Method and device for detecting micro-displacement of rock-soil surface, terminal and medium

Abstract

This invention provides a method, device, terminal, and medium for detecting minute displacements on soil and rock surfaces. The method involves: acquiring a target image set, camera parameters, and target placement information. The target image set includes several target images and several timestamps of the images being captured. Based on the target image set, image point displacement information is obtained. Based on the image point displacement information, the target placement information, and the camera parameters, target displacement information is obtained. Based on the camera parameters and the target placement information, target displacement compensation information is obtained. Based on the target displacement information and the target displacement compensation information, a displacement cloud map is obtained. This improves the accuracy of soil and rock monitoring, enables dynamic monitoring of soil and rock, and enhances the system compatibility and scalability of soil and rock monitoring methods.

Description

Technical Field

[0001] This invention relates to the field of geotechnical engineering safety monitoring technology, specifically to a method, device, terminal, and medium for detecting minute displacements on the surface of soil and rock. Background Technology

[0002] In the field of geotechnical engineering monitoring, traditional displacement detection technologies mainly include total station surveying, LiDAR (Liquid Optical Array Scanner), InSAR (Inductively Coupled Aperture Radar Interferometry), and close-range photogrammetry. Total station surveying monitors soil and rock by manually operating a total station to measure the angle and distance of a prism at predetermined monitoring points, calculating changes in three-dimensional coordinates. LiDAR monitors soil and rock by acquiring surface three-dimensional deformation information from laser point cloud data. InSAR technology monitors soil and rock by analyzing surface deformation using satellite radar interferometric images, suitable for large-scale monitoring. Close-range photogrammetry monitors soil and rock by reconstructing a three-dimensional model of the target from multiple angle photographs.

[0003] Currently, monitoring soil and rock using total station measurements suffers from drawbacks such as low efficiency, poor real-time performance, and high cost. Monitoring soil and rock using laser scanners is hampered by extremely high equipment costs and poor environmental adaptability. Monitoring soil and rock using full InSAR technology is limited by low spatial resolution, severe susceptibility to vegetation obstruction, and long revisit cycles. Monitoring soil and rock using close-range photogrammetry suffers from reliance on high-precision targets, insufficient lens distortion correction, and high algorithm complexity. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention proposes a method, device, terminal, and medium for detecting minute displacements on soil and rock surfaces, aiming to improve the accuracy of soil and rock monitoring, realize dynamic monitoring of soil and rock, and enhance the system compatibility and scalability of soil and rock monitoring methods.

[0005] In a first aspect, embodiments of this application provide a method for detecting minute displacements on the surface of soil and rock, used to detect the displacement of soil and rock with targets arranged in a grid pattern, the method comprising: Acquire a target image set, camera parameters, and target deployment location information. The target image set includes several target images and several shooting times for capturing the target images. Based on the target image set, image point displacement information is obtained; The target displacement information is obtained based on the image point displacement information, the target deployment position information, and the camera parameters; Based on the camera parameters and the target deployment location information, the target displacement compensation information is obtained; Based on the target displacement information and the target displacement compensation information, a displacement cloud map is obtained.

[0006] Optionally, the camera parameters include camera lens position, camera optical axis, camera focal length, and camera diagonal length. Obtaining target displacement compensation information based on the camera parameters and the target deployment position information includes: Based on the camera lens position, the camera optical axis, and the target placement information, the first included angle, the image point optical axis distance information, and the second included angle information are obtained. The first coupling parameter and the second coupling parameter are obtained based on the camera focal length and the camera diagonal length; Based on the first coupling parameter, the second coupling parameter, the first included angle, the image point optical axis distance information, and the second included angle information, the target displacement compensation amount information is obtained.

[0007] Optionally, obtaining the target displacement compensation information based on the first coupling parameter, the second coupling parameter, the first included angle, the image point optical axis distance information, and the second included angle information includes: ; in, This represents the target displacement compensation for the i-th target. These are the first fitted parameters; These are the second fitting parameters; The third fitting parameter; This is the first coupling parameter; This is the second coupling parameter; The distance between the image point and the optical axis corresponding to the i-th target; The first included angle; It is the second included angle corresponding to the i-th target.

[0008] Optionally, before obtaining the target displacement compensation information based on the first coupling parameter, the second coupling parameter, the first included angle, the image point optical axis distance information, and the second included angle information, the following steps are included: Acquire the initial position information of the calibration target, the position information of the calibration target after movement, and the calibration target dataset. The calibration target dataset includes several camera pitch angles, a set of calibration target images corresponding to the camera pitch angles, and calibration camera parameters corresponding to the camera pitch angles. Based on the calibrated target image set, the image point displacement information is calculated; Based on the calculated image point displacement information, the initial position information of the calibration target, and the calibration camera parameters, the first measurement target displacement information is obtained; Based on the initial position information of the calibration target and the position information of the calibration target after it has moved, the displacement information of the second measurement target is obtained; Based on the second measured target displacement information, the calibration camera parameters, the calibration target initial position information, and the first measured target displacement information, the first fitting parameters, the second fitting parameters, and the third fitting parameters are obtained.

[0009] Optionally, the calibration camera parameters include the calibration camera lens position, calibration camera optical axis, calibration camera focal length, and calibration camera diagonal length. The step of obtaining the first fitting parameters, the second fitting parameters, and the third fitting parameters based on the measured displacement difference information, the calibration camera parameters, the initial position information of the calibration target, and the first measured target displacement information includes: Based on the calibration camera lens position, calibration camera optical axis and the initial position information of the calibration target, the first calibration angle, the calibration image point optical axis distance information and the second calibration angle information are obtained; Based on the second measured target displacement information and the first measured target displacement information, the difference information of the measured displacement values ​​is obtained; Based on the focal length of the calibration camera and the diagonal length of the calibration camera, the first calibration coupling parameter and the second calibration coupling parameter are obtained; Based on the measured displacement difference information, the first calibration coupling parameter, the second calibration coupling parameter, the first calibration angle, the optical axis distance information of the calibration image point, and the second calibration angle information, the error parameters of all calibration targets are fitted to obtain the first fitting parameter, the second fitting parameter, and the third fitting parameter.

[0010] Optionally, the step of fitting the error parameters of all calibration targets based on the measured displacement difference information, the first calibration coupling parameter, the second calibration coupling parameter, the calibration radial distance information, the calibration azimuth angle information, and the calibration target camera included angle information to obtain a first fitting parameter, a second fitting parameter, and a third fitting parameter includes: The fitting parameters to be solved are input as parameter vectors into the virtual physical field parameter equilibrium model, and the force information applied to the data points is obtained by combining the measured displacement value difference information. By simulating a damped dynamic system, the parameter vector is initialized to obtain the initial particle position and initial particle velocity. Calculate the resultant force applied by all data points based on the initial particle position, the initial particle velocity, and the force information applied at the data points; The particle velocity, particle position, and update step size are obtained by updating the particle velocity, updating the particle position, and adjusting the adaptive step size of the dynamic system based on the resultant force applied to all data points. Based on the updated particle velocity, updated particle position, updated step size, and the force information applied to the data points, the resultant force applied to the next updated data points is determined; based on the resultant force applied to the next updated data points, the next updated particle velocity, the next updated particle position, and the next updated step size are obtained, and the first fitting parameters, the second fitting parameters, and the third fitting parameters are obtained after the parameter vector satisfies the convergence condition.

