Long bridge tower top displacement monitoring method, device, equipment, medium and product

Abstract

The application discloses a long bridge tower top displacement monitoring method, device, equipment, medium and product, relates to the bridge health monitoring technical field, and the method comprises the following steps: acquiring a continuous image sequence collected by a camera; respectively pre-processing the continuous image sequence corresponding to the code plate to obtain the pre-processed continuous image sequence corresponding to the code plate; respectively extracting the corner point position of the pre-processed continuous image sequence corresponding to the code plate, and obtaining the pose of the corresponding code plate in the camera coordinate system based on the extracted corner point position; converting the pose of the corresponding code plate from the camera coordinate system to the world coordinate system based on a pre-constructed multi-coordinate system conversion model to obtain the plane displacement of the corresponding code plate in the world coordinate system; and sending the plane displacement of the two code plates in the world coordinate system to a terminal device, so that the terminal device synthesizes the plane displacement of the two code plates based on a pre-constructed decoupling equation to obtain the three-dimensional displacement of the long bridge tower top. The application can effectively improve the accuracy of the monitoring result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bridge health monitoring, in particular to a long-span bridge tower top displacement monitoring method, device, equipment, medium and product. BACKGROUND

[0002] Long-span bridge, commonly referred to as long-span bridge, is a general term for bridges with large span, long length, complex structure and high technical difficulty in the engineering field. The long-span bridge tower is the core force transmission component of the long-span bridge. The three-dimensional displacement of the top of the long-span bridge tower is a key indicator for evaluating the structural stiffness degradation, abnormal cable force and foundation settlement of the bridge. In the prior art, the monitoring method for the top of the long-span bridge tower mainly uses contact sensors (such as accelerometers, inclinometers), total station or GPS positioning technology. However, the above monitoring methods have defects such as easy error accumulation of baseline drift, large precision fluctuation affected by environment, and low positioning accuracy of multi-path effect. Therefore, there is an urgent need to provide a long-span bridge tower top displacement monitoring method that can improve the accuracy of monitoring results. SUMMARY

[0003] In view of the above defects or deficiencies in the related art, the purpose of the present application is to provide a long-span bridge tower top displacement monitoring method, device, equipment, medium and product, which can effectively improve the accuracy of monitoring results.

[0004] To achieve the above-mentioned purpose, the present application provides the following solutions:

[0005] In a first aspect, the present application provides a long-span bridge tower top displacement monitoring method, two code plates are orthogonally arranged at the top of the long-span bridge tower; the method comprises: acquiring a continuous image sequence of a corresponding code plate collected by a camera; the camera comprises two identical first cameras and second cameras, and the first cameras and the second cameras correspond to the two code plates one by one and synchronously collect images of the corresponding code plates; respectively pre-processing the continuous image sequence of the corresponding code plate to obtain a pre-processed continuous image sequence of the corresponding code plate; respectively extracting the corner point positions of each frame of image in the pre-processed continuous image sequence of the corresponding code plate, and based on the extracted corner point positions, obtaining the pose of the corresponding code plate in the camera coordinate system; converting the pose of the corresponding code plate from the camera coordinate system to the world coordinate system based on a pre-constructed multi-coordinate system conversion model to obtain the planar displacement of the corresponding code plate in the world coordinate system; the planar displacement of the corresponding code plate includes the displacement of the corresponding code plate in the horizontal direction and the vertical direction; sending the planar displacement of the two code plates in the world coordinate system to a terminal device, so that the terminal device synthesizes the planar displacement of the two code plates based on a pre-constructed decoupling equation to obtain the three-dimensional displacement of the top of the long-span bridge tower; the pre-constructed decoupling equation is constructed based on the orthogonal geometric constraint relationship of the two code plates.

[0006] Optionally, the preprocessing of the continuous image sequence of the corresponding code plate respectively comprises: enhancing the contrast of local images of the continuous image sequence of the corresponding code plate, and eliminating the salt and pepper noise of the continuous image sequence after the contrast enhancement, to obtain a noise-eliminated continuous image sequence; after the noise-eliminated continuous image sequences of the two code plates are aligned in the time dimension, the abnormal images of the noise-eliminated continuous image sequence of the corresponding code plate are removed, and / or the noise-eliminated continuous image sequence of the corresponding code plate is rectified by using a pre-constructed image rectification model, to obtain the preprocessing continuous image sequence of the corresponding code plate.

[0007] Optionally, the extraction of the corner point position of each image in the preprocessing continuous image sequence of the corresponding code plate respectively comprises: detecting the code plate ID of the preprocessing continuous image sequence of the corresponding code plate by using the detectMarkers algorithm of OpenCV, and verifying the detected code plate ID based on a preset dictionary to determine whether the corresponding code plate is a valid code plate; in the case that the corresponding code plate is valid, the pixel coordinates of four corner points of each image in the preprocessing continuous image sequence of the corresponding code plate are extracted; the pixel coordinates of the four corner points of each image are optimized at a sub-pixel level by using the cornerSubPix algorithm of OpenCV, and the abnormal points of the four corner points of each image after the sub-pixel level optimization are removed, to obtain the corner point position in the preprocessing continuous image sequence of the corresponding code plate.

[0008] Optionally, the obtaining of the pose of the corresponding code plate in the camera coordinate system based on the extracted corner point position comprises: projecting the 3D physical coordinates of the corner point position of the corresponding code plate to 2D pixel coordinates based on a camera projection equation, to obtain a linear equation set after eliminating a scale factor; the linear equation set is solved by using singular value decomposition, to obtain a rotation matrix and a translation matrix of the corresponding code plate relative to the corresponding camera.

[0009] Optionally, the pre-constructed multi-coordinate system conversion model is:

[0010] ;

[0011] wherein, X w represents the displacement of the corresponding code plate in the X-axis direction in the world coordinate system, and the unit is meter; Y w represents the displacement of the corresponding code plate in the Y-axis direction in the world coordinate system, and the unit is meter; u represents the displacement of the corresponding code plate in the X-axis direction in the pixel coordinate system, and the unit is pixel; vrepresents the displacement of the corresponding code plate in the Y-axis direction in the pixel coordinate system, and the unit is pixel; J represents the Jacobian matrix, that is,

[0012] .

