Method, equipment, medium and product for constructing rock-soil three-dimensional virtual model

Abstract

The invention discloses a method, equipment, medium and product for constructing a rock-soil three-dimensional virtual model, and relates to the field of rock-soil reconnaissance, and the method comprises the steps: receiving a reconnaissance image of a target sub-region; performing feature region marking on each investigation image to mark a feature region; gathering the investigation images belonging to the same target sub-region into the same class based on the feature region to obtain a plurality of groups of similar images; for each group of images of the same kind, the reconnaissance images included in each group of images of the same kind are fused to obtain a fused image of each target sub-region; determining a first image value of each fused image, wherein the image values are used for reflecting the qualification degree of the fused images; when the first image value of each fused image falls into a preset first qualified range, constructing a three-dimensional virtual model of the target area based on each fused image; and when the first image value of the fusion image does not fall into the first qualified range, generating a prompt that the three-dimensional virtual model does not conform to construction. The efficiency of constructing the rock-soil three-dimensional virtual model is improved.

Description

Technical Field

[0001] The present application relates to the field of geotechnical exploration technology, and in particular to a method, equipment, medium and product for constructing a three-dimensional geotechnical virtual model. Background Art

[0002] Geotechnical investigation refers to the investigation, research, analysis and evaluation of the geological, environmental characteristics and geotechnical conditions of the construction site by using various surveying techniques and methods according to the requirements of the construction project. Its purpose is to identify, analyze and evaluate the geological, environmental characteristics and geotechnical conditions of the construction site, and on this basis, compile survey documents, solve existing geotechnical problems, and ensure the smooth progress of engineering design and construction. Building a three-dimensional virtual model of geotechnical is a common geotechnical investigation method.

[0003] The prior art constructs a three-dimensional virtual model by the following method: collecting survey images of the target area through survey equipment; and sending the survey images to a three-dimensional virtual model construction platform, and completing the construction through the three-dimensional virtual model construction platform; when the constructed three-dimensional virtual model is unqualified, re-collecting the survey images of the target area through the survey equipment to re-construct the three-dimensional virtual model until a qualified three-dimensional virtual model is constructed.

[0004] In addition, the application document with the authorization announcement number CN202410156758.8 and the authorization announcement date 20240823 discloses a "Geotechnical Engineering Survey Big Data Archiving Method and System". The method includes the following steps: performing survey data partitioning processing on the initial geotechnical engineering survey data to generate grouped geotechnical engineering survey data; performing data recoding processing on the grouped geotechnical engineering survey data to obtain geotechnical engineering survey data; performing replication and proliferation processing on the geotechnical engineering survey data to obtain a copy of the geotechnical engineering survey data; using the copy of the geotechnical engineering survey data to perform hash collision deduplication processing on the geotechnical engineering survey data to obtain deduplicated geotechnical engineering survey data. After archiving processing, it is stored in the database for later convenient use. For example, when it is necessary to build a three-dimensional virtual model for geotechnical, data is obtained from the database and a three-dimensional virtual modeling operation is performed.

[0005] From the above content, it can be seen that the prior art has at least the following technical problems: when the constructed three-dimensional virtual model is significantly different from the actual survey image, the survey image will be re-collected and the three-dimensional virtual model will be reconstructed until a qualified three-dimensional virtual model is constructed. Therefore, the construction is often repeated many times before a qualified three-dimensional virtual model can be constructed, and the model construction efficiency is low. Summary of the invention

[0006] The purpose of this application is to provide a method, device, medium and product method, device, medium and product for constructing a three-dimensional virtual model of geotechnical materials, so as to solve the problem of low efficiency in constructing the model described in the background technology.

[0007] To achieve the above objectives, this application provides the following solutions: In a first aspect, the present application provides a method for constructing a three-dimensional virtual model of geotechnical structures, comprising: Receiving a survey image sent by a geotechnical survey device, wherein the survey image is a plurality of images of a plurality of target sub-regions acquired by the geotechnical survey device, wherein the plurality of target sub-regions are obtained by dividing the target region; Marking the characteristic regions of each of the survey images to mark the characteristic regions of each of the survey images; Based on the feature region, survey images belonging to the same target sub-region are grouped into the same category, recorded as similar images, thereby obtaining multiple groups of similar images; For each group of similar images, the survey images included in the group of similar images are fused to obtain a fused image of each target sub-region; Determine an image value of each of the fused images, recorded as a first image value, wherein the image value is used to reflect the qualification degree of the fused image; When the first image value of each of the fused images falls within a predetermined first qualified range, constructing a three-dimensional virtual model of the target area based on each of the fused images; When there is a first image value of the fused image that does not fall within the first qualified range, a reminder that it does not meet the requirements for building a three-dimensional virtual model is generated.

