A real estate surveying and mapping method and system based on machine vision

Abstract

The present invention discloses a real estate surveying and mapping method and system based on machine vision, which relates to the technical field of visual surveying and mapping. The method and system quantify the image quality and eliminate redundant data by calculating and evaluating the image quality index Tzls, thereby reducing the work pressure of subsequent data processing. The method is combined with an image acquisition component and uses a multi-source data fusion technology to improve the environmental adaptability of image surveying and mapping. The method comprehensively calculates the total fit degree Qhd by comparing the geometric shapes and textures of a pre-disaster model with those of a post-disaster model. The method divides the total fit degree Qhd into gears according to a preset fit threshold value, and clarifies the degree of damage to the affected buildings. Finally, based on a surveying and mapping data set, the damage characteristics of the building are extracted, the damage index Shzs is calculated and evaluated, and the degree of damage to the building is quantified. A suggestion generation unit is used to provide multi-level repair suggestions from comprehensive reconstruction to minor maintenance, so as to meet the repair needs of buildings with different degrees of damage. Meanwhile, targeted repair plans are provided according to different degrees of damage, so as to optimize resource allocation and avoid resource waste.

Description

Technical Field

[0001] The present invention relates to the field of visual surveying and mapping technology, and in particular to a real estate surveying and mapping method and system based on machine vision. Background Art

[0002] The real estate surveying and mapping system is a system that uses modern technology to conduct real estate and land surveying and mapping. Its background technologies include GPS, remote sensing technology, geographic information system GIS, etc. Through these technologies, the system can accurately measure and record geospatial data, and realize functions such as land boundary determination, cadastral management, and land use planning. The real estate surveying and mapping system has important applications in real estate development, land management, urban planning and other fields, improving the efficiency and accuracy of surveying and mapping work, and helping to ensure the rational use of land resources and the sustainability of social and economic development.

[0003] In the invention patent with application number 202311514609.6, a real estate surveying and mapping method is disclosed, including: acquiring a SAR image; generating graph structure data based on the acquired SAR image; inputting the graph structure data into an image processing model, and outputting a depth value or elevation value corresponding to a pixel of the SAR image, and a result of whether the pixel belongs to a building; generating a depth map or elevation map of the same size as the SAR image based on the depth value or elevation value output by the first fully connected layer, and marking the pixels belonging to the building; in the face of the problem that SAR images are difficult to accurately analyze the outline of buildings due to the complex secondary reflection effect between high-rise urban buildings with complex configurations, the present invention eliminates dihedral interference through the model branch of graph coding, and then analyzes the building outline by comprehensively analyzing the features of the original image, and the granularity of the processed results can be used for the requirements of real estate measurement.

[0004] However, in actual applications, the system is only suitable for simple urban high-rise building mapping; the above technical solution still has some technical shortcomings when applied to post-disaster restoration mapping, including limited data processing conditions, poor environmental adaptability and poor real-time performance; first, this method involves the generation of multiple images, and if there are abnormalities in the SAR image, the generated image will be inaccurate, which will affect the mapping results, the calculation amount is large, and the requirements for resources and the environment are high; secondly, there are many interference factors in the complex urban environment, such as the height, density and material reflection characteristics of the building, which may affect the analysis effect of the SAR image and cause unstable results; finally, due to the complex processing flow, it is difficult to meet the needs of real-time mapping, and it is not friendly to application scenarios that need to quickly obtain mapping results; and after a natural disaster, the terrain and building structure change significantly, and SAR images are difficult to provide accurate building contour information, and the model is difficult to adapt to sudden changes in environmental characteristics. Summary of the invention

[0005] Technical issues solved

[0006] In view of the deficiencies of the prior art, the present invention provides a real estate surveying and mapping method and system based on machine vision, which solves the problems mentioned in the background technology.

[0007] Technical Solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: a real estate surveying and mapping system based on machine vision, including a surveying and mapping data acquisition module, a structural data processing module, a surveying and mapping model building module, a damage feature analysis module and a result presentation module;

[0009] The surveying and mapping data acquisition module is used to collect images of the disaster-stricken area; first, the image acquisition component is deployed, then the surveying and mapping area is divided, and finally, according to the surveying and mapping area, the acquisition route of the image acquisition component is planned to collect image data of the disaster-stricken area in real time;

[0010] The structural data processing module is used to process the collected image data of the disaster-stricken area; first, the image data of the disaster-stricken area is preprocessed, including denoising, splicing, 3D processing and format conversion, and all data are dimensionlessly processed, and then the collected data is extracted and screened, and the extracted and screened data are constructed as a surveying and mapping data set;

[0011] The mapping model building module is used to perform three-dimensional reconstruction based on the mapping data set and the historical building data, and generate a pre-disaster model and a post-disaster model respectively; and optimize and semantically segment the pre-disaster model, and finally calculate the total fit degree Qhd of the pre-disaster model and the post-disaster model, and divide the total fit degree Qhd into three levels: high, medium, and low;

[0012] The damage characteristic analysis module is used to analyze the damage degree of buildings after the disaster; according to the damage condition of the buildings, the damage index Shzs is calculated, and the damage degree of the buildings in the disaster area is evaluated using the damage index Shzs;

[0013] The result presentation module is used to analyze the potential risks of the affected buildings and give reconstruction suggestions based on the total fit degree Qhd combined with the damage index Shzs; finally, the model analysis results and reconstruction suggestions are displayed through digital maps, and a visual map is generated using GIS software.

[0014] Preferably, the surveying and mapping data acquisition module includes a preparation unit, a route planning unit and an acquisition unit; the preparation unit is used to deploy image acquisition components, including using a drone equipped with a high-definition camera to take aerial photos of the disaster-stricken area to obtain full-view data of the disaster-stricken area; secondly, using a mobile camera on the ground to take real-scene detail images in the disaster-stricken area; then using a thermal imaging camera to capture infrared radiation and generate images; and finally using a LiDAR sensor to obtain three-dimensional point cloud data of the disaster-stricken area;

[0015] The route planning unit obtains the basic map of the disaster area through the GIS system or other map services, determines the specific area that needs to be surveyed, divides the surveyed area into multiple sub-areas, determines the boundaries of each sub-area, and numbers each sub-area, including QY 1 , QY 2 , QY 3 、...、QY n , n represents the total number of sub-areas; finally, the flight route of the UAV is planned based on the coverage, overlap, flight altitude and safety;

[0016] The acquisition unit installs image acquisition software in the image acquisition component, performs equipment debugging, and then performs acquisition, and transmits the acquired image data to the storage system in real time;

[0017] Preferably, the structural data processing module includes a preprocessing unit and a screening unit; the preprocessing unit denoises the image data of the disaster-stricken area through a filter, then finds the overlapping corresponding points between the image data of the disaster-stricken area, and uses the corresponding points to splice the image data of the disaster-stricken area and generate a large-area puzzle; finally, stereo matching is performed using multi-view images to generate point cloud data, and all the image data of the disaster-stricken area are converted into a unified format, and screened after dimensionless processing.

