Geological survey method and system based on artificial intelligence

Abstract

The invention is suitable for the technical field of geological survey, and particularly relates to a geological survey method and system based on artificial intelligence, and the method comprises the steps: obtaining a to-be-surveyed water area map, and constructing and training an artificial intelligence model; surveying equipment parameters are called, surveying points are constructed according to the to-be-surveyed water area map, a surveying equipment moving path is generated based on the surveying points, and single-point geological surveying data are obtained; constructing a three-dimensional coordinate system, marking survey data, and generating a single-point survey coordinate dot matrix; and fusing the single-point exploration coordinate dot matrixes to obtain a fused elevation dot matrix, identifying an abnormal region contained in the fused elevation dot matrix, carrying out information additional recording, and generating a geological exploration model. According to the method, the surveying path is constructed based on the to-be-surveyed water area map, and the surveying ranges corresponding to the two adjacent surveying processes are overlapped during surveying, so that the riverbed surveying is realized from different directions, the automatic recognition of the riverbed features is realized by using the artificial intelligence model, and the surveying convenience is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of geological survey, and in particular relates to a geological survey method and system based on artificial intelligence. Background Art

[0002] Riverbed survey is a detailed investigation activity specifically targeting the river bottom topography, geological conditions and sediment composition, aiming to fully understand the structural characteristics of the riverbed and its changes over time. This work not only involves accurate measurement of the surface morphology of the riverbed, but also includes analysis of its deep material composition, lithology and particle grading. By using modern technical means such as lidar, sonar detection, drilling sampling and field sampling, riverbed survey can provide key basic data support for flood prevention and disaster reduction, water resources management, waterway maintenance, water conservancy project construction and ecological and environmental protection.

[0003] In the current riverbed survey method, ships are generally used to carry out survey equipment. During the operation, professional surveying personnel are required to conduct on-site control, which results in high survey costs and great operational difficulty. Summary of the invention

[0004] The purpose of the present invention is to provide a geological survey method based on artificial intelligence, aiming to solve the problems that in the current riverbed survey method, a ship is generally used to carry the survey equipment for detection, and professional surveying personnel are required to perform on-site control during the operation, resulting in high survey costs and great operational difficulty.

[0005] The present invention is achieved by a geological survey method based on artificial intelligence, the method comprising: Obtain a map of the water area to be surveyed, and construct and train an artificial intelligence model, wherein the artificial intelligence model is used to identify structural features of the riverbed bottom; Retrieve survey equipment parameters, construct survey points according to the map of the water area to be surveyed, generate survey equipment movement paths based on the survey points, obtain single-point geological survey data, and ensure that the coverage area overlap rate of adjacent single-point geological survey data is higher than 50%; Construct a three-dimensional coordinate system based on the moving path of the survey equipment, mark the survey data based on the single-point geological survey data, and generate a single-point survey coordinate lattice; The single-point survey coordinate matrix is ​​fused to obtain a fused elevation matrix, the abnormal areas contained therein are identified, the information is supplemented, and a geological survey model is generated through an artificial intelligence model.

[0006] Preferably, the steps of retrieving survey equipment parameters, constructing survey points according to the map of the water area to be surveyed, generating a moving path of the survey equipment based on the survey points, and obtaining single-point geological survey data specifically include: Obtaining the maximum survey distance of the survey equipment, determining the maximum survey height based on the maximum survey distance, and constructing a survey grid; Selecting multiple survey points in the map of the water area to be surveyed based on the survey grid, determining coordinate information of the survey points, and constructing a moving path of the survey equipment based on the coordinate information; The survey equipment is controlled to move according to its moving path. When the survey equipment arrives at the survey point, point-by-point measurements are performed according to the survey grid to obtain single-point geological survey data.

[0007] Preferably, the steps of constructing a three-dimensional coordinate system based on the moving path of the survey equipment, marking the survey data based on the single-point geological survey data, and generating a single-point survey coordinate lattice specifically include: Construct a three-dimensional coordinate system, construct a water plane according to the map of the water area to be surveyed, and mark the moving path of the survey equipment in the three-dimensional coordinate system; Extract each set of measurement data from the single-point geological survey data, and extract the elevation information, azimuth information and distance information contained therein; Data is marked once in the three-dimensional coordinate system according to each set of measurement data to obtain a single-point survey coordinate matrix.