[0011] Optionally, the step of inputting the fitted parameters to be solved as parameter vectors into the virtual physics field parameter equilibrium model, and combining the measured displacement difference information to obtain the applied force information at the data points, includes: The fitting parameters to be solved are input as parameter vectors into the virtual physics field parameter equilibrium model to obtain the information of the difference in calculated displacement values; Based on the measured displacement difference information and the calculated displacement difference information, the calibration target residual information is obtained.

[0012] Optionally, obtaining the applied force information at the data point based on the calibration target residual information includes: ; Where s is the scale parameter; To calibrate the residual of target j at the nth camera pitch angle; The residual function relative to the parameter vector The gradient; Let L2 norm be the gradient vector; It is a very small positive number.

[0013] Optionally, based on the measured displacement value difference information and the measured displacement value difference information, the calibration target residual information is obtained, including: ; in, To calibrate the target residual of target j at the nth camera pitch angle; The difference in measured displacement values ​​of the j-th calibration target at the n-th camera elevation angle; This is the difference in displacement values ​​calculated for the j-th calibration target at the n-th camera elevation angle.

[0014] Secondly, embodiments of this application provide a device for detecting minute displacements on soil and rock surfaces, comprising: The information acquisition module is used to acquire target image set, camera parameters and target deployment location information. The target image set includes several target images and several shooting times of the target images. The image point displacement determination module is used to obtain image point displacement information based on the target image set; The target displacement determination module is used to obtain target displacement information based on the image point displacement information, the target deployment position information, and the camera parameters. The displacement compensation determination module is used to obtain target displacement compensation information based on the camera parameters and the target deployment position information. The displacement cloud map determination module is used to obtain a displacement cloud map based on the target displacement information and the target displacement compensation amount information.

[0015] Thirdly, embodiments of this application provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method for detecting minute displacements on the soil and rock surface as described in any one of the first aspects above.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for detecting minute displacements on the surface of soil and rock as described in any one of the first aspects above.

[0017] Fifthly, embodiments of this application provide a computer program product that, when run on a terminal device, causes the terminal device to execute the method for detecting minute displacements on the surface of soil and rock as described in any of the first aspects.

[0018] This application obtains a target image set, camera parameters, and target deployment location information. The target image set includes several target images and several shooting times for those images. Based on the target image set, image point displacement information is obtained. Based on the image point displacement information, the target deployment location information, and the camera parameters, target displacement information is obtained. Based on the camera parameters and the target deployment location information, target displacement compensation information is obtained. Based on the target displacement information and the target displacement compensation information, a displacement cloud map is obtained. This improves the accuracy of soil and rock monitoring, enables dynamic monitoring of soil and rock, and enhances the system compatibility and scalability of soil and rock monitoring methods. Attached Figure Description

[0019] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0020] Figure 1 This is a schematic flowchart of a method for detecting minute displacements on the surface of soil and rock provided in an embodiment of this application; Figure 2 This is a flowchart illustrating the second embodiment of the method for detecting minute displacements on the soil and rock surface provided in this application; Figure 3 This is a schematic diagram of the structure of the micro-displacement detection device on the soil and rock surface provided in the embodiments of this application; Figure 4 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application. Detailed Implementation

[0021] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0022] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0023] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0024] The execution subject of the method for detecting minute displacements on the soil and rock surface provided in this application embodiment can be a device for detecting minute displacements on the soil and rock surface. The device can acquire a target image set, camera parameters, and target placement information. The target image set includes several target images and several shooting times of the target images. Based on the target image set, image point displacement information is obtained. Based on the image point displacement information, the target placement information, and the camera parameters, target displacement information is obtained. Based on the camera parameters and the target placement information, target displacement compensation information is obtained. Based on the target displacement information and the target displacement compensation information, a displacement cloud map is obtained.

[0025] Figure 1 A schematic flowchart illustrating the detection of minute displacements on soil and rock surfaces according to an embodiment of this application is shown. This is an example and not a limitation; the method can be applied to the aforementioned device for detecting minute displacements on soil and rock surfaces. Figure 1 As shown, the method may include: S10, acquire target image set, camera parameters and target deployment location information, wherein the target image set includes several target images and several shooting times of the target images; To improve the accuracy of soil and rock monitoring, achieve dynamic monitoring of soil and rock, and enhance the system compatibility and scalability of soil and rock monitoring methods, a soil and rock surface micro-displacement detection device acquires a target image set, camera parameters, and target deployment location information. The target image set includes several target images and several shooting times for capturing these images. The target images are those captured by the camera at the specified shooting times; these images can be images that have undergone noise reduction and feature extraction. The camera parameters include camera tilt angle (camera pitch angle), camera lens position, camera optical axis, camera focal length, and camera diagonal length. The target deployment location information is the actual position or coordinate position of the target at the initial deployment. The target image set is the set of images captured by the camera every 30 minutes, 20 minutes, or 60 minutes after setting the timer mode; the resolution of the camera when capturing the target is 1920×1080. The shooting time is the time the camera captures the target, and the interval between two shooting times can be 30 minutes, 20 minutes, or 60 minutes. The method for detecting minute displacements on rock and soil surfaces is particularly suitable for monitoring millimeter-level displacements in scenarios such as open-pit mine slopes, landslides, and tunnel surrounding rock. The target placement information consists of data information composed of the placement locations of i targets.

[0026] S20, obtain image point displacement information based on the target image set; After acquiring a target image set, the micro-displacement detection device for soil and rock surfaces obtains image point displacement information based on the target image set. Specifically, it can determine the image point displacement value based on the target size and direction of movement. That is, it extracts the image plane coordinates (x, y) of feature points from the real-time acquired target images. The image point displacement information consists of data information composed of the image point displacements corresponding to i targets.

[0027] S30, based on the image point displacement information, the target deployment position information, and the camera parameters, the target displacement information is obtained; After acquiring the target placement location information and camera parameters, as well as the image point displacement information, the rock and soil surface micro-displacement detection device obtains the target displacement information based on the target image point displacement information, the target placement location information, and the camera parameters.

[0028] In one implementation, the camera parameters include the camera lens position and the camera focal length. Obtaining the target displacement information based on the target image point displacement information, the target deployment position information, and the camera parameters specifically includes: obtaining object distance information based on the target deployment position information and the camera lens position; and processing the camera focal length, the object distance information, and the image point displacement information using the principle of similar triangles to obtain the target displacement information. The target displacement information consists of data information composed of the target displacements corresponding to i targets.

[0029] S40, based on the camera parameters and the target deployment position information, obtain the target displacement compensation information; After acquiring camera parameters and target placement information, as well as target displacement information, the micro-displacement detection device for soil and rock surfaces obtains target displacement compensation information based on the camera parameters and target placement information. The target displacement compensation information consists of data composed of the target displacement compensation amounts corresponding to i targets.

