Tunnel deformation monitoring method based on chain inertial vision measurement

Abstract

This application relates to the technical field of tunnel deformation monitoring, and more particularly to a tunnel deformation monitoring method based on chained inertial vision measurement. The method comprises dividing a reservoir tunnel area to be monitored into a plurality of monitoring areas; acquiring image data and camera inertial data for each monitoring area; determining target displacement data for the corresponding monitoring area based on the image data; determining deformation data for the corresponding monitoring area based on the target displacement data and camera inertial data; and generating deformation monitoring results for the corresponding monitoring area based on the deformation data. This application has the effect of improving the accuracy of reservoir tunnel deformation monitoring calculations and the adaptability of deformation monitoring.

Description

Technical Field

[0001] The present application relates to the technical field of tunnel deformation monitoring, and in particular to a tunnel deformation monitoring method based on chain inertial vision measurement. Background Art

[0002] At present, reservoir tunnels, as an important part of water conservancy projects, undertake functions such as water transmission, flood discharge, and maintenance channels. In order to ensure the safe operation of reservoir tunnels, it is necessary to conduct long-term monitoring of the structural deformation of the tunnels to determine whether there are risks such as abnormal displacement, settlement, and deformation, so as to take maintenance measures in time to prevent serious structural damage and safety accidents.

[0003] Existing deformation monitoring of reservoir tunnels mainly adopts single-point measurement method and total station measurement method. Among them, the single-point measurement method usually relies on manual measurement using level, total station or static GPS equipment on a regular basis. The measurement frequency of this method is low, and it is difficult to achieve continuous monitoring of deformation. In addition, manual operation is easily affected by environmental factors, resulting in large measurement errors. Although the total station measurement method can provide high-precision data, it relies on a single fixed station, making it difficult to measure at the bends of the tunnel. At the same time, the equipment cost is high and the measurement cycle is long, so there is room for improvement. Summary of the Invention

[0004] The present application provides a tunnel deformation monitoring method based on chain inertial vision measurement, which can improve the accuracy of deformation monitoring calculation of reservoir tunnels and the adaptability of deformation monitoring.

[0005] The above-mentioned invention objective of this application is achieved through the following technical solutions:

[0006] A tunnel deformation monitoring method based on chained inertial vision measurement, the tunnel deformation monitoring method based on chained inertial vision measurement comprising:

[0007] Divide the reservoir tunnel area to be monitored into several monitoring areas;

[0008] Acquire image data and camera inertial data of each monitoring area, and determine target displacement data of the corresponding monitoring area based on the image data;

[0009] Determining deformation data of a corresponding monitoring area based on the target displacement data and the camera inertial data;

[0010] A deformation monitoring result of the corresponding monitoring area is generated according to the deformation amount data.

[0011] By adopting the above technical solution, the reservoir tunnel area to be monitored is divided into several monitoring areas, which can ensure that the monitoring system can perform refined monitoring of different areas, avoid data confusion caused by overall monitoring, and thus improve the accuracy of monitoring. By obtaining image data and camera inertial data of each monitoring area and determining the target displacement data of the corresponding monitoring area based on the image data, the displacement information of the reservoir tunnel can be obtained and analyzed in real time, avoiding data errors caused by a single measurement method, thereby improving the stability and reliability of deformation monitoring. By determining the deformation variable data of the corresponding monitoring area based on the target displacement data and camera inertial data, the data of visual measurement and inertial measurement can be comprehensively considered, and the measurement error caused by external environmental interference can be reduced, thereby improving the accuracy of deformation variable calculation and making the monitoring results more credible.

[0012] In a preferred example, the present application may be further configured as follows: the tunnel deformation monitoring method based on chained inertial vision measurement further includes:

[0013] Obtain target images and corresponding camera inertial data of different monitoring areas of the reservoir tunnel at any time, wherein the camera inertial data is collected by the inertial measurement unit of the inertial camera;

[0014] Inputting the corresponding target image and the camera inertial data into an initial model, and optimizing the model parameters of the initial model through back propagation and model evaluation indicators;

[0015] When the model evaluation index reaches a preset threshold, the training of the initial model is completed to obtain a deformable model.