[0013] Optionally, the pre-constructed decoupling equation is:

[0014] ;

[0015] wherein the movement displacement of the top end of the long-span bridge tower in the X-axis direction in the world coordinate system is X w1 , the movement displacement in the Y-axis direction is X w2 , and the movement displacement in the Z-axis direction is 1 / 2 ( Y w1 + Y w2 ); wherein, X w1 is the movement displacement of the code plate parallel to the longitudinal axis of the long-span bridge in the X-axis direction, Y w1 is the movement displacement of the code plate parallel to the longitudinal axis of the long-span bridge in the Y-axis direction; X w2 is the movement displacement of the code plate perpendicular to the longitudinal axis of the long-span bridge in the X-axis direction, Y w2 is the movement displacement of the code plate perpendicular to the longitudinal axis of the long-span bridge in the Y-axis direction.

[0016] In a second aspect, the application provides a long-span bridge tower top end displacement monitoring device, and two code plates are orthogonally arranged at the long-span bridge tower top end; the device comprises:

[0017] an acquisition module configured to acquire a continuous image sequence of the corresponding code plate collected by a camera; the camera comprises a first camera and a second camera which are completely identical, and the first camera and the second camera correspond to the two code plates one by one and synchronously collect images of the corresponding code plates;

[0018] a preprocessing module configured to pre-process the continuous image sequence of the corresponding code plate respectively to obtain a pre-processed continuous image sequence of the corresponding code plate;

[0019] The extraction and solving module is configured to extract the corner point position of each frame of image in the pre-processed continuous image sequence of the corresponding code plate respectively, and obtain the pose of the corresponding code plate in the camera coordinate system based on the extracted corner point position.

[0020] The conversion module is configured to convert the pose of the corresponding code plate from the camera coordinate system to the world coordinate system based on a pre-constructed multi-coordinate system conversion model, and obtain the planar displacement of the corresponding code plate in the world coordinate system; the planar displacement of the corresponding code plate includes the displacement of the corresponding code plate in the horizontal direction and the displacement of the corresponding code plate in the vertical direction.

[0021] The synthesis module is configured to send the planar displacement of the two code plates in the world coordinate system to the terminal device, so that the terminal device synthesizes the planar displacement of the two code plates based on a pre-constructed decoupling equation to obtain the three-dimensional displacement of the top end of the long bridge tower; the pre-constructed decoupling equation is constructed based on the orthogonal geometric constraint relationship of the two code plates.

[0022] In a third aspect, the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the long bridge tower top end displacement monitoring method according to any one of the above.

[0023] In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of the long bridge tower top end displacement monitoring method according to any one of the above.

[0024] In a fifth aspect, the present application provides a computer program product comprising a computer program, wherein the computer program is executed by a processor to implement the steps of the long bridge tower top end displacement monitoring method according to any one of the above.

[0025] According to the embodiments provided in the present application, the following technical effects are disclosed:

[0026] The application provides a long bridge tower top end displacement monitoring method, device, equipment, medium and product, which has the advantages that, compared with a traditional contact type sensor, the monitoring mode of the code plate combined with the camera does not need to lay long distance sensing optical fibers, reduces installation complexity and construction cost, and the adaptive light compensation algorithm carried by the camera itself can improve the image acquisition accuracy, effectively reduces the influence of air refraction and night light on image acquisition, improves the extraction success rate of the code plate corner point position, and improves the accuracy of the monitoring result to a certain extent; on the other hand, two code plates are orthogonally arranged at the long bridge tower top end, the decoupling equation is constructed in advance in combination with the orthogonal geometric constraint relationship, the displacement of the two code plates on the plane is converted into the displacement of the long bridge tower in the three-dimensional space, in this process, the X axis and the Y axis of the two code plates are orthogonal and uncoupled, and the Z axis is double-source fusion, which not only overcomes the limitation that a single code plate cannot cover all spatial directions, but also reduces error factors, effectively solves the problems of monocular vision calibration error drift and high multi-camera fusion re-projection error, and improves the accuracy of the monitoring result to a certain extent. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments will be briefly introduced below. Obviously, the drawings in the following description only constitute some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0028] Figure 1 It is an application environment diagram of a long bridge tower top end displacement monitoring method in an embodiment of the present application;

[0029] Figure 2 It is a flowchart of a long bridge tower top end displacement monitoring method provided by an embodiment of the present application;

[0030] Figure 3 It is a structural diagram of the first code plate or the second code plate;

[0031] Figure 4 It is a diagram of the camera coordinate system and the world coordinate system;

[0032] Figure 5 It is a functional module diagram of a long bridge tower top end displacement monitoring device provided by an embodiment of the present application;

[0033] Figure 6 It is a structural diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0035] The above purposes, features and advantages of the present application will be more apparent and understandable, and the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0036] The long bridge tower top displacement monitoring method provided by the embodiments of the present application can be applied to the application environment as shown in the drawings. Figure 1 The application environment includes a long bridge tower 10, two code plates orthogonally arranged at the top end of the long bridge tower, and two cameras arranged on the ground. The two code plates are a first code plate 20 and a second code plate 30. The first code plate is parallel to the longitudinal axis of the long bridge, and the second code plate is perpendicular to the longitudinal axis of the long bridge. The two cameras are a first camera 40 and a second camera 50. The first camera 40 collects image data of the first code plate 20, and the second camera 50 collects image data of the second code plate 30. The first camera and the second camera are completely identical, and a data processing and transmission module 60 is mounted on each of the first camera and the second camera.

[0037] The data processing and transmission module 60 of the first camera is configured to acquire a first continuous image sequence of the first code plate collected by the first camera; pre-process the first continuous image sequence to obtain a pre-processed first continuous image sequence; extract the corner point position of each frame of image in the pre-processed first continuous image sequence, and obtain the pose of the first code plate in the camera coordinate system based on the extracted corner point position; convert the pose of the first code plate from the camera coordinate system to the world coordinate system based on a pre-constructed multi-coordinate system conversion model to obtain the plane displacement of the first code plate in the world coordinate system, and send the plane displacement of the first code plate in the world coordinate system to the server.

[0038] The data processing and transmission module 60 of the first camera is configured to acquire a first continuous image sequence of the first code plate collected by the first camera; pre-process the first continuous image sequence to obtain a pre-processed first continuous image sequence; extract the corner point position of each frame of image in the pre-processed first continuous image sequence, and obtain the pose of the first code plate in the camera coordinate system based on the extracted corner point position; convert the pose of the first code plate from the camera coordinate system to the world coordinate system based on a pre-constructed multi-coordinate system conversion model to obtain the plane displacement of the first code plate in the world coordinate system, and send the plane displacement of the first code plate in the world coordinate system to the server.

