Calibration-free laser vision fusion measurement method and system for large-scale structure deformation

Abstract

The present application discloses a calibration-free laser vision fusion measurement method and system for large-scale structure deformation, wherein the method sets a visual image acquisition instrument, a laser emitter emits a laser line on the inner wall of the target structure and images it on the visual image acquisition instrument, and determines the target offset of the pixel points between the laser line and the reference line based on the target image formed on the acquisition instrument. Prior to this, by controlling the actual displacement of the measured object and the pixel displacement corresponding to the displacement process imaged by the visual image acquisition instrument, the corresponding relationship between the pixel displacement and the proportional coefficient is fitted to obtain a predetermined relationship table. After obtaining the target offset corresponding to the target image, the proportional coefficient corresponding to the target offset is obtained by querying the predetermined relationship table; based on the proportional coefficient, the target offset is converted into the actual physical displacement caused by the deformation of the target structure. The actual displacement can be obtained only through pixel displacement, without the need for calibration in a complex on-site working environment.

Description

Technical Field

[0001] The present application relates to the field of deformation monitoring technology, and in particular to a calibration-free large-scale structure deformation laser vision fusion measurement method and system. Background Art

[0002] Currently, laser ranging and three-dimensional laser scanning methods are commonly used to monitor the structural deformation of various structures in infrastructure. However, these methods often require external parameter calibration before use under various complex working conditions, which is difficult and complex to calibrate. Summary of the Invention

[0003] The embodiments of the present application provide a calibration-free large-scale structure deformation laser vision fusion measurement method and system to solve the technical problem of difficult calibration under complex working conditions.

[0004] According to a first aspect of an embodiment of the present application, a calibration-free laser vision fusion measurement method for deformation of a large structure is provided, the method comprising: collecting a target image formed by a laser line emitted by a laser emitter in a target structure by a visual image acquisition instrument; determining a target offset of pixel points between the laser line and a reference line based on the target image; obtaining a proportional coefficient corresponding to the target offset by querying a predetermined relationship table; the predetermined relationship table records the correspondence between the offset and the proportional coefficient; converting the target offset into a physical displacement based on the proportional coefficient; and determining the deformation data of the target structure according to the physical displacement corresponding to all pixel points.

[0005] Furthermore, before collecting the target image formed by the laser line emitted by the laser emitter in the target structure through the visual image acquisition instrument, the method also includes: collecting the measurement image formed by the laser line emitted by the laser emitter based on the movement of the measured object a predetermined number of times through the visual image acquisition instrument; performing fitting based on the number of movements of the measured object, the actual displacement of the measured object and the pixel offset in the measurement image to obtain a fitting function between the proportional coefficient and the pixel offset; determining the corresponding relationship between the proportional coefficient and the pixel offset based on the fitting function; and recording the corresponding relationship in a predetermined relationship table.

[0006] Furthermore, the performing fitting based on the number of movements of the measured object, the actual displacement of the measured object, and the pixel offset in the measured image includes performing fitting based on the number of movements of the measured object, the actual displacement of the measured object in each movement, a proportional coefficient corresponding to a change in the angle between the laser plane and the imaging plane caused by each movement, and the pixel offset in the measured image.

[0007] Furthermore, there are multiple measuring objects, and the moving directions of the measuring objects are consistent with the deformation direction along the radial direction of the target structure.

[0008] Furthermore, determining the correspondence between the proportional coefficient and the pixel offset based on the fitting function includes: constructing the Euclidean norm of the residual vector in the fitting function based on the least squares method; deriving the Euclidean norm, and determining the correspondence between the proportional coefficient and the pixel offset based on the result of the derivation being equal to 0.

[0009] Furthermore, determining the target offset of the pixel points between the laser line and the baseline based on the target image includes: after denoising the target image, determining whether the background interference complexity in the target image meets a predetermined condition; in response to the background interference complexity meeting the predetermined condition, adjusting the threshold corresponding to the target image based on the local window mean, standard deviation and empirical coefficient corresponding to the target image; determining the pixel coordinates of the laser line in the target image based on a predetermined algorithm and the threshold; and determining the target offset of the pixel points between the laser line and the baseline based on the pixel coordinates.

[0010] Furthermore, the proportional coefficient is related to the scale factor of the visual image acquisition instrument and the cosine value of the angle between the laser plane and the imaging plane; wherein the proportional factor is equal to the product of the pixel size and the object distance divided by the focal length.

