Slope structural surface identification method, device and equipment and readable storage medium

Abstract

The invention provides a slope structural plane identification method, device and equipment and a readable storage medium, and relates to the technical field of three-dimensional point cloud structural plane identification, and the method comprises the steps: obtaining a three-dimensional point cloud data set; obtaining a plurality of initial point cloud sets; obtaining a screened target point cloud set; obtaining a normal vector of each point in the target point cloud set; obtaining a structural plane grouping category corresponding to each point in the target point cloud set; and performing calculation according to the structural surface grouping category to obtain a target calculation result. According to the method, the slope image is converted and reconstructed to establish the slope three-dimensional point cloud set, the boundary points are screened and rejected through the curvature threshold value, the calculation precision of the normal vector is improved, the remaining center points are input into the preset neural network for recognition and classification, the corresponding structural surface grouping category is obtained, and the classification accuracy of the structural surface is improved. According to the method, accurate recognition of the rock mass structural surfaces is realized in combination with the neural network model, and the recognition efficiency of the rock mass structural surfaces is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of three-dimensional point cloud structural surface recognition, and in particular to a slope structural surface recognition method, device, equipment and readable storage medium. Background Art

[0002] In the existing research on slope structural surfaces, the research objects are usually natural outcrop slopes, which are characterized by being undamaged, the original structure is intact, there are many exposed structures, obvious structural features, and large changes in surface curvature. Existing technical means can be used to solve the feature extraction of such body structures. However, for a large number of high-steep and broken rock slopes, the surface structural features and surface curvature are not obvious. The existing technical means are low in accuracy, poor in effect, and slow in speed in the application of high-steep slope feature recognition, and it is difficult to play a role. Therefore, it is urgent to propose an intelligent analysis and recognition method for complex rock mass three-dimensional point cloud structural surfaces. Summary of the invention

[0003] The purpose of the present invention is to provide a slope structure surface identification method, device, equipment and readable storage medium to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0004] In a first aspect, the present application provides a slope structure surface identification method, comprising:

[0005] Acquire a slope image, and transform and reconstruct the slope image to obtain a three-dimensional point cloud data set;

[0006] Classifying the three-dimensional point cloud data set based on a nearest neighbor search algorithm to obtain a plurality of initial point cloud sets, wherein the initial point cloud sets are composed of target points and nearest neighbor points;

[0007] Calculating the curvature value of each target point according to the multiple initial point cloud sets, and performing coplanar screening of the points based on the curvature values ​​to obtain a screened target point cloud set;

[0008] Calculate according to the target point cloud set to obtain the normal vector of each point in the target point cloud set;

[0009] Bringing the normal vector into a pre-trained neural network model to obtain the structural surface grouping category corresponding to each point in the target point cloud set;

[0010] Calculation is performed according to the structural surface grouping category corresponding to each point in the target point cloud set to obtain a target calculation result, wherein the target calculation result includes the inclination and the dip of each structural surface in the structural surface grouping category.

[0011] In a second aspect, the present application also provides a slope structure surface identification device, comprising:

[0012] A first acquisition unit is used to acquire a slope image, and perform transformation and reconstruction based on the slope image to obtain a three-dimensional point cloud data set;

[0013] A classification unit, used for classifying the three-dimensional point cloud data set based on a nearest neighbor search algorithm to obtain a plurality of initial point cloud sets, wherein the initial point cloud sets are composed of target points and nearest neighbor points;

[0014] A screening unit, configured to calculate a curvature value of each target point according to a plurality of initial point cloud sets, and perform coplanar screening of the points based on the curvature value to obtain a screened target point cloud set;

[0015] A first obtaining unit is used to perform calculation according to the target point cloud set to obtain a normal vector of each point in the target point cloud set;

[0016] An input unit is used to input the normal vector into a pre-trained neural network model to obtain a structural surface grouping category corresponding to each point in the target point cloud set;

[0017] The first calculation unit is used to perform calculation according to the structural surface grouping category corresponding to each point in the target point cloud set to obtain a target calculation result, wherein the target calculation result includes the inclination and the dip of each structural surface in the structural surface grouping category.

[0018] In a third aspect, the present application also provides a slope structure surface identification device, comprising:

[0019] Memory for storing computer programs;

[0020] A processor is used to implement the steps of the slope structure surface identification method when executing the computer program.

[0021] In a fourth aspect, the present application further provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned slope structural surface identification method are implemented.