[0008] Preferably, the steps of fusing the single-point survey coordinate lattices to obtain a fused elevation lattice, identifying the abnormal areas contained therein, supplementing the information, and generating a geological survey model through an artificial intelligence model specifically include: The single-point survey coordinate matrix is ​​fused to obtain a fused elevation matrix, and the fused elevation matrix is ​​projected onto the water plane; The number of projection points contained in each survey grid is counted. When the number of projection points is lower than the preset value, the area corresponding to the survey grid is regarded as an abnormal area. A supplementary survey control path is generated based on the location of the abnormal area. The survey equipment records information according to the supplementary survey control path, and the riverbed characteristics are identified through the artificial intelligence model to obtain a geological survey model.

[0009] Preferably, when supplementing the information, the surveying equipment obtains the measurement data by vertical measurement.

[0010] Another object of the present invention is to provide a geological survey system based on artificial intelligence, the system comprising: A map acquisition module is used to acquire a map of the water area to be surveyed, and to construct and train an artificial intelligence model, wherein the artificial intelligence model is used to identify structural features of the riverbed bottom; The path construction module is used to retrieve the parameters of the survey equipment, construct the survey points according to the map of the water area to be surveyed, generate the moving path of the survey equipment based on the survey points, obtain the single-point geological survey data, and the overlap rate of the coverage area corresponding to the adjacent single-point geological survey data is higher than 50%; The single-point survey module is used to construct a three-dimensional coordinate system based on the moving path of the survey equipment, mark the survey data based on the single-point geological survey data, and generate a single-point survey coordinate lattice; The survey model construction module is used to fuse the single-point survey coordinate lattices to obtain the fused elevation lattices, identify the abnormal areas contained therein, supplement the information, and generate a geological survey model through an artificial intelligence model.

[0011] Preferably, the path construction module includes: A survey grid construction unit, used to obtain a maximum survey distance of the survey equipment, determine a maximum survey height based on the maximum survey distance, and construct a survey grid; A path construction unit, used to select a plurality of survey points in the map of the water area to be surveyed based on the survey grid, determine the coordinate information of the survey points, and construct a moving path of the survey equipment based on the coordinate information; The single-point measurement unit is used to control the movement of the survey equipment according to the moving path of the survey equipment. When the survey equipment arrives at the survey point, it performs point-by-point measurement according to the survey grid to obtain single-point geological survey data.

[0012] Preferably, the single-point survey module includes: A coordinate system construction unit, used to construct a three-dimensional coordinate system, construct a water plane according to the map of the water area to be surveyed, and mark the moving path of the survey equipment in the three-dimensional coordinate system; A measurement data extraction unit is used to extract each set of measurement data in the single-point geological survey data, and extract the elevation information, azimuth information and distance information contained therein; The coordinate lattice construction unit is used to mark the data once in the three-dimensional coordinate system according to each set of measurement data to obtain a single-point survey coordinate lattice.

[0013] Preferably, the survey model building module includes: The dot matrix fusion unit is used to fuse the single-point survey coordinate dot matrix to obtain a fused elevation dot matrix, and project the fused elevation dot matrix into the water plane; The abnormal area identification unit is used to count the number of projection points contained in each survey grid. When the number of projection points is lower than a preset value, the area corresponding to the survey grid is regarded as an abnormal area. The feature recognition unit is used to generate a supplementary survey control path based on the location of the abnormal area. The survey equipment records information according to the supplementary survey control path, identifies the riverbed features through the artificial intelligence model, and obtains a geological survey model.

[0014] Preferably, when supplementing the information, the surveying equipment obtains the measurement data by vertical measurement.

[0015] The present invention provides a geological survey method based on artificial intelligence, which constructs a survey path based on a map of the water area to be surveyed. When conducting the survey, the survey ranges corresponding to two adjacent survey processes overlap, thereby realizing the survey of the riverbed from different directions. The artificial intelligence model is used to realize automatic recognition of riverbed features, thereby improving the convenience of the survey. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of a geological survey method based on artificial intelligence provided by an embodiment of the present invention; Figure 2 A flowchart of the steps of retrieving survey equipment parameters, constructing survey points according to a map of the water area to be surveyed, generating a moving path of the survey equipment based on the survey points, and obtaining single-point geological survey data provided by an embodiment of the present invention; Figure 3 A flowchart of the steps of constructing a three-dimensional coordinate system based on the moving path of the survey equipment, marking the survey data based on the single-point geological survey data, and generating a single-point survey coordinate lattice provided by an embodiment of the present invention; Figure 4 A flowchart of the steps of fusing single-point survey coordinate lattices to obtain a fused elevation lattice, identifying abnormal areas contained therein, supplementing information, and generating a geological survey model through an artificial intelligence model provided by an embodiment of the present invention; Figure 5 An architecture diagram of a geological survey system based on artificial intelligence provided by an embodiment of the present invention; Figure 6 An architecture diagram of a path construction module provided by an embodiment of the present invention; Figure 7 An architectural diagram of a single-point survey module provided in an embodiment of the present invention; Figure 8 An architectural diagram of a survey model building module provided by an embodiment of the present invention; Fig. 9 A schematic diagram of surveying adjacent survey points provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] like Figure 1 As shown, it is a flow chart of a geological survey method based on artificial intelligence provided by an embodiment of the present invention, and the method comprises: S100, obtaining a map of the water area to be surveyed, building and training an artificial intelligence model, wherein the artificial intelligence model is used to identify structural features of the riverbed bottom.

