Building structure deformation measurement method, system and device

Abstract

The invention provides a building structure deformation measurement method, system and device, and relates to the technical field of building structure deformation measurement. The measuring method comprises the following steps: acquiring a laser point physical coordinate, an included angle between a laser emission direction and a world coordinate system and a building image; after the building image is preprocessed, laser point pixel coordinates are extracted; after the relative coordinates of the object surface laser points are calculated, solving a homography transformation matrix, carrying out perspective correction on the building image to obtain an orthographic projection image, and solving a conversion coefficient between pixels and an actual distance; inputting the preprocessed building image into a pre-trained semantic segmentation model to obtain a beam body segmentation mask and a beam body edge curve; and the actual span of the beam body is obtained through conversion of the conversion coefficient. According to the scheme, three-dimensional movement is achieved through the electric driving platform, the positioning position of the laser point can be adjusted according to the size and position of the building structure, buildings of different heights and angles are adapted, and the limitation that only building structures of specific types or sizes can be measured in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of building structure deformation measurement technology, and in particular to a method, system and device for measuring building structure deformation. Background Technology

[0002] Building structures undergo various deformations during long-term use, among which deflection is a crucial indicator for measuring structural safety and plays a key role in assessing structural safety. Traditional deflection measurement methods mainly fall into two categories: contact measurement and non-contact measurement. Contact measurement methods require direct contact with the structure being measured, which is not only complex to implement but also limits the number of measurement points. While non-contact measurement methods avoid direct contact, they suffer from limitations such as limited measurement range and the inability to simultaneously acquire multi-dimensional information.

[0003] With the development of computer vision and laser ranging technology, non-contact deflection measurement based on optical images has gradually become a research hotspot. This type of method captures images of the structure with a camera and combines image processing algorithms to calculate the displacement and deformation of the structure. It has advantages such as non-contact, multi-point measurement, and large information capacity, but it still has many shortcomings and cannot meet the measurement needs of building structure deformation: A journal article titled "Research on Image Processing Algorithm for Laser-Based Bridge Deflection Detection" (Zhao Hongwei et al., Instrumentation Technology and Sensors, 2019) discloses a method that uses a pyramid model to obtain the region of interest (ROI), constructs a multi-layer target image pyramid, detects the laser spot region in the top layer image, and then maps it back to the original image. It employs an ellipse fitting method to achieve sub-pixel-level localization of the laser spot center, achieving high-precision localization through steps such as traversing boundary points, segmenting sub-regions, randomly selecting boundary points, and solving the ellipse equation using the least squares method. However, this scheme requires installing a target on the structure under test, increasing system complexity. It is also sensitive to ambient light interference and atmospheric conditions, and is only applicable to bridge deflection detection.

[0004] The paper titled "Research and Application of Deflection Measurement Method Based on Optical Images" (Feng Jianhao, Jiangsu University, 2021) discloses an off-axis digital image correlation method considering off-axis angle, which can realize long-distance non-contact deflection measurement of bridges. It systematically analyzes the influence of camera intrinsic and extrinsic parameters and environmental factors on the accuracy of deflection measurement. An image correction method based on the SIFT algorithm is established to effectively eliminate measurement errors caused by the attitude changes of the UAV when measuring bridge deflection. However, the measurement accuracy of this method decreases significantly with increasing distance, has high requirements for lighting conditions (large measurement errors occur in low light intensity), requires speckle markings on the surface of the measured structure, and has high computational complexity.

[0005] Patent application CN107588913B, entitled "A Bridge Deflection Detection System and Method," discloses a target design using four solid black circles on a white background for image recognition and positioning; a pan-tilt control system supporting horizontal rotation for precise recording and control of the pan-tilt position; and calculation of the precise distance from the telescope's optical system to the target using geometric relationships. However, this solution requires setting up targets at multiple test points on the bridge, making installation complex. Furthermore, the pan-tilt rotation takes time, affecting real-time performance. The system is also bulky and inconvenient to carry and install, limiting its applicability to bridge deflection detection.

[0006] Patent application CN109631787B, entitled "Method for Detecting the Center of a Light Spot in a Transmissive Target Image and a Bridge Deflection Image-Based Detection Device," discloses a method of dividing all boundary points into multiple sub-regions according to their coordinate positions, randomly selecting boundary points from these sub-regions while ensuring that no collinear points exist; solving the coefficients of the ellipse equation using the least squares method based on the selected boundary points; and calculating the coordinates by traversing the boundary points to calculate the sum of squared residuals, determining the optimally fitted ellipse, and calculating the center coordinates. This method requires installing a transmissive target on the structure under test, is highly sensitive to ambient light interference, and has high algorithm complexity, making system installation and debugging complex. It is only suitable for bridge deflection detection.

[0007] Patent application CN105067208B, entitled "A Multi-channel Bridge Deflection Monitoring Method Based on CCD," discloses a method to obtain displacement by calculating the difference between the center coordinates of a sub-region before and after deformation. The sub-pixel search method employs a quadratic surface fitting approach, forming a local quadratic surface from the element with the largest absolute value in the correlation coefficient matrix and its surrounding pixels, fitting unknown coefficients to calculate sub-pixel positions. Deflection calculation converts pixel units to actual units using a scale calibration method. This scheme requires setting targets at multiple measuring points on the bridge, resulting in complex system wiring, high installation and maintenance costs, high requirements for lighting conditions (requiring additional lighting equipment), and significant environmental influences. Therefore, it is only suitable for bridge deflection detection. Summary of the Invention

[0008] The purpose of this invention is to provide a method, system, and apparatus for measuring structural deformation of buildings, so as to solve at least one of the above-mentioned technical problems existing in the prior art.

[0009] In a first aspect, to solve the above-mentioned technical problems, the present invention provides a method for measuring the deformation of building structures, comprising the following steps: Step 1: Set up the size measurement device and perform preliminary calibration, specifically including a laser rangefinder, a monocular camera, and an electric drive platform; the monocular camera is located at the center of the electric drive platform, and four laser rangefinders are located at the four corners of the electric drive platform; the initial direction of laser emission is perpendicular to the electric drive platform and parallel to the optical axis of the monocular camera; the laser rangefinder includes an angle (e.g., pitch and rotation) motor and an angle sensor, used to control the laser emission angle.