[0018] Preferably, the screening unit is used to quantify the quality of the image data of the disaster area and evaluate the image quality index Tzls for quality screening; the specific calculation method of the image quality index Tzls is as follows:

[0019]

[0020] Wherein, Fbl represents image resolution, Ld represents image brightness, Dbd represents contrast; Jbcs represents basic image parameters, Szq represents color accuracy, Gjy represents illumination uniformity, Tcf represents the number of image repetitions, and Tzs represents the preset image repetition standard threshold; α represents the index used to adjust the basic parameters Jbcs, color accuracy Szq, and illumination uniformity Gjy of the parameter multiplication term; β represents the denominator term used to normalize the entire formula;

[0021] The screening unit compares the preset quality threshold Z with the image quality index Tzls, and the specific evaluation scheme is as follows:

[0022] If the image quality index Tzls ≥ the quality threshold Z, it means that the image quality is qualified, and the image is retained for subsequent surveying and mapping work;

[0023] If the image quality index Tzls is less than the quality threshold Z, it means that the image quality is unqualified and the image is discarded.

[0024] Preferably, the surveying and mapping model building module includes a three-dimensional reconstruction unit, a model optimization unit, a semantic segmentation unit and a model comparison unit; the three-dimensional reconstruction unit generates a post-disaster data model through a surveying and mapping data set, and then generates a pre-disaster model by collecting historical architectural surveying and mapping data; the model optimization unit smoothes the pre-disaster model and the post-disaster model, reconstructs texture and enhances details through grid optimization and accuracy improvement; the semantic segmentation unit performs semantic segmentation on the pre-disaster model by utilizing a deep learning model, and trains and fine-tunes the pre-disaster model according to specific scenarios, and finally semantically annotates each part of the pre-disaster model, including walls, roofs, roads and vegetation.

[0025] Preferably, the model comparison unit calculates the geometric fit Jhqd by comparing the geometric shapes of the pre-disaster model and the post-disaster model, and calculates the texture fit Wlqd by comparing the model texture and the texture of the actual building surface; and then associates the geometric fit Jhqd with the texture fit Wlqd to obtain the total fit Qhd, and the specific calculation method is as follows:

[0026]

[0027] Qhd=w1*Jhqd+w2*Wlqd

[0028] In the formula, N represents the total number of points, P i represents the coordinates of the i-th point in the three-dimensional model, P i ' represents the coordinates of the corresponding i-th point in the actual building; M represents the total texture block, SSIM(I j ,I j ') represents the structural similarity index of the jth texture region; SSIM represents the structural similarity index, I j Represents the image of the jth texture region in the 3D model, I j ' represents the image of the jth texture area corresponding to the actual building;

[0029] w1 and w2 represent the weight values ​​of geometric fit Jhqd and texture fit Wlqd respectively;

[0030] The model comparison unit compares the preset matching threshold with the total matching degree Qhd and divides the files by the following scheme, wherein the matching threshold ranges from [0, 1]:

[0031] If Qhd ≥ 0.7, the fit is considered high, indicating that the pre-disaster model and the post-disaster model are more than 70% consistent and the affected buildings are slightly damaged;

[0032] If 0.4≤Qhd<0.7, the fit is considered moderate, indicating that there is a 40% to 70% agreement between the pre-disaster model and the post-disaster model, and the damaged buildings are classified as moderately damaged;

[0033] If 0.4>Qhd, the fit is considered low, indicating that there is no more than 40% consistency between the pre-disaster model and the post-disaster model, and the affected buildings are severely damaged.

[0034] Preferably, the damage feature analysis module extracts damage features of the post-disaster model based on the surveying and mapping data set, including the total building area Zmj, the building crack area Lmj, the building structure deformation Jbx, the building collapse volume Jdt, the thermal anomaly area Ryc and the number of electrical fault points Dgzs;

[0035] Extract the surveying and mapping data set and calculate the damage index Shzs of the post-disaster building. The specific formula is as follows:

[0036]

[0037] Where q1, q2, q3, q4, q5 and q6 represent the weight values ​​of the total building area Zmj, the building crack area Lmj, the building structure deformation Jbx, the building collapse volume Jdt, the thermal anomaly area Ryc and the number of electrical fault points Dgzs respectively; ln represents logarithmic operation;

[0038] And 0≤q1<1, 0≤q2<1, 0≤q3<1, 0≤q4<1, 0≤q5<1, 0≤q6<1; q1+q2+q3+q4+q5+q6=1;

[0039] The damage feature analysis module compares the preset damage threshold E1 and damage threshold E2 with the damage index Shzs, and the damage threshold E1>damage threshold E2, and generates the following evaluation results:

[0040] If the damage index Shzs> the damage threshold E1, it means that the current building damage level exceeds 65%, and the first assessment result is generated;

[0041] If the damage threshold E1 ≥ the damage index Shzs ≥ the damage threshold E2, it means that the current building damage level is between 30% and 65%, and the second assessment result is generated;

[0042] If the damage threshold E2>damage index Shzs, it means that the current building damage level is less than 30%, and the third assessment result is generated.