[0019] In this step, a map of the water area to be surveyed is obtained. The map of the water area to be surveyed records the boundary coordinates of the water area to be surveyed. The coordinates of any point on the boundary of the water area can be determined based on the map of the water area to be surveyed. The artificial intelligence model is used to identify the characteristics of the bottom of the riverbed. Specifically, the elevation data obtained by processing a convolutional neural network (CNN) can be used to identify the terrain features of the riverbed, such as deep troughs, shallow ponds, and sand dunes.

[0020] S200, retrieve survey equipment parameters, construct survey points according to the map of the water area to be surveyed, generate a moving path of the survey equipment based on the survey points, obtain single-point geological survey data, and the overlap rate of coverage areas corresponding to adjacent single-point geological survey data is higher than 50%.

[0021] In this step, the survey equipment parameters are retrieved, and the survey equipment parameters at least include the maximum survey distance. The survey equipment can be an airborne LiDAR, which is loaded on a drone and driven to move by the drone. The airborne LiDAR has an adjustment module for controlling the airborne LiDAR to measure distances in different directions. According to the map of the water area to be surveyed and the survey equipment parameters, multiple survey points are selected on the map of the water area to be surveyed, and the multiple survey points are connected to obtain the moving path of the survey equipment. When conducting the survey, the drone is controlled to fly along the moving path of the survey equipment. When the drone arrives at the survey point, the water area below is surveyed to obtain single-point geological survey data. When conducting the survey, the water areas corresponding to two adjacent survey points are kept overlapping, and the overlap rate is at least higher than 50%, so as to realize the survey in two directions for each detection position and improve the accuracy of the survey.

[0022] S300, constructing a three-dimensional coordinate system based on the moving path of the surveying equipment, marking the surveying data based on the single-point geological surveying data, and generating a single-point surveying coordinate lattice.

[0023] In this step, a three-dimensional coordinate system is constructed based on the moving path of the survey equipment. The moving path of the survey equipment is drawn in the three-dimensional coordinate system. At the same time, its edge is drawn in a plane of the three-dimensional coordinate system according to the map of the water area to be surveyed, that is, the coordinates of the edge of the water area to be surveyed are extracted, and its Z-axis coordinate is set to the same value, such as 0, so that all points on the edge are located in the same horizontal plane, and the water area plane is obtained. Then, the survey data corresponding to each survey point is marked in the three-dimensional coordinate system, thereby forming a dot matrix in the three-dimensional coordinate system, and each survey point corresponds to a single-point survey coordinate dot matrix.

[0024] S400, fuses the single-point survey coordinate lattice to obtain a fused elevation lattice, identifies the abnormal areas contained therein, supplements the information, and generates a geological survey model through an artificial intelligence model.

[0025] In this step, the single-point survey coordinate matrix is ​​fused, such as Fig. 9 As shown, when the latter single-point survey coordinate lattice is generated, it will overlap with the previous single-point survey coordinate lattice, that is, the purpose of detecting the same position from multiple directions is achieved. Therefore, except for the first survey point and the last survey point, each survey position in other survey points is explored twice from at least two angles to form a complete detection result, avoiding the problem of insufficient slope detection density due to one-way detection. The fused elevation lattice is identified through the artificial intelligence model, and the riverbed features contained therein are identified. The geological survey model is generated by connecting the fused elevation lattices, and the various riverbed features in the geological survey model are marked. Specifically, different colors can be used to distinguish and represent them.

