A method for optimizing urban planning implementation display based on virtual reality technology

Abstract

The application discloses a kind of urban planning implementation display optimization methods based on virtual reality technology, real-time acquisition target city area's built environment data, and obtain planning implementation information;City planning implementation digital sand table is built in ArcGIS Pro platform, and building three-dimensional model generation is realized;Slice extraction and virtual reality roaming display are carried out, and the implementation of key area is shown;Implementation plan is evaluated using form score and style score module, and the slice needing adjustment is marked;Real-time adjustment and optimization are carried out through Oculus Rift VR helmet and Leap Motion handheld controller;The scoring process and achievement of each slice are integrated, and urban planning implementation evaluation optimization report is generated.The system applies virtual reality technology to urban planning implementation, realizes efficient, intuitive urban planning implementation slice extraction, display and optimization, and provides strong support for urban planning decision-making.

Description

Technical Field

[0001] This invention relates to the field of urban planning, specifically a method for optimizing the implementation and display of urban planning based on virtual reality technology. Background Technology

[0002] Urban planning implementation demonstrations offer a more direct and comprehensive way to showcase urban planning schemes and their implementation results. Utilizing virtual reality (VR) technology for interactive optimization of urban planning scheme implementation is a crucial method for achieving high-quality urban development in the new data environment. On one hand, traditional urban planning implementation effectiveness demonstrations only occur after the scheme has been implemented, through on-site surveys and effectiveness evaluations. Technical personnel then use computers to demonstrate the implementation results, providing feedback to planners for the next round of optimization design. This process suffers from long cycles, high manpower consumption, and the inability to provide timely feedback and adjustments, often leading to a disconnect between the initial design, implementation, and post-implementation management of urban planning. On the other hand, with advancements in information technology, urban planning schemes are no longer limited to two-dimensional blueprints. VR technology allows urban planning professionals to experience planning schemes immersively, panoramically, and interactively. However, current VR technology is limited to simulating urban planning design scenarios, providing visualization of the scheme but lacking interactive optimization and real-time implementation effect demonstrations by planners. The human-computer interaction framework is not yet fully developed, hindering effective demonstration and optimization feedback for urban planning schemes.

[0003] The virtual reality-based method for optimizing urban planning implementation is of great significance for the real-time generation and adjustment of urban planning schemes. This method addresses several issues encountered by traditional reviewers during the implementation of urban planning schemes, including the heavy workload of on-site investigations, time-consuming data analysis, long report production cycles leading to untimely feedback, and repeated revisions failing to achieve the desired effect. It enables the implementation display and interactive optimization of urban planning schemes, significantly improving the human-computer interaction efficiency for planners and reviewers in the implementation of urban planning schemes, and facilitating more effective design of urban planning schemes. Summary of the Invention

[0004] To address the shortcomings mentioned in the background section, the present invention aims to provide a method for optimizing the implementation of urban planning based on virtual reality technology. This invention can evaluate the implementation of urban planning and optimize and adjust urban planning schemes through a virtual reality interactive display platform.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] A method for optimizing the implementation and demonstration of urban planning based on virtual reality technology includes the following steps:

[0007] Step 1: Real-time data collection of site conditions and urban planning implementation status.

[0008] Vector data of the built environment of the target urban area was acquired through the OpenStreetMap open platform, including elevation, green space, water system, road, and block boundary data. DJI drones equipped with high-precision GPS modules were used to obtain vertical, side, and surface texture images of ground features. DJI drones equipped with LiDAR modules were used to perform high-precision terrain and object measurements on the site, extracting real-time planning implementation data, including point cloud data of terrain, building locations, building heights, building outlines, and building facade details. Planning scheme data was collected and identified using laser scanning equipment and OCR algorithms to construct a planning scheme indicator library, including planning implementation cycles, construction sequences, planned areas, key area boundaries, block floor area ratios, green space ratios, and architectural style indicators from urban planning schemes.