[0010] In one feasible implementation, the preliminary calibration specifically includes: The monocular camera was calibrated using Zhang Zhengyou's flat-panel calibration method, and its internal and external parameters were acquired and stored. Move the electric drive platform to the standard calibration area, calibrate the initial physical coordinates of the four laser rangefinders using a standard-size calibration plate (a building with known length and width), and record the installation offset of each laser rangefinder relative to the center of the platform. The electric drive platform is moved a preset distance along the X, Y and Z directions respectively. The laser rangefinder readings are compared with the actual distance the platform moves to establish a three-degree-of-freedom position correction model, including the current positioning coordinates of the platform, for subsequent coordinate correction. The angle motor and angle sensor are calibrated, and an angle measurement model is established, including the angle between the laser emission direction and the world coordinate system.

[0011] This lays a solid foundation for accurate image acquisition and laser rangefinder positioning in subsequent steps. At the same time, it keeps the laser rangefinder as parallel to the ground as possible, thereby reducing measurement errors in subsequent steps.

[0012] In one feasible implementation, the electric drive platform includes a servo motor and / or a stepper motor and / or a linear module to enable three-dimensional movement and precise positioning of the platform.

[0013] Step 2: Move the platform of the electric drive platform, rotate the angle motor so that the laser points (spots) of each laser rangefinder are projected onto the corresponding corner points of the building facade to be measured. Collect the laser ranging data after the previous calibration as the physical coordinates of the laser points. Collect the angle between the laser emission direction and the world coordinate system through the angle sensor. At the same time, collect the building image through the monocular camera. The building image includes the laser points and the building facade.

[0014] In one feasible implementation, the physical coordinates of the laser point belong to the world coordinate system and can be denoted as ( ). ), ( ), ( )and( ).

[0015] Step 3: After preprocessing the building image, extract the pixel coordinates of the laser points to provide a high-precision (±1 pixel) image reference for subsequent calculations.

[0016] In one feasible implementation, step 3 specifically includes: Step 31: Obtain the candidate region mask for laser points through noise suppression, HSV color gamut conversion, mask extraction and mask morphology optimization.

[0017] In one feasible implementation, step 31 specifically includes: Step 311: Apply a Gaussian convolution kernel of a preset size (standard deviation of Gaussian function). (Set to 1.2) The original image of the building image is smoothed to obtain a smooth image. This can effectively suppress Gaussian noise and salt-and-pepper noise by using the normal distribution characteristics and weighted averaging of adjacent pixels. Step 312: Select the original image as the guide image and perform guided filtering on the smoothed image (filter radius is 5, regularization parameter is 5). (Set to 100) to obtain a Gaussian filtered image. This can eliminate high-frequency interference from building surface texture while preserving the grayscale difference between the laser point and the background, thus ensuring that the edges of the laser point are clear and not blurry. Step 313: Convert the Gaussian filtered image to the HSV color gamut, set the threshold range for the V channel, and filter out the high-brightness areas from the Gaussian filtered image; Step 314: Set the threshold range for the S channel to remove pure white background reflections from the Gaussian filtered image; Step 315: Perform a logical AND operation on the filtering results of the V channel and S channel to generate a binary mask that only contains the candidate region of the laser point, thereby eliminating more than 95% of non-target pixels and greatly reducing the amount of computation in subsequent processing. Step 316: Perform morphological closing operation (3*3 rectangular structuring element) on the binarized mask to fill the (tiny) holes inside the laser points (caused by noise); then perform morphological opening operation (3*3 rectangular structuring element) to remove noise attached to the mask edges, and obtain a laser point candidate region mask (with complete outline and clean interior).

[0018] Step 32: Based on the laser point candidate region mask, after extracting the candidate region, determine the laser point region image through edge detection and contour feature filtering to avoid interference from workshop light reflection, building surface markers, etc.

[0019] In one feasible implementation, step 32 specifically includes: Step 321: Extract the edge of the Gaussian-filtered image after the laser point candidate region masking to obtain the candidate region. Then, based on the preset double threshold, extract the continuous edge contour of the laser point through Gaussian gradient calculation, non-maximum suppression and hysteresis thresholding to ensure that the edge is free of breakage and redundant edge. Step 322: (using the findContours function of OpenCV tool) After extracting all contours of the candidate region, set the filtering conditions based on the geometric features of the laser point (circle or approximately circle) to filter out the laser point region image.

[0020] In one feasible implementation, the screening criteria include: Filtering condition 1: Based on the actual size of the laser point (the pixel area after imaging is usually between 50-200 pixels), set the area threshold range to eliminate excessively small noise contours and excessively large background interference areas. Filtering criterion 2: Based on roundness Calculation formula ,in, Represents the area of ​​the outline. This indicates the perimeter of the outline and sets a roundness threshold range to eliminate irregular, non-circular outlines. Filtering condition 3: Calculate the ratio of the minimum bounding rectangle of the contour to the area of ​​the contour, and filter out contours with a ratio ≤ preset ratio threshold in order to further eliminate interference from non-laser points.

[0021] Step 33: For the laser point area image, the center pixel coordinates are solved by fitting algorithm, and the final center pixel coordinates are obtained by multi-frame averaging optimization to improve the stability of the center pixel coordinates.

[0022] In one feasible implementation, step 33 specifically includes: Step 331: Using the least squares method, fit a circle to the edge contour of the laser point and solve for the coordinates of the circle center. The specific calculation formula includes: ; in, Indicates the coordinates of the center of the circle; Indicates the radius of the circle; Using all pixels on the edge contour as samples, an error function is constructed. By minimizing the error function through partial derivatives, the coordinates of the circle center and the circle radius are obtained. The specific expressions include: ; in, Indicates the first edge contour The coordinates of each pixel; Step 332: Since the building image can be multiple frames taken under the same conditions, and the above steps are performed separately to obtain multiple sets of center coordinates, the Grubbs criterion is used to remove abnormal center coordinates (i.e., center coordinates that deviate from the mean by more than 2 standard deviations) from the multiple sets of center coordinates from the multiple frames. The arithmetic mean of the remaining center coordinates is then taken to obtain the four (precise) laser point center pixel coordinates. ( ), ( ), ( )and ( ).

[0023] Step 4: Based on the physical coordinates of the laser point and the center pixel coordinates of the laser point, calculate the relative coordinates of the laser point on the object surface, solve the homography transformation matrix, perform perspective correction on the building image, obtain the orthophoto image, and obtain the conversion coefficient between the pixel and the actual distance. This eliminates the errors caused by the perspective distortion of the monocular camera and the non-ideal plane of the building surface, establishes a high-precision mapping relationship between the pixel and the actual distance, and provides a benchmark for subsequent measurements.