[0026] like Figure 2 As shown, as a preferred embodiment of the present invention, the steps of retrieving survey equipment parameters, constructing survey points according to the map of the water area to be surveyed, generating a moving path of the survey equipment based on the survey points, and obtaining single-point geological survey data specifically include: S201, obtaining a maximum survey distance of a survey device, determining a maximum survey height based on the maximum survey distance, and constructing a survey grid.

[0027] In this step, the maximum survey distance of the survey equipment is obtained. The maximum survey distance is the maximum detection distance L of the airborne LiDAR. max , the maximum survey height is based on the maximum detection distance L max And the maximum detection angle θ of the airborne LiDAR max Determine the maximum survey height H max =L max *cos(θ max ), then the maximum detection width B max = 2*L max *sin(θ max ), then the maximum detection range of the airborne LiDAR is a radius of B max A circular area is constructed in which a maximum inscribed square is constructed with a side length L = B max , taking the maximum inscribed square as the survey range of a single survey point to construct a survey grid, that is, dividing the maximum inscribed square into multiple grids, and taking the center of each grid as a detection position, thereby constructing a detection matrix, and the detection point is located directly above the detection matrix.

[0028] S202, selecting a plurality of survey points in the map of the water area to be surveyed based on the survey grid, determining coordinate information of the survey points, and constructing a moving path of the survey equipment based on the coordinate information.

[0029] In this step, multiple survey points are selected in the water area map to be surveyed based on the survey grid, and each survey point corresponds to a grid with a side length of L= B max The coordinate information of the survey points is recorded in the square area, and the moving path of the survey equipment is generated according to the sequence of the survey points.

[0030] S203, controlling the survey equipment to move according to the moving path of the survey equipment, and when the survey equipment arrives at the survey point, performing point-by-point measurement according to the survey grid to obtain single-point geological survey data.

[0031] In this step, the survey equipment is controlled to move according to the moving path of the survey equipment. The UAV flies along the moving path of the survey equipment and hovers at the coordinate information corresponding to the survey point. At this time, the airborne LiDAR starts to send detection light to each detection position in the detection grid, and measures each detection position in the square area once. Each measurement obtains a measurement distance, and the measurement angle (including angle and azimuth) at this time is recorded. After the measurement of a survey point is completed, the single-point geological survey data corresponding to the detection point is obtained.

[0032] like Figure 3 As shown, as a preferred embodiment of the present invention, the steps of constructing a three-dimensional coordinate system based on the moving path of the surveying equipment, marking the surveying data based on the single-point geological survey data, and generating a single-point surveying coordinate lattice specifically include: S301, constructing a three-dimensional coordinate system, constructing a water plane according to the map of the water area to be surveyed, and marking the moving path of the survey equipment in the three-dimensional coordinate system.

[0033] In this step, a three-dimensional coordinate system is constructed, and the coordinate information (X, Y, Z) of the edge of the water area on the map of the water area to be surveyed is extracted. The Z value is normalized and set to the same value, such as 0, and the normalized coordinates are marked in the three-dimensional coordinate system. At this time, the edge of the water area is projected into the plane where the X-axis and the Y-axis are located, and the moving path of the survey equipment is marked in the three-dimensional coordinate system.

[0034] S302, extracting each set of measurement data in the single-point geological survey data, and extracting the elevation information, azimuth information and distance information contained therein.

[0035] S303, marking each set of measurement data in a three-dimensional coordinate system to obtain a single-point survey coordinate matrix.

[0036] In this step, each set of measurement data in the single-point geological survey data is extracted. Since the detection grids corresponding to adjacent survey points have some overlapping detection positions, the overlapping detection positions account for more than 50%. Therefore, the same detection position is detected by at least two survey points, avoiding the problem of obstruction of detection light caused by the slope of the riverbed. The elevation information, azimuth information and distance information contained therein are extracted, the position is marked, and the coordinates corresponding to the current detection position are determined, thereby forming a detection point in the three-dimensional coordinate system. Recording its coordinates will form a single-point survey coordinate lattice, which is a lattice composed of all detection points corresponding to a survey point.

[0037] like Figure 4 As shown, as a preferred embodiment of the present invention, the steps of fusing the single-point survey coordinate lattice to obtain a fused elevation lattice, identifying the abnormal area contained therein, supplementing the information, and generating a geological survey model through an artificial intelligence model specifically include: S401, fusing the single-point survey coordinate lattices to obtain a fused elevation lattice, and projecting the fused elevation lattice onto the water plane.