[0011] Furthermore, converting the target offset into a physical displacement based on the proportional coefficient includes: multiplying the target offset by the proportional coefficient to obtain the physical displacement.

[0012] According to the second aspect of the embodiment of the present application, a calibration-free laser vision fusion measurement system for deformation of large structures is also provided. The system applies the calibration-free laser vision fusion measurement method for deformation of large structures described in any one of the first aspects above. The system includes: a processing device, and at least one pair of visual image collectors and laser emitters; the at least one pair of visual image collectors and laser emitters are arranged on the inner wall of at least one section of the target structure, and the distance between the pair of visual image collectors and the laser emitters is greater than a preset distance; the axis of the laser emitter is parallel to the axis of the target structure, and the processing device establishes a communication connection with at least the visual image collector.

[0013] Furthermore, the visual image acquisition instrument includes: a main camera and an auxiliary camera; the angle between the axis of the main camera and the axis of the auxiliary camera is smaller than a preset threshold.

[0014] The present invention proposes a calibration-free laser vision fusion measurement method for large-scale structure deformation. The method uses a visual image acquisition device to capture a target image formed by a laser line emitted by a laser emitter within a target structure. Based on the target image, a target offset of pixels between the laser line and a reference line is determined. A proportional coefficient corresponding to the target offset is obtained by querying a predetermined relationship table. The predetermined relationship table records the correspondence between the target offset and the proportional coefficient. Based on the proportional coefficient, the target offset is converted into a physical displacement. Deformation data of the target structure is determined based on the physical displacement corresponding to all pixels. Thus, during actual inspection, a simple query of the predetermined relationship table between the proportional coefficient and the target offset is required to obtain the proportional coefficient corresponding to the offset of the current laser line pixel. The offset can then be converted into the actual physical displacement of the target structure based on the proportional coefficient. This conversion from laser line offset to actual structure deformation can be achieved simply by querying the predetermined relationship table, eliminating the need for device parameter calibration before each inspection. This avoids the difficulty of calibration under complex working conditions and the resulting inefficiency, thereby improving inspection efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0016] Figure 1 This is a flow chart of a calibration-free large-scale structure deformation laser vision fusion measurement method according to an embodiment of the present application;

[0017] Figure 2 This is a flow chart of a calibration-free large-scale structure deformation laser vision fusion measurement method according to an embodiment of the present application;

[0018] Figure 3 is a schematic diagram of an imaging relationship according to an embodiment of the present application;

[0019] Figure 4 This is a schematic diagram of the angle between the laser plane and the imaging plane according to an embodiment of the present application. Figure 1 ;

[0020] Figure 5 This is a schematic diagram of the angle between the laser plane and the imaging plane according to an embodiment of the present application. Figure 2 ;

[0021] Figure 6 is a schematic diagram of movement of a measurement object according to an embodiment of the present application;

[0022] Figure 7This is a schematic diagram of a calibration-free large-scale structure deformation laser vision fusion measurement system according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of this application. It should be noted that, in the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] In this embodiment, a calibration-free laser vision fusion measurement method for large-scale structure deformation is provided, wherein, Figure 1 As shown, a visual image acquisition instrument is provided. A laser emitter emits a laser line from the inner wall of the target structure, forming an image on the instrument. The target offset of the pixels between the laser line and the baseline is determined based on the target image formed on the instrument. Prior to this, the correspondence between pixel displacement and proportional coefficient is fitted by controlling the actual displacement of the measured object and the corresponding pixel displacement imaged by the visual image acquisition instrument during the displacement process, generating a predetermined relationship table. After obtaining the target offset corresponding to the target image, the proportional coefficient corresponding to the target offset is retrieved by querying the predetermined relationship table. Based on the proportional coefficient, the target offset is converted into the actual physical displacement resulting from the deformation of the target structure.

[0026] Figure 2 This is a flow chart of a calibration-free large-scale structure deformation laser vision fusion measurement method according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps:

[0027] S10: collecting a target image formed by the laser line emitted by the laser transmitter in the target structure through a visual image acquisition device;

[0028] S20: determining a target offset of pixels between the laser line and the reference line based on the target image;

[0029] S30: Obtaining a proportional coefficient corresponding to the target offset by querying a predetermined relationship table; the predetermined relationship table records the corresponding relationship between the target offset and the proportional coefficient;

[0030] S40: converting the target offset into a physical displacement based on the proportional coefficient;

[0031] S50: Determine deformation data of the target structure according to the physical displacements corresponding to all pixel points.