[0024] In one feasible implementation, step 4 specifically includes: Step 41: Based on the previous calibration data and laser ranging data, solve for the physical coordinates of the laser point (i.e., the precise position of the laser point in the world coordinate system) through spatial geometric calculations. The specific calculation formula includes: ; ; ; in, , , Indicates the first Physical coordinates of each laser point; , , Indicates the current positioning coordinates of the platform; , Indicates the first The installation offset of the laser rangefinder relative to the center of the platform; Indicates the first Real-time laser ranging data collected by a laser rangefinder; , , This represents the angle between the laser emission direction and the world coordinate system.

[0025] Step 42: Define the local coordinate system of the object surface. Among them, the laser point in the upper left corner ( The projection point of ) is taken as the origin. , The axis runs horizontally to the right along the building facade (i.e., in relation to the world coordinate system). (axis parallel) The axis runs vertically downwards along the building facade (i.e., in relation to the world coordinate system). (axis parallel) The axis is along the normal vector direction of the building facade (which can be obtained by fitting the physical coordinates of 4 laser points); Project the physical coordinates of the four laser points onto the local coordinate system of the object surface. Within the plane, the relative coordinates of the laser point on the object surface are obtained and corrected. The horizontal projection error caused by axis tilt (slight tilt of the building surface) is specifically expressed as follows: First projection point The origin The relative coordinates are ; Second projection point The relative coordinate expressions include: ; ; Third projection point The relative coordinate expressions include: ; ; Fourth projection point The relative coordinate expressions include: ; .

[0026] Step 43: Solve for the homography transformation matrix. This matrix is ​​used to calculate the corresponding pixel in the image pixel coordinate system for any point in the local coordinate system of the object surface. This allows for rapid conversion between the two coordinate systems, providing a foundation for subsequent image measurement and target localization. The specific expression includes: ; in, , Indicates the relative coordinates of the laser point on the object surface; , Indicates the center pixel coordinates of the laser point; The 3x3 homography matrix is ​​expressed as follows: ; in, Represents the matrix elements (there are 9 elements in total, but due to homogeneity, the actual requirement is to solve for 8 unknown elements); The specific expressions that expand into non-homogeneous form include: ; In this way, by using the known point pairs between the relative coordinates of the laser point on the object surface and the pixel coordinates of the laser point center, a system of linear equations can be constructed, which can then be solved. (4 pairs of known points are used to construct 8 linear equations and solve for 8 unknown elements.)

[0027] Step 44: Based on the homography transformation matrix, perform perspective correction on the architectural image by setting the corrected image size and inverse perspective transformation (using the OpenCV vision library). Specific expressions include: ; in, express The inverse matrix is ​​used to reverse the transformation from image to object plane into an orthophoto mapping from object plane to image, thereby eliminating perspective distortion; and They represent and Corrected coordinates.

[0028] Preferably, the corrected image size refers to the size of the image first... In the calculation of the maximum relative coordinates, the specific steps include: Horizontal maximum relative coordinates That is, the horizontal distribution range covering all laser points, specifically expressed as: ; Vertical maximum relative coordinates That is, the vertical distribution range covering all laser points, specifically expressed as: ; Then, based on the required measurement accuracy (e.g., 0.1 mm / pixel), the maximum relative coordinates are converted into the number of pixels, specifically including: Horizontal pixels The specific expression is: ,in, This indicates the rounding operation; Vertical pixel count The specific expression is: ; This allows the corrected image size to match the distribution of laser points in the local coordinate system of the object surface, ensuring complete coverage of the object surface area and reasonable pixel accuracy.

[0029] Preferably, the inverse perspective transformation can be implemented using the warpPerspective function, specifically including: using the preprocessed architectural image as the input image; and... As the transformation matrix; * As the output size; use the bicubic interpolation algorithm as the interpolation algorithm; call the warpPerspective function to obtain the orthographic projection image (without perspective distortion).

[0030] Step 46: Calculate the conversion coefficient between pixels and actual distance. The specific expression includes: .

[0031] Preferably, step 46 specifically includes: Step 461: Calculate the average actual distance of the laser point in the horizontal direction. and average pixel distance The specific expressions include: ; ; Calculate the average actual distance of the laser point in the vertical direction and average pixel distance The specific expressions include: ; ; Step 462: Calculate the conversion coefficient between pixels and actual distance. The unit is mm / pixel, and the specific expressions include: ; Thus, given the pixel distances in each direction, it can be directly multiplied by... This method allows for the quick calculation of the actual distance, and vice versa.

[0032] Step 5: Input the preprocessed building image into the pre-trained semantic segmentation model to obtain the beam segmentation mask and beam edge curve; based on the beam segmentation mask, extract the pixel coordinates of the two endpoints a and c of the beam edge curve to obtain the straight line segment ac, and then calculate the pixel coordinates of the midpoint b of the straight line segment ac, thereby obtaining the precise position of the three feature points and completing the automatic recognition and feature point extraction of the beam region.

[0033] In one feasible implementation, the specific training method of the semantic segmentation model includes: preprocessing building images of different sizes and angles, labeling the beam regions and beam edge curves, and generating pixel-level mask labels as a training dataset; training the semantic segmentation model, with the preprocessed building images as input and the mask labels as output; and optimizing the model parameters through backpropagation to enable it to accurately segment beam regions and extract beam edge curves.

[0034] Step 6: Calculate the length (in pixels) of line segment ac, and convert it to the actual span of the beam using a conversion factor; similarly, calculate the height difference between endpoint a and midpoint b. The height difference between endpoint a and endpoint c Horizontal distance between endpoint a and midpoint b and the horizontal distance between midpoint b and endpoint c Then, calculate the deflection value. The specific formula is as follows: ; In this way, by combining the actual span and deflection values ​​with the relevant building codes for the building type, a compliance assessment can be accurately made.

[0035] In one feasible implementation, the conversion in step 6 refers to multiplying the pixel distance of the measured straight line segment by a conversion coefficient.

[0036] Secondly, based on the same inventive concept, this application also provides a building structure deformation measurement system, including a data receiving module, a data processing module and a result generation module; The data receiving module is used to receive laser ranging data as the physical coordinates of the laser point, the angle between the laser emission direction and the world coordinate system, and building images. The data processing module includes a preprocessing unit, a perspective correction unit, a semantic segmentation unit, and a size measurement unit. The preprocessing unit is used to preprocess the building image and extract the pixel coordinates of the laser points; The perspective correction unit calculates the relative coordinates of the laser point on the object surface based on the physical coordinates of the laser point and the center pixel coordinates of the laser point, solves the homography transformation matrix, performs perspective correction on the building image, obtains the orthographic projection image, and obtains the conversion coefficient between the pixel and the actual distance. The semantic segmentation unit is used to input the preprocessed building image into the pre-trained semantic segmentation model to obtain the beam segmentation mask and the beam edge curve; based on the beam segmentation mask, the pixel coordinates of the two endpoints a and c of the beam edge curve are extracted to obtain the straight line segment ac, and then the pixel coordinates of the midpoint b of the straight line segment ac are calculated. The dimensional measurement unit calculates the length of the straight segment ac, converts it using a conversion factor to obtain the actual span of the beam, and calculates the deflection value. ; The result generation module is used to send the results of the size measurement unit to an external source.