[0016] By adopting the above technical solution, target images and corresponding camera inertia data of different monitoring areas of the reservoir tunnel at any time are obtained and input into the initial model, thereby training the initial model to obtain a deformation model. The deformation calculation model is given the ability to adaptively adjust, and can still maintain high calculation accuracy under different monitoring environments, different tunnel structures and different external influencing factors. The influence of the deformation variable at different positions of the target and the camera is fully considered, and the corresponding deformation variable is output, thereby improving the accuracy of the deformation variable.

[0017] In a preferred example, the present application may be further configured as follows: acquiring image data and camera inertial data of each monitoring area, and determining target displacement data of the corresponding monitoring area based on the image data, specifically including:

[0018] According to the preset time period, the image data and camera inertial data of each monitoring area are collected;

[0019] Based on the image processing algorithm and the PnP algorithm, the image data is processed and the posture calculation is performed to obtain the target displacement data.

[0020] By adopting the above technical solution, image data and camera inertial data of each monitoring area are collected, which can ensure the time synchronization of the monitoring data and avoid the inconsistency caused by time drift during the data acquisition process, thereby improving the temporal continuity and integrity of the monitoring data. Then, by obtaining the target displacement data based on the image processing algorithm and the PnP algorithm, the influence of factors such as the camera installation angle, illumination changes, and image distortion on the measurement accuracy can be effectively reduced, thereby improving the stability of the target displacement calculation and making the measurement results more reliable.

[0021] In a preferred example, the present application may be further configured as follows: performing image processing and pose calculation on the image data based on the image processing algorithm and the PnP algorithm to obtain the target displacement data specifically includes:

[0022] Based on the image processing algorithm, target area recognition processing is performed on the image data to obtain target highlight image data;

[0023] Based on the PnP algorithm, the target pose is calculated for the target highlighted image data to obtain the target displacement data.

[0024] By adopting the above technical solution, with the help of image processing algorithms and PnP algorithms, the target area can be accurately identified, the reliability of target positioning can be improved, and the position changes of the target in different camera frames can be combined to calculate the real displacement data of the target, thereby improving the stability of the target displacement calculation.

[0025] In a preferred example, the present application may be further configured as follows: determining the deformation data of the corresponding monitoring area based on the target displacement data and the camera inertial data, specifically including:

[0026] Inputting the target displacement data and the camera inertia data into the deformation model to obtain a deformation variable;

[0027] The deformation variables are fitted based on a time series filtering algorithm and a least square method to obtain deformation variable data of the corresponding monitoring area.

[0028] By adopting the above technical solution, the target displacement data and camera inertial data are input into the deformation model to obtain the deformation variable, which fully combines the advantages of visual measurement and inertial measurement, reduces the data fluctuation caused by a single measurement method, and improves the accuracy of deformation variable calculation. The deformation variable is then fitted to obtain the deformation variable data of the corresponding monitoring area, which can effectively eliminate outliers caused by short-term noise and improve the trend analysis capability of deformation data.

[0029] In a preferred example, the present application may be further configured as follows: generating a deformation monitoring result corresponding to the monitoring area according to the deformation amount data specifically includes:

[0030] Based on the finite element analysis method, the benchmark deformation data of different monitoring areas are obtained;

[0031] The deviation value between the deformation variable data of the current monitoring area and the reference deformation variable data is calculated, and the corresponding deformation monitoring result is generated according to the deviation value.

[0032] By adopting the above technical solution and based on the finite element analysis method, the benchmark deformation data of different monitoring areas can be obtained. The structural characteristics and mechanical model of the reservoir tunnel can be combined to calculate the theoretical benchmark deformation data, thereby providing a reliable comparison standard for the actual monitoring data, avoiding misjudgment due to measurement errors or environmental changes. Furthermore, through the deviation value between the deformation data and the benchmark deformation data, it can be judged whether the deformation of the current monitoring area is within the normal range, thereby improving the credibility of the deformation monitoring results and enabling the monitoring data to be directly used for decision-making analysis.

