an ice and snow landscape optimization design method based on AR interactive technology, which can be loaded and executed by the processor as provided in the above embodiments.

[0117] The memory can be used to store instructions, programs, code, code sets, or instruction sets. The memory may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the AR-based ice and snow landscape optimization design provided in the above embodiments. The data storage area may store data involved in the AR-based ice and snow landscape optimization design method provided in the above embodiments.

[0118] The processor may include one or more processing cores. The processor executes instructions, programs, code sets, or instruction sets stored in memory, and calls data stored in memory to perform various functions and process data as described in this application. The processor may be at least one of the following: Application-Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), controller, microcontroller, and microprocessor. It is understood that, for different devices, the electronic devices used to implement the above-described processor functions may also be other types, and the embodiments of this application do not specifically limit this.

[0119] A communication bus can include a pathway for transmitting information between the aforementioned components. The communication bus can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Communication buses can be categorized as address buses, data buses, control buses, etc.

[0120] This application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described in the above embodiments, representing the ice and snow landscape optimization design method based on AR interactive technology.

[0121] In this embodiment, a computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device. The computer-readable storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer-readable storage medium can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), spoofing random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

[0122] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0123] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions claimed in this application.

Claims

1. A method for optimizing the design of ice and snow landscapes based on AR interactive technology, characterized in that, Includes the following steps: S1. Scan the ice and snow landscape to obtain a three-dimensional data model of the ice and snow landscape; at the same time, acquire the material properties and environmental data of the ice and snow landscape; S2. Construct an ablation prediction model based on the snow and ice ablation dataset to predict the snow and ice landscape ablation and dynamically update the three-dimensional data model of the snow and ice landscape. S3. Based on the dynamically updated three-dimensional data model of the ice and snow landscape, material properties and environmental data, the reflectivity of the ice and snow landscape is predicted by the ray tracing algorithm, and the dynamic distribution characteristics of reflectivity risk are generated. S4. Based on the dynamically updated three-dimensional data model and material properties of the ice and snow landscape, predict the strain trend of the ice and snow landscape through finite element analysis and generate dynamic distribution characteristics of structural risks. S5. Based on the dynamic distribution characteristics of reflective risk and structural risk of the ice and snow landscape, generate a comprehensive risk assessment result for the ice and snow landscape; S6. Based on the comprehensive risk assessment results of the ice and snow landscape, visualize the comprehensive risk assessment results in the AR interactive interface and make selections for ice and snow landscape design.

2. The ice and snow landscape optimization design method based on AR interactive technology according to claim 1, characterized in that, The process involves scanning the ice and snow landscape to obtain a three-dimensional data model of the ice and snow landscape. Obtaining material properties and historical environmental data for ice and snow landscapes includes: S110: Obtain ice and snow landscape structure data through laser scanning, combine it with point cloud registration, register and fuse the obtained structure data, construct a three-dimensional data model of ice and snow landscape, and divide the area according to the equal area of ​​ice and snow landscape structure. S120: By analyzing the variables affecting the sublimation rate of ice and snow through the Penman-Monteith equation, the characteristic data of sublimation rate are obtained, including: the sublimation rate is determined by the density of ice and snow materials, radiation intensity, air temperature, surface temperature of ice and snow landscape, air humidity and wind speed, and historical data are collected to obtain the characteristic dataset of ice and snow melting. S130: Collect data for the Microfacet model, including the reflectivity of ice and snow materials, the refractive index of ice and snow materials, the direction of incident light, and the intensity of incident light, and set it as optical scene data.

3. The ice and snow landscape optimization design method based on AR interactive technology according to claim 2, characterized in that, Based on the snow and ice ablation dataset, an ablation prediction model is constructed to obtain the predicted ablation situation of snow and ice landscapes, including: S210: Based on the snow and ice melting feature dataset, standardize all feature data. The input layer data includes: snow and ice material density, radiation intensity, air temperature, snow and ice landscape surface temperature, air humidity, and wind speed. The output layer data is the melting rate, which is divided into training set, test set, and validation set to build a melting prediction model. S220: Based on a neural network model, the loss is calculated by inputting the training set to update the ablation prediction model; the validation set is input periodically to test the ablation prediction model; the mean square error is calculated using the test set to obtain the final ablation prediction model. S230: Based on the final ablation prediction model, the ablation rate of each region is predicted by inputting thermodynamic data of each region, and the three-dimensional data model of the ice and snow landscape is dynamically updated in combination with the three-dimensional data model of the ice and snow landscape.

