Long-term monitoring method, device, system and medium for structural displacement
By acquiring on-site slope temperature and images, and combining displacement correction models and sliding machine learning, the problem of data drift caused by temperature changes was solved, enabling high-precision, real-time, and low-cost long-term monitoring of slope displacement.
Patent Information
- Application Number
- CN202310998862.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-09
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2043-08-09
AI Technical Summary
Slope displacement monitoring systems based on video images suffer from data drift due to temperature changes during long-term monitoring, leading to inaccurate and unreliable measurement data.
By acquiring on-site temperature and images, identifying the target points to be measured and fixed points, and using an image-based displacement measurement algorithm to calculate the measured displacement, the displacement is corrected using a pre-acquired displacement correction model and a sliding machine learning model, and the model parameters are dynamically adjusted to correct the displacement data.
It enables high-precision, real-time, and low-cost long-term monitoring of slope displacement, avoiding data drift problems and improving the accuracy and reliability of monitoring.
Smart Images

Figure CN116952144B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of slope displacement monitoring, and in particular to a method, device, system and medium for long-term monitoring of structural displacement. Background Art
[0002] At present, the monitoring of slope displacement has gradually developed from the traditional contact measurement method to non-contact intelligent equipment that can be installed at any location. Intelligent equipment includes global positioning system (GPS), laser radar (LiDAR), video image-based system, etc.
[0003] The displacement measurement system based on video images has been widely used in short-term displacement measurement experiments due to its significant advantages such as easy installation, no need for manual intervention, and low cost. In particular, the measurement system based on the digital image correlation (DIC) method has the significant advantages of high precision and multi-target real-time measurement, and has shown obvious advantages in structural displacement measurement. However, when this technology is used for long-term displacement monitoring of slopes, serious displacement data drift will occur. Since the temperature in the outdoor environment will change significantly over time, the temperature change causes the camera sensor to expand and contract, and the change in imaging state causes data drift, making the measurement data inaccurate and unreliable. Summary of the invention
[0004] In order to solve the above technical problems, the embodiments of the present application provide a method, device, system and medium for long-term monitoring of structural displacement.
[0005] In a first aspect, an embodiment of the present application provides a method for long-term monitoring of structural displacement, the method comprising:
[0006] Acquire the temperature of the scene to be measured and the scene image, and identify multiple target points to be measured and multiple fixed target points in the scene image;
[0007] Using an image-based displacement measurement algorithm to calculate the on-site image, to obtain the measured displacement of each of the target points to be measured and the measured displacement of each of the fixed target points;
[0008] Obtaining a first correction displacement of each of the fixed target points by calculating through a pre-acquired first displacement correction model based on the temperature and the measured displacement of each of the fixed target points;
[0009] If the first corrected displacement of each of the fixed target points is a true displacement indicator, the actual displacement of each of the target points to be measured is obtained by calculating the first displacement correction model based on the temperature and the measured displacement of each of the target points to be measured.
[0010] In one embodiment, the method further comprises:
[0011] If the corrected displacement of each of the fixed target points is not the true displacement index, obtaining a second displacement correction model according to the temperature, the measured displacement of each of the fixed target points and the true displacement;
[0012] Obtaining a second corrected displacement of each of the fixed target points based on the temperature and the measured displacement of each of the fixed target points by using the second displacement correction model;
[0013] If the second corrected displacement of each of the fixed target points is the true displacement index, the actual displacement of each of the target points to be measured is obtained by using the second displacement correction model based on the temperature and the measured displacement of each of the target points to be measured.
[0014] In one embodiment, the scene image includes a previous image and a current image before and after deformation, and the image-based displacement measurement algorithm is used to calculate the scene image to obtain the measured displacement of each of the target points to be measured and the measured displacement of each of the fixed target points, including:
[0015] Iteratively calculating the previous image and the current image using an image-based displacement measurement algorithm to obtain an image displacement between the previous image and the current image;
[0016] The measured displacement of each of the target points to be measured and the measured displacement of each of the fixed target points are calculated according to the image displacement.
[0017] In one embodiment, the step of calculating the measured displacement of each of the target points to be measured and the measured displacement of each of the fixed target points according to the image displacement includes:
[0018] The image displacement is converted into the measured displacement of each of the target points to be measured and the measured displacement of each of the fixed target points according to the oblique optical axis pinhole imaging model.
[0019] In one embodiment, the method further comprises:
[0020] Setting a plurality of target points to be measured and a plurality of fixed target points at the site to be measured;
[0021] The real displacement index is set for each of the fixed target points.
[0022] In one embodiment, the method further comprises:
[0023] Setting up video camera monitoring equipment and temperature sensors at the site to be tested;
[0024] The on-site image is collected by the video camera monitoring device and the temperature is collected by the temperature sensor.