[0022] The beneficial effects of the present invention are:

[0023] The present invention establishes a three-dimensional point cloud set of the slope by transforming and reconstructing the slope image, and screens and eliminates boundary points through a curvature threshold to improve the calculation accuracy of the normal vector, and inputs the remaining center points into a preset neural network for identification and classification to obtain the corresponding structural surface grouping category, thereby calculating the inclination and dip angle of any structural surface. The present invention realizes the accurate identification of rock structural surfaces in combination with a neural network model, and effectively improves the recognition efficiency of rock structural surfaces.

[0024] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 It is a schematic diagram of the process of the slope structural surface identification method described in an embodiment of the present invention;

[0027] Figure 2 is a schematic diagram of an initial point cloud set described in an embodiment of the present invention;

[0028] Figure 3 Schematic diagram of geometric coordinates of normal vectors described in an embodiment of the present invention;

[0029] Figure 4 It is a schematic diagram of the structure of the slope structure surface identification device described in an embodiment of the present invention;

[0030] Figure 5 It is a schematic diagram of the structure of the slope structure surface identification device described in an embodiment of the present invention.

[0031] Markings in the figure:

[0032] 10. First acquisition unit; 20. Classification unit; 30. Screening unit; 40. First obtaining unit; 50. Bring-in unit; 60. First calculation unit; 800. Slope structure surface identification device; 801. Processor; 802. Memory; 803. Multimedia component; 804. I / O interface; 805. Communication component. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0034] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0035] Embodiment 1:

[0036] This embodiment provides a slope structural surface identification method.

[0037] See also Figure 1 , the figure shows that the method includes step S10, step S20, step S30, step S40, step S50 and step S60.

[0038] Step S10. Obtain a slope image, and perform transformation and reconstruction based on the slope image to obtain a three-dimensional point cloud data set;

[0039] Specifically, considering the complex terrain at the location of the slope, drones are usually used to shoot slope images. First, it is necessary to determine the key research area based on the on-site environment of the slope and formulate a flight plan for the drone. The flight plan needs to include the drone's take-off and landing locations, flight time, flight trajectory, detection control points, and key detection areas. It is necessary to ensure the flight safety of the drone and to ensure that comprehensive slope images can be collected. All the collected slope image data are converted into a three-dimensional point cloud dataset through the Structure From Motion (SFM) method.

[0040] Step S20. Classify the three-dimensional point cloud data set based on the nearest neighbor search algorithm to obtain multiple initial point cloud sets, where the initial point cloud sets are composed of target points and nearest neighbor points;

[0041] Specifically, the k-nearest neighbor search algorithm is used to perform neighbor search on the 3D point cloud dataset, such as Figure 2As shown, for any point in the three-dimensional point cloud, multiple adjacent points will be found to form a point cloud set. The dotted line range is an initial point cloud set, the black dots are target points, the white dots are adjacent points, and the gray dots are the remaining points.

[0042] Step S30. Calculate the curvature value of each target point based on the multiple initial point cloud sets, and perform coplanar screening of the points based on the curvature values ​​to obtain a screened target point cloud set;

[0043] Specifically, the curvature value of each point in the initial point cloud set is calculated by the principal component analysis algorithm, and a coplanar detection is performed.

[0044] Specifically, step S30 specifically includes step S31, step S32, step S33, step S34 and step S35:

[0045] Step S31. Calculate based on the initial point cloud set to obtain a covariance matrix;

[0046] Step S32. Perform eigenvalue decomposition based on the covariance matrix to obtain multiple eigenvalues;

[0047] Specifically, the principal component analysis algorithm automatically calculates the three eigenvalues ​​of each point by constructing a covariance matrix, which are λ1, λ2, and λ3, where λ1≥λ2≥λ3.

[0048] Step S33. Calculate the curvature based on multiple eigenvalues ​​to obtain the curvature value of the target point in the initial point cloud set;

[0049] Step S34. Compare the curvature value of each target point with the first set threshold value, and select a plurality of basic points whose corresponding curvature values ​​are less than the first set threshold value;

[0050] Step S35. Constructing a target point cloud based on all basic points;

[0051] Specifically, the calculation formula of the curvature value is:

[0052]

[0053] Where φ is the curvature value; λ1, λ2 and λ3 are eigenvalues, and λ1≥λ2≥λ3;

[0054] The calculated curvature value is compared with the preset curvature threshold, and the points whose curvature value is greater than the curvature threshold are considered as boundary points and are removed.

[0055] Step S40. Calculate according to the target point cloud set to obtain the normal vector of each point in the target point cloud set;

[0056] Specifically, the least squares method is used to calculate the normal vectors of the coplanar points, and the expression of the fitted plane is:

[0057] A i x+B i y+C i z+D i =0

[0058] Among them, A i , B i and C i Respectively represent the three-dimensional coordinates of the normal vector of the fitting plane where the i-th point is located; x, y and z represent the three-dimensional coordinates of the i-th point, respectively. i is the distance from the i-th point to the center of the fitting plane.