[0038] In this step, the single-point survey coordinate matrix is ​​fused, that is, all single-point survey coordinate matrixes are marked in the same three-dimensional coordinate system to form a global fused elevation matrix. When there are obstacles on the riverbed, such as steep slopes and other structures, it will affect the extension of the detection light, resulting in some areas not being detected. At this time, the fused elevation matrix is ​​projected into the water plane, and the detection grid is also projected into the water plane.

[0039] S402, counting the number of projection points contained in each survey grid, when the number of projection points is lower than a preset value, the area corresponding to the survey grid is regarded as an abnormal area.

[0040] In this step, the number of projection points contained in each survey grid is counted. When the number of projection points in the survey grid is lower than the preset value, it means that the detection density of the area is too low or cannot be detected. In this case, the survey grid is regarded as an abnormal area.

[0041] S403, generating a supplementary survey control path based on the location of the abnormal area, the survey equipment performs information supplementation according to the supplementary survey control path, identifies the riverbed characteristics through the artificial intelligence model, and obtains a geological survey model.

[0042] In this step, a supplementary survey control path is generated based on the location of the abnormal area, all abnormal areas are marked, and their coordinates are extracted. Global path planning is performed according to the location of all abnormal areas to generate a supplementary survey control path. The UAV flies according to the supplementary survey control path, and performs supplementary detection on each survey grid to obtain supplementary survey information, which is supplemented into the three-dimensional coordinate system. Surface fitting is performed based on the supplemented fused elevation point matrix to obtain a geological survey model, and the riverbed features are identified through the artificial intelligence model, and the riverbed features are marked in the model. When supplementing information, the survey equipment uses vertical measurement to obtain measurement data to ensure that the number of surveys in each survey grid reaches the preset value.

[0043] like Figure 5 As shown, a geological survey system based on artificial intelligence is provided in an embodiment of the present invention, and the system includes: The map acquisition module 100 is used to acquire a map of the water area to be surveyed, and to construct and train an artificial intelligence model, wherein the artificial intelligence model is used to identify structural features of the riverbed bottom.

[0044] In this system, the map acquisition module 100 acquires a map of the water area to be surveyed, which records the boundary coordinates of the water area to be surveyed. The coordinates of any point on the boundary of the water area can be determined based on the map of the water area to be surveyed. The artificial intelligence model is used to identify the characteristics of the bottom of the riverbed. Specifically, the elevation data obtained by processing a convolutional neural network (CNN) can be used to identify the terrain features of the riverbed, such as deep troughs, shallow ponds, and sand dunes.

[0045] The path construction module 200 is used to retrieve the survey equipment parameters, construct survey points according to the map of the water area to be surveyed, generate the survey equipment movement path based on the survey points, and obtain single-point geological survey data. The overlap rate of the coverage area corresponding to adjacent single-point geological survey data is higher than 50%.

[0046] In the present system, the path construction module 200 retrieves the parameters of the survey equipment, which at least include the maximum survey distance. The survey equipment may be an airborne LiDAR, which is loaded on a drone and driven to move by the drone. The airborne LiDAR is provided with an adjustment module for controlling the airborne LiDAR to measure distances in different directions. A plurality of survey points are selected on the map of the water area to be surveyed according to the map of the water area to be surveyed and the parameters of the survey equipment, and the plurality of survey points are connected to obtain a moving path of the survey equipment. When conducting a survey, the drone is controlled to fly along the moving path of the survey equipment. When the drone arrives at the survey point, the water area below is surveyed to obtain single-point geological survey data. When conducting a survey, the water areas corresponding to two adjacent survey points are kept overlapping, and the overlap rate is at least higher than 50%, thereby achieving surveys in two directions for each detection position and improving the accuracy of the survey.

[0047] The single-point survey module 300 is used to construct a three-dimensional coordinate system based on the moving path of the survey equipment, mark the survey data based on the single-point geological survey data, and generate a single-point survey coordinate lattice.

[0048] In this system, the single-point survey module 300 constructs a three-dimensional coordinate system based on the moving path of the survey equipment. In the three-dimensional coordinate system, the moving path of the survey equipment is drawn, and at the same time, its edge is drawn in a plane of the three-dimensional coordinate system according to the map of the water area to be surveyed, that is, the coordinates of the edge of the water area to be surveyed are extracted, and its Z-axis coordinate is set to the same value, such as 0, so that all points on the edge are located in the same horizontal plane, and the water area plane is obtained, and then the survey data corresponding to each survey point is marked in the three-dimensional coordinate system, thereby forming a dot matrix in the three-dimensional coordinate system, and each survey point corresponds to a single-point survey coordinate dot matrix.

