Cave three-dimensional modeling method and system based on multi-sensor fusion

Abstract

The invention relates to the technical field of cave three-dimensional modeling, in particular to a cave three-dimensional modeling method and system based on multi-sensor fusion, and the method comprises the steps: recognizing a simulation feature network point set, calculating the simulation precision according to the simulation feature network point set and an actual verification network point set, carrying out the point drawing according to the area of a unit test grid and the simulation precision, and carrying out the calculation of the simulation precision. Performing regression analysis on the area precision point set to obtain an area precision regression line; constructing a triangular plane current grid according to a current to-be-measured cave region; performing inner wall secondary sensing sampling on the three-dimensional unit current grid according to predicted regression precision to obtain a secondary three-dimensional sampling point set; and performing three-dimensional correction on the current grid of the three-dimensional unit by using the secondary three-dimensional sampling point set to obtain an initial cave three-dimensional model, and fusing the cave sensing image and the initial cave three-dimensional model to obtain a target cave three-dimensional model. According to the invention, the laser sampling efficiency and the cave three-dimensional modeling precision can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cave three-dimensional modeling, and in particular to a cave three-dimensional modeling method and system based on multi-sensor fusion. Background Art

[0002] In the fields of cave exploration, underground space mapping and geological disaster monitoring, three-dimensional modeling technology is a key means to achieve environmental digitization and intelligent analysis.

[0003] Traditional mesh reconstruction algorithms use a fixed laser sampling frequency to perform three-dimensional sampling of caves. This sampling method is difficult to adapt to the multi-scale structure of caves and does not fully consider the impact of cave wall characteristics on point cloud sampling. This results in excessive redundancy in flat areas and insufficient resolution in steep areas. As a result, the current process of three-dimensional cave sampling and modeling suffers from low laser sampling efficiency and poor 3D cave modeling accuracy. Summary of the Invention

[0004] The present invention provides a cave three-dimensional modeling method and system based on multi-sensor fusion, the main purpose of which is to improve laser sampling efficiency and cave three-dimensional modeling accuracy.

[0005] To achieve the above objectives, the present invention provides a method for three-dimensional cave modeling based on multi-sensor fusion, comprising:

[0006] Based on the preset triangular plane test grid, the pre-built inertial measurement sensor is used to perform sensing sampling on the inner wall of the cave to obtain a three-dimensional test grid of the cave;

[0007] Extracting plane unit test grids in sequence from the triangular plane test grid, and identifying the three-dimensional unit test grid corresponding to the plane unit test grid in the cave three-dimensional test grid;

[0008] Uniformly setting a plane check point set within the plane unit test grid according to a preset number of precision check points;

[0009] Identifying, within the three-dimensional unit test grid, a simulated feature mesh point set corresponding to the planar check point set;

[0010] Performing cave wall sensing sampling based on the plane verification point set to obtain an actual verification grid point set;

[0011] Calculating simulation accuracy based on the simulation feature mesh point set and the actual verification mesh point set;

[0012] Calculating the unit test grid area of ​​the three-dimensional unit test grid, and plotting points according to the unit test grid area and simulation accuracy to obtain an area accuracy point set;

[0013] Performing regression analysis on the area accuracy point set to obtain an area accuracy regression line;

[0014] Receiving a current cave area to be measured, and constructing a current triangular plane mesh according to the current cave area to be measured;

[0015] Performing cave wall sensing sampling based on the triangular plane current grid to obtain a three-dimensional unit current grid;

[0016] Identify the unit current grid area of ​​the three-dimensional unit current grid, and extract the prediction regression accuracy from the area accuracy regression line according to the unit current grid area;

[0017] Performing secondary sensing sampling of the inner wall of the current grid of the three-dimensional unit according to the predicted regression accuracy to obtain a secondary three-dimensional sampling point set;

[0018] Performing three-dimensional correction on the current grid of the three-dimensional unit using the secondary three-dimensional sampling point set to obtain an initial three-dimensional cave model;

[0019] A pre-built sensor camera is used to acquire a cave sensor image, and the cave sensor image and the initial cave three-dimensional model are fused to obtain a target cave three-dimensional model.

[0020] Optionally, the method of performing cave wall sensing sampling using a pre-built inertial measurement sensor based on a preset triangular plane test grid to obtain a cave three-dimensional test grid includes:

[0021] Identifying triangular plane grid points in the triangular plane test grid, identifying surface normal vectors of the triangular plane grid points relative to the inner wall of the cave, and obtaining a surface normal vector set;

[0022] Extracting face normal vectors in sequence from the face normal vector set;

[0023] Performing laser sampling of the cave inner wall on the surface normal vector using a laser radar, and performing attitude calibration on the laser radar using the inertial measurement sensor to obtain a test three-dimensional sampling point set;

[0024] Identifying a planar unit grid point set of a planar unit test grid, and identifying a unit normal vector group corresponding to the planar unit grid point set in the surface normal vector set;

[0025] Identifying a test unit sampling point group corresponding to the unit normal vector group in the test three-dimensional sampling point set, wherein the number of test unit sampling points in the test unit sampling point group is 3;

[0026] The test unit sampling point groups are connected in pairs to obtain a three-dimensional cave test grid.

[0027] Optionally, the evenly setting a plane check point set in the plane unit test grid according to a preset number of accuracy check points includes:

[0028] The number of unit grid test split blocks of the plane unit test grid is determined according to the number of precision check points, wherein the number of precision check points is , n is a preset positive integer;

[0029] Splitting the planar unit test grid equally according to the number of unit grid test split blocks to obtain a test unit grid sub-block set, wherein the test unit grid sub-blocks in the test unit grid sub-block set are regular triangles;

[0030] A test sub-block center point of each test unit grid sub-block in the test unit grid sub-block set is identified, and the test sub-block center point is used as a plane check point to obtain a plane check point set.

[0031] Optionally, identifying the simulated feature mesh point set corresponding to the planar check point set in the three-dimensional unit test grid includes:

[0032] Identifying a check normal vector corresponding to each plane check point in the plane check point set to obtain a check normal vector set, wherein the check normal vector refers to a surface normal vector of the plane check point relative to the inner wall of the cave;

[0033] Identifying line-plane intersections between each verification normal vector in the verification normal vector set and the three-dimensional unit test grid to obtain a line-plane intersection set;

[0034] The line-surface intersection point set is used as a simulation feature mesh point set.

[0035] Optionally, calculating the simulation accuracy based on the simulated feature mesh point set and the actual verification mesh point set includes:

[0036] Identify the associated simulated mesh points and the associated actual mesh points corresponding to the plane check point in the simulated feature mesh point set and the actual check mesh point set;

[0037] Identifying the simulated mesh point heights and the actual mesh point heights of the associated simulated mesh points and the associated actual mesh points in the direction of the verification normal vector to obtain a simulated mesh point height set and an actual mesh point height set;

[0038] According to the simulated mesh point height set and the actual mesh point height set, the simulation accuracy is calculated using the following formula:

[0039]

[0040] in, represents the simulation accuracy of the i-th plane unit test grid, Indicates the precision adjustment index, represents the number of plane checkpoints in the i-th plane unit test grid, Indicates the actual mesh point height corresponding to the jth plane check point in the i-th plane unit test grid, Indicates the simulated mesh point height corresponding to the jth plane checkpoint in the i-th plane unit test grid, Indicates the absolute value symbol.

