Multi-source data fusion-based three-dimensional modeling method and system for slope in hard mountainous area

Abstract

The invention relates to the technical field of three-dimensional modeling, in particular to a hard mountainous area slope three-dimensional modeling method and system based on multi-source data fusion. The method comprises the following steps: performing multi-angle acquisition on a mountain slope by using an unmanned aerial vehicle cluster to obtain slope multi-angle image data; performing ground laser scanning on the mountain slope to obtain a slope point cloud data set; carrying out seismic reflection wave detection on the mountainous area slope to obtain slope seismic reflection data; carrying out electromagnetic chromatography detection on the mountain slope to obtain slope electromagnetic chromatography data; carrying out fusion and inversion on the slope seismic reflection data and the slope electromagnetic tomography data to obtain slope internal structure data; performing coarse registration on the slope multi-angle image data and the slope point cloud data set to obtain initial image-point cloud registration data; according to the invention, fine reconstruction of the complete slope three-dimensional model can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of three-dimensional modeling, and in particular to a three-dimensional modeling method and system for slopes in difficult mountainous areas based on multi-source data fusion. Background Art

[0002] Traditional slope modeling methods mainly rely on ground surveying and geological exploration. These methods have certain advantages in flat or easily accessible areas, but face many challenges in rugged mountainous areas. First, the terrain in rugged mountainous areas is complex, with cliffs and gullies, and it is difficult for traditional ground surveying equipment to enter these areas for data collection. For example, in some high-altitude mountainous areas, due to the steep terrain and harsh climate, the entry of surveying personnel and equipment is greatly restricted, which not only increases the difficulty and cost of measurement, but also in some cases, it is even impossible to obtain complete terrain data. In addition, the complexity of geological conditions also brings difficulties to modeling. The geological structure in rugged mountainous areas is diverse, the rock layers are broken, and faults are developed. Traditional geological exploration methods are difficult to accurately capture these complex geological features. For example, in some areas where geological disasters occur frequently, the geological structure below the surface is complex and changeable, and traditional exploration methods are difficult to fully reveal these structures, thus affecting the accuracy and reliability of slope modeling. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a three-dimensional modeling method and system for slopes in difficult mountainous areas based on multi-source data fusion to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above purpose, a 3D modeling method for slopes in difficult mountainous areas based on multi-source data fusion includes the following steps:

[0005] Step S1: Use a drone cluster to collect multi-angle data of the mountain slope to obtain multi-angle image data of the slope; perform ground laser scanning on the mountain slope to obtain a slope point cloud data set;

[0006] Step S2: Perform seismic reflection wave detection on the mountain slope to obtain seismic reflection data of the slope; perform electromagnetic tomography detection on the mountain slope to obtain electromagnetic tomography data of the slope; fuse and invert the seismic reflection data of the slope with the electromagnetic tomography data of the slope to obtain the internal structure data of the slope;

[0007] Step S3: Coarsely align the multi-angle image data of the slope with the point cloud data set of the slope to obtain initial image-point cloud registration data; perform tensor field interpolation fine alignment on the initial image-point cloud registration data to obtain image-point cloud registration data; perform spatial unified transformation on the image-point cloud registration data and the internal structure data of the slope to obtain unified slope image-point cloud data;

[0008] Step S4: performing improved watershed segmentation on the slope image-point cloud unified data to obtain slope unit division data; performing structural surface recognition on the slope unit division data to obtain slope structural surface feature data; performing feature extraction on the slope structural surface feature data and the slope internal structure data to obtain slope hierarchical feature data;

[0009] Step S5: Layer the slope hierarchical feature data to obtain slope layered data; reconstruct the surface of the slope layered data to obtain a slope spatial surface model; and reconstruct the mountain slope in three dimensions based on the slope spatial surface model to obtain a complete slope three-dimensional model.

[0010] The present invention can quickly obtain multi-angle image data of slopes in difficult mountainous areas through multi-angle acquisition of drone clusters, without the need for manual entry into dangerous areas, reducing the safety risks of personnel and equipment, while expanding the scope of data acquisition and ensuring the comprehensiveness and integrity of the data. The three-dimensional point cloud data set of the slope can be accurately obtained through ground laser scanning, which makes up for the deficiency of traditional ground measurement in obtaining complete data in complex terrain. Seismic reflection wave detection can effectively identify geological structures such as stratum interfaces and faults, while electromagnetic tomography detection can reveal the conductivity distribution inside the slope. After the data fusion and inversion of the two, the internal structure data of the slope can be obtained more accurately, overcoming the problem that traditional geological exploration methods are difficult to accurately capture geological features under complex geological conditions. After rough registration, the tensor field interpolation fine registration method is used to further improve the registration accuracy of the image and point cloud data and ensure the consistency of the data in space. The improved watershed segmentation method can more accurately divide the slope unit, avoiding the problem of over-segmentation or under-segmentation that is prone to occur in traditional watershed algorithms in complex terrain. Through structural surface recognition and feature extraction, the structural surface feature data of the slope can be effectively extracted and fused with the internal structural data to obtain the hierarchical feature data of the slope. Through the hierarchical processing and surface reconstruction of the hierarchical feature data of the slope, the spatial surface model of the slope can be obtained. On this basis, combined with the reconstruction process of the middle and deep layers, the fine reconstruction of the complete three-dimensional model of the slope is finally achieved. This model can not only accurately reflect the external morphology and internal structure of the slope, but also reveal the hierarchical characteristics and geological details of the slope. Compared with traditional modeling methods, it has higher accuracy and reliability.

[0011] Preferably, the present invention further provides a three-dimensional modeling system for slopes in difficult mountainous areas based on multi-source data fusion, which is used to execute the three-dimensional modeling method for slopes in difficult mountainous areas based on multi-source data fusion as described above. The three-dimensional modeling system for slopes in difficult mountainous areas based on multi-source data fusion comprises:

[0012] The data acquisition module is used to use a drone cluster to collect data from multiple angles on the mountain slopes to obtain multi-angle image data of the slopes; perform ground laser scanning on the mountain slopes to obtain a slope point cloud data set;

[0013] The structural detection module is used to detect seismic reflection waves on mountain slopes to obtain seismic reflection data of the slopes; to detect electromagnetic tomography on mountain slopes to obtain electromagnetic tomography data of the slopes; to fuse and invert the seismic reflection data of the slopes with the electromagnetic tomography data of the slopes to obtain the internal structure data of the slopes;

[0014] The data registration and unification module is used to roughly register the multi-angle image data of the slope with the slope point cloud data set to obtain the initial image-point cloud registration data; perform tensor field interpolation fine registration on the initial image-point cloud registration data to obtain the image-point cloud registration data; perform spatial unified transformation on the image-point cloud registration data and the internal structure data of the slope to obtain the slope image-point cloud unified data;

[0015] The segmentation module is used to perform improved watershed segmentation on the unified data of slope image and point cloud to obtain slope unit division data; perform structural surface recognition on the slope unit division data to obtain slope structural surface feature data; perform feature extraction on the slope structural surface feature data and the slope internal structure data to obtain slope hierarchical feature data;

[0016] The three-dimensional reconstruction module is used to stratify the hierarchical characteristic data of the slope to obtain the slope stratification data; to reconstruct the surface of the slope stratification data to obtain the slope spatial surface model; to reconstruct the mountain slope in three dimensions based on the slope spatial surface model to obtain a complete slope three-dimensional model.

[0017] In the present invention, the data acquisition module can automatically and efficiently obtain multi-angle image data and point cloud data sets of the slopes in the difficult mountainous areas through the coordinated work of the drone cluster and the ground laser scanning equipment, reducing the labor intensity and time cost of manual collection, and improving the accuracy and consistency of data collection. Through the structural detection module combined with seismic reflection wave detection and electromagnetic tomography detection technology, the geological structure inside the slope can be fully and accurately detected, and the fused and inverted data can more truly reflect the geological characteristics inside the slope. Through the data registration and unification module, the method of combining coarse registration and tensor field interpolation fine registration can be used to efficiently and accurately realize the spatial registration of image and point cloud data, and perform spatial unified transformation with internal structure data, ensuring the quality and consistency of data fusion. Through the segmentation module, the improved watershed segmentation algorithm and structural surface recognition can be used to intelligently divide the slope units and extract the structural surface feature data, improving the accuracy and efficiency of feature extraction. The three-dimensional reconstruction module can automatically realize the fine reconstruction of the three-dimensional model of the slope through the hierarchical processing and surface reconstruction of the hierarchical feature data. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Other features, objects and advantages of the present invention will become more apparent from the detailed description made with reference to the following drawings:

[0019] Figure 1 A schematic flow chart of the steps of a method for three-dimensional modeling of slopes in difficult mountainous areas based on multi-source data fusion according to an embodiment is shown.

[0020] Figure 2 A detailed flow chart of step S26 of an embodiment is shown.

[0021] Figure 3 A detailed flow chart of step S5 of an embodiment is shown. DETAILED DESCRIPTION

[0022] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0023] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0024] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0025] To achieve this, please refer to Figures 1 to 3 The present invention provides a three-dimensional modeling method for slopes in difficult mountainous areas based on multi-source data fusion, comprising the following steps:

[0026] Step S1: Use a drone cluster to collect multi-angle data of the mountain slope to obtain multi-angle image data of the slope; perform ground laser scanning on the mountain slope to obtain a slope point cloud data set;

[0027] Step S2: Perform seismic reflection wave detection on the mountain slope to obtain seismic reflection data of the slope; perform electromagnetic tomography detection on the mountain slope to obtain electromagnetic tomography data of the slope; fuse and invert the seismic reflection data of the slope with the electromagnetic tomography data of the slope to obtain the internal structure data of the slope;

[0028] Step S3: Coarsely align the multi-angle image data of the slope with the point cloud data set of the slope to obtain initial image-point cloud registration data; perform tensor field interpolation fine alignment on the initial image-point cloud registration data to obtain image-point cloud registration data; perform spatial unified transformation on the image-point cloud registration data and the internal structure data of the slope to obtain unified slope image-point cloud data;

[0029] Step S4: performing improved watershed segmentation on the slope image-point cloud unified data to obtain slope unit division data; performing structural surface recognition on the slope unit division data to obtain slope structural surface feature data; performing feature extraction on the slope structural surface feature data and the slope internal structure data to obtain slope hierarchical feature data;

[0030] Step S5: Layer the slope hierarchical feature data to obtain slope layered data; reconstruct the surface of the slope layered data to obtain a slope spatial surface model; and reconstruct the mountain slope in three dimensions based on the slope spatial surface model to obtain a complete slope three-dimensional model.