[0039] The server receives the planar displacement of the first code plate and the planar displacement of the second code plate, synthesizes the planar displacement of the first code plate and the planar displacement of the second code plate based on a pre-constructed decoupling equation, and obtains the three-dimensional displacement of the top end of the long bridge tower; the pre-constructed decoupling equation is constructed based on the orthogonal geometric constraint relationship of the two code plates.

[0040] It should be noted that the data processing and transmission module 60 and the terminal device in the above embodiment utilize computer vision libraries such as OpenCV to realize on-site calculation of the planar displacement of the first code plate or the planar displacement of the second code plate, thereby avoiding problems such as long delay time, data packet loss and image distortion caused by large image data volume and long-distance transmission, and ensuring the accuracy of the monitoring result.

[0041] In other embodiments, the first camera and the second camera are not equipped with the data processing and transmission module 60, the first camera and the second camera are in close proximity to the terminal device, the terminal device acquires a first continuous image sequence of the first code plate collected by the first camera; the first continuous image sequence is preprocessed to obtain a preprocessed first continuous image sequence; the corner point position of each frame of image in the preprocessed first continuous image sequence is extracted, and the pose of the first code plate in the camera coordinate system is obtained based on the extracted corner point position; the pose of the first code plate is converted from the camera coordinate system to the world coordinate system based on a pre-constructed multi-coordinate system conversion model, and the planar displacement of the first code plate in the world coordinate system is obtained, at the same time, the terminal device acquires a second continuous image sequence of the second code plate synchronously collected by the second camera; the second continuous image sequence is preprocessed to obtain a preprocessed second continuous image sequence; the corner point position of each frame of image in the preprocessed second continuous image sequence is extracted, and the pose of the second code plate in the camera coordinate system is obtained based on the extracted corner point position; the pose of the second code plate is converted from the camera coordinate system to the world coordinate system based on the pre-constructed multi-coordinate system conversion model, and the planar displacement of the second code plate in the world coordinate system is obtained, and the planar displacement of the second code plate in the world coordinate system is sent to the server; then, the terminal device synthesizes the planar displacement of the two code plates based on the pre-constructed decoupling equation, and obtains the three-dimensional displacement of the top end of the long bridge tower.

[0042] In an exemplary embodiment, as shown in Figure 2 a long bridge tower top end displacement monitoring method is provided, which can be executed by the terminal device alone or by the data processing and transmission module 60 and the terminal device together, and the embodiment of the present application is described by taking the execution of the data processing and transmission module 60 and the terminal device together as an example. The method comprises the following steps S201 to S205. Wherein:

[0043] Step S201, acquiring a continuous image sequence of a corresponding code plate collected by a camera.

[0044] In the example embodiment, the camera comprises a first camera and a second camera which are completely identical, the first camera acquires image data of the first code plate, the second camera acquires image data of the second code plate, and the first camera and the second camera synchronously acquire image data of the first code plate and the second code plate. The continuous image sequence is a continuous image or a video acquired. Figure 3 As shown in the figure, both code plates comprise a substrate made of high-weather-resistance composite material, an LED backlight plate 201 covered on the substrate, an ArUco code 202 hollowed out on the substrate, and an anti-glare coated high-transparency glass cover plate, with a size of 0.4m x 0.4m. The ArUco code dictionary is selected as DICT_4X4_1000 specification, which is convenient for high-precision identification at a long distance.

[0045] In order to facilitate the first camera to shoot the complete first code plate and the second camera to shoot the complete second code plate, when the first code plate and the second code plate are installed, the first code plate and the second code plate can be arranged at the edge of the top of the tower of a long bridge, and an orthogonal rigid fixing frame is adopted, the first code plate is installed as a longitudinal bridge direction code plate (X-axis direction) parallel to the extension direction of the bridge, the two-dimensional code plane of the first code plate is parallel to the longitudinal bridge direction axis, and the second code plate is installed as a transverse bridge direction code plate (Y-axis direction) perpendicular to the extension direction of the bridge, the two-dimensional code plane of the second code plate is parallel to the transverse bridge direction axis. The installation support is configured with a three-axis fine adjustment holder, so as to ensure that the normal vector of the first code plate and the second code plate and the preset monitoring direction maintain an installation accuracy of ±0.5°. Here, the preset monitoring direction is subject to actual monitoring, and the embodiment of the present application is not limited in particular.

[0046] The LED backlight plate of the first code plate and the second code plate is powered by an external power supply or a solar panel 203 and a storage battery, and a built-in photosensitive sensor realizes day and night self-adaptive brightness adjustment. The photosensitive sensor monitors the ambient illuminance (range 0.01-100,000 lux) in real time, and a microcontroller generates a PWM signal according to a preset illuminance-brightness mapping curve (such as reducing the LED current when the daytime is >300 lux, and increasing the output when the nighttime is <30 lux); the LED driving circuit dynamically adjusts the current (10%-100% duty cycle) accordingly, and at the same time, the solar management system coordinates the external power supply and the storage battery power supply, so as to maintain the basic brightness when the light is insufficient, and maintain the best identification contrast of more than 500 cd / m².

[0047] The first camera and the second camera are selected as long-focus cameras. The long-focus cameras have a long-focus lens with a focal length ≥ 400 mm, an aperture F value ≤ 2.8, a high-sensitivity CMOS sensor with a resolution ≥ 4K, a frame rate ≥ 10 fps, and support for an HDR mode to cope with dynamic light changes. The high-sensitivity CMOS sensor is equipped with an optical image stabilization module and a constant-temperature shell to reduce the influence of environmental vibration and temperature on imaging. The first camera and the second camera are located on the two sides of the tower of the long bridge, the first camera is aligned with the ArUco code of the first code plate in the longitudinal direction of the bridge, and the second camera is aligned with the ArUco code of the second code plate in the transverse direction of the bridge, forming a stereo observation angle. The first camera and the second camera are both mounted on independent shockproof gimbals. The pitch angle and the azimuth angle of the first camera and the second camera are adjusted to ensure that the corresponding ArUco code is located in the center region of the image. The image is zoomed in, and the edge of the code plate in the image is greater than or equal to 10% of the width of the image, to avoid the ArUco code moving out of the shooting area due to the swing of the tower of the long bridge. When the first camera, the second camera, the first code plate, and the second code plate are installed, the distance between the first camera and the first code plate and the distance between the second camera and the second code plate are both Z c .

[0048] In step S202, the continuous image sequences of the corresponding code plates are preprocessed respectively to obtain the preprocessed continuous image sequences of the corresponding code plates.