[0025] In a second aspect, an embodiment of the present application provides a long-term monitoring device for structural displacement, the long-term monitoring device for structural displacement comprising:
[0026] An acquisition module, used to acquire the temperature of the scene to be measured and the scene image, and identify multiple target points to be measured and multiple fixed target points in the scene image;
[0027] A first calculation module, used to calculate the scene image using an image-based displacement measurement algorithm to obtain a measured displacement of each of the target points to be measured and a measured displacement of each of the fixed target points;
[0028] A second calculation module is used to calculate based on the temperature and the measured displacement of each of the fixed target points by using a pre-acquired first displacement correction model to obtain a first correction displacement of each of the fixed target points;
[0029] The third calculation module is used to calculate the actual displacement of each target point to be measured by using the first displacement correction model based on the temperature and the measured displacement of each target point to be measured if the first corrected displacement of each fixed target point is a true displacement indicator.
[0030] In one embodiment, the device further comprises:
[0031] a processing module, configured to obtain a second displacement correction model according to the temperature, the measured displacement and the true displacement of each of the fixed target points if the corrected displacement of each of the fixed target points is not the true displacement index;
[0032] Obtaining a second corrected displacement of each of the fixed target points based on the temperature and the measured displacement of each of the fixed target points by using the second displacement correction model;
[0033] If the second corrected displacement of each of the fixed target points is the true displacement index, the actual displacement of each of the target points to be measured is obtained by using the second displacement correction model based on the temperature and the measured displacement of each of the target points to be measured.
[0034] In a third aspect, an embodiment of the present application provides a long-term monitoring system for structural displacement, comprising a memory and a processor, wherein the memory is used to store a computer program, and when the computer program is run by the processor, the long-term monitoring method for structural displacement provided in the first aspect is executed.
[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when executed on a processor, executes the method for long-term monitoring of structural displacement provided in the first aspect.
[0036] The method for long-term monitoring of structural displacement provided by the present application obtains the temperature and the site image of the site to be measured, identifies multiple target points to be measured and multiple fixed target points in the site image; uses an image-based displacement measurement algorithm to calculate the site image to obtain the measured displacement of each target point to be measured and the measured displacement of each fixed target point; calculates based on the temperature and the measured displacement of each fixed target point using a pre-acquired first displacement correction model to obtain a first corrected displacement of each fixed target point; if the first corrected displacement of each fixed target point is a true displacement indicator, calculates based on the temperature and the measured displacement of each target point to be measured using the first displacement correction model to obtain the actual displacement of each target point to be measured, thereby realizing high-precision, real-time, low-cost, and easy-to-promote long-term monitoring of slope displacement. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present application and should not be regarded as limiting the scope of protection of the present application. In each of the drawings, similar components are numbered similarly.
[0038] Figure 1 A schematic diagram of a process of a method for long-term monitoring of structural displacement provided by an embodiment of the present application is shown;
[0039] Figure 2 A schematic diagram of the structure of a structural displacement monitoring system provided by an embodiment of the present application is shown;
[0040] Figure 3 A schematic diagram of a calculation process of image displacement provided by an embodiment of the present application is shown;
[0041] Figure 4 A three-dimensional schematic diagram of a pinhole imaging model provided in an embodiment of the present application is shown;
[0042] Figure 5 A schematic diagram of a mathematical model of a pinhole imaging model provided in an embodiment of the present application is shown;
[0043] Figure 6 Another schematic diagram of the process of the long-term monitoring method of structural displacement provided by an embodiment of the present application is shown;
[0044] Figure 7 A schematic structural diagram of a long-term monitoring device for structural displacement provided in an embodiment of the present application is shown.
[0045] Icons: 1- video camera monitoring equipment; 2- temperature sensor; 3- bracket; 4- slope; 5- target point to be measured; 6- fixed target point; 600- long-term monitoring device for structural displacement; 601- acquisition module; 602- first calculation module; 603- second calculation module; 604- third calculation module. DETAILED DESCRIPTION
[0046] The technical solution in the present application will be clearly and completely described below in conjunction with the drawings in the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments.
[0047] The components of the present application generally described and shown in the drawings herein may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.
[0048] Hereinafter, the terms "including", "having" and their cognates, which may be used in various embodiments of the present application, are intended only to indicate specific features, numbers, steps, operations, elements, components, or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing items or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations of the foregoing items.
[0049] Furthermore, the terms “first”, “second”, “third”, etc. are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.
[0050] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present application.
[0051] Example 1
[0052] The present application provides a method for long-term monitoring of structural displacement.