[0032] In this embodiment, the visual image capture device may include a camera. The visual image capture device may be paired with a laser emitter, and each visual image capture device may be used to capture a target image formed by a laser beam emitted by a laser emitter within a target structure. The laser emitter may also be referred to as a laser, and the visual image capture device may be mounted on the inner wall of the target structure. The laser emitter may emit a fan-shaped laser beam along a cross-section of the target structure toward the inner wall of the target structure. Here, the cross-section may be a cross-section perpendicular to the radial direction of the target structure. The target structure may be a tunnel, for example.

[0033] In one embodiment, deformation detection can be based on the principle of laser triangulation to measure the structural deformation of the measured plane. Based on the proportional coefficient, a geometric relationship model between the laser plane and the imaging plane can be established to eliminate the measurement error caused by the non-parallelism of the two planes. The laser line can also be called the monitoring line. The relationship between the laser plane and the imaging plane is as follows: Figure 3 As shown, where O W is the origin of the laser plane coordinate system, X W 、Y W and Z W are the X-axis, Y-axis and Z-axis of the laser plane coordinate system respectively; C is the origin of the imaging plane coordinate system, X C 、Y C and Z C are the X, Y, and Z axes of the laser plane coordinate system, respectively. a1, b1, and c1 are the pixel positions of the reference line on the laser plane, a2, b2, and c2 are the pixel positions of the laser line on the laser plane, a1', b1', and c1' are the pixel positions of the reference line on the imaging plane, and a2', b2', and c2' are the pixel positions of the laser line on the imaging plane.

[0034] Among them, such as Figure 4As shown in the figure, the fan-shaped laser line emitted by the laser transmitter forms a laser plane in space, which has a fixed angle θ with the imaging plane of the visual image acquisition device. When the object surface shifts, the position of the laser line on the visual image acquisition device shifts, resulting in an angle change Δθ. By establishing a sine theorem model, the pixel offset (Δh) can be converted into actual displacement (Δy) given the known distance between the laser plane and the visual image acquisition device (i.e., the object distance L) and the focal length f of the visual image acquisition device. Here, is the linear calibration coefficient. This yields the formula: Δh = k1·Δy.

[0035] In one embodiment, the target offset is the offset of the aforementioned pixel point. Determining the target offset of the pixel point between the laser line and the baseline may refer to determining the target offset between the coordinates of each pixel point on the laser line and the coordinates on the baseline.

[0036] In one embodiment, the physical displacement is the aforementioned actual displacement, i.e., the displacement of a point resulting from the actual deformation of the target structure. The predetermined relationship table may record proportional coefficients corresponding to different target offsets. For example, the predetermined relationship table may be generated based on a fitting function between the target offsets and the proportional coefficients.

[0037] In one embodiment, a complete geometric relationship model is established based on the baseline distance L from the laser emitter to the optical center of the visual image acquisition device, the focal length f, the initial angle α between the laser plane normal vector and the baseline, and the actual angle θ between the laser plane and the imaging plane as a dynamic calibration parameter. According to the modified laser point projection model, Figure 5 As shown in the figure, when the angle between the laser plane and the imaging plane is θ, the relationship between the pixel displacement Δh (i.e., target offset or pixel offset) and the actual displacement Δy (i.e., physical displacement or actual displacement) can be expressed as follows:

[0038]

[0039] By introducing a dynamic compensation mechanism for the angle θ, the measurement accuracy under complex installation conditions is significantly improved.

[0040] In one embodiment, determining the deformation data of the target structure based on the physical displacement corresponding to all pixel points may include: traversing the physical displacement corresponding to all pixel points on the laser line in the target image to generate a full-field displacement distribution map representing the deformation of the target structure.

[0041] In one embodiment, before step S10, the method may further include establishing a baseline. Establishing the baseline may include capturing a plurality of baseline images corresponding to light emitted by the laser transmitter and averaging the images when the target structure is not deformed or the disturbance level is less than a predetermined value; extracting the position of the laser line using a Steger algorithm after eliminating noise interference to obtain a stable baseline and storing the position information of each pixel on the baseline.