[0049] In the example embodiment, the preprocessing includes processing each frame of image in the continuous image sequences of the first code plate and the second code plate by using adaptive histogram equalization and median filtering to eliminate noise interference such as rain, fog, and camera shake; and correcting the continuous image sequences of the first code plate and the second code plate.

[0050] Optionally, the contrast of the local images of the continuous image sequences of the corresponding code plates is enhanced, and the salt and pepper noise of the continuous image sequences after contrast enhancement is eliminated to obtain noise-eliminated continuous image sequences. After the noise-eliminated continuous image sequences of the two code plates are aligned in the time dimension, the abnormal images of the noise-eliminated continuous image sequences of the corresponding code plates are removed, and / or the noise-eliminated continuous image sequences of the corresponding code plates are corrected by using a pre-constructed image correction model to obtain the preprocessed continuous image sequences of the corresponding code plates.

[0051] In step S203, the corner point positions of each frame of image in the preprocessed continuous image sequences of the corresponding code plates are extracted respectively, and based on the extracted corner point positions, the poses of the corresponding code plates in the camera coordinate system are obtained.

[0052] In the example embodiment, the ArUco codes are hollowed out on the first code plate and the second code plate, and the extracted corner point positions are the positions of the four corners of the ArUco codes.

[0053] Optionally, the detectMarkers algorithm of OpenCV is used to detect the code plate ID of the pre-processed continuous image sequence corresponding to the code plate, and the detected code plate ID is verified based on a preset dictionary to determine whether the corresponding code plate is a valid code plate; in the case that the corresponding code plate is valid, the pixel coordinates of the four corner points of each image in the pre-processed continuous image sequence of the corresponding code plate are extracted; the cornerSubPix algorithm of OpenCV is used to optimize the pixel coordinates of the four corner points of each image of the corresponding code plate at a sub-pixel level, and the abnormal points of the four corner points of each image after sub-pixel level optimization are removed, to obtain the corner point positions in the pre-processed continuous image sequence of the corresponding code plate.

[0054] Further, the 3D physical coordinates of the corner point positions of the corresponding code plate are projected to 2D pixel coordinates based on a camera projection equation, and a linear equation set is obtained after the scale factor is eliminated; the linear equation set is solved by singular value decomposition to obtain the rotation matrix and the translation matrix of the corresponding code plate relative to the corresponding camera. That is, based on the 3D physical coordinates of the code plate corner points (known code plate size) and the 2D image pixel coordinates, the EPnP algorithm is used to calculate the rotation matrix R and the translation matrix t of the code plate relative to the camera. This algorithm introduces four virtual control points, converts the 3D-2D matching problem into a linear solution, and then solves the optimal rotation matrix and translation matrix through SVD to minimize the re-projection error.

[0055] In step S204, the pose of the corresponding code plate is converted from the camera coordinate system to the world coordinate system based on a pre-constructed multi-coordinate system conversion model, to obtain the planar displacement of the corresponding code plate in the world coordinate system.

[0056] In the example embodiment, the planar displacement of the corresponding code plate includes the displacement of the corresponding code plate in the horizontal direction and the displacement of the corresponding code plate in the vertical direction.

[0057] As can be understood in combination with the above embodiments, first, the camera parameters of the first camera and the second camera are calibrated, the poses of the first code plate and the second code plate are solved, and the multi-coordinate system conversion algorithm is constructed using the calibration parameters, and the specific process is as follows:

[0058] The camera intrinsic calibration is performed using Zhang Zhengyou calibration method: a high-precision checkerboard calibration board (black and white checkerboard size accuracy ≤0.01 mm) is used, and calibration images are collected through multiple views (≥20 groups of poses). The calibration board needs to cover different depths and regions of the camera field of view to ensure the spatial uniformity of the calibration parameters.

[0059] The following internal parameters are calculated: focal length (f x , f y ): unit pixel, representing the zoom effect of the lens on imaging. Principal point coordinates (c x , c yOffset of pixel coordinate system origin relative to sensor center. Radial distortion coefficients (k1, k2, k3): Correction of lens barrel / pincushion distortion. Tangential distortion coefficients (p1, p2): Correction of distortion caused by lens misalignment.

[0060] The distortion correction formula is as follows (1):

[0061] (1)

[0062] wherein, and x' and y' are normalized coordinates, x'' and y'' are normalized coordinates after distortion correction, the original normalized coordinates (x', y') are adjusted to x'' and y'' after considering the radial and tangential distortion of the lens, and the pixel coordinates (u, v) after distortion correction are as follows (2):

[0063] (2)

[0064] The calibration accuracy is evaluated by re-projection error (RMS error≤0.1 pixel), and if it exceeds the limit, the calibration image is re-collected or the calibration algorithm parameters are optimized. The subsequent image processing is performed on the image after distortion correction.

[0065] The focal length (f x, ) in the above content y ) is the principal point coordinate (c x , c y ) of the camera, and K is the camera intrinsic matrix, i.e. as follows (3):

[0066] (3)

[0067] Then, the specific process of ArUco code detection and corner extraction of the first code plate and the second code plate is as follows:

[0068] Sub-pixel level corner positioning: the detectMarkers algorithm of opencv is used to detect the ArUco code of the first code plate and the second code plate, and the cornerSubPix algorithm of opencv is used to optimize the four corner coordinates of the ArUco code of the first code plate and the second code plate to sub-pixel level (accuracy up to 0.1 pixel), reducing the influence of image noise and motion blur. Remove abnormal corner points to improve the stability of the solution in a dynamic scene. Code plate ID matching and screening: verify the detected code plate ID according to the preset ArUco dictionary (such as DICT_6X6), and filter out invalid identifiers.

[0069] EPnP solution: based on the 3D physical coordinates of the codeboard corner points (known codeboard size) and 2D image pixel coordinates, the EPnP algorithm is selected to calculate the rotation matrix R and translation matrix t of the codeboard relative to the camera. The EPnP algorithm converts the 3D-2D matching problem into a linear solution by introducing four virtual control points {ck}. The 3D point is represented as a weighted sum of control points, i.e. formula (4):

[0070] (4)

[0071] wherein, jk is a weight coefficient, satisfying , j represents the j th 3D point, and k represents the kth control point.

[0072] The 3D point ( X j ,Y j ) is projected to the image pixel coordinates ( u j ,v j ) using the projection equation (5), i.e.

[0073] (5)

[0074] wherein, s j is a scale factor (non-zero scalar); K is the camera intrinsic matrix; r1 and r2 are the first two columns of the rotation matrix R (the third column r3 = r1 x r2).