[0041] Optionally, performing regression analysis on the area accuracy point set to obtain an area accuracy regression line includes:

[0042] Identifying the area precision coordinates of each area precision point in the area precision point set to obtain an area precision coordinate set;

[0043] Based on the area precision coordinate set, the slope of the regression line is calculated using the following formula:

[0044]

[0045] Where k represents the slope of the regression line, Indicates the number of flat unit test grids, Represents the horizontal coordinate of the pth area precision coordinate in the area precision coordinate set, Represents the ordinate of the pth area precision coordinate in the area precision coordinate set;

[0046] According to the area precision coordinate system, the regression line intercept is calculated using the following formula:

[0047]

[0048] in, represents the intercept of the regression line;

[0049] The area accuracy regression line is determined according to the regression line slope and the regression line intercept, wherein the area accuracy regression line equation is as follows:

[0050]

[0051] in, represents the regression accuracy function value, Represents the grid area function value.

[0052] Optionally, performing secondary sensing sampling of the inner wall of the current grid of the three-dimensional unit according to the predicted regression accuracy to obtain a secondary three-dimensional sampling point set includes:

[0053] Identifying a planar unit current grid corresponding to the three-dimensional unit current grid in the triangular planar current grid;

[0054] According to the predicted regression accuracy, the accuracy supplement points are calculated using the following formula:

[0055]

[0056] in, represents the number of points of precision complement, e represents the natural constant, represents the prediction regression accuracy, Indicates the floor symbol;

[0057] The number of precision supplement points is used as the current number of unit grid split blocks of the current grid of the plane unit;

[0058] Splitting the current plane unit grid equally according to the number of current split blocks of the unit grid to obtain a current unit grid sub-block set, wherein the current unit grid sub-block in the current unit grid sub-block set is an equilateral triangle;

[0059] Identifying a current sub-block center point of each current unit grid sub-block in the current unit grid sub-block set, and using the current sub-block center point as a plane complementary point to obtain a plane complementary point set;

[0060] The inner wall of the cave is sensed and sampled according to the plane supplementary point set to obtain a secondary three-dimensional sampling point set.

[0061] Optionally, performing three-dimensional correction on the current three-dimensional unit grid using the secondary three-dimensional sampling point set to obtain an initial three-dimensional cave model includes:

[0062] Identifying a co-edge unit grid sub-block group in the current unit grid sub-block set, and identifying a co-edge sub-block center group of the co-edge unit grid sub-block group, wherein the co-edge unit grid sub-block group refers to two current unit grid sub-blocks that share the same edge;

[0063] Identifying, in the quadratic three-dimensional sampling point set, an associated quadratic three-dimensional sampling point group corresponding to the co-edge sub-block center group;

[0064] Connecting the associated quadratic three-dimensional sampling points in the associated quadratic three-dimensional sampling point group to obtain a three-dimensional corrected feature line;

[0065] The three-dimensional correction feature line is used to perform three-dimensional correction on the current grid of the three-dimensional unit to obtain an initial three-dimensional cave model.

[0066] Optionally, fusing the cave sensor image and the initial cave three-dimensional model to obtain the target cave three-dimensional model includes:

[0067] Using the cave sensor image to identify the texture color of each triangular plane in the initial cave three-dimensional model;

[0068] The texture color of the initial cave three-dimensional model is supplemented according to the texture color of the triangular plane to obtain a target cave three-dimensional model.

[0069] To achieve the above objectives, the present invention further provides a cave 3D modeling system based on multi-sensor fusion, comprising:

[0070] An area accuracy regression line identification module is used to perform cave inner wall sensing sampling using a pre-built inertial measurement sensor based on a preset triangular plane test grid to obtain a three-dimensional cave test grid; sequentially extract plane unit test grids in the triangular plane test grid, and identify the three-dimensional unit test grid corresponding to the plane unit test grid in the three-dimensional cave test grid; uniformly set a plane verification point set in the plane unit test grid according to a preset number of accuracy verification points; identify a simulation feature mesh point set corresponding to the plane verification point set in the three-dimensional unit test grid; perform cave inner wall sensing sampling based on the plane verification point set to obtain an actual verification mesh point set; calculate simulation accuracy based on the simulation feature mesh point set and the actual verification mesh point set; calculate the unit test grid area of ​​the three-dimensional unit test grid, and perform point mapping based on the unit test grid area and simulation accuracy to obtain an area accuracy point set; perform regression analysis on the area accuracy point set to obtain an area accuracy regression line;

[0071] A three-dimensional unit current grid acquisition module is used to receive the current cave area to be measured, construct a triangular plane current grid according to the current cave area to be measured; perform cave inner wall sensor sampling based on the triangular plane current grid to obtain a three-dimensional unit current grid;

[0072] a three-dimensional unit current grid correction module, configured to identify the unit current grid area of ​​the three-dimensional unit current grid, extract the predicted regression accuracy from the area accuracy regression line based on the unit current grid area; perform secondary sensing sampling of the inner wall of the three-dimensional unit current grid based on the predicted regression accuracy to obtain a secondary three-dimensional sampling point set; and perform three-dimensional correction on the three-dimensional unit current grid using the secondary three-dimensional sampling point set to obtain an initial three-dimensional cave model;

[0073] The target cave three-dimensional model construction module is used to use a pre-built sensor camera to obtain cave sensor images, fuse the cave sensor images and the initial cave three-dimensional model, and obtain the target cave three-dimensional model.

[0074] In order to solve the above problem, the present invention further provides an electronic device, comprising:

[0075] A memory storing at least one instruction; and a processor executing the instruction stored in the memory to implement the above-mentioned cave three-dimensional modeling method based on multi-sensor fusion.

[0076] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned cave three-dimensional modeling method based on multi-sensor fusion.

