Method, system, device and storage medium for geological information monitoring of rock slopes

Abstract

The present application relates to a method, system, device, and storage medium for monitoring geological information of rock slopes, belonging to the field of data processing technology. The method comprises: obtaining a candidate point and multiple initial known point sets adjacent to the candidate point, wherein the candidate point refers to a feature point to be classified, and the initial known point set is a collection of feature points belonging to the same category; calculating the eigenvalues ​​and eigenvectors of the candidate point and each initial known point set; determining a target known point set based on the eigenvalues ​​and eigenvectors, wherein the target known point set is at least one of the multiple initial known point sets; and obtaining geological data based on the candidate point and the target known point set. The present application has the effect of improving the accuracy of the analysis results of rock and soil structures.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, system, device and storage medium for monitoring geological information of rock slopes. Background Art

[0002] Geological information such as occurrence, trace length, roughness, and strength contained in rock mass structures is the data required for geotechnical and geological surveys. This geological information can be used to assess the health and development trends of rock and soil. Currently, the following methods are commonly used to collect geological information from rock mass structures:

[0003] 1. Manual data collection. Geologists use measuring tools such as compasses and tape measures to survey geotechnical structures on-site and manually record the results. This data collection method relies primarily on geologists' physical contact with the geotechnical structures being surveyed, resulting in intuitive and accurate information. However, it also has significant drawbacks. This method is limited by topographical conditions, posing significant safety risks to geologists in environments like rocky slopes. Furthermore, manual data collection is inefficient and lacks comprehensive information, making it incompatible with the rapid and efficient construction requirements of modern engineering projects.

[0004] 2. 3D laser scanning. Using drones equipped with high-definition cameras, image information of rock slopes is acquired, and a 3D real-life model of the slope is generated. This model is then used for information identification and geological surveys, providing a strong basis for subsequent slope stability analysis and engineering support scheme design. Although the image information collected using this method encompasses a wide range of valid geotechnical information, the subsequent processing of this method is complex, requiring geologists to possess a high level of expertise in analyzing the image information. Using multiple algorithmic models to analyze geotechnical structures can lead to widely varying results from different geologists due to varying experience, making it difficult to form a unified analysis result.

[0005] Therefore, it is currently urgent to provide a processing method that can obtain comprehensive geological information and provide high-accuracy analysis results based on the three-dimensional laser scanning method. Summary of the Invention

[0006] In order to solve the problem of low accuracy of current analysis results for geotechnical structures, the present application provides a geological information monitoring method, system, device and storage medium for rock slopes.

[0007] In a first aspect of the present application, a method for monitoring geological information of a rock slope is provided. The method comprises:

[0008] Obtaining a candidate point and a plurality of initial known point sets adjacent to the candidate point, wherein the candidate point refers to a feature point to be classified, and the initial known point set is a collection of feature points belonging to the same category;

[0009] Calculating the eigenvalues ​​and eigenvectors of the candidate points and each of the initial known point sets;

[0010] Determine a target known point set according to the eigenvalue and the eigenvector, wherein the target known point set is at least one point set among the multiple initial known point sets;

[0011] Geological data is obtained according to the candidate points and the target known point set.

[0012] By adopting the above technical solution, a candidate point and multiple initial known point sets adjacent to the candidate point are first obtained. Then, the eigenvalues ​​and eigenvectors of the candidate point and each of the initial known point sets are calculated. Then, based on the eigenvalues ​​and eigenvectors, at least one point set is selected from the multiple initial known point sets as the target known point set. Finally, geological data for the candidate point and the target known point set is calculated. Based on this obtained geological data, not only can a final matching point set be selected for the candidate point, but also the geological data obtained after the candidate point is placed in the point set can be obtained. This allows all candidate points to be placed in the correct point set, resulting in a geotechnical structure composed of accurate feature points, thereby improving the accuracy of the analysis results of the geotechnical structure.