[0075] Substitute the projection equation (5) into the control point expression and eliminate the scale factor s j to obtain a linear equation system, i.e. formula (6):

[0076] (6)

[0077] By solving the optimal (R, t) through the control point coordinates {ckworld} and {ckcam}, the re-projection error is minimized, i.e. formula (7) is obtained:

[0078] (7)

[0079] The optimal rotation matrix R and translation matrix t are solved by SVD.

[0080] After that, the pixel displacement and codeboard plane actual displacement conversion algorithm process is as follows:

[0081] As Figure 4 shown, the ArUco code plane of the first code board or the second code board is Z w =0, the physical displacement is (Δ X w ,Δ Y w ). The world coordinate system is converted to the camera coordinate system by the rotation matrix R and the translation matrix t solved above. Specifically, the camera coordinate system (X X c , Y c ,Z c ) is used as an intermediate conversion bridge, and the final goal is to directly convert the pixel displacement (Δ u , v ) to the actual displacement (Δ X w , Y w ) of the code board plane; the focal length (f x , f y ) and the principal point coordinates (cx, cy) are the intrinsic parameters of the camera. The conversion between the camera coordinate system and the pixel coordinate system is as follows (8):

[0082] (8)

[0083] For a point (X X w , Y w ,0) in the world coordinate system, its camera coordinate system coordinates are as follows (9):

[0084] (9)

[0085] The projection to the pixel coordinate system is as follows (10):

[0086] (10)

[0087] When the first code board or the second code board has a physical displacement (Δ X w , Y w ), the new camera coordinates are as follows (11):

[0088] (11)

[0089] wherein R is an element in the rotation matrix R, and the subscript is its position in the matrix.

[0090] Assuming that the displacement is small (d ), the pixel displacement expression can be linearized to obtain the projection equation, i.e., the following formula (12):

[0091] (12)

[0092] After the above formula (12) is written in matrix form, the conversion relationship between the pixel displacement and the actual displacement can be obtained, i.e., the pre-constructed multi-coordinate system conversion model is the following formula (13):

[0093] (13)

[0094] wherein, the above formula X w represents the displacement of the first code plate in the world coordinate system, and the unit is meter; Y w represents the displacement of the second code plate in the world coordinate system, and the unit is meter; u represents the displacement of the first code plate in the pixel coordinate system, and the unit is pixel; v represents the displacement of the second code plate in the pixel coordinate system, and the unit is pixel; J represents the Jacobian matrix, the Jacobian matrix J is the following formula (14), and the Z c obtained by a laser range finder when the first code plate, the second code plate, the first camera and the second camera are installed;

[0095] (14).

[0096] Finally, the terminal device uses computer vision libraries such as OpenCV to solve the displacement in the pre-processed first continuous image sequence and the pre-processed second continuous image sequence on site, so as to avoid inaccurate monitoring results caused by long-distance transmission and large data volume. In an example, the displacement solved by the first code plate is represented as (x X w1 , Y w1 ), and the displacement solved by the second code plate is represented as (x X w2 , Y w2 ).

[0097] Step S205: Send the planar displacements of the two code plates in the world coordinate system to the terminal device so that the terminal device can synthesize the planar displacements of the two code plates based on the pre-constructed decoupling equations to obtain the three-dimensional displacement of the top of the bridge tower of the long bridge.

[0098] In the example embodiment, the pre-constructed decoupling equations are built based on the orthogonal geometric constraints of the two code plates. In conjunction with the above embodiment, the first code plate is parallel to the longitudinal direction (X-axis) of the bridge and is used to monitor the displacement of the long bridge tower along the bridge's extension direction (e.g., along the bridge axis); the second code plate is parallel to the transverse direction (Y-axis) of the bridge and is used to monitor the displacement of the long bridge tower along the bridge's width direction (e.g., in the horizontal direction perpendicular to the bridge axis). The two code plates are held vertically together by a rigid fixing structure, jointly covering the main displacement directions of the long bridge tower tops in the horizontal plane and providing a basis for calculating the vertical direction (Z-axis) displacement. A first camera acquires displacement data of the first code plate in the longitudinal plane, including the X-axis and minor displacements perpendicular to that plane; a second camera acquires displacement data of the second code plate in the transverse plane, including the Y-axis and minor displacements perpendicular to that plane.

[0099] The terminal device calculates the displacement of the first code plate as ( X w1 , Y w1 The displacement of the second code plate is ( X w2 , Y w2 After that, the displacement of the first code plate is ( X w1 , Y w1 The displacement of the second code plate is ( X w2 , Y w2 ) is sent to the server; the server receives ( X w1 , Y w1 )and( X w2 , Y w2 After that, based on the orthogonal geometric relationship between the first code plate and the second code plate, the displacement decoupling equation is constructed, namely the following equation (15):

[0100] (15)

[0101] The redundant information in the data of the first and second code plates can be eliminated by the above formula (15), and finally the data at the top of the bridge tower of the long bridge can be synthesized. X, Y, Z Absolute displacement in three directions enables complete monitoring of three-dimensional displacement.

[0102] It should be noted that the terminal device will shift the first code plate by ( X w1 , Y w1 The displacement of the second code plate is () X w2 , Y w2 The data is encapsulated in JSON format with CRC checksums and sequence numbers to ensure transmission integrity. High-priority transmission is triggered for displacement exceeding limits (e.g., ΔX > 10mm), using UDP protocol to guarantee low latency (e.g., latency < 50ms). Under normal circumstances, data is packaged at fixed intervals (e.g., 1 second / time), using TCP protocol to ensure reliability. It integrates 4G / 5G cellular networks and LoRa wireless modules, automatically switching transmission channels based on signal strength. In case of signal interruption, a local data queue (capacity ≥ 24 hours) is cached, prioritizing the retransmission of unsuccessful data once the link is restored. Encryption and anti-interference: AES-256 encryption algorithm is used to protect data security, and frequency hopping (FHSS) technology is used to avoid interference in the same frequency band, ensuring the stability and security of data transmission.

[0103] By transforming multiple coordinate systems and solving solid geometric relationships, the planar displacements of the first and second code plates are merged into three-dimensional spatial displacements, overcoming the limitation that a single code plate cannot cover all spatial directions, and ultimately achieving high-precision monitoring of the three-dimensional displacement of the top of the bridge tower of a long bridge.