[0008] Optionally, for each group of similar images, fusing the survey images included in the group of similar images to obtain a fused image of each target sub-region includes: For each group of similar images, based on the characteristic area of ​​each survey image, the group of similar images is divided into two categories, namely target images and background images; The target image and the background image included in each group of similar images are fused using a predetermined first image fusion method to obtain a fused image corresponding to each group of similar images.

[0009] Optionally, after determining the image value of each fused image and recording it as the first image value, the method further includes: When the first image value of each of the fused images falls within a second qualified range but does not fall within the first qualified range, the fused images are fused again by a predetermined second image fusion method to obtain a new fused image, wherein the second qualified range is larger than the first qualified range and includes the first qualified range; determining an image value of the new fused image, recorded as a second image value, and constructing a three-dimensional virtual model of the target area based on each of the new fused images when the second image value falls within the first qualified range; When the second image value still does not fall within the first qualified range, an unqualified reminder is generated and sent to the survey equipment, so that the survey equipment re-collects the survey image and returns to execute the survey image sent by the receiving geotechnical survey equipment and subsequent steps.

[0010] Optionally, the first image value of the fused image is a divergence, and determining the image value of each fused image, recorded as the first image value, includes: For each of the fused images, determining the gradient fields of the target image and the background image used when fusion is performed into the fused image; Overlaying the gradient field of the target image corresponding to the fused image onto the gradient field of the background image to obtain the gradient field of the fused image; The gradient field of the fused image is derived to obtain a divergence of the fused image, and the divergence of the fused image is recorded as a first image value of the fused image.

[0011] Optionally, constructing the three-dimensional virtual model of the target area based on the fused images includes: Determine the correlation coefficient between each fused image; For each fused image, another fused image with the highest correlation coefficient is determined; and every two fused images with the highest correlation coefficients are constructed using a predetermined three-dimensional virtual model construction method, thereby obtaining the three-dimensional virtual model.

[0012] Optionally, after constructing the three-dimensional virtual model of the target area based on the fused images, the method further includes: determining a similarity between the three-dimensional virtual model and the survey image; When the similarity is greater than or equal to a predetermined value, the three-dimensional virtual model is determined to be qualified; or, when the similarity is less than a predetermined value, the three-dimensional virtual model is determined to be unqualified.

[0013] Optionally, the predetermined second image fusion method includes a Poisson image fusion method based on a gradient field.

[0014] In a second aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any one of the methods described in the first aspect.

[0015] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect.

[0016] In a fourth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0017] According to the specific embodiments provided in this application, this application discloses the following technical effects: The method for constructing a three-dimensional virtual model of geotechnical structures provided in an embodiment of the present application promptly receives a survey image surveyed by a surveying device; then performs feature area marking on the survey image, and marks the feature area from the survey image; based on the feature area of ​​each survey image, the survey images of the same target sub-area are aggregated into the same category and fused to obtain a fused image of the target sub-area, and determine whether the fused image is qualified, and when it is unqualified, generate an unqualified reminder and stop the three-dimensional virtual model construction operation; while for the prior art, the fused image is not determined to be qualified, but the fused image is directly used to construct the three-dimensional virtual model, so that if the fused image is unqualified, an accurate three-dimensional virtual model will inevitably not be obtained, and more seriously, it is an erroneous three-dimensional virtual model; therefore, compared with the prior art, the present application constructs the three-dimensional virtual model after ensuring that the fused image is qualified, which can avoid using unqualified fused images to construct the three-dimensional virtual model, improve the accuracy of the constructed three-dimensional virtual model, and thus improve the efficiency of constructing the three-dimensional virtual model. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 This is an application environment diagram of a method for constructing a three-dimensional virtual model of geotechnical materials in one embodiment of the present application; Figure 2 A schematic diagram of a process for constructing a three-dimensional virtual model of geotechnical structures provided in one embodiment of the present application; Figure 3 A schematic diagram of a process for generating a fused image provided by an embodiment of the present application; Figure 4 A schematic flow chart of a method for constructing a three-dimensional virtual model of geotechnical structures provided in another embodiment of the present application; Figure 5A schematic diagram of another process of generating a fused image provided by an embodiment of the present application; Figure 6 A schematic flow chart of a method for determining a first image value provided in another embodiment of the present application; Figure 7 A schematic diagram of a flow chart of another method for constructing a three-dimensional virtual model of geotechnical structures provided in an embodiment of the present application; Figure 8 A flowchart of a method for determining whether a three-dimensional virtual model is qualified provided in one embodiment of the present application; Fig. 9 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0021] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0022] The method for constructing a three-dimensional virtual model of rock and soil provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the application environment includes survey equipment and a server.