[0013] In a possible implementation, calculating the feature values ​​of the candidate point and each of the initial known point sets includes:

[0014] Putting the candidate points into the initial known point set to obtain a first set of points to be tested;

[0015] Converting the first set of points to be measured into an initial matrix;

[0016] Calculating the covariance matrix of the initial matrix;

[0017] Eigenvalues ​​and eigenvectors are obtained according to the covariance matrix.

[0018] In a possible implementation, the eigenvalue and eigenvector are calculated by the following calculation formula, including: Cw=λw,

[0019] Where C is the covariance matrix, function, n is the number of feature points in the first test set, is the average value of the distances of all feature points in the first test set in the x direction, is the average distance of all feature points in the first test set in the y direction, w is the eigenvector of the covariance matrix C, and λ is the eigenvalue of the covariance matrix C.

[0020] In a possible implementation, determining a target known point set according to the eigenvalue and the eigenvector includes:

[0021] Obtaining a deviation parameter according to the eigenvalue and the eigenvector;

[0022] The initial known point set whose deviation parameter is lower than the preset value is used as the target known point set.

[0023] In a possible implementation, the deviation parameter is calculated using the following formula:

[0024]

[0025] Among them, η is the deviation parameter, and λ1, λ2, and λ3 are all eigenvalues.

[0026] In a possible implementation, obtaining geological data according to the candidate points and the target known point set includes:

[0027] Putting the candidate points into the target known point set to obtain a second set of points to be measured;

[0028] Calculating the plane equation of the second set of points to be measured;

[0029] Geological data is obtained according to the plane equation.

[0030] In a possible implementation: the geological data includes a strike angle and a dip angle;

[0031] The obtaining of geological data according to the plane equation includes:

[0032]

[0033]

[0034] Wherein, θ is the strike angle, μ is the inclination angle, A, B, and C are all plane coefficients of a preset plane, and the preset plane is related to the plane equation.

[0035] In a second aspect of the present application, a geological information monitoring system for rock slopes is provided. The system comprises:

[0036] A data acquisition module is used to acquire a candidate point and a plurality of initial known point sets adjacent to the candidate point, wherein the candidate point refers to a feature point to be classified, and the initial known point set is a collection of feature points belonging to the same category;

[0037] The data calculation module is used to calculate the eigenvalues ​​and eigenvectors of the candidate points and each of the initial known point sets:

[0038] a data determination module, configured to determine a target known point set according to the eigenvalue and the eigenvector, wherein the target known point set is at least one of the multiple initial known point sets;

[0039] A data generation module is used to obtain geological data based on the candidate points and the target known point set.

[0040] In a third aspect of the present application, a device for monitoring geological information of a rock slope is provided. The device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements any of the above-mentioned methods for monitoring geological information of a rock slope when executing the program.

[0041] In a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, any of the above-mentioned geological information monitoring methods for rock slopes is implemented.

[0042] In summary, this application includes at least one of the following beneficial technical effects:

[0043] First, a candidate point and multiple initial known point sets adjacent to the candidate point are obtained. Eigenvalues ​​and eigenvectors are then calculated for each of the candidate point and each of the initial known point sets. Based on the eigenvalues ​​and eigenvectors, at least one point set is selected from the multiple initial known point sets as the target known point set. Finally, geological data is calculated for the candidate point and the target known point set. Based on this geological data, not only is a final matching point set selected for the candidate point, but the geological data obtained after the candidate point is placed in the point set can also be obtained. This allows all candidate points to be placed in the correct point set, resulting in a geotechnical structure composed of accurate feature points, thereby improving the accuracy of the geotechnical structure analysis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic diagram of an exemplary operating environment of an embodiment of the present application.

[0045] Figure 2 It is a flow chart of the geological information monitoring method of the rock slope according to the embodiment of the present application.

[0046] Figure 3 It is a schematic diagram of determining feature vectors in a two-dimensional point cloud in an embodiment of the method of the present application.