[0030] Furthermore, referring to Figure 2 , Figure 2 This is a schematic flowchart of the second embodiment of the method for detecting minute displacements on the surface of soil and rock according to the present invention. Based on the above... Figure 2 In the illustrated embodiment, the camera parameters include camera lens position, camera optical axis, camera focal length, and camera diagonal length; obtaining target displacement compensation information based on the camera parameters and the target deployment position information includes: S41, based on the camera lens position, the camera optical axis and the target placement position information, obtain the first included angle, the image point optical axis distance information and the second included angle information; After acquiring the camera lens position, camera optical axis and target placement information, the rock and soil surface micro-displacement detection device obtains the first included angle, image point optical axis distance information and second included angle information based on the camera lens position, camera optical axis and target placement information; As one implementation method, a first included angle, image point optical axis distance information, and second included angle information are obtained based on the camera lens position, the camera optical axis, and the target placement position information. Specifically, this includes: obtaining the first included angle based on the camera lens position and the camera optical axis; and obtaining the image point optical axis distance information and the second included angle information based on the camera lens position, the camera optical axis, and the target placement position information.

[0031] The camera lens position refers to the camera's coordinate position.

[0032] The spatial coordinate system is defined by the origin O at the optical center of the camera lens. The Zc axis (optical axis) is perpendicular to the camera's imaging plane (CCD / CMOS plane) and points towards the scene. The Xc and Yc axes are parallel to two sides of the imaging plane, forming a right-handed coordinate system (Xc axis is horizontal to the right, and Yc axis is vertical downward).

[0033] Among them, the first included angle The angle between the optical axes of the target camera; the first angle Yc is the angle between the line connecting a point in space (such as a target feature point) and the origin O, and the camera's optical axis (Zc axis). A symbol is introduced for this angle to accurately describe the asymmetric distortion caused by the camera's pitch attitude. It is defined that when the point is above the optical axis (in the half-space where Yc < 0), Yc is considered to be in a certain position. When located below the optical axis (half-space where Yc>0) Its absolute value represents the angle of deviation from the optical axis. The angle between the line connecting the center point of the target and the optical center of the camera lens and the optical axis (that is, the first angle).

[0034] Among them, the distance between the optical axis of the image point The Euclidean distance (in mm) from the image point formed by the object point (target) to the principal point (the intersection of the optical axis and the imaging plane); the distance between the image point and the optical axis. That is, the optical axis distance of the image point corresponding to the i-th target. This represents the distance from the image point corresponding to the i-th target to the optical axis on the imaging plane. The image point optical axis distance information is composed of data information consisting of the optical axis distances of the image points corresponding to the i targets.

[0035] Principal point: The intersection of the optical axis and the imaging plane, with coordinates as follows: , where f is the focal length. Since the imaging point lies on the focal plane, the coordinates of the principal point are... When the object distance is infinite, the image distance is equal to the focal length, so the image is formed on the focal plane.

[0036] Here, the image point is the projection of the object point onto the imaging plane. The image point can be determined using the current target position information. Image points are automatically identified from the captured photograph using image recognition algorithms (such as Hough circle detection, template matching, or feature point extraction) to obtain their image plane coordinates. , (Unit: pixels), then normalized to spatial coordinates as follows: .

[0037] Among them, the second included angle The angle between the position vector of the image point on the imaging plane and the positive direction of the Xc axis has the following geometric meaning: it describes the direction of the image point relative to the horizontal axis of the coordinate system. The second angle... It is the second included angle corresponding to the i-th target. The second angle information is the angle between the image point corresponding to the i-th target and the horizontal direction on the imaging plane. The second angle information is the data information composed of the second angles corresponding to the i-th targets.

[0038] Positive and negative values ​​and quadrants: Positive and negative values ​​follow the right-hand rule (rotation counterclockwise around the Zc axis from the positive Xc axis is positive, and rotation clockwise is negative).

[0039] Typically, a planar coordinate system can be divided into four quadrants: First quadrant (Xc>0, Yc<0): φ is negative (or 0 to -π / 2).

[0040] Second quadrant (Xc<0, Yc<0): φ is negative (or -π / 2 to -π).

[0041] Third quadrant (Xc<0, Yc>0): φ is a positive value (or π to π / 2).

[0042] Fourth quadrant (Xc>0, Yc>0): φ is a positive value (or π / 2 to 0).

[0043] S42, based on the camera focal length and the camera diagonal length, obtain the first coupling parameter and the second coupling parameter; After acquiring the camera focal length and diagonal length, the soil surface micro-displacement detection device derives a first coupling parameter and a second coupling parameter based on these parameters. The first coupling parameter... ; Let be the camera focal length; where, the second coupling parameter ; This is the diagonal length of the sensor, which is also the diagonal length of the camera. Second coupling parameter. These are constants related to the sensor specifications.

[0044] S43, based on the first coupling parameter, the second coupling parameter, the first included angle, the image point optical axis distance information, and the second included angle information, the target displacement compensation amount information is obtained.

[0045] After obtaining the first coupling parameter, the second coupling parameter, the first included angle, the image point optical axis distance information, the second included angle information, and the target displacement information, the micro-displacement detection device on the soil and rock surface obtains the target displacement compensation amount information based on the first coupling parameter, the second coupling parameter, the first included angle, the image point optical axis distance information, and the second included angle information.

[0046] As one implementation, obtaining the target displacement compensation information based on the first coupling parameter, the second coupling parameter, the first included angle, the image point optical axis distance information, and the second included angle information includes: ; in, This represents the target displacement compensation for the i-th target. These are the first fitted parameters; These are the second fitting parameters; The third fitting parameter; This is the first coupling parameter; This is the second coupling parameter; The distance between the image point and the optical axis corresponding to the i-th target; The first included angle; It is the second included angle corresponding to the i-th target.

[0047] in This can suppress the excessive amplification of large-angle curvature terms, making the model stable at the edge of the field of view. (Denominator) Considering the coupling of higher-order radial distortion of the image plane to the tangential component.

[0048] As one implementation, before obtaining the target displacement compensation information based on the first coupling parameter, the second coupling parameter, the first included angle, the image point optical axis distance information, and the second included angle information, the following steps are included: A1, obtain the first fitting parameters, the second fitting parameters, and the third fitting parameters.

[0049] Before obtaining the target displacement compensation information, the soil and rock surface micro-displacement detection device acquires or obtains the first fitting parameter, the second fitting parameter, and the third fitting parameter.

[0050] In one implementation, obtaining or acquiring the first fitting parameters, the second fitting parameters, and the third fitting parameters specifically includes: acquiring the initial position information of the calibration target, the position information of the calibration target after movement, and the calibration target dataset, wherein the calibration target dataset includes several camera pitch angles, a set of calibration target images corresponding to the camera pitch angles, and calibration camera parameters corresponding to the camera pitch angles; obtaining calculated image point displacement information based on the calibration target image set; obtaining first measured target displacement information based on the calculated image point displacement information, the initial position information of the calibration target, and the calibration camera parameters; obtaining second measured target displacement information based on the initial position information of the calibration target and the position information of the calibration target after movement; and obtaining the first fitting parameters, the second fitting parameters, and the third fitting parameters based on the second measured target displacement information, the calibration camera parameters, the initial position information of the calibration target, and the first measured target displacement information.

