Geological disaster interpretation method, device, equipment and medium under steep terrain

Abstract

The invention discloses a geological disaster interpretation method, device and equipment under steep terrain and a medium, and relates to the field of remote sensing geological disaster investigation, and the method comprises the steps: obtaining data and radar point cloud data of a target region; extracting a ground point cloud of the target area from the radar point cloud data; performing feature extraction, clustering and point cloud segmentation on the ground point cloud in sequence to determine slope units in the target area; performing rotation transformation on the point clouds in the slope units; classifying and correcting all the converted slope surface units in the target area, and determining abrupt slope point clouds in the target area; and performing three-dimensional visual rendering on the abrupt slope point cloud to obtain an abrupt slope three-dimensional model of the target area, and performing geological disaster interpretation based on the abrupt slope three-dimensional model and the topographic data and geological data in the data to obtain an interpretation result. And the interpretation of geological disasters in steep terrains can be conveniently and efficiently realized.

Description

Technical Field

[0001] The present application relates to the field of remote sensing geological disaster investigation, and in particular to a method, device, equipment and medium for interpreting geological disasters in steep terrain. Background Art

[0002] Geological disasters are widely distributed in mountainous areas with complex terrain. They are characterized by strong suddenness and high concealment, and are a major hidden danger threatening engineering safety. Accurately identifying the scale and development degree of disasters is of great practical significance for disaster management.

[0003] Affected by the undulating terrain and vegetation coverage, it is often difficult to obtain the full picture of high-altitude disasters on steep terrain by relying solely on manpower. Aerial photography technology has overcome this defect to a certain extent, and it can collect images through aerial photography to conduct investigations. However, orthophotos rely on horizontal plane projection, resulting in severe compression of vertical steep slope information. Even if oblique photography is used to restore stereo information, the data is still affected by vegetation coverage, and the true distribution of disasters cannot be ascertained.

[0004] LiDAR technology has the advantages of high geometric accuracy and strong three-dimensional observation capabilities. Through point cloud filtering processing, the influence of vegetation can be removed and the true micro-topography of the target area can be restored. Although LiDAR technology has shown strong technical advantages in geological disaster investigation, its application still faces some challenges. In terms of data processing, the relevant point cloud filtering algorithms are mostly based on the principle of terrain continuity assumption. They are less applicable in areas with sudden changes in terrain such as steep slopes and cliffs. They are easy to identify the corresponding areas as noise points and filter them out, resulting in the loss of key information. In order to overcome this defect, manual correction methods are currently used, but this method is time-consuming and labor-intensive and difficult to meet the needs of batch data processing.

[0005] With the increasing number of engineering construction in mountainous areas, the threat posed by geological disasters on steep slopes is becoming increasingly serious. How to overcome the impact of adverse natural conditions and quickly identify geological disasters that affect engineering safety has become a core issue that needs to be solved urgently. Summary of the invention

[0006] The purpose of this application is to provide a method, device, equipment and medium for interpreting geological hazards in steep terrain, which can conveniently and efficiently realize the interpretation of geological hazards in steep terrain.

[0007] To achieve the above objectives, this application provides the following solutions.

[0008] In a first aspect, the present application provides a method for interpreting geological hazards in steep terrain, comprising the following steps.

[0009] Obtain information data and radar point cloud data of the target area; the information data includes: terrain data, geological data and vegetation data.

[0010] A ground point cloud of the target area is extracted from the radar point cloud data.

[0011] The ground point cloud is subjected to feature extraction, clustering and point cloud segmentation in sequence to determine the slope surface units in the target area; one slope surface unit corresponds to one terrain category; and the terrain category is divided according to slope gradient and slope aspect.

[0012] The point cloud in the slope surface unit is subjected to rotation transformation to obtain a transformed slope surface unit; the normal vector of the transformed slope surface unit coincides with the vertical axis.

[0013] All converted slope surface units in the target area are classified and corrected to determine a steep slope point cloud in the target area; the slope of the steep slope point cloud is greater than a set slope value.