[0049] The survey model construction module 400 is used to fuse the single-point survey coordinate lattices to obtain a fused elevation lattice, identify the abnormal areas contained therein, supplement the information, and generate a geological survey model through an artificial intelligence model.

[0050] In this system, the survey model building module 400 fuses the single-point survey coordinate matrix, such as Fig. 9 As shown, when the latter single-point survey coordinate lattice is generated, it will overlap with the previous single-point survey coordinate lattice, that is, the purpose of detecting the same position from multiple directions is achieved. Therefore, except for the first survey point and the last survey point, each survey position in other survey points is explored twice from at least two angles to form a complete detection result, avoiding the problem of insufficient slope detection density due to one-way detection. The fused elevation lattice is identified through the artificial intelligence model, and the riverbed features contained therein are identified. The geological survey model is generated by connecting the fused elevation lattices, and the various riverbed features in the geological survey model are marked. Specifically, different colors can be used to distinguish and represent them.

[0051] like Figure 6 As shown, as a preferred embodiment of the present invention, the path construction module 200 includes: The survey grid construction unit 201 is used to obtain the maximum survey distance of the survey equipment, determine the maximum survey height based on the maximum survey distance, and construct a survey grid.

[0052] In this module, the survey grid construction unit 201 obtains the maximum survey distance of the survey equipment, which is the maximum detection distance L of the airborne LiDAR. max , the maximum survey height is based on the maximum detection distance L max And the maximum detection angle θ of the airborne LiDARmax Determine the maximum survey height H max =L max *cos(θ max ), then the maximum detection width B max = 2*L max *sin(θ max ), then the maximum detection range of the airborne LiDAR is a radius of B max A circular area is constructed in which a maximum inscribed square is constructed with a side length L = B max , taking the maximum inscribed square as the survey range of a single survey point to construct a survey grid, that is, dividing the maximum inscribed square into multiple grids, and taking the center of each grid as a detection position, thereby constructing a detection matrix, and the detection point is located directly above the detection matrix.

[0053] The path construction unit 202 is used to select a plurality of survey points in the map of the water area to be surveyed based on the survey grid, determine the coordinate information of the survey points, and construct a moving path of the survey equipment based on the coordinate information.

[0054] In this module, the path construction unit 202 selects multiple survey points in the water area map to be surveyed based on the survey grid, and each survey point corresponds to a side length L= B max The coordinate information of the survey points is recorded in the square area, and the moving path of the survey equipment is generated according to the sequence of the survey points.

[0055] The single-point measurement unit 203 is used to control the movement of the survey equipment according to the moving path of the survey equipment, and when the survey equipment arrives at the survey point, it performs point-by-point measurement according to the survey grid to obtain single-point geological survey data.

[0056] In this module, the single-point measurement unit 203 controls the movement of the survey equipment according to the moving path of the survey equipment. The UAV flies along the moving path of the survey equipment and hovers at the coordinate information corresponding to the survey point. At this time, the airborne LiDAR starts to send detection light to each detection position in the detection grid, and measures each detection position in the square area once. Each measurement obtains a measurement distance, and the measurement angle (including angle and azimuth) at this time is recorded. After the measurement of a survey point is completed, the single-point geological survey data corresponding to the detection point is obtained.

[0057] like Figure 7 As shown, as a preferred embodiment of the present invention, the single-point survey module 300 includes: The coordinate system construction unit 301 is used to construct a three-dimensional coordinate system, construct a water plane according to the map of the water area to be surveyed, and mark the moving path of the survey equipment in the three-dimensional coordinate system.

[0058] In this module, the coordinate system construction unit 301 constructs a three-dimensional coordinate system, extracts the coordinate information (X, Y, Z) of the edge of the water area on the map of the water area to be surveyed, normalizes the Z value, sets it to the same value, such as 0, and then marks the normalized coordinates in the three-dimensional coordinate system. At this time, the edge of the water area is projected into the plane where the X-axis and the Y-axis are located, and then the moving path of the survey equipment is marked in the three-dimensional coordinate system.

[0059] The measurement data extraction unit 302 is used to extract each set of measurement data in the single-point geological survey data, and extract the elevation information, azimuth information and distance information contained therein.

[0060] The coordinate lattice construction unit 303 is used to perform a data marking in a three-dimensional coordinate system according to each set of measurement data to obtain a single-point survey coordinate lattice.