[0051] As one implementation, before obtaining the target displacement compensation information based on the first coupling parameter, the second coupling parameter, the first included angle, the image point optical axis distance information, and the second included angle information, the following steps are included: A1. Obtain the initial position information of the calibration target, the position information of the calibration target after movement, and the calibration target dataset. The calibration target dataset includes several camera pitch angles, a set of calibration target images corresponding to the camera pitch angles, and calibration camera parameters corresponding to the camera pitch angles. Before determining the target displacement compensation information, the soil and rock surface micro-displacement detection device acquires the initial position information of the calibration target, the position information of the calibration target after movement, and a calibration target dataset. The calibration target dataset includes several camera pitch angles, a set of calibration target images corresponding to the camera pitch angles, and calibration camera parameters corresponding to the camera pitch angles. Here, the camera pitch angle is n; the calibration target image set consists of images of j calibration targets (all calibration targets) taken by the camera at n camera pitch angles before the calibration target moves (initial position) and after the calibration target moves (position after movement). The calibration target image set includes... Zhang images; camera parameters are calibrated at n camera pitch angles; initial target position information is determined by... The data information consists of the initial positions of the calibration targets corresponding to each calibration target. The position information after the calibration targets move is composed of... The data information consists of the positions of the calibration targets after they have moved, corresponding to each calibration target.

[0052] For example, each target has a set of data, so 50 targets would result in 50 sets of data. Then, adjust the lens tilt angle n times (in 5° increments), repeating the above steps for each adjustment. This will ultimately yield 50 × n sets of data. The more data available, the better the calibrated parameters will be. , , The more accurate.

[0053] To determine the first, second, and third fitting parameters, this application proposes a novel parameter fitting paradigm. Its core principle is completely different from traditional optimization frameworks based on error minimization (such as least squares) or probabilistic inference (such as Bayesian estimation). Inspired by the concept in theoretical physics of "particles moving in a potential field until equilibrium is reached," this algorithm uses the parameter vector to be solved... It is regarded as a "point mass" in a high-dimensional virtual physical space, and by simulating the relaxation motion of the point mass in the "resultant force field" generated by all observation data, it is finally located at the equilibrium position where the resultant force is zero. This position is the optimal parameter solution.

[0054] A2, based on the calibrated target image set, calculate the image point displacement information; After acquiring a set of images of a calibration target, the micro-displacement detection device for soil and rock surfaces calculates the displacement information of image points based on these images. The calculated image point displacement information is obtained by... The data information consists of the displacement of the calculated image point corresponding to each calibration target.

[0055] A3. Based on the calculated image point displacement information, the initial position information of the calibration target, and the calibration camera parameters, the first measurement target displacement information is obtained. After acquiring the initial position information of the calibration target and the parameters of the calibration camera, and obtaining the calculated image point displacement information, the soil and rock surface micro-displacement detection device obtains the first measurement target displacement information based on the calculated image point displacement information, the initial position information of the calibration target, and the calibration camera parameters. The first measurement target displacement information is derived from... The data information consists of the displacement of the first measured target corresponding to each calibration target.

[0056] A4. Based on the initial position information of the calibration target and the displacement information of the first measurement target, the displacement information of the second measurement target is obtained. After acquiring the initial position information of the calibration target and obtaining the first measurement target displacement information, the soil and rock surface micro-displacement detection device obtains the second measurement target displacement information based on the initial position information of the calibration target and the first measurement target displacement information. The second measurement target displacement information is obtained by... The data information consists of the displacement of the second measurement target corresponding to each calibration target.

[0057] A5. Based on the second measured target displacement information, the calibration camera parameters, the calibration target initial position information, and the first measured target displacement information, the first fitting parameters, the second fitting parameters, and the third fitting parameters are obtained. After acquiring the calibration camera parameters and the initial position information of the calibration target, as well as the second and first measurement target displacement information, the soil and rock surface micro-displacement detection device obtains the first fitting parameters, the second fitting parameters, and the third fitting parameters based on the second measurement target displacement information, the calibration camera parameters, the initial position information of the calibration target, and the first measurement target displacement information.

[0058] As one implementation, the calibrated camera parameters include the calibrated camera lens position, calibrated camera optical axis, calibrated camera focal length, and calibrated camera diagonal length. Based on the second measured target displacement information, the calibrated camera parameters, the calibrated target initial position information, and the first measured target displacement information, a first fitting parameter, a second fitting parameter, and a third fitting parameter are obtained, specifically including: B1. Based on the calibration camera lens position, the calibration camera optical axis, and the initial position information of the calibration target, the first calibration angle, the calibration image point optical axis distance information, and the second calibration angle information are obtained. The micro-displacement detection device for soil and rock surfaces, after acquiring information on the position of the calibration camera lens, the optical axis of the calibration camera, and the initial position of the calibration target, as well as obtaining the first measurement target displacement information, derives, based on the calibration camera lens position, the optical axis of the calibration camera, and the initial position of the calibration target, information on the first calibration angle, the distance between the calibration image point and the optical axis, and information on the second calibration angle. The distance between the calibration image point and the optical axis is determined by... The data information consists of the optical axis distances between the calibration image points corresponding to each calibration target. The second calibration angle information is composed of... The data information consists of the second calibration angle corresponding to each calibration target.

[0059] As one implementation method, based on the calibration camera lens position, calibration camera optical axis, and initial position information of the calibration target, a first calibration angle, the distance information of the calibration image point optical axis, and a second calibration angle are obtained. Specifically, this includes: obtaining the first calibration angle based on the calibration camera lens position and the calibration camera optical axis; and obtaining the distance information of the calibration image point optical axis and the second calibration angle based on the calibration camera lens position, calibration camera optical axis, and initial position information of the calibration target.

[0060] Specifically, to obtain the first calibration angle, the optical axis distance information of the calibration image point, and the second calibration angle information, please refer to step S41; Among them, the calibration camera lens position is the coordinate position of the calibration camera.

[0061] The spatial coordinate system is defined with the optical center of the calibration camera lens as the origin O. The Zc axis (optical axis) is perpendicular to the imaging plane of the calibration camera (CCD / CMOS plane) and points in the direction of the scene. The Xc and Yc axes are parallel to two sides of the imaging plane, forming a right-handed coordinate system (Xc axis is horizontal to the right, and Yc axis is vertical downward).

[0062] Wherein, the first calibrated included angle at the nth camera pitch angle. The angle between the target camera and the optical axis at the nth camera pitch angle; the first calibration angle at the nth camera pitch angle. Let Yc be the angle between the line connecting a point in space (such as a target feature point) and the origin O, and the optical axis (Zc axis) of the calibration camera. A symbol is introduced for this angle to accurately describe the asymmetric distortion caused by the camera's pitch attitude. At the nth camera pitch angle, it is defined that when the point is above the optical axis (in the half-space where Yc < 0),... When located below the optical axis (half-space where Yc>0) Its absolute value represents the angle of deviation from the optical axis. The angle between the line connecting the center point of the calibration target and the optical center point of the calibration camera lens at the nth camera pitch angle and the optical axis (that is, the first calibration angle at the nth camera pitch angle).

[0063] Among them, the optical axis distance of the calibrated image point The Euclidean distance (in mm) from the principal point (the intersection of the optical axis and the imaging plane) to the image point formed by the object point (target) at the nth camera pitch angle; calibrating the optical axis distance of the image point. That is, the optical axis distance of the calibration image point corresponding to the j-th calibration target at the n-th camera pitch angle. (Optical axis distance of calibration image point) Let be the distance from the image point corresponding to the j-th target on the imaging plane to the optical axis at the n-th camera pitch angle.