[0037] Thirdly, based on the same inventive concept, this application also provides a building structure deformation measurement device, including a processor, a memory, and a bus. The memory stores instructions and data that can be read by the processor. The processor is used to call the instructions and data in the memory to execute the building structure deformation measurement method as described above. The bus connects the various functional components for transmitting information.

[0038] In one feasible implementation, the size measuring device further includes a laser rangefinder, a monocular camera, and an electric drive platform.

[0039] In one feasible implementation, the laser rangefinder further includes an angle motor and an angle sensor.

[0040] By adopting the above technical solution, the present invention has the following beneficial effects: This invention provides a method, system, and device for measuring the deformation of building structures. The electric drive platform supports three-dimensional movement and laser rangefinder angle adjustment. The laser point positioning position can be adjusted according to the size and location of the building structure. The four laser rangefinders can be adjusted to adapt to building (beam and column) structures of different heights and angles, which solves the limitation of existing technologies that can only measure building structures of specific types or sizes. This scheme establishes a position correction model through preliminary three-degree-of-freedom calibration, and combines multiple measurements and mean filtering of laser ranging readings to achieve a laser point physical coordinate error of ≤0.1mm. The system employs a sub-pixel-level precision image processing algorithm to identify the laser spot center, and performs coordinate transformation by combining camera calibration parameters and laser projection angle. The deflection measurement error is ≤0.1mm, and the span measurement error is ≤0.5%, which is far superior to the accuracy level of traditional measurement methods. This solution adopts an automatic control mode, which can realize the fully automated operation from laser projection, data acquisition, image processing to result output. Four laser rangefinders work together to achieve precise positioning through angle adjustment and distance measurement without human intervention. This solution adopts a non-contact measurement method. Neither the laser rangefinder nor the monocular camera needs to contact the building structure surface. Measurements can be completed within a safe distance, and there is no need to set up targets on the building structure surface. This not only avoids the safety risks of working at height or measuring at close range, but also does not cause any damage to the building structure surface. It is particularly suitable for deformation detection of building structures that are already in use. Attached Figure Description

[0041] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0042] Figure 1 A flowchart of a method for measuring structural deformation of a building provided in an embodiment of the present invention; Figure 2 Examples of the main stages in step 3 are shown below; (a) is a Gaussian filtered image; (b) is an HSV color gamut converted image; (c) is a binarized mask image; and (d) is a laser dot region image. Figure 3 This is a schematic diagram of the process of calculating the physical coordinates of the laser point in step 4; Figure 4 This is a schematic diagram illustrating the calculation process of the relative coordinates of the laser point on the object surface in step 4. Figure 5 This is a schematic diagram of projection points provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of deflection calculation provided in an embodiment of the present invention. Detailed Implementation

[0043] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0045] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0046] The present invention will be further explained below with reference to specific embodiments.

[0047] It should also be noted that the specific embodiments or implementation methods described below are a series of optimized settings listed by the present invention to further explain the specific content of the invention, and these settings can be combined or used in conjunction with each other.

[0048] Example 1: like Figure 1-6 As shown in the figure, this embodiment provides a method for measuring the deformation of a building structure, which includes the following steps: Step 1: Set up the size measurement device and perform preliminary calibration, specifically including a laser rangefinder, a monocular camera, and an electric drive platform; the monocular camera is located at the center of the electric drive platform, and four laser rangefinders are located at the four corners of the electric drive platform; the laser emission direction is perpendicular to the electric drive platform and parallel to the optical axis of the monocular camera; the laser rangefinder includes an angle (e.g., pitch and rotation) motor and an angle sensor to control the laser emission angle.

[0049] Furthermore, the preliminary calibration specifically includes: The monocular camera was calibrated using Zhang Zhengyou's flat plate calibration method, and its internal and external parameters (such as focal length, pixel size, and distortion coefficient) were acquired and stored. Move the electric drive platform to the standard calibration area, calibrate the initial physical coordinates of the four laser rangefinders using a standard-size calibration plate (a building with known length and width), and record the installation offset of each laser rangefinder relative to the center of the platform. The electric drive platform is moved a preset distance along the X, Y and Z directions respectively. The laser rangefinder readings are compared with the actual distance the platform moves to establish a three-degree-of-freedom position correction model, including the current positioning coordinates of the platform, for subsequent coordinate correction. The angle motor and angle sensor are calibrated, and an angle measurement model is established, including the angle between the laser emission direction and the world coordinate system.

[0050] Furthermore, the electric drive platform includes a servo motor and / or a stepper motor and / or a linear module to enable three-dimensional movement and precise positioning of the platform.

[0051] Step 2: Move the platform of the electric drive platform, rotate the angle motor so that the laser points (spots) of each laser rangefinder are projected onto the corresponding corner points of the building facade to be measured. Collect the laser ranging data after the previous calibration as the physical coordinates of the laser points. Collect the angle between the laser emission direction and the world coordinate system through the angle sensor. At the same time, collect the building image through the monocular camera. The building image includes the laser points and the building facade.

[0052] Furthermore, the physical coordinates of the laser point belong to the world coordinate system and can be denoted as ( ). ), ( ), ( )and( ).

[0053] Step 3: After preprocessing the building image, extract the pixel coordinates of the laser points to provide a high-precision (±1 pixel) image reference for subsequent calculations.

[0054] Furthermore, step 3 specifically includes: Step 31: Obtain the candidate region mask for laser points through noise suppression, HSV color gamut conversion, mask extraction and mask morphology optimization.