[0023] The survey equipment communicates with the server through the network. The data storage system can store the data that the server needs to process. The data storage system can be set up separately, integrated on the server, or placed on the cloud or other servers.

[0024] Furthermore, the survey equipment is used to survey the target area on site, obtain survey images, and send the survey images to the server.

[0025] Among them, a cloud platform optimization system is configured in the server, and the method of constructing a three-dimensional virtual model of geotechnical materials in this application is implemented through the cloud platform optimization system. After receiving the survey image to be processed, the server constructs a three-dimensional virtual model of geotechnical materials based on the survey image, and returns the construction result (whether the construction is successful) to the survey equipment, so that the survey equipment can perform further processing based on the construction result.

[0026] Furthermore, the cloud platform optimization system is built based on cloud computing technology. For example, the data receiving function in the cloud platform is established based on the application programming interface (API) technology, which is used to receive the survey images sent by the survey equipment.

[0027] In an exemplary embodiment, Figure 2 As shown, a method for constructing a three-dimensional virtual model of geotechnical soil is provided. The method is applied to Figure 1 The server comprises the following steps 201 to 207: Step 201 : receiving a survey image sent by a geotechnical survey device, wherein the survey image is a plurality of images of a plurality of target sub-regions collected by the geotechnical survey device, and the plurality of target sub-regions are obtained by dividing a target region.

[0028] Among them, the survey images include different types of images such as geological structure images, topographic images, and hydrogeological images. Of course, each type of image is also collected by different types of survey equipment.

[0029] The survey equipment is determined by the type of survey images that are expected to be collected. For example, when it is necessary to collect three types of images, namely, geological structure images, topographic images, and hydrogeological images, at least three types of survey equipment are required.

[0030] Generally, each target sub-area will use each predetermined type of survey equipment for image acquisition. The number of survey images corresponding to each target sub-area is also related to the number of types of survey equipment. The more types there are, the more survey images there will be.

[0031] In addition, since the target area to be surveyed is generally large, it will be divided into multiple target sub-areas for regional survey. After the survey equipment collects the survey image of each target sub-area, it will be sent to the server in real time.

[0032] Step 202 : Marking a characteristic region of each survey image to mark a characteristic region of each survey image.

[0033] The method of marking the feature area may be one or more of edge detection, angle detection, texture analysis, and color features.

[0034] Since the characteristics of rock and soil are relatively uncertain, a variety of different feature region marking methods are used to mark the image to mark different feature regions in the image. The specific feature region marking methods used can be determined manually based on the characteristics of the surveyed rock and soil.

[0035] In addition, before marking the feature area, the survey image can also be enhanced by image enhancement technology to optimize the survey image, improve the visual effect and quality of the survey image, and improve the speed and accuracy of feature area marking.

[0036] Furthermore, after the feature area marking is completed, the survey image can be re-identified to identify invalid data and duplicate data in the survey image, and the invalid data and duplicate data can be deleted to reduce the computing load of the cloud platform and improve the efficiency of subsequent image processing.

[0037] Step 203 , based on the feature region, survey images belonging to the same target sub-region are grouped into the same category and recorded as similar images, thereby obtaining multiple groups of similar images.

[0038] Since each target sub-region has its own characteristics, the survey images of the same target sub-region can be grouped into the same category through the characteristic regions of the survey images. Since there are multiple target sub-regions, multiple groups of images of the same type will be obtained.

[0039] Step 204 , for each group of similar images, the survey images included in the group of similar images are fused to obtain a fused image of each target sub-region.