[0033] In a preferred example, the present application can be further configured as follows: after obtaining the deformation monitoring result, if the deviation value exceeds a preset warning threshold, an alarm mechanism is triggered, and the deformation monitoring result is visualized to obtain a three-dimensional deformation thermal map.

[0034] By adopting the above technical solution, after obtaining the deformation monitoring results, if the deviation value exceeds the preset warning threshold, the alarm mechanism is triggered, and an alarm can be issued immediately when the deformation is abnormal, thereby improving the ability to ensure the safety of the reservoir tunnel structure. By visualizing the deformation monitoring results, the monitoring personnel can intuitively view the overall deformation of the reservoir tunnel and quickly identify high-risk areas, thereby improving the readability and visualization analysis capabilities of the monitoring results, making the monitoring data easier to understand and analyze.

[0035] In summary, this application includes at least one of the following beneficial technical effects:

[0036] 1. By adopting the above technical solution, the reservoir tunnel area to be monitored is divided into several monitoring areas, which can ensure that the monitoring system can carry out refined monitoring of different areas, avoid data confusion caused by overall monitoring, and thus improve the accuracy of monitoring. By obtaining image data and camera inertial data of each monitoring area and determining the target displacement data of the corresponding monitoring area based on the image data, the displacement information of the reservoir tunnel can be obtained and analyzed in real time, avoiding data errors caused by a single measurement method, thereby improving the stability and reliability of deformation monitoring. By determining the deformation data of the corresponding monitoring area based on the target displacement data and camera inertial data, the data of visual measurement and inertial measurement can be comprehensively considered, reducing the measurement error caused by external environmental interference, thereby improving the accuracy of deformation calculation and making the monitoring results more reliable.

[0037] 2. By adopting the above technical solution, by obtaining target images and corresponding camera inertial data of different monitoring areas of the reservoir tunnel at any time and inputting them into the initial model, the initial model is trained to obtain a deformation model. This deformation calculation model has the ability to adaptively adjust. It can still maintain high calculation accuracy under different monitoring environments, different tunnel structures and different external influencing factors. It fully considers the influence of the deformation variable at different positions of the target and camera, outputs the corresponding deformation variable, and thus improves the accuracy of the deformation variable.

[0038] 3. After obtaining the deformation monitoring results, if the deviation value exceeds the preset warning threshold, the alarm mechanism will be triggered. This will immediately issue an alarm when the deformation is abnormal, thereby improving the ability to ensure the safety of the reservoir tunnel structure. By visualizing the deformation monitoring results, monitoring personnel can intuitively view the overall deformation of the reservoir tunnel and quickly identify high-risk areas, thereby improving the readability and visualization analysis capabilities of the monitoring results, making the monitoring data easier to understand and analyze. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a flow chart of an implementation method of a tunnel deformation monitoring method based on chained inertial vision measurement in one embodiment of the present application;

[0040] Figure 2 This is another implementation flow chart of a tunnel deformation monitoring method based on chained inertial vision measurement in one embodiment of the present application;

[0041] Figure 3 This is a flowchart for implementing step S20 in the tunnel deformation monitoring method based on chained inertial vision measurement in one embodiment of the present application;

[0042] Figure 4 This is a flowchart for implementing step S22 in the tunnel deformation monitoring method based on chained inertial vision measurement in one embodiment of the present application;

[0043] Figure 5 This is a flowchart for implementing step S30 in the tunnel deformation monitoring method based on chained inertial vision measurement in one embodiment of the present application;

[0044] Figure 6 This is a flowchart for implementing step S40 in the tunnel deformation monitoring method based on chained inertial vision measurement in one embodiment of the present application;

[0045] Figure 7 This is a schematic diagram of the setup of a tunnel deformation monitoring method based on chain inertial vision measurement in one embodiment of the present application. DETAILED DESCRIPTION

[0046] The following examples will help those skilled in the art further understand the purpose of this application, but are not intended to limit this application in any form. It should be noted that those skilled in the art may make several modifications and improvements without departing from the scope of this application. These modifications and improvements are all within the scope of this application.