[0055] Furthermore, step 31 specifically includes: Step 311: Apply a Gaussian convolution kernel of a preset size (e.g., 5x5) with the standard deviation of the Gaussian function. (Set to 1.2) The original image of the building image is smoothed to obtain a smooth image. This can effectively suppress Gaussian noise and salt-and-pepper noise by using the normal distribution characteristics and weighted averaging of adjacent pixels. Step 312: Select the original image as the guide image and perform guided filtering on the smoothed image (filter radius is 5, regularization parameter is 5). (Setting the value to 100) yields a Gaussian filtered image, such as Figure 2 As shown in Figure (a), this can eliminate high-frequency interference from building surface texture while preserving the grayscale difference between the laser point and the background, thereby ensuring that the edges of the laser point are clear and not blurry. Step 313: Convert the Gaussian-filtered image to the HSV color gamut to enhance the distinction between the laser points and the background, such as... Figure 2 As shown in Figure (b); set the V channel threshold range, for example... High-brightness areas are selected from the Gaussian-filtered image; In particular, the threshold range of the V channel can be dynamically corrected according to the mean brightness of the Gaussian filtered image ±10, so as to avoid missed detection in strong light or weak light environments. Step 314: Set the threshold range for the S channel, for example... Remove pure white background reflections (such as strong reflections on steel structure surfaces) from the Gaussian filtered image. Step 315: Perform a logical AND operation on the filtering results of the V and S channels to generate a binary mask containing only the candidate regions of laser points, thereby eliminating more than 95% of non-target pixels and significantly reducing the computational load of subsequent processing. Figure 2 As shown in Figure (c); Step 316: Perform morphological closing operation (3*3 rectangular structuring element) on the binarized mask to fill the (tiny) holes inside the laser points (caused by noise); then perform morphological opening operation (3*3 rectangular structuring element) to remove noise attached to the mask edges, and obtain a laser point candidate region mask (with complete outline and clean interior).

[0056] Step 32: Based on the laser point candidate region mask, after extracting the candidate regions, the laser point region image is determined through edge detection and contour feature filtering to avoid interference from workshop light reflections, building surface markers, etc. Figure 2 As shown in Figure (d) of the document.

[0057] Furthermore, step 32 specifically includes: Step 321: Extract the edge of the Gaussian-filtered image after the laser point candidate region masking to obtain the candidate region. Then, based on the preset dual thresholds (e.g., the low threshold is 50 and the high threshold is 150), extract the continuous edge contour of the laser point through Gaussian gradient calculation, non-maximum suppression and hysteresis thresholding to ensure that the edge is free of breakage and redundant edge. Step 322: (using the findContours function of OpenCV tool) After extracting all contours of the candidate region, set the filtering conditions based on the geometric features of the laser point (circle or approximately circle) to filter out the laser point region image.

[0058] Furthermore, the screening criteria include: Filtering criterion 1: Based on the actual size of the laser spot (the pixel area after imaging is usually between 50-200 pixels), set the area threshold range, for example... This is to eliminate excessively small noise contours and excessively large background interference areas; Filtering criterion 2: Based on roundness Calculation formula ,in, Represents the area of ​​the outline. This represents the perimeter of the outline, and sets a roundness threshold range, for example... To eliminate irregular non-circular outlines (such as rectangular markers, striped reflections, etc.); Filtering condition 3: Calculate the ratio of the minimum bounding rectangle of the contour to the area of ​​the contour, and filter out contours with a ratio ≤ a preset ratio threshold (e.g., 1.5) to further eliminate non-laser point interference.

[0059] Step 33: For the laser point area image, the center pixel coordinates are solved by fitting algorithm, and the final center pixel coordinates are obtained by multi-frame averaging optimization to improve the stability of the center pixel coordinates.

[0060] Furthermore, step 33 specifically includes: Step 331: Using the least squares method, fit a circle to the edge contour of the laser point and solve for the coordinates of the circle center. The specific calculation formula includes: ; in, Indicates the coordinates of the center of the circle; Indicates the radius of the circle; Using all pixels on the edge contour as samples, an error function is constructed. By minimizing the error function through partial derivatives, the coordinates of the circle center and the circle radius are obtained. The specific expressions include: ; in, Indicates the first edge contour The coordinates of each pixel; Specifically, if the error function exceeds the error threshold, the laser point area image is re-screened or the preprocessing parameters are optimized to ensure fitting accuracy; the error threshold is ≤0.3 pixels. Step 332: Since the building image can be multiple frames (e.g., 5 frames) taken under the same conditions, and the above steps are performed separately to obtain multiple sets of center coordinates (e.g., 5 sets), the abnormal center coordinates (i.e., center coordinates deviating from the mean by more than 2 standard deviations) from the multiple sets of center coordinates from the multiple frames are removed using the Grubbs criterion. The arithmetic mean of the remaining center coordinates is then taken to obtain the four (precise) laser point center pixel coordinates. ( ), ( ), ( )and ( ).

[0061] Step 4: Based on the physical coordinates of the laser point and the center pixel coordinates of the laser point, calculate the relative coordinates of the laser point on the object surface, solve the homography transformation matrix, perform perspective correction on the building image, obtain the orthophoto image, and obtain the conversion coefficient between the pixel and the actual distance. This eliminates the errors caused by the perspective distortion of the monocular camera and the non-ideal plane of the building surface, establishes a high-precision mapping relationship between the pixel and the actual distance, and provides a benchmark for subsequent measurements.

[0062] Furthermore, step 4 specifically includes: Step 41, as follows Figure 3 As shown, based on previous calibration data and laser ranging data, the physical coordinates of the laser point are solved through spatial geometric calculations. The specific calculation formulas include: ; ; ; in, , , Indicates the first Physical coordinates of each laser point; , , Indicates the current positioning coordinates of the platform; , Indicates the first The installation offset of the laser rangefinder relative to the center of the platform; Indicates the first Real-time laser ranging data collected by a laser rangefinder; , , This represents the angle between the laser emission direction and the world coordinate system.

[0063] Step 42: Define the local coordinate system of the object surface. Among them, the laser point in the upper left corner ( The projection point of ) is taken as the origin. , The axis runs horizontally to the right along the building facade (i.e., in relation to the world coordinate system). (axis parallel) The axis runs vertically downwards along the building facade (i.e., in relation to the world coordinate system). (axis parallel) The axis is along the normal vector direction of the building facade (which can be obtained by fitting the physical coordinates of 4 laser points); like Figure 4-5 As shown, the physical coordinates of the four laser points are projected onto the local coordinate system of the object surface. Within the plane, the relative coordinates of the laser point on the object surface are obtained and corrected. The horizontal projection error caused by axis tilt (slight tilt of the building surface) is specifically expressed as follows: First projection point The origin The relative coordinates are ; Second projection point The relative coordinate expressions include: ; ; Third projection point The relative coordinate expressions include: ; ; Fourth projection point The relative coordinate expressions include: ; .