[0043] Preferably, the result presentation module includes a suggestion generation unit and a display unit; the suggestion generation unit associates the high, medium and low results obtained by evaluating the total fit degree Qhd with the evaluation result of the damage index Shzs to give the following reconstruction suggestions:

[0044] If the total fit degree Qhd is high and the damage index Shzs is the first assessment result, it means that the damaged building is more than 70% consistent with the original building structure, which is high risk, and the serious damage will lead to potential structural instability. At this time, the building should be repaired and the building structure should be fully reinforced;

[0045] If the total fit degree Qhd is high and the damage index Shzs is the second assessment result, it means that the damaged building is more than 70% consistent with the original building structure, with a medium risk, but the damaged parts affect the building function. At this time, partial repair and reinforcement are carried out to restore the building's use function;

[0046] If the total fit Qhd is high and the damage index Shzs is the third assessment result, it means that the damaged building is more than 70% consistent with the original building structure, with low risk and overall structural stability; minor repairs and maintenance are carried out at this time;

[0047] If the overall fit Qhd is medium and the damage index Shzs is the first assessment result, it means that the damaged building is 40% to 70% consistent with the original building structure, which is high risk, and the building is unstable due to structural differences and severe damage; at this time, key repairs or partial reconstruction are carried out;

[0048] If the overall fit Qhd is medium and the damage index Shzs is the second assessment result, it means that the damaged building is 40% to 70% consistent with the original building structure, with medium risk, structural differences and medium damage affecting the safety and function of the building, and structural repair and reinforcement should be carried out at this time;

[0049] If the overall fit Qhd is medium and the damage index Shzs is the third assessment result, it means that the damaged building is 40% to 70% consistent with the original building structure, with low risk, slight structural differences and low degree of damage. At this time, surface repair and maintenance are carried out;

[0050] If the total fit Qhd is low and the damage index Shzs is the first assessment result, it means that the consistency between the damaged building and the original building structure does not exceed 40%, which is high risk, with large structural differences and serious damage, and high safety hazards. At this time, it is recommended to fully rebuild;

[0051] If the total fit Qhd is low and the damage index Shzs is the second assessment result, it means that the consistency between the damaged building and the original building structure does not exceed 40%, which is a medium risk, but the structural difference is large, and the part that needs to be repaired affects the safety of the building. In this case, it is recommended to rebuild part of the structure and repair other parts;

[0052] If the total fit Qhd is low and the damage index Shzs is the third assessment result, it means that the consistency between the damaged building and the original building structure does not exceed 40%, which is a low risk. Although the structural difference is large, the damage is light and the overall stability is stable. At this time, the damaged part should be repaired and the overall maintenance and reinforcement should be carried out.

[0053] Preferably, the display unit displays the comparative analysis results of the pre-disaster model and the post-disaster model, as well as the reconstruction suggestions for the buildings after the disaster. All the display contents are then integrated using GIS, and finally the building damage is displayed on the human-computer interaction interface.

[0054] Preferably, a real estate surveying and mapping method based on machine vision comprises the following steps:

[0055] Step 1: The surveying and mapping data acquisition module collects images of the disaster-stricken area; first, the image acquisition component is deployed, then the surveying and mapping area is divided, and finally, according to the surveying and mapping area, the acquisition route of the image acquisition component is planned to collect image data of the disaster-stricken area in real time;

[0056] Step 2, the structural data processing module processes the collected image data of the disaster-stricken area; first, the image data of the disaster-stricken area is preprocessed, including denoising, splicing, 3D processing and format conversion, and all data are dimensionlessly processed, and then the collected data is extracted and screened, and the extracted and screened data are constructed as a surveying and mapping data set;

[0057] Step 3: The surveying and mapping model building module performs three-dimensional reconstruction based on the surveying and mapping data set and the historical building data to generate a pre-disaster model and a post-disaster model respectively; and optimizes and semantically segments the pre-disaster model, and finally calculates the total fit degree Qhd of the pre-disaster model and the post-disaster model, and divides the total fit degree Qhd into three levels: high, medium, and low;

[0058] Step 4: The damage characteristic analysis module analyzes the damage degree of the buildings after the disaster; calculates the damage index Shzs according to the damage of the buildings, and uses the damage index Shzs to evaluate the damage degree of the buildings in the disaster area.

[0059] Step 5: The result presentation module analyzes the potential risks of the affected buildings and gives reconstruction suggestions based on the total fit degree Qhd and the damage index Shzs; finally, the model analysis results and reconstruction suggestions are displayed through digital maps, and a visual map is generated using GIS software.

[0060] Beneficial Effects

[0061] The present invention provides a real estate surveying and mapping method and system based on machine vision, which has the following beneficial effects:

[0062] (1) A real estate surveying and mapping method and system based on machine vision collects image data from multiple sources to provide multi-dimensional information of the disaster area; evaluates the image quality index Tzls through multiple parameter calculations, quantifies the image quality and eliminates redundant data to ensure that the quality of the retained image data meets the requirements, improves the image quality, and reduces the pressure of subsequent data processing work, while improving the accuracy and reliability of subsequent surveying and mapping work; combines image acquisition components and uses multi-source data fusion technology to improve the environmental adaptability of image surveying and mapping.

[0063] (2) This real estate surveying and mapping method and system based on machine vision compares the geometric shapes and textures of the pre-disaster model and the post-disaster model, calculates the geometric fit Jhqd and the texture fit Wlqd respectively, and combines the two to calculate the total fit Qhd, providing a multi-level model comparison method, making the fit evaluation more comprehensive and accurate; the total fit Qhd is divided into three levels of high, medium and low according to the preset fit threshold, which clarifies the degree of damage of the affected buildings and improves the scientificity and operability of the assessment; finally, based on the surveying and mapping data set, the damage characteristics of the building are extracted, including the total building area Zmj, the building crack area Lmj, the building structure deformation Jbx, the building collapsed volume Jdt, the thermal anomaly area Ryc and the number of electrical fault points Dgzs; by combining the weight values ​​of each damage feature, the damage index Shzs is calculated to quantify the degree of damage to the building, and the damage index Shzs is evaluated at the same time, generating different assessment results, and clarifying the degree of damage to the affected buildings.