[0031] In this embodiment, a high-resolution RGB camera is used to carry out multi-angle image acquisition of the mountain slope by using a drone cluster to obtain multi-angle image data of the slope. Then, a ground laser scanner is used to scan the slope to generate a slope point cloud data set. At the same time, a seismic reflection wave detection device is used to detect the slope to obtain seismic reflection data of the slope; and an electromagnetic tomography detection device is used to detect the slope to obtain electromagnetic tomography data of the slope. Through data processing software, such as GeoStudio, the seismic reflection data and the electromagnetic tomography data are fused and inverted to obtain the internal structure data of the slope. OpenCV software is used to roughly align the multi-angle image data of the slope with the slope point cloud data set to obtain initial image-point cloud registration data. Then, the tensor field interpolation method in MATLAB is used to precisely align the initial image-point cloud registration data to obtain image-point cloud registration data. Then, the image-point cloud registration data and the internal structure data of the slope are spatially unified transformed by Leica Geo Office software to obtain slope image-point cloud unified data. The improved watershed algorithm in MATLAB was used to segment the unified data of slope image and point cloud to obtain the slope unit division data. Then, the CloudCompare software was used to identify the structural surface of the slope unit division data to obtain the slope structural surface feature data. The feature extraction algorithm in MATLAB was used to extract the feature of the slope structural surface feature data and the slope internal structure data to obtain the slope hierarchical feature data. The MeshLab software was used to perform layered processing on the slope hierarchical feature data to obtain the slope layered data. Then, the surface of the slope layered data was reconstructed to obtain the slope spatial surface model. Finally, based on the slope spatial surface model, the SolidWorks software was used to perform three-dimensional reconstruction of the mountain slope to obtain a complete three-dimensional model of the slope.

[0032] Preferably, step S1 comprises the following steps:

[0033] Step S11: collecting a side panoramic image of the mountain slope to obtain a side panoramic image of the slope, and performing regional mission planning for the drone cluster based on the side panoramic image of the slope to obtain a drone flight mission;

[0034] Specifically, a drone with a high-resolution camera can be selected. The drone is equipped with a 360-degree panoramic camera, which can capture the entire slope at one time. Before the flight, the flight parameters of the drone are set according to the terrain characteristics of the slope and the expected flight altitude, including a flight speed of 5 meters per second and a flight altitude of 100 meters. During the flight, the drone flies in a spiral along the side of the slope and takes a panoramic photo every 5 meters. In this way, a panoramic view of the side of the slope can be obtained. Using image processing software, multiple panoramic photos taken are stitched and corrected to generate a complete panoramic view of the side of the slope. Based on this panoramic view, the drone cluster is tasked in different regions. For example, the slope is divided into three regions, each of which is roughly equal in area, and different numbers of drones and flight tasks are assigned according to the complexity of the terrain and data collection requirements of each region. For example, in areas with steeper terrain, two drones are assigned for high-density image acquisition, while in areas with relatively flat terrain, one drone is assigned for conventional image acquisition.

[0035] Step S12: assigning routes to the drone cluster based on the drone flight mission to obtain drone route planning data;

[0036] Specifically, the route of the drone cluster can be planned according to the panoramic view of the side of the slope and the flight mission of the drone. Use the drone route planning software, which can automatically generate the optimal flight route according to the terrain data and flight mission requirements. In the software, the terrain data of the slope and the flight mission parameters of each area, such as flight altitude, flight speed and shooting interval, are input. Based on these parameters, the software generates a detailed route for each drone. For example, in areas with steep terrain, the route is designed to fly along the contour line. In areas with flat terrain, the route is designed to fly in a straight line. In addition, the battery life and flight safety factors of the drone can be considered, and multiple temporary landing points and emergency avoidance areas can be set in the route. For example, in the middle area of ​​the slope, a temporary landing point is set so that the drone can land and replace the battery in time when the battery is low. In the edge area of ​​the slope, an emergency avoidance area is set to cope with sudden wind changes or other flight obstacles. Through the above steps, the drone route planning data can be obtained.

[0037] Step S13: Performing an aerial laser rangefinder scan on the side of the mountain slope to obtain slope characteristic data;

[0038] Specifically, a UAV equipped with a laser radar system can be used for aerial laser ranging scanning. The UAV is equipped with a laser radar with a measurement range of 100 meters, an accuracy of 0.02 meters, and a high-capacity battery. Before the flight, the flight parameters of the UAV are set according to the terrain characteristics of the slope, including a flight speed of 8 meters per second and a flight altitude of 150 meters. The UAV flies parallel to the side of the slope and performs a laser scan every 10 meters horizontal distance to obtain the elevation data of the slope surface. During the scanning process, the laser radar emits laser pulses at a frequency of 1,000 times per second, measures the time from the laser emission to the return, and calculates the elevation value of each point on the slope surface. After the scanning is completed, the acquired laser ranging data is imported into a professional geographic information system (GIS) software, and the software generates a three-dimensional point cloud model of the slope based on these data and calculates the slope value of each point. For example, in the steep area of ​​the slope, the slope value can reach more than 65 degrees, while in the gentle area of ​​the slope, the slope value is less than 15 degrees. Through the above steps, the slope characteristic data can be obtained.

[0039] Step S14: highly stratify the UAV route planning data according to the slope characteristic data to obtain UAV stratified acquisition data;

[0040] Specifically, the slope characteristic data can be imported into the route planning software, and the software divides the slope into different height levels according to the slope value. Specifically, the area with a slope of 0-25 degrees is divided into a low altitude level, and the flight altitude is set to 80 meters; the area with a slope of 25-50 degrees is divided into a medium altitude level, and the flight altitude is set to 120 meters; the area with a slope of 50-70 degrees is divided into a high altitude level, and the flight altitude is set to 160 meters. In each altitude level, the route of the drone is further refined according to the terrain characteristics and data collection requirements. For example, in the flat area of ​​the low altitude level, the route is designed to fly in a straight line, the drone flies at a speed of 6 meters per second, and takes a photo every 10 meters; in the medium slope area of ​​the medium altitude level, the route is designed to fly along the contour line, the drone flies at a speed of 7 meters per second, and takes a photo every 12 meters; in the steep area of ​​the high altitude level, the route is designed to fly along the slope line, the drone flies at a speed of 5 meters per second, and takes a photo every 8 meters. Through the above steps, the UAV layered collection data can be obtained.

[0041] Step S15: using a drone cluster to collect multi-angle data on the mountain slope according to the layered data collected by the drone, and obtaining multi-angle image data of the slope;

[0042] Specifically, the slope can be collected from multiple angles using drone clusters according to the layered data collection of drones. The slope is divided into three height levels according to the layered data collection: low level (0-50 meters), middle level (50-100 meters) and high level (100-150 meters). Different numbers and types of drones are deployed for each level. In the low level, three quadcopters equipped with high-resolution RGB cameras are deployed. The camera resolution of these drones is 20 million pixels, the flight speed is set to 5 meters per second, and the flight altitude is 40 meters. The drones take pictures of the slope at angles of 45 degrees, 90 degrees and 135 degrees along the preset route, taking a picture every 5 meters. In the middle level, two fixed-wing drones equipped with infrared cameras are deployed. The resolution of the infrared cameras is 10 million pixels, the flight speed is 10 meters per second, and the flight altitude is 80 meters. The drones take pictures of the slope at angles of 30 degrees, 60 degrees and 90 degrees, taking a picture every 10 meters. At the upper level, a multi-rotor drone equipped with a hyperspectral camera is deployed. The resolution of the hyperspectral camera is 5 million pixels, the flight speed is 8 meters per second, and the flight altitude is 120 meters. The drone takes pictures of the slope at angles of 15 degrees, 45 degrees, and 75 degrees, taking a picture every 15 meters. Through the above steps, multi-angle image data of the slope can be obtained.

[0043] Step S16: Perform laser radar site planning on the mountain slope according to the slope gradient characteristic data to obtain laser scanning site distribution data, and perform multi-site scanning on the mountain slope according to the laser scanning site distribution data to obtain a slope point cloud data set.

[0044] Specifically, the slope can be divided into several scanning areas according to the slope gradient characteristic data, and the area of ​​each area is about 100 square meters. LiDAR stations are planned at the center point and four corner points of each area. For example, in the steep area of ​​the slope, the distance between the stations is set to 50 meters; in the gentle area of ​​the slope, the distance between the stations is set to 100 meters. Multiple high-performance ground LiDAR devices are used for multi-site scanning. These LiDAR devices have a measurement range of 100 meters, an accuracy of 0.01 meters, and a scanning frequency of 50,000 times per second. During the scanning process, the LiDAR device performs a full-scale scan of the slope with a 360-degree viewing angle to obtain the elevation data and three-dimensional coordinate information of the slope surface. The scanning time for each station is about 30 minutes. After the scanning is completed, the point cloud data of each station is imported into the professional point cloud processing software, and the software generates a three-dimensional point cloud model of the slope based on these data. Through the above steps, a slope point cloud data set can be obtained.

[0045] The present invention can comprehensively acquire the terrain features and slope information of the slope by performing panoramic image acquisition and aerial laser ranging scanning on the side of the slope, so that the acquisition process can more accurately cover the key areas of the slope, avoiding data omissions or errors caused by complex terrain. Through reasonable route planning and flight mission allocation, the UAV can fly safely according to the actual terrain features of the slope. Through a highly layered data acquisition method, detailed data at different height levels of the slope can be obtained. Through reasonable LiDAR site planning, the scanning process can more efficiently cover the key areas of the slope. This not only improves the efficiency of LiDAR scanning, but also ensures that the acquired point cloud data has higher accuracy and integrity.

[0046] Preferably, step S2 comprises the following steps:

[0047] Step S21: Arrange seismic wave sources on the mountain slope to obtain seismic source arrangement data;

[0048] Specifically, a controllable seismic source device can be selected as a seismic wave source, which can generate seismic waves with a frequency range of 10-100Hz. During the layout process, the seismic wave source device is evenly distributed at the bottom and middle areas of the slope according to the terrain characteristics of the slope and the detection requirements. Specifically, a seismic source point is laid out every 50 meters at the bottom of the slope, and a seismic source point is laid out every 70 meters in the middle of the slope. At each seismic source point, the excitation parameters of the seismic source device are set, including an excitation frequency of 30Hz, an excitation energy of 500J, and an excitation interval of 2 seconds. During the layout process, a GPS positioning device is used to locate each seismic source point, and the coordinates, elevation, excitation parameters and other information of the seismic source point are recorded to finally obtain the seismic source layout data.

