Bridge displacement monitoring and alarm method, terminal and storage medium

Abstract

The present invention provides a bridge displacement monitoring and alarm method, terminal, and storage medium. The method includes: extracting the position information of different bridge feature points in the current frame image of the target bridge; calculating the center of mass position information, and determining the macroscopic rigid body deformation parameters of the target bridge based on the center of mass position information of the initial frame and the center of mass position information of the current frame; updating the local relative displacement sequence of the target bridge according to the position information of different bridge feature points and the center of mass position information of the current frame; and determining the local deformation parameters of different bridge feature points; performing PCA decomposition on the local relative displacement sequence and extracting the principal component contribution rate; and providing a collapse warning for the target bridge based on the macroscopic rigid body deformation parameters, local deformation parameters, and principal component contribution rate. The above scheme can not only monitor the macroscopic rigid body deformation of the bridge, but also capture local deformation information, thereby comprehensively reflecting the structural state of the bridge and improving the accuracy of bridge monitoring and collapse warning.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge detection, and in particular to a bridge displacement monitoring and alarm method, a terminal and a storage medium. Background Art

[0002] With the growing problem of aging infrastructure, monitoring the health of bridge structures has become a crucial issue for ensuring public safety. Traditional monitoring methods rely on physical sensors such as accelerometers, strain gauges, and displacement sensors, which are costly, complex to deploy, and difficult to achieve large-scale, comprehensive, and real-time monitoring.

[0003] In recent years, breakthroughs in computer vision technology have opened up new avenues for non-contact monitoring. Image-based monitoring methods, which can acquire global data by deploying cameras, have the advantages of low cost, scalability, and non-invasiveness, and have become a research hotspot in bridge monitoring. Existing image-based bridge monitoring methods typically assess the structural condition of bridges by tracking displacement changes at key bridge points (such as bearings and piers). However, this approach often misses the structural condition of many bridge locations, resulting in inaccurate overall bridge monitoring. Summary of the Invention

[0004] The embodiments of the present invention provide a bridge displacement monitoring and alarm method, a terminal and a storage medium to solve the problem of insufficient accuracy in monitoring the overall structural status of a bridge in the prior art.

[0005] In a first aspect, an embodiment of the present invention provides a bridge displacement monitoring and alarm method, comprising:

[0006] Extracting the position information of different bridge feature points in the current frame image of the target bridge;

[0007] Calculating the center of mass position information in the current frame image, and determining the macroscopic rigid body deformation parameters of the target bridge based on the center of mass position information of the initial frame and the center of mass position information of the current frame;

[0008] updating the local relative displacement sequence of the target bridge according to the position information of different bridge feature points and the center of mass position information of the current frame; and determining the local deformation parameters of different bridge feature points; the local deformation parameters include local rigid residual and local relative displacement parameters;

[0009] Performing PCA decomposition on the local relative displacement sequence to extract the principal component contribution rate; the local relative displacement sequence includes multiple frames of local relative displacements of each bridge feature point;

[0010] Based on the macroscopic rigid body deformation parameters, the local deformation parameters and the principal component contribution rate, a collapse warning is performed on the target bridge.

[0011] In a second aspect, an embodiment of the present invention provides a terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method described in any possible implementation of the first aspect are implemented.

[0012] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the method described in any possible implementation of the first aspect above.

[0013] An embodiment of the present invention provides a bridge displacement monitoring and alarm method, terminal, and storage medium. The method extracts the position information of different bridge feature points in a current frame image of a target bridge; calculates the center of mass position information in the current frame image, and determines the macroscopic rigid body deformation parameters of the target bridge based on the center of mass position information of the initial frame and the center of mass position information of the current frame; updates the local relative displacement sequence of the target bridge based on the position information of different bridge feature points and the center of mass position information of the current frame; and determines the local deformation parameters of different bridge feature points. The local deformation parameters include local rigid residuals and local relative displacement parameters; performs PCA decomposition on the local relative displacement sequence to extract the principal component contribution rate; the local relative displacement sequence includes multiple frames of local relative displacements of each bridge feature point; and finally, based on the macroscopic rigid body deformation parameters, the local deformation parameters, and the principal component contribution rate, provides a collapse warning for the target bridge. The above scheme can not only monitor the macroscopic rigid body deformation of the bridge, but also capture local deformation information, thereby comprehensively reflecting the structural status of the bridge and improving the accuracy of bridge monitoring and collapse warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0015] Figure 1 This is a flow chart of the bridge displacement monitoring and alarm method provided by an embodiment of the present invention;