[0047] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0048] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0049] The present application is further described in detail below with reference to the accompanying drawings.

[0050] In one embodiment, if Figure 1 As shown, the present application discloses a tunnel deformation monitoring method based on chain inertial vision measurement, which specifically includes the following steps:

[0051] S10: Divide the reservoir tunnel area to be monitored into several monitoring areas.

[0052] Specifically, the reservoir tunnel area to be monitored is divided according to its structural characteristics, length, bending conditions and monitoring needs. The division of the monitoring area can be based on established structural units, such as tunnel segments, segmental construction joints, key structural support points, etc. At the same time, the camera's field of view and installation position need to be considered to ensure that the camera can fully cover each monitoring area. The number and boundaries of the monitoring areas can be dynamically adjusted according to historical deformation conditions and structural health assessment results. After the division is completed, the number, coordinate range and corresponding camera monitoring range of each monitoring area need to be recorded in the system database to facilitate the automated execution of subsequent data collection and analysis.

[0053] For example, Figure 7 As shown, nine sections of the tunnel were selected for target installation. These sections are numbered ai. Each section defines a monitoring area, with six targets installed along the wall of each section, ensuring symmetrical and even distribution of the three targets on the left and right sides. To monitor all sections, five monitoring stations were set up in the tunnel. Each station consists of two inertial cameras facing opposite directions and a target, monitoring the targets on both sides of each station. The target installed in section c is a cooperative target. Due to field of view limitations, the targets in section c are only installed on the wall outside the curve. Since each target is only unidirectional, three targets were selected on the outer wall, each with a back-to-back installation to ensure simultaneous observation by both station 2, which is located before the curve, and station 3, which is located after the curve.

[0054] S20: Obtain image data and camera inertial data of each monitoring area, and determine target displacement data of the corresponding monitoring area based on the image data.

[0055] Specifically, during each monitoring cycle, multiple inertial cameras synchronously collect image data of each monitoring area, and the inertial measurement unit (IMU) synchronously records the camera attitude data. The image data is stored in the database through the image transmission protocol and timestamp alignment is performed to ensure that all data sources can be correctly matched and associated. The image data is then processed through the built-in algorithm to determine the displacement of the target, thereby obtaining the target displacement data of the corresponding monitoring area.

[0056] S30: Determine deformation data of the corresponding monitoring area based on the target displacement data and the camera inertia data.

[0057] Specifically, a preset calculation model is used to input the displacement data of the target corresponding to the monitoring area and the camera inertia data into the calculation model. After obtaining the target displacement data, the calculation model uses the transformation matrix to convert it into a unified global coordinate system, and combines it with the camera inertia data to calculate the displacement distribution of each target in the monitoring area, thereby outputting the deformation data of the corresponding monitoring area.

[0058] S40: generating deformation monitoring results corresponding to the monitoring area according to the deformation amount data.

[0059] Specifically, the calculated deformation variable data is compared with the baseline deformation variable data of the corresponding monitoring area, and the deformation variable growth rate is calculated based on the time series trend of the deformation variable to determine whether the deformation variable has an accelerating development trend. In the calculation process of the deformation monitoring results, different deformation variable thresholds are set, including normal state threshold, warning threshold and danger threshold, and compared with the current monitoring data. If the deformation variable data is within the normal range, it is marked as "normal"; if it exceeds the warning threshold, it is marked as "warning"; if it exceeds the danger threshold, it is marked as "abnormal".