[0064] Principal point: The intersection of the optical axis and the imaging plane, with coordinates as follows: , where f is the focal length. Since the imaging point lies on the focal plane, the coordinates of the principal point are... When the object distance is infinite, the image distance is equal to the focal length, so the image is formed on the focal plane.

[0065] Here, the image point is the projection of the object point onto the imaging plane. The image point can be determined using the current position information of the calibration target. The image point is automatically identified from the captured photograph using image recognition algorithms (such as Hough circle detection, template matching, or feature point extraction) to obtain its image plane coordinates. , (Unit: pixels), then normalized to spatial coordinates as follows: .

[0066] Among them, the second calibration angle Let Xc be the angle between the position vector of the image point on the imaging plane and the positive direction of the Xc axis at the nth camera pitch angle. Geometrically, it describes the direction of the image point relative to the horizontal axis of the coordinate system. Second calibration angle. To calibrate the second calibration angle corresponding to target j at the nth camera pitch angle. Let be the angle between the image point corresponding to the j-th target on the imaging plane and the horizontal direction at the n-th camera pitch angle.

[0067] B2, based on the second measured target displacement information and the first measured target displacement information, obtain the measured displacement value difference information; After obtaining the displacement information of the second and first measuring targets, the micro-displacement detection device for soil and rock surfaces calculates the displacement difference information based on the displacement difference information and the first measuring target displacement information. The displacement difference is the difference between the second measuring target displacement information (the displacement value of the actual directly measured calibration target) and the first measuring target displacement information (the displacement value of the target calculated using similar triangles). The displacement difference information is derived from... The data information consists of the difference in the measured displacement values ​​corresponding to each calibration target.

[0068] B3. Based on the focal length of the calibration camera and the diagonal length of the calibration camera, the first calibration coupling parameter and the second calibration coupling parameter are obtained; After acquiring the focal length and diagonal length of the calibration camera, the micro-displacement detection device for soil and rock surfaces obtains a first calibration coupling parameter and a second calibration coupling parameter based on these parameters. The first calibration coupling parameter... ; To calibrate the camera focal length; wherein, the second calibration coupling parameter ; To calibrate the sensor's diagonal length, which is also to calibrate the camera's diagonal length. The second calibration step is to determine the coupling parameters. To fix constants related to the sensor specifications for calibration.

[0069] B4. Based on the measured displacement difference information, the first calibration coupling parameter, the second calibration coupling parameter, the first calibration angle, the optical axis distance information of the calibration image point, and the second calibration angle information, the error parameters of all calibration targets are fitted to obtain the first fitting parameter, the second fitting parameter, and the third fitting parameter.

[0070] After obtaining the measured displacement difference information, the first calibration coupling parameter, the second calibration coupling parameter, the first calibration angle, the distance between the calibration image point and the optical axis, and the second calibration angle information, the micro-displacement detection device on the rock and soil surface fits the error parameters of all calibration targets according to the measured displacement difference information, the first calibration coupling parameter, the second calibration coupling parameter, the first calibration angle, the distance between the calibration image point and the optical axis, and the second calibration angle information to obtain the first fitting parameter, the second fitting parameter, and the third fitting parameter.

[0071] When comparing the first fitting parameters, the second fitting parameters, and the third fitting parameters, the calculation formula for the calibration target displacement compensation amount is obtained by reference.

[0072] As one implementation method, the error parameters of all calibration targets are fitted based on the measured displacement difference information, the first calibration coupling parameter, the second calibration coupling parameter, the first calibration angle, the optical axis distance information of the calibration image point, and the second calibration angle information to obtain a first fitting parameter, a second fitting parameter, and a third fitting parameter, including: C1, using the fitting parameters to be solved as the parameter vector input into the virtual physical field parameter equilibrium model, and combining the measured displacement value difference information, the force information applied to the data points is obtained; When fitting error parameters, the micro-displacement detection device on the soil and rock surface uses the fitting parameters to be solved as the parameter vector input into the virtual physical field parameter equilibrium model, and combines the measured displacement value difference information to obtain the applied force information of the data point.

[0073] As one implementation method, the fitting parameters to be solved are input as parameter vectors into the virtual physics field parameter equilibrium model. Combined with the measured displacement difference information, the applied force information at the data points is obtained, including: D1, using the fitting parameters to be solved as the parameter vector input into the virtual physics field parameter equilibrium model, obtains the information of the difference in calculated displacement values; When fitting error parameters, the micro-displacement detection device on the soil and rock surface uses the fitting parameters to be solved as the parameter vector input into the virtual physical field parameter equilibrium model to obtain the information of the difference in calculated displacement values.

[0074] The design of the force function is one of the key innovations of this algorithm. It must satisfy two core characteristics: directionality and robustness. Directionality means that the direction of the force should guide the particle to reduce the residual; robustness means that the force generated by outliers should have an upper limit and should not disrupt the balance of the entire system.

[0075] First, the model parameters , , The calibration was conducted on-site during monitoring. Targets were first deployed, and the spatial coordinates of the target center and the optical center of the camera lens were measured using a total station. The coordinates of each target at the nth camera elevation angle were then calculated. From the image captured by the camera, the elevation angle of each target at the nth camera angle can be calculated. and Then, each target is randomly moved (the displacement value is very small, such as 0.5~10cm, which is on the same order of magnitude as the monitoring and warning value). The spatial position of the target after the movement is measured by a total station. The displacement value of the target can be known by measuring the displacement value of the target. The camera position remains unchanged. The displacement value of the target image point is calculated by two imaging operations. The target displacement value is further calculated by the displacement value of the image point.

[0076] For example, each target has a set of data, so 50 targets would result in 50 sets of data. Then, adjust the lens tilt angle n times (in 5° increments), repeating the above steps for each adjustment. This will ultimately yield 50 × n sets of data. The more data available, the better the calibrated parameters will be. , , The more accurate.

[0077] To determine the first, second, and third fitting parameters, this application proposes a novel parameter fitting paradigm. Its core principle is completely different from traditional optimization frameworks based on error minimization (such as least squares) or probabilistic inference (such as Bayesian estimation). Inspired by the concept in theoretical physics of "particles moving in a potential field until equilibrium is reached," this algorithm uses the parameter vector to be solved... It is regarded as a "point mass" in a high-dimensional virtual physical space, and by simulating the relaxation motion of the point mass in the "resultant force field" generated by all observation data, it is finally located at the equilibrium position where the resultant force is zero. This position is the optimal parameter solution.

[0078] The specific formula for obtaining the displacement difference information is as follows: ; in, To calculate the difference in displacement values ​​for calibrating target j at the nth camera pitch angle; These are the first fitted parameters; These are the second fitting parameters; The third fitting parameter; The first calibration coupling parameter; This is the second calibration coupling parameter; To calibrate the optical axis distance of the image point corresponding to target j at the nth camera pitch angle; To calibrate the second calibration angle corresponding to target j at the nth camera pitch angle; Let be the first calibration angle at the nth camera pitch angle.

[0079] in This can suppress the excessive amplification of large-angle curvature terms, making the model stable at the edge of the field of view. (Denominator) Considering the coupling of higher-order radial distortion of the image plane to the tangential component.

[0080] D2. Based on the measured displacement difference information and the calculated displacement difference information, the calibration target residual information is obtained.

[0081] After obtaining the difference information between measured and calculated displacement values, the micro-displacement detection device for soil and rock surfaces uses these information to obtain the residual information of the calibration target. The residual information of the calibration target is derived from... The data information consists of the residuals of each calibration target.