[0016] Figure 2 Schematic diagram of the installation position of a camera for photographing a target bridge deck according to an embodiment of the present invention;

[0017] Figure 3 Schematic diagram of the structure of a bridge displacement monitoring and alarm device provided by an embodiment of the present invention;

[0018] Figure 4 is a schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0020] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below with reference to the accompanying drawings.

[0021] See also Figure 1 , which shows a flow chart of the bridge displacement monitoring and alarm method provided by an embodiment of the present invention, which is described in detail as follows:

[0022] S101: Extracting position information of different bridge feature points in a current frame image of a target bridge.

[0023] In this embodiment, a camera may be used to capture an image of the target bridge, and the image may be an image of the complete bridge deck of the target bridge. Figure 2 A schematic diagram of the installation position of a camera for shooting a target bridge deck is shown. Figure 2 The camera 10 is mounted on one side of the target bridge 30 via a bracket 20 and takes a bird's-eye view of the entire bridge deck to obtain an image of the bridge deck. It is understood that capturing the bridge deck structure requires coverage of different lighting conditions and shooting angles (e.g., front view, side view, and close-up of the bridge deck). In this embodiment, a single camera can capture a complete image of the target bridge deck. If a single camera is unable to capture the complete image of the target bridge deck, multiple cameras can simultaneously capture images of the target bridge deck at different locations, and synchronization technology can be used to obtain a complete image of the target bridge deck in the same frame.

[0024] After the cameras are set up, video data containing the target bridge structure is captured. Before bridge displacement monitoring, the video data is first selected as a training set. Manual annotation tools are used to annotate key bridge features, identifying the target bridge's feature points and forming a standardized dataset. Manual annotation tools can include CVAT (Computer Vision Annotation Tool) and Labelme (Label Generation Tool). Key bridge features include core load-bearing areas, edge and deformation-sensitive areas, and rigid reference areas. Core load-bearing areas include the midpoint of the mid-span main beam, support connection points, and feature points at the top of the pier; edge and deformation-sensitive areas include corner points at the edge of the bridge deck, joint locations, and guardrail connection points; and rigid reference areas include stable abutments or ground fixed points. Then, based on the annotated data, transfer learning is performed using the pre-trained YOLOv8-Pose model. This training is customized for bridge feature points, improving the accuracy and robustness of the model's detection of bridge feature points.

[0025] During the actual monitoring process, the trained YOLOv8-Pose model is used to perform real-time inference on the video stream to extract the position information of different bridge feature points of the bridge structure.

[0026] This embodiment uses the above method to generate a time series trajectory for each bridge feature point in the target bridge. The time series trajectory includes multiple frames of position information that changes over time. If the trajectory is interrupted due to occlusion or missed detection, an interpolation method is used to complete the trajectory.

[0027] S102: Calculate the center of mass position information in the current frame image, and determine the macroscopic rigid body deformation parameters of the target bridge based on the center of mass position information of the initial frame and the center of mass position information of the current frame.

[0028] In one possible implementation, the specific implementation process of calculating the center of mass position information in the current frame image in S102 includes:

[0029] S201: Subtracting the position information of each bridge feature point in the current frame image from the initial position information of the corresponding bridge feature point to obtain the relative displacement of each bridge feature point.