[0064] Step 43: Solve for the homography transformation matrix. This matrix is ​​used to calculate the corresponding pixel in the image pixel coordinate system for any point in the local coordinate system of the object surface. This allows for rapid conversion between the two coordinate systems, providing a foundation for subsequent image measurement and target localization. The specific expression includes: ; in, , Indicates the relative coordinates of the laser point on the object surface; , Indicates the center pixel coordinates of the laser point; The 3x3 homography matrix is ​​expressed as follows: ; in, Represents the matrix elements (there are 9 elements in total, but due to homogeneity, the actual requirement is to solve for 8 unknown elements); The specific expressions that expand into non-homogeneous form include: ; In this way, by using the known point pairs between the relative coordinates of the laser point on the object surface and the pixel coordinates of the laser point center, a system of linear equations can be constructed, which can then be solved. (4 sets of known point pairs, construct 8 linear equations, solve for 8 unknown elements), specifically: Construct a set of relative coordinates of laser points on the object surface The specific expressions include: ; Construct the set of center pixel coordinates of the laser point The specific expressions include: ; For each pair of known points, after eliminating the scaling factor by combining the homogeneous coordinate relationship, two linear equations are obtained, for example: Depend on (By fixing the proportions using homogeneity, we simplify the calculation), substituting into the perspective transformation formula, we get: ; Rearranging it into the standard linear equation form, we get: ; Given 4 pairs of points, 8 linear equations can be constructed, forming a matrix: ; in, This represents an 8x8 coefficient matrix, which can be obtained from the coordinate values ​​of 4 known pairs of points. and Fill in the information according to the above process; This represents an 8*1 unknown vector, i.e. ; This represents an 8x1 constant vector, which can be represented by the coordinates of 4 known pairs of points. and Arranged in corresponding order; Because actual data contains minor noise (such as image recognition errors, laser point positioning errors, etc.). There is usually no perfect solution, and the optimal solution must be found by using the least squares method.

[0065] Preferably, the least squares method is specifically solved using the Singular Value Decomposition (SVD) method, and the specific steps include: Step a1, for Perform singular value decomposition to obtain ,in, This represents the first orthogonal 8x8 matrix. Represents an 8x8 diagonal matrix. Represents an 8x8 second orthogonal matrix transpose; Step a2, take Zhongyu The column vector corresponding to the smallest singular value in the equation yields the optimal solution to the linear equation, i.e. ; Step a3, Fill the 8 elements in order to In the middle; then (based on the homogeneity assumption) let =0、 =0 and =1, thus obtaining .

[0066] Step 44: Based on the homography transformation matrix, perform perspective correction on the architectural image by setting the corrected image size and inverse perspective transformation (using the OpenCV vision library). Specific expressions include: ; in, express The inverse matrix is ​​used to reverse the transformation from image to object plane into an orthophoto mapping from object plane to image, thereby eliminating perspective distortion; and They represent and Corrected coordinates; The corrected image size refers to the size of the image first... In the calculation of the maximum relative coordinates, the specific steps include: Horizontal maximum relative coordinates That is, the horizontal distribution range covering all laser points, specifically expressed as: ; Vertical maximum relative coordinates That is, the vertical distribution range covering all laser points, specifically expressed as: ; Then, based on the required measurement accuracy (e.g., 0.1 mm / pixel), the maximum relative coordinates are converted into the number of pixels, specifically including: Horizontal pixels The specific expression is: ,in, This indicates the rounding operation; Vertical pixel count The specific expression is: ; In this way, the size of the corrected image can be matched with the distribution of laser points in the local coordinate system of the object surface, ensuring complete coverage of the object surface area and reasonable pixel accuracy; In particular, if * For images smaller than 500*500 pixels, the precision requirement can be reduced (e.g., adjust from 0.1mm / pixel to 0.2mm / pixel) and then recalculated to ensure that the effective information of the image is complete and no details are lost. The inverse perspective transformation can be implemented using the `warpPerspective` function, specifically including: using the preprocessed architectural image (i.e., the Gaussian filtered image obtained in step 312) as the input image; and... As the transformation matrix; * As the output size; use the bicubic interpolation algorithm as the interpolation algorithm; call the warpPerspective function to obtain the orthographic projection image (without perspective distortion); Step 46: Calculate the conversion coefficient between pixels and actual distance. The specific expression includes: .

[0067] Preferably, step 46 specifically includes: Step 461: Calculate the average actual distance of the laser point in the horizontal direction. and average pixel distance The specific expressions include: ; ; Calculate the average actual distance of the laser point in the vertical direction and average pixel distance The specific expressions include: ; ; Step 462: Calculate the conversion coefficient between pixels and actual distance. The unit is mm / pixel, and the specific expressions include: ; Thus, given the pixel distances in each direction, it can be directly multiplied by... This method allows for the quick calculation of the actual distance, and vice versa.

[0068] Step 5: Input the preprocessed building image (i.e. the Gaussian filtered image obtained in step 312) into the pre-trained semantic segmentation model to obtain the beam segmentation mask and beam edge curve; based on the beam segmentation mask, extract the pixel coordinates of the two endpoints a and c of the beam edge curve, obtain the straight line segment ac, and calculate the pixel coordinates of the midpoint b of the straight line segment ac, thereby obtaining the precise position of the three feature points and completing the automatic recognition and feature point extraction of the beam region.

[0069] Furthermore, the specific training method of the semantic segmentation model includes: preprocessing building images of different sizes and angles, labeling the beam regions and beam edge curves, and generating pixel-level mask labels as training datasets; training the semantic segmentation model (e.g., deeplabv3 deep learning model, U-Net semantic segmentation model, and SegNet semantic segmentation model), with the preprocessed building images as input and the mask labels as output; and optimizing the model parameters through backpropagation to enable it to accurately segment beam regions and extract beam edge curves.

[0070] Step 6, as follows Figure 6 As shown, the length of straight line segment ac is calculated, and the actual span of the beam is obtained by converting it using a conversion factor; similarly, the height difference between endpoint a and midpoint b is calculated. The height difference between endpoint a and endpoint c Horizontal distance between endpoint a and midpoint b and the horizontal distance between midpoint b and endpoint c Then, calculate the deflection value. The specific formula is as follows: ; In this way, by combining the actual span and deflection values ​​with the relevant building codes for the building type, a compliance assessment can be accurately made.

[0071] Furthermore, the conversion in step 6 refers to multiplying the pixel distance of the measured straight line segment by a conversion coefficient.