[0082] As one implementation method, the calibration target residual information is obtained based on the measured displacement value difference information and the measured displacement value difference information, including: ; in, The residual for calibrating target j at the nth camera pitch angle is the calibration residual for calibrating target j at the nth camera pitch angle. This is the difference in measured displacement values ​​of the j-th calibration target at the n-th camera pitch angle, which is also the difference in measured displacement values ​​of the j-th calibration target at the n-th camera pitch angle. This is the difference in calculated displacement values ​​of the j-th calibration target at the n-th camera elevation angle, which is also the difference in calculated displacement values ​​of the j-th calibration target at the n-th camera elevation angle.

[0083] For each data point i, the fitting residual is defined as the difference between the calculated value from the model and the observed value. This indicates the measured value (the subscript m represents measured). Indicates the calculated value (the subscript 'c' stands for calculated): ; D3. Based on the calibration target residual information, obtain the force information applied to the data point.

[0084] After obtaining the residual information of the calibration target, the micro-displacement detection device on the soil and rock surface obtains the applied force information at the data points based on the residual information. The applied force information at the data points is obtained from... The data information consists of the applied force at each data point corresponding to a calibration target.

[0085] As one implementation method, the force applied to data point nj (the calibration target j at the nth camera pitch angle) is defined using the following nonlinear function. Based on the calibration target residual information, the force information applied to the data point is obtained, including: ; Where s is the scale parameter; To calibrate the residual of target j at the nth camera pitch angle; That is, calibrating the target residual information; The residual function relative to the parameter vector The gradient; Let L2 norm be the gradient vector; It is a very small positive number.

[0086] in, The function is a saturated function. When the residual When the absolute value is very large (it may be due to outliers). The value approaches π / 2, thus bringing the entire factor close to 1. s is a scaling parameter used to control how quickly the force reaches saturation. A larger s value means that a smaller residual can produce a force close to its maximum value. It is the residual function relative to the parameter vector gradient (i.e.) It indicates in which direction the parameter particle moves to most quickly reduce the residual of the current data point. It is the L2 norm of the gradient vector. γ is a very small positive number (e.g., ...). This prevents division by zero errors when the gradient norm is close to zero.

[0087] Here, the parameter particle is the combination of parameters to be optimized. It is considered as a virtual particle with "mass" and "velocity," moving within its high-dimensional parameter space. The DataPointForceSource applies force to the parameter particle for each observed data point i (calibration target). Apply a "force" The direction of this force is to make the particle Along this path, the fitting residual for that data point can be reduced. The direction of motion. The resultant force field is the vector sum of the forces generated by all data points, constituting the physical environment of the parametric particle. The equilibrium state and solution represent the optimal parameters. That is, the state in which the net force on the particle is zero. In this state, the tension / thrust generated by all data points reaches a dynamic equilibrium. The relaxation process is the algorithm's simulation of the particle's motion in a medium with a "dissipative" effect (similar to damped vibration), causing its kinetic energy to gradually decay and eventually stabilize near the equilibrium point.

[0088] C2 is used to simulate a damped dynamic system, initialize the parameter vector, and obtain the initial particle position and initial particle velocity. After obtaining the applied force information at the data points, the micro-displacement detection device on the rock and soil surface initializes the parameter vector by simulating a damped dynamic system, thereby obtaining the initial particle position and initial particle velocity.

[0089] Here, the parameter particle is the combination of parameters to be optimized. It is considered as a virtual particle with "mass" and "velocity," moving within its high-dimensional parameter space. The DataPointForceSource applies force to the parameter particle for each observed data point i (calibration target). Apply a "force" The direction of this force is to make the particle Along this path, the fitting residual for that data point can be reduced. The direction of motion. The resultant force field is the vector sum of the forces generated by all data points, constituting the physical environment of the parametric particle. The equilibrium state and solution represent the optimal parameters. That is, the state in which the net force on the particle is zero. In this state, the tension / thrust generated by all data points reaches a dynamic equilibrium. The relaxation process is the algorithm's simulation of the particle's motion in a medium with a "dissipative" effect (similar to damped vibration), causing its kinetic energy to gradually decay and eventually stabilize near the equilibrium point.

[0090] In other words, the goal of the algorithm is to find a way to make of We achieve this by simulating a damped dynamic system. During algorithm initialization, we set the algorithm hyperparameters: The learning rate (virtual time step) is recommended to be initialized to 0.01. The momentum dissipation coefficient ( The constant γ can be 0.1 to simulate energy loss. s is the force saturation rate, recommended to be 5.0. γ is the zero-prevention constant, which can be set to... . The convergence threshold of the resultant force can be defined as follows: . As the step size convergence threshold, it can be . As the velocity convergence threshold, it can be Initialize particle position parameters. (Can be set to) (Or set based on experience). Initialize particle velocity. .

[0091] C3, calculate the resultant force applied by all data points based on the initial particle position, the initial particle velocity, and the force information applied by the data points; After obtaining the initial particle position, the initial particle velocity, and the applied force information at the data points, the micro-displacement detection device on the soil and rock surface calculates the resultant force applied by all data points (calibrating target j at the nth camera pitch angle) based on the initial particle position, initial particle velocity, and applied force information at the data points. .

[0092] C4 updates the particle velocity, particle position, and update step size by adjusting the adaptive step size of the dynamic system based on the resultant force applied to all data points. The soil surface micro-displacement detection device obtains the resultant force applied by all data points (calibrating target j at the nth camera elevation angle). Then, based on the resultant force applied to all data points, the particle velocity and particle position are updated, and the adaptive step size of the dynamic system is adjusted to obtain the updated particle velocity, updated particle position, and updated step size.

[0093] In other words, iteration loop. : When calculating the instantaneous resultant force, at the current position Calculate the resultant force applied to all data points according to the above formula. When updating particle velocities, in, for The velocity of particles that iterates over time; for The velocity of particles that iterates over time; The acceleration impulse generated by the resultant force. for The amount of velocity decay at any given moment. Its function is to simulate damping, ensuring that the system's energy is gradually dissipated and eventually stabilizes. When updating particle positions... In other words, the position is updated based on the new velocity. During adaptive step size adjustment, the dot product of two consecutive velocity vectors is calculated. If the dot product of two consecutive velocity vectors is less than 0, it indicates that the velocity direction has been drastically reversed, and the particle is "oscillating." At this time, the step size is adjusted. Halved: This can help particles stably approach the equilibrium point.

[0094] C5, based on the updated particle velocity, updated particle position, updated step size, and the force information applied to the data points, determines the resultant force applied to the next updated data points; based on the resultant force applied to the next updated data points, obtains the next updated particle velocity, the next updated particle position, and the next updated step size, and obtains the first fitting parameters, the second fitting parameters, and the third fitting parameters after the parameter vector satisfies the convergence condition.

[0095] After obtaining the updated particle velocity, updated particle position, update step size, and applied force information at the data points, the micro-displacement detection device for soil and rock surfaces determines the resultant force applied to the next updated data points based on these parameters. Based on the resultant force applied to the next updated data points, it obtains the next updated particle velocity, next updated particle position, and next update step size. Finally, after the parameter vector satisfies the convergence condition, it obtains the first fitting parameters, the second fitting parameters, and the third fitting parameters. The convergence condition includes both the first and second convergence conditions.