[0014] The steep slope point cloud is rendered in three-dimensional visualization to obtain a three-dimensional model of the steep slope in the target area, and geological disasters are interpreted based on the three-dimensional model of the steep slope, the terrain data and the geological data to obtain an interpretation result; the interpretation result includes: steep slope geological disasters in the target area.

[0015] In a second aspect, the present application provides a device for interpreting geological hazards in steep terrain, comprising the following modules.

[0016] The data acquisition module is used to acquire information data and radar point cloud data of the target area; the information data includes: terrain data, geological data and vegetation data.

[0017] The ground point cloud extraction module is used to extract the ground point cloud of the target area from the radar point cloud data.

[0018] The slope unit determination module is used to perform feature extraction, clustering and point cloud segmentation on the ground point cloud in sequence to determine the slope units in the target area; one slope unit corresponds to one terrain category; the terrain category is divided according to slope gradient and slope direction.

[0019] The point cloud conversion module is used to perform rotational transformation on the point cloud in the slope surface unit to obtain a converted slope surface unit; the normal vector of the converted slope surface unit coincides with the vertical axis.

[0020] The fine classification and correction module is used to classify and correct all converted slope surface units in the target area to determine the steep slope point cloud in the target area; the slope of the steep slope point cloud is greater than the set slope value.

[0021] The geological disaster interpretation module is used to perform three-dimensional visualization rendering on the steep slope point cloud to obtain a three-dimensional model of the steep slope in the target area, and interpret the geological disasters based on the three-dimensional model of the steep slope, the terrain data and the geological data to obtain an interpretation result; the interpretation result includes: steep slope geological disasters in the target area.

[0022] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described methods for interpreting geological hazards in steep terrain.

[0023] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for interpreting geological hazards in steep terrain.

[0024] According to the specific embodiments provided by the present application, the present application has the following technical effects: the present application provides a method, device, equipment and medium for interpreting geological disasters in steep terrain, by extracting the ground point cloud of the target area from the radar point cloud data, performing feature extraction, clustering and point cloud segmentation on the ground point cloud in turn, determining the slope unit in the target area, and determining the steep slope point cloud in the target area by rotationally transforming, classifying and correcting the point cloud in the slope unit, thereby realizing the interpretation of geological disasters. The present application overcomes the problem that the point cloud filtering algorithm has poor applicability in areas with sudden terrain changes (such as steep slopes), which may lead to the loss of key information, and can conveniently and efficiently realize the interpretation of geological disasters in steep terrain. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 This is a diagram of the application environment of a method for interpreting geological hazards in steep terrain in one embodiment of the present application.

[0027] Figure 2 A schematic flow chart of a method for interpreting geological hazards in steep terrain provided in one embodiment of the present application.

[0028] Figure 3 A schematic diagram of a terrain-simulating flight route parallel to contour lines provided in an embodiment of the present application.

[0029] Figure 4A schematic diagram of a vertical contour line flight route provided in an embodiment of the present application.

[0030] Figure 5 A schematic diagram of an orthogonal route provided in one embodiment of the present application.

[0031] Figure 6 A schematic diagram of a slope analysis result provided in one embodiment of the present application.

[0032] Figure 7 A schematic diagram of slope analysis results provided in one embodiment of the present application.

[0033] Figure 8 A schematic diagram of a point cloud segmentation result provided in an embodiment of the present application.

[0034] Fig. 9 A schematic diagram of the slope normal vector extraction and reprojection process provided in one embodiment of the present application.

[0035] Fig.10 A schematic diagram of artificial section review provided in one embodiment of the present application.

[0036] Fig.11 A schematic diagram of a three-dimensional model of a steep slope obtained by three-dimensional visualization rendering provided in an embodiment of the present application.

[0037] Fig.12 A schematic cross-sectional view of a steep slope three-dimensional model after model accuracy evaluation provided in an embodiment of the present application.

[0038] Fig.13 An orthophoto image provided in accordance with an embodiment of the present application.