[0077] Beneficial effect: In order to solve the problem described in the background technology, the present invention first analyzes the relationship between the unit test grid area and the simulation accuracy to obtain the area accuracy regression line, and then identifies the predicted regression accuracy corresponding to the current grid area of ​​different units through the area accuracy regression line. Finally, the inner wall secondary sensing sampling is performed according to the predicted regression accuracy, thereby achieving the effect of three-dimensional correction of the current grid of the three-dimensional unit by the secondary three-dimensional sampling point set of the secondary sensing sampling. When obtaining the area accuracy regression line, it is necessary to first perform cave inner wall sensing sampling according to the triangular plane test grid using the pre-built inertial measurement sensor to obtain the cave three-dimensional test grid. In order to achieve targeted analysis of the plane unit test grid, it is necessary to perform cave inner wall sensing sampling on the triangular plane test grid. The plane unit test grids are extracted in sequence from the test grid. Since there is a corresponding relationship between the three-dimensional unit test grid and the plane unit test grid, it is necessary to identify the three-dimensional unit test grid corresponding to the plane unit test grid in the cave three-dimensional test grid. In order to calculate the simulation accuracy, it is necessary to evenly set the plane verification point set in the plane unit test grid according to the preset number of accuracy verification points. In order to perform a comparison, it is necessary to identify the simulation feature mesh point set corresponding to the plane verification point set in the three-dimensional unit test grid. Then, the cave inner wall is sensed and sampled according to the plane verification point set to obtain the actual verification mesh point set. At this time, the simulation accuracy can be calculated based on the simulation feature mesh point set and the actual verification mesh point set. In order to analyze the corresponding relationship between the unit test grid area and the simulation accuracy, it is necessary to calculate the unit test grid area of ​​the three-dimensional unit test grid, and then draw points according to the unit test grid area and the simulation accuracy to obtain an area accuracy point set. Finally, regression analysis is performed on the area accuracy point set to obtain an area accuracy regression line. After obtaining the area accuracy regression line, the current cave area to be tested can be received, and a triangular plane current grid can be constructed according to the current cave area to be tested. Then, the cave inner wall sensing sampling is performed according to the triangular plane current grid to obtain a three-dimensional unit current grid. At this time, the three-dimensional unit current grid can be three-dimensionally corrected. First, the unit of the three-dimensional unit current grid needs to be identified. The current grid area is then extracted from the area accuracy regression line based on the current grid area of ​​the unit. Since the greater the predicted regression accuracy, the fewer the number of secondary three-dimensional sampling points required, the inner wall secondary sensing sampling of the current three-dimensional unit grid can be performed based on the predicted regression accuracy to obtain a secondary three-dimensional sampling point set. Finally, the secondary three-dimensional sampling point set is used to perform three-dimensional correction on the current three-dimensional unit grid to obtain an initial three-dimensional cave model. Since the initial three-dimensional cave model does not contain texture and color information, a pre-built sensor camera can be used to obtain a cave sensor image, and the cave sensor image and the initial three-dimensional cave model are fused to obtain the target three-dimensional cave model. Therefore, the present invention can improve laser sampling efficiency and cave three-dimensional modeling accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 A schematic diagram of a flow chart of a cave 3D modeling method based on multi-sensor fusion provided in one embodiment of the present invention;

[0079] Figure 2 A functional module diagram of a cave 3D modeling system based on multi-sensor fusion provided by one embodiment of the present invention;

[0080] Figure 3 A schematic structural diagram of an electronic device for implementing the method for three-dimensional cave modeling based on multi-sensor fusion provided in one embodiment of the present invention.

[0081] Description of reference numerals:

[0082] 1. Electronic device; 10. Processor; 11. Memory; 12. Bus.

[0083] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0084] 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.

[0085] The embodiment of the present application provides a method for three-dimensional cave modeling based on multi-sensor fusion. The execution subject of the method for three-dimensional cave modeling based on multi-sensor fusion includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for three-dimensional cave modeling based on multi-sensor fusion can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0086] Reference Figure 1 FIG. 1 is a flow chart of a method for three-dimensional cave modeling based on multi-sensor fusion according to an embodiment of the present invention. In this embodiment, the method for three-dimensional cave modeling based on multi-sensor fusion includes:

[0087] S1. Based on the preset triangular plane test grid, the pre-built inertial measurement sensor is used to perform sensing sampling on the inner wall of the cave to obtain a three-dimensional test grid of the cave.

[0088] It is understood that the triangular plane test grid refers to a triangular grid located on a preset plane and used to test the area accuracy regression line. The triangular plane test grid is composed of multiple equilateral triangle units. The triangle side length of the equilateral triangle unit can be set according to the user's accuracy requirements for three-dimensional modeling, for example, it can be 2 cm. The area accuracy regression line refers to the regression line that represents the relationship between the unit grid area and the simulation accuracy. See the following embodiment for details. The plane refers to the reference horizontal plane passing through the preset internal surface position of the cave.

[0089] Furthermore, the inertial measurement unit (IMU) refers to an integrated sensor that measures the acceleration and angular velocity of a carrier in an inertial reference frame, thereby calculating the carrier's state of motion. The carrier may be a laser radar (LiDAR). Cave wall sensing sampling refers to the sampling process of measuring the spatial location of the cave wall using an inertial measurement sensor and LiDAR based on the surface normal vectors of points within a triangular plane test grid. See the following embodiments for details. The surface normal vector refers to a normal vector perpendicular to the plane, pointing upward and originating from a point in the triangular plane grid.

[0090] In detail, the three-dimensional cave test grid refers to a triangular mesh surface formed by connecting the spatial locations of the inner wall obtained by sensing and sampling the inner wall of the cave.

[0091] In an embodiment of the present invention, the method of performing cave wall sensing sampling using a pre-built inertial measurement sensor based on a preset triangular plane test grid to obtain a cave three-dimensional test grid includes:

[0092] Identifying triangular plane grid points in the triangular plane test grid, identifying surface normal vectors of the triangular plane grid points relative to the inner wall of the cave, and obtaining a surface normal vector set;

[0093] Extracting face normal vectors in sequence from the face normal vector set;

[0094] Performing laser sampling of the cave inner wall on the surface normal vector using a laser radar, and performing attitude calibration on the laser radar using the inertial measurement sensor to obtain a test three-dimensional sampling point set;

[0095] Identifying a planar unit grid point set of a planar unit test grid, and identifying a unit normal vector group corresponding to the planar unit grid point set in the surface normal vector set;

[0096] Identifying a test unit sampling point group corresponding to the unit normal vector group in the test three-dimensional sampling point set, wherein the number of test unit sampling points in the test unit sampling point group is 3;

[0097] The test unit sampling point groups are connected in pairs to obtain a three-dimensional cave test grid.

[0098] It can be explained that the triangular plane grid points refer to the grid points of the plane test grid. The surface normal vector set refers to the set of surface normal vectors corresponding to each triangular plane grid point. The laser sampling of the cave inner wall refers to the process of using a laser radar to measure the spatial position of the intersection of the surface normal vector and the cave inner wall. Since it is necessary to obtain spatial information such as the attitude, speed and position of the laser radar, it is necessary to use an inertial measurement sensor to calibrate the attitude of the laser radar. The test three-dimensional sampling point set refers to the set of three-dimensional spatial locations of the cave inner wall measured according to the normal vectors of the triangular plane grid points in the process of testing the regression relationship between the test unit test grid area and the simulation accuracy.

[0099] Furthermore, the plane unit test grid refers to a unit grid in a triangular plane test grid. Since the triangular plane test grid is composed of multiple equilateral triangles, the plane unit test grid is the smallest equilateral triangle in the triangular plane test grid. The plane unit grid point set refers to a set of three grid points of the plane unit test grid. The unit normal vector group refers to three surface normal vectors with the plane unit grid point in the plane unit grid point set as the vector starting point. The test unit sampling point group refers to the three three-dimensional spatial intersection points of the unit normal vector in the unit normal vector group and the inner wall of the cave.

[0100] S2. Extracting plane unit test grids in sequence from the triangular plane test grid, and identifying three-dimensional unit test grids corresponding to the plane unit test grids in the cave three-dimensional test grid.

[0101] Furthermore, the three-dimensional unit test grid refers to a spatial three-dimensional grid obtained by connecting the test unit sampling point groups corresponding to the planar unit grid point sets in the planar unit test grid.

[0102] S3. Evenly setting a plane check point set in the plane unit test grid according to a preset number of precision check points.

[0103] It is understood that the number of accuracy check points refers to the number of sites preset for checking the simulation accuracy of the three-dimensional unit test grid. The plane check point set refers to the set of sites used to check the simulation accuracy of the three-dimensional unit test grid.