[0009] Step Two: Construction of Digital Sand Table for Urban Planning Implementation

[0010] The data obtained in Step 1 is input into the ArcGIS Pro geographic information system platform. The planning scheme indicator library is connected with the built environment vector data of the target city area according to the plot number to obtain site vector data containing planning scheme indicators for each plot. A deep learning classifier is then used to automatically classify the point cloud data to obtain building points. The building points and feature images are input into ContextCapture 3D modeling software to generate 3D building models containing building facade textures. The 3D models are then input into the ArcGIS Pro geographic information system platform and spatially matched with the site vector data to obtain a digital sandbox for urban planning implementation. This data is then distributed and stored in the cloud via Amazon Web Services (AWS).

[0011] Step 3: Extraction of urban planning slices and virtual reality tour display

[0012] The urban planning implementation digital sand table constructed in step two is divided into N 1km*1km grid tiles. Overlay analysis is performed using the ArcGIS Pro geographic information system platform to obtain key area tiles. K tiles are extracted using a weighted extraction algorithm, and these extracted tiles are loaded into an UltraLAB workstation powered by the Unity 3D engine for real-time rendering and display.

[0013] Step 4: Evaluation of the Implementation of Urban Planning Slices

[0014] A morphological scoring module was used to calculate the plot ratio and green space ratio of the extracted slices. The weighted sum of the plot ratio and green space ratio calculation results yielded the morphological score of the extracted slices. A landscape scoring module was used to calculate the material texture and color matching degree between the implementation scheme and the planning scheme in the extracted slices. The calculation results were normalized and then summed to obtain the landscape score of the extracted slices. Finally, the morphological score and landscape score of the extracted slices were summed and sorted. The 20% of slices with the lowest scores were displayed in red and marked as adjustment slices.

[0015] Step 5: Optimization and Adjustment of Urban Planning Scheme

[0016] Reviewers, wearing Oculus Rift VR headsets and Leap Motion handheld controllers, roamed through virtual reality scenes. Using the Leap Motion handheld controllers, they tracked the user's movements and gestures in real time, correcting the building height and floor area ratio information of the proposed solutions, and adjusting information such as material texture and color, thereby completing the optimization and adjustment of the solutions.

[0017] Step Six: Generate an evaluation and optimization report on the implementation of urban planning.

[0018] The evaluation process and deliverables of the implementation plans for each segment are integrated and summarized to form a review report on the implementation, evaluation, and modification of the planning scheme.

[0019] Furthermore, the deep learning classifier is a convolutional neural network model trained in a supervised manner based on a point cloud dataset, which can automatically classify unprocessed point cloud data.

[0020] Furthermore, the weight extraction algorithm normalizes the weights of elements in the set and transforms them into a probability distribution, then extracts elements by generating random numbers between 0 and 1. Each grid slice contains three weighting factors: a key area weighting factor, a planning time series weighting factor, and a sampling frequency adjustment factor. The key area weighting factor is assigned a value of 1 when the slice is a key slice, and a value of 0.5 when the slice is a non-key slice. The planning time series weighting factor is calculated using the following formula:

[0021]

[0022] Where B(t) is the time-series weighting factor for the planning, t a Let t be the date on day t. b t0 is the construction date of the slice, and t0 is the planning implementation date. λ is a positive parameter.

[0023] The formula for calculating the number of extractions adjustment factor is as follows:

[0024]

[0025] Where C i This is the extraction count adjustment factor, where n is the number of times slice i has been extracted.

[0026] The formula for calculating the probability that slice i is selected on day t is:

[0027]

[0028] Where A i and A j B represents the weighting factor for the key regions of detection slices i and j, respectively. i (t) and B j (t) represent the planning time-series weighting factors for detection slices i and j, respectively, C i and C j These are adjustment factors for the number of extractions of detection slices i and j, respectively.