[0030] The position information can be the position coordinates, and the relative displacement of the bridge feature point is calculated using the following formula:

[0031]

[0032] in,( , ) is the position coordinate of the i-th bridge feature point at time t, is the initial moment, ( , ) is the position coordinate of the i-th bridge feature point at the initial time t0. represents the lateral relative displacement of the i-th bridge feature point at time t, represents the longitudinal relative displacement of the i-th bridge feature point at time t.

[0033] S202: Convert the relative displacement of each bridge feature point on the image into an actual relative displacement.

[0034] In this embodiment, for each bridge feature point in each frame of the image, a line segment is drawn parallel to the width of the bridge deck, passing through the bridge feature point and with the two sides of the bridge as endpoints. This line segment is used as the bridge pixel width line, and the pixel length of the line segment in the image is measured. ; and calculate the pixel rate corresponding to each bridge feature point based on the actual bridge deck width w obtained from the bridge design drawing or on-site measurement .

[0035] After determining the pixel rate, the relative displacement of each bridge feature point i in the time t image is normalized and converted according to the pixel rate corresponding to the bridge feature point to obtain the actual relative displacement. The conversion formula is as follows:

[0036]

[0037] in, represents the actual relative lateral displacement of the bridge feature point i at time t, Represents the actual relative longitudinal displacement of the bridge feature point i at time t.

[0038] S203: Performing weighted averaging on the actual relative displacements of all bridge feature points in the current frame image to obtain the centroid position information of the target bridge.

[0039] In one possible implementation, the center of mass position information includes center of mass coordinates; the specific implementation process of S203 includes:

[0040] Based on the formula Calculating the centroid coordinates of the target bridge;

[0041] in, represents the horizontal coordinate of the center of mass at time t, represents the vertical coordinate of the centroid at time t; N represents the number of characteristic points of the bridge; (t) represents the actual relative lateral displacement of the i-th bridge feature point at time t; (t) represents the actual relative longitudinal displacement of the i-th bridge characteristic point at time t; Represents the weight of the i-th bridge feature point.

[0042] The weights of bridge feature points at each location vary, and are assigned based on the importance of each bridge structural location. Specifically, the weight of bridge feature points in the midspan is greater than that of bridge feature points in the support area, which in turn is greater than that of bridge feature points in the edge area. The midspan and the area directly above the main beam are assigned higher weights, while the weights of bridge feature points near the support or in the edge area are adjusted based on their load characteristics. In practical applications, the weights of each bridge feature point can be determined based on bridge design drawings, finite element simulations, or empirical knowledge.

[0043] In one possible embodiment, the macroscopic rigid body deformation parameters include center of mass displacement, center of mass tilt angle, and main vibration frequency;

[0044] The specific implementation process of determining the macroscopic rigid body deformation parameters of the target bridge based on the center of mass position information of the initial frame and the center of mass position information of the current frame in S102 includes:

[0045] Subtracting the center of mass position information of the current frame from the center of mass position information of the initial frame to obtain the center of mass displacement of the current frame; the center of mass displacement includes the horizontal displacement of the center of mass and the vertical displacement of the center of mass;

[0046] Determine the inclination angle of the center of mass of the current frame based on the lateral displacement and longitudinal displacement of the center of mass of the current frame;

[0047] Performing a fast Fourier transform on the current center-of-mass trajectory sequence to obtain a spectrum of the current center-of-mass trajectory sequence, and extracting the main vibration frequency of the spectrum; the current center-of-mass trajectory sequence includes all center-of-mass position information from the initial frame to the current frame.

[0048] In this embodiment, after the centroid position information is calculated according to S201 to S203, the centroid position coordinates of the initial frame are determined. and the center of mass position coordinates at the current time t , then subtract the horizontal coordinate of the center of mass of the initial frame from the horizontal coordinate of the center of mass of the current frame to get the horizontal displacement of the center of mass of the current frame; subtract the vertical coordinate of the center of mass of the initial frame from the vertical coordinate of the center of mass of the current frame to get the vertical displacement of the center of mass of the current frame. The specific formula is: , represents the lateral displacement of the center of mass, represents the longitudinal displacement of the center of mass.