[0060] In one embodiment, if Figure 2 As shown, the tunnel deformation monitoring method based on chain inertial vision measurement also includes:

[0061] S1: Obtain target images and corresponding camera inertial data of different monitoring areas of the reservoir tunnel at any time, wherein the camera inertial data is collected by the inertial measurement unit of the inertial camera.

[0062] Specifically, in the process of shape variable calculation, historical data is needed for model training. Therefore, it is necessary to retrieve target images at different monitoring times from the database and obtain the camera inertial data of the corresponding time points at the same time. In order to ensure the integrity of the data, the data is first aligned in time, that is, the camera image and IMU data are matched according to the timestamp, and linear interpolation or time synchronization adjustment is performed to ensure that all data points are aligned in the time dimension to ensure the accuracy of subsequent model training.

[0063] S2: Input the corresponding target image and camera inertial data into the initial model, and optimize the model parameters of the initial model through back propagation and model evaluation indicators.

[0064] Specifically, when training the deformation model, it is first necessary to extract features from the target image data and fuse them with the inertial data to form the input features of the model. During the backpropagation process, the gradient descent method is used to continuously optimize the model parameters to minimize the value of the loss function. At the same time, model evaluation indicators, such as prediction error or loss function value, are used to measure the fitting effect of the model. If the error converges to the set range, the model training is considered complete, otherwise the parameters continue to be optimized until the preset threshold is reached.

[0065] S3: When the model evaluation index reaches the preset threshold, the training of the initial model is completed and the deformable model is obtained.

[0066] Specifically, during the model training process, parameters are continuously adjusted to optimize the accuracy of the deformation model. When the model's evaluation indicators, such as the prediction error or the value of the loss function, are stable within the set threshold range and there is no obvious optimization after several consecutive rounds of iterations, the model training is considered to be completed, thereby obtaining a trained deformation model, and the deformation model is stored for subsequent deformation variable calculation and trend prediction.

[0067] In one embodiment, if Figure 3 As shown, in step S20, image data and camera inertial data of each monitoring area are obtained, and target displacement data of the corresponding monitoring area is determined based on the image data, specifically including:

[0068] S21: According to a preset time period, image data and camera inertial data of each monitoring area are collected.

[0069] Specifically, during each monitoring cycle, the inertial camera synchronous acquisition instruction is triggered, causing all cameras to acquire images according to the set sampling interval. The image data collected by each camera is automatically associated with a timestamp and stored in a database. At the same time, the inertial measurement unit (IMU) collects the camera's acceleration, pitch angle, and other attitude data for use in posture compensation in subsequent processing. After the acquisition is completed, all camera image data and inertial data are classified and stored according to the monitoring area, and a data integrity check is performed. If there is data loss, the re-acquisition mechanism is triggered, causing the camera to perform additional re-acquisition in the next time period to ensure data integrity and continuity. The inertial camera sampling frequency is set to 60Hz, the measurement synchronization error of multiple inertial cameras is 20ms, the field of view angle is 3.5°×2.7°, and the coverage range is ≤100m.

[0070] S22: Based on the image processing algorithm and the PnP algorithm, the image data is processed and the posture is calculated to obtain the target displacement data.

[0071] Specifically, the collected image data is first denoised and enhanced to improve image quality and target recognizability. Denoising can be done by Gaussian filtering or bilateral filtering, and enhancement can be done by adaptive histogram equalization for brightness equalization. Feature point detection algorithms such as SIFT, ORB, or SURF are then used to extract features of the target in the image, and the FLANN matching algorithm or optical flow method is used for target tracking to calculate the displacement of the target between adjacent frames. Then, the PnP (Perspective-n-Point) algorithm is used to solve the spatial pose change of the target based on the intrinsic and extrinsic parameters of the camera, and finally the three-dimensional displacement data of the target is obtained and converted to a unified coordinate system for subsequent deformation calculation.

[0072] In one embodiment, if Figure 4As shown, in step S22, image processing and pose calculation are performed on the image data based on the image processing algorithm and the PnP algorithm to obtain target displacement data, specifically including:

[0073] S221: Based on the image processing algorithm, target area recognition processing is performed on the image data to obtain target highlight image data.