[0040] Each group of similar images includes survey images collected by different types of survey equipment. Of course, these survey images are also divided into target images and background images.

[0041] Step 205: determine an image value of each of the fused images, recorded as a first image value, and the image value is used to reflect the qualification degree of the fused image.

[0042] Due to the quality problem of the survey image itself and the loss in the fusion process, the fused image may be unqualified and cannot be used later. Therefore, the qualification degree of the fused image can be reflected by the first image value.

[0043] The first image value may be a divergence. Of course, the first image value may also be other indicators that can reflect the degree of image qualification, and this application does not limit this.

[0044] Step 206: when the first image value of each of the fused images falls within a predetermined first qualified range, construct a three-dimensional virtual model of the target area based on each of the fused images.

[0045] Step 207: When there is a first image value of the fused image that does not fall within the first qualified range, a reminder that it does not meet the requirements for building a three-dimensional virtual model is generated.

[0046] Among them, the first qualified range is used to indicate that: when the first image value falls within it, the fused image is qualified, and an accurate three-dimensional virtual model of the target area can be constructed through multiple fused images; when the first image value does not fall within it, the fused image is unqualified, and the three-dimensional virtual model of the target area cannot be constructed through multiple fused images, or the constructed three-dimensional virtual model has low accuracy and does not meet the requirements.

[0047] Among them, the first qualified range can be an empirical value.

[0048] The method for constructing a three-dimensional virtual model of geotechnical structures provided in an embodiment of the present application promptly receives a survey image surveyed by a surveying device; then performs feature area marking on the survey image, and marks the feature area from the survey image; based on the feature area of ​​each survey image, the survey images of the same target sub-area are aggregated into the same category and fused to obtain a fused image of the target sub-area, and determine whether the fused image is qualified, and when it is unqualified, generate an unqualified reminder and stop the three-dimensional virtual model construction operation; while for the prior art, the fused image is not determined to be qualified, but the fused image is directly used to construct the three-dimensional virtual model, so that if the fused image is unqualified, an accurate three-dimensional virtual model will inevitably not be obtained, and more seriously, it is an erroneous three-dimensional virtual model; therefore, compared with the prior art, the present application constructs the three-dimensional virtual model after ensuring that the fused image is qualified, which can avoid using unqualified fused images to construct the three-dimensional virtual model, improve the accuracy of the constructed three-dimensional virtual model, and thus improve the efficiency of constructing the three-dimensional virtual model.

[0049] In addition, with the prior art, when it is found that the three-dimensional virtual model is unqualified, it is necessary to re-collect the survey images to re-construct the three-dimensional virtual model until a qualified three-dimensional virtual model is constructed, which wastes time; while with the present application, it is possible to avoid using unqualified fused images to construct a three-dimensional virtual model, thereby reducing the problem of wasted time.

[0050] Alternatively, see Figure 3 , step 204 can be implemented by the following steps 2041-2042: Step 2041 , for each group of similar images, based on the feature region of each survey image, the group of similar images is divided into two categories, namely, target images and background images.

[0051] Step 2042: Use a predetermined first image fusion method to fuse the target image and the background image included in each group of similar images to obtain a fused image corresponding to each group of similar images.

[0052] By dividing each group of similar images into target images and background images and then fusing them, the key information in the survey images can be better extracted and fused.

[0053] The first image fusion algorithm may be a gradient field overlay method, which directly overlays the gradient field of the target image onto the gradient field of the background image, and then generates a fused image by integration or other reconstruction methods. For a more specific fusion process, please refer to the relevant prior art, which will not be described in detail in this application.

[0054] Alternatively, see Figure 4 In another exemplary embodiment of the present application, after step 205, the method further includes the following steps 301 to 304: Step 301, when the first image value of each of the fused images falls within a second qualified range but does not fall within the first qualified range, the fused images are fused again by a predetermined second image fusion method to obtain a new fused image, and the second qualified range is larger than the first qualified range and includes the first qualified range.

[0055] When the first image value falls within the second qualified range but does not fall within the first qualified range, it means that the fused image may fall within the first qualified range after being processed by the predetermined second image fusion method, thereby meeting the requirements of three-dimensional construction.

[0056] The second qualified range may be an empirical value.

[0057] Step 302: determine the image value of the new fused image, recorded as the second image value.