[0059] Step S50: Bring the normal vector into the pre-trained neural network model to obtain the structural surface grouping category corresponding to each point in the target point cloud set;

[0060] Specifically, the present application adopts a self-organizing map neural network model as a recognition model. Unlike general neural networks that are trained based on the reverse transfer of loss functions, the self-organizing map neural network model uses a competitive learning strategy, relying on competition between neurons to gradually optimize the network, and uses a neighbor relationship function to maintain the topological structure of the input space. Therefore, compared to neural networks that require supervised learning, the training phase of the self-organizing map neural network model does not require sample labels, and data can be clustered without knowing the category, greatly improving the efficiency of data processing. The recognition phase of the self-organizing map neural network model also has high recognition efficiency and recognition accuracy.

[0061] Specifically, step S50 specifically includes step S51, step S52, step S53, step S54, step S55, step S56, step S57, step S58, step S59 and step S510:

[0062] Step S51. Obtaining the initial learning rate, initial neighborhood radius, initial weight vector, maximum number of iterations and set number of nodes of the neural network model;

[0063] Step S52. Calculate the distance between each point in the target point cloud and each neuron in the neural network model, and determine the target neuron corresponding to the minimum distance;

[0064] Specifically, a normal vector of a point is randomly selected in the input target point cloud set as an input sample, the distance between the input sample and multiple neurons is calculated, and the neuron with the smallest distance is found as the winning neuron.

[0065] In this application, the improved square of the cosine distance is used to calculate the distance between the input sample and the neuron, and the corresponding calculation formula is:

[0066]

[0067] Among them, P i is the i-th point in the target point cloud; P j is the jth neuron; is the normal vector of the i-th point in the target point cloud; is the transpose of the normal vector of the jth neuron.

[0068] Step S53. Calculation operation: based on the initial neighborhood radius and the minimum distance corresponding to the target neuron, calculate the winning neighborhood;

[0069] Specifically, the calculation formula for the winning neighborhood is:

[0070]

[0071] Among them, h(i) is the winning neighborhood of the i-th point in the target point cloud set; d min (i) is the distance between the i-th point in the target point cloud and the winning neuron; δ(t-1) is the initial neighborhood radius after the t-1th iteration update.

[0072] Step S54. Acquisition operation: acquiring the number of calculations of the winning neighborhood as the number of iterations;

[0073] Step S55. First update operation: based on the initial learning rate, the number of iterations and the maximum number of iterations, update the initial learning rate;

[0074] Specifically, the update formula for the initial learning rate is:

[0075]

[0076] Among them, α(t) is the initial learning rate after the tth iteration update; α0 is the initial learning rate; t is the number of iterations; T is the maximum number of iterations.

[0077] Step S56. Second update operation: based on the initial neighborhood radius, the number of iterations and the maximum number of iterations, update the initial neighborhood radius;

[0078] Specifically, the update formula of the initial neighborhood radius is:

[0079]

[0080] Among them, δ(t) is the initial neighborhood radius after the tth iteration update; k is the set number of nodes; t is the number of iterations; T is the maximum number of iterations.

[0081] Step S57. The third update operation: based on the initial weight vector, the winning neighborhood, the initial weight vector, the initial learning rate, the normal vector and the initial neighborhood radius, update the initial weight vector;

[0082] Specifically, the update formula of the initial weight vector is:

[0083]

[0084] Among them, W j (t+1) is the weight vector of the j-th neuron after the t+1th iteration update; W j (t) is the weight vector of the j-th neuron after the t-th iteration update; α(t) is the initial learning rate after the ith iteration update; h(t) is the winning neighborhood of the ith point in the target point cloud set; is the normal vector of the i-th point in the target point cloud.

[0085] Step S58. Repeat the calculation operation, the acquisition operation, the first update operation, the second update operation and the third update operation until the number of iterations is greater than the maximum number of iterations, and divide all points in the target point cloud set into structural surface classification clusters based on the updated initial weight vector, and the structural surface classification clusters include multiple structural surface clusters;

[0086] Specifically, the above iterative operation is repeated until a maximum number of iterations is reached.

[0087] Step S59. Adjust and set the number of nodes to obtain a plurality of corresponding structural surface classification clusters, wherein the number of structural surface clusters in each structural surface classification cluster is different;

[0088] Specifically, by changing the set node number k of the output layer, different numbers of structural surface classification clusters can be obtained. Usually, the set node number is an integer between 2 and 8. The node number can be adjusted according to the application scenario and is not particularly limited here.