[0049] After determining the lateral displacement of the center of mass and the longitudinal displacement of the center of mass, based on the formula Determine the centroid tilt angle, where The tilt angle of the center of mass at time t indicates the tendency of the bridge to rotate or overturn, which is common under uneven settlement or abnormal loads. If the tilt angle increases sharply in a short period of time, it indicates the risk of structural instability.

[0050] The centroid trajectory includes the centroid displacement of consecutive frames that changes with time, which can reflect the changes in the overall translation state of the bridge, such as overall settlement, overall lateral displacement, etc. The high-frequency fluctuation components in the centroid trajectory are used to analyze the vibration characteristics of the structure. Perform a Fast Fourier Transform (FFT) to extract the main vibration frequencies:

[0051]

[0052] Analyze the dominant frequencies of center of mass vibration And its changing trend, under normal circumstances, the vibration frequency of the bridge center of mass is relatively stable; when the structural stiffness decreases, such as cracks appear or the section is weakened, the main frequency of the center of mass will drift and decrease.

[0053] S103: updating the local relative displacement sequence of the target bridge according to the position information of different bridge feature points and the center of mass position information of the current frame; and determining the local deformation parameters of different bridge feature points; the local deformation parameters include local rigid residual and local relative displacement parameters.

[0054] In a possible implementation, the local relative displacement parameters include a local relative displacement distribution standard deviation and a local relative displacement distribution range;

[0055] The specific implementation process of determining the local deformation parameters of different bridge feature points in S103 includes:

[0056] Calculating local relative displacements of different bridge feature points in the current frame based on position information of different bridge feature points in the current frame and center of mass position information of the current frame;

[0057] Based on the local relative displacements of all bridge feature points in the current frame, the standard deviation and the range of the local relative displacement distribution of the target bridge in the current frame are calculated;

[0058] All bridge feature points are divided into multiple feature point clusters according to spatial proximity;

[0059] Based on the position information of each bridge feature point in the current frame and the position information of the initial frame, the rigid transformation matrix corresponding to the bridge feature point is fitted;

[0060] For each cluster of bridge feature points, calculate the local fitting residuals of the cluster based on the position information of each bridge feature point in the current frame, the position information in the initial frame, and the rigid transformation matrix. <0000​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​ Calculate the local fitting residual for each feature point cluster.

[0072] in, represents the position of the i-th bridge feature point at time t; is the position of the i-th bridge feature point at the initial moment; , are the fitted rotation matrix and translation vector respectively.

[0073] It can be seen from the above embodiments that the larger the RMS, the more serious the local rigidity mismatch. The long-term cumulative growth or short-term sharp jump of RMS will cause local damage.

[0074] In one possible implementation, when the centroid position information is obtained by weighted averaging the actual relative displacement, the position information of each bridge feature point needs to be normalized to the position information of the actual coordinate system by pixel ratio. Accordingly, the specific implementation process of S103 is as follows:

[0075] According to the position information of different bridge feature points in the actual coordinate system and the center of mass position information of the current frame, the local relative displacement sequence of the target bridge is updated; and the local deformation parameters of different bridge feature points are determined.

[0076] S104: Performing PCA decomposition on the local relative displacement sequence to extract principal component contribution rates; the local relative displacement sequence includes multiple frames of local relative displacements of each bridge feature point.

[0077] In this embodiment, the local relative displacement sequence includes multiple frames of local relative displacements for each bridge feature point. This embodiment can determine the principal component contribution rate and energy spectrum diffusion by performing PCA decomposition on the local relative displacement sequence. Energy spectrum diffusion measures the degree of dispersion of the principal component energy among its various order components and can be quantitatively described by information entropy or energy entropy. A higher entropy value indicates a more dispersed energy distribution and a more complex structural deformation.

[0078] S105: Based on the macroscopic rigid body deformation parameter, the local deformation parameter and the principal component contribution rate, a collapse warning is issued for the target bridge.