[0039] Fig.14 A schematic diagram of the landslide interpretation results provided in one embodiment of the present application.

[0040] Fig.15 A structural diagram of a geological disaster interpretation device under steep terrain provided in one embodiment of the present application.

[0041] Fig.16 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0044] The method for interpreting geological hazards in steep terrain provided by the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the data and radar point cloud data of the target area to the server 104. After the server 104 receives the data and radar point cloud data of the target area, the server 104 obtains the data and radar point cloud data of the target area; extracts the ground point cloud of the target area from the radar point cloud data; performs feature extraction, clustering and point cloud segmentation on the ground point cloud in sequence to determine the slope unit in the target area; performs rotation transformation on the point cloud in the slope unit to obtain the converted slope unit; classifies and corrects all the converted slope units in the target area to determine the steep slope point cloud in the target area; performs three-dimensional visualization rendering on the steep slope point cloud to obtain a three-dimensional model of the steep slope in the target area, and interprets geological hazards based on the three-dimensional model of the steep slope, the terrain data and the geological data to obtain an interpretation result.

[0045] The server 104 can feed back the obtained interpretation result to the terminal 102. In addition, in some embodiments, the geological disaster interpretation method under steep terrain can also be implemented by the server 104 or the terminal 102 alone, such as the terminal 102 can directly process the data and radar point cloud data of the target area, or the server 104 can obtain the data and radar point cloud data of the target area from the data storage system, and process the data and radar point cloud data of the target area.

[0046] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0047] In an exemplary embodiment, Figure 2As shown, a method for interpreting geological hazards under steep terrain is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used for explanation, and the steps include the following steps 201 to 206.

[0048] Step 201, obtaining information data and radar point cloud data of the target area; the information data includes: terrain data, geological data and vegetation data.

[0049] Step 202: extracting the ground point cloud of the target area from the radar point cloud data.

[0050] Step 203, performing feature extraction, clustering and point cloud segmentation on the ground point cloud in sequence to determine the slope units in the target area.

[0051] Wherein, one slope unit corresponds to one terrain category; the terrain category is divided according to slope gradient and slope direction.

[0052] Step 204, performing a rotation transformation on the point cloud in the slope surface unit to obtain a transformed slope surface unit; the normal vector of the transformed slope surface unit coincides with the vertical axis.

[0053] Step 205 , classifying and correcting all converted slope surface units in the target area, and determining a steep slope point cloud in the target area; the slope of the steep slope point cloud is greater than a set slope value.

[0054] Step 206, performing three-dimensional visualization rendering on the steep slope point cloud to obtain a three-dimensional model of the steep slope in the target area, and performing geological disaster interpretation based on the three-dimensional model of the steep slope, the terrain data and the geological data to obtain an interpretation result.

[0055] Wherein, the interpretation result includes: steep slope geological hazards in the target area.

[0056] By implementing the above steps 201 to 206, through the segmentation and classification of the steep slope point cloud, the problem of poor applicability of the point cloud filtering algorithm in areas with sudden changes in terrain (such as steep slopes) which may lead to loss of key information is overcome, and the interpretation of geological disasters in steep terrain can be achieved conveniently and efficiently.

[0057] In another exemplary embodiment of the present application, step 201 specifically includes: acquiring a topographic map of the target area to obtain topographic data, acquiring a geological map of the target area to obtain geological data, and acquiring vegetation types and corresponding canopy density of the target area to obtain vegetation data; determining a terrain-simulating flight route of the laser radar according to the vegetation data of the target area; and controlling the laser radar to fly in the target area according to the terrain-simulating flight route to collect radar point cloud data of the target area.

[0058] In practical applications, the topographic map can be an engineering topographic map. In addition, an open source medium-resolution (≤30m) digital elevation model can be used as topographic data. The geological map can exemplarily include information such as stratum lithology and occurrence. The range of canopy density corresponding to vegetation types can be [0, 1].