[0029] Furthermore, the morphological scoring module calculates the plot ratio R = S(total building area of ​​the extracted slice) / S(total land area of ​​the extracted slice) and the green space ratio G = S(green space area of ​​the extracted slice) / S(total land area of ​​the extracted slice) for the input extracted slice. The calculation formula F = 1*R + 5.5*G is used to weight and add the plot ratio and green space ratio calculation results to obtain the morphological scoring result F of the extracted slice.

[0030] Furthermore, the aforementioned appearance scoring module refers to merging the implementation scheme and the planning scheme, and using the Gray-Level Co-occurrence Matrix (GLCM) method to calculate the gray-level images of the material texture of the extracted slices for both the implementation scheme and the planning scheme to obtain the co-occurrence matrix. The eigenvalues ​​X of the co-occurrence matrix are then calculated to determine the material texture matching degree K.

[0031] K = -|X_implementation scheme characteristic value - X_planning scheme characteristic value|

[0032] For the extracted slices, calculate the color histogram of the building facade under white light illumination, and calculate the color matching degree X between the implementation scheme Q and the planning scheme P:

[0033]

[0034] Among them, Q i P i Here, represents the value of the i-th point in the histogram, and N is the number of points in the histogram. Then, the results of the material texture matching degree and color matching degree calculations are normalized using the following formula:

[0035]

[0036] The normalized material texture matching degree and color matching degree results of the extracted slices are weighted and summed using I = K + X to obtain the appearance score result I of the extracted slices.

[0037] Furthermore, the adjustment slice labeling is achieved by adding the morphology score and appearance score to obtain a comprehensive score result C = F + I. The comprehensive score results are sorted, and the slices with the lowest 20% of the scores are labeled as adjustment slices. The adjustment slices are then displayed in red on the UltraLAB workstation platform driven by the Unity 3D engine.

[0038] Furthermore, the urban planning scheme optimization and adjustment operation refers to the reviewers wearing Oculus Rift VR headsets and Leap Motion handheld controllers to roam in a virtual reality scene, locate the adjustment slice displayed in red, and modify the building height and plot ratio information of the implemented scheme in conjunction with the information display panel, and adjust the material texture and color. The Leap Motion handheld controller will track the user's movements and gesture commands in real time.

[0039] Furthermore, the specific method for correcting the building height of the implemented scheme is as follows: the reviewer selects the building height attribute, and the information display panel will pop up information on the average building height and maximum building height limit of the adjustment slice. At the same time, the workstation platform driven by the Unity 3D engine will simulate the maximum building height limit of the 3D adjustment slice and render the part of the building in the adjustment slice that exceeds the maximum building height limit as RGB (255, 0, 0) color. The reviewer swings his right hand up and down twice to open the edit mode, and can modify the average building height and maximum building height limit values ​​in the information display panel. After the adjustment is completed, he draws circles with both hands to save the adjustment result.

[0040] Furthermore, the specific method for correcting the floor area ratio information of the implemented scheme is as follows: when the reviewer selects the floor area ratio attribute, the adjustment slice will be quickly displayed in a bird's-eye view. The information display panel will pop up the street name, street number and street floor area ratio information contained in the adjustment slice. At the same time, the UltraLAB workstation platform driven by the Unity 3D engine will render the streets in the adjustment slice that exceed the floor area ratio limit as RGB (0, 0, 255) colors. The reviewer will swing his right hand up and down twice to open the edit mode, select the street with his left hand, modify the floor area ratio value of the street in the information display panel, and save the adjustment result by drawing circles with both hands after the adjustment is completed.

[0041] Furthermore, the method for adjusting information such as material texture and color is as follows: when the reviewer selects the material texture and color attributes, the adjustment slice will quickly switch to the human perspective (viewpoint height 1.8m) and automatically activate the walkthrough mode. The walkthrough will stop after the reviewer raises their right hand and taps twice. Then, by swinging their right hand up and down twice, the reviewer can activate the editing mode. The reviewer can select elements using their left hand, and the information display panel will automatically pop up to show the material texture and color attributes. The reviewer can adjust and modify the material texture and color. After adjustment, the reviewer can save the results by drawing circles with both hands and continue the walkthrough until the solution is adjusted. The UltraLAB workstation platform, powered by the Unity 3D engine, will display the optimized solution in real time.