[0079] In one possible implementation, the specific implementation process of S105 includes:

[0080] S301: If the macroscopic rigid body deformation parameter exceeds a preset macroscopic alarm condition, triggering a level 1 alarm of the target bridge;

[0081] S302: If the local deformation parameter exceeds a preset local alarm condition, triggering a secondary alarm of the target bridge;

[0082] S303: If the local deformation parameter exceeds the preset local alarm condition and the decrease in the principal component contribution rate exceeds a preset amplitude threshold, triggering a level 3 alarm for the target bridge;

[0083] The level of the first level alarm is lower than the level of the second level alarm, and the level of the second level alarm is lower than the level of the third level alarm.

[0084] In one possible implementation, the macroscopic rigid body deformation parameters include center of mass displacement, center of mass inclination angle, and main vibration frequency; the specific implementation process of S301 includes:

[0085] If the absolute value of the center of mass displacement exceeds the preset center of mass displacement threshold, or the absolute value of the center of mass inclination angle exceeds the preset angle threshold, or the difference between the main vibration frequency and the baseline frequency is less than the preset frequency difference, a level one alarm is triggered for the target bridge.

[0086] In this embodiment, when a level one alarm is triggered, it indicates that the overall displacement of the bridge is abnormal and the local area is not damaged. At this time, the level one alarm can be displayed through the terminal to prompt the user that a level one alarm exists on the target bridge.

[0087] In a possible implementation, the local relative displacement parameters include a local relative displacement distribution standard deviation and a local relative displacement distribution range;

[0088] The specific implementation process of S302 includes:

[0089] If the absolute value of the local rigid residual is greater than a preset residual threshold, or the standard deviation of the local relative displacement distribution is greater than a preset standard deviation threshold, or the range of the local relative displacement distribution is greater than a preset range threshold, a secondary alarm of the target bridge is triggered.

[0090] In this embodiment, when a second-level warning occurs, it indicates that damage or local buckling occurs in a local area of ​​the target bridge. The second-level alarm can also be displayed on the terminal, and the location of the local area of ​​the alarm can be indicated.

[0091] In one possible embodiment, when the second-level alarm is triggered, and at this time the decrease in the contribution rate of the first principal component of PCA exceeds a preset amplitude threshold, and the energy diffusion exceeds a preset diffusion threshold, the third-level alarm of the target bridge is triggered. Triggering the third-level alarm indicates that the structure of the target bridge is complexly deformed and there is a risk of instability or imminent collapse. At this time, relevant personnel can be notified through multiple alarm methods so that the relevant personnel can understand the risk as soon as possible and respond in a timely manner.

[0092] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0093] The following are device embodiments of the present invention. For details not fully described therein, reference may be made to the corresponding method embodiments described above.

[0094] Figure 3 The following is a schematic diagram showing the structure of a bridge displacement monitoring and alarm device provided by an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0095] like Figure 3 As shown, the bridge displacement monitoring and alarm device 100 includes:

[0096] The position information extraction module 110 is used to extract the position information of different bridge feature points in the current frame image of the target bridge;

[0097] A macroscopic rigid body deformation parameter acquisition module 120 is configured to calculate the center of mass position information in the current frame image, and determine the macroscopic rigid body deformation parameters of the target bridge based on the center of mass position information of the initial frame and the center of mass position information of the current frame;

[0098] The local deformation parameter acquisition module 130 is used to update the local relative displacement sequence of the target bridge according to the position information of different bridge feature points and the center of mass position information of the current frame; and determine the local deformation parameters of different bridge feature points; the local deformation parameters include local rigid residual and local relative displacement parameters;

[0099] The principal component extraction module 140 is used to perform PCA decomposition on the local relative displacement sequence to extract the principal component contribution rate; the local relative displacement sequence includes multiple frames of local relative displacements of each bridge feature point;

[0100] The collapse warning module 150 is configured to provide a collapse warning for the target bridge based on the macroscopic rigid body deformation parameter, the local deformation parameter, and the principal component contribution rate.