[0053] For details, see Figure 1 , long-term monitoring methods for structural displacement include:
[0054] Step S101, obtaining the temperature of a site to be measured and a site image, and identifying a plurality of target points to be measured and a plurality of fixed target points in the site image.
[0055] It should be noted that in order to solve the data drift phenomenon caused by temperature changes when the displacement measurement technology based on video images is used for long-term monitoring, the long-term monitoring method of structural displacement provided in this embodiment can be applied to Figure 2 The structural displacement long-term monitoring system shown in the figure includes a video camera monitoring device 1, a temperature sensor 2, and a bracket 3. In addition, during use, it can also include a slope structure 4 at the site to be measured, a target point to be measured 5, and a fixed target point 6. The sliding machine learning model combining temperature data and an image-based displacement measurement algorithm (DIC) is used to correct the displacement data, thereby realizing high-precision, low-cost, and easy-to-install long-term monitoring of structural displacement.
[0056] In one embodiment, the method further comprises:
[0057] Setting a plurality of target points to be measured and a plurality of fixed target points at the site to be measured;
[0058] The real displacement index is set for each of the fixed target points.
[0059] See also Figure 2 The video camera monitoring device 1 is fixed by a bracket 3, the temperature sensor 2 is fixed by the bracket 3, the bracket 3 is set at the site to be tested, and the site to be tested is a slope structure 4, and the slope structure 4 can be a large slope structure. Exemplarily, a plurality of target points 5 to be tested and a plurality of fixed target points 6 are set on the slope structure 4. The video camera monitoring device 1 can be calibrated, and after collecting the scene image, the target points to be tested and the fixed target points are identified in the scene image. The real displacement index can be set to 0.
[0060] In one embodiment, the method further comprises:
[0061] Setting up video camera monitoring equipment and temperature sensors at the site to be tested;
[0062] The on-site image is collected by the video camera monitoring device and the temperature is collected by the temperature sensor.
[0063] See also Figure 2 , synchronously collecting the on-site image of the scene to be measured through the video camera monitoring device 1 and collecting the temperature of the scene to be measured through the temperature sensor 2.
[0064] Step S102: using an image-based displacement measurement algorithm to calculate the on-site image, to obtain the measured displacement of each of the target points to be measured and the measured displacement of each of the fixed target points.
[0065] In this embodiment, the image displacement of the target point to be measured is calculated using a DIC algorithm that is accurate to sub-pixels. The DIC algorithm iteratively calculates the correlation coefficient of the image of the target point to be measured before and after deformation to calculate its image displacement (in pixels). In order to obtain the real displacement (in millimeters), it is also necessary to convert the image displacement and the actual displacement for each target point to be measured according to the oblique optical axis pinhole imaging model.
[0066] It should be noted that during long-term monitoring, the temperature changes over a wide range. Studies have shown that temperature changes can cause changes in the physical state of cameras and other imaging devices, thereby causing displacement data calculated from images taken by the imaging device to drift. During long-term monitoring, the scene image can be a continuous multi-frame video image. Specifically, the scene image includes the previous image and the current image before and after deformation. Step S102 includes:
[0067] Iteratively calculating the previous image and the current image using an image-based displacement measurement algorithm to obtain an image displacement between the previous image and the current image;
[0068] The measured displacement of each of the target points to be measured and the measured displacement of each of the fixed target points are calculated according to the image displacement.
[0069] In this way, a relatively accurate measured displacement can be calculated through the image displacement measurement algorithm.
[0070] Exemplarily, the image displacement is obtained using a digital image correlation (DIC) algorithm, which obtains the displacement of each target point to be measured by matching the corresponding image sub-areas in the image before and after deformation. Figure 3 Explain the principle.
[0071] The target point to be measured in the reference image centered Reference sub-area, reference sub-area can be used Indicates that, according to the principle of maximum correlation, a specific search algorithm is used to find the target point to be measured in the deformed image A target sub-region with the center as the center. The target sub-region can be Thus, the following displacement vector can be derived: The calculation formula is: , so that the target point to be measured can be determined and Displacement component in the direction .
[0072] In this way, the image displacement can be quickly calculated using an image-based displacement measurement algorithm.
[0073] In one embodiment, the step of calculating the measured displacement of each of the target points to be measured and the measured displacement of each of the fixed target points according to the image displacement includes:
[0074] The image displacement is converted into the measured displacement of each of the target points to be measured and the measured displacement of each of the fixed target points according to the oblique optical axis pinhole imaging model.