[0042] The beneficial effects of this invention are:

[0043] 1. This invention extracts slices from the digital sand table of urban planning implementation through a weighted extraction algorithm, ensuring the universality of slice extraction while improving the targeting of extraction. It effectively reduces the performance requirements of real-time rendering and display equipment and improves the efficiency of planners in reviewing and optimizing urban planning implementation results.

[0044] 2. This invention improves the timeliness of displaying planning implementation results by collecting planning implementation data in real time and calculating the morphological and landscape scores of extracted slices. It enables continuous tracking and evaluation of planning implementation results, breaks through the subjective judgment of reviewers in the past evaluation of planning implementation, provides an objective basis for optimizing and adjusting urban planning schemes, and ensures the feasibility of optimized urban planning schemes.

[0045] 3. This invention uses a virtual reality display and interaction platform and equipment to display the implementation status of planning and the evaluation results of the implementation status, and tracks action and gesture command information, making the expression of evaluation results more intuitive, realizing the real-time optimization of urban planning schemes, and improving the efficiency of urban planning scheme optimization and adjustment. Attached Figure Description

[0046] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0047] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] A method for optimizing the implementation and demonstration of urban planning based on virtual reality technology, such as Figure 1 As shown, it includes the following steps:

[0049] I. Real-time Data Collection of Site Conditions and Urban Planning Implementation. Built-up environment vector data for the target urban area is acquired through the OpenStreetMap platform, including elevation, green space, water system, road, and street boundary data. DJI drones equipped with high-precision GPS modules are used to obtain vertical, side, and surface texture images of ground features. DJI drones equipped with LiDAR modules are used to perform high-precision terrain and object measurements on the site, extracting real-time planning implementation data, including point cloud data of terrain, building locations, building heights, building outlines, and building facade details. Planning scheme data is collected and identified using laser scanning equipment and OCR algorithms to construct a planning scheme indicator library, including planning implementation cycles, construction sequences, planned areas, key area boundaries, street floor area ratio, green space ratio, and architectural style indicators from urban planning schemes.

[0050] II. Construction of a Digital Sand Table for Urban Planning Implementation. The data obtained in Step 1 is input into the ArcGIS Pro geographic information system platform. The planning scheme indicator library is connected to the built environment vector data of the target urban area according to the plot number to obtain site vector data containing planning scheme indicators for each plot. A deep learning classifier is then used to automatically classify the point cloud data to obtain building points. The building points and feature images are input into ContextCapture 3D modeling software to generate 3D building models containing building facade textures. The 3D models are then input into the ArcGIS Pro geographic information system platform and spatially matched with the site vector data to obtain a digital sand table for urban planning implementation. This sand table is then distributed and stored in the cloud via Amazon Web Services (AWS) cloud servers.

[0051] The deep learning classifier is a convolutional neural network model trained in a supervised manner based on a point cloud dataset, which can automatically classify unprocessed point cloud data.

[0052] III. Urban Planning Tile Extraction and Virtual Reality Walkthrough Display. The urban planning implementation digital sandbox constructed in Step II is divided into N 1km*1km grid tiles. Overlay analysis is performed using the ArcGIS Pro geographic information system platform to obtain key area tiles. K tiles are extracted using a weighted extraction algorithm, and these extracted tiles are loaded into an UltraLAB workstation powered by the Unity 3D engine for real-time rendering and display.