[0096] The first convergence condition is: That is, the net force is close enough to zero, and equilibrium has been reached.

[0097] The second convergence condition is: and In other words, the distance and speed at which the particles have moved are small enough that they have come to a standstill.

[0098] If the parameter vector satisfies either the first or second convergence condition, then the first, second, and third fitted parameters are obtained. That is, if either the first or second convergence condition is met, the loop exits, and the optimal parameter estimate is output. Otherwise, continue iterating. This includes the estimation of optimal parameters. It includes the first fitting parameter, the second fitting parameter, and the third fitting parameter. S50, based on the target displacement information and the target displacement compensation information, a displacement cloud map is obtained.

[0099] After obtaining the target displacement information and the target displacement compensation information, the micro-displacement detection device on the soil and rock surface obtains a displacement cloud map based on the target displacement information and the target displacement compensation information.

[0100] As one implementation method, a displacement cloud map is obtained based on the target displacement information and the target displacement compensation information, specifically including: E1, based on the target displacement information and the target displacement compensation information, the target displacement is corrected to obtain the target corrected displacement information; After obtaining the target displacement information and target displacement compensation information, the micro-displacement detection device for soil and rock surfaces corrects the target displacement based on these two information, thus obtaining the corrected target displacement information. The corrected target displacement information is obtained from... The data information consists of the target correction displacement corresponding to each calibration target.

[0101] in, ;in The target correction displacement for the i-th target is the actual displacement of the i-th target after correction. The target displacement is calculated for the i-th target; This represents the target displacement compensation amount for the i-th target.

[0102] For example, input parameter: first included angle The optical axis distance of the image point corresponding to the i-th target The second included angle corresponding to the i-th target , ; Fitting results Calculate the compensation amount, which is also the target displacement compensation amount. The calculated original displacement value is also the target displacement calculated for the i-th target. Finally, the displacement is corrected, which is to obtain the target corrected displacement. .

[0103] E2, Based on the target, correct the displacement information and generate a displacement cloud map; After obtaining the target-corrected displacement information, the micro-displacement detection device on the soil and rock surface generates a displacement cloud map based on this information. After obtaining the target-corrected displacement information, the data is visualized to generate the displacement cloud map, with red areas indicating displacement exceeding a threshold (>3mm). If the same area is detected to have displacement exceeding the threshold three times consecutively, an SMS alarm is automatically sent.

[0104] Comparative experiment: Simultaneous monitoring of a slope with a total station for 72 hours, the results showed: Average error: 0.28mm; Maximum error: 0.51mm; Correlation coefficient .

[0105] Environmental testing: Under rainfall conditions (visibility <50m), the target recognition rate remains above 95%.

[0106] When detecting minute displacements on the surface of soil and rock, a total station is used to measure the spatial coordinates of the target center and the optical center of the camera lens, and the coordinates of each target are calculated. The image captured by the camera can be solved. and The camera position remains unchanged, and images are captured every hour to obtain an image set. Each image set is compared with the previous one. If an image point has shifted, the target displacement value can be calculated from the image point displacement value. Then, the compensation amount Δd is calculated using a compensation model. Finally, the target displacement value calculated from the image point displacement value is corrected using high-precision correction to obtain the final target displacement value. Ultimately, a displacement cloud map and an early warning report are generated.

[0107] Compared to total stations, this application offers a 5-fold increase in monitoring efficiency and supports multi-point synchronous data acquisition; it requires no manual intervention and supports remote control. Compared to InSAR, this application achieves centimeter-level spatial resolution (superior to InSAR's 10-meter level); vegetation obstruction is reduced by 80%, making it suitable for complex scenarios such as open-pit mine slopes. Compared to LiDAR, this application reduces equipment costs by 90%, simplifies maintenance, increases data acquisition speed by 30%, and supports real-time monitoring.

[0108] This application achieves a displacement detection accuracy of 0.5mm through a discrete curvature compensation algorithm, which is superior to traditional photogrammetry (2-5mm). It also reduces system costs, lowering the total system cost by more than 60% compared to laser scanners. Furthermore, it enhances the environmental adaptability of soil and rock monitoring methods, demonstrating strong algorithm robustness and maintaining high recognition rates even under rain, fog, and low-light conditions. This application overcomes the bottleneck of traditional distortion correction through a discrete curvature compensation model. It is compatible with various target and camera types, supports rapid deployment and expansion, and improves system versatility.

[0109] This application focuses on a discrete curvature compensation algorithm as its core innovation. Through high-precision modeling and real-time compensation of image distortion, it achieves reliable monitoring of millimeter-level displacement on soil and rock surfaces. The system is compatible with various target types (including prism targets, reflectors, etc.) and possesses good versatility and environmental adaptability.

[0110] This application obtains a target image set, camera parameters, and target deployment location information. The target image set includes several target images and several shooting times for those images. Based on the target image set, image point displacement information is obtained. Based on the image point displacement information, the target deployment location information, and the camera parameters, target displacement information is obtained. Based on the camera parameters and the target deployment location information, target displacement compensation information is obtained. Based on the target displacement information and the target displacement compensation information, a displacement cloud map is obtained. This improves the accuracy of soil and rock monitoring, enables dynamic monitoring of soil and rock, and enhances the system compatibility and scalability of soil and rock monitoring methods.

[0111] For those consistent with the above, please refer to Figure 3 , Figure 3 This application provides a schematic diagram of a device for detecting minute displacements on the surface of soil and rock, as illustrated in an embodiment. Figure 3 As shown, the device includes: The information acquisition module 301 is used to acquire a target image set, camera parameters, and target deployment location information. The target image set includes several target images and several shooting times for capturing the target images. The image point displacement determination module 302 is used to obtain image point displacement information based on the target image set; The target displacement determination module 303 is used to obtain target displacement information based on the image point displacement information, the target deployment position information, and the camera parameters. The displacement compensation determination module 304 is used to obtain target displacement compensation information based on the camera parameters and the target deployment position information. The displacement cloud map determination module 305 is used to obtain a displacement cloud map based on the target displacement information and the target displacement compensation amount information.

[0112] This application also provides a terminal device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor. When the processor executes the computer program, it implements the steps in the embodiment of the method for detecting minute displacements on the soil and rock surface.

[0113] This application also provides a computer storage medium storing a computer program for electronic data exchange, which causes a computer to perform some or all of the steps of any of the methods for detecting minute displacements on soil and rock surfaces described in the above method embodiments.

[0114] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program that causes a computer to perform some or all of the steps of any of the methods for detecting minute displacements on soil and rock surfaces as described in the above method embodiments.

[0115] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable storage medium can include at least: any entity or device capable of carrying computer program code to a device / terminal equipment, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable storage media cannot be electrical carrier signals or telecommunication signals.