[0075] When monitoring deformation of large structures, it is difficult or impossible to make the optical axis of the camera perpendicular to the surface of the measured structure due to the limitations of the instrument installation position. Although the roll angle of the camera rotating around the optical axis can be easily adjusted to zero, there is still a pitch angle between the optical axis of the camera and the horizontal plane. In this case, due to the different distances from each measurement point to the optical center of the camera, the calibration coefficient (scale factor) of each target point to be measured is no longer a constant. Therefore, a suitable calibration model is required to determine the scale factor, which is used to determine the conversion relationship between the image displacement and the actual physical displacement of each target point to be measured. According to the pinhole imaging principle, the imaging model for determining the oblique optical axis is as follows: Figure 4 shown.
[0076] See also Figure 5 ,based on Figure 5 A mathematical model can be established. According to the triangle similarity principle, the calibration formula for converting the image displacement v to the actual measured displacement V can be:
[0077]
[0078] In the formula is the object distance from the measured point to the optical center of the camera, and the focal length of the camera is , the unit pixel size of the camera target surface is , are the coordinates of the image center, is the angle between the camera and the horizontal plane. Since half the height of the camera target surface is farther than the camera focal length, in actual measurement, It can be regarded as 90°. The oblique optical axis pinhole imaging model can represent the geometric relationship between the camera plane and the measured plane, from which the mathematical relationship between the image displacement and the actual displacement can be derived. Indicates the actual measured displacement, Indicates image displacement. The measured point can be the target point to be measured and the fixed target point in this embodiment.
[0079] In this way, the measured displacement of the target point to be measured and the measured displacement of the fixed target point are obtained based on the oblique optical axis pinhole imaging model and the rapid conversion of the image displacement.
[0080] Step S103 , calculating based on the temperature and the measured displacement of each of the fixed target points using a pre-acquired first displacement correction model to obtain a first correction displacement of each of the fixed target points.
[0081] Step S104: if the first corrected displacement of each of the fixed target points is a true displacement indicator, the actual displacement of each of the target points to be measured is obtained by calculating the first displacement correction model based on the temperature and the measured displacement of each of the target points to be measured.
[0082] In this embodiment, due to the significant change in ambient temperature, data drift occurs during the long-term monitoring of structural displacement. To address this problem, a solution is proposed to correct displacement data using a sliding machine learning model. The sliding machine learning model can be understood as a dynamically adjusted displacement calibration model. Demonstrationally, several fixed target points with a true displacement index of zero are set near the target point to be measured. Image and temperature data are collected in real time, and the measured displacements of the target point to be measured and the fixed target point are calculated using an image-based displacement measurement algorithm. Machine learning modeling is performed using the true displacement, measured displacement and temperature of the fixed target point, and the displacement of the target point to be measured is corrected using the model. During the acquisition process, the displacement of the fixed target point is first corrected using an existing model. If the displacement of the fixed target point after correction is zero, that is, the model is valid, and the displacement of the target point to be measured is corrected using the model. If the displacement of the fixed target point after correction is not zero, that is, the model is invalid, the sliding update model is remodeled using the parameters of the fixed target point, and the target point to be measured is corrected again. This process is repeated until the measurement is completed.
[0083] In one embodiment, the method further comprises:
[0084] If the corrected displacement of each of the fixed target points is not the true displacement index, obtaining a second displacement correction model according to the temperature, the measured displacement of each of the fixed target points and the true displacement;
[0085] Obtaining a second corrected displacement of each of the fixed target points based on the temperature and the measured displacement of each of the fixed target points by using the second displacement correction model;
[0086] If the second corrected displacement of each of the fixed target points is the true displacement index, the actual displacement of each of the target points to be measured is obtained by using the second displacement correction model based on the temperature and the measured displacement of each of the target points to be measured.
[0087] In this embodiment, if the second corrected displacement of each of the fixed target points is not the real displacement index, the next scene image is continuously acquired to perform the next round of displacement correction process of the target points to be measured.
[0088] See also Figure 6 , after first acquiring the scene image, obtain temperature data , calculate the measured displacement of each fixed target point 6 and the measured displacement of the target point 5 Based on the measurement results of the fixed target point 6, learn to calculate the mathematical relationship between the real displacement of the fixed target point and various parameters ,use Correct the displacement of the target point 5 to be measured. For example, the real displacement of the fixed target point 6 is known. v i , i=1 , 2 , ... , n , the measured displacement of the fixed target point 6 V i , i=1 , 2 , ... , n ,temperature c i , i=1 , 2 , ... , n , and obtain the first displacement correction model:
[0089]
[0090] After collecting the second image and calculating the measured displacements of the target points 5 and the fixed target points 6, first use Correct the first correction displacement of the fixed target point. For example, the first correction displacement of the fixed target point is expressed as ,judge Is equal to 0, if the first correction displacement is zero (the real displacement index of the fixed target point is zero), indicating If effective, use Correct the real displacement of the target point to be measured in the second image:
[0091] , is the actual displacement of the target point to be measured.