[0053] The weight extraction algorithm normalizes the weights of elements in the set and transforms them into a probability distribution, then extracts elements by generating random numbers between 0 and 1. Each grid slice contains three weighting factors: a key area weighting factor, a planning time series weighting factor, and a sampling frequency adjustment factor. The key area weighting factor is assigned a value of 1 when the slice is a key slice, and a value of 0.5 when the slice is not a key slice. The planning time series weighting factor is calculated using the following formula:

[0054]

[0055] Where B(t) is the time-series weighting factor for the planning, t a Let t be the date on day t. b t0 is the construction date of the slice, and t0 is the planning implementation date. λ is a positive parameter.

[0056] The formula for calculating the number of extractions adjustment factor is as follows:

[0057]

[0058] Where C i This is the extraction count adjustment factor, where n is the number of times slice u has been extracted.

[0059] The formula for calculating the probability that slice i is selected on day t is:

[0060]

[0061] Where A i and A j B represents the weighting factor for the key regions of detection slices i and j, respectively. i (t) and B j (t) represent the planning time-series weighting factors for detection slices i and j, respectively, C i and C j These are adjustment factors for the number of extractions of detection slices i and j, respectively.

[0062] IV. Evaluation of the Implementation of Urban Planning Slices

[0063] A morphological scoring module was used to calculate the plot ratio and green space ratio of the extracted slices. The weighted sum of the plot ratio and green space ratio calculation results yielded the morphological score of the extracted slices. A landscape scoring module was used to calculate the material texture and color matching degree between the implementation scheme and the planning scheme in the extracted slices. The calculation results were normalized and then summed to obtain the landscape score of the extracted slices. Finally, the morphological score and landscape score of the extracted slices were summed and sorted. The 20% of slices with the lowest scores were displayed in red and marked as adjustment slices.

[0064] The morphological scoring module calculates the plot ratio R = S(total building area of ​​the extracted slice) / S(total land area of ​​the extracted slice) and the green space ratio G = S(green space area of ​​the extracted slice) / S(total land area of ​​the extracted slice) for the input extracted slice. It uses the calculation formula F = 1*R + 5.5*G to weightedly add the plot ratio and green space ratio calculation results to obtain the morphological scoring result F of the extracted slice.

[0065] The aforementioned appearance scoring module refers to the fusion of the implementation scheme and the planning scheme. For the extracted slices, the Gray-Level Co-occurrence Matrix (GLCM) method is used to calculate the gray-level images of the material texture of both the implementation scheme and the planning scheme to obtain the co-occurrence matrix. The eigenvalues ​​X of the co-occurrence matrix are then calculated, and the material texture matching degree K is calculated.

[0066] K = -|X_implementation scheme characteristic value - X_planning scheme characteristic value|

[0067] For the extracted slices, calculate the color histogram of the building facade under white light illumination, and calculate the color matching degree X between the implementation scheme Q and the planning scheme P:

[0068]

[0069] Among them, Q i P i Here, represents the value of the i-th point in the histogram, and N is the number of points in the histogram. Then, the results of the material texture matching degree and color matching degree calculations are normalized using the following formula:

[0070]

[0071] The normalized material texture matching degree and color matching degree results of the extracted slices are weighted and summed using I = K + X to obtain the appearance score result I of the extracted slices.

[0072] The adjustment slice labeling is achieved by adding the shape score and appearance score to obtain a comprehensive score result C = F + I. The comprehensive score results are sorted, and the slices with the lowest 20% of the scores are labeled as adjustment slices. The adjustment slices are then displayed in red in the UltraLAB workstation platform driven by the Unity 3D engine.

[0073] V. Optimization and Adjustment of Urban Planning Schemes. Reviewers, wearing Oculus Rift VR headsets and Leap Motion handheld controllers, roamed in a virtual reality scene. Using the Leap Motion controllers, they tracked the user's movements and gestures in real time, correcting the building height and floor area ratio information of the implemented scheme, and adjusting information such as material texture and color, thereby completing the optimization and adjustment of the scheme.

[0074] The urban planning scheme optimization and adjustment operation refers to the reviewers wearing Oculus Rift VR headsets and LeapMotion handheld controllers to roam in a virtual reality scene, locate the adjustment slice displayed in red, and modify the building height and plot ratio information of the implemented scheme, as well as adjust the material texture and color, in conjunction with the information display panel. The LeapMotion handheld controller will track the user's movements and gesture commands in real time.