[0059] In this embodiment, the terrain-mimicking flight route of the laser radar is determined according to the vegetation data of the target area, specifically including: taking different route designs according to the canopy density differences in the vegetation data of the target area to optimize the data collection effect. Specifically, for low vegetation canopy density areas (the canopy density range is [0, 0.2]), a terrain-mimicking flight route with a heading approximately parallel to the contour line (such as Figure 3 In the medium vegetation density area (the density range is (0.2, 0.7]), a terrain-simulating flight route with a heading approximately perpendicular to the contour line is adopted (such as Figure 4 As shown in the figure, data collection is performed to improve the density and accuracy of point cloud data; for areas with high vegetation density (the range of density is (0.7, 1]), two terrain-simulating flight routes are designed, and the two headings are orthogonal to each other (as shown in the figure). Figure 5 as shown) to ensure data integrity and coverage quality in complex environments.

[0060] In another exemplary embodiment of the present application, step 202 specifically includes: denoising the radar point cloud data to obtain denoised point cloud data; and extracting the ground point cloud of the target area from the denoised point cloud data using a progressive TINDensification (PTD) filtering algorithm.

[0061] The denoising process is as follows: by counting the height differences and point densities of points in the local area, the radar point cloud data is denoised. Specifically, based on the set threshold, isolated points and abnormal elevation points in the data are identified and removed to eliminate the influence of abnormal noise on subsequent analysis. For example, a height threshold and a point density threshold are set to remove point clouds with a height greater than the height threshold in the radar point cloud data, and remove point clouds with a point density less than the point density threshold in the radar point cloud data, to obtain denoised point cloud data.

[0062] In this embodiment, the recommended values ​​of main parameters of the progressively encrypted triangulated network filtering algorithm are shown in Table 1.

[0063] Table 1 Selection of point cloud filtering parameters under different terrain conditions

[0064] The ground point cloud of the target area is extracted from the denoised point cloud data using a progressively encrypted triangulated network filtering algorithm, specifically including: selecting initial ground points from the denoised point cloud data to establish a triangulated network using a progressively encrypted triangulated network filtering algorithm, gradually encrypting and screening out points that meet ground features, and gradually relaxing the elevation threshold to adapt to complex terrain. In each round of iteration, the ground points are updated and the triangulated network is encrypted, and finally the ground point cloud is extracted.

[0065] In another exemplary embodiment of the present application, step 203 specifically includes: constructing terrain grid data by interpolation according to the ground point cloud; extracting features from each pixel in the terrain grid data to obtain feature values ​​of each pixel; the feature values ​​include: slope and aspect; clustering the feature values ​​of all pixels to obtain clustering results; segmenting the ground point cloud according to the clustering results and the continuity of the slope and aspect to obtain the slope surface units in the target area. The slope analysis result is as follows: Figure 6 The slope analysis results are shown in Figure 7 shown. Figure 6 It shows the classification of the slope (0-90°) of the target area, and different depths correspond to different terrain slope intervals, describing the degree of terrain undulation; Figure 7 The classification of the slope aspect (0-360°) of the target area is shown, and different depths correspond to different slope aspect intervals, where 0° is due north.

[0066] Specifically, according to the ground point cloud, the terrain grid data is constructed by interpolation, the slope and aspect of each pixel in the terrain grid data are calculated, and cluster analysis is performed based on the calculated characteristic values. According to the results of digital terrain analysis, the slope and aspect are divided into different intervals and combined to form terrain categories, as shown in Table 2, so as to ensure that the pixel units in each category have similar terrain characteristics, thereby improving the accuracy and reliability of automatic extraction of ground points. Among them, the slope is divided into three intervals, namely [0, 28), [28, 45) and [45, 90). The aspect is divided into three intervals, namely [0, 115), [115, 180) and [180, 360). The ground target area is divided into 9 categories based on the two. When the ground pixel meets the requirements of a certain category in Table 2, the digital quantization (Digital Number, DN) value of the pixel is assigned to the corresponding category value (for example, category 1, DN value is 1), and the entire target area is traversed in turn to obtain the terrain category division grid Terrain. The Terrain is processed by morphological filtering with an open operation using a 3×3 structural element to eliminate noise points and connect isolated units. Finally, the result is vectorized and each independent slope unit is extracted based on the vector range. The point cloud segmentation result is shown in the figure below. Figure 8 As shown, Figure 8 Category 1, category 3, category 5, and category 8 corresponding to Table 2 are shown.