[0061] In this module, the measurement data extraction unit 302 extracts each set of measurement data in the single-point geological survey data. Since the detection grids corresponding to adjacent survey points have some overlapping detection positions, the overlapping detection positions account for more than 50%. Therefore, the same detection position is detected by at least two survey points, avoiding the problem of obstruction of the detection light due to the slope of the riverbed. The elevation information, azimuth information and distance information contained therein are extracted, the position is marked, and the coordinates corresponding to the current detection position are determined, thereby forming a detection point in the three-dimensional coordinate system. Recording its coordinates will form a single-point survey coordinate lattice, which is a lattice composed of all detection points corresponding to a survey point.

[0062] like Figure 8 As shown, as a preferred embodiment of the present invention, the survey model building module 400 includes: The dot matrix fusion unit 401 is used to fuse the single-point survey coordinate dot matrix to obtain a fused elevation dot matrix, and project the fused elevation dot matrix into the water plane.

[0063] In this module, the dot matrix fusion unit 401 fuses the single-point survey coordinate dot matrix, that is, marks all the single-point survey coordinate dot matrixes in the same three-dimensional coordinate system to form a global fused elevation dot matrix. When there are obstacles on the riverbed, such as steep slopes and other structures, it will affect the extension of the detection light, resulting in some areas not being detected. At this time, the fused elevation dot matrix is ​​projected into the water plane, and the detection grid is also projected into the water plane.

[0064] The abnormal area identification unit 402 is used to count the number of projection points contained in each survey grid. When the number of projection points is lower than a preset value, the area corresponding to the survey grid is regarded as an abnormal area.

[0065] In this module, the abnormal area identification unit 402 counts the number of projection points contained in each survey grid. When the number of projection points in the survey grid is lower than a preset value, it means that the detection density of the area is too low or cannot be detected. In this case, the survey grid is regarded as an abnormal area.

[0066] The feature recognition unit 403 is used to generate a supplementary survey control path based on the location of the abnormal area. The survey equipment records information according to the supplementary survey control path, identifies the riverbed features through the artificial intelligence model, and obtains a geological survey model.

[0067] In this module, the feature recognition unit 403 generates a supplementary survey control path based on the location of the abnormal area, marks all abnormal areas, extracts their coordinates, and performs global path planning according to the locations of all abnormal areas to generate a supplementary survey control path. The UAV flies according to the supplementary survey control path, performs supplementary detection on each survey grid to obtain supplementary survey information, supplements it to the three-dimensional coordinate system, performs surface fitting based on the supplemented fused elevation point matrix to obtain a geological survey model, and identifies riverbed features through an artificial intelligence model, and marks the riverbed features in the model. When supplementing information, the survey equipment uses vertical measurement to obtain measurement data to ensure that the number of surveys in each survey grid reaches a preset value.

[0068] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A geological survey method based on artificial intelligence, characterized in that: The method comprises: Obtain a map of the water area to be surveyed, and construct and train an artificial intelligence model, wherein the artificial intelligence model is used to identify structural features of the riverbed bottom; Retrieve survey equipment parameters, construct survey points according to the map of the water area to be surveyed, generate survey equipment movement paths based on the survey points, obtain single-point geological survey data, and ensure that the coverage area overlap rate of adjacent single-point geological survey data is higher than 50%; Construct a three-dimensional coordinate system based on the moving path of the survey equipment, mark the survey data based on the single-point geological survey data, and generate a single-point survey coordinate lattice; The single-point survey coordinate matrix is ​​fused to obtain a fused elevation matrix, the abnormal areas contained therein are identified, the information is supplemented, and a geological survey model is generated through an artificial intelligence model.

2. The artificial intelligence-based geological survey method according to claim 1, characterized in that: The steps of retrieving survey equipment parameters, constructing survey points according to the map of the water area to be surveyed, generating a moving path of the survey equipment based on the survey points, and obtaining single-point geological survey data specifically include: Obtaining the maximum survey distance of the survey equipment, determining the maximum survey height based on the maximum survey distance, and constructing a survey grid; Selecting multiple survey points in the map of the water area to be surveyed based on the survey grid, determining coordinate information of the survey points, and constructing a moving path of the survey equipment based on the coordinate information; The survey equipment is controlled to move according to its moving path. When the survey equipment arrives at the survey point, point-by-point measurements are performed according to the survey grid to obtain single-point geological survey data.