[0075] The specific method for correcting the building height of the implemented scheme is as follows: the reviewer selects the building height attribute, and the information display panel will pop up the information of the average building height and maximum building height limit of the adjustment slice. At the same time, the workstation platform driven by the Unity 3D engine will simulate the maximum building height limit of the 3D adjustment slice and render the part of the building in the adjustment slice that exceeds the maximum building height limit as RGB (255, 0, 0) color. The reviewer swings his right hand up and down twice to open the edit mode, and can modify the average building height and maximum building height limit values ​​in the information display panel. After the adjustment is completed, he draws circles with both hands to save the adjustment result.

[0076] The specific method for correcting the floor area ratio information of the implemented scheme is as follows: when the reviewer selects the floor area ratio attribute, the adjustment slice will be quickly displayed in a bird's-eye view. The information display panel will pop up the street name, street number and street floor area ratio information contained in the adjustment slice. At the same time, the UltraLAB workstation platform driven by the Unity 3D engine will render the street in the adjustment slice that exceeds the floor area ratio limit as RGB (0, 0, 255) color. The reviewer will swing his right hand up and down twice to open the edit mode, select the street with his left hand, modify the floor area ratio value of the street in the information display panel, and save the adjustment result by drawing circles with both hands after the adjustment is completed.

[0077] The method for adjusting material texture and color information is as follows: When the reviewer selects the material texture and color attributes, the adjustment slice will quickly switch to the human perspective (viewpoint height 1.8m) and automatically activate the walkthrough mode. The walkthrough will stop after the reviewer raises their right hand and taps twice. Then, by swinging their right hand up and down twice, the reviewer can activate the edit mode. The reviewer can use their left hand to select elements, and the information display panel will automatically pop up to show the material texture and color attributes. The reviewer can adjust and modify the material texture and color. After adjustment, the reviewer can save the results by drawing circles with both hands and continue the walkthrough until the solution is adjusted. The UltraLAB workstation platform, powered by the Unity 3D engine, will display the optimized solution in real time.

[0078] Step Six: Generate an evaluation and optimization report on the implementation of urban planning.

[0079] The evaluation process and deliverables of the implementation plans for each segment are integrated and summarized to form a review report on the implementation, evaluation, and modification of the planning scheme.