[0064] (3) This real estate surveying and mapping method and system based on machine vision provides detailed data information and evaluation results through precise comparative analysis and damage assessment, enabling decision makers to make accurate judgments and decisions based on scientific data; through the suggestion generation unit, it provides multi-level repair suggestions from comprehensive reconstruction to minor maintenance, adapting to the repair needs of buildings with different degrees of damage, and improving the pertinence and effectiveness of decision-making; at the same time, it provides targeted repair plans according to different degrees of damage, optimizes resource allocation, avoids waste of resources, and improves the efficiency and effectiveness of repair work; by combining the total fit degree Qhd and the damage index Shzs, the system can adapt to a variety of post-disaster scenarios, not only limited to simple urban high-rise building mapping, but also applicable to other complex building environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 A schematic diagram of the framework structure of a real estate surveying and mapping system based on machine vision according to the present invention;

[0066] Figure 2 The present invention is a flowchart of a real estate surveying and mapping method based on machine vision. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] Example 1

[0069] See also Figure 1 , the present invention provides a real estate surveying and mapping system based on machine vision, including a surveying and mapping data acquisition module, a structural data processing module, a surveying and mapping model building module, a damage feature analysis module and a result presentation module;

[0070] The surveying and mapping data acquisition module is used to collect images of the disaster-stricken area; first, the image acquisition component is deployed, then the surveying and mapping area is divided, and finally, according to the surveying and mapping area, the acquisition route of the image acquisition component is planned to collect image data of the disaster-stricken area in real time;

[0071] The structural data processing module is used to process the collected image data of the disaster-stricken area; first, the image data of the disaster-stricken area is preprocessed, including denoising, splicing, 3D processing and format conversion, and all data are dimensionlessly processed, and then the collected data is extracted and screened, and the extracted and screened data are constructed as a surveying and mapping data set;

[0072] The mapping model building module is used to perform three-dimensional reconstruction based on the mapping data set and the historical building data, and generate a pre-disaster model and a post-disaster model respectively; and optimize and semantically segment the pre-disaster model, and finally calculate the total fit degree Qhd of the pre-disaster model and the post-disaster model, and divide the total fit degree Qhd into three levels: high, medium, and low;

[0073] The damage characteristic analysis module is used to analyze the damage degree of buildings after the disaster; according to the damage condition of the buildings, the damage index Shzs is calculated, and the damage degree of the buildings in the disaster area is evaluated using the damage index Shzs;

[0074] The result presentation module is used to analyze the potential risks of the affected buildings and give reconstruction suggestions based on the total fit degree Qhd combined with the damage index Shzs; finally, the model analysis results and reconstruction suggestions are displayed through digital maps, and a visual map is generated using GIS software.

[0075] In this embodiment, the functions of the surveying and mapping data acquisition module include image acquisition, surveying and mapping area division, acquisition route planning and real-time data acquisition; the functions of the structural data processing module include preprocessing and data extraction and screening; the functions of the surveying and mapping model establishment module include three-dimensional reconstruction, model optimization, semantic segmentation and total fit degree Qhd calculation and gear division; the functions of the damage feature analysis module include damage degree analysis, feature extraction and damage index Shzs calculation; the functions of the result presentation module include displaying comparative analysis results and generating reconstruction suggestions.

[0076] Example 2

[0077] See also Figure 1 , the surveying and mapping data acquisition module includes a preparation unit, a route planning unit and an acquisition unit; the preparation unit is used to deploy image acquisition components, including using a drone equipped with a high-definition camera to take aerial photos of the disaster-stricken area to obtain full-view data of the disaster-stricken area; secondly, using a mobile camera on the ground to take real-scene detail images in the disaster-stricken area; then using a thermal imaging camera to capture infrared radiation and generate images; finally, using a LiDAR sensor to obtain three-dimensional point cloud data of the disaster-stricken area;

[0078] The route planning unit obtains the basic map of the disaster area through the GIS system or other map services, determines the specific area that needs to be surveyed, divides the surveyed area into multiple sub-areas, determines the boundaries of each sub-area, and numbers each sub-area, including QY 1 , QY 2 , QY 3 、...、QY n , n represents the total number of sub-areas; finally, the flight route of the UAV is planned based on the coverage, overlap, flight altitude and safety;

[0079] The acquisition unit installs image acquisition software in the image acquisition component, performs equipment debugging, and then performs acquisition, and transmits the acquired image data to the storage system in real time;

[0080] In this embodiment, the drone is equipped with a high-definition camera to take aerial photos of the disaster area, quickly cover a large area, and provide high-resolution bird's-eye images; a ground camera is used to capture the details and close-up perspective of the building to supplement the deficiencies in the drone's aerial images; a thermal imaging camera is used to detect hot spots or electrical fault points after a fire; the LiDAR sensor can generate a high-precision three-dimensional model to help analyze the structure and damage of the building in detail; the image acquisition component covers the overall appearance, details, thermal anomalies and three-dimensional structure of the disaster area.

[0081] Example 3

[0082] The structural data processing module includes a preprocessing unit and a screening unit; the preprocessing unit denoises the image data of the disaster area through a filter, then finds the overlapping corresponding points between the image data of the disaster area, uses the corresponding points to splice the image data of the disaster area and generate a large-area puzzle; finally, stereo matching is performed using multi-view images to generate point cloud data, and all the image data of the disaster area are converted into a unified format, and screened after dimensionless processing.

[0083] The screening unit is used to quantify the quality of the image data of the disaster area and evaluate the image quality index Tzls for quality screening; the specific calculation method of the image quality index Tzls is as follows:

[0084]

[0085] Wherein, Fbl represents image resolution, Ld represents image brightness, Dbd represents contrast; Jbcs represents basic image parameters, Szq represents color accuracy, Gjy represents illumination uniformity, Tcf represents the number of image repetitions, and Tzs represents the preset image repetition standard threshold; α represents the index used to adjust the basic parameters Jbcs, color accuracy Szq, and illumination uniformity Gjy of the parameter multiplication term; β represents the denominator term used to normalize the entire formula;

[0086] The screening unit compares the preset quality threshold Z with the image quality index Tzls, and the specific evaluation scheme is as follows:

[0087] If the image quality index Tzls ≥ the quality threshold Z, it means that the image quality is qualified, and the image is retained for subsequent surveying and mapping work;

[0088] If the image quality index Tzls is less than the quality threshold Z, it means that the image quality is unqualified and the image is discarded.