[0042] Here, the position information may include coordinate data. Step S20 may include: performing pre-processing on the target image, such as noise reduction and fracture repair; extracting the precise position of the current laser line based on the Steger algorithm; and comparing the position of each pixel of the laser line with the position of the corresponding pixel of the baseline one by one to calculate the target offset.

[0043] Here, the offset may be a lateral offset, that is, an offset in the X-axis direction of the laser plane, wherein the X-axis and the Y-axis of the laser plane are perpendicular to the radial direction of the target structure, and the Z-axis is consistent with the radial direction.

[0044] Thus, during the actual inspection process, a simple query of the pre-set relationship table between the proportional coefficient and the target offset can be used to find the proportional coefficient corresponding to the offset of the current laser line pixel. This offset can then be converted to the actual physical displacement of the target structure itself based on the proportional coefficient. This conversion from laser line offset to actual structure deformation can be achieved simply by querying the pre-set relationship table, eliminating the need for equipment parameter calibration before each inspection. This avoids the difficulty of calibration under complex working conditions, which can lead to inefficiencies and improves inspection efficiency and accuracy.

[0045] In some embodiments, before step S10, the method further includes:

[0046] The visual image acquisition device acquires a measurement image formed by a laser line emitted by a laser emitter during a predetermined number of movements of the measurement object;

[0047] performing fitting based on the number of movements of the measured object, the actual displacement of the measured object, and the pixel offset in the measured image to obtain a fitting function between a proportional coefficient and the pixel offset;

[0048] Determining a correspondence between the scale coefficient and the pixel offset based on the fitting function;

[0049] The corresponding relationship is recorded in a predetermined relationship table.

[0050] In one embodiment, there are multiple measuring objects, and the movement direction of the measuring objects is consistent with the deformation direction along the radial direction of the target structure. Specifically, the multiple measuring objects can be made of thermally stable Invar standard blocks, which serve as calibration blocks. The calibration blocks are manually fixed at specific points, and the movement process can involve vertically moving the calibration blocks along the radial direction of the target structure. After each movement, the visual image acquisition device is synchronously triggered to capture a measurement image, recording the actual displacement and the pixel offset of the laser line in the measurement image.

[0051] Here, the predetermined number of times can be 50, so the three calibration blocks generate a total of 150 sets of data, covering the full range of 0-4096 pixels of the target structure cross section. Each time the measurement object is moved, the measurement image will correspond to the actual displacement of the measured structure.

[0052] In one embodiment, performing the fitting based on the number of movements of the measured object, the actual displacement of the measured object, and the pixel offset in the measured image may include:

[0053] Fitting is performed based on the number of movements of the measured object, the actual displacement of the measured object in each movement, the proportional coefficient corresponding to the change in the angle between the laser plane and the imaging plane caused by each movement, and the pixel offset in the measured image.

[0054] Here, each pixel's horizontal coordinate The corresponding proportional coefficient It can be directly calculated based on the relationship between the actual displacement and the pixel offset, that is, based on the number of times the measured object is moved, the actual displacement of the measured object in each movement, and the proportional coefficient corresponding to the change in the angle between the laser plane and the imaging plane caused by each movement. The pixel offset in the measured image is fitted to obtain the fitting function:

[0055]

[0056] Where j is the number of times the object is moved. Indicates the pixel at the jth movement The displacement is the pixel offset, which is caused by the tilt of the laser plane, resulting in an angle between the laser plane and the imaging plane. Change, and then As the spatial position changes, the same horizontal coordinate Generate multiple groups in different numbers of moves , the input data of the overdetermined equations are fitted.

[0057] like Figure 6 As shown, for the i The actual displacement of each movement is h, proportionality factor It can represent the proportional relationship between the target offset and the physical displacement, and it can also represent the proportional relationship between the pixel offset and the actual displacement. i is a positive integer greater than 0 and less than or equal to n, and n is the total number of pixels on the laser line.

[0058] In one embodiment, if the predetermined number of times is 50, an observation equation containing 50 sets of movement data is established for each pixel, and a total of 204,800 equations are generated for the 4096 pixels of the full screen. The fitting function can be further expressed as , where f is a fifth-order polynomial fitting formula.

[0059] In this way, by collecting the corresponding measurement images during the multiple movements of the measured object along the deformation direction, the corresponding relationship between the proportional coefficient and the pixel offset can be accurately obtained based on the displacement of the pixel points in the measured image and the actual displacement of the measured object, which is conducive to quickly and accurately obtaining the required proportional coefficient in the actual deformation detection process.