Claims

1. A method for optimizing the implementation and demonstration of urban planning based on virtual reality technology, characterized in that, Includes the following steps: Step 1: Real-time data collection of site conditions and urban planning implementation status. The built environment vector data of the target urban area is obtained through the OpenStreetMap open platform, including elevation, green space, water system, road and block boundary data; DJI drones equipped with high-precision GPS modules are used to obtain vertical, side and surface images of ground features, and DJI drones equipped with LiDAR modules are used to conduct high-precision terrain and object measurements of the site, extracting planning implementation data in real time, including point cloud data of terrain, building location, building height, building outline and building facade details; planning scheme data is collected and identified through laser scanning equipment and OCR algorithms to build a planning scheme indicator library, including planning implementation cycle, construction sequence, planning area, key area boundaries, block floor area ratio, green space ratio and architectural style indicators in urban planning schemes; Step Two: Construction of Digital Sand Table for Urban Planning Implementation The data obtained in step one is input into the ArcGIS Pro geographic information system platform. The planning scheme indicator library is connected with the built environment vector data of the target city area according to the plot number to obtain site vector data containing planning scheme indicators of each plot. A deep learning classifier is used to automatically classify the point cloud data to obtain building points. The building points and ground feature images are input into ContextCapture 3D modeling software to generate 3D building models containing building facade textures. The 3D models are input into the ArcGIS Pro geographic information system platform and spatially matched with the site vector data to obtain a digital sandbox for urban planning implementation. The data is then distributed and stored in the cloud via AWS cloud servers. Step 3: Extraction of urban planning slices and virtual reality tour display The digital sand table for urban planning implementation constructed in step two is divided into N 1km*1km grid tiles. The ArcGIS Pro geographic information system platform is used for overlay analysis to obtain key area tiles. K tiles are extracted using a weighted extraction algorithm, and the extracted tiles are loaded into an UltraLAB workstation powered by the Unity 3D engine for real-time rendering and display. Step 4: Evaluation of the Implementation of Urban Planning Slices The morphological scoring module is used to calculate the plot ratio and green space ratio of the extracted slices. The plot ratio and green space ratio calculation results are weighted to obtain the morphological score of the extracted slices. The landscape scoring module is used to calculate the material texture matching degree and color matching degree between the implementation scheme and the planning scheme in the extracted slices. The calculation results are normalized and then added together to obtain the landscape score of the extracted slices. Finally, the morphological score and landscape score of the extracted slices are added together and sorted. The 20% of slices with the lowest scores are displayed in red and marked as adjustment slices. Step 5: Evaluation of the Implementation of Urban Planning Slices Reviewers, wearing Oculus Rift VR headsets and Leap Motion handheld controllers, roamed through virtual reality scenes. Using the Leap Motion handheld controllers, they tracked the user's movements and gestures in real time, corrected the building height and floor area ratio information of the proposed solutions, and adjusted the material texture and color information, thereby completing the optimization and adjustment of the solutions. Step Six: Generate an evaluation and optimization report on the implementation of urban planning. The evaluation process and deliverables of the implementation plans for each segment are integrated and summarized to form a review report on the implementation, evaluation, and modification of the planning scheme.

2. The method for optimizing urban planning implementation based on virtual reality technology according to claim 1, characterized in that, The deep learning classifier in step two is a convolutional neural network model trained in a supervised manner based on a point cloud dataset, which can automatically classify unprocessed point cloud data.

3. The method for optimizing urban planning implementation based on virtual reality technology according to claim 2, characterized in that, The weight extraction algorithm in step three involves normalizing the weights of elements in the set and converting them into a probability distribution, then extracting elements by generating random numbers between 0 and 1. Each grid slice contains three weighting factors: a key area weighting factor, a planning time series weighting factor, and a sampling frequency adjustment factor. The key area weighting factor is assigned a value of 1 when the slice is a key slice, and a value of 0.5 when the slice is a non-key slice. The planning time series weighting factor is calculated using the following formula: Where B(t) is the time-series weighting factor for the planning, t a Let t be the date on day t. b t0 is the construction date of the slice, t0 is the planning implementation date; λ is a positive parameter; The formula for calculating the number of extractions adjustment factor is as follows: Where C i The number of extractions is adjusted by n, where n is the number of times slice i has been extracted. The formula for calculating the probability that slice i is selected on day t is: Where A i and A j B represents the weighting factor for the key regions of detection slices i and j, respectively. i (t) and B j (t) represent the planning time-series weighting factors for detection slices i and j, respectively, C i and C j These are adjustment factors for the number of extractions of detection slices i and j, respectively.

4. The method for optimizing urban planning implementation based on virtual reality technology according to claim 3, characterized in that, The morphological scoring result in step four refers to the calculation of the plot ratio R = total building area of ​​the extracted slice / total land area of ​​the extracted slice, and the calculation of the green space ratio G = green space area of ​​the extracted slice / total land area of ​​the extracted slice. The calculation formula F = 1*R + 5.5*G is used to weight and add the plot ratio and green space ratio calculation results to obtain the morphological scoring result F of the extracted slice.

