Tunnel deformation monitoring method and system based on computer vision

Abstract

The invention relates to the technical field of tunnel deformation monitoring, and discloses a tunnel deformation monitoring method and system based on computer vision, and the system comprises a determination module which is configured to determine the initial shooting frequency of a high-definition industrial camera based on basic parameters; the primary judgment module is configured to judge whether deformation exists in the monitoring area or not based on the analysis result; the secondary judgment module is configured to judge whether to adjust the initial shooting frequency or not according to the initial deformation characteristic value; the processing module is configured to analyze the deformation relevance of all the monitoring areas in the edge range, determine the adjustment coefficient of the initial shooting frequency based on the deformation relevance and obtain the final shooting frequency; and the grading module is configured to determine the deformation grade of the tunnel to be monitored according to the final deformation characteristic value. According to the invention, real-time monitoring of tunnel deformation is realized, and the monitoring precision is high.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tunnel deformation monitoring, in particular to a tunnel deformation monitoring method and system based on computer vision. BACKGROUND

[0002] With the rapid development and continuous progress of modern transportation industry, as a key infrastructure connecting various places and ensuring smooth traffic operation, the safety performance and structural stability of tunnels in the actual use process have attracted widespread attention from all sectors of society. In order to ensure that the tunnel can serve the transportation system for a long time and safely, it is particularly important to accurately and effectively monitor its deformation. However, the traditional tunnel deformation monitoring method often relies on manual operation, which requires professional technicians to regularly go to the site for on-site measurement and data collection. This monitoring method not only consumes a lot of human resources and increases the work intensity, but also inevitably has a large measurement error due to human factors and equipment limitations, which is difficult to meet the current high-standard and high-precision monitoring requirements.

[0003] Therefore, it is necessary to design a tunnel deformation monitoring method and system based on computer vision to solve the problems existing in the current technology. SUMMARY

[0004] In view of this, the present application provides a tunnel deformation monitoring method and system based on computer vision, which aims to meet the current high-standard and high-precision monitoring requirements.

[0005] In one aspect, the present application provides a tunnel deformation monitoring system based on computer vision, comprising:

[0006] A determination module is configured to determine a tunnel to be monitored, divide the tunnel to be monitored into regions, and obtain a plurality of monitoring regions; a high-definition industrial camera is erected in each monitoring region, basic parameters of each monitoring region are collected, and an initial shooting frequency of the high-definition industrial camera is determined based on the basic parameters;

[0007] A primary judgment module is configured to collect initial regional image data of each monitoring region at the initial shooting frequency within a preset time interval, analyze the initial regional image data, and determine whether the monitoring region has deformation based on the analysis result;

[0008] A secondary judgment module is configured to obtain an initial deformation characteristic value of the monitoring region when it is determined that the monitoring region has deformation, and determine whether to adjust the initial shooting frequency according to the initial deformation characteristic value;

[0009] a processing module configured to, when determining to adjust the initial shooting frequency, determine an edge range with a geometric center of the monitoring area as a center and k as a radius, analyze deformation relevance of all the monitoring areas located in the edge range, determine an adjustment coefficient of the initial shooting frequency based on the deformation relevance, and obtain a final shooting frequency;

[0010] a grading module configured to, within a preset time interval, collect final regional image data of each monitoring area at the final shooting frequency, analyze all the final regional image data, and obtain a final deformation characteristic value of the tunnel to be monitored; and determine a deformation grade of the tunnel to be monitored according to the final deformation characteristic value.

[0011] Further, when determining the initial shooting frequency of the high-definition industrial camera based on the basic parameters, the method comprises:

[0012] analyzing the basic parameters to obtain a monitoring area, an importance degree, and an actual distance of the high-definition industrial camera to the monitoring area of the monitoring area;

[0013] determining a basic shooting frequency of the high-definition industrial camera according to the importance degree;

[0014] determining an optimization coefficient of the basic shooting frequency according to the monitoring area and the actual distance;

[0015] multiplying the optimization coefficient and the basic shooting frequency to obtain the initial shooting frequency.

[0016] Further, when determining the basic shooting frequency of the high-definition industrial camera according to the importance degree, the method comprises:

[0017] the importance degree comprises a high level, a medium level, and a low level;

[0018] when the importance degree is the high level, determining the basic shooting frequency as a first shooting frequency;

[0019] when the importance degree is the medium level, determining the basic shooting frequency as a second shooting frequency, the second shooting frequency being lower than the first shooting frequency;

[0020] when the importance degree is the low level, determining the basic shooting frequency as a third shooting frequency, the third shooting frequency being lower than the second shooting frequency.

[0021] Further, when determining the optimization coefficient of the basic shooting frequency according to the monitoring area and the actual distance, the method comprises:

[0022] respectively, and comparing the actual distance with an actual distance threshold value, and determining the optimization coefficient according to the comparison results;

[0023] When the monitoring area is greater than or equal to the monitoring area threshold value, and the actual distance is greater than or equal to the actual distance threshold value, the optimization coefficient is determined as a first optimization coefficient;

[0024] When the monitoring area is greater than or equal to the monitoring area threshold value, and the actual distance is less than the actual distance threshold value, the optimization coefficient is determined as a second optimization coefficient;

[0025] When the monitoring area is less than the monitoring area threshold value, and the actual distance is greater than or equal to the actual distance threshold value, the optimization coefficient is determined as a third optimization coefficient;

[0026] When the monitoring area is less than the monitoring area threshold value, and the actual distance is less than the actual distance threshold value, the optimization coefficient is determined as a fourth optimization coefficient.