[0067] Table 2 Terrain classification (unit: °)

[0068] In another exemplary embodiment of the present application, step 204 specifically includes the following steps.

[0069] (1) Performing plane fitting analysis on the point cloud in the slope unit using the least squares method to calculate the normal vector of the optimal fitting plane; the optimal fitting plane is the fitting plane corresponding to the minimum sum of square errors.

[0070] Specifically, let the plane equation be z = a 0 x+a 1 y+a 2, ( x,y,z ) represents the coordinates of a point on a plane. Select n Point, i The spatial coordinates of a point are expressed as ( x i ,y i ,z i ), i =1,2,…, n , n≥3. According to the principle of least squares method, the sum of squares of errors is calculated by calculating the partial derivative to be zero Minimum, and find the plane equation parameters a 0, a 1, a 2.

[0071] A simple transformation of the plane equation makes a 0 x+a 1 y-z+a 2=0, then the normal vector of the optimal fitting plane N =( a 0, a 1, -1).

[0072] (2) According to the angle between the normal vector of the optimal fitting plane and the vertical axis θ The rotation angle and rotation direction required for the point cloud are calculated; and the point cloud in the slope unit is rotationally transformed according to the rotation angle and the rotation direction to obtain a transformed slope unit.

[0073] Specifically, according to Calculate the required rotation angle of the point cloud. Z =(0,0,1) is the vector in the positive direction of the vertical axis, , .

[0074] Calculate the plane NoZ The equation is recorded as a 1 x - a 0 y = 0. With the origin o Centered on NoZ The normal vector of the best fitting plane in the plane N According to the rotation angle θ Rotate to Z The positive direction of the axis coincides, so the point cloud of the slope unit is reprojected to the horizontal plane.

[0075] The slope normal vector extraction and reprojection process is as follows Fig. 9 shown. Fig. 9 Part (a) shows the original radar point cloud data, Fig. 9 Part (b) shows the normal vector, Fig. 9 Part (c) shows the point cloud in the converted slope surface unit.

[0076] In another exemplary embodiment of the present application, step 205 specifically includes: using a progressively encrypted triangulated network filtering algorithm to classify all converted slope surface units in the target area to obtain classification results; using artificial profiles to correct the classification results, and determining the steep slope point cloud in the target area based on the corrected classification results.

[0077] Specifically, the point cloud of all converted slope units in the target area is processed using a progressive encryption triangulation filtering algorithm, and encryption is performed based on key ground points to ensure that micro-relief features are accurately identified and classification results are obtained. Subsequently, combined with manual profile review, the classification results are corrected and optimized, misclassifications are eliminated, and missed ground points are retrieved to ensure the accuracy and completeness of ground point classification. Fig.10 As shown in the figure, through manual profile review, missed ground points can be recalled and misclassified vegetation points can be eliminated. Fig.10 Region I in the figure shows the missed classification area. The missed classification is mainly caused by the sudden change of terrain undulation, which leads to the missing of ground points in local raised or sunken areas. These points need to be manually added to the ground point category. Fig.10 Region II in the figure shows the misclassified area. Misclassification usually occurs in areas with dense vegetation. Especially when the ground points are sparse, the algorithm may mistake the upper vegetation for ground points. Therefore, manual adjustment is required to ensure accurate classification.

[0078] In another exemplary embodiment of the present application, step 206 specifically includes: constructing a digital elevation model by interpolation based on the steep slope point cloud; performing three-dimensional visualization rendering on the digital elevation model to obtain a three-dimensional model of the steep slope in the target area; establishing a three-dimensional electronic sand table based on the steep slope three-dimensional model, the terrain data and the geological data; interpreting geological disasters based on the three-dimensional electronic sand table and geological disaster remote sensing interpretation signs to obtain interpretation results.