[0104] In an embodiment of the present invention, the step of uniformly setting a planar check point set within the planar unit test grid according to a preset number of accuracy check points includes:

[0105] The number of unit grid test split blocks of the plane unit test grid is determined according to the number of precision check points, wherein the number of precision check points is , n is a preset positive integer;

[0106] Splitting the planar unit test grid equally according to the number of unit grid test split blocks to obtain a test unit grid sub-block set, wherein the test unit grid sub-blocks in the test unit grid sub-block set are regular triangles;

[0107] A test sub-block center point of each test unit grid sub-block in the test unit grid sub-block set is identified, and the test sub-block center point is used as a plane check point to obtain a plane check point set.

[0108] It is understandable that the number of unit grid test split blocks refers to the number of splits of the planar unit test grid. The number of unit grid test split blocks is equal to the number of precision check points. Since the planar unit test grid in the form of an equilateral triangle is split into multiple small equal equilateral triangles, the number of unit grid test split blocks should be a power function with 4 as the base. The test unit grid sub-block set refers to the set of grid sub-blocks obtained after the planar unit test grid is equally split.

[0109] S4. Identify, within the three-dimensional unit test grid, a simulated feature mesh point set corresponding to the planar verification point set.

[0110] It should be understood that the simulated feature mesh point set refers to the intersection set of the surface normal vectors passing through the plane verification points and the three-dimensional unit test mesh.

[0111] In an embodiment of the present invention, identifying the simulated feature mesh point set corresponding to the planar verification point set in the three-dimensional unit test grid includes:

[0112] Identifying a check normal vector corresponding to each plane check point in the plane check point set to obtain a check normal vector set, wherein the check normal vector refers to a surface normal vector of the plane check point relative to the inner wall of the cave;

[0113] Identifying line-plane intersections between each verification normal vector in the verification normal vector set and the three-dimensional unit test grid to obtain a line-plane intersection set;

[0114] The line-surface intersection point set is used as a simulation feature mesh point set.

[0115] It is understood that the verification normal vector refers to the surface normal vector passing through the plane verification point. The verification normal vector set refers to the set of verification normal vectors corresponding to each plane verification point. The line-plane intersection point refers to the intersection point of the verification normal vector with the plane on which the three-dimensional unit test grid resides. The line-plane intersection point set refers to the set of line-plane intersection points of each verification normal vector with the three-dimensional unit test grid.

[0116] S5. Perform sensor sampling on the inner wall of the cave according to the plane verification point set to obtain an actual verification grid point set.

[0117] It can be understood that the actual verification mesh point set refers to the set of intersection points of the surface normal vectors passing through the plane verification points and the inner wall of the cave.

[0118] S6. Calculate simulation accuracy based on the simulation feature mesh point set and the actual verification mesh point set.

[0119] In detail, the simulation accuracy refers to the simulation accuracy of the three-dimensional unit test grid.

[0120] In an embodiment of the present invention, the step of calculating the simulation accuracy based on the simulated feature mesh point set and the actual verification mesh point set includes:

[0121] Identify the associated simulated mesh points and the associated actual mesh points corresponding to the plane check point in the simulated feature mesh point set and the actual check mesh point set;

[0122] Identifying the simulated mesh point heights and the actual mesh point heights of the associated simulated mesh points and the associated actual mesh points in the direction of the verification normal vector to obtain a simulated mesh point height set and an actual mesh point height set;

[0123] According to the simulated mesh point height set and the actual mesh point height set, the simulation accuracy is calculated using the following formula:

[0124]

[0125] in, represents the simulation accuracy of the i-th plane unit test grid, Indicates the precision adjustment index, represents the number of plane checkpoints in the i-th plane unit test grid, Indicates the actual mesh point height corresponding to the jth plane check point in the i-th plane unit test grid, Indicates the simulated mesh point height corresponding to the jth plane checkpoint in the i-th plane unit test grid, Indicates the absolute value symbol.

[0126] In detail, the associated simulated mesh point refers to a simulated feature mesh point that is on the same surface normal vector as the plane verification point, and the associated actual mesh point refers to an actual verification mesh point that is on the same surface normal vector as the plane verification point. The simulated mesh point height refers to the height distance of the associated simulated mesh point from the plane in the direction of the verification normal vector. The actual mesh point height refers to the height distance of the associated actual mesh point from the plane in the direction of the verification normal vector. The simulated mesh point height set refers to the set of simulated mesh point heights corresponding to each associated simulated mesh point, and the actual mesh point height set refers to the set of actual mesh point heights corresponding to each associated actual mesh point. The precision adjustment index refers to an index for adjusting the value of the simulation precision. The larger the precision adjustment index, the greater the value of the simulation precision. It can be set according to actual conditions.

[0127] S7. Calculate the unit test grid area of ​​the three-dimensional unit test grid, and plot points according to the unit test grid area and simulation accuracy to obtain an area accuracy point set.

[0128] It can be explained that the unit test grid area refers to the grid area of ​​the three-dimensional unit test grid, and the area accuracy point set refers to a set of coordinate points with the unit test grid area as the independent variable and the simulation accuracy as the dependent variable.

[0129] S8. Perform regression analysis on the area accuracy point set to obtain an area accuracy regression line.

[0130] Furthermore, the area accuracy regression line refers to a regression line that describes the relationship between the unit test grid area and simulation accuracy.

[0131] In the embodiment of the present invention, performing regression analysis on the area accuracy point set to obtain an area accuracy regression line includes:

[0132] Identifying the area precision coordinates of each area precision point in the area precision point set to obtain an area precision coordinate set;

[0133] Based on the area precision coordinate set, the slope of the regression line is calculated using the following formula:

[0134]

[0135] Where k represents the slope of the regression line, Indicates the number of flat unit test grids, Represents the horizontal coordinate of the pth area precision coordinate in the area precision coordinate set, Represents the ordinate of the pth area precision coordinate in the area precision coordinate set;

[0136] According to the area precision coordinate system, the regression line intercept is calculated using the following formula:

[0137]

[0138] in, represents the intercept of the regression line;

[0139] The area accuracy regression line is determined according to the regression line slope and the regression line intercept, wherein the area accuracy regression line equation is as follows:

[0140]

[0141] in, represents the regression accuracy function value, Represents the grid area function value.

[0142] It is understandable that the least square method can be used to perform regression analysis on the area accuracy point set to obtain the area accuracy regression line. The least square method is an existing technology and will not be described in detail here.

[0143] Specifically, the area precision coordinates refer to the coordinates of the area precision points determined in a pre-constructed grid area-simulation precision coordinate system, where the grid area-simulation precision coordinate system uses the unit test grid area as the abscissa and the simulation precision as the ordinate. The area precision coordinate set refers to the set of area precision coordinates of each area precision point. The regression line slope refers to the slope of the area precision regression line. The regression line intercept refers to the intercept of the area precision regression line.

[0144] S9. Receive the current cave area to be measured, and construct a current triangular plane mesh according to the current cave area to be measured.