[0092] If the displacement of the fixed target point after correction is not zero, it means If the measured displacement of the fixed target point in the second image, the corresponding temperature, and the real displacement of the fixed target point 6 are used, for example, if the measured displacement of each fixed target point in the second image is V j , j=1 , 2 , ... , m ,temperature c j , j=1 , 2 , ... , m, then the real displacement of the fixed target point is v j =f 2 (V j , c j ) , j=1 , 2 , ... , m, re-learn a new second displacement correction model :
[0093]
[0094] Determine the true displacement of a fixed target point Is it established? If established, use Correct the second correction displacement of the target point to be measured in the second image:
[0095] , is the actual displacement of the target point to be measured.
[0096] This process is repeated until the measurement is completed.
[0097] This correction method breaks the traditional idea of fixed sample library. According to the correction effect of the model on the fixed target point, it is judged whether the model and sample library are invalid. The sliding update model can realize high-precision long-term monitoring of structural displacement. The universal mathematical model is as follows:
[0098]
[0099] in, Indicates the real displacement of the target point 5 to be measured; represents the measured displacement of the fixed target point 6, i=1 , 2 , ... , n ; Represents temperature data, i=1 , 2 , ... , n The mathematical model is used to correct the displacement of the target point to be measured. First, a series of displacement data of the fixed target point 6 are measured. And the corresponding temperature data , through an appropriate function , and obtain the correction model. This correction model can convert the measured displacement of the fixed target point 6 and temperature Mapped to its true displacement Next, the displacement of the target point 5 to be measured is corrected using this correction model, that is, the real displacement of the target point to be measured is calculated. .
[0100] This universal mathematical model can be applied to different structural displacement measurement scenarios. It only requires selecting the appropriate correction function according to the specific situation. By continuously updating and optimizing the correction model, combined with the sliding update method, high-precision long-term monitoring of structural displacement can be achieved, and the failure problem of the traditional fixed sample library can be avoided.
[0101] The long-term monitoring method for structural displacement is applied to the long-term monitoring system for structural displacement provided in this embodiment to achieve high-precision, real-time, low-cost, and easy-to-promote long-term monitoring of slope displacement.
[0102] The method for long-term monitoring of structural displacement provided in the present embodiment obtains the temperature and the site image of the site to be measured, identifies multiple target points to be measured and multiple fixed target points in the site image; uses an image-based displacement measurement algorithm to calculate the site image to obtain the measured displacement of each target point to be measured and the measured displacement of each fixed target point; uses a pre-acquired first displacement correction model to calculate based on the temperature and the measured displacement of each fixed target point to obtain a first corrected displacement of each fixed target point; if the first corrected displacement of each fixed target point is a true displacement indicator, uses the first displacement correction model to calculate based on the temperature and the measured displacement of each target point to be measured to obtain the actual displacement of each target point to be measured, thereby realizing high-precision, real-time, low-cost, and easy-to-promote long-term monitoring of slope displacement.
[0103] Example 2
[0104] In addition, the present application provides a long-term monitoring device for structural displacement.
[0105] like Figure 7 As shown, the long-term monitoring device 600 for structural displacement includes:
[0106] An acquisition module 601 is used to acquire the temperature of the scene to be measured and the scene image, and identify multiple target points to be measured and multiple fixed target points in the scene image;
[0107] A first calculation module 602 is used to calculate the scene image using an image-based displacement measurement algorithm to obtain a measured displacement of each of the target points to be measured and a measured displacement of each of the fixed target points;
[0108] A second calculation module 603 is used to calculate based on the temperature and the measured displacement of each of the fixed target points by using a pre-acquired first displacement correction model to obtain a first correction displacement of each of the fixed target points;
[0109] The third calculation module 604 is used to calculate the actual displacement of each target point to be measured by using the first displacement correction model based on the temperature and the measured displacement of each target point to be measured if the first corrected displacement of each fixed target point is a true displacement indicator.
[0110] In one embodiment, the long-term structural displacement monitoring device 600 further includes:
[0111] a processing module, configured to obtain a second displacement correction model according to the temperature, the measured displacement and the true displacement of each of the fixed target points if the corrected displacement of each of the fixed target points is not the true displacement index;
[0112] Obtaining a second corrected displacement of each of the fixed target points based on the temperature and the measured displacement of each of the fixed target points by using the second displacement correction model;
[0113] If the second corrected displacement of each of the fixed target points is the true displacement index, the actual displacement of each of the target points to be measured is obtained by using the second displacement correction model based on the temperature and the measured displacement of each of the target points to be measured.