[0047] Figure 4 It is a schematic diagram of determining feature vectors in a three-dimensional point cloud in an embodiment of the method of the present application.

[0048] Figure 5 This is an example diagram of a three-dimensional real-scene model of the monitoring area in the embodiment of the method of this application.

[0049] Figure 6 This is an example diagram of a three-dimensional point cloud model of the monitoring area in an embodiment of the method of the present application.

[0050] Figure 7 This is an example diagram of the distribution of known point sets on the structural surface of the monitoring area in the embodiment of the method of this application.

[0051] Figure 8 This is a block diagram of a geological information monitoring system for rock slopes according to an embodiment of the present application.

[0052] Explanation of the accompanying symbols: 10. Data acquisition terminal; 20. Data processing terminal; 21. Data acquisition module; 22. Data calculation module; 23. Data determination module; 24. Data generation module; 30. Display terminal. DETAILED DESCRIPTION

[0053] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0054] Figure 1 A schematic diagram of an exemplary operating environment in which embodiments of the present application can be implemented is shown. The operating environment includes a data acquisition terminal 10, a data processing terminal 20 and a display terminal 30. The data processing terminal 20 is communicatively connected to the data acquisition terminal 10 and the display terminal 30 respectively.

[0055] Among them, the data acquisition terminal 10 is an intelligent terminal such as an unmanned aerial camera, an unmanned aerial vehicle radar, a radio altimeter, etc. The data acquisition terminal 10 is used to collect the geotechnical structure conditions in the monitoring area, obtain an image of the monitoring area, or obtain data such as the partitions of different sub-areas in the monitoring area. Sub-areas such as rocks, ground cracks, etc. are located in the monitoring area and are combined together to form the structure of the rock slope. In this example, first, according to the size of the monitoring area and the collection range of each data acquisition terminal 10, an appropriate number of data acquisition terminals 10 are selected to ensure the real-time and comprehensiveness of data collection. Then, a reasonable collection plan is formulated according to the terrain conditions of the monitoring area, including the navigation route, collection time and angle selection. Finally, the selected data acquisition terminal 10 is used to obtain data such as the image of the monitoring area and the size of the intervals between the sub-areas according to the set collection plan to obtain data related to the monitoring area, providing data support for the data processing terminal 20 to evaluate the monitoring area.

[0056] The data processing terminal 20 is composed of one or more servers. After obtaining the image of the monitoring area, the interval size of different sub-areas and other data from the data acquisition terminal 10, the data processing terminal 20 establishes a three-dimensional model of the monitoring area. In order to ensure the accuracy of the assessment of the geotechnical structure of the monitoring area, the geotechnical structure of the monitoring area is further analyzed and processed based on the three-dimensional model to obtain accurate assessment results.

[0057] The display terminal 30 is composed of one or more displays. After further analysis and processing based on the three-dimensional model, the data processing terminal 20 transmits the obtained evaluation results to the display terminal 30 for display, so that geologists can intuitively view the geotechnical structure of the monitoring area.

[0058] It should be noted that Figure 1 The operating environment shown is for illustrative purposes only and is not intended to limit the application or use of the embodiments of the present invention. For example, the operating environment may include multiple data acquisition terminals 10, multiple data processing terminals 20, and multiple display terminals 30.

[0059] Figure 2 A flow chart of a method for monitoring geological information of a rock slope according to an embodiment of the present application is shown. Figure 1 Specifically, the main process of the geological information monitoring method for rock slopes is described as follows.

[0060] Step S100: Acquire a three-dimensional model of the monitoring area.