[0060] In some embodiments, determining the correspondence between the scale coefficient and the pixel offset based on the fitting function may include:

[0061] Constructing the Euclidean norm of the residual vector in the fitting function based on the least squares method;

[0062] The Euclidean norm is derived, and a corresponding relationship between the proportional coefficient and the pixel offset is determined based on a case where a result of the derivation is equal to 0.

[0063] Here, assume there is a set of observation data points: ( )、( ),…,( ),

[0064] ,

[0065] Then the polynomial fitting model, that is, the aforementioned fitting function, can be expressed as:

[0066]

[0067] Where S is the column vector of proportional coefficients corresponding to the measured image (i.e., dependent variable), X is the matrix of pixel offsets (i.e., independent variables), such as the Vandermonde matrix, and A is the coefficient vector to be determined. is the residual vector.

[0068] In one embodiment, the Euclidean norm of the residual vector in the fitting function is constructed based on the least squares method. , which can be expressed as: J(A)=||S-XA|| 2 =(S-XA) T (S-XA).

[0069] Furthermore, J(A)=S T S-2A T X T S+A T X T XA.

[0070] In one embodiment, taking a derivative of the Euclidean norm and determining the correspondence between the scale factor and the pixel offset based on a result of the derivative being equal to 0 may include taking a first-order derivative of the Euclidean norm and setting it to zero to obtain a minimum value, that is:

[0071]

[0072] From this we get:

[0073]

[0074] when When is a full-rank matrix, the normal equations have a unique solution:

[0075]

[0076] If there is an ill-conditioned matrix or insufficient rank, the pseudo-inverse can be used:

[0077]

[0078] Then the predicted value of S after fitting is for:

[0079]

[0080] Therefore, the complete fifth-order polynomial least squares fitting problem is, That is, the proportional coefficient required based on the pixel offset or the target offset. The corresponding relationship between the proportional coefficient and the pixel offset can be strictly expressed in matrix form as follows:

[0081] , , .

[0082] In this way, based on the Euclidean norm of the residual vector in the fitting function, that is, the sum of squared errors, combined with the case where the derivative is equal to 0, the minimum error can be represented, and then the correspondence between the proportional coefficient and the pixel offset, that is, the correspondence between the proportional coefficient and the target offset, can be more accurately obtained.

[0083] In some embodiments, determining a target offset of pixels between the laser line and a reference line based on the target image includes:

[0084] After performing denoising on the target image, determining whether the background interference complexity in the target image meets a predetermined condition;

[0085] In response to the background interference complexity reaching a predetermined condition, adjusting a threshold corresponding to the target image based on a local window mean, a standard deviation, and an empirical coefficient corresponding to the target image;

[0086] Determine pixel coordinates of the laser line in the target image based on a predetermined algorithm and the threshold;

[0087] A target offset of a pixel point between the laser line and a reference line is determined based on the pixel point coordinates.

[0088] In one embodiment, in the numerical calculation module, high-precision image processing and dynamic compensation algorithms are used to convert the pixel coordinates of the laser line into actual deformation data. Based on the laser light strip image captured by the industrial camera, Gaussian filtering and morphological closing operations are first used to eliminate ambient light interference and speckle noise. After denoising, the sub-pixel coordinates of the center of the laser light strip are extracted by the Steger algorithm. The Steger algorithm calculates the normal direction of the light strip based on the Hessian matrix, and iterates the grayscale center of gravity along the normal direction to achieve a positioning accuracy of the light strip center of ±0.05 pixels. For complex background interference, adaptive threshold segmentation can be used, and the threshold calculation formula is:

[0089] T(x,y)=μ(x,y)+k*σ(x,y).

[0090] Where μ(x, y) is the local window mean, σ(x, y) is the standard deviation, and the empirical coefficient k can be between 1.2 and 1.5, which significantly improves the noise suppression capability.

[0091] In some embodiments, the scaling coefficient is related to the scaling factor of the visual image acquisition device and the cosine value of the angle between the laser plane and the imaging plane; wherein the scaling factor is equal to the product of the pixel size and the object distance divided by the focal length.