[0114] In one embodiment, the scene image includes a previous image and a current image before and after deformation, and the first calculation module 602 is further used to iteratively calculate the previous image and the current image using an image-based displacement measurement algorithm to obtain an image displacement between the previous image and the current image;
[0115] The measured displacement of each of the target points to be measured and the measured displacement of each of the fixed target points are calculated according to the image displacement.
[0116] In one implementation, the first calculation module 602 is further configured to convert the image displacement into a measured displacement of each of the target points to be measured and a measured displacement of each of the fixed target points according to an oblique optical axis pinhole imaging model.
[0117] The long-term structural displacement monitoring device 600 provided in this embodiment can implement the long-term structural displacement monitoring method provided in Embodiment 1, and will not be described again here to avoid repetition.
[0118] The long-term monitoring device for structural displacement provided in the present embodiment obtains the temperature and the on-site image of the on-site to be measured, identifies a plurality of target points to be measured and a plurality of fixed target points in the on-site image; calculates the on-site image using an image-based displacement measurement algorithm to obtain the measured displacement of each of the target points to be measured and the measured displacement of each of the fixed target points; calculates based on the temperature and the measured displacement of each of the fixed target points using a pre-acquired first displacement correction model to obtain a first corrected displacement of each of the fixed target points; if the first corrected displacement of each of the fixed target points is a true displacement indicator, calculates based on the temperature and the measured displacement of each of the target points to be measured using the first displacement correction model to obtain the actual displacement of each of the target points to be measured, thereby realizing high-precision, real-time, low-cost, and easy-to-promote long-term monitoring of slope displacement.
[0119] Example 3
[0120] In addition, the present application provides a long-term monitoring system for structural displacement, including a video camera monitoring device and a temperature sensor, the video camera monitoring device including a memory and a processor, the memory storing a computer program, and the computer program executing the long-term monitoring method for structural displacement described in Example 1.
[0121] The long-term structural displacement monitoring system provided in this embodiment can implement the long-term structural displacement monitoring method provided in Example 1, and will not be described again here to avoid repetition.
[0122] Example 4
[0123] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for long-term monitoring of structural displacement provided in Example 1 is implemented.
[0124] In this embodiment, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
[0125] The computer-readable storage medium provided in this embodiment can implement the long-term monitoring method of structural displacement provided in Example 1, and will not be described again here to avoid repetition.
[0126] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or terminal including the element.
[0127] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.
[0128] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.
Claims
1. A method for long-term monitoring of structural displacement, characterized in that: The invention is applied to a long-term monitoring system for structural displacement, which comprises: a video camera monitoring device, a temperature sensor and a bracket, wherein the bracket is arranged at a site to be measured, and the site to be measured is a slope structure, wherein the video camera monitoring device and the temperature sensor are respectively fixed by the bracket, and a plurality of target points to be measured and a plurality of fixed target points are arranged at the slope structure, and the method comprises: The video camera monitoring device collects a scene image of the scene to be measured and the temperature of the scene to be measured is collected by the temperature sensor, and a plurality of target points to be measured and a plurality of fixed target points in the scene image are identified; Using an image-based displacement measurement algorithm to calculate the on-site image, to obtain the measured displacement of each of the target points to be measured and the measured displacement of each of the fixed target points; Obtaining a first correction displacement of each of the fixed target points by calculating based on the temperature and the measured displacement of each of the fixed target points using a first displacement correction model pre-acquired based on the first image; If the first corrected displacement of each of the fixed target points is a true displacement indicator, the actual displacement of each of the target points to be measured is obtained by calculating the first displacement correction model based on the temperature and the measured displacement of each of the target points to be measured; If the corrected displacement of each of the fixed target points is not the true displacement index, obtaining a second displacement correction model according to the temperature corresponding to the second image, the measured displacement of each of the fixed target points and the true displacement; Obtaining a second corrected displacement of each of the fixed target points based on the temperature and the measured displacement of each of the fixed target points by using the second displacement correction model; If the second corrected displacement of each of the fixed target points is the true displacement