[0104] By implementing the steps S201 to S205, two code plates are orthogonally arranged at the top end of the long bridge tower, and a continuous image sequence of the two code plates is collected by two cameras one-to-one; by preprocessing the continuous image sequence of the corresponding code plate, a preprocessed continuous image sequence of the corresponding code plate is obtained; by extracting the corner point position of each frame of image in the preprocessed continuous image sequence of the corresponding code plate, and by the extracted corner point position, the pose of the corresponding code plate in the camera coordinate system is obtained; by the pre-constructed multi-coordinate system conversion model, the pose of the corresponding code plate is converted from the camera coordinate system to the world coordinate system, and the planar displacement of the corresponding code plate in the world coordinate system is obtained; by the pre-constructed decoupling equation, the planar displacements of the two code plates are synthesized, and the three-dimensional displacement of the top end of the long bridge tower is obtained. Compared with the prior art, on the one hand, compared with the traditional contact sensor, the monitoring method using code plates combined with cameras does not need to lay long-distance sensing optical fibers, reduces the installation complexity and construction cost, and because the self-adaptive light compensation algorithm carried by the camera itself can improve the image collection accuracy, effectively reduces the influence of air refraction and night light on image collection, improves the success rate of subsequent extraction of code plate corner point position, and to some extent, improves the accuracy of the monitoring result. On the other hand, the two code plates are orthogonally arranged at the top end of the long bridge tower, and the decoupling equation pre-constructed combined with the orthogonal geometric constraint relationship converts the displacement of the two code plates in the plane into the displacement of the long bridge tower in the three-dimensional space. In this process, the X-axis and Y-axis of the two code plates are orthogonal and uncoupled, and the Z-axis is double-source fused. Not only does it overcome the limitation that a single code plate cannot cover all spatial directions, but it also reduces error factors, effectively solves the problems of monocular vision calibration error drift and high multi-camera fusion re-projection error, and to some extent, can improve the accuracy of the monitoring result.

[0105] In another embodiment, the above method further comprises: the server warning the long bridge tower. Specifically, the server analyzes whether the displacement of the top end of the long bridge tower in a preset time period is greater than or equal to a preset threshold based on the historical data and the current three-dimensional displacement of the top end of the long bridge tower returned by the terminal device, and if the displacement of the top end of the long bridge tower is greater than or equal to the preset threshold, the server sends a warning information to the user terminal or a display interface. The warning information can be sent in the form of a pop-up window, a short message or a language form. The warning information can include the current displacement, the historical displacement, etc.

[0106] By real-time warning and historical data analysis of the top end of the long bridge tower, the efficiency and reliability of bridge health monitoring can be significantly improved, the operation and maintenance cost can be greatly reduced, and the method is suitable for long-term health monitoring and safety warning of long-span bridges.

[0107] Based on the same inventive concept, the embodiment of the present application also provides a long bridge tower top displacement monitoring device for implementing the long bridge tower top displacement monitoring method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more long bridge tower top displacement monitoring device embodiments provided below can refer to the limitations of the long bridge tower top displacement monitoring method described above, which will not be repeated here.

[0108] In an exemplary embodiment, as shown in Figure 5 A long bridge tower top displacement monitoring device is provided, and the long bridge tower top displacement monitoring 500 includes an acquisition module 501, a preprocessing module 502, an extraction and solving module 503, a conversion module 504, and a synthesis module 505, wherein:

[0109] The acquisition module 501 is configured to acquire a continuous image sequence of a corresponding code plate collected by a camera; the camera includes two identical first cameras and second cameras, and the first cameras and the second cameras correspond to two code plates one-to-one and synchronously collect images of the corresponding code plates;

[0110] The preprocessing module 502 is configured to pre-process the continuous image sequence of the corresponding code plate respectively to obtain a pre-processed continuous image sequence of the corresponding code plate;

[0111] The extraction and solving module 503 is configured to extract the corner point position of each frame of image in the pre-processed continuous image sequence of the corresponding code plate respectively, and obtain the pose of the corresponding code plate in the camera coordinate system based on the extracted corner point position;

[0112] The conversion module 504 is configured to convert the pose of the corresponding code plate from the camera coordinate system to the world coordinate system based on a pre-constructed multi-coordinate system conversion model to obtain the planar displacement of the corresponding code plate in the world coordinate system; the planar displacement of the corresponding code plate includes the displacement of the corresponding code plate in the horizontal direction and the vertical direction;

[0113] The synthesis module 505 is configured to send the planar displacement of the two code plates in the world coordinate system by a terminal device, so that the terminal device synthesizes the planar displacement of the two code plates based on a pre-constructed decoupling equation to obtain the three-dimensional displacement of the long bridge tower top; the pre-constructed decoupling equation is constructed based on the orthogonal geometric constraint relationship of the two code plates.

[0114] As an optional implementation, the preprocessing module 502 is specifically configured to enhance the contrast of the local image of the corresponding code plate in the continuous image sequence and eliminate the salt and pepper noise of the continuous image sequence after the contrast enhancement, to obtain a noise-eliminated continuous image sequence; after the noise-eliminated continuous image sequences of the two code plates are aligned in the time dimension, the abnormal images of the noise-eliminated continuous image sequence of the corresponding code plate are removed and / or the image correction model constructed in advance is used to correct the image of the noise-eliminated continuous image sequence of the corresponding code plate, to obtain a preprocessed continuous image sequence of the corresponding code plate.

[0115] As an optional implementation, the extraction and calculation module 503 is specifically configured to detect the code plate ID of the preprocessed continuous image sequence of the corresponding code plate by using the detectMarkers algorithm of OpenCV, and verify the detected code plate ID based on a preset dictionary to determine whether the corresponding code plate is a valid code plate; in the case that the corresponding code plate is valid, the pixel coordinates of the four corner points of each image in the preprocessed continuous image sequence of the corresponding code plate are extracted; the pixel coordinates of the four corner points of each image of the corresponding code plate are optimized at a sub-pixel level by using the cornerSubPix algorithm of OpenCV, and the abnormal points of the four corner points of each image after the sub-pixel level optimization are removed, to obtain the corner point positions in the preprocessed continuous image sequence of the corresponding code plate.

[0116] As an optional implementation, the extraction and calculation module 503 is further specifically configured to project the 3D physical coordinates of the corner point positions of the corresponding code plate to 2D pixel coordinates based on a camera projection equation, to obtain a linear equation set after eliminating a scale factor; the linear equation set is solved by using singular value decomposition, to obtain a rotation matrix and a translation matrix of the corresponding code plate relative to the corresponding camera.