[0089] In this embodiment, by calculating the image quality index Tzls and setting the quality threshold, automatic quality screening of image data is achieved, ensuring that high-quality image data enters the subsequent processing flow, thereby improving the efficiency and accuracy of the overall surveying and mapping work; the image resolution Fbl is used to evaluate the clarity and detail capture capability of the image. High-resolution images can capture more details, which helps to improve the accuracy of surveying and mapping and the quality of three-dimensional reconstruction; the image brightness Ld ensures that the image is within the visible range and avoids detail loss caused by being too dark or too bright. Appropriate brightness can improve the image's recognizability and detail presentation effect; the contrast Dbd enhances the structure and edge details in the image, making it easier to distinguish different building parts and materials. High contrast helps to more accurately identify and stitch images in subsequent processing; the basic image parameters Jbcs unify the basic attributes of the image, such as size, format and color depth to ensure data consistency and standardization, which is helpful for subsequent data processing and analysis; color accuracy Szq ensures that the color of the image is consistent with the actual scene, improves the accuracy of identifying building materials and signs of damage, and accurate color restoration is particularly important for certain special imaging (such as thermal imaging); lighting uniformity Gjy avoids areas that are too bright or too dark in the image, ensures uniform lighting, and ensures that the details of all parts can be clearly presented, which has a great impact on the overall quality of the image and the accuracy of subsequent processing; the number of image repetitions Tcf improves the reliability and integrity of the data through multiple sampling and multi-perspective images. Appropriate repeated images are used for denoising, image stitching and accuracy improvement; the total number of images Tzs ensures that there is enough data to cover all details of the surveying and mapping area, providing comprehensive surveying and mapping information. More image data improves the comprehensiveness and accuracy of the assessment.

[0090] Example 4

[0091] The surveying and mapping model building module includes a three-dimensional reconstruction unit, a model optimization unit, a semantic segmentation unit and a model comparison unit; the three-dimensional reconstruction unit generates a post-disaster data model through a surveying and mapping data set, and then generates a pre-disaster model by collecting historical architectural surveying and mapping data; the model optimization unit smoothes the pre-disaster model and the post-disaster model, reconstructs texture and enhances details through grid optimization and accuracy improvement; the semantic segmentation unit performs semantic segmentation on the pre-disaster model by using a deep learning model, and trains and fine-tunes the pre-disaster model according to specific scenarios, and finally semantically annotates each part of the pre-disaster model, including walls, roofs, roads and vegetation.

[0092] The model comparison unit calculates the geometric fit Jhqd by comparing the geometric shapes of the pre-disaster model and the post-disaster model, and calculates the texture fit Wlqd by comparing the model texture and the texture of the actual building surface; then the geometric fit Jhqd and the texture fit Wlqd are correlated and calculated to obtain the total fit Qhd, and the specific calculation method is as follows:

[0093]

[0094] Qhd=w1*Jhqd+w2*Wlqd

[0095] In the formula, N represents the total number of points, P i represents the coordinates of the i-th point in the three-dimensional model, P i ' represents the coordinates of the corresponding i-th point in the actual building; M represents the total texture block, SSIM(I j ,I j ') represents the structural similarity index of the jth texture region; SSIM represents the structural similarity index, I j Represents the image of the jth texture region in the 3D model, I j ' represents the image of the jth texture area corresponding to the actual building;

[0096] w1 and w2 represent the weight values ​​of geometric fit Jhqd and texture fit Wlqd respectively;

[0097] The model comparison unit compares the preset matching threshold with the total matching degree Qhd and divides the files by the following scheme, wherein the matching threshold ranges from [0, 1]:

[0098] If Qhd ≥ 0.7, the fit is considered high, indicating that the pre-disaster model and the post-disaster model are more than 70% consistent and the affected buildings are slightly damaged;

[0099] If 0.4≤Qhd<0.7, the fit is considered moderate, indicating that there is a 40% to 70% agreement between the pre-disaster model and the post-disaster model, and the damaged buildings are classified as moderately damaged;

[0100] If 0.4>Qhd, the fit is considered low, indicating that there is no more than 40% consistency between the pre-disaster model and the post-disaster model, and the affected buildings are severely damaged.

[0101] In this embodiment, the purpose of calculating the geometric fit Jhqd and the texture fit Wlqd is to provide an accurate assessment of the degree of damage to the building, comprehensively assess the overall damage to the building, and improve the accuracy and efficiency of the assessment process; by identifying slightly damaged buildings with a high fit, buildings that require minor repairs can be quickly screened out, thereby saving resources and time; medium fit identifies buildings that require partial repairs and provides clear repair and reinforcement suggestions; low fit effectively identifies buildings that require comprehensive reconstruction and provides clear reconstruction suggestions to ensure the thoroughness of post-disaster reconstruction work.

[0102] Example 5

[0103] The damage feature analysis module extracts the damage features of the post-disaster model based on the surveying and mapping data set, including the total building area Zmj, the building crack area Lmj, the building structure deformation Jbx, the building collapse volume Jdt, the thermal anomaly area Ryc and the number of electrical fault points Dgzs;

[0104] Extract the surveying and mapping data set and calculate the damage index Shzs of the post-disaster building. The specific formula is as follows:

[0105]

[0106] Where q1, q2, q3, q4, q5 and q6 represent the weight values ​​of the total building area Zmj, the building crack area Lmj, the building structure deformation Jbx, the building collapse volume Jdt, the thermal anomaly area Ryc and the number of electrical fault points Dgzs respectively; ln represents logarithmic operation;

[0107] And 0≤q1<1, 0≤q2<1, 0≤q3<1, 0≤q4<1, 0≤q5<1, 0≤q6<1; q1+q2+q3+q4+q5+q6=1;

[0108] The damage feature analysis module compares the preset damage threshold E1 and damage threshold E2 with the damage index Shzs, and the damage threshold E1>damage threshold E2, and generates the following evaluation results:

[0109] If the damage index Shzs> the damage threshold E1, it means that the current building damage level exceeds 65%, and the first assessment result is generated;

[0110] If the damage threshold E1 ≥ the damage index Shzs ≥ the damage threshold E2, it means that the current building damage level is between 30% and 65%, and the second assessment result is generated;

[0111] If the damage threshold E2>damage index Shzs, it means that the current building damage level is less than 30%, and the third assessment result is generated.