[0049] Step S22: arranging receiver arrays on the mountain slopes according to the seismic source layout data to obtain slope receiver layout data;

[0050] Specifically, a highly sensitive seismic detector with a frequency response range of 5-200Hz can be selected as a receiver. When arranging the receiver array, a grid-like arrangement scheme is designed according to the location of the earthquake source and the terrain characteristics of the slope. Specifically, at the bottom and middle areas of the slope, a row of receivers is arranged every 10 meters, and each row of receivers is spaced 15 meters apart to form a uniformly distributed grid. For example, near the first source point at the bottom of the slope, 5 receivers are arranged, located directly above, above the left, above the right, below the left and below the right of the source point. Near the source point in the middle of the slope, 7 receivers are arranged. A small pit is dug around each receiver, and the receiver is placed vertically in the pit and fixed with soil and stones. At the same time, a GPS positioning device is used to locate each receiver, and the coordinates, elevation, and layout parameters of the receiver are recorded to finally obtain the slope receiver layout data.

[0051] Step S23: configuring the trigger timing of the receiver array according to the slope receiver layout data to obtain receiver trigger sequence data;

[0052] Specifically, the receiver layout data can be imported into the seismic wave detection control system, which can automatically generate a trigger timing scheme based on the location and number of receivers. During the configuration process, the parameters of the trigger timing are set, including the trigger delay time, trigger interval, and trigger sequence. For example, the trigger delay time is set to 0.1 seconds to compensate for the difference in propagation speed of seismic waves in different media; the trigger interval is set to 0.5 seconds; and the trigger sequence is set to start from the receiver at the bottom of the slope and trigger upward in sequence. After the configuration is completed, the trigger timing scheme is simulated and tested to check the trigger time and signal synchronization of each receiver. Finally, the receiver trigger sequence data is obtained.

[0053] Step S24: Exciting the mountain slope with seismic waves according to the receiver trigger sequence data to obtain slope seismic wave data, and identifying the first arrival wave of the slope seismic wave data to obtain slope wave arrival time data;

[0054] Specifically, the arranged controllable seismic source equipment can be used to perform seismic wave excitation at each source point in turn according to the timing in the trigger sequence data. For example, at the first source point at the bottom of the slope, the source device is excited at a frequency of 30 Hz and an energy of 500 J under the control of the trigger signal to generate a seismic wave signal; then, at the second source point in the middle of the slope, the source device is excited at the same frequency and energy under the control of the trigger signal, and so on. During the excitation process, the propagation of seismic waves and the signal reception of the receiver are monitored in real time through the seismic wave detection control system. After the seismic wave excitation is completed, the seismic wave data received by each receiver is collected and imported into the seismic data processing software. The software performs first-arrival wave recognition on the seismic wave data according to the propagation characteristics of the seismic wave and the trigger timing of the receiver, that is, identifies the initial time point when the seismic wave arrives at each receiver. For example, in the receiver array at the bottom of the slope, the first-arrival wave recognition result shows that the time for the seismic wave to arrive at the first receiver is 1.2 seconds, the time for arriving at the second receiver is 1.5 seconds, and so on. Through the first-arrival wave recognition, the slope wave arrival time data can be obtained.

[0055] Step S25: performing travel time inversion on the slope seismic wave data according to the slope wave arrival time data to obtain seismic wave velocity structure data, and performing waveform inversion on the seismic wave velocity structure data to obtain slope seismic reflection data;

[0056] Specifically, the slope wave arrival time data and the preset seismic wave propagation model can be imported into the software. The software adopts a travel time inversion algorithm based on the least squares method, which can invert the propagation velocity structure of seismic waves in the slope medium according to the time difference of seismic waves arriving at the receiver. During the inversion process, the initial model parameters of the inversion are set, including the initial velocity of the seismic wave as 2000 meters per second, the velocity gradient as 0.5 seconds, etc. These parameters are determined according to the geological background of the slope and previous empirical data. The software continuously adjusts the velocity model parameters through iterative calculation to minimize the error between the calculated theoretical wave arrival time and the actual wave arrival time. After multiple iterations, the slope seismic wave velocity structure data is finally obtained, which reflects in detail the distribution of the propagation velocity of seismic waves in different media of the slope. For example, in the rock layer of the slope, the seismic wave velocity can reach 3000 meters per second, while in the soil layer, the velocity is about 1500 meters per second. After obtaining the velocity structure data, the seismic wave velocity structure data is further subjected to waveform inversion. The software uses a waveform inversion algorithm based on the wave equation, which can invert the seismic reflection data of the slope according to the propagation velocity and waveform characteristics of the seismic wave. During the inversion process, the initial reflection coefficient model of the inversion is set, and the reflection interface and reflection waveform of the slope are calculated based on the seismic wave velocity structure data and the actual seismic wave data. For example, at a fault interface of the slope, the inversion results show that there is an obvious reflection peak, indicating that the interface has a high reflection coefficient. Through waveform inversion, the seismic reflection data of the slope can be obtained.

[0057] Step S26: Perform electromagnetic tomography detection on the mountain slope to obtain slope electromagnetic tomography data, and fuse and invert the slope seismic reflection data and the slope electromagnetic tomography data to obtain slope internal structure data.

[0058] Specifically, please refer to the sub-steps of step S26 for the detailed implementation process of this embodiment.

[0059] The present invention can ensure accurate excitation and reception of seismic wave signals through the arrangement of seismic wave sources and receiver arrays. The reasonable trigger timing configuration makes the acquisition of seismic wave data more stable and reliable, and also helps to improve the accuracy of seismic wave velocity structure data, so that the obtained seismic reflection data can more accurately reflect the geological structure inside the slope. Through electromagnetic tomography detection, it is possible to penetrate deep into the slope to detect the distribution of conductivity at different depths. Through the fusion and inversion of seismic reflection data and electromagnetic tomography data, the data information of two different physical properties is integrated, and the internal structure of the slope can be analyzed and interpreted from multiple angles. This overcomes the limitations of a single data source under certain geological conditions, improves the comprehensiveness and accuracy of the internal structure of the slope, and makes the obtained internal structure data of the slope more real and reliable.

[0060] Preferably, step S26 comprises the following steps:

[0061] Step S261: Arranging electromagnetic transmitting sources on the mountain slope to obtain electromagnetic source arrangement data, and arranging receiving electrodes on the mountain slope according to the electromagnetic source arrangement data to obtain electrode arrangement data;

[0062] Specifically, the GEM-2 electromagnetic induction instrument can be selected, which can generate electromagnetic waves with a frequency range of 1-10MHz. During the layout process, according to the terrain characteristics of the slope and the detection requirements, the electromagnetic emission source equipment is evenly distributed at the bottom and middle areas of the slope. Specifically, a transmission source point is arranged every 30 meters at the bottom of the slope, and a transmission source point is arranged every 50 meters in the middle of the slope. At each transmission source point, the transmission parameters of the transmission source equipment are set, including a transmission frequency of 5MHz, a transmission power of 500W, and a transmission time of 10 seconds. During the layout process, a GPS positioning device is used to accurately locate each transmission source point, and the coordinates, elevation, and transmission parameters of the transmission source point are recorded, and finally the electromagnetic source layout data is obtained. The receiving electrode is laid out on the mountain slope according to the electromagnetic source layout data. A high-sensitivity electrode is selected as the receiver, and the resistivity measurement range of the electrode is 0.1-1000Ω·m. When arranging the receiving electrodes, a grid-like layout scheme is adopted, with a row of electrodes arranged every 10 meters, and each row of electrodes is spaced 15 meters apart to form a uniformly distributed grid. For example, near the first transmitting source point at the bottom of the slope, 6 receiving electrodes are arranged, located directly above, above the left, above the right, below the left, below the right, and directly below the transmitting source point. A small pit is dug around each receiving electrode, and the electrode is placed vertically in the pit and fixed with soil and stones. At the same time, a GPS positioning device is used to accurately locate each receiving electrode, and the coordinates, elevation, and layout parameters of the electrode are recorded to finally obtain the electrode layout data.

[0063] Step S262: configuring the excitation waveform of the electromagnetic emission source according to the electrode layout data to obtain electromagnetic excitation waveform data;

[0064] Specifically, the electrode layout data can be imported into the Geonics EM-38 electromagnetic induction measurement system, which can automatically generate an excitation waveform scheme based on the position and number of electrodes. During the configuration process, the parameters of the excitation waveform are set, including the waveform type, frequency range, amplitude, and phase. For example, a sine wave is selected as the excitation waveform type, the frequency range is set to 2-8MHz, the amplitude is set to 2V, and the phase is set to 0 degrees. In addition, the excitation waveform can be optimized and adjusted according to the geological characteristics of the slope and the detection target. For example, in the rock layer area of ​​the slope, the excitation frequency is appropriately increased; in the soil layer area of ​​the slope, the excitation frequency is appropriately reduced. After the configuration is completed, the electromagnetic excitation waveform data is finally obtained.

[0065] Step S263: performing electromagnetic field measurement on the receiving electrode according to the electromagnetic excitation waveform data to obtain slope electromagnetic field data;

[0066] Specifically, the electromagnetic field of the mountain slope can be measured using the receiving electrode according to the electromagnetic excitation waveform data. First, ensure that the electromagnetic emission source equipment transmits stably according to the preset waveform parameters, with a transmission frequency of 2-8MHz and an amplitude of 2V. During the measurement process, each receiving electrode is connected to a high-precision electromagnetic field measuring instrument, which can collect the electromagnetic signals received by the electrode in real time and convert them into electromagnetic field strength data. Each receiving electrode is measured synchronously. For example, at the first receiving electrode at the bottom of the slope, the measurement results show that the electromagnetic field strength at a frequency of 2MHz is 0.5V / m, and the electromagnetic field strength at a frequency of 8MHz is 0.3V / m. Record the electromagnetic field strength data of each electrode at different frequencies, and combine it with the layout position and elevation information of the electrode to obtain the slope electromagnetic field data.

[0067] Step S264: invert and reconstruct the slope electromagnetic field data to obtain slope conductivity distribution data;

[0068] Specifically, the slope electromagnetic field data can be imported into the GeoElectrical module in GeoStudio software, and the initial model parameters of the inversion can be set according to the geological background of the slope and previous empirical data. For example, the initial conductivity is set to 0.1S / m, and the conductivity change gradient is set to 0.01S / m. These parameters are determined based on the typical geological conditions of the area where the slope is located and the inversion experience of previous similar projects. The GeoElectrical module adopts an inversion algorithm based on the finite difference method, specifically the finite difference forward and inverse algorithm. The algorithm constructs a three-dimensional grid model of the slope, fits the electromagnetic field data with the model, and calculates the conductivity distribution of the slope medium. During the inversion process, the inversion results are iteratively optimized multiple times. Each iteration adjusts the conductivity model parameters according to the inversion error and model fit. For example, by comparing the error between the inversion result and the actual electromagnetic field data, the initial value and change gradient of the conductivity are appropriately adjusted to reduce the error. After multiple iterations, the error between the slope conductivity distribution data and the actual electromagnetic field data is finally minimized. The inversion results show that the conductivity in the rock layer of the slope is low, about 0.05S / m, while the conductivity in the water-bearing soil layer of the slope is high, about 0.5S / m. Through the above steps, the slope conductivity distribution data is finally obtained.