[0145] It can be explained that the current cave area to be tested refers to the cave area that currently needs to be three-dimensionally modeled, and the current cave area to be tested is located in a plane. The triangular plane current grid refers to an equilateral triangle grid located in a plane and used to perform three-dimensional modeling of the cave inner wall corresponding to the current cave area to be tested, and the triangular plane test grid is composed of multiple equilateral triangle units.

[0146] S10. Performing cave wall sensing sampling based on the current triangular plane grid to obtain a current three-dimensional unit grid.

[0147] Furthermore, the three-dimensional unit current grid refers to a three-dimensional unit space grid obtained by performing cave inner wall sensing sampling based on the grid points of a single equilateral triangle unit in the triangular plane current grid.

[0148] S11 , identifying the unit current grid area of ​​the three-dimensional unit current grid, and extracting the prediction regression accuracy from the area accuracy regression line according to the unit current grid area.

[0149] It should be understood that the unit current grid area refers to the triangle area of ​​the three-dimensional unit current grid. The predicted regression accuracy refers to the simulation accuracy of the three-dimensional unit current grid predicted based on the area accuracy regression line of the unit current grid area.

[0150] S12. Perform secondary sensing sampling of the inner wall of the current grid of the three-dimensional unit according to the predicted regression accuracy to obtain a secondary three-dimensional sampling point set.

[0151] It can be explained that the secondary 3D sampling point set refers to the set of sampling points used to perform 3D correction on the current 3D unit grid. The inner wall secondary sensing sampling refers to the sampling process of using inertial measurement sensors and lidar to perform complementary measurement of the inner wall spatial positions on the current 3D unit grid.

[0152] In an embodiment of the present invention, performing secondary sensing sampling of the inner wall of the current grid of the three-dimensional unit according to the predicted regression accuracy to obtain a secondary three-dimensional sampling point set includes:

[0153] Identifying a planar unit current grid corresponding to the three-dimensional unit current grid in the triangular planar current grid;

[0154] According to the predicted regression accuracy, the accuracy supplement points are calculated using the following formula:

[0155]

[0156] in, represents the number of points of precision complement, e represents the natural constant, represents the prediction regression accuracy, Indicates the floor symbol;

[0157] The number of precision supplement points is used as the current number of unit grid split blocks of the current grid of the plane unit;

[0158] Splitting the current plane unit grid equally according to the number of current split blocks of the unit grid to obtain a current unit grid sub-block set, wherein the current unit grid sub-block in the current unit grid sub-block set is an equilateral triangle;

[0159] Identifying a current sub-block center point of each current unit grid sub-block in the current unit grid sub-block set, and using the current sub-block center point as a plane complementary point to obtain a plane complementary point set;

[0160] The inner wall of the cave is sensed and sampled according to the plane supplementary point set to obtain a secondary three-dimensional sampling point set.

[0161] It can be explained that the current grid of the planar unit refers to the equilateral triangle unit grid of the three-dimensional unit current grid vertically projected on the plane. The number of precision complementary points refers to the number of grid points for three-dimensional correction of the current grid of the three-dimensional unit. The current number of unit grid split blocks refers to the number of blocks for equally splitting the current grid of the planar unit. The current unit grid sub-block set refers to the set of sub-blocks of equal-area equilateral triangle units that are evenly split into the current grid of the planar unit. The current sub-block center point refers to the center point of the current unit grid sub-block, that is, the center point of the equilateral triangle unit. The plane complementary point refers to the location located in the current grid of the planar unit for secondary sensing sampling of the inner wall. The plane complementary point set refers to the set of plane complementary points corresponding to each current unit grid sub-block.

[0162] S13. Perform three-dimensional correction on the current three-dimensional unit grid using the secondary three-dimensional sampling point set to obtain an initial three-dimensional cave model.

[0163] It can be understood that the initial three-dimensional cave model refers to the cave three-dimensional model obtained by three-dimensionally correcting the current grid of the three-dimensional unit using secondary sensing sampling of the inner wall.

[0164] In an embodiment of the present invention, the method of performing three-dimensional correction on the current three-dimensional unit grid using the secondary three-dimensional sampling point set to obtain an initial three-dimensional cave model includes:

[0165] Identifying a co-edge unit grid sub-block group in the current unit grid sub-block set, and identifying a co-edge sub-block center group of the co-edge unit grid sub-block group, wherein the co-edge unit grid sub-block group refers to two current unit grid sub-blocks that share the same edge;

[0166] Identifying, in the quadratic three-dimensional sampling point set, an associated quadratic three-dimensional sampling point group corresponding to the co-edge sub-block center group;

[0167] Connecting the associated quadratic three-dimensional sampling points in the associated quadratic three-dimensional sampling point group to obtain a three-dimensional corrected feature line;

[0168] The three-dimensional correction feature line is used to perform three-dimensional correction on the current grid of the three-dimensional unit to obtain an initial three-dimensional cave model.

[0169] It is understood that the co-edge sub-block center group refers to the center points of two co-edge unit grid sub-blocks in the co-edge unit grid sub-block group, and the co-edge unit grid sub-block is an equilateral triangle. The associated secondary 3D sampling point group refers to the two corresponding secondary 3D sampling points in the direction of the surface normal vector of the co-edge sub-block center group in the secondary 3D sampling point set. The 3D corrected feature line refers to the 3D space line segment formed by connecting the associated secondary 3D sampling point groups.

[0170] S14. Using a pre-built sensor camera to acquire a cave sensor image, fusing the cave sensor image with the initial cave three-dimensional model to obtain a target cave three-dimensional model.

[0171] It is understood that the cave sensor image refers to the image of the inner wall of the current cave area to be measured taken by the sensor camera. The target cave 3D model refers to the cave 3D model obtained by supplementing the texture and color of the initial cave 3D model using the cave sensor image.

[0172] In an embodiment of the present invention, fusing the cave sensor image and the initial cave 3D model to obtain the target cave 3D model includes:

[0173] Using the cave sensor image to identify the texture color of each triangular plane in the initial cave three-dimensional model;

[0174] The texture color of the initial cave three-dimensional model is supplemented according to the texture color of the triangular plane to obtain a target cave three-dimensional model.

[0175] It can be understood that the triangular plane refers to the smallest spatial triangular unit in the initial cave three-dimensional model.