[0089] Step S510. Determine an optimal structural surface classification cluster from multiple structural surface classification clusters as a structural surface grouping category;

[0090] Specifically, step S510 specifically includes step S5101, step S5102, step S5103, step S5104, step S5105, step S5106, step S5107, step S5108 and step S5109:

[0091] Step S5101. Calculate the trace of the covariance matrix of the structural surface cluster based on the structural surface classification cluster to obtain a first value;

[0092] Step S5102. Calculate the trace of the covariance matrix between the structural surface clusters based on the structural surface classification clusters to obtain a second value;

[0093] Step S5103. Calculate the difference between the set number of nodes and the second set threshold to obtain a third value;

[0094] Step S5104. Calculate the difference between the number of points in the target point cloud set and the number of structural surface clusters in the structural surface classification cluster to obtain a fourth value;

[0095] Step S5105. Calculate the ratio of the second value to the first value to obtain a fifth value;

[0096] Step S5106. Calculate the ratio of the fourth value to the third value to obtain a correction factor;

[0097] Step S5107. Calculate the product of the fifth value and the correction factor to obtain an index value;

[0098] Step S5108. Determine the maximum value from the multiple index values ​​corresponding to the multiple structural surface classification clusters as the target index value;

[0099] Step S5109. The structural surface classification cluster corresponding to the target index value is used as the optimal classification cluster, and the optimal classification cluster is used as the structural surface grouping category;

[0100] Specifically, the Kahanan index is used as an evaluation index of clustering effectiveness to determine the optimal classification cluster. The calculation formula of the Kahanan index is:

[0101]

[0102] Where CH is the Kahanan index; tr(B K ) is the covariance matrix B between structural face clusters K trace; tr(W K ) is the covariance matrix W of the structural face cluster K trace; N is the number of points in the target point cloud; k is the set number of nodes.

[0103] The structural surface classification cluster corresponding to the largest Kahanan index is taken as the structural surface classification group.

[0104] Step S60. Calculate according to the structural surface grouping category corresponding to each point in the target point cloud set to obtain a target calculation result, the target calculation result including the inclination and inclination of each structural surface in the structural surface grouping category;

[0105] Specifically, step S60 specifically includes step S61, step S62, step S63, step S64, step S65, step S66 and step S67:

[0106] Step S61. Extracting structural surface grouping categories based on a spatial clustering algorithm to obtain multiple single structural surfaces;

[0107] Step S62. Calculate the normal vector of each single structural surface to obtain multiple target normal vectors, where the target normal vector consists of a horizontal coordinate, a vertical coordinate and a vertical coordinate;

[0108] Specifically, a spatial clustering algorithm is used to extract a single structural surface in the structural surface grouping category, and the normal vector of each structural surface is calculated. The normal vector is a three-dimensional coordinate, including a horizontal coordinate, a vertical coordinate, and a vertical coordinate. The specific calculation principle of the structural surface normal vector is the same as the calculation principle of the normal vector of each point, which will not be repeated here.

[0109] Step S63. Calculate the arccosine function value of the vertical coordinate to obtain the inclination angle;

[0110] Specifically, according to the definition of structural surface occurrence and Figure 3 From the geometric coordinate diagram of the normal vector, we can see that the inclination angle is the angle between the structural surface and the horizontal plane, that is, the angle between the component C of the normal vector n=(A, B, C) on the Z axis and the Z axis. The calculation formula is:

[0111] α=arccos(C)

[0112] Among them, α is the inclination angle of the structural surface; C is the vertical coordinate of the normal vector of the structural surface.

[0113] Step S64. Calculate based on the abscissa and ordinate to obtain an initial tendency;

[0114] Specifically, step S64 specifically includes step S641, step S642, step S643 and step S644:

[0115] Step S641. Calculate the sum of the squares of the horizontal coordinate and the vertical coordinate to obtain a first result;

[0116] Step S642. Perform square root calculation on the first result to obtain a second result;

[0117] Step S643. Calculate the ratio of the ordinate to the second result to obtain a third result;

[0118] Step S644. Calculate the arccosine function value of the third result to obtain the initial tendency;

[0119] Specifically, the initial tendency calculation formula is:

[0120]

[0121] Among them, β0 is the initial inclination; B is the ordinate of the normal vector of the structural surface; A is the abscissa of the normal vector of the structural surface.