index, the actual displacement of each of the target points to be measured is obtained by using the second displacement correction model based on the temperature and the measured displacement of each of the target points to be measured; Among them, the real displacement index is 0. After the first acquisition of the on-site image, the temperature data is obtained. , calculate the measured displacement of each fixed target point and the measured displacement of the target point to be measured According to the measurement results of the fixed target point, learn to calculate the real displacement of the fixed target point and the first displacement correction model of each parameter ; The true displacement of the fixed target point is known v i , i=1 , 2 , ... , n , the measured displacement of the fixed target point V i , i=1 , 2 , ... , n ,temperature c i , i=1 , 2 , ... , n , and obtain the first displacement correction model: After acquiring the second image and calculating the measured displacements of each target point to be measured and the fixed target point, the first displacement correction model is first used Correct the first correction displacement of the fixed target point. The first correction displacement of the fixed target point is expressed as , determine the first correction displacement of the fixed target point Is equal to 0, if the first correction displacement of the fixed target point is zero, determining the first displacement correction model If the displacement correction model is valid, the first displacement correction model is used. Correct the real displacement of the target point to be measured in the second image: , is the real displacement of the target point to be measured; If the displacement of the fixed target point after correction is not zero, determine the first displacement correction model If it fails, the second displacement correction model is determined by using the measured displacement of the fixed target point in the second image, the corresponding temperature, and the real displacement of the fixed target point , if in the second image, the measured displacement of each fixed target point V j , j=1 , 2 , ... , m ,temperature c j , j=1 , 2 , ... , m , then the real displacement of the fixed target point v j =f 2 (V j ,c j ) , j=1 , 2 , ... , m, re-learn a new second displacement correction model : Determine the true displacement of a fixed target point Is it established? If established, use Correct the second correction displacement of the target point to be measured in the second image: , is the real displacement of the target point to be measured; The scene image includes a previous image and a current image before and after deformation, and the image-based displacement measurement algorithm is used to calculate the scene image to obtain the measured displacement of each target point to be measured and the measured displacement of each fixed target point, including: Iteratively calculating the previous image and the current image using an image-based displacement measurement algorithm to obtain an image displacement between the previous image and the current image; Calculating the measured displacement of each of the target points to be measured and the measured displacement of each of the fixed target points according to the image displacement; The adopting an image-based displacement measurement algorithm to iteratively calculate the previous image and the current image to obtain the image displacement between the previous image and the current image includes: The previous image is used as the reference image, the current image is used as the deformed image, and the target point to be measured in the reference image is used as the centered Reference sub-area, reference sub-area can be used Indicates that, according to the principle of maximum correlation, a specific search algorithm is used to find the target point to be measured in the deformed image A target sub-region with the center as the center. The target sub-region can be Representation; thus, the following displacement vector can be derived The calculation formula is: , so that the target point to be measured can be determined and Displacement component in the direction ; The step of calculating the measured displacement of each of the target points to be measured and the measured displacement of each of the fixed target points according to the image displacement includes: The image displacement is converted into the measured displacement of each target point to be measured and the measured displacement of each fixed target point according to the oblique optical axis pinhole imaging model; the oblique optical axis pinhole imaging model represents the geometric relationship between the camera plane and the measured plane, and the mathematical relationship between the image displacement and the actual displacement can be obtained from the geometric relationship; The converting the image displacement into the measured displacement of each target point to be measured and the measured displacement of each fixed target point according to the oblique optical axis pinhole imaging model comprises: According to the triangle similarity principle, the calibration formula for converting the image displacement v to the actual measured displacement V is obtained: In the formula is the object distance from the measured point to the optical center of the camera, and the focal length of the camera is , the unit pixel size of the camera target surface is , are the coordinates of the image center, is the angle between the camera and the horizontal plane, Indicates the actual measured displacement, represents image displacement, and the measured point is the target point to be measured or the fixed target point.
2. The method according to claim 1, characterized in that The method further comprises: Setting a plurality of target points to be measured and a plurality of fixed target points at the site to be measured; The real displacement index is set for each of the fixed target points.