[0058] Step 303: When the second image value falls within the first qualified range, construct a three-dimensional virtual model of the target area based on each of the new fused images.

[0059] The second image value has the same meaning as the first image value, which will not be elaborated here.

[0060] This indicates that after the fused image is processed by the predetermined second image fusion technology, the new fused image obtained has fallen into the first qualified range and can meet the requirements of three-dimensional construction.

[0061] Step 304: when the second image value still does not fall within the first qualified range, an unqualified reminder is generated and sent to the survey equipment, so that the survey equipment re-collects the survey image and returns to execute the survey image sent by the receiving geotechnical survey equipment and subsequent steps.

[0062] This indicates that after the fused image is processed by the predetermined second image fusion technology, it still cannot fall into the first qualified range and cannot meet the requirements of three-dimensional construction. Therefore, it is necessary to generate a failure reminder so that the survey device re-collects the survey image.

[0063] In addition, it should be noted that each survey device can survey any target sub-region, and after surveying the target sub-region, the survey image obtained is not marked with which target sub-region the survey image corresponds to, so when there is an unqualified fused image or a new fused image, all target sub-regions need to be surveyed again. That is, it is necessary to start again from step 201 until the fused image or the new fused image of each target sub-region is qualified.

[0064] Alternatively, see Figure 5 In another exemplary embodiment of the present application, the second image fusion method predetermined in step 301 includes a Poisson image fusion method based on a gradient field, and step 301 is implemented by the following steps 3011-3012: Step 3011, determining the gradient field of each of the fused images.

[0065] Step 3012: for each of the fused images, fuse the fused images again based on the gradient field of the fused images to obtain a new fused image.

[0066] Furthermore, the Poisson equations of each fused image can be solved by the Gauss-Seidel iteration method, that is, the gradient field of the fused image can be input into the Poisson equation, so that the Poisson value of the fused image can be solved, and then the image fusion can be performed based on the Poisson value. The process is as follows: The process of Gauss-Seidel iteration method is as follows: 1. Assume that the initial solution is u (0), that is i is 0, which is used as the starting point of iteration; 2. According to the discretization form of Poisson's equation, after discretization, a scatter plot will be constructed on the grid map. The scattered points on the graph are the grid points, and the value of each grid point of the solution is updated; 3. Repeat step 2 until convergence or the preset number of iterations is reached; Discretize the rectangular area (that is, the image to be fused) into N×M grid points, and the distance between each two grid points is h , we can get the following discretized Poisson equation:

[0067] Update grid points ( i , j ) is:

[0068] in, k Indicates the number of current iterations. The initial solution can be obtained based on the boundary conditions. ui For the i The grid points obtained after iterations; Will x The direction is divided into N grid points. y The direction is divided into M grid points; in, i = 0, 1, ..., N; j = 0, 1, ..., M; f i，j Indicates that at the grid point ( i , j ) is a known function f ( x , y ) value; h Indicates the distance between every two grids.

[0069] Furthermore, for a more detailed method for solving the Poisson equation, reference can be made to the relevant description of the prior art, which will not be described in detail in this application.

[0070] Alternatively, see Figure 6 In another exemplary embodiment of the present application, the first image value of the fused image is a divergence, and step 205 is implemented by the following steps 2051 to 2053: Step 2051: for each of the fused images, determine the gradient fields of the target image and the background image used when the fused images are fused into the fused image.

[0071] Step 2052: Overlay the gradient field of the target image corresponding to the fused image onto the gradient field of the background image to obtain the gradient field of the fused image.

[0072] It should be noted here that step 2051 and step 2052 can also be used to calculate the gradient field in the above step 3011.

[0073] Step 2053: Derivative the gradient field of the fused image to obtain the divergence of the fused image, and record the divergence of the fused image as the first image value of the fused image.

[0074] Of course, the first image value may be represented by other characteristic values ​​of the image, which will not be described in detail in this application.

[0075] Alternatively, see Figure 7 In another exemplary embodiment of the present application, step 206 is implemented by the following steps 2061-2062: Step 2061, determining the correlation coefficient between each fused image.

[0076] The fused image here refers to the fused image used to construct the three-dimensional virtual model, and can be either the fused image in step 204 or the new fused image in step 301 .

[0077] The correlation coefficient ranges from -1 to 1. Values ​​close to 1 indicate a strong positive correlation, values ​​close to -1 indicate a strong negative correlation, and values ​​close to 0 indicate no correlation.