[0122] Step S65. Compare the horizontal coordinate with the third set threshold to obtain a comparison result;

[0123] Step S66. When the comparison result indicates that the horizontal coordinate is less than the third set threshold, the difference between the fourth set threshold and the initial tendency is calculated to obtain the tendency;

[0124] Step S67. When the comparison result indicates that the horizontal coordinate is not less than the third set threshold, the initial tendency is taken as the tendency;

[0125] Specifically, Figure 3 As shown, the inclination is the angle between the projection of the unit normal vector n = (A, B, C) on the XOY plane and the positive direction of the Y axis. There are many cases depending on the different quadrants of the normal vector projection on the XOY plane. The calculation formula can be simplified as:

[0126]

[0127] Among them, β is the inclination; β0 is the initial inclination; A is the horizontal coordinate of the normal vector of the structural surface.

[0128] The average value of the inclination and dip of all single structural surfaces in each category of structural surfaces is taken as the inclination and dip value of the structural surface of that category to realize the identification and classification of the slope structural surface.

[0129] Embodiment 2:

[0130] like Figure 4 As shown, this embodiment provides a slope structure surface identification device, the device comprising:

[0131] A first acquisition unit 10 is used to acquire a slope image and perform transformation and reconstruction based on the slope image to obtain a three-dimensional point cloud data set;

[0132] A classification unit 20 is used to classify the three-dimensional point cloud data set based on a nearest neighbor search algorithm to obtain a plurality of initial point cloud sets, where the initial point cloud sets are composed of target points and nearest neighbor points;

[0133] A screening unit 30 is used to calculate the curvature value of each target point according to the multiple initial point cloud sets, and perform coplanar screening of the points based on the curvature value to obtain a screened target point cloud set;

[0134] A first obtaining unit 40 is used to perform calculation according to the target point cloud set to obtain a normal vector of each point in the target point cloud set;

[0135] The input unit 50 is used to input the normal vector into the pre-trained neural network model to obtain the structural surface grouping category corresponding to each point in the target point cloud set;

[0136] The first calculation unit 60 is used to perform calculation according to the structural surface grouping category corresponding to each point in the target point cloud set to obtain a target calculation result, wherein the target calculation result includes the inclination and the dip of each structural surface in the structural surface grouping category.

[0137] In a specific embodiment disclosed in the present application, the screening unit 30 includes:

[0138] A second calculation unit is used to perform calculation based on the initial point cloud set to obtain a covariance matrix;

[0139] A decomposition unit, used for performing eigenvalue decomposition based on the covariance matrix to obtain multiple eigenvalues;

[0140] The second obtaining unit is used to calculate the curvature based on the multiple eigenvalues ​​to obtain the curvature value of the target point in the initial point cloud set;

[0141] A first comparison unit is used to compare the curvature value of each target point with a first set threshold value, and select a plurality of basic points whose corresponding curvature values ​​are less than the first set threshold value;

[0142] The constituting unit is used to construct a target point cloud set based on all basic points.

[0143] In a specific embodiment disclosed in the present application, the bringing-in unit 50 includes:

[0144] The second acquisition unit is used to obtain the initial learning rate, initial neighborhood radius, initial weight vector, maximum number of iterations and set number of nodes of the neural network model;

[0145] The third calculation unit is used to calculate the distance between each point in the target point cloud set and each neuron in the neural network model, and determine the target neuron corresponding to the minimum distance;

[0146] A fourth calculation unit, configured to calculate a winning neighborhood based on an initial neighborhood radius and a minimum distance corresponding to a target neuron;

[0147] The third acquisition unit is used for an acquisition operation: obtaining the number of calculations of the winning neighborhood as the number of iterations;

[0148] A first updating unit, configured for a first updating operation: updating the initial learning rate based on the initial learning rate, the number of iterations, and the maximum number of iterations;

[0149] A second updating unit, configured for a second updating operation: updating the initial neighborhood radius based on the initial neighborhood radius, the number of iterations, and the maximum number of iterations;

[0150] A third updating unit, configured for a third updating operation: updating the initial weight vector based on the initial weight vector, the winning neighborhood, the initial weight vector, the initial learning rate, the normal vector, and the initial neighborhood radius;

[0151] A repeating unit is used to repeat the calculation operation, the acquisition operation, the first update operation, the second update operation and the third update operation until the number of iterations is greater than the maximum number of iterations, and to divide all points in the target point cloud set into structural surface classification clusters based on the updated initial weight vector, where the structural surface classification clusters include multiple structural surface clusters;

[0152] An adjustment unit is used to adjust the number of set nodes to obtain a plurality of corresponding structural surface classification clusters, and the number of structural surface clusters in each structural surface classification cluster is different;

[0153] The first determining unit is used to determine an optimal structural surface classification cluster from multiple structural surface classification clusters as a structural surface grouping category.