[0061] Specifically, after receiving the image of the monitored area and the intervals between different sub-areas, the data processing terminal 20 uses the structure-from-motion (SFM) algorithm to identify and match feature points in the image. Feature points are pixels in the image. By classifying and merging each feature point, the geotechnical structure of the monitored area is deduced. Then, based on the SfM algorithm, multi-view stereo (MVS) technology is used to generate a denser three-dimensional point cloud by matching the brightness and color between pixels in the image. Finally, the generated three-dimensional point cloud is denoised and invalid feature points are removed through filters using density-based filtering, outlier detection and removal, plane fitting, and normal filtering to obtain a three-dimensional model.

[0062] In order to further analyze the geotechnical structure in the monitoring area, this application inputs the obtained three-dimensional model into the next step for further analysis and processing.

[0063] Step S200: obtaining candidate points and a plurality of initial known point sets adjacent to the candidate points according to the three-dimensional model. The candidate points refer to feature points to be classified, and the initial known point sets are a collection of feature points belonging to the same category.

[0064] After obtaining the 3D model, the K-nearest neighbor (KNN) classification algorithm is used to determine candidate points and an initial known point set. Candidate points are unclassified feature points in the 3D model, while an initial known point set stores feature points of the same type, such as a set of feature points that all belong to the same crack or rock.

[0065] In a three-dimensional model, each feature point has a unique spatial coordinate. Therefore, after determining the candidate point, you can select multiple initial known point sets adjacent to the candidate point. Then, according to the following steps, determine the point set to which the candidate point belongs. That is, include the candidate point in one of the initial known point sets, so that each feature point has a corresponding point set, improving the accuracy of the three-dimensional model.

[0066] Step S300: Calculate the eigenvalues ​​and eigenvectors of the candidate points and each of the initial known point sets.

[0067] Specifically, the candidate points are sequentially added to each initial known point set to obtain a first set of test points after the candidate points are added. In this example, after each initial known point set is added, a corresponding first set of test points is generated. Therefore, when there are multiple known initial point sets, multiple first sets of test points will also be obtained. Then, for each first set of test points, the following process is executed:

[0068] Step S310: Convert the first set of points to be tested into an initial matrix. Assuming that the first set of points to be tested is m vectors of n dimensions, the first set of points to be tested is a matrix X with m rows and n columns, that is:

[0069]

[0070] Then perform zero mean processing on each row of the matrix X, that is, subtract the mean of the row so that the mean value of the row is 0: in, The matrix after mean value is called the initial matrix and is represented by M.

[0071] Step S320: Calculate the covariance matrix of the initial matrix. Specifically, the covariance matrix is: C is the covariance matrix, M is the initial matrix, and T represents the matrix transpose, such as M T is the transposed matrix of the initial matrix.

[0072] Step S330: Obtain eigenvalues and eigenvectors based on the covariance matrix. The calculation formula is: Cw = λw, where C is the covariance matrix, function n is the number of feature points in the first set of points to be measured, is the average value of the distances of the feature points in the first set of points to be measured in the x direction, is the average value of the distances of the feature points in the first set of points to be measured in the y direction, w is the eigenvector of the covariance matrix C, and λ is the eigenvalue of the covariance matrix C.

[0073] It should be noted that for each of the multiple first sets of points to be measured obtained in this application, the eigenvalues and eigenvectors of each first set of points to be measured need to be calculated through the processes of the above steps S310 - step S330.

[0074] In addition, after calculating the eigenvalues of all the first sets of points to be measured, arrange the corresponding eigenvectors in descending order of eigenvalues to obtain a reference matrix, denoted by Q. Then, according to requirements, reduce the dimension of matrix M to obtain matrix Y. According to the dimension k of matrix Y, where k < m, take the first k rows of the reference matrix Q as the transformation matrix P. Then, the reduced - dimension matrix Y is: Y = M * P.