[0069] Step S265: reconstructing the slope electromagnetic data according to the slope conductivity distribution data to obtain slope electromagnetic tomography data;

[0070] Specifically, the slope conductivity distribution data can be imported into EIDORS Electromagnetic Impedance Tomography and Diffuse Optical Tomography Reconstruction Software, and the image reconstruction parameters can be set according to the geometric characteristics of the slope and the electromagnetic field measurement data. The image resolution is set to 1 meter × 1 meter. The reconstruction range is set to cover the entire slope area. The reconstruction algorithm uses the algebraic reconstruction technology (ART) implemented in the EIDORS software. During the image reconstruction process, the EIDORS software gradually optimizes the electromagnetic field distribution inside the slope through iterative calculations based on the conductivity distribution data and the electromagnetic field propagation model, and converts it into visual image data. For example, in the rock layer area of ​​the slope, the image is displayed as a dark area with low conductivity; while in the water-bearing soil layer area of ​​the slope, the image is displayed as a light area with high conductivity. Through the image reconstruction of the EIDORS software, the slope electromagnetic tomography data can be obtained, which intuitively displays the conductivity distribution characteristics inside the slope in the form of an image.

[0071] Step S266: fusing and inverting the slope seismic reflection data and the slope electromagnetic tomography data to obtain the slope internal structure data.

[0072] Specifically, the slope seismic reflection data and the slope electromagnetic tomography data can be imported into the GIM software. Then, the GIM software uses the Bayesian inversion algorithm to jointly invert the seismic reflection data and the electromagnetic tomography data. During the inversion process, the algorithm takes into account the propagation characteristics of seismic waves and electromagnetic waves in the slope medium, such as the reflection coefficient of seismic waves and the conductivity change of electromagnetic waves, as well as the correlation and complementarity between the two data. For example, at a certain fault interface of the slope, the seismic reflection data shows an obvious reflection peak, indicating that the interface has a high reflection coefficient, while the electromagnetic tomography data shows an abnormal change in conductivity, indicating a change in the material composition or water content of the interface. Through data fusion and inversion, the GIM software can integrate this information to determine the precise position, shape and properties of the fault interface. Finally, the internal structure data of the slope is obtained, which reflects the geological structure, rock layer distribution and material composition of the slope in detail. For example, the inversion results show that there are multiple fault interfaces and rock layer interfaces inside the slope, and the conductivity and reflection coefficient characteristics of each interface are clearly visible.

[0073] The present invention can ensure accurate excitation and reception of electromagnetic signals by arranging electromagnetic emission sources and receiving electrodes. Reasonable electrode arrangement provides a stable basis for electromagnetic field measurement. By inverting and reconstructing the electromagnetic field data of the slope, the conductivity distribution data of the slope can be obtained. This can reveal the conductivity differences of different materials inside the slope, thereby more carefully reflecting the geological structure and material distribution characteristics inside the slope. Image reconstruction is performed based on the conductivity distribution data, and the obtained slope electromagnetic tomography data has high clarity and readability. This can intuitively display the structural characteristics inside the slope, allowing technicians to more intuitively identify and analyze the geological structure of the slope, thereby improving the practicality and ease of use of the data.

[0074] Preferably, step S3 comprises the following steps:

[0075] Step S31: extracting feature points from the multi-angle image data of the slope to obtain a slope image feature point set, and extracting feature points from the slope point cloud data set to obtain a slope point cloud feature point set;

[0076] Specifically, for multi-angle image data, the image processing software Adobe Photoshop is used, and the SIFT (Scale Invariant Feature Transform) algorithm is selected as the method for feature point extraction. The algorithm can detect key points in the image and extract the feature descriptors of the key points. In the extraction process, the parameters of the SIFT algorithm are set, such as the number of scale space layers is 3, the sampling interval of each scale space is 1.2 times, and the threshold of the feature point is 0.01. Through the setting of parameters, the software detects a large number of feature points in each image and generates a 128-dimensional feature vector for each feature point. For example, in an image of the slope, 500 feature points are extracted, and these feature points are mainly concentrated in the edge, corner points and texture-rich areas of the slope. For the slope point cloud data set, the point cloud processing software CloudCompare is used, which can extract feature points from the point cloud data. The PCA (Principal Component Analysis) algorithm is selected as the method for feature point extraction. The algorithm can identify feature points in the point cloud based on the local geometric features of the point cloud data. During the extraction process, the parameters of the PCA algorithm are set, such as the radius of the local neighborhood is 0.1 meters, the curvature threshold of the feature point is 0.5, etc. Through the setting of parameters, the software identifies a large number of feature points in the point cloud data and calculates the normal vector and curvature value for each feature point. For example, in the point cloud data of the slope, 800 feature points are extracted, and these feature points are mainly distributed in the concave and convex change area of ​​the slope and near the structural surface. Finally, the slope image feature point set and the slope point cloud feature point set are obtained.

[0077] Step S32: matching the slope image feature point set with the slope point cloud feature point set to obtain the slope initial matching point pair data;

[0078] Specifically, OpenCV can be used for feature point matching. OpenCV uses the FLANN (Fast Approximate Nearest Neighbor) algorithm as a feature point matching method, which can quickly find the nearest neighbor matching point pairs in large-scale feature point data. During the matching process, the parameters of the FLANN algorithm are set, such as the number of trees is 5, the branching factor is 32, and the number of search iterations is 10. Through the setting of parameters, the software establishes a large number of matching point pairs between the image feature point set and the point cloud feature point set. For example, in a certain area of ​​the slope, a feature point in the image feature point set and a feature point in the point cloud feature point set are matched as a pair. They are very close in spatial position, and the distance between the feature descriptors is small. Through the above steps, the initial matching point pair data of the slope is finally obtained.

[0079] Step S33: screening the initial matching point pair data of the slope to obtain the effective matching point pair data of the slope;

[0080] Specifically, the initial matching point pair data of the slope can be imported into the OpenCV software, and the RANSAC (Random Sample Consensus) algorithm in OpenCV can be used to screen the initial matching point pair data. The RANSAC algorithm fits the model by randomly selecting the minimum point set, and evaluates all data points to identify and eliminate incorrect matching point pairs and retain stable matching point pairs. During the implementation process, the parameters of the RANSAC algorithm are set, such as the number of iterations is 1000 times and the threshold of the inliers is 3 pixels. The setting of these parameters is based on the resolution of the slope image data and the distribution of feature points. For example, in the slope image, the average spacing of the feature points is 10 pixels, so the inliers threshold is set to 3 pixels. Through the screening of the RANSAC algorithm, the OpenCV software identifies and eliminates about 30% of the incorrect matching point pairs from a large number of initial matching point pairs, and finally obtains the effective matching point pair data of the slope.

[0081] Step S34: performing ICP iterative registration on the slope image feature point set and the slope point cloud feature point set according to the slope effective matching point pair data to obtain a feature point registration transformation matrix;

[0082] Specifically, the valid matching point pair data, image feature point set and point cloud feature point set can be imported into the CloudCompare software. Next, the ICP registration algorithm is started, which iteratively finds the nearest point pair and calculates the transformation matrix. During the ICP registration process, the parameters of the algorithm are set, such as the maximum number of iterations is 50 times and the registration accuracy is 0.01 meters. The setting of these parameters is based on the scale and accuracy requirements of the slope data. For example, the length of the slope is 100 meters and the width is 50 meters, and the registration accuracy is set to 0.01 meters. In each iteration, the CloudCompare software updates the position of the feature points according to the current transformation matrix and recalculates the distance error of the nearest point pair. After multiple iterations, the feature point registration transformation matrix is ​​finally obtained. The matrix contains translation, rotation and scaling transformation parameters, which can accurately transform the image feature point set to a spatial position that matches the point cloud feature point set.

[0083] Step S35: spatially transform the slope multi-angle image data and the slope point cloud data set according to the feature point registration transformation matrix to obtain initial image-point cloud registration data;

[0084] Specifically, the multi-angle image data and point cloud data set of the slope can be imported into the Leica Geo Office software, and the feature point registration transformation matrix can be imported. The spatial transformation tool in the software can be used to perform accurate spatial transformation on the image data and point cloud data according to the feature point registration transformation matrix. During the spatial transformation process, the transformation parameters are set, such as the interpolation method is selected as bilinear interpolation. For example, the original resolution of the slope image is 0.5 meters / pixel. Through the bilinear interpolation method, the detailed features can be maintained in the transformed image to avoid pixel distortion or blurring. At the same time, for the point cloud data, the nearest neighbor interpolation method is selected. For example, in the steep area of ​​the slope, the point cloud density is high. Through the nearest neighbor interpolation method, the high-density features of the area can be maintained in the transformed point cloud data. After the spatial transformation processing of the Leica Geo Office software, the multi-angle image data and the point cloud data set of the slope are accurately transformed to the same spatial coordinate system to obtain the initial image-point cloud registration data.

[0085] Step S36: Perform tensor field interpolation precise registration on the initial image-point cloud registration data to obtain image-point cloud registration data, and perform spatial unified transformation on the image-point cloud registration data and the slope internal structure data to obtain slope image-point cloud unified data.

[0086] Specifically, please refer to the sub-steps of step S36 for the detailed implementation process of this embodiment.

[0087] The present invention can accurately capture the key feature points of the slope surface by extracting feature points from the multi-angle image data and point cloud data set of the slope. This can ensure the consistency of the image data and the point cloud data at the feature point level, provide a reliable basis for data matching and registration, and improve the accuracy of data fusion. By using the RANSAC algorithm to screen the initial matching point pair data, the wrong matching point pairs can be effectively removed and the valid matching point pairs can be retained. This improves the robustness and reliability of data matching, making the obtained valid matching point pair data more accurate. Through the ICP iterative registration method, the feature point registration transformation matrix can be accurately calculated, thereby achieving high-precision registration of the image feature point set and the point cloud feature point set. Through tensor field interpolation precise registration, the spatial consistency and smoothness of the registration data can be further improved. After the image-point cloud registration data and the slope internal structure data are spatially unified, the slope image-point cloud unified data obtained can effectively fuse data from different sources in space, achieving seamless connection and unified expression of data.