[0101] In one possible implementation, the macroscopic rigid body deformation parameter acquisition module 120 includes:

[0102] A relative displacement calculation unit is used to subtract the position information of each bridge feature point in the current frame image from the initial position information of the corresponding bridge feature point to obtain the relative displacement of each bridge feature point;

[0103] An actual relative displacement conversion unit, used to convert the relative displacement of each bridge feature point on the image into an actual relative displacement;

[0104] The centroid position calculation unit is used to perform weighted averaging on the actual relative displacements of all bridge feature points in the current frame image to obtain the centroid position information of the target bridge.

[0105] In one possible implementation, the center of mass position information includes center of mass coordinates; and the center of mass position calculation unit is specifically configured to:

[0106] Based on the formula Calculating the centroid coordinates of the target bridge;

[0107] in, represents the horizontal coordinate of the center of mass at time t, represents the vertical coordinate of the center of mass at time t; N represents the number of bridge feature points in the current frame image; (t) represents the actual relative lateral displacement of the i-th bridge feature point at time t; (t) represents the actual relative longitudinal displacement of the i-th bridge characteristic point at time t; Represents the weight of the i-th bridge feature point.

[0108] In one possible embodiment, the macroscopic rigid body deformation parameters include center of mass displacement, center of mass tilt angle, and main vibration frequency;

[0109] The macroscopic rigid body deformation parameter acquisition module 120 includes:

[0110] Subtracting the center of mass position information of the current frame from the center of mass position information of the initial frame to obtain the center of mass displacement of the current frame; the center of mass displacement includes the horizontal displacement of the center of mass and the vertical displacement of the center of mass;

[0111] Determine the inclination angle of the center of mass of the current frame based on the lateral displacement and longitudinal displacement of the center of mass of the current frame;

[0112] Performing a fast Fourier transform on the current center-of-mass trajectory sequence to obtain a spectrum of the current center-of-mass trajectory sequence, and extracting the main vibration frequency of the spectrum; the current center-of-mass trajectory sequence includes all center-of-mass position information from the initial frame to the current frame.

[0113] In a possible implementation, the local relative displacement parameters include a local relative displacement distribution standard deviation and a local relative displacement distribution range;

[0114] The local deformation parameter acquisition module 130 includes:

[0115] Calculating local relative displacements of different bridge feature points in the current frame based on position information of different bridge feature points in the current frame and center of mass position information of the current frame;

[0116] Based on the local relative displacements of all bridge feature points in the current frame, the standard deviation and the range of the local relative displacement distribution of the target bridge in the current frame are calculated;

[0117] All bridge feature points are divided into multiple feature point clusters according to spatial proximity;

[0118] Based on the position information of each bridge feature point in the current frame and the position information of the initial frame, the rigid transformation matrix corresponding to the bridge feature point is fitted;

[0119] For each bridge feature point cluster, the local fitting residual of the feature point cluster is calculated based on the position information of each bridge feature point in the feature point cluster in the current frame, the position information of the initial frame and the rigid transformation matrix.

[0120] In one possible implementation, the collapse warning module 150 includes:

[0121] a first-level alarm unit, configured to trigger a first-level alarm of the target bridge if the macroscopic rigid body deformation parameter exceeds a preset macroscopic alarm condition;

[0122] a secondary alarm unit, configured to trigger a secondary alarm of the target bridge if the local deformation parameter exceeds a preset local alarm condition;

[0123] A third-level alarm unit is configured to trigger a third-level alarm for the target bridge if the local deformation parameter exceeds the preset local alarm condition and the decrease in the principal component contribution rate exceeds a preset amplitude threshold;

[0124] The level of the first level alarm is lower than the level of the second level alarm, and the level of the second level alarm is lower than the level of the third level alarm.