[0079] Specifically, the 3D visualization rendering and model accuracy evaluation process is as follows: interpolate the steep slope point cloud data to construct a digital elevation model, perform 3D visualization rendering on the digital elevation model, and establish a steep slope 3D model. Using the original radar point cloud data as the standard, randomly select no less than 20 verification points within the data range, and use the root mean square error (RMSE) method to evaluate the 3D accuracy of the steep slope 3D model. x Taking direction as an example, x Root mean square error of direction The calculation method is shown in the following formula.

[0080] .

[0081] In the formula, mTo verify the points, For verification point j The horizontal coordinate of the steep slope three-dimensional model, For verification point j The horizontal coordinate of the laser point at the corresponding position. x Root mean square error of direction , y Root mean square error of direction and z Root mean square error of direction When the error is less than the index in Table 3, the 3D model of the steep slope can be used for subsequent interpretation. If it does not meet the requirements, the area with large error is manually corrected. The 3D model of the steep slope obtained by 3D visualization rendering is shown in Figure 3. Fig.11 As shown in Figure 2, the cross section of the steep slope 3D model after model accuracy evaluation is as follows: Fig.12 shown.

[0082] Fig.12 The figure shows the model accuracy check process. The area indicated by the arrow is affected by factors such as terrain undulation and improper selection of point cloud classification parameters. The algorithm mistakenly classifies non-ground points such as vegetation as ground points, which in turn affects the terrain accuracy and causes the model to be abnormally convex. Fig.12 The real ground points and the abnormal raised areas of the model are displayed. After measurement, the model elevation error reaches 0.35m, which exceeds the threshold (that is, the accuracy exceeds the limit), and point cloud classification and modeling need to be re-performed.

[0083] Table 3 Model accuracy evaluation error requirements (unit: m)

[0084] The geological disaster interpretation process is as follows: a three-dimensional electronic sand table is established based on the three-dimensional model of the steep slope, the terrain data and the geological data, and identification is carried out in combination with the geological disaster remote sensing interpretation signs to achieve geological disaster interpretation. Among them, the interpretation results can also include: long joints and fissures on steep slopes, dangerous rocks on probes, back walls of landslides, water collection channels and other information to provide data support for risk assessment. The effect of geological disaster interpretation is as follows Fig.13 and Fig.14 As shown. Fig.13 The orthophoto map is shown. Fig.14 The interpretation results of the landslide body are shown.

[0085] The embodiment of the present application obtains data and radar point cloud data of the target area, performs preliminary classification of the radar point cloud data to obtain rough terrain, segments the terrain to extract slope units, and performs further refined classification and correction after rotational transformation of the point cloud in the slope unit to obtain steep slope point cloud, thereby realizing geological disaster interpretation. The embodiment of the present application comprehensively considers terrain undulation and vegetation coverage conditions, and overcomes the problem of poor applicability of the point cloud filtering algorithm in areas with sudden changes in terrain by establishing a route design method that adapts to different vegetation density, as well as a steep slope point cloud segmentation and classification method, thereby restoring the true landform under the vegetation and providing a convenient and efficient technical means for geological disaster investigation in areas with complex terrain.

[0086] Based on the same inventive concept, the embodiment of the present application also provides a device for interpreting geological hazards under steep terrain for implementing the above-mentioned method for interpreting geological hazards under steep terrain. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the device for interpreting geological hazards under steep terrain provided below can refer to the limitations of the method for interpreting geological hazards under steep terrain above, and will not be repeated here.

[0087] In an exemplary embodiment, Fig.15 As shown, a device for interpreting geological hazards in steep terrain is provided, which includes the following modules.

[0088] The data acquisition module 301 is used to acquire information data and radar point cloud data of the target area; the information data includes: terrain data, geological data and vegetation data.