[0088] Preferably, step S36 includes the following steps:

[0089] Step S361: constructing a tensor field for the initial image-point cloud registration data to obtain image-point cloud tensor field data;

[0090] Specifically, the initial image-point cloud registration data can be imported into the TensorFlow software. The data includes the pixel value matrix of the image and the three-dimensional coordinate matrix of the point cloud. The image data and the point cloud data are tensorized and converted into tensor field data using the tensor operation function in TensorFlow. In the process of tensor field construction, the dimension and shape parameters of the tensor are set. For example, the tensor dimension of the image data is set to (height, width, channels), where height is the height of the image, width is the width of the image, and channels is the number of channels of the image (such as RGB three channels); the tensor dimension of the point cloud data is set to (points, features), where points is the number of points in the point cloud, and features is the feature dimension of each point (such as three-dimensional coordinates, normal vectors, etc.). Through the tensor operation of TensorFlow, the image data and the point cloud data are fused into a unified tensor field, which contains the texture information of the image and the geometric information of the point cloud. For example, in a certain area of ​​the slope, the image tensor field contains the rock texture features of the area, while the point cloud tensor field contains the terrain undulation features of the area. Through tensor field construction, image-point cloud tensor field data can be obtained.

[0091] Step S362: performing main direction decomposition on the image-point cloud tensor field data to obtain main direction data of the image-point cloud tensor;

[0092] Specifically, the image-point cloud tensor field data can be imported into MATLAB, the data is stored in the form of a multi-dimensional matrix, and the tensor decomposition function of MATLAB, such as the tensor_decomp function, is called to perform main direction decomposition on the tensor field data. In the main direction decomposition process, the decomposition parameters, such as the decomposition rank and the number of iterations, are set. For example, setting the decomposition rank to 5 means that the tensor field is decomposed into 5 main direction components; the number of iterations is set to 100 times. MATLAB calculates the main direction components and corresponding weight coefficients of the tensor field data by alternating least squares method. For example, in a certain area of ​​the slope, the main direction decomposition results show that the first main direction component mainly reflects the rock texture direction of the area, and the second main direction component mainly reflects the slope direction of the terrain. Through the main direction decomposition, the main direction data of the image-point cloud tensor can be obtained, which reveals the main structural features and direction information in the slope image and point cloud data.

[0093] Step S363: constructing image-point cloud radial basis functions for the initial image-point cloud registration data according to the main direction data of the image-point cloud tensor to obtain image-point cloud interpolation basis functions;

[0094] Specifically, the main direction data of the image-point cloud tensor can be imported into SciPy. The data includes the texture feature points of the image and the geometric feature points of the point cloud, as well as their corresponding main direction information. The radial basis function (RBF) module in SciPy is used to construct the interpolation basis function of the initial image-point cloud registration data according to the main direction data. During the construction process, the type and parameters of the radial basis function are set, and the Gaussian radial basis function (Gaussian RBF) is selected as the interpolation basis function. The shape parameter of the radial basis function is set to 1.0, which affects the smoothness of the function and the interpolation accuracy. For example, in the steep area of ​​the slope, the distribution of image and point cloud data is relatively dense. Through Gaussian RBF interpolation, the terrain changes and image texture characteristics of the area can be accurately captured. SciPy calculates the image-point cloud interpolation basis function based on the main direction data of the image-point cloud tensor and the set radial basis function parameters. The basis function can smoothly interpolate the image data and point cloud data in space and fill the gaps and discontinuous parts in the data.

[0095] Step S364: performing precise registration on the initial image-point cloud registration data according to the image-point cloud interpolation basis function to obtain image-point cloud registration data;

[0096] Specifically, the initial image-point cloud registration data and interpolation basis functions can be imported into CloudCompare, the registration tool in the software is started, and the interpolation basis functions are used to perform fine spatial transformation and adjustment on the image data and point cloud data. In the fine registration process, the registration parameters are set, such as the registration accuracy of 0.005 meters, which is higher than the previous initial registration accuracy. For example, in a corner area of ​​the slope, there is a slight misalignment or deviation between the image data and the point cloud data. Through the guidance of the interpolation basis function, CloudCompare can accurately adjust the pixel position of the image data and the point coordinates of the point cloud data so that they are completely aligned in space. At the same time, the software will also perform local optimization on the registered data according to the smoothness characteristics of the interpolation basis function to eliminate the registration error caused by data noise or irregular distribution. After fine registration processing, the image-point cloud registration data can be obtained. The registration results show that the image data and the point cloud data are highly consistent in spatial position, and the registration error is less than 0.005 meters. For example, in the crack area of ​​the slope, the crack texture in the image data is highly matched with the crack morphology in the point cloud data, clearly showing the direction and width of the crack.

[0097] Step S365: performing coordinate uniform conversion on the image-point cloud registration data and the slope internal structure data to obtain initial slope image-point cloud unified data;

[0098] Specifically, the image-point cloud registration data and the slope internal structure data can be imported into Leica GeoOffice. The image-point cloud registration data contains the image texture information and point cloud geometry information that have been precisely registered, while the slope internal structure data contains the geological structure information obtained by seismic reflection and electromagnetic tomography. The coordinate conversion tool in the software is used to convert the two sets of data into a unified coordinate system. During the coordinate conversion process, the target coordinate system is set to WGS84UTM Zone45N. The software automatically calculates the conversion matrix based on the original coordinate system parameters of the image-point cloud registration data and the slope internal structure data, and accurately converts the two sets of data to the target coordinate system. For example, the original coordinate system of the image-point cloud registration data is the local rectangular coordinate system, and the original coordinate system of the slope internal structure data is the geographic coordinate system. Through coordinate conversion, they are all converted to data in the WGS 84UTM Zone 45N coordinate system. The converted data are completely aligned in spatial position, and the initial slope image-point cloud unified data is finally obtained.

[0099] Step S366: Perform spatial registration evaluation on the initial slope image-point cloud unified data to obtain registration accuracy evaluation data, and perform registration error compensation on the initial slope image-point cloud unified data based on the registration accuracy evaluation data to obtain slope image-point cloud unified data.

[0100] Specifically, the initial slope image-point cloud unified data can be imported into CloudCompare, the spatial registration evaluation tool in the software is started, and the evaluation parameters are set, such as the threshold of the registration error is 0.01 meters, which is set according to the accuracy requirements of slope modeling and the actual situation of the data. The software obtains the registration accuracy evaluation data by calculating the registration error of each point in the data, that is, the distance difference between the actual position of the point and the theoretical position. For example, in a gentle area of ​​the slope, the registration error is generally less than 0.005 meters, while in a steep area of ​​the slope, the registration error is large, and the error of some points exceeds 0.01 meters. According to the registration accuracy evaluation data, in the area with large errors, the local optimization function of CloudCompare is used to fine-tune the data, and the registration error is reduced to the threshold range by adjusting the properties such as the position and normal vector of the point. For example, in steep areas, the normal vector of the point cloud data is optimized to better conform to the geometric characteristics of the terrain, thereby reducing the registration error. After the registration error compensation, the slope image-point cloud unified data is finally obtained.

[0101] The present invention can accurately capture the spatial variation characteristics and main direction information of the data by constructing an image-point cloud tensor field and performing main direction decomposition. By using the image-point cloud radial basis function for interpolation, the initial image-point cloud registration data can be effectively smoothed to fill the gaps and discontinuous parts in the data. This can better adapt to complex terrain and data distribution characteristics, making the registered data smoother and more continuous. Through unified coordinate conversion, the image-point cloud registration data and the internal structure data of the slope are accurately aligned in space, achieving seamless connection and unified expression between different data sources. Through spatial registration evaluation, registration accuracy evaluation data is obtained, and the registration results can be comprehensively tested and analyzed for accuracy. Registration error compensation based on the evaluation data can further improve the accuracy and reliability of the registration results and ensure the accuracy and consistency of the data in space.

[0102] Preferably, step S4 comprises the following steps:

[0103] Step S41: performing spatial gradient distribution recognition on the slope image-point cloud unified data to obtain slope spatial gradient field data;

[0104] Specifically, the unified data of slope image and point cloud can be imported into MATLAB. The data is stored in the form of a multidimensional matrix, which contains the texture information of the image and the geometric information of the point cloud. The image processing toolbox in MATLAB is used to identify the spatial gradient distribution of the data. In the recognition process, the Sobel operator is selected as the gradient detection operator. The Sobel operator can effectively detect the edge and gradient changes in the data. The window size of the Sobel operator is set to 3×3 pixels. For example, in a rock edge area of ​​the slope, the Sobel operator can accurately detect the gradient change between the rock and the soil layer and obtain the gradient value of the area. MATLAB obtains the spatial gradient field data of the slope by calculating the gradient amplitude and direction of each point in the data. The gradient field data is represented in the form of vectors. The length of each vector represents the gradient amplitude, and the direction represents the gradient direction. For example, in the steep area of ​​the slope, the gradient vector is longer and points downward, indicating that the slope of the area is larger and the slope is downward.

[0105] Step S42: Selecting marker points from the slope spatial gradient field data to obtain slope watershed marker data;

[0106] Specifically, the slope spatial gradient field data can be imported into ArcGIS, and the data is stored in the form of raster data. Each raster unit corresponds to a gradient vector. The spatial analysis tools in ArcGIS are used to detect local extreme values ​​of the gradient field data and select watershed marker points. In the process of selecting marker points, the threshold parameters of the local extreme value are set, such as the gradient amplitude threshold of the extreme value is 10, and the neighborhood range of the extreme value is 5×5 grids. The setting of these parameters is based on the terrain characteristics of the slope and the distribution of the gradient field data. For example, in the top area of ​​the slope, the gradient amplitude is large and the gradient amplitude in the surrounding neighborhood is small, which meets the extreme value condition, so it is selected as a watershed marker point. ArcGIS identifies the local extreme value points that meet the conditions by calculating the gradient amplitude of each raster unit and the gradient change in the neighborhood, and marks them as watershed marker points. For example, there is an obvious watershed between two adjacent ridges of the slope, and the marker points on it are distributed in a continuous line. Through the selection of marker points, the slope watershed marker data is obtained.

[0107] Step S43: performing distance transformation on the slope watershed marker data to obtain a slope watershed distance map;

[0108] Specifically, the slope watershed marker data can be imported into OpenCV, and the data is stored in the form of a binary image, where the watershed marker point is a white pixel and the background is a black pixel. The distance transformation function in OpenCV, such as cv2.distanceTransform, is used to perform distance transformation on the watershed marker data. In the distance transformation process, the distance type of the transformation is set to DIST_L2 (Euclidean distance), which can calculate the straight-line distance from the pixel point to the nearest white pixel (watershed marker point). At the same time, the mask size of the transformation is set to 3×3 pixels. For example, in a certain area of ​​the slope, in the image obtained after the distance transformation, the gray value of each pixel point represents its distance to the nearest watershed marker point. The closer the distance, the lower the gray value of the pixel point, and the farther the distance, the higher the gray value of the pixel point. Through the distance transformation, the slope watershed distance map is obtained, which shows the distribution of the distance from each pixel point to the watershed marker point in the form of a grayscale image.