[0078] In the present application, the correlation coefficient may be the Spearman correlation coefficient. Of course, other correlation coefficients may also be selected, which will not be described in detail in the present application.

[0079] Furthermore, regarding the calculation of the correlation coefficient, reference may be made to the relevant prior art, and this application will not elaborate on it here.

[0080] Furthermore, the correlation coefficient can also be tested for significance: a hypothesis test is performed to determine whether the correlation coefficient is significantly different from 0, usually using a t-test or a z-test. For related content, please refer to the relevant prior art, which will not be described in detail in this application.

[0081] Furthermore, the results of the correlation coefficient can be visualized: a scatter plot visualization tool is used to display the correlation between variables. For related content, please refer to the relevant prior art, and this application will not elaborate on it here.

[0082] Step 2062: for each fused image, determine another fused image with the highest correlation coefficient; construct every two fused images with the highest correlation coefficient using a predetermined three-dimensional virtual model construction method, thereby obtaining the three-dimensional virtual model.

[0083] For three-dimensional virtual models, MATLAB software can be used for modeling and mesh functions can be used for drawing.

[0084] Furthermore, when performing three-dimensional construction, the fused image can be combined with the geological information and constructed through a predetermined construction method, for example, through a mesh function.

[0085] Of course, other existing 3D virtual model construction methods can also be used for construction, such as methods based on deep learning; specifically, it can be: single image reconstruction, using neural networks (such as 3D-R2N2, Pixel2Mesh) to predict 3D structure from a single image, or multi-view reconstruction: combining multiple images and generating a 3D model through a neural network (such as MVSNet). Another example is a method based on structured light or laser scanning, and another example is a method based on RGB-D cameras.

[0086] Alternatively, see Figure 8In another exemplary embodiment of the present application, after step 206, the method further includes the following steps 501-502: Step 501: Determine the similarity between the three-dimensional virtual model and the survey image.

[0087] The survey image is directly obtained by the survey equipment and reflects the most realistic geotechnical conditions. Therefore, by comparing the 3D virtual model with the survey image, the qualification of the 3D virtual model can be determined.

[0088] Furthermore, the three-dimensional virtual image and the survey image can be compared by a similarity comparison formula, and the similarity comparison formula is as follows:

[0089] in, Represents two sets of data, one of which is X j , X ij ; is the similarity between two sets of data. The larger the value, the more similar the two sets of data are. 0≤ ≤1; is the variance between the two corresponding data in the two sets of data, is the data in the first set of data, For the second set of data The corresponding data; d is the number of data in each of the two groups of data, and the number of data in the two groups of data is the same; It is the sum of the products of similar data, that is, the sum of the products of all corresponding data in two sets of data; e is a natural constant; For data X j and data X ij The norm or length of .

[0090] Step 502: when the similarity is greater than or equal to a predetermined value, determine that the three-dimensional virtual model is qualified; or when the similarity is less than a predetermined value, determine that the three-dimensional virtual model is unqualified.

[0091] Furthermore, when the 3D virtual model is unqualified, an unqualified reminder can be generated so that further measures can be taken. For example, the current 3D virtual model can be corrected to obtain a more accurate 3D virtual model; if a more accurate 3D virtual model cannot be obtained through correction, step 206 can be re-executed to obtain a new 3D virtual model; if a qualified 3D virtual model is still not obtained after re-execution of 206 for multiple times, steps 201 to 207 can be re-executed until a qualified 3D virtual model is obtained.

[0092] From the above content, it can be seen that the cloud platform processes and verifies data in real time, avoiding multiple surveys, reducing the number of surveys, and improving the efficiency of building three-dimensional virtual models.

[0093] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store relevant data for constructing a three-dimensional virtual model of geotechnical structures. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for constructing a three-dimensional virtual model of geotechnical structures can be implemented.