[0089] The ground point cloud extraction module 302 is used to extract the ground point cloud of the target area from the radar point cloud data.

[0090] The slope unit determination module 303 is used to perform feature extraction, clustering and point cloud segmentation on the ground point cloud in sequence to determine the slope units in the target area; one slope unit corresponds to one terrain category; the terrain category is divided according to slope gradient and slope aspect.

[0091] The point cloud conversion module 304 is used to perform rotational transformation on the point cloud in the slope surface unit to obtain a converted slope surface unit; the normal vector of the converted slope surface unit coincides with the vertical axis.

[0092] The fine classification and correction module 305 is used to classify and correct all converted slope surface units in the target area to determine the steep slope point cloud in the target area; the slope of the steep slope point cloud is greater than the set slope value.

[0093] The geological disaster interpretation module 306 is used to perform three-dimensional visualization rendering on the steep slope point cloud to obtain a three-dimensional model of the steep slope in the target area, and interpret the geological disasters based on the three-dimensional model of the steep slope, the terrain data and the geological data to obtain an interpretation result; the interpretation result includes: steep slope geological disasters in the target area.

[0094] The method and device for interpreting geological hazards under steep terrain in the above-mentioned embodiment mainly include the following aspects: obtaining data and radar point cloud data of the target area; preliminary classification of point clouds and terrain construction; extraction of slope units and segmentation of point clouds; three-dimensional terrain visualization and geological hazard interpretation. This application comprehensively considers natural conditions such as terrain undulation and vegetation coverage, and effectively solves the problem of poor applicability of point cloud filtering algorithms in areas with sudden changes in terrain such as steep slopes and cliffs by establishing route design, slope unit extraction and point cloud segmentation methods, providing an efficient and convenient technical means for restoring the true landform of high and steep slopes and investigating hidden geological hazards.

[0095] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Fig.16 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store information data and radar point cloud data of the target area. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for interpreting geological hazards under steep terrain is implemented.

[0096] Those skilled in the art will understand that Fig.16 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0097] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0098] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0099] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0100] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0101] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, etc., but is not limited thereto.

[0102] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0103] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for interpreting geological hazards in steep terrain, characterized in that: The method for interpreting geological hazards under steep terrain includes: Acquire data and radar point cloud data of the target area; the data includes: terrain data, geological data and vegetation data; Extracting a ground point cloud of the target area from the radar point cloud data; Performing feature extraction, clustering and point cloud segmentation on the ground point cloud in sequence to determine the slope surface unit in the target area; one slope surface unit corresponds to one terrain category; the terrain category is divided according to slope gradient and slope aspect; Performing a rotation transformation on the point cloud in the slope surface unit to obtain a transformed slope surface unit; the normal vector of the transformed slope surface unit coincides with the vertical axis; Classifying and correcting all converted slope surface units in the target area to determine a steep slope point cloud in the target area; the slope of the steep slope point cloud is greater than a set slope value; The steep slope point cloud is rendered in three-dimensional visualization to obtain a three-dimensional model of the steep slope in the target area, and geological disasters are interpreted based on the three-dimensional model of the steep slope, the terrain data and the geological data to obtain an interpretation result; the interpretation result includes: steep slope geological disasters in the target area.

2. The method for interpreting geological hazards in steep terrain according to claim 1, characterized in that: Obtain the data and radar point cloud data of the target area, including: Obtaining a topographic map of the target area to obtain topographic data, obtaining a geological map of the target area to obtain geological data, and obtaining vegetation types and corresponding canopy density of the target area to obtain vegetation data; Determine the terrain-mimicking flight route of the laser radar based on vegetation data of the target area; The laser radar is controlled to fly in the target area according to the terrain-simulating flight route to collect radar point cloud data of the target area.

3. The method for interpreting geological hazards in steep terrain according to claim 1, characterized in that: Extracting the ground point cloud of the target area from the radar point cloud data specifically includes: Performing denoising processing on the radar point cloud data to obtain denoised point cloud data; A progressively encrypted triangulated network filtering algorithm is used to extract the ground point cloud of the target area from the denoised point cloud data.