[0075] According to the calculation formula of matrix Y, each column in matrix Y is an eigenvector and they are orthogonal to each other. If the principal component analysis method is adopted, the direction with the largest variance is taken as the main feature. For the sake of illustration, take Figure 3 as an example: Suppose there is a two - dimensional point cloud, and all the feature points in this two - dimensional point cloud are located within an elliptical shape. Then the two - dimensional point cloud only includes two variables in the x and y directions. Suppose there are two axes with different lengths. The algebraic equation of the long axis is y1 = a1x1 + b1, and the algebraic equation of the short axis is y2 = a2x2 + b2. The change of the point cloud along the long axis is larger, while the change along the short axis is smaller. At this time, when calculated using the principal component analysis algorithm, if k = 1, the direction that can be extracted is the direction with the largest variance, that is, the long - axis direction, which not only achieves the purpose of dimensionality reduction but also clarifies the direction with larger variance. Then the reduced - dimension feature points are the projections on the long axis, representing the main information of this two - dimensional point cloud. The information in the short - axis direction is not the main information and is thus lost. If k = 2, the point cloud is not reduced in dimension, and the short - axis direction is the direction of the second eigenvector, which is orthogonal and uncorrelated to the long - axis direction. However, at this time, the main direction of the point cloud can also be clarified as the long - axis direction.

[0076] The two-dimensional point cloud is extended to the three-dimensional point cloud. At this time, the three-dimensional point cloud is included in the ellipsoid. The directions of the three eigenvectors calculated by the principal component analysis algorithm are z1=a1y1+b1x1+c1, z2=a2y2+b2x2+c2, z3=a3y3+b3x3+c3, and their eigenvalues ​​are represented by λ1, λ2, and λ3. When k=1, all points are projected to the z1 direction, forming a straight line; when k=2, the point cloud is projected to the z1 and z2 directions, forming a plane; when k=3, the point cloud is still in three-dimensional space, such as Figure 4 It should be noted that, since this application needs to know the classification of feature points in a three-dimensional model, the point cloud involved does not need dimensionality reduction, so in this example, k=3.

[0077] Step S400: determining a target known point set according to the eigenvalues ​​and the eigenvectors, where the target known point set is at least one point set among the multiple initial known point sets.

[0078] After calculating the eigenvalues ​​and eigenvectors of each first set of points to be measured, the deviation parameters of the initial known point set corresponding to the first set of points to be measured are calculated based on the eigenvalues ​​and eigenvectors, specifically:

[0079] Among them, η is the deviation parameter, and λ1, λ2, and λ3 are all eigenvalues.

[0080] Then, the initial known point set with a deviation parameter lower than the preset value is used as the target known point set. In this example, when η is 0, the initial known point set is completely in the same plane, but due to measurement errors and slight surface fluctuations, η is basically not 0 in reality. When judging whether a point set can be considered to be in a plane, it is necessary to set a deviation threshold, that is, the maximum allowable value of the deviation parameter. When the deviation parameter η of a point set is less than the set deviation threshold, it can be determined that it belongs to the same plane. The larger the set deviation threshold, the looser the condition for whether the point set is a plane. In this example, the deviation threshold is 0.2, so when the deviation parameter η ≥ 0.2, the initial known point set will be discarded.

[0081] It should be noted that the deviation threshold set in this example is 0.2 because it is widely believed in the industry that when the main components of a point set account for more than 80% of the entire point set, it can already well represent the entire point set.

[0082] It should also be noted that the above-mentioned initial known point set corresponding to the first set of points to be tested means: after eliminating the candidate points in the first set of points to be tested, a point set that is exactly the same as the initial known point set is obtained, and the initial known point set is considered to correspond to the first set of points to be tested.

[0083] In addition, if there are multiple deviation parameters all smaller than the deviation threshold, the initial known point set corresponding to the first test point set whose deviation parameter is smaller than the deviation threshold will be used as the target known point set, that is, there are multiple target known point sets.

[0084] Step S500: Obtain geological data based on the candidate points and the target known point set.