[0074] Specifically, the target area is first identified by calibrating the target image area in advance and drawing the area of ​​interest; then the image in the area is denoised using a median filter, and the pixels within a certain neighborhood of a pixel are arranged according to the grayscale level, with the median value as the output object, thereby eliminating abnormal pixel values. Finally, the position of the maximum point of the weighted pixel value is used as the measurement target position for identification, thereby forming highlighted target image data and providing input for subsequent posture calculations.

[0075] S222: Based on the PnP algorithm, the target pose is calculated for the target highlighted image data to obtain the target displacement data.

[0076] Specifically, the PnP algorithm is used to calculate the target's pose changes. First, the target's feature points are extracted from the highlighted target image data. A matching algorithm is then used to find corresponding point pairs between adjacent frames. Then, based on the camera's intrinsic parameter matrix, distortion coefficients, and extrinsic parameters, the target's spatial pose changes are calculated to obtain the target's three-dimensional displacement data. This data is then converted to a unified coordinate system, ultimately generating target displacement data at different time points and storing it in a database for subsequent deformation calculations. Robust optimization methods can also be used for error compensation to remove anomalous data points caused by occlusion and illumination changes.

[0077] In one embodiment, if Figure 5 As shown, in step S30, the deformation data of the corresponding monitoring area is determined based on the target displacement data and the camera inertial data, specifically including:

[0078] S31: Input the target displacement data and the camera inertia data into the deformation model to obtain the deformation variable.

[0079] Specifically, during the deformation calculation process, the target displacement data and the camera inertia data are input into the deformation model. The deformation model considers the influence of the deformation at different positions of the target and the camera, and outputs the corresponding deformation.

[0080] S32: Fitting the deformation variables based on the time series filtering algorithm and the least square method to obtain deformation variable data of the corresponding monitoring area.

[0081] Specifically, after the deformation variable calculation is completed, in order to remove short-term measurement errors and data fluctuations, a time series filtering algorithm is used to smooth the data. The time series filtering uses Kalman filtering or exponentially weighted moving average method to ensure the stability of the deformation variable data. Then, the least squares method is used to fit the deformation variable curve to obtain the deformation variable data of the corresponding monitoring area.

[0082] In one embodiment, if Figure 6 As shown, in step S40, the deformation monitoring result of the corresponding monitoring area is generated according to the deformation amount data, which specifically includes:

[0083] S41: Based on the finite element analysis method, obtain the benchmark deformation data of different monitoring areas.

[0084] Specifically, in order to obtain benchmark deformation data, a finite element model of the reservoir tunnel is first established. This model takes into account factors such as material properties, boundary conditions and external loads. Then, static and dynamic analyses are performed based on the finite element model to calculate the deformation distribution under normal working conditions, thereby obtaining benchmark deformation data for different monitoring areas.

[0085] S42: Calculate the deviation between the deformation variable data of the current monitoring area and the reference deformation variable data, and generate a corresponding deformation monitoring result according to the deviation.

[0086] Specifically, by comparing the deformation data of the current monitoring area with the baseline deformation data, the deformation of the current monitoring area can be determined, thereby obtaining the deformation monitoring result. If the deformation exceeds the set threshold, it is determined that the monitoring area has abnormal deformation.

[0087] In one embodiment, after the deformation monitoring result is obtained, if the deviation value exceeds a preset warning threshold, an alarm mechanism is triggered, and the deformation monitoring result is visualized to obtain a three-dimensional deformation thermal map.

[0088] Specifically, after the deformation monitoring results are generated, if the deviation value exceeds the set threshold, the alarm mechanism is triggered. The alarm methods include real-time alarm, remote notification and automatic report generation. The real-time alarm can remind the monitoring personnel through the sound and light alarm device. The remote notification can use SMS, email or monitoring system push to send the alarm information to relevant personnel. At the same time, the deformation results are visualized using a three-dimensional deformation heat map. The three-dimensional heat map uses color to map the deformation size of different areas. Red indicates a severely deformed area, yellow indicates a warning area, and green indicates a normal area, so that the monitoring personnel can intuitively analyze the deformation situation.