[0112] In this embodiment, the total building area Zmj is collected to understand the overall scale of the building, which is used as a benchmark for relative calculation of the degree of damage. The total area is an important basic data for evaluating the scope of damage; the building crack area Lmj is collected to evaluate the severity of the structural damage of the building. The size of the crack area Lmj directly reflects the scope and degree of damage to the building, and is an important basis for judging whether the building has structural problems, and can provide necessary information for structural repair or reconstruction; the building structure deformation Jbx is collected to evaluate the overall stability and deformation degree of the building. The structural deformation reflects the displacement, tilt and other changes that occur in the building after the disaster, and can directly indicate the safety status of the building, and evaluate whether there is a risk of collapse or the need for structural reinforcement; The building collapse volume Jdt is collected to measure the scale of the collapsed part of the building. The building collapse volume Jdt directly reflects the severity of the damage to the building and the part that needs to be rebuilt. It is an important parameter for evaluating the cost and workload of post-disaster reconstruction. The thermal anomaly area Ryc is collected to detect thermal anomalies inside the building through thermal imaging, including overheated wires and ruptured pipes, to assess potential fire hazards or other internal damage. The thermal anomaly area Ryc helps identify hidden damaged areas and provides a more comprehensive damage assessment. The number of electrical fault points Dgzs is collected to assess the degree of damage to the building's electrical system. The number of electrical fault points reflects the damage to the power system, assesses whether there are electrical safety hazards, and provides a basis for repairing the electrical system.

[0113] Example 6

[0114] The result presentation module includes a suggestion generation unit and a display unit; the suggestion generation unit associates the high, medium and low results obtained by the overall fit degree Qhd evaluation with the evaluation result of the damage index Shzs to give the following reconstruction suggestions:

[0115] If the total fit degree Qhd is high and the damage index Shzs is the first assessment result, it means that the damaged building is more than 70% consistent with the original building structure, which is high risk, and the serious damage will lead to potential structural instability. At this time, the building should be repaired and the building structure should be fully reinforced;

[0116] If the total fit degree Qhd is high and the damage index Shzs is the second assessment result, it means that the damaged building is more than 70% consistent with the original building structure, with a medium risk, but the damaged parts affect the building function. At this time, partial repair and reinforcement are carried out to restore the building's use function;

[0117] If the total fit Qhd is high and the damage index Shzs is the third assessment result, it means that the damaged building is more than 70% consistent with the original building structure, with low risk and overall structural stability; minor repairs and maintenance are carried out at this time;

[0118] If the overall fit Qhd is medium and the damage index Shzs is the first assessment result, it means that the damaged building is 40% to 70% consistent with the original building structure, which is high risk, and the building is unstable due to structural differences and severe damage; at this time, key repairs or partial reconstruction are carried out;

[0119] If the overall fit Qhd is medium and the damage index Shzs is the second assessment result, it means that the damaged building is 40% to 70% consistent with the original building structure, with medium risk, structural differences and medium damage affecting the safety and function of the building, and structural repair and reinforcement should be carried out at this time;

[0120] If the overall fit Qhd is medium and the damage index Shzs is the third assessment result, it means that the damaged building is 40% to 70% consistent with the original building structure, with low risk, slight structural differences and low degree of damage. At this time, surface repair and maintenance are carried out;

[0121] If the total fit Qhd is low and the damage index Shzs is the first assessment result, it means that the consistency between the damaged building and the original building structure does not exceed 40%, which is high risk, with large structural differences and serious damage, and high safety hazards. At this time, it is recommended to fully rebuild;

[0122] If the total fit Qhd is low and the damage index Shzs is the second assessment result, it means that the consistency between the damaged building and the original building structure does not exceed 40%, which is a medium risk, but the structural difference is large, and the part that needs to be repaired affects the safety of the building. In this case, it is recommended to rebuild part of the structure and repair other parts;

[0123] If the total fit Qhd is low and the damage index Shzs is the third assessment result, it means that the consistency between the damaged building and the original building structure does not exceed 40%, which is a low risk. Although the structural difference is large, the damage is light and the overall stability is stable. At this time, the damaged part should be repaired and the overall maintenance and reinforcement should be carried out.

[0124] The display unit displays the comparative analysis results of the pre-disaster model and the post-disaster model, as well as the reconstruction suggestions for the buildings after the disaster. All the display contents are then integrated using GIS, and finally the building damage is displayed on the human-computer interaction interface.

[0125] In this embodiment, a high degree of fit indicates that the overall structure of the building has not changed much; a medium degree of fit indicates that part of the structure of the building has changed significantly; a low degree of fit indicates that the structure of the building has changed seriously; based on different assessment results, targeted repair or reconstruction suggestions are provided to ensure the rational use of resources and efficient post-disaster recovery work; through detailed damage assessments and reasonable repair suggestions, it helps to reduce the potential risks of buildings and improve the safety and stability of buildings after disasters.

[0126] Example 7

[0127] See also Figure 2 , a real estate surveying and mapping method based on machine vision, comprising the following steps:

[0128] Step 1: The surveying and mapping data acquisition module collects images of the disaster-stricken area; first, the image acquisition component is deployed, then the surveying and mapping area is divided, and finally, according to the surveying and mapping area, the acquisition route of the image acquisition component is planned to collect image data of the disaster-stricken area in real time;

[0129] Step 2, the structural data processing module processes the collected image data of the disaster-stricken area; first, the image data of the disaster-stricken area is preprocessed, including denoising, splicing, 3D processing and format conversion, and all data are dimensionlessly processed, and then the collected data is extracted and screened, and the extracted and screened data are constructed as a surveying and mapping data set;

[0130] Step 3: The surveying and mapping model building module performs three-dimensional reconstruction based on the surveying and mapping data set and the historical building data to generate a pre-disaster model and a post-disaster model respectively; and optimizes and semantically segments the pre-disaster model, and finally calculates the total fit degree Qhd of the pre-disaster model and the post-disaster model, and divides the total fit degree Qhd into three levels: high, medium, and low;

[0131] Step 4: The damage characteristic analysis module analyzes the damage degree of the buildings after the disaster; calculates the damage index Shzs according to the damage of the buildings, and uses the damage index Shzs to evaluate the damage degree of the buildings in the disaster area.

[0132] Step 5: The result presentation module analyzes the potential risks of the affected buildings and gives reconstruction suggestions based on the total fit degree Qhd and the damage index Shzs; finally, the model analysis results and reconstruction suggestions are displayed through digital maps, and a visual map is generated using GIS software.

[0133] In this embodiment, step one ensures all-round data collection of the disaster-stricken area to provide high-quality original data for subsequent processing and analysis; step two improves data quality to ensure the accuracy and reliability of subsequent three-dimensional reconstruction and analysis; step three creates an accurate three-dimensional model, and improves the details and comprehensibility of the model through optimization and segmentation; step four quantitatively evaluates the degree of damage to buildings after the disaster to provide accurate damage information; step five intuitively displays the damage to buildings, provides scientific and feasible reconstruction suggestions, and supports the decision-making process.