[0117] As an optional implementation, the pre-constructed multi-coordinate system conversion model is as follows:

[0118] ;

[0119] wherein, Xw represents the displacement of the corresponding code plate in the X-axis direction in the world coordinate system, and the unit is meter; Yw represents the displacement of the corresponding code plate in the Y-axis direction in the world coordinate system, and the unit is meter; u represents the displacement of the corresponding code plate in the X-axis direction in the pixel coordinate system, and the unit is pixel; v represents the displacement of the corresponding code plate in the Y-axis direction in the pixel coordinate system, and the unit is pixel; J represents a Jacobian matrix, that is:

[0120] .

[0121] As an optional implementation, the pre-constructed decoupling equation is:

[0122] ;

[0123] wherein the movement displacement of the top end of the long bridge tower in the X-axis direction in the world coordinate system is X w1 the movement displacement of the top end of the long bridge tower in the Y-axis direction is X w2 the movement displacement of the top end of the long bridge tower in the Z-axis direction is 1 / 2 ( Y w1 + Y w2 ; wherein, X w1 is the movement displacement of the deck plate parallel to the longitudinal axis of the long bridge in the X-axis direction, Y w1 is the movement displacement of the deck plate parallel to the longitudinal axis of the long bridge in the Y-axis direction; X w2 is the movement displacement of the deck plate perpendicular to the longitudinal axis of the long bridge in the X-axis direction, Y w2 is the movement displacement of the deck plate perpendicular to the longitudinal axis of the long bridge in the Y-axis direction.

[0124] When this implementation is implemented, on the one hand, compared with the traditional contact sensor, the monitoring method using the deck plate combined with the camera does not need to lay long-distance sensing optical fibers, reduces the installation complexity and construction cost, and because the camera itself is equipped with an adaptive light compensation algorithm, the image acquisition accuracy can be improved, the influence of air refraction and night light on image acquisition can be effectively reduced, the success rate of extracting the corner point position of the deck plate can be improved, and the accuracy of the monitoring result can be improved to a certain extent. On the other hand, the two deck plates are orthogonally arranged at the top end of the long bridge tower, and the decoupling equation pre-constructed combined with the orthogonal geometric constraint relationship converts the displacement of the two deck plates in the plane into the displacement of the long bridge tower in the three-dimensional space. In this process, the X-axis and Y-axis of the two deck plates are orthogonal and uncoupled, and the Z-axis is double-source fusion, which not only overcomes the limitation that a single deck plate cannot cover all spatial directions, but also reduces error factors, effectively solves the problems of monocular vision calibration error drift and high multi-camera fusion re-projection error, and to a certain extent, the accuracy of the monitoring result can be improved.

[0125] In an exemplary embodiment, a computer device is provided, which can be a server or a terminal, and an internal structure diagram thereof can be as shown in FIG. 1. Figure 6 The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store the long-span bridge tower top displacement monitoring data. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with external terminals through network connection. The computer program is executed by the processor to implement a long-span bridge tower top displacement monitoring method.

[0126] Those skilled in the art can understand that Figure 6 The structure shown in the above embodiment is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the diagram, or combine certain components, or have a different arrangement of components.

[0127] In an exemplary embodiment, a computer device is provided, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0128] In an exemplary embodiment, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0129] In an exemplary embodiment, a computer program product is provided, which includes a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0130] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of the related data need to comply with relevant regulations.

[0131] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to a memory, a database or other medium used in the embodiments provided in the present application can include at least one of a non-volatile and a volatile memory. The non-volatile memory can include a read-only memory (ROM), a magnetic tape, a floppy disk, a flash memory, an optical storage, a high-density embedded non-volatile memory, a resistive random access memory (ReRAM), a magnetoresistive random access memory (MRAM), a ferroelectric random access memory (FRAM), a phase change memory (PCM), a graphene memory, etc. The volatile memory can include a random access memory (RAM) or an external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as a static random access memory (SRAM) or a dynamic random access memory (DRAM), etc.

[0132] The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0133] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combinations of the technical features do not exist contradictory, they should be considered as the scope of the present application.

[0134] The principles and implementation modes of the present application are described by applying specific examples in the present application. The above embodiments are only used to help understand the method and its core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range can be changed. In conclusion, the content of the present application should not be understood as a limitation.

Claims

1. A method for monitoring the displacement at the top of a long bridge tower, characterized in that, Two code plates are orthogonally installed at the top of the bridge tower of the long bridge. The two code plates are the first code plate and the second code plate. The first code plate and the second code plate can be set at the edge of the top of the bridge tower of the long bridge and adopt an orthogonal rigid fixing structure. The first code plate is installed as a longitudinal bridge code plate parallel to the extension direction of the bridge, and the QR code plane of the first code plate is parallel to the longitudinal bridge axis. The second code plate is installed as a transverse bridge code plate perpendicular to the extension direction of the bridge, and the QR code plane of the second code plate is parallel to the transverse bridge axis. Both the first and second code plates include a substrate made of high weather-resistant composite material, an LED backlight plate covering the substrate, an ArUco code hollowed out on the substrate, and a high-transparency glass cover plate with anti-glare coating. The method for monitoring the displacement at the top of the bridge tower of the long bridge includes: Acquire a continuous image sequence of the corresponding code plate captured by the camera; the camera includes an identical first camera and a second camera, the first camera and the second camera correspond one-to-one with the two code plates and synchronously acquire images of the corresponding code plates; The continuous image sequences of the corresponding code plates are preprocessed to obtain the preprocessed continuous image sequences of the corresponding code plates. The corner positions of each frame in the preprocessed continuous image sequence of the corresponding code board are extracted respectively, and the pose of the corresponding code board in the camera coordinate system is obtained based on the extracted corner positions. Based on a pre-built multi-coordinate system transformation model, the pose of the corresponding code plate is transformed from the camera coordinate system to the world coordinate system, and the planar displacement of the corresponding code plate in the world coordinate system is obtained; the planar displacement of the corresponding code plate includes the horizontal displacement and the vertical displacement of the corresponding code plate. The planar displacements of the two code plates in the world coordinate system are sent to the terminal device, so that the terminal device can synthesize the planar displacements of the two code plates based on a pre-constructed decoupling equation to obtain the three-dimensional displacement of the top of the bridge tower of the long bridge; the pre-constructed decoupling equation is based on the orthogonal geometric constraint relationship of the two code plates; wherein, the planar displacement of the first code plate is ( ∆X w1 , ∆Y w1 The planar displacement of the second code plate is ( ∆X w2 , ∆Y w2 The three-dimensional displacement synthesized based on the pre-constructed decoupling equation is ( ∆X w1 , ∆X w2 , 1 / 2 ( ∆Y w1+ ∆Y w2 )).