[0154] In a specific implementation manner disclosed in the present application, the first determining unit includes:

[0155] A third obtaining unit is used to calculate the trace of the covariance matrix of the structural surface cluster based on the structural surface classification cluster to obtain a first value;

[0156] a fourth obtaining unit, used for calculating the trace of the covariance matrix between the structural surface clusters based on the structural surface classification clusters to obtain a second value;

[0157] a fifth calculation unit, configured to calculate a difference between the set number of nodes and a second set threshold value to obtain a third value;

[0158] A sixth calculation unit, used for calculating the difference between the number of points in the target point cloud set and the number of structural surface clusters in the structural surface classification clusters, to obtain a fourth value;

[0159] a seventh calculation unit, configured to calculate a ratio of the second value to the first value to obtain a fifth value;

[0160] an eighth calculation unit, configured to calculate a ratio of the fourth value to the third value to obtain a correction factor;

[0161] a ninth calculation unit, configured to calculate the product of the fifth value and the correction factor to obtain an exponential value;

[0162] A second determining unit is used to determine a maximum value from a plurality of index values ​​corresponding to a plurality of structural surface classification clusters as a target index value;

[0163] The first is used as a unit to take the structural surface classification cluster corresponding to the target index value as the optimal classification cluster, and take the optimal classification cluster as the structural surface grouping category.

[0164] In a specific implementation disclosed in the present application, the first calculation unit 60 includes:

[0165] An extraction unit, used for extracting structural surface grouping categories based on a spatial clustering algorithm to obtain multiple single structural surfaces;

[0166] a tenth calculation unit, used for calculating the normal vector of each single structural surface to obtain a plurality of target normal vectors, wherein the target normal vectors are composed of a horizontal coordinate, a vertical coordinate and a vertical coordinate;

[0167] An eleventh calculation unit is used to calculate the arccosine function value of the vertical coordinate to obtain the inclination angle;

[0168] A twelfth calculation unit, used for performing calculation based on the abscissa and the ordinate to obtain an initial tendency;

[0169] A second comparison unit, used for comparing the horizontal coordinate with a third set threshold value to obtain a comparison result;

[0170] a fifth obtaining unit, configured to calculate a difference between a fourth set threshold and an initial tendency to obtain a tendency when the comparison result indicates that the horizontal coordinate is less than a third set threshold;

[0171] The second as unit is used to take the initial tendency as the tendency when the comparison result indicates that the horizontal coordinate is not less than a third set threshold value.

[0172] In a specific implementation manner disclosed in the present application, the fifth obtaining unit includes:

[0173] A thirteenth calculating unit, used for calculating the sum of the squares of the abscissa and the ordinate to obtain a first result;

[0174] A square root calculation unit, used for performing a square root calculation on the first result to obtain a second result;

[0175] A fourteenth calculation unit, used for calculating the ratio of the ordinate to the second result to obtain a third result;

[0176] The fifteenth calculation unit is used to calculate the arc cosine function value of the third result to obtain an initial tendency.

[0177] It should be noted that, regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0178] Embodiment 3:

[0179] Corresponding to the above method embodiment, this embodiment further provides a slope structure surface identification device. The slope structure surface identification device described below and the slope structure surface identification method described above can refer to each other.

[0180] Figure 5 FIG. 8 is a block diagram of a slope structure surface identification device 800 according to an exemplary embodiment. Figure 5 As shown, the slope structure surface identification device 800 may include: a processor 801 and a memory 802. The slope structure surface identification device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0181] The processor 801 is used to control the overall operation of the slope structure surface recognition device 800 to complete all or part of the steps in the above-mentioned slope structure surface recognition method. The memory 802 is used to store various types of data to support the operation of the slope structure surface recognition device 800, and these data may include, for example, instructions for any application or method operated on the slope structure surface recognition device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the slope structure surface identification device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0182] In an exemplary embodiment, the slope structure surface identification device 800 can be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), digital signal processors (Digital Signal Processor, referred to as DSP), digital signal processing devices (Digital Signal Processing Device, referred to as DSPD), programmable logic devices (Programmable Logic Device, referred to as PLD), field programmable gate arrays (Field Programmable Gate Array, referred to as FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned slope structure surface identification method.

[0183] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned slope structure surface identification method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the slope structure surface identification device 800 to complete the above-mentioned slope structure surface identification method.

[0184] Embodiment 4:

[0185] Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the slope structure surface identification method described above can refer to each other.

[0186] A readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the slope structural surface identification method of the above method embodiment are implemented.