[0072] Example 2: This embodiment provides a building structure deformation measurement system, including a data receiving module, a data processing module, and a result generation module; The data receiving module is used to receive laser ranging data as the physical coordinates of the laser point, the angle between the laser emission direction and the world coordinate system, and building images. The data processing module includes a preprocessing unit, a perspective correction unit, a semantic segmentation unit, and a size measurement unit. The preprocessing unit is used to preprocess the building image and extract the pixel coordinates of the laser points; The perspective correction unit calculates the relative coordinates of the laser point on the object surface based on the physical coordinates of the laser point and the center pixel coordinates of the laser point, solves the homography transformation matrix, performs perspective correction on the building image, obtains the orthographic projection image, and obtains the conversion coefficient between the pixel and the actual distance. The semantic segmentation unit is used to input the preprocessed building image into the pre-trained semantic segmentation model to obtain the beam segmentation mask and the beam edge curve; based on the beam segmentation mask, the pixel coordinates of the two endpoints a and c of the beam edge curve are extracted to obtain the straight line segment ac, and then the pixel coordinates of the midpoint b of the straight line segment ac are calculated. The dimensional measurement unit calculates the length of the straight segment ac, converts it using a conversion factor to obtain the actual span of the beam, and calculates the deflection value. ; The result generation module is used to send the results of the size measurement unit to an external source.

[0073] Example 3: This embodiment provides a building structure deformation measurement device, including a processor, a memory, and a bus. The memory stores instructions and data that can be read by the processor. The processor is used to call the instructions and data in the memory to execute the building structure deformation measurement method described above. The bus connects the various functional components for transmitting information.

[0074] Furthermore, the size measuring device also includes a laser rangefinder, a monocular camera, and an electric drive platform.

[0075] Furthermore, the laser rangefinder also includes an angle motor and an angle sensor.

[0076] In another embodiment, this solution can also be implemented using an integrated device, which may include corresponding modules that perform one or more steps in the various embodiments described above. A module may be one or more hardware modules specifically configured to perform the corresponding step, or implemented by a processor configured to perform the corresponding step, or stored in a computer-readable medium for implementation by a processor, or implemented through some combination thereof.

[0077] The processor executes the various methods and processes described above. For example, the method implementations in this scheme can be implemented as software programs tangibly contained in a machine-readable medium, such as memory. In some implementations, part or all of the software program can be loaded and / or installed via memory and / or a communication interface. When the software program is loaded into memory and executed by the processor, one or more steps of the methods described above can be performed. Alternatively, in other implementations, the processor can be configured to execute one of the methods described above by any other suitable means (e.g., by means of firmware).

[0078] This device can be implemented using a bus architecture. A bus architecture can include any number of interconnect buses and bridges, depending on the specific application of the hardware and overall design constraints. The bus connects various circuits, including one or more processors, memory, and / or hardware modules. The bus can also connect various other circuits such as peripherals, voltage regulators, power management circuitry, external antennas, etc.

[0079] Buses can be Industry Standard Architecture (ISA) buses, Peripheral Component Interconnect (PCI) buses, or Extended Industry Standard Component (EISA) buses, etc. Buses can be divided into address buses, data buses, control buses, etc.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method of measuring deformation of a building structure, characterized by, The application relates to a method for measuring the size of a building facade, comprising the following steps:

1. setting up a size measuring device and performing preliminary calibration, specifically including a laser range finder, a monocular camera and an electrically-driven platform; the monocular camera is located at the center of the platform table of the electrically-driven platform, and four laser range finders are located at the four corners of the platform table of the electrically-driven platform; the laser emission direction is perpendicular to the platform table of the electrically-driven platform and parallel to the optical axis of the monocular camera; the laser range finder comprises an angle motor and an angle sensor, which are used for controlling the laser emission angle; 2. moving the platform table of the electrically-driven platform, rotating the angle motor, and collecting the laser ranging data after the laser points of the laser range finders are projected onto the corresponding corner points of the building facade to be measured, as the physical coordinates of the laser points; the angle between the laser emission direction and the world coordinate system is collected through the angle sensor, and the building image is collected through the monocular camera; 3. after the building image is pretreated, the pixel coordinates of the laser points are extracted; 4. after the relative coordinates of the laser points on the object surface are calculated based on the physical coordinates of the laser points and the pixel coordinates of the laser point centers, the homographic transformation matrix is solved, the building image is perspective-corrected, the orthographic projection image is obtained, and the conversion coefficient between the pixel and the actual distance is obtained; 5. the pretreated building image is input into a pre-trained semantic segmentation model to obtain a beam segmentation mask and a beam edge curve; based on the beam segmentation mask, the pixel coordinates of the two end points a and c of the beam edge curve are extracted to obtain a straight line segment ac, and the pixel coordinates of the midpoint b of the straight line segment ac are calculated; the preliminary calibration specifically comprises the following steps:

1. calibrating the monocular camera through Zhang Zhengyou's plane calibration method to obtain and store the internal and external parameters; 2. moving the platform table of the electrically-driven platform to a standard calibration area, calibrating the initial physical coordinates of the four laser range finders through a standard size calibration plate, and recording the installation offset of each laser range finder relative to the center of the platform table; 3. moving the platform table of the electrically-driven platform along the X direction, the Y direction and the Z direction by a preset distance respectively, comparing the readings of the laser range finders with the actual moving distance of the platform table, and establishing a three-degree-of-freedom position correction model, including the current positioning coordinates of the platform table; 4. calibrating the angle motor and the angle sensor to establish an angle measurement model, including the angle between the laser emission direction and the world coordinate system. The step 3 specifically comprises the following steps:

1. obtaining a laser point candidate region mask through noise suppression, HSV color domain conversion, mask extraction and mask morphology optimization; 2. extracting a candidate region based on the laser point candidate region mask, determining a laser point region image through edge detection and contour feature screening; 3. solving the center pixel coordinates of the laser point region image through a fitting algorithm, and obtaining the final center pixel coordinates through multi-frame average optimization. The step 31 specifically comprises the following steps:

1. smoothing the original image of the building image through a preset size of Gaussian convolution kernel to obtain a smoothed image; 2. selecting the original image as a guide image, performing guided filtering on the smoothed image to obtain a Gaussian filter image; 3. converting the Gaussian filter image to the HSV color domain, setting the V channel threshold range, and screening out a high-luminance region from the Gaussian filter image. ​ ​ ​ Step 6, calculate the length of the straight line segment ac, and convert it to the actual span of the beam body through the conversion coefficient; similarly, convert the height difference between the end point a and the midpoint b , the height difference between the end point a and the end point c , the horizontal distance between the end point a and the midpoint b , and the horizontal distance between the midpoint b and the end point c Then, calculate the deflection value The specific formula is: 。 2. The measurement method according to claim 1, characterized in that, ​ ​ ​ ​ ​ 3. The measurement method according to claim 1, characterized in that, ​ ​ ​ ​ 4. The measurement method according to claim 3, characterized in that, ​ ​ ​ ​ Step 314, set the S channel threshold range, and eliminate the pure white background reflection points in the Gaussian filter image; Step 315, perform logical AND operation on the screening results of the V channel and the S channel to generate a binary mask containing only the laser point candidate region; Step 316, perform morphological closing operation on the binary mask to fill the holes inside the laser point, and then perform morphological opening operation to remove the noise attached to the edge of the mask, to obtain the laser point candidate region mask.