2. The method for monitoring the displacement at the top of a long bridge tower according to claim 1, characterized in that, The step of preprocessing the continuous image sequences of the corresponding code plates to obtain the preprocessed continuous image sequences of the corresponding code plates includes: Enhance the contrast of local images in the continuous image sequence corresponding to the code plate, and eliminate salt-and-pepper noise in the contrast-enhanced continuous image sequence to obtain a noise-reduced continuous image sequence. After aligning the noise-cancelled continuous image sequences of the two code plates in the time dimension, abnormal images in the noise-cancelled continuous image sequence of the corresponding code plate are removed and / or the noise-cancelled continuous image sequence of the corresponding code plate is corrected using a pre-built image correction model to obtain the pre-processed continuous image sequence of the corresponding code plate.

3. The method for monitoring the displacement at the top of a long bridge tower according to claim 1, characterized in that, The step of extracting the corner positions of each frame in the preprocessed continuous image sequence corresponding to the code plate includes: The codeboard ID of the preprocessed continuous image sequence corresponding to the codeboard is detected using OpenCV's detectMarkers algorithm, and the detected codeboard ID is verified based on a preset dictionary to determine whether the corresponding codeboard is a valid codeboard. If the corresponding code plate is valid, extract the pixel coordinates of the four corner points of each frame in the preprocessed continuous image sequence of the corresponding code plate; The cornerSubPix algorithm of OpenCV is used to optimize the pixel coordinates of the four corner points of each frame of the corresponding code board at the subpixel level, and the abnormal points of the four corner points of each frame of the subpixel-optimized image are removed to obtain the corner point positions in the preprocessed continuous image sequence of the corresponding code board.

4. The method for monitoring the displacement at the top of a long bridge tower according to claim 3, characterized in that, The step of obtaining the pose of the corresponding codeboard in the camera coordinate system based on the extracted corner point positions includes: Based on the camera projection equation, the 3D physical coordinates of the corner position of the corresponding code board are projected to the 2D pixel coordinates, and the linear equation system is obtained after eliminating the scale factor. Singular value decomposition is used to solve the linear equations to obtain the rotation and translation matrices of the corresponding code plate relative to the corresponding camera.

5. The method for monitoring the displacement at the top of a long bridge tower according to claim 1, characterized in that, The pre-constructed multi-coordinate system transformation model is as follows: ； in, X w This indicates the displacement of the corresponding code plate along the X-axis in the world coordinate system, in meters; Y w This represents the displacement of the corresponding code plate along the Y-axis in the world coordinate system, in meters. u This represents the displacement of the corresponding code plate along the X-axis in the pixel coordinate system, in pixels. v This represents the displacement of the corresponding code plate along the Y-axis in the pixel coordinate system, in pixels; J represents the Jacobian matrix, i.e.: 。 6. The method for monitoring the displacement at the top of a long bridge tower according to claim 1, characterized in that, The pre-constructed decoupling equation is: ； Among them, the displacement of the top of the bridge tower in the X-axis direction in the world coordinate system is: X w1 The displacement in the Y-axis direction is X w2 The displacement in the Z-axis direction is 1 / 2 ( Y w1 + Y w2 );in, X w1 The displacement of the code plate, which is parallel to the longitudinal axis of the long bridge, in the X-axis direction. Y w1 The displacement of the code plate in the Y-axis direction, which is parallel to the longitudinal axis of the long bridge. X w2 The displacement of the code plate perpendicular to the longitudinal axis of the long bridge in the X-axis direction. Y w2 The displacement of the code plate perpendicular to the longitudinal axis of the long bridge in the Y-axis direction.

7. A displacement monitoring device for the top of a long bridge tower, characterized in that, Two code plates are orthogonally installed at the top of the bridge tower of the long bridge; the two code plates are the first code plate and the second code plate, which can be set at the edge of the top of the bridge tower of the long bridge and adopt an orthogonal rigid fixing structure. The first code plate, installed as a longitudinal bridge code plate parallel to the bridge's extension direction, has its QR code plane parallel to the longitudinal bridge axis. The second code plate, installed as a transverse bridge code plate perpendicular to the bridge's extension direction, has its QR code plane parallel to the transverse bridge axis. Both the first and second code plates include a substrate made of a high-weather-resistant composite material, an LED backlight panel covering the substrate, an ArUco code hollowed out on the substrate, and a high-transparency glass cover with an anti-glare coating. The displacement monitoring device at the top of the long bridge tower includes: The acquisition module is used to acquire a continuous image sequence of the corresponding code plate captured by the camera; the camera includes an identical first camera and a second camera, the first camera and the second camera correspond one-to-one with the two code plates and synchronously acquire images of the corresponding code plates; The preprocessing module is used to preprocess the continuous image sequence of the corresponding code plate to obtain the preprocessed continuous image sequence of the corresponding code plate. The extraction and calculation module is used to extract the corner positions of each frame in the preprocessed continuous image sequence of the corresponding code board, and to obtain the pose of the corresponding code board in the camera coordinate system based on the extracted corner positions. The transformation module is used to transform the pose of the corresponding code plate from the camera coordinate system to the world coordinate system based on a pre-built multi-coordinate system transformation model, so as to obtain the planar displacement of the corresponding code plate in the world coordinate system; the planar displacement of the corresponding code plate includes the horizontal displacement and the vertical displacement of the corresponding code plate. A synthesis module is used by the terminal device to send the planar displacements of two code plates in the world coordinate system, so that the terminal device can synthesize the planar displacements of the two code plates based on a pre-constructed decoupling equation to obtain the three-dimensional displacement of the top of the bridge tower of the long bridge; the pre-constructed decoupling equation is based on the orthogonal geometric constraint relationship of the two code plates; wherein, the planar displacement of the first code plate is ( ∆X w1 , ∆Y w1 The planar displacement of the second code plate is ( ∆X w2 , ∆Y w2 The three-dimensional displacement synthesized based on the pre-constructed decoupling equation is ( ∆X w1 , ∆X w2 , 1 / 2 ( ∆Y w1+ ∆Y w2 )).

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the method for monitoring the displacement at the top of the tower of a long bridge as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method for monitoring the displacement at the top of the tower of a long bridge as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the method for monitoring the displacement at the top of the tower of a long bridge as described in any one of claims 1-6.

Images