5. The method for optimizing urban planning implementation based on virtual reality technology according to claim 4, characterized in that, The appearance scoring result in step four refers to the fusion of the implementation scheme and the planning scheme. For the extracted slices, the grayscale co-occurrence matrix method is used to calculate the material texture grayscale images of the implementation scheme and the planning scheme respectively to obtain the co-occurrence matrix. The eigenvalue X of the co-occurrence matrix is ​​then calculated, and the material texture matching degree K is calculated. K = -|Eigenvalue of the X-Scheme - Eigenvalue of the X-Planning Scheme| For the extracted slices, calculate the color histogram of the building facade under white light illumination, and calculate the color matching degree X between the implementation scheme Q and the planning scheme P: Among them, Q i P i Here, represents the value of the i-th point in the histogram, and N is the number of points in the histogram. Then, the results of the material texture matching degree and color matching degree calculations are normalized using the following formula: The normalized material texture matching degree and color matching degree results of the extracted slices are weighted and summed using I = K + X to obtain the appearance score result I of the extracted slices.

6. The method for optimizing urban planning implementation and display based on virtual reality technology according to claim 5, characterized in that, In step four, the adjustment slices are labeled by adding the shape score and appearance score to obtain the comprehensive score result C = F + I. The comprehensive score results are sorted, and the slices with the lowest 20% of the scores are labeled as adjustment slices. The adjustment slices are displayed in red in the UltraLAB workstation platform driven by the Unity 3D engine.

7. The method for optimizing urban planning implementation based on virtual reality technology according to claim 6, characterized in that, The urban planning scheme optimization and adjustment operation in step five refers to the reviewers wearing Oculus Rift VR headsets and Leap Motion handheld controllers to roam in a virtual reality scene, locate the adjustment slice displayed in red, and modify the building height and plot ratio information of the implemented scheme in conjunction with the information display panel, and adjust the material texture and color. The Leap Motion handheld controller will track the user's movements and gesture commands in real time.

8. The method for optimizing urban planning implementation and display based on virtual reality technology according to claim 7, characterized in that, The specific method for correcting the building height of the implemented scheme in step five is as follows: the reviewer selects the building height attribute, and the information display panel will pop up information on the average building height and maximum building height limit of the adjustment slice. At the same time, the UltraLAB workstation platform driven by the Unity 3D engine will simulate the maximum building height limit of the 3D adjustment slice and render the part of the building in the adjustment slice that exceeds the maximum building height limit as RGB (255, 0, 0) color. The reviewer swings his right hand up and down twice to open the edit mode, modifies the average building height and maximum building height limit values ​​in the information display panel, and saves the adjustment result by drawing circles with both hands after the adjustment is completed.

9. The method for optimizing urban planning implementation and display based on virtual reality technology according to claim 8, characterized in that, The specific method for correcting the floor area ratio information of the implemented scheme in step five is as follows: When the reviewer selects the floor area ratio attribute, the adjustment slice will be quickly displayed in a bird's-eye view. The information display panel will pop up the street name, street number and street floor area ratio information contained in the adjustment slice. At the same time, the UltraLAB workstation platform driven by the Unity 3D engine will render the streets in the adjustment slice that exceed the floor area ratio limit as RGB (0, 0, 255) colors. The reviewer will swing his right hand up and down twice to open the edit mode, select the street with his left hand, modify the floor area ratio value of the street in the information display panel, and save the adjustment result by drawing circles with both hands after the adjustment is completed.

10. The method for optimizing urban planning implementation and display based on virtual reality technology according to claim 9, characterized in that, The method for adjusting material texture and color information in step five is as follows: When the reviewer selects the material texture and color attributes, the adjustment slice will quickly switch to the human perspective and automatically start the roaming mode; after the reviewer raises their right hand and taps twice, the roaming will stop, and then the reviewer will swing their right hand up and down twice to open the editing mode. The reviewer uses their left hand to select elements, and the information display panel will automatically pop up to display the material texture and color attributes. The reviewer adjusts and modifies the material texture and color, and after the adjustment is completed, they draw circles with both hands to save the adjustment results and continue roaming until the solution is adjusted. The UltraLAB workstation platform driven by the Unity 3D engine will display the optimized effect of the solution in real time.

Images