[0094] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0095] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0096] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0097] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0098] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0099] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, in the embodiments provided in the present application, any reference to a memory, a database or other medium can include at least one of a non-volatile and a volatile memory. Non-volatile memory can include a read-only memory (ROM), a magnetic tape, a floppy disk, a flash memory, an optical memory, a high-density embedded non-volatile memory, a resistive random access memory (ReRAM), a magnetoresistive random access memory (MRAM), a ferroelectric random access memory (FRAM), a phase change memory (PCM), a graphene memory, etc. Volatile memory can include a random access memory (RAM) or an external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0100] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0101] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0102] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for constructing a three-dimensional virtual model of geotechnical materials, characterized in that: include: Receiving a survey image sent by a geotechnical survey device, wherein the survey image is a plurality of images of a plurality of target sub-regions acquired by the geotechnical survey device, wherein the plurality of target sub-regions are obtained by dividing the target region; Marking the characteristic regions of each of the survey images to mark the characteristic regions of each of the survey images; Based on the feature region, survey images belonging to the same target sub-region are grouped into the same category, recorded as similar images, thereby obtaining multiple groups of similar images; For each group of similar images, the survey images included in the group of similar images are fused to obtain a fused image of each target sub-region; Determine an image value of each of the fused images, recorded as a first image value, wherein the image value is used to reflect the qualification degree of the fused image; When the first image value of each of the fused images falls within a predetermined first qualified range, constructing a three-dimensional virtual model of the target area based on each of the fused images; When there is a first image value of the fused image that does not fall within the first qualified range, a reminder that it does not meet the requirements for building a three-dimensional virtual model is generated.

2. The method for constructing a three-dimensional virtual model of geotechnical materials according to claim 1, characterized in that: For each group of similar images, the survey images included in the group of similar images are fused to obtain a fused image of each target sub-region, including: For each group of similar images, based on the characteristic area of ​​each survey image, the group of similar images is divided into two categories, namely target images and background images; The target image and the background image included in each group of similar images are fused using a predetermined first image fusion method to obtain a fused image corresponding to each group of similar images.

3. The method for constructing a three-dimensional virtual model of geotechnical materials according to claim 2, characterized in that: After determining the image value of each fused image and recording it as the first image value, the method further includes: When the first image value of each of the fused images falls within a second qualified range but does not fall within the first qualified range, the fused images are fused again by a predetermined second image fusion method to obtain a new fused image, wherein the second qualified range is larger than the first qualified range and includes the first qualified range; Determine an image value of the new fused image, recorded as a second image value; When the second image value falls within the first qualified range, constructing a three-dimensional virtual model of the target area based on each of the new fused images; When the second image value still does not fall within the first qualified range, an unqualified reminder is generated and sent to the survey equipment, so that the survey equipment re-collects the survey image and returns to execute the survey image sent by the receiving geotechnical survey equipment and subsequent steps.

4. The method for constructing a three-dimensional virtual model of geotechnical materials according to claim 2, characterized in that: The first image value of the fused image is a divergence, and the step of determining the image value of each fused image, recorded as the first image value, includes: For each of the fused images, determining the gradient fields of the target image and the background image used when fusion is performed into the fused image; Overlaying the gradient field of the target image corresponding to the fused image onto the gradient field of the background image to obtain the gradient field of the fused image; The gradient field of the fused image is derived to obtain a divergence of the fused image, and the divergence of the fused image is recorded as a first image value of the fused image.

5. The method for constructing a three-dimensional geotechnical virtual model according to claim 1, characterized in that: The constructing of the three-dimensional virtual model of the target area based on the fused images comprises: Determine the correlation coefficient between each fused image; For each fused image, another fused image with the highest correlation coefficient is determined; and every two fused images with the highest correlation coefficients are constructed using a predetermined three-dimensional virtual model construction method, thereby obtaining the three-dimensional virtual model.

6. The method for constructing a three-dimensional virtual model of geotechnical materials according to any one of claims 1 to 5, characterized in that: After constructing the three-dimensional virtual model of the target area based on the fused images, the method further includes: determining a similarity between the three-dimensional virtual model and the survey image; When the similarity is greater than or equal to a predetermined value, the three-dimensional virtual model is determined to be qualified; or, when the similarity is less than a predetermined value, the three-dimensional virtual model is determined to be unqualified.

7. The method for constructing a three-dimensional virtual model of geotechnical materials according to claim 3, characterized in that: The predetermined second image fusion method includes a Poisson image fusion method based on a gradient field.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for constructing a three-dimensional virtual model of geotechnical materials as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for constructing a three-dimensional virtual model of geotechnical materials according to any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for constructing a three-dimensional virtual model of geotechnical materials according to any one of claims 1 to 7 is implemented.

Images