[0125] In one possible embodiment, the macroscopic rigid body deformation parameters include center of mass displacement, center of mass inclination angle, and main vibration frequency; the first-level alarm unit includes:

[0126] If the absolute value of the center of mass displacement exceeds the preset center of mass displacement threshold, or the absolute value of the center of mass inclination angle exceeds the preset angle threshold, or the difference between the main vibration frequency and the baseline frequency is less than the preset frequency difference, a level one alarm is triggered for the target bridge.

[0127] In a possible implementation, the local relative displacement parameters include a local relative displacement distribution standard deviation and a local relative displacement distribution range;

[0128] The secondary alarm unit includes:

[0129] If the absolute value of the local rigid residual is greater than a preset residual threshold, or the standard deviation of the local relative displacement distribution is greater than a preset standard deviation threshold, or the range of the local relative displacement distribution is greater than a preset range threshold, a secondary alarm of the target bridge is triggered.

[0130] Figure 4 Schematic diagram of a terminal provided by an embodiment of the present invention. Figure 4 As shown, the terminal 4 of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the above-mentioned embodiments of the bridge displacement monitoring and alarm method are implemented, for example Figure 1 Alternatively, when the processor 40 executes the computer program 42 , the functions of the modules / units in the above-mentioned device embodiments are realized.

[0131] Exemplarily, the computer program 42 may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 42 in the terminal 4.

[0132] The terminal 4 can be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 4 can include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will understand that Figure 4 It is only an example of terminal 4 and does not constitute a limitation on terminal 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0133] The processor 40 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0134] The memory 41 may be an internal storage unit of the terminal 4, such as a hard drive or memory of the terminal 4. The memory 41 may also be an external storage device of the terminal 4, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the memory 41 may include both the internal storage unit of the terminal 4 and an external storage device. The memory 41 is used to store the computer program and other programs and data required by the terminal. The memory 41 may also be used to temporarily store data that has been output or is about to be output.

[0135] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0136] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0137] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0138] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical functional division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, and can be electrical, mechanical, or other forms.

[0139] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0140] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0141] If the integrated module / unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can also implement all or part of the processes in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned bridge displacement monitoring and alarm method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard drive, a magnetic disk, an optical disk, computer memory, read-only memory (ROM), random access memory (RAM), an electrical carrier signal, a telecommunications signal, and software distribution media.

[0142] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A bridge displacement monitoring and alarm method, characterized in that: include: Extracting the position information of different bridge feature points in the current frame image of the target bridge; Calculating the center of mass position information in the current frame image, and determining the macroscopic rigid body deformation parameters of the target bridge based on the center of mass position information of the initial frame and the center of mass position information of the current frame; updating the local relative displacement sequence of the target bridge according to the position information of different bridge feature points and the center of mass position information of the current frame; and determining the local deformation parameters of different bridge feature points; the local deformation parameters include local rigid residual and local relative displacement parameters; Performing PCA decomposition on the local relative displacement sequence to extract the principal component contribution rate; the local relative displacement sequence includes multiple frames of local relative displacements of each bridge feature point; Based on the macroscopic rigid body deformation parameter, the local deformation parameter and the principal component contribution rate, a collapse warning is performed on the target bridge; The calculating of the center of mass position information in the current frame image includes: Subtract the position information of each bridge feature point in the current frame image from the initial position information of the corresponding bridge feature point to obtain the relative displacement of each bridge feature point; Convert the relative displacement of each bridge feature point on the image into the actual relative displacement; Performing weighted averaging on the actual relative displacements of all bridge feature points in the current frame image to obtain the centroid position information of the target bridge; The center of mass position information includes the center of mass coordinates; the weighted average of the actual relative displacements of all bridge feature points in the current frame image to obtain the center of mass position information of the target bridge includes: Based on the formula Calculating the centroid coordinates of the target bridge; in, represents the horizontal coordinate of the center of mass at time t, represents the vertical coordinate of the center of mass at time t; N Indicates the number of bridge feature points in the current frame image; (t) represents the time t i The actual relative lateral displacement of each bridge feature point; (t) represents the time t i The actual relative longitudinal displacement of each bridge feature point; Indicates the i The weight of each bridge feature point; The macroscopic rigid body deformation parameters include center of mass displacement, center of mass tilt angle and main vibration frequency; The determining of the macroscopic rigid body deformation parameters of the target bridge based on the center of mass position information of the initial frame and the center of mass position information of the current frame includes: Subtracting the center of mass position information of the current frame from the center of mass position information of the initial frame to obtain the center of mass displacement of the current frame; the center of mass displacement includes the horizontal displacement of the center of mass and the vertical displacement of the center of mass; Determine the inclination angle of the center of mass of the current frame based on the lateral displacement and longitudinal displacement of the center of mass of the current frame; Performing a fast Fourier transform on the current center-of-mass trajectory sequence to obtain a spectrum of the current center-of-mass trajectory sequence, and extracting the main vibration frequency of the spectrum; the current center-of-mass trajectory sequence includes all center-of-mass position information from the initial frame to the current frame.