5. The measurement method according to claim 4, characterized in that, The step 32 specifically comprises: Step 321, edge extraction is performed on the Gaussian filter image processed by the laser point candidate region mask to obtain a candidate region, and then based on a preset double threshold, the continuous edge contour of the laser point is extracted through Gaussian gradient calculation, non-maximum suppression and lag threshold processing; Step 322, after extracting all the contours of the candidate region, the laser point region image is screened out based on the geometric features of the laser point.

6. The measurement method according to claim 5, characterized in that, The screening conditions comprise: Screening condition 1, setting an area threshold range according to the actual size of the laser point; Screening Condition 2, based on circularity The formula for calculating circularity wherein, A represents the profile area, L represents the profile perimeter, and a threshold range of circularity is set; Screening condition 3, calculating the ratio of the minimum circumscribed rectangle of the contour to the contour area, and screening out the contour with a ratio ≤ a preset proportion threshold.

7. The measurement method according to claim 3, characterized by, The step 33 specifically comprises: Step 331, circular fitting is performed on the edge contour of the laser point by the least square method to solve the coordinates of the center of the circle, and the specific calculation formula comprises: ； wherein denotes the center coordinate of the circle; denotes the radius of the circle; With all the pixel points on the edge contour as samples, an error function is constructed, and the error function is minimized by taking partial derivatives to obtain the coordinates of the circle center and the circle radius; the specific expression of the error function includes: ； in, Indicates the first edge contour The coordinates of each pixel; Step 332, the building image is a plurality of images under the same shooting condition, and the above steps are executed respectively to obtain a plurality of groups of center coordinates, the abnormal center coordinates in the plurality of groups of center coordinates derived from the plurality of images are removed through the Grubbs criterion, and the arithmetic mean of the remaining center coordinates is taken to obtain four laser point center pixel coordinates, i.e. ( ), ( ), ( ), and ( ).

8. The measurement method according to claim 2, characterized by, The step 4 specifically comprises: Step 41, based on the previous calibration data and the laser ranging data, the physical coordinates of the laser point are solved by spatial geometric operation, and the specific calculation formula comprises: ； ； ； in, , , Indicates the first Physical coordinates of each laser point; , , Indicates the current positioning coordinates of the platform; , Indicates the first The installation offset of the laser rangefinder relative to the center of the platform; Indicates the first Real-time laser ranging data collected by a laser rangefinder; , , Indicates the angle between the laser emission direction and the world coordinate system; Step 42, define the local coordinate system of the object surface ; wherein the projection point of the upper left corner laser point is taken as the origin , The axis is horizontal to the right along the building facade; The axis is vertical downward along the building facade; The axis is along the normal vector direction of the building facade; The four laser points are projected to the local coordinate system of the object plane The relative coordinates of the laser points on the object plane are obtained, and the horizontal projection error caused by the axis tilt is corrected The specific expression includes: First projection point , i.e. the origin , the relative coordinates are ; Second projection point The relative coordinate expression of the second projection point includes: ； ； Third projection point The relative coordinate expression of the third projection point includes: ； ； Fourth projection point The relative coordinate expression of the fourth projection point includes: ； ； Step 43, solving the homography transformation matrix, and the specific expression comprises: ； wherein, , represents the relative coordinates of the laser point on the object plane; , represents the center pixel coordinates of the laser point; represents a 3*3 homography matrix; Step 44, based on the homography transformation matrix, the perspective correction of the building image is performed by setting the correction image size and inverse perspective transformation, and the specific expression comprises: ； wherein denotes the inverse matrix of and denotes and corrected coordinates; The correction image size refers to first correcting the image size in the image to be processed In the method, the maximum relative coordinate is calculated, specifically including: horizontal maximum relative coordinate , and the specific expression is: ; vertical maximum relative coordinate , and the specific expression is: ; According to the measurement accuracy requirement, the maximum relative coordinate is converted into the number of pixels, which specifically comprises: Horizontal pixel number The specific expression is: wherein, represents a rounding operation. Vertical pixel number , and the specific expression is: ; Step 46, calculating the conversion coefficient between the pixel and the actual distance, and the specific expression comprises: 。 9. A building structure deformation measurement system employing the measurement method according to any one of claims 1 to 8, characterized by It comprises a data receiving module, a data processing module and a result generating module; The data receiving module is used for receiving the laser ranging data as the physical coordinates of the laser point, the angle between the laser emission direction and the world coordinate system, and the building image; The data processing module comprises a preprocessing unit, a perspective correction unit, a semantic segmentation unit and a size measurement unit; The preprocessing unit is used for preprocessing the building image and extracting the pixel coordinates of the laser point; The perspective correction unit calculates the relative coordinates of the object surface laser point based on the physical coordinates of the laser point and the pixel coordinates of the laser point center, solves the homography transformation matrix, performs perspective correction on the building image, obtains the orthographic projection image and obtains the conversion coefficient between the pixel and the actual distance; The semantic segmentation unit is used for inputting the preprocessed building image into a pre-trained semantic segmentation model to obtain a beam body segmentation mask and a beam body edge curve; based on the beam body segmentation mask, the pixel coordinates of the two end points a and c of the beam body edge curve are extracted to obtain a straight line segment ac, and the pixel coordinates of the midpoint b of the straight line segment ac are calculated; The size measurement unit calculates the length of the straight line segment ac, and converts the actual span of the beam body through the conversion coefficient. calculating the deflection value ; The result generating module is configured to send the result of the size measuring unit.

10. A building structure deformation measuring device characterized by comprising: The system comprises a processor, a memory and a bus, the memory stores instructions and data read by the processor, the processor is configured to call the instructions and data in the memory to execute the measurement method as claimed in any one of claims 1-8, and the bus is connected between each functional component for transmitting information.

Images