[0109] Step S44: performing watershed growth diffusion on the marked points in the slope watershed marked data according to the slope watershed distance map to obtain the initial segmentation data of the slope;

[0110] Specifically, the slope watershed marker data and the watershed distance map can be imported into MATLAB, and the regional growing algorithm in MATLAB is used to perform watershed growth diffusion on the watershed marker points. In the process of watershed growth diffusion, the threshold parameters of growth are set, such as the growth distance threshold of 5 pixels, which is set according to the terrain characteristics of the slope and the distribution of the watershed distance map. For example, in a certain mountaintop area of ​​the slope, starting from the watershed marker point, growth diffusion is performed along the low gray value area in the distance map until a pixel point with a gray value greater than the growth distance threshold is encountered in the distance map. MATLAB gradually expands the watershed range of the watershed marker point through iterative calculation, and merges adjacent pixels into the same watershed. For example, between two adjacent ridges of the slope, two independent watershed areas are formed after watershed growth diffusion, corresponding to two different watershed marker points. Through watershed growth diffusion, the initial segmentation data of the slope can be obtained.

[0111] Step S45: performing boundary optimization on the initial segmentation data of the slope to obtain slope unit division data;

[0112] Specifically, the initial segmentation data of the slope can be imported into ImageJ, and the data is stored in the form of a segmented binary image, in which different unit areas are represented by different pixel values. The boundary smoothing and optimization tools in ImageJ are used to refine the segmented boundary. In the boundary optimization process, the opening and closing operations in morphological operations are selected as the main tools. The opening operation can remove small burrs and irregular details on the boundary, and the closing operation can fill small gaps and holes on the boundary. The size of the structural element of the opening and closing operations is set to 3×3 pixels. For example, in a unit area of ​​the slope, there are some small bumps and burrs on the boundary after the initial segmentation. Through the processing of the opening and closing operations, the boundary becomes smoother and the shape of the unit area becomes more regular. Through the above steps, the slope unit division data can be obtained.

[0113] Step S46: performing structural surface recognition on the slope unit division data to obtain slope structural surface feature data, and performing feature extraction on the slope structural surface feature data and the slope internal structure data to obtain slope hierarchical feature data.

[0114] Specifically, please refer to the sub-steps of step S46 for the detailed implementation process of this embodiment.

[0115] The present invention can accurately identify the natural boundary and unit boundary of the slope through spatial gradient distribution recognition and watershed marking. Through the process of distance transformation and watershed growth and diffusion, the noise and discontinuity in the slope data can be effectively processed, making the segmentation result more stable and robust. Distance transformation can quantify the distance relationship between the marked point and the surrounding points, while watershed growth and diffusion can reasonably expand the area according to the distance information, which can reduce the segmentation error caused by data noise or local discontinuity. Through structural surface recognition, the structural surface features in the slope, such as joints and cracks, can be accurately identified. By combining the internal structural data of the slope for feature extraction, the hierarchical feature data of the slope can be further enriched and improved, so that the model can more realistically reflect the structural hierarchy and geological characteristics of the slope. By extracting and fusing the features of the structural surface feature data and the internal structural data, the obtained hierarchical feature data of the slope can effectively integrate and hierarchically express the surface features and internal structural features of the slope.

[0116] Preferably, step S46 includes the following steps:

[0117] Step S461: Calculate the surface curvature of the slope unit division data to obtain slope surface curvature distribution data;

[0118] Specifically, the slope unit division data can be imported into CloudCompare, and the data is stored in the form of point clouds. Each point contains three-dimensional coordinate information. The surface curvature calculation tool in the software is used to perform curvature analysis on the surface of each unit area. In the curvature calculation process, Gaussian curvature is selected as the calculation indicator. The neighborhood radius of the curvature calculation is set to 0.5 meters. For example, in a rock unit area of ​​the slope, the surface is relatively steep and has some uneven features. The curvature distribution map of the area is obtained through Gaussian curvature calculation. The figure shows that the curvature value of the rock surface is high, and the curvature value changes significantly in the uneven parts. CloudCompare software generates slope surface curvature distribution data based on the curvature value of each point.

[0119] Step S462: extracting height difference characteristic lines of the mountain slope according to the slope surface curvature distribution data to obtain the slope height difference characteristic lines;

[0120] Specifically, the curvature distribution data of the slope surface can be imported into MATLAB, and the data is stored in the form of a two-dimensional matrix. Each element in the matrix corresponds to the curvature value of a point. The Canny edge detection algorithm in MATLAB is used to extract the height difference characteristic line of the curvature distribution data. In the process of characteristic line extraction, the threshold parameters of the Canny algorithm are set, such as the high threshold is 0.8 and the low threshold is 0.2. These thresholds are set according to the range of the curvature distribution data and the requirements of characteristic line extraction. The high threshold is used to detect obvious height difference edges, and the low threshold is used to connect edge breakpoints. For example, in a certain area of ​​the slope, there is an obvious height difference at the junction of the rock layer and the soil layer. The Canny algorithm can accurately detect the edge of the junction and extract the height difference characteristic line. MATLAB identifies the height difference characteristic line by calculating the gradient amplitude and direction in the curvature distribution data, and stores it in the form of vector line elements. Each line element represents a height difference characteristic line.

[0121] Step S463: performing structural surface trend statistics on the slope height difference characteristic line to obtain structural surface direction distribution data;

[0122] Specifically, the slope height difference feature line data can be imported into ArcGIS, and the "azimuth" tool in ArcGIS can be used to calculate the direction of each feature line. This tool can automatically calculate the azimuth of the line element, that is, the angle between the line element and the north, so as to obtain the strike angle of each feature line. In the statistical process, the statistical interval angle is set to 10 degrees, and the azimuth range of 0-360 degrees is divided into 36 intervals, each of which represents a strike direction. For example, the interval of 0-10 degrees represents a strike direction close to the north. Through the spatial analysis function of ArcGIS, the strike angles of all feature lines are counted, and the number and proportion of feature lines in each strike direction are calculated. For example, in a certain area of ​​the slope, the statistical results show that the number of feature lines with a strike angle of 45-55 degrees is the largest, accounting for 30%, indicating that the structural surface in this area is mainly northeast-southwest, and finally the structural surface direction distribution data is obtained.

[0123] Step S464: clustering the structural surface direction distribution data to obtain slope structural surface family data;

[0124] Specifically, the structural surface direction distribution data can be imported into Python, and the data is stored in the form of feature vectors. Each feature vector contains a strike angle and the corresponding number of feature lines. The K-means clustering algorithm is selected as the clustering method. The algorithm can divide the data into multiple clusters according to the similarity of the data. In the clustering process, the number of clusters is set to 5. At the same time, the initialization method of the algorithm is set to "k-means++". Scikit-learn divides the structural surface into 5 clusters according to the distance between the feature vectors through iterative calculation, and each cluster represents a structural surface family. For example, one of the clusters contains structural surfaces with a strike angle in the range of 40-60 degrees, and the number of feature lines is relatively large, indicating that this is a major structural surface family. Through the above steps, the slope structural surface family data can be obtained.

[0125] Step S465: performing spatial correlation measurement on the slope structural surface family data to obtain slope structural surface correlation data;

[0126] Specifically, the slope structural surface family data can be imported into the R language. The data is stored in the form of spatial objects. Each spatial object represents a structural surface family, including its spatial position and geometric features. The gDistance function in the rgeos package is used to calculate the spatial distance between different structural surface families. For example, the minimum distance between two adjacent structural surface families is calculated to evaluate their spatial proximity. The gIntersection function can also be used to calculate the spatial intersection area between structural surface families to evaluate their spatial overlap. Through the above steps, the slope structural surface correlation data can be obtained and stored in the form of a numerical matrix. Each element in the matrix represents the correlation measure between two structural surface families. For example, the value of an element in the matrix is ​​0.05, which means that the minimum distance between the two structural surface families is 0.05 meters, indicating that they are relatively close in space and there is a certain degree of mutual influence.

[0127] Step S466: combining the structural surfaces according to the slope structural surface correlation data to obtain the slope structural surface characteristic data;

[0128] Specifically, the structural surface association data can be imported into Python to construct a weighted undirected graph. The nodes in the graph represent structural surface families, the edges represent the association relationship between structural surface families, and the weight of the edge is the association metric. The graph is clustered using NetworkX's graph clustering algorithm, such as the Louvain community discovery algorithm. The algorithm identifies the community structure in the graph by maximizing the modularity, thereby achieving the combination of structural surface families. During the clustering process, the resolution parameter of the algorithm is set to 1.0. For example, the clustering results show that several originally scattered structural surface families are combined into a large structural surface feature area. These families are adjacent in space and have similar strike and dip characteristics, indicating that they belong to the same geological structural unit. Through the above steps, the slope structural surface feature data can be obtained, and the spatial distribution and association relationship of the structural surface can be displayed in the form of a graph.

[0129] Step S467: performing stress field evolution on the slope structural surface characteristic data to obtain slope stress field data, and performing weak surface identification on the mountain slope according to the slope stress field data to obtain slope weak surface data;

[0130] Specifically, the characteristic data of the slope structural surface can be imported into ABAQUS to establish a three-dimensional geometric model of the slope. According to geological data and experimental data, the corresponding mechanical parameters, such as elastic modulus, Poisson's ratio, and shear strength, are assigned to different rock and soil units in the model. The static analysis module of ABAQUS is used to apply external loads and boundary conditions to the slope model to simulate the stress distribution of the slope under different working conditions. For example, when simulating rainfall conditions, the influence of water pressure on slope stability is considered, and the seepage pressure is applied to the rock and soil units of the slope to simulate the water penetration and saturation process. Through finite element calculation, the stress field data of the slope is obtained, including the stress tensor, principal stress direction, and stress concentration area information of each unit. Using the post-processing function of ABAQUS, the stress concentration area and the area with a small angle between the principal stress direction and the structural surface are extracted as the weak surface of the slope. For example, in a certain area of ​​the slope, the stress concentration coefficient reaches 1.5, and the angle between the principal stress direction and the structural surface is less than 30 degrees, indicating that the area is a weak surface and there is a risk of sliding or shear failure. Through the above steps, the weak surface data of the slope can be obtained.

[0131] Step S468: Perform stability assessment on the weak surface data of the slope to obtain weak surface stability assessment data, and perform multi-scale fusion of the weak surface stability assessment data and the internal structure data of the slope to obtain hierarchical characteristic data of the slope.