[0085] For the target known point set obtained, it can be preliminarily determined that most of the feature points inside it are in the same plane. Since the number of adjacent feature points searched by the target known point set is limited, and the size and number of structural surfaces vary from place to place, the target known point set is only a part of the structural surface. Therefore, after determining the coplanarity of the target known point set, this application also needs to place the candidate points in the target known point set in sequence, obtain the corresponding second set of points to be tested, and calculate the geological data of each second set of points to be tested. Finally, the target known point set in which the candidate points are finally placed is determined based on the geological data, thus completing the classification of the candidate points.

[0086] The second set of points to be tested corresponding to the target known point set is a point set identical to the target known point set obtained after eliminating candidate points in the second set of points to be tested. The target known point set is considered to correspond to the second set of points to be tested.

[0087] Specifically, since all the feature points in the target known point set are not strictly speaking in the same plane, the present application adopts the least squares method to fit the best plane of the second test point set. The fitted plane can minimize the variance of the distances from all feature points in the second test point set to the plane. For ease of explanation, an example is given below:

[0088] First, set a preset plane in advance. If the plane equation of the preset plane is: Ax+By+Cz+D=0, where A, B, C, and D are the plane coefficients of the preset plane, then the distance d from point o (x, y, z) in space to the preset plane can be calculated using the following formula:

[0089]

[0090] Then the variance S of the distances from each point in the second set of measured points to the preset plane can be calculated using the following formula:

[0091] If you want the variance S to be minimum, it should satisfy:

[0092] At the same time, let a1 be -A / C, a2 be -B / C, and a3 be -D. Finally, through the calculation formula of variance S and the conditions that variance S needs to meet, we get the following set of equations:

[0093]

[0094] Solving the above equations can obtain the components of the unit normal vector of the preset plane in all directions:

[0095]

[0096] The unit normal vector of the preset plane is used as the normal vector of the candidate point in the Knn algorithm, so that all feature points in the second set of points to be measured can be marked with the normal vector of the preset plane.

[0097] After obtaining the plane equation of the preset plane, the geological data of the second set of test points can be calculated using the plane equation. The geological data includes the strike angle θ and the dip angle μ. The strike angle θ is the angle between the strike line and the true north direction, specifically:

[0098]

[0099] The inclination angle μ is:

[0100] The calculation formulas for strike angle and dip angle require that the plane coefficients of the plane equation are not 0. When a coefficient is 0, refer to Table 1 to determine the strike angle and dip angle. Table 1:

[0101] A B C Direction inclination 0 0 1 level 0 0 1 0 East-West Direction 90 1 0 0 North-South direction 90 0 N N East-West Direction - N 0 N North-South direction - N N 0 - 90

[0102] The N in Table 1 refers to the true north direction, also referred to as the N axis. Therefore, the direction of the structural surface formed by the second set of test points is:

[0103]

[0104] After obtaining the strike angle and inclination of the second set of points to be tested, that is, after obtaining the strike angle and inclination of the structural surface formed by the second set of points to be tested, the target known point set corresponding to the second set of points to be tested with the smallest strike angle and inclination values ​​is selected as the final known point set, and the candidate point is placed in the final known point set. The strike angle and inclination values ​​of the second set of points to be tested are also used to obtain the strike angle and inclination of the structural surface of the final known point set. Therefore, the present application can not only select an adaptive point set for the candidate point, but also obtain the strike angle of the structural surface formed after the candidate point is placed in the point set, thereby obtaining an accurate geotechnical structure of the monitoring area.