[0176] In order to solve the problems described in the background technology, the present invention first analyzes the relationship between the unit test grid area and the simulation accuracy to obtain the area accuracy regression line, and then identifies the predicted regression accuracy corresponding to the current grid area of ​​different units through the area accuracy regression line. Finally, the inner wall secondary sensing sampling is performed according to the predicted regression accuracy, thereby achieving the effect of three-dimensional correction of the current grid of the three-dimensional unit using the secondary three-dimensional sampling point set of the secondary sensing sampling. When obtaining the area accuracy regression line, it is necessary to first perform cave inner wall sensing sampling based on the triangular plane test grid using a pre-built inertial measurement sensor to obtain the cave three-dimensional test grid. In order to achieve targeted analysis of the plane unit test grid, it is necessary to perform cave inner wall sensing sampling based on the triangular plane test grid. The plane unit test grids are extracted in sequence. Since there is a corresponding relationship between the three-dimensional unit test grid and the plane unit test grid, it is necessary to identify the three-dimensional unit test grid corresponding to the plane unit test grid in the cave three-dimensional test grid. In order to calculate the simulation accuracy, it is necessary to evenly set the plane verification point set in the plane unit test grid according to the preset number of accuracy verification points. In order to perform a comparison, it is necessary to identify the simulation feature mesh point set corresponding to the plane verification point set in the three-dimensional unit test grid. Then, the cave inner wall sensor sampling is performed according to the plane verification point set to obtain the actual verification mesh point set. At this time, the simulation accuracy can be calculated according to the simulation feature mesh point set and the actual verification mesh point set, which is In order to analyze the correspondence between the unit test grid area and the simulation accuracy, it is necessary to calculate the unit test grid area of ​​the three-dimensional unit test grid, and then draw points according to the unit test grid area and the simulation accuracy to obtain an area accuracy point set. Finally, regression analysis is performed on the area accuracy point set to obtain an area accuracy regression line. After obtaining the area accuracy regression line, the current cave area to be tested can be received, and a triangular plane current grid can be constructed according to the current cave area to be tested. Then, the cave inner wall sensing sampling is performed according to the triangular plane current grid to obtain a three-dimensional unit current grid. At this time, the three-dimensional unit current grid can be three-dimensionally corrected. First, it is necessary to identify the unit of the three-dimensional unit current grid. The area of ​​the previous grid is then extracted from the area accuracy regression line based on the current grid area of ​​the unit. Since the greater the predicted regression accuracy, the fewer the number of secondary three-dimensional sampling points required, the inner wall secondary sensing sampling of the current three-dimensional unit grid can be performed based on the predicted regression accuracy to obtain a secondary three-dimensional sampling point set. Finally, the secondary three-dimensional sampling point set is used to perform three-dimensional correction on the current three-dimensional unit grid to obtain an initial three-dimensional cave model. Since the initial three-dimensional cave model does not contain texture and color information, a pre-built sensor camera can be used to obtain a cave sensor image, and the cave sensor image and the initial three-dimensional cave model are fused to obtain the target three-dimensional cave model. Therefore, the present invention can improve laser sampling efficiency and cave three-dimensional modeling accuracy.

[0177] like Figure 2 , which is a functional module diagram of a cave 3D modeling system based on multi-sensor fusion provided by one embodiment of the present invention.

[0178] The multi-sensor fusion-based 3D cave modeling system 100 described in the present invention can be installed in an electronic device. Depending on the functions implemented, the multi-sensor fusion-based 3D cave modeling system 100 can include an area accuracy regression line identification module 101, a 3D unit current grid acquisition module 102, a 3D unit current grid correction module 103, and a target cave 3D model construction module 104. The modules described in the present invention, also referred to as units, refer to a series of computer program segments that can be executed by an electronic device processor and can perform fixed functions, and are stored in the memory of the electronic device.

[0179] The area accuracy regression line identification module 101 is used to perform cave inner wall sensing sampling using a pre-built inertial measurement sensor according to a preset triangular plane test grid to obtain a cave three-dimensional test grid; sequentially extract plane unit test grids in the triangular plane test grid, and identify the three-dimensional unit test grid corresponding to the plane unit test grid in the cave three-dimensional test grid; uniformly set a plane verification point set in the plane unit test grid according to a preset number of accuracy verification points; identify a simulation feature mesh point set corresponding to the plane verification point set in the three-dimensional unit test grid; perform cave inner wall sensing sampling according to the plane verification point set to obtain an actual verification mesh point set; calculate simulation accuracy according to the simulation feature mesh point set and the actual verification mesh point set; calculate the unit test grid area of ​​the three-dimensional unit test grid, and perform point mapping according to the unit test grid area and simulation accuracy to obtain an area accuracy point set; perform regression analysis on the area accuracy point set to obtain an area accuracy regression line;

[0180] The three-dimensional unit current grid acquisition module 102 is used to receive the current cave area to be measured, construct a triangular plane current grid according to the current cave area to be measured; perform cave inner wall sensor sampling based on the triangular plane current grid to obtain the three-dimensional unit current grid;

[0181] The three-dimensional unit current grid correction module 103 is used to identify the unit current grid area of ​​the three-dimensional unit current grid, extract the predicted regression accuracy from the area accuracy regression line according to the unit current grid area; perform secondary sensing sampling of the inner wall of the three-dimensional unit current grid according to the predicted regression accuracy to obtain a secondary three-dimensional sampling point set; and perform three-dimensional correction on the three-dimensional unit current grid using the secondary three-dimensional sampling point set to obtain an initial three-dimensional cave model;

[0182] The target cave 3D model construction module 104 is used to obtain cave sensor images using a pre-built sensor camera, and fuse the cave sensor images with the initial cave 3D model to obtain a target cave 3D model.

[0183] In detail, each module in the cave 3D modeling system 100 based on multi-sensor fusion in the embodiment of the present invention adopts the same method as above when in use. Figure 1 The same technical means are used as the cave three-dimensional modeling method based on multi-sensor fusion described in , and can produce the same technical effects, so I will not go into details here.

[0184] like Figure 3 , which is a schematic structural diagram of an electronic device for implementing a cave three-dimensional modeling method based on multi-sensor fusion provided by an embodiment of the present invention.

[0185] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a three-dimensional cave modeling method program based on multi-sensor fusion.

[0186] The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard drive, a multimedia card, a card-type memory (e.g., SD or DX memory), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard drive of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped on the electronic device 1. Furthermore, the memory 11 includes both the internal storage unit of the electronic device 1 and external storage devices. The memory 11 can be used not only to store application software installed on the electronic device 1 and various types of data, such as the code of a multi-sensor fusion-based cave 3D modeling method program, but also to temporarily store data that has been output or is about to be output.

[0187] In some embodiments, the processor 10 may be comprised of an integrated circuit, such as a single packaged integrated circuit or a combination of multiple packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control core (control unit) of the electronic device, connecting the various components of the electronic device using various interfaces and circuits. It executes programs or modules stored in the memory 11 (e.g., a program for a three-dimensional cave modeling method based on multi-sensor fusion) and accesses data stored in the memory 11 to perform various functions and process data.

[0188] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0189] Figure 3 Only the electronic device with components is shown, and it can be understood by those skilled in the art that Figure 3 The structure shown does not constitute a limitation on the electronic device 1 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0190] For example, although not shown, the electronic device 1 may further include a power supply (e.g., a battery) to power various components. Preferably, the power supply may be logically connected to the at least one processor 10 via a power management device, thereby enabling functions such as charge management, discharge management, and power consumption management via the power management device. The power supply may further include any components such as one or more DC or AC power supplies, a recharging device, a power failure detection circuit, a power converter or inverter, and a power status indicator. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which are not further described here.

[0191] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0192] Optionally, the electronic device 1 may further include a user interface, which may be a display or an input unit (such as a keyboard). Optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display may also be appropriately referred to as a display screen or a display unit, and is used to display information processed by the electronic device 1 and to display a visual user interface.