4. The ice and snow landscape optimization design method based on AR interactive technology according to claim 3, characterized in that, Based on the dynamically updated 3D data model of the ice and snow landscape, material properties, and environmental data, the reflectivity of the ice and snow landscape is predicted using a ray tracing algorithm, generating dynamic distribution characteristics of reflectivity risk, including: S310: Based on the dynamically updated three-dimensional data model of the ice and snow landscape, endow the surface roughness, reflectivity, and refractive index characteristics to the three-dimensional data model of the ice and snow landscape, and construct a Microfacet model; S320: Input the incident light intensity and incident light direction in the optical scene data, set the light source parameters, and calculate the specular intensity through the Microfacet model to obtain the specular intensity distribution of each ice and snow landscape area; S330: Evaluate the impact of the specular intensity distribution of each ice and snow landscape area on human vision to obtain the dynamic distribution characteristics of the specular risk of each ice and snow landscape area.

5. The ice and snow landscape optimization design method based on AR interactive technology according to claim 1, characterized in that, Predict the stress and strain distribution of the ice and snow landscape through finite element analysis, and generate the dynamic distribution characteristics of structural risk including: S410: Import the dynamically updated three-dimensional data model of the ice and snow landscape into finite element analysis software, perform geometric cleaning and simplification, and implement regional mesh division.加密网格 in the stress concentration area and use sparse grids in large flat areas to construct a finite element model; S420: Define the creep material properties of the ice and snow landscape in the finite element model, apply gravitational acceleration, and constrain the bottom degrees of freedom; S430: Calculate the real-time strain of each area of the ice and snow landscape through a finite element solver to obtain the strain trend of each area of the ice and snow landscape, generate a strain contour map, and obtain the dynamic distribution characteristics of the structural risk of each area of the ice and snow landscape.

6. The ice and snow landscape optimization design method based on AR interactive technology according to claim 1, characterized in that, Generate the comprehensive risk assessment result of the ice and snow landscape based on the dynamic distribution characteristics of the specular risk and structural risk of the ice and snow landscape, including: Based on the dynamic distribution characteristics of the specular risk and structural risk, unify the quantification of the specular risk and structural risk to the same scale, assign weights to the specular risk score and structural risk score according to the impact caused by the risk, and obtain the comprehensive risk assessment result of each ice and snow landscape area through weighted calculation.

7. The ice and snow landscape optimization design method based on AR interactive technology according to claim 1, characterized in that, Visualize the comprehensive risk assessment result in the AR interaction interface and update the design plan, including: In the AR interaction interface, based on the comprehensive risk assessment result of each ice and snow landscape area, recommend and display the optimal design plan, and render different colors according to the optimal design plan and cover each ice and snow landscape area corresponding to the comprehensive risk level. According to the area of user interaction, dynamically update and display the real-time specular risk distribution and structural risk distribution of the interaction area.

8. An ice and snow landscape optimization design system based on AR interactive technology, applied to the method of any one of claims 1-7, characterized in that, Including: A multi-source data acquisition and analysis module for obtaining the three-dimensional data model, material properties, and environmental data of the ice and snow landscape through laser scanning, environmental sensing, and material testing; An ablation prediction module for constructing a neural network model based on the ice and snow ablation data set to obtain the predicted ablation situation of the ice and snow landscape and dynamically update the three-dimensional data model of the ice and snow landscape; A specular risk prediction module for predicting the specular intensity of the ice and snow landscape through a ray tracing algorithm based on the dynamically updated three-dimensional data model, material properties, and environmental data of the ice and snow landscape, and generating the dynamic distribution characteristics of the specular risk; A structural risk prediction module for predicting the stress and strain distribution of the ice and snow landscape through finite element analysis based on the dynamically updated three-dimensional data model and material properties of the ice and snow landscape, and generating the dynamic distribution characteristics of the structural risk; The comprehensive risk assessment module is used to generate comprehensive risk assessment results for the ice and snow landscape based on the dynamic distribution characteristics of reflective risk and structural risk of the ice and snow landscape. The AR interaction and design update module is used to visualize the comprehensive risk assessment results in the AR interactive interface based on the comprehensive risk assessment results of the ice and snow landscape, and to update the design scheme.

9. An electronic device, characterized in that, include: A processor and a memory, wherein the memory stores a computer program; the processor implements the method as described in any one of claims 1-7 by executing the computer program.

10. A readable storage medium, characterized in that, The device stores instructions that, when executed on the device, cause the computer to perform the ice and snow landscape optimization design method based on AR interactive technology as described in any one of claims 1-7.

Images