[0092] Here, the proportional coefficient can be the quotient of the proportional factor and the cosine value of the angle. For example, the proportional coefficient can be expressed as s i = , where the scale factor of the visual image acquisition instrument is , is the scale factor when the X-axis of the visual image acquisition instrument is parallel to the laser plane, which represents the relationship between object distance, focal length and pixel size.

[0093] The cosine value of the angle between the laser plane and the imaging plane is cosθ.

[0094] In this way, the proportionality factor can be incorporated into the angle between the laser plane and the imaging plane to avoid directly using the pixel offset as the actual displacement to calculate the proportionality factor, which can easily lead to systematic errors.

[0095] In some embodiments, converting the target offset into a physical displacement based on the proportional coefficient includes: multiplying the target offset by the proportional coefficient to obtain the physical displacement.

[0096] This application also provides a calibration-free large-scale structure deformation laser vision fusion measurement system, such as Figure 7 As shown, the system applies the calibration-free large-scale structure deformation laser vision fusion measurement method described in any one or more of the aforementioned method embodiments, and the system includes: a processing device, and at least one pair of visual image acquisition instruments and laser transmitters;

[0097] The at least one pair of visual image collectors and laser emitters are arranged on the inner wall of at least one section of the target structure, and the distance between the pair of visual image collectors and the laser emitters is greater than a preset distance;

[0098] The axis of the laser emitter is parallel to the axis of the target structure, and the processing device at least establishes a communication connection with the visual image acquisition instrument.

[0099] Here, a pair of visual image acquisition devices and laser emitters can be installed on the inner wall of a section of the target structure. Multiple pairs of visual image acquisition devices and laser emitters can be sequentially installed on multiple sections of the target structure. The laser emitters use semiconductor lasers as their light source, combined with precision optical components and intelligent control circuits. Semiconductor lasers with a wavelength of 635nm-808nm are used to achieve normal operating conditions and high dust penetration, ensuring that the laser beam maintains high collimation during long-distance transmission. Laser emitters are deployed along the centerline of the underground structure vault, embedded in the sidewall base, or on supporting structures, spaced every 100-150 meters along the longitudinal direction of the monitoring area, and networked in pairs with visual image acquisition devices (such as industrial cameras).

[0100] In one embodiment, the laser transmitter can be mounted using embedded anchors (e.g., M12 stainless steel) to ensure the laser transmitter axis is parallel to the target structure axis. The laser plane can be incident at an angle of 15-30° to enhance fringe contrast. The projection direction extends longitudinally along the target structure to facilitate coverage of the full width of the target cross-section (e.g., from the vault to the invert).

[0101] In one embodiment, the laser transmitter may further include: an IP67-level moisture-proof sealing cover, a rubber shock-absorbing pad in the vibration-sensitive area, and a temperature and humidity sensing-linked power adaptive module to ensure the stability of laser projection under complex working conditions.

[0102] In one embodiment, the visual image acquisition device, serving as the system's core sensing unit, can consist of a main camera, auxiliary cameras, and a miniature weather station, enabling comprehensive collection of deformation information. The main camera can be equipped with a 75mm fixed-focus industrial lens and a global shutter complementary metal-oxide-semiconductor (CMOS) sensor, achieving a resolution of 4096×3072 and a dynamic range of 60dB. Combined with the lens's high-contrast optical properties, this ensures clear capture of submillimeter laser stripe deformation details within a 20m monitoring distance.

[0103] In one embodiment, the main camera is installed at a fixed inclination angle of 15°±2°, with a baseline spacing of 1.2m from the laser transmitter. A magnetic damping base is used to suppress environmental vibrations. The auxiliary camera is arranged at a 30° angle to the main camera axis, and the coaxiality error between the auxiliary camera and the main camera axis is less than 0.1°. This error can also be calibrated using a theodolite, for example. The field of view overlap rate between the auxiliary camera and the main camera can be greater than or equal to 80%. The overall deployment scheme significantly improves the robustness and data reliability of deformation monitoring in complex environments through high-precision optical configuration and strict installation specifications.

[0104] In one embodiment, the processing device can be an intelligent processing module that is responsible for data processing, feature extraction, and decision control, and adopts a three-level architecture design. The processing device can include a field controller, a communication module, and an edge server.