[0193] The program of the cave three-dimensional modeling method based on multi-sensor fusion stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve the following:

[0194] Based on the preset triangular plane test grid, the pre-built inertial measurement sensor is used to perform sensing sampling on the inner wall of the cave to obtain a three-dimensional test grid of the cave;

[0195] Extracting plane unit test grids in sequence from the triangular plane test grid, and identifying the three-dimensional unit test grid corresponding to the plane unit test grid in the cave three-dimensional test grid;

[0196] Uniformly setting a plane check point set within the plane unit test grid according to a preset number of precision check points;

[0197] Identifying, within the three-dimensional unit test grid, a simulated feature mesh point set corresponding to the planar check point set;

[0198] Performing cave wall sensing sampling based on the plane verification point set to obtain an actual verification grid point set;

[0199] Calculating simulation accuracy based on the simulation feature mesh point set and the actual verification mesh point set;

[0200] Calculating the unit test grid area of ​​the three-dimensional unit test grid, and plotting points according to the unit test grid area and simulation accuracy to obtain an area accuracy point set;

[0201] Performing regression analysis on the area accuracy point set to obtain an area accuracy regression line;

[0202] Receiving a current cave area to be measured, and constructing a current triangular plane mesh according to the current cave area to be measured;

[0203] Performing cave wall sensing sampling based on the triangular plane current grid to obtain a three-dimensional unit current grid;

[0204] Identify the unit current grid area of ​​the three-dimensional unit current grid, and extract the prediction regression accuracy from the area accuracy regression line according to the unit current grid area;

[0205] Performing secondary sensing sampling of the inner wall of the current grid of the three-dimensional unit according to the predicted regression accuracy to obtain a secondary three-dimensional sampling point set;

[0206] Performing three-dimensional correction on the current grid of the three-dimensional unit using the secondary three-dimensional sampling point set to obtain an initial three-dimensional cave model;

[0207] A pre-built sensor camera is used to acquire a cave sensor image, and the cave sensor image and the initial cave three-dimensional model are fused to obtain a target cave three-dimensional model.

[0208] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0209] Furthermore, if the modules / units integrated into the electronic device 1 are implemented as software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. The computer-readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0210] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program is executed by a processor of an electronic device, the computer program can implement:

[0211] Based on the preset triangular plane test grid, the pre-built inertial measurement sensor is used to perform sensing sampling on the inner wall of the cave to obtain a three-dimensional test grid of the cave;

[0212] Extracting plane unit test grids in sequence from the triangular plane test grid, and identifying the three-dimensional unit test grid corresponding to the plane unit test grid in the cave three-dimensional test grid;

[0213] Uniformly setting a plane check point set within the plane unit test grid according to a preset number of precision check points;

[0214] Identifying, within the three-dimensional unit test grid, a simulated feature mesh point set corresponding to the planar check point set;

[0215] Performing cave wall sensing sampling based on the plane verification point set to obtain an actual verification grid point set;

[0216] Calculating simulation accuracy based on the simulation feature mesh point set and the actual verification mesh point set;

[0217] Calculating the unit test grid area of ​​the three-dimensional unit test grid, and plotting points according to the unit test grid area and simulation accuracy to obtain an area accuracy point set;

[0218] Performing regression analysis on the area accuracy point set to obtain an area accuracy regression line;

[0219] Receiving a current cave area to be measured, and constructing a current triangular plane mesh according to the current cave area to be measured;

[0220] Performing cave wall sensing sampling based on the triangular plane current grid to obtain a three-dimensional unit current grid;

[0221] Identify the unit current grid area of ​​the three-dimensional unit current grid, and extract the prediction regression accuracy from the area accuracy regression line according to the unit current grid area;

[0222] Performing secondary sensing sampling of the inner wall of the current grid of the three-dimensional unit according to the predicted regression accuracy to obtain a secondary three-dimensional sampling point set;

[0223] Performing three-dimensional correction on the current grid of the three-dimensional unit using the secondary three-dimensional sampling point set to obtain an initial three-dimensional cave model;

[0224] A pre-built sensor camera is used to acquire a cave sensor image, and the cave sensor image and the initial cave three-dimensional model are fused to obtain a target cave three-dimensional model.

[0225] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only exemplary, and actual implementations may have other division methods.

[0226] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0227] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0228] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0229] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A cave 3D modeling method based on multi-sensor fusion, characterized in that: The method comprises: Based on the preset triangular plane test grid, the pre-built inertial measurement sensor is used to perform sensing sampling on the inner wall of the cave to obtain a three-dimensional test grid of the cave; Extracting plane unit test grids in sequence from the triangular plane test grid, and identifying the three-dimensional unit test grid corresponding to the plane unit test grid in the cave three-dimensional test grid; Uniformly setting a plane check point set within the plane unit test grid according to a preset number of precision check points; Identifying, within the three-dimensional unit test grid, a simulated feature mesh point set corresponding to the planar check point set; Performing cave wall sensing sampling based on the plane verification point set to obtain an actual verification grid point set; Calculating simulation accuracy based on the simulation feature mesh point set and the actual verification mesh point set; Calculating the unit test grid area of ​​the three-dimensional unit test grid, and plotting points according to the unit test grid area and simulation accuracy to obtain an area accuracy point set; Performing regression analysis on the area accuracy point set to obtain an area accuracy regression line; Receiving a current cave area to be measured, and constructing a current triangular plane mesh according to the current cave area to be measured; Performing cave wall sensing sampling based on the triangular plane current grid to obtain a three-dimensional unit current grid; Identify the unit current grid area of ​​the three-dimensional unit current grid, and extract the prediction regression accuracy from the area accuracy regression line according to the unit current grid area; Performing secondary sensing sampling of the inner wall of the current grid of the three-dimensional unit according to the predicted regression accuracy to obtain a secondary three-dimensional sampling point set; Performing three-dimensional correction on the current grid of the three-dimensional unit using the secondary three-dimensional sampling point set to obtain an initial three-dimensional cave model; A pre-built sensor camera is used to acquire a cave sensor image, and the cave sensor image and the initial cave three-dimensional model are fused to obtain a target cave three-dimensional model.

2. The cave 3D modeling method based on multi-sensor fusion according to claim 1, characterized in that: The method of obtaining a three-dimensional cave test grid by performing sensing sampling on the inner wall of the cave using a pre-built inertial measurement sensor according to the preset triangular plane test grid includes: Identifying triangular plane grid points in the triangular plane test grid, identifying surface normal vectors of the triangular plane grid points relative to the inner wall of the cave, and obtaining a surface normal vector set; Extracting face normal vectors in sequence from the face normal vector set; Performing laser sampling of the cave inner wall on the surface normal vector using a laser radar, and performing attitude calibration on the laser radar using the inertial measurement sensor to obtain a test three-dimensional sampling point set; Identifying a planar unit grid point set of a planar unit test grid, and identifying a unit normal vector group corresponding to the planar unit grid point set in the surface normal vector set; Identifying a test unit sampling point group corresponding to the unit normal vector group in the test three-dimensional sampling point set, wherein the number of test unit sampling points in the test unit sampling point group is 3; The test unit sampling point groups are connected in pairs to obtain a three-dimensional cave test grid.

3. The cave 3D modeling method based on multi-sensor fusion according to claim 2, characterized in that: The uniformly setting a plane check point set in the plane unit test grid according to a preset number of accuracy check points includes: The number of unit grid test split blocks of the plane unit test grid is determined according to the number of precision check points, wherein the number of precision check points is , n is a preset positive integer; Splitting the planar unit test grid equally according to the number of unit grid test split blocks to obtain a test unit grid sub-block set, wherein the test unit grid sub-blocks in the test unit grid sub-block set are regular triangles; A test sub-block center point of each test unit grid sub-block in the test unit grid sub-block set is identified, and the test sub-block center point is used as a plane check point to obtain a plane check point set.