3. A long-term monitoring device for structural displacement, characterized in that: The invention is applied to a long-term monitoring system for structural displacement, which comprises: a video camera monitoring device, a temperature sensor and a bracket, wherein the bracket is arranged at a site to be measured, and the site to be measured is a slope structure, wherein the video camera monitoring device and the temperature sensor are respectively fixed by the bracket, and a plurality of target points to be measured and a plurality of fixed target points are arranged at the slope structure, and the device comprises: An acquisition module, used to collect a scene image of the scene to be measured by the video camera monitoring device and to collect the temperature of the scene to be measured by the temperature sensor, and to identify a plurality of target points to be measured and a plurality of fixed target points in the scene image; A first calculation module, used to calculate the scene image using an image-based displacement measurement algorithm to obtain a measured displacement of each of the target points to be measured and a measured displacement of each of the fixed target points; A second calculation module is used to calculate based on the temperature and the measured displacement of each of the fixed target points by using a first displacement correction model pre-acquired based on the first image, so as to obtain a first correction displacement of each of the fixed target points; A third calculation module is used for, if the first corrected displacement of each of the fixed target points is a true displacement index, calculating based on the temperature and the measured displacement of each of the target points to be measured by using the first displacement correction model to obtain the actual displacement of each of the target points to be measured; a processing module, configured to obtain a second displacement correction model according to the temperature corresponding to the second image, the measured displacement and the true displacement of each of the fixed target points if the corrected displacement of each of the fixed target points is not the true displacement index; Obtaining a second corrected displacement of each of the fixed target points based on the temperature and the measured displacement of each of the fixed target points by using the second displacement correction model; If the second corrected displacement of each of the fixed target points is the true displacement index, the actual displacement of each of the target points to be measured is obtained by using the second displacement correction model based on the temperature and the measured displacement of each of the target points to be measured; Among them, the real displacement index is 0. After the first acquisition of the on-site image, the temperature data is obtained. , calculate the measured displacement of each fixed target point and the measured displacement of the target point to be measured According to the measurement results of the fixed target point, learn to calculate the real displacement of the fixed target point and the first displacement correction model of each parameter ; The true displacement of the fixed target point is known v i , i=1 , 2 , ... , n , the measured displacement of the fixed target point V i , i=1 , 2 , ... , n ,temperature c i , i=1 , 2 , ... , n , and obtain the first displacement correction model: After acquiring the second image and calculating the measured displacements of each target point to be measured and the fixed target point, the first displacement correction model is first used Correct the first correction displacement of the fixed target point. The first correction displacement of the fixed target point is expressed as , determine the first correction displacement of the fixed target point Is equal to 0, if the first correction displacement of the fixed target point is zero, determining the first displacement correction model If the displacement correction model is valid, the first displacement correction model is used. Correct the real displacement of the target point to be measured in the second image: , is the real displacement of the target point to be measured; If the displacement of the fixed target point after correction is not zero, determine the first displacement correction model If it fails, the second displacement correction model is determined by using the measured displacement of the fixed target point in the second image, the corresponding temperature, and the real displacement of the fixed target point , if in the second image, the measured displacement of each fixed target point V j , j=1 , 2 , ... , m ,temperature c j , j=1 , 2 , ... , m , then the real displacement of the fixed target point v j =f 2 (V j ,c j ) , j=1 , 2 , ... , m, re-learn a new second displacement correction model : Determine the true displacement of a fixed target point Is it established? If established, use Correct the second correction displacement of the target point to be measured in the second image: , is the real displacement of the target point to be measured; The scene image includes a previous image and a current image before and after deformation, and the image-based displacement measurement algorithm is used to calculate the scene image to obtain the measured displacement of each target point to be measured and the measured displacement of each fixed target point, including: Iteratively calculating the previous image and the current image using an image-based displacement measurement algorithm to obtain an image displacement between the previous image and the current image; Calculating the measured displacement of each of the target points to be measured and the measured displacement of each of the fixed target points according to the image displacement; The adopting an image-based displacement measurement algorithm to iteratively calculate the previous image and the current image to obtain the image displacement between the previous image and the current image includes: The previous image is used as the reference image, the current image is used as the deformed image, and the target point to be measured in the reference image is used as the centered Reference sub-area, reference sub-area can be used Indicates that, according to the principle of maximum correlation, a specific search algorithm is used to find the target point to be measured in the deformed image A target sub-region with the center as the center. The target sub-region can be Representation; thus, the following displacement vector can be derived The calculation formula is: , so that the target point to be measured can be determined and Displacement component in the direction ; The step of calculating the measured displacement of each of the target points to be measured and the measured displacement of each of the fixed target points according to the image displacement includes: The image displacement is converted into the measured displacement of each target point to be measured and the measured displacement of each fixed target point according to the oblique optical axis pinhole imaging model; the oblique optical axis pinhole imaging model represents the geometric relationship between the camera plane and the measured plane, and the mathematical relationship between the image displacement and the actual displacement can be obtained from the geometric relationship; The converting the image displacement into the measured displacement of each target point to be measured and the measured displacement of each fixed target point according to the oblique optical axis pinhole imaging model comprises: According to the triangle similarity principle, the calibration formula for converting the image displacement v to the actual measured displacement V is obtained: In the formula is the object distance from the measured point to the optical center of the camera, and the focal length of the camera is , the unit pixel size of the camera target surface is , are the coordinates of the image center, is the angle between the camera and the horizontal plane, Indicates the actual measured displacement, represents image displacement, and the measured point represents the target point to be measured or the fixed target point.
4. A long-term monitoring system for structural displacement, characterized in that: The method comprises a video camera monitoring device and a temperature sensor, wherein the video camera monitoring device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is run by the processor, the method for long-term monitoring of structural displacement according to claim 1 or 2 is executed.
5. A computer-readable storage medium, characterized in that: It stores a computer program, which executes the method for long-term monitoring of structural displacement according to claim 1 or 2 when running on a processor.