3. The artificial intelligence-based geological survey method according to claim 1, characterized in that: The steps of constructing a three-dimensional coordinate system based on the moving path of the survey equipment, marking the survey data based on the single-point geological survey data, and generating a single-point survey coordinate lattice specifically include: Construct a three-dimensional coordinate system, construct a water plane according to the map of the water area to be surveyed, and mark the moving path of the survey equipment in the three-dimensional coordinate system; Extract each set of measurement data from the single-point geological survey data, and extract the elevation information, azimuth information and distance information contained therein; Data is marked once in the three-dimensional coordinate system according to each set of measurement data to obtain a single-point survey coordinate matrix.

4. The artificial intelligence-based geological survey method according to claim 2, characterized in that: The steps of fusing the single-point survey coordinate lattices to obtain a fused elevation lattice, identifying the abnormal areas contained therein, supplementing the information, and generating a geological survey model through an artificial intelligence model specifically include: The single-point survey coordinate matrix is ​​fused to obtain a fused elevation matrix, and the fused elevation matrix is ​​projected onto the water plane; The number of projection points contained in each survey grid is counted. When the number of projection points is lower than the preset value, the area corresponding to the survey grid is regarded as an abnormal area. A supplementary survey control path is generated based on the location of the abnormal area. The survey equipment records information according to the supplementary survey control path, and the riverbed characteristics are identified through the artificial intelligence model to obtain a geological survey model.

5. The artificial intelligence-based geological survey method according to claim 4, characterized in that: When supplementing the information, the surveying equipment obtains the measurement data by vertical measurement.

6. A geological survey system based on artificial intelligence, characterized in that: The system comprises: A map acquisition module is used to acquire a map of the water area to be surveyed, and to construct and train an artificial intelligence model, wherein the artificial intelligence model is used to identify structural features of the riverbed bottom; The path construction module is used to retrieve the parameters of the survey equipment, construct the survey points according to the map of the water area to be surveyed, generate the moving path of the survey equipment based on the survey points, obtain the single-point geological survey data, and the overlap rate of the coverage area corresponding to the adjacent single-point geological survey data is higher than 50%; The single-point survey module is used to construct a three-dimensional coordinate system based on the moving path of the survey equipment, mark the survey data based on the single-point geological survey data, and generate a single-point survey coordinate lattice; The survey model construction module is used to fuse the single-point survey coordinate lattices to obtain the fused elevation lattices, identify the abnormal areas contained therein, supplement the information, and generate a geological survey model through an artificial intelligence model.

7. The artificial intelligence-based geological survey system according to claim 6, characterized in that: The path building module includes: A survey grid construction unit, used to obtain a maximum survey distance of the survey equipment, determine a maximum survey height based on the maximum survey distance, and construct a survey grid; A path construction unit, used to select a plurality of survey points in the map of the water area to be surveyed based on the survey grid, determine the coordinate information of the survey points, and construct a moving path of the survey equipment based on the coordinate information; The single-point measurement unit is used to control the movement of the survey equipment according to the moving path of the survey equipment. When the survey equipment arrives at the survey point, it performs point-by-point measurement according to the survey grid to obtain single-point geological survey data.

8. The artificial intelligence-based geological survey system according to claim 6, characterized in that: The single-point survey module includes: A coordinate system construction unit, used to construct a three-dimensional coordinate system, construct a water plane according to the map of the water area to be surveyed, and mark the moving path of the survey equipment in the three-dimensional coordinate system; A measurement data extraction unit is used to extract each set of measurement data in the single-point geological survey data, and extract the elevation information, azimuth information and distance information contained therein; The coordinate lattice construction unit is used to mark the data once in the three-dimensional coordinate system according to each set of measurement data to obtain a single-point survey coordinate lattice.

9. The artificial intelligence-based geological survey system according to claim 7, characterized in that: The survey model building module includes: The dot matrix fusion unit is used to fuse the single-point survey coordinate dot matrix to obtain a fused elevation dot matrix, and project the fused elevation dot matrix into the water plane; The abnormal area identification unit is used to count the number of projection points contained in each survey grid. When the number of projection points is lower than a preset value, the area corresponding to the survey grid is regarded as an abnormal area. The feature recognition unit is used to generate a supplementary survey control path based on the location of the abnormal area. The survey equipment records information according to the supplementary survey control path, identifies the riverbed features through the artificial intelligence model, and obtains a geological survey model.

10. The artificial intelligence-based geological survey system according to claim 9, characterized in that: When supplementing the information, the surveying equipment obtains the measurement data by vertical measurement.

Images