[0105] The field controller can support real-time deep learning algorithms to perform sub-pixel positioning and preliminary deformation calculations of the laser line. The edge server can utilize an Intel Xeon W-11955M processor, equipped with 128GB of memory and a 2TB solid-state drive (SSD), enabling parallel processing and long-term storage of multi-section data. The communication module utilizes 5G New Radio (NR) Sub-6GHz technology, supporting 2Gbps downlink and 1Gbps uplink rates, ensuring real-time transmission of monitoring data. High-speed data exchange between the field controller, communication module, and edge server is achieved via Fibre Channel (FC) and Gigabit Ethernet (GbE), with latency below 10μs. The system utilizes containerized deployment technology, supporting dynamic expansion and hot-update of functional modules, ensuring continuous and stable operation under complex operating conditions.

[0106] In some embodiments, the visual image acquisition device includes: a main camera and an auxiliary camera; the angle between the axis of the main camera and the axis of the auxiliary camera is less than a preset threshold.

[0107] Here, the preset threshold may be 30°, 45° or 60°, etc. For example, the angle between the main camera axis and the auxiliary camera axis may be 30°.

[0108] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0109] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, hard disk, or tape), an optical medium (e.g., a DVD), or a semiconductor medium such as a solid-state drive (SSD).

[0110] The above description is only a preferred embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the scope of protection of the present application.

[0111] The foregoing is merely a list of specific embodiments of the present application, intended to enable those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the broadest scope consistent with the principles and novel features of the present application.

Claims

1. A calibration-free laser vision fusion measurement method for large-scale structure deformation, characterized in that: The method comprises: The visual image acquisition device acquires a measurement image formed by a laser line emitted by a laser emitter during a predetermined number of movements of the measurement object; performing fitting based on the number of movements of the measured object, the actual displacement of the measured object in each movement, the proportional coefficient corresponding to the change in the angle between the laser plane and the imaging plane caused by each movement, and the pixel offset in the measured image, to obtain a fitting function between the proportional coefficient and the pixel offset; Constructing the Euclidean norm of the residual vector in the fitting function based on the least squares method; Derivative the Euclidean norm, and determining a corresponding relationship between the proportional coefficient and the pixel offset based on a result of the derivative being equal to 0; Recording the corresponding relationship in a predetermined relationship table; A target image formed by the laser line emitted by the laser transmitter is collected in the target structure by a visual image collector; determining a target offset of pixels between the laser line and a reference line based on the target image; Obtaining a proportional coefficient corresponding to the target offset by querying a predetermined relationship table; the predetermined relationship table records the corresponding relationship between the target offset and the proportional coefficient; the proportional coefficient is related to the scale factor of the visual image acquisition device and the cosine value of the angle between the laser plane and the imaging plane; wherein the proportional factor is equal to the product of the pixel size and the object distance divided by the focal length; Converting the target offset into a physical displacement based on the proportional coefficient; The deformation data of the target structure is determined according to the physical displacements corresponding to all pixel points.

2. The method according to claim 1, characterized in that There are multiple measuring objects, and the moving directions of the measuring objects are consistent with the deformation direction along the radial direction of the target structure.

3. The method according to claim 1, characterized in that The determining, based on the target image, a target offset of pixels between the laser line and the reference line includes: After performing denoising on the target image, determining whether the background interference complexity in the target image meets a predetermined condition; In response to the background interference complexity reaching a predetermined condition, adjusting a threshold corresponding to the target image based on a local window mean, a standard deviation, and an empirical coefficient corresponding to the target image; Determine pixel coordinates of the laser line in the target image based on a predetermined algorithm and the threshold; A target offset of a pixel point between the laser line and a reference line is determined based on the pixel point coordinates.

4. The method according to claim 1, wherein The converting the target offset into a physical displacement based on the proportional coefficient includes: The physical displacement is obtained by multiplying the target offset by the proportional coefficient.

5. A calibration-free large-scale structure deformation laser vision fusion measurement system, characterized by: The system applies the method according to any one of claims 1 to 4, and the system comprises: a processing device, and at least one pair of visual image acquisition instruments and laser transmitters; The at least one pair of visual image collectors and laser emitters are arranged on the inner wall of at least one section of the target structure, and the distance between the pair of visual image collectors and the laser emitters is greater than a preset distance; The axis of the laser emitter is parallel to the axis of the target structure, and the processing device at least establishes a communication connection with the visual image acquisition instrument.

6. The system according to claim 5, characterized in that The visual image acquisition device includes: a main camera and an auxiliary camera; The angle between the main camera axis and the auxiliary camera axis is smaller than a preset threshold.

Images