[0089] 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 this application.

[0090] Those skilled in the art will clearly understand that for the sake of convenience and brevity in description, only the division of the above-mentioned functional units and modules is used as an example. 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 system can be divided into different functional units or modules to complete all or part of the functions described above.

[0091] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application 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 application, and should all be included in the scope of protection of the present application.

Claims

1. A tunnel deformation monitoring method based on chain inertial vision measurement, characterized in that: The tunnel deformation monitoring method based on chained inertial vision measurement includes: The reservoir tunnel area to be monitored is divided into a plurality of monitoring areas defined by a plurality of monitoring stations along its strike direction, wherein each of the monitoring stations is equipped with an inertial camera capable of two-way observation, and a cooperative target is set between two adjacent monitoring stations, the cooperative target being used for joint observation by the two adjacent monitoring stations; Acquire image data and camera inertial data of each monitoring area, and determine target displacement data of the corresponding monitoring area based on the image data; Determining deformation data of a corresponding monitoring area based on the target displacement data and the camera inertial data; generating a deformation monitoring result of a corresponding monitoring area according to the deformation amount data; The tunnel deformation monitoring method based on chained inertial vision measurement further includes: Obtain target images and corresponding camera inertial data of different monitoring areas of the reservoir tunnel at any time, wherein the camera inertial data is collected by the inertial measurement unit of the inertial camera; Inputting the corresponding target image and the camera inertial data into an initial model, and optimizing the model parameters of the initial model through back propagation and model evaluation indicators; When the model evaluation index reaches a preset threshold, the training of the initial model is completed to obtain a deformable model.

2. The tunnel deformation monitoring method based on chained inertial vision measurement according to claim 1 is characterized in that: The acquiring of image data and camera inertial data of each monitoring area, and determining target displacement data of the corresponding monitoring area based on the image data, specifically includes: According to the preset time period, the image data and camera inertial data of each monitoring area are collected; Based on the image processing algorithm and the PnP algorithm, the image data is processed and the posture calculation is performed to obtain the target displacement data.

3. The tunnel deformation monitoring method based on chained inertial vision measurement according to claim 2 is characterized in that: The image processing and pose calculation are performed on the image data based on the image processing algorithm and the PnP algorithm to obtain the target displacement data, specifically including: Based on the image processing algorithm, target area recognition processing is performed on the image data to obtain target highlight image data; Based on the PnP algorithm, the target pose is calculated for the target highlighted image data to obtain the target displacement data.

4. The tunnel deformation monitoring method based on chained inertial vision measurement according to claim 1 is characterized in that: The determining of deformation data of a corresponding monitoring area based on the target displacement data and the camera inertial data specifically includes: Inputting the target displacement data and the camera inertia data into the deformation model to obtain a deformation variable; The deformation variables are fitted based on a time series filtering algorithm and a least square method to obtain deformation variable data of the corresponding monitoring area.

5. The tunnel deformation monitoring method based on chained inertial vision measurement according to claim 4 is characterized in that: Generating a deformation monitoring result corresponding to the monitoring area according to the deformation amount data specifically includes: Based on the finite element analysis method, the benchmark deformation data of different monitoring areas are obtained; The deviation value between the deformation variable data of the current monitoring area and the reference deformation variable data is calculated, and the corresponding deformation monitoring result is generated according to the deviation value.

6. The tunnel deformation monitoring method based on chained inertial vision measurement according to claim 5 is characterized in that: After the deformation monitoring result is obtained, if the deviation value exceeds a preset warning threshold, an alarm mechanism is triggered, and the deformation monitoring result is visualized to obtain a three-dimensional deformation thermodynamic map.

Images