[0187] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0188] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0189] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A slope structural surface identification method, characterized in that: include: Acquire a slope image, and transform and reconstruct the slope image to obtain a three-dimensional point cloud data set; Classifying the three-dimensional point cloud data set based on a nearest neighbor search algorithm to obtain a plurality of initial point cloud sets, wherein the initial point cloud sets are composed of target points and nearest neighbor points; Calculating the curvature value of each target point according to the multiple initial point cloud sets, and performing coplanar screening of the points based on the curvature values ​​to obtain a screened target point cloud set; Calculate according to the target point cloud set to obtain the normal vector of each point in the target point cloud set; Bringing the normal vector into a pre-trained neural network model to obtain the structural surface grouping category corresponding to each point in the target point cloud set; Calculation is performed according to the structural surface grouping category corresponding to each point in the target point cloud set to obtain a target calculation result, wherein the target calculation result includes the inclination and the dip of each structural surface in the structural surface grouping category.

2. The slope structure surface identification method according to claim 1 is characterized in that , the curvature value of each target point is calculated according to multiple initial point cloud sets, and the coplanar screening of points is performed based on the curvature value to obtain the screened target point cloud set, including: Perform calculation based on the initial point cloud set to obtain a covariance matrix; Performing eigenvalue decomposition based on the covariance matrix to obtain multiple eigenvalues; Calculating curvature based on multiple eigenvalues ​​to obtain a curvature value of a target point in the initial point cloud set; Compare the curvature value of each target point with a first set threshold value, and select a plurality of basic points, wherein the curvature values ​​corresponding to the basic points are less than the first set threshold value; The target point cloud set is constructed based on all basic points.

3. The slope structure surface identification method according to claim 1 is characterized in that , bring the normal vector into the pre-trained neural network model to obtain the structural surface grouping category corresponding to each point in the target point cloud set, including: Obtaining an initial learning rate, an initial neighborhood radius, an initial weight vector, a maximum number of iterations, and a set number of nodes of the neural network model; Calculate the distance between each point in the target point cloud and each neuron in the neural network model, and determine the target neuron corresponding to the minimum distance; Calculation operation: based on the initial neighborhood radius and the minimum distance corresponding to the target neuron, calculate the winning neighborhood; Acquisition operation: obtaining the number of calculations of the winning neighborhood as the number of iterations; First update operation: based on the initial learning rate, the number of iterations and the maximum number of iterations, updating the initial learning rate; Second update operation: based on the initial neighborhood radius, the number of iterations and the maximum number of iterations, updating the initial neighborhood radius; A third updating operation: updating the initial weight vector based on the initial weight vector, the superior neighborhood, the initial weight vector, the initial learning rate, the normal vector and the initial neighborhood radius; Repeating the calculation operation, the acquisition operation, the first update operation, the second update operation and the third update operation until the number of iterations is greater than the maximum number of iterations, and dividing all points in the target point cloud set into structural surface classification clusters based on the updated initial weight vector, wherein the structural surface classification clusters include multiple structural surface clusters; Adjusting the set number of nodes to obtain a plurality of corresponding structural surface classification clusters, wherein the number of structural surface clusters in each structural surface classification cluster is different; An optimal structural surface classification cluster is determined from a plurality of structural surface classification clusters as the structural surface grouping category.

4. The slope structure surface identification method according to claim 3 is characterized in that , determining the optimal structural surface classification cluster from multiple structural surface classification clusters as the structural surface grouping category, including: Calculate the trace of the covariance matrix of the structural surface cluster based on the structural surface classification cluster to obtain a first value; Calculate the trace of the covariance matrix between the structural surface clusters based on the structural surface classification clusters to obtain a second value; Calculate the difference between the set number of nodes and the second set threshold to obtain a third value; Calculate the difference between the number of points in the target point cloud set and the number of structural surface clusters in the structural surface classification cluster to obtain a fourth value; Calculate the ratio of the second value to the first value to obtain a fifth value; Calculating a ratio of the fourth value to the third value to obtain a correction factor; Calculating the product of the fifth value and the correction factor to obtain an index value; Determine a maximum value from multiple index values ​​corresponding to multiple structural surface classification clusters as a target index value; The structural surface classification cluster corresponding to the target index value is used as the optimal classification cluster, and the optimal classification cluster is used as the structural surface grouping category.