[0132] Specifically, the weak surface data of the slope can be imported into Slope / W, and the strip method in the limit equilibrium method can be selected for stability analysis in combination with the simple geometric model of the slope and the parameters of the rock and soil body. In the process of stability assessment, the analysis parameters are set, such as the calculation method of the safety factor is the Morgenstern-Price method, which considers the non-uniform sliding surface between strips and the interaction force between strips. At the same time, the analysis conditions are set, such as considering the influence of water pressure under different rainfall conditions and the seismic force under different earthquake intensities. For example, when simulating heavy rainfall conditions, the input rainfall intensity is 100 mm / hour to calculate the influence of water pressure on slope stability; when simulating earthquake conditions, the input earthquake acceleration is 0.3g to evaluate the influence of seismic force on the stability of the weak surface of the slope. Through the calculation of Slope / W, the stability assessment data of the weak surface is obtained, including information such as the safety factor, the position of the sliding surface and the volume of the sliding body, and the stability assessment data of the weak surface is multi-scale fused with the internal structure data of the slope. Using GeoStudio's multi-physics coupling analysis function, the stability assessment results are combined with the geological structure, rock and soil parameters, and stress field data of the slope to generate hierarchical slope feature data. For example, in a certain area of ​​the slope, the fusion results show that the safety factor of the weak surface is 1.2, and there are faults and weak interlayers in the area, indicating that the stability of the area is poor. Through the above steps, the hierarchical slope feature data can be obtained.

[0133] The present invention can accurately identify the structural surface characteristics of the slope by calculating the surface curvature and extracting the height difference characteristic lines of the slope unit division data. This can fully reveal the structural surface characteristics of the slope, such as joints and cracks, and improve the accuracy and comprehensiveness of the structural surface feature extraction. Through the structural surface trend statistics, the trend distribution of the slope structural surface can be accurately analyzed. By clustering and spatially correlating the structural surface direction distribution data, the structural surface data can be effectively organized and associated. This makes the structural surface data more logical and systematic. By combining the stress field evolution and weak surface identification, the stability of the slope can be evaluated and predicted, which enables the structural characteristic data of the slope to better serve the stability analysis and disaster prevention of the slope.

[0134] Preferably, step S5 comprises the following steps:

[0135] Step S51: stratifying the hierarchical characteristic data of the slope to obtain stratified slope data, and extracting surface point cloud from the stratified slope data to obtain discrete surface point cloud data of the slope;

[0136] Specifically, the hierarchical feature data of the slope can be imported into Python, and the array slicing function of NumPy can be used to divide the data into different hierarchical data according to the hierarchical identifiers in the hierarchical feature data. For example, the hierarchical feature data of the slope contains three levels: surface, middle and deep. Through array slicing operations, the surface data, middle data and deep data are extracted respectively. Surface point cloud extraction is performed on the layered slope data. Cluster analysis is performed on the point cloud in the surface data using SciPy's clustering algorithm, such as DBSCAN (Density-Based Spatial Clustering of Applications with Noise). The parameters of the DBSCAN algorithm are set, such as a neighborhood radius of 0.1 meters and a minimum number of points of 10, to identify dense areas and discrete points in the surface point cloud. Through clustering analysis, discrete surface point cloud data of the slope are extracted, which contain surface terrain feature points and structural feature points.

[0137] Step S52: reconstructing the surface of the discrete surface point cloud data of the slope to obtain a spatial surface model of the slope;

[0138] Specifically, you can import discrete surface point cloud data into MeshLab, start MeshLab's surface reconstruction tool, select the Poisson surface reconstruction algorithm, and during the reconstruction process, set the algorithm parameters, such as the depth is 9, that is, the maximum depth of the octree is 9; at the same time, set the normal vector consistency parameter to 1 to ensure that the normal vector of the reconstructed surface is consistent with the normal vector in the point cloud data. MeshLab gradually constructs the surface of the slope by calculating the normal vector field of the point cloud data and solving the Poisson equation. For example, in a corner area of ​​the slope, the surface reconstruction results show clear corner shapes and edge details. Finally, the spatial surface model of the slope is obtained, which is presented in the form of a three-dimensional mesh.

[0139] Step S53: extracting middle-layer features from the slope space surface model to obtain middle-layer feature data of the slope space, and performing implicit surface middle-layer reconstruction on the middle-layer feature data of the slope space to obtain a middle-layer model of the slope space;

[0140] Specifically, the spatial surface model of the slope can be imported into MATLAB, and the image processing toolbox in MATLAB can be used to extract the middle-layer features of the surface model. The Laplacian of Gaussian (LoG) operator is selected as the feature extraction operator. The LoG operator can detect the edge and curvature features in the model. Set the parameters of the LoG operator, such as σ (standard deviation) to 2 pixels. For example, in a rock layer area of ​​the slope, the LoG operator can accurately extract the edge features and curvature change features of the rock layer, and obtain the middle-layer feature data of the area. Using the implicit surface reconstruction function in MATLAB, such as the isosurface function, according to the value of the middle-layer feature data, the isovalue surface is extracted as an implicit surface. Set the isovalue threshold to 0.5, that is, extract the isovalue surface with the middle-layer feature data value of 0.5. Through the above steps, the spatial middle-layer model of the slope is obtained.

[0141] Step S54: performing deep interpolation grid division on the slope space middle layer model to obtain the slope space deep layer grid, and performing deep reconstruction on the slope space deep layer grid to obtain the slope space deep layer model;

[0142] Specifically, the middle-layer model of the slope space can be imported into ANSYS, and the meshing tool of ANSYS can be used to perform deep interpolation meshing on the middle-layer model. Select tetrahedral mesh as the mesh type, set the mesh size parameters, such as the maximum mesh size is 0.5 meters, and the minimum mesh size is 0.1 meters. For example, in a steep area of ​​the slope, the mesh size is small during meshing; while in the gentle area of ​​the slope, the mesh size is larger. Through meshing, the deep mesh of the slope space is obtained. Then, the finite element analysis function of ANSYS is used to optimize and reconstruct the deep mesh. For example, optimize the shape and distribution of the mesh, and eliminate singular points and too small mesh units in the mesh. Through deep reconstruction, the deep model of the slope space is obtained.

[0143] Step S55: integrating the slope space surface model, the slope space middle layer model and the slope space deep layer model to obtain a complete slope three-dimensional model.

[0144] Specifically, the slope space surface model, the slope space middle model and the slope space deep model can be imported into SolidWorks respectively, and the three models can be accurately aligned and combined using the assembly function of SolidWorks. First, the slope space surface model is selected as the reference and placed at the bottom of the assembly to ensure its correspondence with the actual terrain. Then, the slope space middle model is placed above the surface model, and the position and rotation angle of the middle model are adjusted to match the edge and structural features of the surface model. For example, in a corner area of ​​the slope, the edge of the middle model is aligned with the corner edge of the surface model. Finally, the slope space deep model is placed below the middle model, and the depth and range of the deep model are adjusted to connect it with the bottom structure of the middle model. For example, in a rock layer area of ​​the slope, the rock layer of the deep model is connected to the rock layer of the middle model to form a complete rock structure. Through the above steps, a complete slope three-dimensional model can be obtained, which is presented in the form of a unified assembly.

[0145] The present invention can effectively separate and reconstruct the different levels of features of the slope by performing layered processing on the hierarchical feature data of the slope. This enables the model to more finely reflect the hierarchical structure and feature changes of the slope, and improves the detail expression and accuracy of the model. By using the surface point cloud data for surface reconstruction, the external morphology and surface features of the slope can be accurately reconstructed. This can capture the subtle changes and local features of the slope. Through implicit surface reconstruction and deep grid interpolation reconstruction, the internal structural features of the slope can be effectively expressed. Implicit surface reconstruction can smoothly represent the complex surface features of the middle layer, while interpolation reconstruction can accurately depict the structural details of the deep layer, so that the middle and deep models can better reflect the internal structure and hierarchical relationship of the slope, and improve the structural expression ability of the model. By integrating the surface, middle and deep models, the complete three-dimensional slope model obtained can effectively integrate and uniformly express the external morphology, internal structure and hierarchical features of the slope.

[0146] Preferably, the present invention further provides a three-dimensional modeling system for slopes in difficult mountainous areas based on multi-source data fusion, which is used to execute the three-dimensional modeling method for slopes in difficult mountainous areas based on multi-source data fusion as described above. The three-dimensional modeling system for slopes in difficult mountainous areas based on multi-source data fusion comprises:

[0147] The data acquisition module is used to use a drone cluster to collect data from multiple angles on the mountain slopes to obtain multi-angle image data of the slopes; perform ground laser scanning on the mountain slopes to obtain a slope point cloud data set;

[0148] The structural detection module is used to detect seismic reflection waves on mountain slopes to obtain seismic reflection data of the slopes; to detect electromagnetic tomography on mountain slopes to obtain electromagnetic tomography data of the slopes; to fuse and invert the seismic reflection data of the slopes with the electromagnetic tomography data of the slopes to obtain the internal structure data of the slopes;

[0149] The data registration and unification module is used to roughly register the multi-angle image data of the slope with the slope point cloud data set to obtain the initial image-point cloud registration data; perform tensor field interpolation fine registration on the initial image-point cloud registration data to obtain the image-point cloud registration data; perform spatial unified transformation on the image-point cloud registration data and the internal structure data of the slope to obtain the slope image-point cloud unified data;

[0150] The segmentation module is used to perform improved watershed segmentation on the unified data of slope image and point cloud to obtain slope unit division data; perform structural surface recognition on the slope unit division data to obtain slope structural surface feature data; perform feature extraction on the slope structural surface feature data and the slope internal structure data to obtain slope hierarchical feature data;

[0151] The three-dimensional reconstruction module is used to stratify the hierarchical characteristic data of the slope to obtain the slope stratification data; to reconstruct the surface of the slope stratification data to obtain the slope spatial surface model; to reconstruct the mountain slope in three dimensions based on the slope spatial surface model to obtain a complete slope three-dimensional model.