4. The cave 3D modeling method based on multi-sensor fusion according to claim 3, characterized in that: The step of identifying the simulated feature mesh point set corresponding to the planar check point set in the three-dimensional unit test grid includes: Identifying a check normal vector corresponding to each plane check point in the plane check point set to obtain a check normal vector set, wherein the check normal vector refers to a surface normal vector of the plane check point relative to the inner wall of the cave; Identifying line-plane intersections between each verification normal vector in the verification normal vector set and the three-dimensional unit test grid to obtain a line-plane intersection set; The line-surface intersection point set is used as a simulation feature mesh point set.

5. The method for three-dimensional cave modeling based on multi-sensor fusion according to claim 4, characterized in that: The calculating of simulation accuracy based on the simulation feature mesh point set and the actual verification mesh point set includes: Identify the associated simulated mesh points and the associated actual mesh points corresponding to the plane check point in the simulated feature mesh point set and the actual check mesh point set; Identifying the simulated mesh point heights and the actual mesh point heights of the associated simulated mesh points and the associated actual mesh points in the direction of the verification normal vector to obtain a simulated mesh point height set and an actual mesh point height set; According to the simulated mesh point height set and the actual mesh point height set, the simulation accuracy is calculated using the following formula: ； in, represents the simulation accuracy of the i-th plane unit test grid, Indicates the precision adjustment index, represents the number of plane checkpoints in the i-th plane unit test grid, Indicates the actual mesh point height corresponding to the jth plane check point in the i-th plane unit test grid, Indicates the simulated mesh point height corresponding to the jth plane checkpoint in the i-th plane unit test grid, Indicates the absolute value symbol.

6. The method for three-dimensional cave modeling based on multi-sensor fusion according to claim 5, characterized in that: The performing regression analysis on the area accuracy point set to obtain an area accuracy regression line includes: Identifying the area precision coordinates of each area precision point in the area precision point set to obtain an area precision coordinate set; Based on the area precision coordinate set, the slope of the regression line is calculated using the following formula: ； Where k represents the slope of the regression line, Indicates the number of flat unit test grids, Represents the horizontal coordinate of the pth area precision coordinate in the area precision coordinate set, Represents the ordinate of the pth area precision coordinate in the area precision coordinate set; According to the area precision coordinate system, the regression line intercept is calculated using the following formula: ； in, represents the intercept of the regression line; The area accuracy regression line is determined according to the regression line slope and the regression line intercept, wherein the area accuracy regression line equation is as follows: ； in, represents the regression accuracy function value, Represents the grid area function value.

7. The method for three-dimensional cave modeling based on multi-sensor fusion according to claim 6, characterized in that: The performing secondary sensing sampling of the inner wall of the current grid of the three-dimensional unit according to the predicted regression accuracy to obtain a secondary three-dimensional sampling point set includes: Identifying a planar unit current grid corresponding to the three-dimensional unit current grid in the triangular planar current grid; According to the predicted regression accuracy, the accuracy supplement points are calculated using the following formula: ； in, represents the number of points of precision complement, e represents the natural constant, represents the prediction regression accuracy, Indicates the floor symbol; The number of precision supplement points is used as the current number of unit grid split blocks of the current grid of the plane unit; Splitting the current plane unit grid equally according to the number of current split blocks of the unit grid to obtain a current unit grid sub-block set, wherein the current unit grid sub-block in the current unit grid sub-block set is an equilateral triangle; Identifying a current sub-block center point of each current unit grid sub-block in the current unit grid sub-block set, and using the current sub-block center point as a plane complementary point to obtain a plane complementary point set; The inner wall of the cave is sensed and sampled according to the plane supplementary point set to obtain a secondary three-dimensional sampling point set.

8. The method for three-dimensional cave modeling based on multi-sensor fusion according to claim 7, characterized in that: The method of performing three-dimensional correction on the current three-dimensional unit grid using the secondary three-dimensional sampling point set to obtain an initial three-dimensional cave model includes: Identifying a co-edge unit grid sub-block group in the current unit grid sub-block set, and identifying a co-edge sub-block center group of the co-edge unit grid sub-block group, wherein the co-edge unit grid sub-block group refers to two current unit grid sub-blocks that share the same edge; Identifying, in the quadratic three-dimensional sampling point set, an associated quadratic three-dimensional sampling point group corresponding to the co-edge sub-block center group; Connecting the associated quadratic three-dimensional sampling points in the associated quadratic three-dimensional sampling point group to obtain a three-dimensional corrected feature line; The three-dimensional correction feature line is used to perform three-dimensional correction on the current grid of the three-dimensional unit to obtain an initial three-dimensional cave model.

9. The method for three-dimensional cave modeling based on multi-sensor fusion according to claim 8, characterized in that: The step of fusing the cave sensor image and the initial cave three-dimensional model to obtain a target cave three-dimensional model includes: Using the cave sensor image to identify the texture color of each triangular plane in the initial cave three-dimensional model; The texture color of the initial cave three-dimensional model is supplemented according to the texture color of the triangular plane to obtain a target cave three-dimensional model.

10. A cave 3D modeling system based on multi-sensor fusion, characterized in that: The system comprises: An area accuracy regression line identification module is used to perform cave inner wall sensing sampling using a pre-built inertial measurement sensor based on a preset triangular plane test grid to obtain a three-dimensional cave test grid; sequentially extract plane unit test grids in the triangular plane test grid, and identify the three-dimensional unit test grid corresponding to the plane unit test grid in the three-dimensional cave test grid; uniformly set a plane verification point set in the plane unit test grid according to a preset number of accuracy verification points; identify a simulation feature mesh point set corresponding to the plane verification point set in the three-dimensional unit test grid; perform cave inner wall sensing sampling based on the plane verification point set to obtain an actual verification mesh point set; calculate simulation accuracy based on the simulation feature mesh point set and the actual verification mesh point set; calculate the unit test grid area of ​​the three-dimensional unit test grid, and perform point mapping based on the unit test grid area and simulation accuracy to obtain an area accuracy point set; perform regression analysis on the area accuracy point set to obtain an area accuracy regression line; A three-dimensional unit current grid acquisition module is used to receive the current cave area to be measured, construct a triangular plane current grid according to the current cave area to be measured; perform cave inner wall sensor sampling based on the triangular plane current grid to obtain a three-dimensional unit current grid; a three-dimensional unit current grid correction module, configured to identify the unit current grid area of ​​the three-dimensional unit current grid, extract the predicted regression accuracy from the area accuracy regression line based on the unit current grid area; perform secondary sensing sampling of the inner wall of the three-dimensional unit current grid based on the predicted regression accuracy to obtain a secondary three-dimensional sampling point set; and perform three-dimensional correction on the three-dimensional unit current grid using the secondary three-dimensional sampling point set to obtain an initial three-dimensional cave model; The target cave three-dimensional model construction module is used to use a pre-built sensor camera to obtain cave sensor images, fuse the cave sensor images and the initial cave three-dimensional model, and obtain the target cave three-dimensional model.

Images