[0134] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A real estate surveying and mapping system based on machine vision, characterized in that: It includes surveying and mapping data acquisition module, structural data processing module, surveying and mapping model building module, damage feature analysis module and result presentation module; The surveying and mapping data acquisition module is used to collect images of the disaster-stricken area; first, the image acquisition component is deployed, then the surveying and mapping area is divided, and finally, according to the surveying and mapping area, the acquisition route of the image acquisition component is planned to collect image data of the disaster-stricken area in real time; The structural data processing module is used to process the collected image data of the disaster-stricken area; first, the image data of the disaster-stricken area is preprocessed, including denoising, splicing, 3D processing and format conversion, and all data are dimensionlessly processed, and then the collected data is extracted and screened, and the extracted and screened data are constructed as a surveying and mapping data set; The mapping model building module is used to perform three-dimensional reconstruction based on the mapping data set and the historical building data, and generate a pre-disaster model and a post-disaster model respectively; and optimize and semantically segment the pre-disaster model, and finally calculate the total fit degree Qhd of the pre-disaster model and the post-disaster model, and divide the total fit degree Qhd into three levels: high, medium, and low; The damage characteristic analysis module is used to analyze the damage degree of buildings after the disaster; according to the damage condition of the buildings, the damage index Shzs is calculated, and the damage degree of the buildings in the disaster area is evaluated using the damage index Shzs; The result presentation module is used to analyze the potential risks of the affected buildings and give reconstruction suggestions based on the total fit degree Qhd combined with the damage index Shzs; finally, the model analysis results and reconstruction suggestions are presented through digital maps, and a visual map is generated using GIS software; The surveying and mapping model building module includes a three-dimensional reconstruction unit, a model optimization unit, a semantic segmentation unit and a model comparison unit; the three-dimensional reconstruction unit generates a post-disaster data model through a surveying and mapping data set, and then generates a pre-disaster model by collecting historical architectural surveying and mapping data; the model optimization unit performs smoothing, texture reconstruction and detail enhancement on the pre-disaster model and the post-disaster model through grid optimization and precision improvement; the semantic segmentation unit performs semantic segmentation on the pre-disaster model by using a deep learning model, and trains and fine-tunes the pre-disaster model according to specific scenarios, and finally semantically annotates each part of the pre-disaster model, including walls, roofs, roads and vegetation; The model comparison unit calculates the geometric fit Jhqd by comparing the geometric shapes of the pre-disaster model and the post-disaster model, and calculates the texture fit Wlqd by comparing the model texture and the texture of the actual building surface; then the geometric fit Jhqd and the texture fit Wlqd are correlated and calculated to obtain the total fit Qhd, and the specific calculation method is as follows: ； ； ； In the formula, N represents the total number of points, represents the coordinates of the i-th point in the three-dimensional model, Indicates the corresponding The coordinates of the points; M represents the total texture block, represents the structural similarity index of the jth texture region; represents the structural similarity index, represents the image of the jth texture region in the 3D model, Indicates the corresponding An image of a texture region; w1 and w2 represent the weight values ​​of geometric fit Jhqd and texture fit Wlqd respectively; The model comparison unit compares the preset matching threshold with the total matching degree Qhd and divides the files by the following scheme, wherein the matching threshold ranges from between: If Qhd ≥ 0.7, the fit is considered high, indicating that the pre-disaster model and the post-disaster model are more than 70% consistent and the affected buildings are slightly damaged; If 0.4≤Qhd<0.7, the fit is considered moderate, indicating that there is a 40% to 70% agreement between the pre-disaster model and the post-disaster model, and the damaged buildings are classified as moderately damaged; If 0.4>Qhd, the fit is considered low, indicating that there is no more than 40% agreement between the pre-disaster model and the post-disaster model, and the affected buildings are severely damaged; The damage feature analysis module extracts the damage features of the post-disaster model based on the surveying and mapping data set, including the total building area Zmj, the building crack area Lmj, the building structure deformation Jbx, the building collapse volume Jdt, the thermal anomaly area Ryc and the number of electrical fault points Dgzs; Extract the surveying and mapping data set and calculate the damage index Shzs of the post-disaster building. The specific formula is as follows: ； Where q1, q2, q3, q4, q5 and q6 represent the weight values ​​of the total building area Zmj, the building crack area Lmj, the building structure deformation Jbx, the building collapse volume Jdt, the thermal anomaly area Ryc and the number of electrical fault points Dgzs respectively; ln represents logarithmic operation; And 0≤q1<1, 0≤q2<1, 0≤q3<1, 0≤q4<1, 0≤q5<1, 0≤q6<1; q1+q2+q3+q4+q5+q6=1; The damage feature analysis module compares the preset damage threshold E1 and damage threshold E2 with the damage index Shzs, and the damage threshold E1>damage threshold E2, and generates the following evaluation results: If the damage index Shzs> the damage threshold E1, it means that the current building damage level exceeds 65%, and the first assessment result is generated; If the damage threshold E1 ≥ the damage index Shzs ≥ the damage threshold E2, it means that the current building damage level is between 30% and 65%, and the second assessment result is generated; If the damage threshold E2>damage index Shzs, it means that the current building damage level is less than 30%, and the third assessment result is generated.

2. The real estate surveying and mapping system based on machine vision according to claim 1, characterized in that: The surveying and mapping data acquisition module includes a preparation unit, a route planning unit and an acquisition unit; the preparation unit is used to deploy image acquisition components, including using a drone equipped with a high-definition camera to take aerial photos of the disaster-stricken area to obtain full-view data of the disaster-stricken area; secondly, using a mobile camera on the ground to take real-scene detail images in the disaster-stricken area; then using a thermal imaging camera to capture infrared radiation and generate images; and finally using a LiDAR sensor to obtain three-dimensional point cloud data of the disaster-stricken area; The route planning unit obtains the basic map of the disaster area through the GIS system or other map services, determines the specific area that needs to be surveyed, divides the surveyed area into multiple sub-areas, determines the boundaries of each sub-area, and numbers each sub-area, including QY 1 , QY 2 , QY 3 、...、QY n , n represents the total number of sub-areas; finally, the flight route of the UAV is planned based on the coverage, overlap, flight altitude and safety; The acquisition unit installs image acquisition software in the image acquisition component, performs equipment debugging, and then performs acquisition, and transmits the acquired image data to the storage system in real time.