[0105] To facilitate the description of the above-mentioned process of processing the three-dimensional model of the monitoring area in steps S100 to S500, the engineering example carried out by this application is as follows:

[0106] First, a monitoring area was selected on the highway slope. A high-resolution digital image of the steep slope in the monitoring area was obtained by close-range photography using a drone. A high-resolution 3D real-scene model (such as the ContextCapture software) was built using the ContextCapture software. Figure 5 ) and 3D point cloud models (as shown Figure 6 As shown in Figure 2), the 3D point cloud model is also called a 3D model. In the 3D point cloud, an area with obvious surface features is selected and the semi-automatic recognition algorithm of the slope structural surface information is applied. The DSE software of the Matlab platform is used to obtain the structural surface information of the slope and draw the distribution map of the known point set in the structural surface (as shown in Figure 2). Figure 7 Finally, the structural surface of the monitoring area is shown in Table 2:

[0107] Group 1 (marked by dotted line) Group 2 (marked with solid lines) Number of measurements: 10 / 10 Number of measurements: 26 / 26 Inclination: 202.87° Inclination direction: 155.68° Inclination: 64.91° Inclination: 57.61° Confidence angle: 20.15° Confidence angle: 4.55° Confidence level: 95% Confidence level: 95% Linear crack ratio [1 / m]: 0.33 Linear crack ratio [1 / m]: 1.97 Total exposed length [m]: 28.12 Total [m]: 103.91 Average value [m]: 3.03 Average value [m]: 0.51 Median[m]:0.47 Median[m]:0.37 Standard deviation [m]: 4.99 Standard deviation [m]: 0.62 Minimum value [m]: 0.0 Minimum value [m]: 0.0 Maximum value [m]: 12.93 Maximum value [m]: 3.56

[0108] It can be seen from this that when selecting an adaptive point set for a candidate point, the present application can also obtain information such as the distribution and position of the structural surface of the known point set after the candidate point is placed in different known point sets.

[0109] It should be noted that after obtaining an accurate geotechnical structure of the monitored area, this application not only transmits the geotechnical structure to the display terminal 30 for display, but also archives it in a geographic information system for subsequent access. This image is also used as a stereographic projection to clearly understand the geotechnical structure of the monitored area, providing data support for slope stability analysis. Furthermore, the orientation of the structural planes of the geotechnical structure is cataloged to facilitate the discovery of geotechnical structure changes during long-term observation, providing data support for analyzing the development patterns of the geotechnical structure.

[0110] Figure 8 A block diagram of a geological information monitoring system for a rock slope according to an embodiment of the present application is shown. The system includes a data acquisition module 21 , a data calculation module 22 , a data determination module 23 and a data generation module 24 .

[0111] The data acquisition module 21 is used to acquire candidate points and a plurality of initial known point sets adjacent to the candidate points. The candidate points are feature points to be classified, and the initial known point sets are a collection of feature points belonging to the same category.

[0112] The data calculation module 22 is used to calculate the eigenvalues ​​and eigenvectors of the candidate points and each initial known point set:

[0113] A data determination module 23 is configured to determine a target known point set according to the eigenvalues ​​and the eigenvectors, where the target known point set is at least one of the multiple initial known point sets;

[0114] The data generation module 24 is used to obtain geological data based on the candidate points and the target known point set.

[0115] The modules involved in the embodiments described in this application can be implemented in software or hardware. The modules described can also be set in a processor. For example, it can be described as follows: a processor includes a data acquisition module 21, a data calculation module 22, a data determination module 23, and a data generation module 24. In some cases, the names of these modules do not constitute a limitation on the modules themselves. For example, the data acquisition module 21 can also be described as "a module for obtaining candidate points and multiple initial known point sets adjacent to the candidate points."

[0116] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0117] In order to better execute the program of the above method, the present application also provides a device, which includes a memory and a processor.

[0118] The memory can be used to store instructions, programs, codes, code sets, or instruction sets. The memory can include a program storage area and a data storage area. The program storage area can store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the aforementioned method for monitoring geological information of rock slopes. The data storage area can store data related to the aforementioned method for monitoring geological information of rock slopes.

[0119] The processor may include one or more processing cores. The processor executes the various functions of the present application and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory, calling data stored in the memory. The processor may be at least one of a special application integrated circuit, a digital signal processor, a digital signal processing device, a programmable logic device, a field programmable gate array, a central processing unit, a controller, a microcontroller, and a microprocessor. It is understood that for different devices, the electronic device used to implement the above-mentioned processor functions can also be other, and the embodiments of the present application are not specifically limited.