2. The bridge displacement monitoring and alarm method according to claim 1 is characterized in that: The local relative displacement parameters include the local relative displacement distribution standard deviation and the local relative displacement distribution range; Determine the local deformation parameters of the different bridge feature points based on the position information of the different bridge feature points and the center of mass position information of the current frame, including: Calculating local relative displacements of different bridge feature points in the current frame based on position information of different bridge feature points in the current frame and center of mass position information of the current frame; Based on the local relative displacements of all bridge feature points in the current frame, the standard deviation and the range of the local relative displacement distribution of the target bridge in the current frame are calculated; All bridge feature points are divided into multiple feature point clusters according to spatial proximity; Based on the position information of each bridge feature point in the current frame and the position information of the initial frame, the rigid transformation matrix corresponding to the bridge feature point is fitted; For each bridge feature point cluster, the local fitting residual of the feature point cluster is calculated based on the position information of each bridge feature point in the feature point cluster in the current frame, the position information of the initial frame and the rigid transformation matrix.

3. The bridge displacement monitoring and alarm method according to claim 1 is characterized in that: The step of providing a collapse warning for the target bridge based on the macroscopic rigid body deformation parameter, the local deformation parameter, and the principal component contribution rate includes: If the macroscopic rigid body deformation parameter exceeds the preset macroscopic alarm condition, a first-level alarm of the target bridge is triggered; If the local deformation parameter exceeds the preset local alarm condition, a secondary alarm of the target bridge is triggered; If the local deformation parameter exceeds the preset local alarm condition and the decrease in the principal component contribution rate exceeds a preset amplitude threshold, a level 3 alarm is triggered for the target bridge; The level of the first level alarm is lower than the level of the second level alarm, and the level of the second level alarm is lower than the level of the third level alarm.

4. The bridge displacement monitoring and alarm method according to claim 3 is characterized in that: The macroscopic rigid body deformation parameters include center of mass displacement, center of mass tilt angle and main vibration frequency; If the macroscopic rigid body deformation parameter exceeds a preset macroscopic alarm condition, triggering a first-level alarm of the target bridge includes: If the absolute value of the center of mass displacement exceeds the preset center of mass displacement threshold, or the absolute value of the center of mass inclination angle exceeds the preset angle threshold, or the difference between the main vibration frequency and the baseline frequency is less than the preset frequency difference, a level one alarm is triggered for the target bridge.

5. The bridge displacement monitoring and alarm method according to claim 3 is characterized in that: The local relative displacement parameters include the local relative displacement distribution standard deviation and the local relative displacement distribution range; If the local deformation parameter exceeds the preset local alarm condition, triggering a secondary alarm of the target bridge includes: If the absolute value of the local rigid residual is greater than a preset residual threshold, or the standard deviation of the local relative displacement distribution is greater than a preset standard deviation threshold, or the range of the local relative displacement distribution is greater than a preset range threshold, a secondary alarm of the target bridge is triggered.

6. A terminal comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images