3. The real estate surveying and mapping system based on machine vision according to claim 2, characterized in that: The structural data processing module includes a preprocessing unit and a screening unit; the preprocessing unit denoises the image data of the disaster area through a filter, then finds the overlapping corresponding points between the image data of the disaster area, uses the corresponding points to splice the image data of the disaster area and generate a large-area puzzle; finally, stereo matching is performed using multi-view images to generate point cloud data, and all the image data of the disaster area are converted into a unified format, and screened after dimensionless processing.

4. The real estate surveying and mapping system based on machine vision according to claim 3, characterized in that: The screening unit is used to quantify the quality of the image data of the disaster area and evaluate the image quality index Tzls for quality screening; the specific calculation method of the image quality index Tzls is as follows: ； ； Where, Fbl represents image resolution, Ld represents image brightness, Dbd represents contrast; Jbcs represents basic image parameters, Szq represents color accuracy, Gjy represents illumination uniformity, Tcf represents the number of image repetitions, and Tzs represents the preset image repetition standard threshold; Indicates the index used to adjust the basic parameters Jbcs, color accuracy Szq and illumination uniformity Gjy of the parameter multiplication term; Represents the denominator term used to normalize the entire formula; The screening unit compares the preset quality threshold Z with the image quality index Tzls, and the specific evaluation scheme is as follows: If the image quality index Tzls ≥ the quality threshold Z, it means that the image quality is qualified, and the image is retained for subsequent surveying and mapping work; If the image quality index Tzls is less than the quality threshold Z, it means that the image quality is unqualified and the image is discarded.

5. The real estate surveying and mapping system based on machine vision according to claim 4, characterized in that: The result presentation module includes a suggestion generation unit and a display unit; the suggestion generation unit associates the high, medium and low results obtained by the overall fit degree Qhd evaluation with the evaluation result of the damage index Shzs to give the following reconstruction suggestions: If the total fit Qhd is high and the damage index Shzs is the first assessment result, it means that the damaged building is more than 70% consistent with the original building structure, which is high risk, and the serious damage will lead to potential structural instability. At this time, the building should be repaired and the building structure should be fully reinforced; If the total fit degree Qhd is high and the damage index Shzs is the second assessment result, it means that the damaged building is more than 70% consistent with the original building structure, with a medium risk, but the damaged parts affect the building function. At this time, partial repair and reinforcement are carried out to restore the building's use function; If the total fit Qhd is high and the damage index Shzs is the third assessment result, it means that the damaged building is more than 70% consistent with the original building structure, the risk is low, and the overall structure is stable; at this time, minor repairs and maintenance are carried out; If the overall fit Qhd is medium and the damage index Shzs is the first assessment result, it means that the damaged building is 40% to 70% consistent with the original building structure, which is a high risk, and the building is unstable due to structural differences and severe damage; At this time, focused repair or partial reconstruction is carried out; If the overall fit Qhd is medium and the damage index Shzs is the second assessment result, it means that the damaged building is 40% to 70% consistent with the original building structure, with medium risk, structural differences and medium damage affecting the safety and function of the building, and structural repair and reinforcement should be carried out at this time; If the overall fit Qhd is medium and the damage index Shzs is the third assessment result, it means that the damaged building is 40% to 70% consistent with the original building structure, with low risk, slight structural differences and low degree of damage. At this time, surface repair and maintenance are carried out; If the total fit Qhd is low and the damage index Shzs is the first assessment result, it means that the consistency between the damaged building and the original building structure does not exceed 40%, which is a high risk, with large structural differences and serious damage, and high safety hazards. At this time, it is recommended to fully rebuild; If the total fit Qhd is low and the damage index Shzs is the second assessment result, it means that the consistency between the damaged building and the original building structure does not exceed 40%, which is a medium risk, but the structural difference is large. In this case, it is recommended to rebuild part of the structure and repair other parts; If the total fit Qhd is low and the damage index Shzs is the third assessment result, it means that the consistency between the damaged building and the original building structure does not exceed 40%, which is a low risk. Although the structural difference is large, the damage is light and the overall stability is stable. At this time, the damaged part should be repaired and the overall maintenance and reinforcement should be carried out.

6. The real estate surveying and mapping system based on machine vision according to claim 5, characterized in that: The display unit displays the comparative analysis results of the pre-disaster model and the post-disaster model, as well as the reconstruction suggestions for the buildings after the disaster. All the display contents are integrated using GIS, and finally the building damage is displayed on the human-computer interaction interface.

7. A real estate surveying and mapping method based on machine vision, applied to a real estate surveying and mapping system based on machine vision according to any one of claims 1 to 6, characterized in that: The following steps are involved: Step 1: The surveying and mapping data acquisition module collects images of the disaster-stricken area; first, the image acquisition component is deployed, then the surveying and mapping area is divided, and finally, according to the surveying and mapping area, the acquisition route of the image acquisition component is planned to collect image data of the disaster-stricken area in real time; Step 2, the structural data processing module processes the collected image data of the disaster-stricken area; first, the image data of the disaster-stricken area is preprocessed, including denoising, splicing, 3D processing and format conversion, and all data are dimensionlessly processed, and then the collected data is extracted and screened, and the extracted and screened data are constructed as a surveying and mapping data set; Step 3: The surveying and mapping model building module performs three-dimensional reconstruction based on the surveying and mapping data set and the historical building data to generate a pre-disaster model and a post-disaster model respectively; and optimizes and semantically segments the pre-disaster model, and finally calculates the total fit degree Qhd of the pre-disaster model and the post-disaster model, and divides the total fit degree Qhd into three levels: high, medium, and low; Step 4: The damage characteristic analysis module analyzes the damage degree of the buildings after the disaster; calculates the damage index Shzs according to the damage of the buildings, and uses the damage index Shzs to evaluate the damage degree of the buildings in the disaster area; Step 5: The result presentation module analyzes the potential risks of the affected buildings and gives reconstruction suggestions based on the total fit degree Qhd and the damage index Shzs; finally, the model analysis results and reconstruction suggestions are displayed through digital maps, and a visual map is generated using GIS software.

Images