4. The method for interpreting geological hazards in steep terrain according to claim 1, characterized in that: The ground point cloud is sequentially subjected to feature extraction, clustering and point cloud segmentation to determine the slope surface units in the target area, specifically including: According to the ground point cloud, terrain raster data is constructed by interpolation; Extracting features from each pixel in the terrain grid data to obtain feature values ​​of each pixel; the feature values ​​include: slope and slope direction; Cluster the characteristic values ​​of all pixels to obtain the clustering results; The ground point cloud is segmented according to the clustering result and the continuity of the slope and the slope aspect to obtain the slope surface units in the target area.

5. The method for interpreting geological hazards in steep terrain according to claim 1, characterized in that: The point cloud in the slope unit is subjected to a rotation transformation to obtain a transformed slope unit, specifically comprising: The point cloud in the slope unit is analyzed by plane fitting using the least square method to calculate the normal vector of the optimal fitting plane; the optimal fitting plane is the fitting plane corresponding to the minimum sum of square errors; Calculate the required rotation angle and rotation direction of the point cloud according to the angle between the normal vector of the best fitting plane and the vertical axis; The point cloud in the slope surface unit is rotationally transformed according to the rotation angle and the rotation direction to obtain a transformed slope surface unit.

6. The method for interpreting geological hazards in steep terrain according to claim 1, characterized in that: Classifying and correcting all converted slope surface units in the target area to determine the steep slope point cloud in the target area specifically includes: Using a progressively encrypted triangulated network filtering algorithm to classify all converted slope surface units in the target area, and obtaining a classification result; The classification result is corrected by using an artificial profile, and the steep slope point cloud in the target area is determined according to the corrected classification result.

7. The method for interpreting geological hazards in steep terrain according to claim 1, characterized in that: Performing three-dimensional visualization rendering on the steep slope point cloud to obtain a three-dimensional model of the steep slope in the target area, and interpreting geological hazards based on the three-dimensional model of the steep slope, the terrain data and the geological data to obtain an interpretation result, specifically including: According to the steep slope point cloud, a digital elevation model is constructed by interpolation; Performing three-dimensional visual rendering on the digital elevation model to obtain a three-dimensional model of the steep slope in the target area; Establishing a three-dimensional electronic sand table according to the three-dimensional model of the steep slope, the terrain data and the geological data; The geological disaster interpretation is performed according to the three-dimensional electronic sand table and the geological disaster remote sensing interpretation marks to obtain the interpretation results.

8. A geological disaster interpretation device under steep terrain, characterized in that: The device for interpreting geological hazards under steep terrain comprises: A data acquisition module is used to acquire information data and radar point cloud data of the target area; the information data includes: terrain data, geological data and vegetation data; A ground point cloud extraction module, used to extract the ground point cloud of the target area from the radar point cloud data; A slope unit determination module is used to perform feature extraction, clustering and point cloud segmentation on the ground point cloud in sequence to determine the slope units in the target area; one slope unit corresponds to one terrain category; the terrain category is divided according to slope gradient and slope aspect; A point cloud conversion module, used for performing rotational transformation on the point cloud in the slope surface unit to obtain a converted slope surface unit; the normal vector of the converted slope surface unit coincides with the vertical axis; A fine classification and correction module, used for classifying and correcting all converted slope surface units in the target area, and determining a steep slope point cloud in the target area; the slope of the steep slope point cloud is greater than a set slope value; The geological disaster interpretation module is used to perform three-dimensional visualization rendering on the steep slope point cloud to obtain a three-dimensional model of the steep slope in the target area, and interpret the geological disasters based on the three-dimensional model of the steep slope, the terrain data and the geological data to obtain an interpretation result; the interpretation result includes: steep slope geological disasters in the target area.

9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for interpreting geological hazards in steep terrain as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for interpreting geological hazards in steep terrain described in any one of claims 1 to 7 is implemented.

Images