[0120] The present application also provides a computer-readable storage medium, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, among other media capable of storing program code. The computer-readable storage medium stores a computer program capable of being loaded by a processor and executing the aforementioned rock slope geological information monitoring method.

[0121] The above description is merely a preferred embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the aforementioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for monitoring geological information of rock slopes, characterized in that: include: Obtaining a three-dimensional model of the monitoring area, and obtaining candidate points and a plurality of initial known point sets adjacent to the candidate points based on the three-dimensional model, wherein the candidate points are feature points to be classified, and the initial known point sets are a collection of feature points belonging to the same category; the feature points are used to deduce the geotechnical structure of the monitoring area; Calculating the eigenvalues ​​and eigenvectors of the candidate points and each of the initial known point sets; Determine a target known point set according to the eigenvalue and the eigenvector, wherein the target known point set is at least one point set among the multiple initial known point sets; Geological data is obtained according to the candidate points and the target known point set.

2. The geological information monitoring method for rock slope according to claim 1, characterized in that: The calculating of the feature values ​​of the candidate points and each of the initial known point sets includes: Putting the candidate points into the initial known point set to obtain a first set of points to be tested; Converting the first set of points to be measured into an initial matrix; Calculating the covariance matrix of the initial matrix; Eigenvalues ​​and eigenvectors are obtained according to the covariance matrix.

3. The geological information monitoring method for rock slope according to claim 2, characterized in that: The eigenvalues ​​and eigenvectors are calculated using the following formulas: Cw=λw, Where C is the covariance matrix, function n is the number of feature points in the first test set, is the average value of the distances of all feature points in the first test set in the x direction, is the average distance of all feature points in the first test set in the y direction, w is the eigenvector of the covariance matrix C, and λ is the eigenvalue of the covariance matrix C.

4. The geological information monitoring method for rock slope according to claim 1, characterized in that: The determining of the target known point set according to the eigenvalue and the eigenvector includes: Obtaining a deviation parameter according to the eigenvalue and the eigenvector; The initial known point set whose deviation parameter is lower than the preset value is used as the target known point set.

5. The geological information monitoring method for rock slope according to claim 4, characterized in that: The deviation parameter is calculated by the following formula: Among them, η is the deviation parameter, and λ1, λ2, and λ3 are all eigenvalues.

6. The geological information monitoring method for rock slope according to claim 1, characterized in that: The obtaining of geological data according to the candidate points and the target known point set includes: Putting the candidate points into the target known point set to obtain a second set of points to be measured; Calculating the plane equation of the second set of points to be measured; Geological data is obtained according to the plane equation.

7. The geological information monitoring method for rock slope according to claim 6, characterized in that: The geological data include strike angle and dip angle; The obtaining of geological data according to the plane equation includes: Wherein, θ is the strike angle, μ is the inclination angle, A, B, and C are all plane coefficients of a preset plane, and the preset plane is related to the plane equation.

8. A geological information monitoring system for rock slopes, characterized in that: include: A data acquisition module (21) is used to acquire candidate points and a plurality of initial known point sets adjacent to the candidate points based on the three-dimensional model, wherein the candidate points are feature points to be classified, the initial known point sets are a collection of feature points of the same type, the feature points are used to deduce the geotechnical structure of the monitored area, and the three-dimensional model is a three-dimensional model of the monitored area; The data calculation module (22) is used to calculate the eigenvalues ​​and eigenvectors of the candidate points and each of the initial known point sets: A data determination module (23) is used to determine a target known point set based on the eigenvalue and the eigenvector, wherein the target known point set is at least one of the multiple initial known point sets; A data generation module (24) is used to obtain geological data based on the candidate points and the target known point set.

9. A geological information monitoring device for rock slopes, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images