[0116] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0117] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0118] In the embodiments provided in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0119] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

Claims

1. A method for detecting minute displacements on soil and rock surfaces, characterized in that, The method for detecting the displacement of soil and rock with targets arranged in a grid pattern includes: Acquire a target image set, camera parameters, and target deployment location information. The target image set includes several target images and several shooting times for capturing the target images. Based on the target image set, image point displacement information is obtained; The target displacement information is obtained based on the image point displacement information, the target deployment position information, and the camera parameters; Based on the camera parameters and the target deployment location information, the target displacement compensation information is obtained; Based on the target displacement information and the target displacement compensation information, a displacement cloud map is obtained; The camera parameters include camera lens position, camera optical axis, camera focal length, and camera diagonal length. The step of obtaining target displacement compensation information based on the camera parameters and the target deployment position information includes: Based on the camera lens position, the camera optical axis, and the target placement position information, the first included angle, the image point optical axis distance information, and the second included angle information are obtained; the first included angle is the angle between the line connecting the target placement point and the origin in space and the camera optical axis; the second included angle is the angle between the position vector of the target placement point on the imaging plane and the positive direction of the horizontal axis. The first coupling parameter and the second coupling parameter are obtained based on the camera focal length and the camera diagonal length; Based on the first coupling parameter, the second coupling parameter, the first included angle, the image point optical axis distance information, and the second included angle information, the target displacement compensation amount information is obtained; The step of obtaining target displacement compensation information based on the first coupling parameter, the second coupling parameter, the first included angle, the image point optical axis distance information, and the second included angle information includes: ； in, This represents the target displacement compensation for the i-th target. These are the first fitted parameters; These are the second fitting parameters; The third fitting parameter; This is the first coupling parameter; This is the second coupling parameter; The distance between the image point and the optical axis corresponding to the i-th target; The first included angle; The second included angle corresponding to the i-th target; in, , ; The focal length of the camera; This is the diagonal length of the sensor.

2. The method for detecting minute displacements on soil and rock surfaces according to claim 1, characterized in that, Before obtaining the target displacement compensation information based on the first coupling parameter, the second coupling parameter, the first included angle, the image point optical axis distance information, and the second included angle information, the process includes: Acquire the initial position information of the calibration target, the position information of the calibration target after movement, and the calibration target dataset. The calibration target dataset includes several camera pitch angles, a set of calibration target images corresponding to the camera pitch angles, and calibration camera parameters corresponding to the camera pitch angles. Based on the calibrated target image set, the image point displacement information is calculated; Based on the calculated image point displacement information, the initial position information of the calibration target, and the calibration camera parameters, the first measurement target displacement information is obtained; Based on the initial position information of the calibration target and the position information of the calibration target after it has moved, the displacement information of the second measurement target is obtained; Based on the second measured target displacement information, the calibration camera parameters, the calibration target initial position information, and the first measured target displacement information, the first fitting parameters, the second fitting parameters, and the third fitting parameters are obtained.

3. The method for detecting minute displacements on soil and rock surfaces according to claim 2, characterized in that, The calibration camera parameters include the calibration camera lens position, calibration camera optical axis, calibration camera focal length, and calibration camera diagonal length. The process of obtaining a first fitting parameter, a second fitting parameter, and a third fitting parameter based on the measured displacement difference information, the calibration camera parameters, the initial position information of the calibration target, and the first measured target displacement information includes: Based on the calibration camera lens position, the calibration camera optical axis, and the initial position information of the calibration target, the first calibration angle, the calibration image point optical axis distance information, and the second calibration angle information are obtained; Based on the second measured target displacement information and the first measured target displacement information, the difference information of the measured displacement values ​​is obtained; Based on the focal length of the calibration camera and the diagonal length of the calibration camera, the first calibration coupling parameter and the second calibration coupling parameter are obtained; Based on the measured displacement difference information, the first calibration coupling parameter, the second calibration coupling parameter, the first calibration angle, the optical axis distance information of the calibration image point, and the second calibration angle information, the error parameters of all calibration targets are fitted to obtain the first fitting parameter, the second fitting parameter, and the third fitting parameter.

4. The method for detecting minute displacements on soil and rock surfaces according to claim 3, characterized in that, The step of fitting error parameters of all calibration targets based on the measured displacement difference information, the first calibration coupling parameter, the second calibration coupling parameter, the calibration radial distance information, the calibration azimuth angle information, and the calibration target camera included angle information to obtain a first fitting parameter, a second fitting parameter, and a third fitting parameter, including: The fitting parameters to be solved are input as parameter vectors into the virtual physical field parameter equilibrium model, and the force information applied to the data points is obtained by combining the measured displacement value difference information. By simulating a damped dynamic system, the parameter vector is initialized to obtain the initial particle position and initial particle velocity. Calculate the resultant force applied by all data points based on the initial particle position, the initial particle velocity, and the force information applied at the data points; The particle velocity, particle position, and update step size are obtained by updating the particle velocity, updating the particle position, and adjusting the adaptive step size of the dynamic system based on the resultant force applied to all data points. Based on the updated particle velocity, updated particle position, updated step size, and the force information applied to the data points, the resultant force applied to the next updated data points is determined; based on the resultant force applied to the next updated data points, the next updated particle velocity, the next updated particle position, and the next updated step size are obtained, and the first fitting parameters, the second fitting parameters, and the third fitting parameters are obtained after the parameter vector satisfies the convergence condition.

5. The method for detecting minute displacements on soil and rock surfaces according to claim 4, characterized in that, The process involves inputting the fitted parameters to be solved as parameter vectors into the virtual physics field parameter equilibrium model, and combining this with the measured displacement difference information to obtain the applied force information at the data points, including: The fitting parameters to be solved are input as parameter vectors into the virtual physics field parameter equilibrium model to obtain the information of the difference in calculated displacement values; Based on the measured displacement difference information and the calculated displacement difference information, the calibration target residual information is obtained; Based on the calibration target residual information, the applied force information of the data points is obtained.

6. A device for detecting minute displacements on the surface of soil and rock, characterized in that, include: The information acquisition module is used to acquire target image set, camera parameters and target deployment location information. The target image set includes several target images and several shooting times of the target images. The image point displacement determination module is used to obtain image point displacement information based on the target image set; The target displacement determination module is used to obtain target displacement information based on the image point displacement information, the target deployment position information, and the camera parameters. The displacement compensation determination module is used to: The camera parameters include camera lens position, camera optical axis, camera focal length, and camera diagonal length; based on the camera lens position, camera optical axis, and target placement position information, obtain a first included angle, image point optical axis distance information, and a second included angle; the first included angle is the angle between the line connecting the target placement point and the origin in space and the camera optical axis; the second included angle is the angle between the position vector of the target placement point on the imaging plane and the positive direction of the horizontal axis; based on the camera focal length and camera diagonal length, obtain a first coupling parameter and a second coupling parameter; based on the first coupling parameter, the second coupling parameter, the first included angle, the image point optical axis distance information, and the second included angle information, obtain target displacement compensation amount information; obtaining the target displacement compensation amount information based on the first coupling parameter, the second coupling parameter, the first included angle, the image point optical axis distance information, and the second included angle information includes: ;in, This represents the target displacement compensation for the i-th target. These are the first fitted parameters; These are the second fitting parameters; The third fitting parameter; This is the first coupling parameter; This is the second coupling parameter; The distance between the image point and the optical axis corresponding to the i-th target; The first included angle; Let be the second included angle corresponding to the i-th target; where, , ; The focal length of the camera; The diagonal length of the sensor; The displacement cloud map determination module is used to obtain a displacement cloud map based on the target displacement information and the target displacement compensation amount information.

7. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for detecting minute displacements on the soil and rock surface as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for detecting minute displacements on the soil and rock surface as described in any one of claims 1 to 5.

Images