[0152] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0153] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A three-dimensional modeling method for slopes in difficult mountainous areas based on multi-source data fusion, characterized in that: The following steps are involved: Step S1: Use a drone cluster to collect multi-angle data of the mountain slope to obtain multi-angle image data of the slope; perform ground laser scanning on the mountain slope to obtain a slope point cloud data set; Step S2: Perform seismic reflection wave detection on the mountain slope to obtain seismic reflection data of the slope; perform electromagnetic tomography detection on the mountain slope to obtain electromagnetic tomography data of the slope; fuse and invert the seismic reflection data of the slope with the electromagnetic tomography data of the slope to obtain the internal structure data of the slope; Step S3: Coarsely align the multi-angle image data of the slope with the point cloud data set of the slope to obtain initial image-point cloud registration data; perform tensor field interpolation fine alignment on the initial image-point cloud registration data to obtain image-point cloud registration data; perform spatial unified transformation on the image-point cloud registration data and the internal structure data of the slope to obtain unified slope image-point cloud data; Step S4: performing improved watershed segmentation on the slope image-point cloud unified data to obtain slope unit division data; performing structural surface recognition on the slope unit division data to obtain slope structural surface feature data; performing feature extraction on the slope structural surface feature data and the slope internal structure data to obtain slope hierarchical feature data; Step S5: Layer the slope hierarchical feature data to obtain slope layered data; reconstruct the surface of the slope layered data to obtain a slope spatial surface model; and reconstruct the mountain slope in three dimensions based on the slope spatial surface model to obtain a complete slope three-dimensional model.

2. The three-dimensional modeling method for slopes in difficult mountainous areas based on multi-source data fusion according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: collecting a side panoramic image of the mountain slope to obtain a side panoramic image of the slope, and performing regional mission planning for the drone cluster based on the side panoramic image of the slope to obtain a drone flight mission; Step S12: assigning routes to the drone cluster based on the drone flight mission to obtain drone route planning data; Step S13: Performing an aerial laser rangefinder scan on the side of the mountain slope to obtain slope characteristic data; Step S14: highly stratify the UAV route planning data according to the slope characteristic data to obtain UAV stratified acquisition data; Step S15: using a drone cluster to collect multi-angle data on the mountain slope according to the layered data collected by the drone, and obtaining multi-angle image data of the slope; Step S16: Perform laser radar site planning on the mountain slope according to the slope gradient characteristic data to obtain laser scanning site distribution data, and perform multi-site scanning on the mountain slope according to the laser scanning site distribution data to obtain a slope point cloud data set.

3. The method for three-dimensional modeling of slopes in difficult mountainous areas based on multi-source data fusion according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: Arrange seismic wave sources on the mountain slope to obtain seismic source arrangement data; Step S22: arranging receiver arrays on the mountain slopes according to the seismic source layout data to obtain slope receiver layout data; Step S23: configuring the trigger timing of the receiver array according to the slope receiver layout data to obtain receiver trigger sequence data; Step S24: Exciting the mountain slope with seismic waves according to the receiver trigger sequence data to obtain slope seismic wave data, and identifying the first arrival wave of the slope seismic wave data to obtain slope wave arrival time data; Step S25: performing travel time inversion on the slope seismic wave data according to the slope wave arrival time data to obtain seismic wave velocity structure data, and performing waveform inversion on the seismic wave velocity structure data to obtain slope seismic reflection data; Step S26: Perform electromagnetic tomography detection on the mountain slope to obtain slope electromagnetic tomography data, and fuse and invert the slope seismic reflection data and the slope electromagnetic tomography data to obtain slope internal structure data.

4. The method for three-dimensional modeling of slopes in difficult mountainous areas based on multi-source data fusion according to claim 3 is characterized in that: Step S26 includes the following steps: Step S261: Arranging electromagnetic transmitting sources on the mountain slope to obtain electromagnetic source arrangement data, and arranging receiving electrodes on the mountain slope according to the electromagnetic source arrangement data to obtain electrode arrangement data; Step S262: configuring the excitation waveform of the electromagnetic emission source according to the electrode layout data to obtain electromagnetic excitation waveform data; Step S263: performing electromagnetic field measurement on the receiving electrode according to the electromagnetic excitation waveform data to obtain slope electromagnetic field data; Step S264: invert and reconstruct the slope electromagnetic field data to obtain slope conductivity distribution data; Step S265: reconstructing the slope electromagnetic data according to the slope conductivity distribution data to obtain slope electromagnetic tomography data; Step S266: fusing and inverting the slope seismic reflection data and the slope electromagnetic tomography data to obtain the slope internal structure data.

5. The method for three-dimensional modeling of slopes in difficult mountainous areas based on multi-source data fusion according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: extracting feature points from the multi-angle image data of the slope to obtain a slope image feature point set, and extracting feature points from the slope point cloud data set to obtain a slope point cloud feature point set; Step S32: matching the slope image feature point set with the slope point cloud feature point set to obtain the slope initial matching point pair data; Step S33: screening the initial matching point pair data of the slope to obtain the effective matching point pair data of the slope; Step S34: performing ICP iterative registration on the slope image feature point set and the slope point cloud feature point set according to the slope effective matching point pair data to obtain a feature point registration transformation matrix; Step S35: spatially transform the slope multi-angle image data and the slope point cloud data set according to the feature point registration transformation matrix to obtain initial image-point cloud registration data; Step S36: Perform tensor field interpolation precise registration on the initial image-point cloud registration data to obtain image-point cloud registration data, and perform spatial unified transformation on the image-point cloud registration data and the slope internal structure data to obtain slope image-point cloud unified data.

6. The method for three-dimensional modeling of slopes in difficult mountainous areas based on multi-source data fusion according to claim 5 is characterized in that: Step S36 includes the following steps: Step S361: constructing a tensor field for the initial image-point cloud registration data to obtain image-point cloud tensor field data; Step S362: performing main direction decomposition on the image-point cloud tensor field data to obtain main direction data of the image-point cloud tensor; Step S363: constructing image-point cloud radial basis functions for the initial image-point cloud registration data according to the main direction data of the image-point cloud tensor to obtain image-point cloud interpolation basis functions; Step S364: performing precise registration on the initial image-point cloud registration data according to the image-point cloud interpolation basis function to obtain image-point cloud registration data; Step S365: performing coordinate uniform conversion on the image-point cloud registration data and the slope internal structure data to obtain initial slope image-point cloud unified data; Step S366: Perform spatial registration evaluation on the initial slope image-point cloud unified data to obtain registration accuracy evaluation data, and perform registration error compensation on the initial slope image-point cloud unified data based on the registration accuracy evaluation data to obtain slope image-point cloud unified data.

7. The method for three-dimensional modeling of slopes in difficult mountainous areas based on multi-source data fusion according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: performing spatial gradient distribution recognition on the slope image-point cloud unified data to obtain slope spatial gradient field data; Step S42: Selecting marker points from the slope spatial gradient field data to obtain slope watershed marker data; Step S43: performing distance transformation on the slope watershed marker data to obtain a slope watershed distance map; Step S44: performing watershed growth diffusion on the marked points in the slope watershed marked data according to the slope watershed distance map to obtain the initial segmentation data of the slope; Step S45: performing boundary optimization on the initial segmentation data of the slope to obtain slope unit division data; Step S46: performing structural surface recognition on the slope unit division data to obtain slope structural surface feature data, and performing feature extraction on the slope structural surface feature data and the slope internal structure data to obtain slope hierarchical feature data.

8. The method for three-dimensional modeling of slopes in difficult mountainous areas based on multi-source data fusion according to claim 7 is characterized in that: Step S46 includes the following steps: Step S461: Calculate the surface curvature of the slope unit division data to obtain slope surface curvature distribution data; Step S462: extracting height difference characteristic lines of the mountain slope according to the slope surface curvature distribution data to obtain the slope height difference characteristic lines; Step S463: performing structural surface trend statistics on the slope height difference characteristic line to obtain structural surface direction distribution data; Step S464: clustering the structural surface direction distribution data to obtain slope structural surface family data; Step S465: performing spatial correlation measurement on the slope structural surface family data to obtain slope structural surface correlation data; Step S466: combining the structural surfaces according to the slope structural surface correlation data to obtain the slope structural surface characteristic data; Step S467: performing stress field evolution on the slope structural surface characteristic data to obtain slope stress field data, and performing weak surface identification on the mountain slope according to the slope stress field data to obtain slope weak surface data; Step S468: Perform stability assessment on the weak surface data of the slope to obtain weak surface stability assessment data, and perform multi-scale fusion of the weak surface stability assessment data and the internal structure data of the slope to obtain hierarchical characteristic data of the slope.

9. The method for three-dimensional modeling of slopes in difficult mountainous areas based on multi-source data fusion according to claim 1 is characterized in that: Step S5 includes the following steps: Step S51: stratifying the hierarchical characteristic data of the slope to obtain stratified slope data, and extracting surface point cloud from the stratified slope data to obtain discrete surface point cloud data of the slope; Step S52: reconstructing the surface of the discrete surface point cloud data of the slope to obtain a spatial surface model of the slope; Step S53: extracting middle-layer features from the slope space surface model to obtain middle-layer feature data of the slope space, and performing implicit surface middle-layer reconstruction on the middle-layer feature data of the slope space to obtain a middle-layer model of the slope space; Step S54: performing deep interpolation grid division on the slope space middle layer model to obtain the slope space deep layer grid, and performing deep reconstruction on the slope space deep layer grid to obtain the slope space deep layer model; Step S55: integrating the slope space surface model, the slope space middle layer model and the slope space deep layer model to obtain a complete slope three-dimensional model.

10. A three-dimensional modeling system for slopes in difficult mountainous areas based on multi-source data fusion, characterized in that: Used to execute the three-dimensional modeling method of slopes in difficult mountainous areas based on multi-source data fusion as claimed in claim 1, the three-dimensional modeling system of slopes in difficult mountainous areas based on multi-source data fusion comprises: The data acquisition module is used to use a drone cluster to collect data from multiple angles on the mountain slopes to obtain multi-angle image data of the slopes; perform ground laser scanning on the mountain slopes to obtain a slope point cloud data set; The structural detection module is used to detect seismic reflection waves on mountain slopes to obtain seismic reflection data of the slopes; to detect electromagnetic tomography on mountain slopes to obtain electromagnetic tomography data of the slopes; to fuse and invert the seismic reflection data of the slopes with the electromagnetic tomography data of the slopes to obtain the internal structure data of the slopes; The data registration and unification module is used to roughly register the multi-angle image data of the slope with the slope point cloud data set to obtain the initial image-point cloud registration data; perform tensor field interpolation fine registration on the initial image-point cloud registration data to obtain the image-point cloud registration data; perform spatial unified transformation on the image-point cloud registration data and the internal structure data of the slope to obtain the slope image-point cloud unified data; The segmentation module is used to perform improved watershed segmentation on the slope image-point cloud unified data to obtain slope unit division data; Perform structural surface recognition on the slope unit division data to obtain slope structural surface feature data; perform feature extraction on the slope structural surface feature data and the slope internal structure data to obtain slope hierarchical feature data; The three-dimensional reconstruction module is used to stratify the hierarchical characteristic data of the slope to obtain the slope stratification data; to reconstruct the surface of the slope stratification data to obtain the slope spatial surface model; to reconstruct the mountain slope in three dimensions based on the slope spatial surface model to obtain a complete slope three-dimensional model.

Images