5. A slope structure surface identification device, characterized in that: include: A first acquisition unit is used to acquire a slope image, and perform transformation and reconstruction based on the slope image to obtain a three-dimensional point cloud data set; A classification unit, used for classifying the three-dimensional point cloud data set based on a nearest neighbor search algorithm to obtain a plurality of initial point cloud sets, wherein the initial point cloud sets are composed of target points and nearest neighbor points; A screening unit, configured to calculate a curvature value of each target point according to a plurality of initial point cloud sets, and perform coplanar screening of the points based on the curvature value to obtain a screened target point cloud set; A first obtaining unit is used to perform calculation according to the target point cloud set to obtain a normal vector of each point in the target point cloud set; An input unit is used to input the normal vector into a pre-trained neural network model to obtain a structural surface grouping category corresponding to each point in the target point cloud set; The first calculation unit is used to perform calculation according to the structural surface grouping category corresponding to each point in the target point cloud set to obtain a target calculation result, wherein the target calculation result includes the inclination and the dip of each structural surface in the structural surface grouping category.

6. The slope structure surface identification device according to claim 5, characterized in that: The screening unit comprises: A second calculation unit, used for performing calculation based on the initial point cloud set to obtain a covariance matrix; A decomposition unit, used for performing eigenvalue decomposition based on the covariance matrix to obtain multiple eigenvalues; A second obtaining unit is used to calculate the curvature based on the multiple eigenvalues ​​to obtain the curvature value of the target point in the initial point cloud set; A first comparison unit, configured to compare the curvature value of each target point with a first set threshold value, and select a plurality of basic points, wherein the curvature values ​​corresponding to the basic points are smaller than the first set threshold value; A construction unit is used to construct the target point cloud set based on all basic points.

7. The slope structure surface identification device according to claim 5, characterized in that: The bringing-in unit comprises: A second acquisition unit is used to acquire an initial learning rate, an initial neighborhood radius, an initial weight vector, a maximum number of iterations, and a set number of nodes of the neural network model; A third calculation unit is used to calculate the distance between each point in the target point cloud set and each neuron in the neural network model, and determine the target neuron corresponding to the minimum distance; A fourth calculation unit, configured to calculate a superior neighborhood based on the initial neighborhood radius and the minimum distance corresponding to the target neuron; A third acquisition unit is used for an acquisition operation: acquiring the number of calculations of the winning neighborhood as the number of iterations; A first updating unit, configured for a first updating operation: updating the initial learning rate based on the initial learning rate, the number of iterations and the maximum number of iterations; A second updating unit, configured for a second updating operation: updating the initial neighborhood radius based on the initial neighborhood radius, the number of iterations, and the maximum number of iterations; A third updating unit, configured for a third updating operation: updating the initial weight vector based on the initial weight vector, the superior neighborhood, the initial weight vector, the initial learning rate, the normal vector, and the initial neighborhood radius; a repeating unit, configured to repeat the calculation operation, the acquisition operation, the first update operation, the second update operation and the third update operation until the number of iterations is greater than the maximum number of iterations, and to divide all points in the target point cloud set into structural surface classification clusters based on the updated initial weight vector, wherein the structural surface classification clusters include a plurality of structural surface clusters; An adjusting unit, used for adjusting the set number of nodes to obtain a plurality of corresponding structural surface classification clusters, wherein the number of structural surface clusters in each structural surface classification cluster is different; The first determining unit is used to determine an optimal structural surface classification cluster from multiple structural surface classification clusters as the structural surface grouping category.

8. The slope structure surface identification device according to claim 7, characterized in that: The determining unit comprises: A third obtaining unit is used to calculate the trace of the covariance matrix of the structural surface cluster based on the structural surface classification cluster to obtain a first value; a fourth obtaining unit, configured to calculate the trace of the covariance matrix between the structural surface clusters based on the structural surface classification clusters to obtain a second value; a fifth calculation unit, configured to calculate a difference between the set number of nodes and a second set threshold value to obtain a third value; A sixth calculation unit, used for calculating the difference between the number of points in the target point cloud set and the number of structural surface clusters in the structural surface classification cluster to obtain a fourth value; a seventh calculation unit, configured to calculate a ratio of the second value to the first value to obtain a fifth value; an eighth calculation unit, configured to calculate a ratio of the fourth value to the third value to obtain a correction factor; a ninth calculation unit, configured to calculate the product of the fifth value and the correction factor to obtain an exponential value; A second determining unit is used to determine a maximum value from a plurality of index values ​​corresponding to a plurality of structural surface classification clusters as a target index value; The first is used as a unit, for taking the structural surface classification cluster corresponding to the target index value as the optimal classification cluster, and taking the optimal classification cluster as the structural surface grouping category.

9. A slope structure surface identification device, characterized in that: include: Memory for storing computer programs; A processor is used to implement the steps of the slope structure surface identification method as described in any one of claims 1 to 4 when executing the computer program.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the slope structure surface identification method according to any one of claims 1 to 4 are implemented.

Images