[0027] Further, when analyzing the initial regional image data and judging whether the monitoring area has deformation based on the analysis result, the method comprises:

[0028] Analyzing the initial regional image data to obtain deformation parameters of the monitoring area, wherein the deformation parameters comprise displacement, strain value and inclination angle;

[0029] Comparing the deformation parameters with a preset deformation threshold value, and if any one or more of the deformation parameters exceeds the deformation threshold value, it is determined that the monitoring area has deformation;

[0030] Otherwise, it is determined that the monitoring area has no deformation.

[0031] Further, when judging whether to adjust the initial shooting frequency according to the initial deformation characteristic value, the method comprises:

[0032] Comparing the initial deformation characteristic value with a deformation standard value, and judging whether to adjust the initial shooting frequency according to the comparison result;

[0033] When the initial deformation characteristic value is greater than or equal to the deformation standard value, it is determined to adjust the initial shooting frequency;

[0034] Otherwise, it is determined not to adjust the initial shooting frequency.

[0035] Further, when analyzing the deformation correlation of all the monitoring areas located in the edge range, the method comprises:

[0036] comparing the deformation characteristic values of all the monitoring areas within the edge range to determine deformation difference between adjacent monitoring areas;

[0037] calculating deformation correlation coefficients between the monitoring areas according to the deformation difference;

[0038] determining the deformation correlation according to the deformation correlation coefficients.

[0039] Further, when determining the adjustment coefficient of the initial shooting frequency based on the deformation correlation and obtaining the final shooting frequency, the method comprises:

[0040] comparing the deformation correlation with a preset correlation threshold to determine a correlation strength level;

[0041] determining the adjustment coefficient of the initial shooting frequency according to the correlation strength level;

[0042] multiplying the adjustment coefficient and the initial shooting frequency to obtain the final shooting frequency.

[0043] Further, when determining the deformation level of the tunnel to be monitored according to the final deformation characteristic value, the method comprises:

[0044] comparing the final deformation characteristic value with a first deformation value and a second deformation value, and determining the deformation level of the tunnel to be monitored according to the comparison result; wherein the first deformation value is less than the second deformation value;

[0045] when the final deformation characteristic value is less than or equal to the first deformation value, determining that the deformation level of the tunnel to be monitored is a first level;

[0046] when the final deformation characteristic value is greater than the first deformation value and less than or equal to the second deformation value, determining that the deformation level is a second level;

[0047] when the final deformation characteristic value is greater than the second deformation value, determining that the deformation level is a third level.

[0048] Compared with the prior art, the tunnel deformation monitoring system based on computer vision has the advantages that the tunnel deformation monitoring system based on computer vision can realize real-time monitoring of tunnel deformation and has high monitoring precision. The tunnel is divided into regions, and a high-definition industrial camera is erected in each monitoring region, so that comprehensive monitoring of each region of the tunnel can be realized. Meanwhile, the initial shooting frequency of the high-definition industrial camera is determined according to the basic parameters of the monitoring region, so that unnecessary shooting can be reduced while the monitoring precision is ensured, and the efficiency is improved. When it is preliminarily judged that the monitoring region has deformation, the initial deformation characteristic value is further obtained, and whether the initial shooting frequency is adjusted is judged according to the initial deformation characteristic value, so that the deformation condition can be accurately captured. In addition, by analyzing the deformation correlation of all the monitoring regions located in the edge range, the adjustment coefficient of the initial shooting frequency can be more accurately determined, so that a more suitable final shooting frequency can be obtained. Finally, the deformation grade of the tunnel to be monitored is determined according to the final deformation characteristic value, which provides an important basis for the maintenance and management of the tunnel.

[0049] In another aspect, the application further provides a tunnel deformation monitoring method based on computer vision, comprising the following steps:

[0050] A tunnel to be monitored is determined, and the tunnel to be monitored is divided into regions to obtain a plurality of monitoring regions;

[0051] A high-definition industrial camera is erected in each monitoring region, and the basic parameters of each monitoring region are collected, and the initial shooting frequency of the high-definition industrial camera is determined based on the basic parameters;

[0052] In a preset time interval, the initial regional image data of each monitoring region is collected at the initial shooting frequency, and the initial regional image data is analyzed, and whether the monitoring region has deformation is judged based on the analysis result;

[0053] When it is judged that the monitoring region has deformation, the initial deformation characteristic value of the monitoring region is obtained, and whether the initial shooting frequency is adjusted is judged according to the initial deformation characteristic value;

[0054] When it is judged that the initial shooting frequency is adjusted, the edge range is determined with the geometric center of the monitoring region as the center and k as the radius, the deformation correlation of all the monitoring regions located in the edge range is analyzed, the adjustment coefficient of the initial shooting frequency is determined based on the deformation correlation, and the final shooting frequency is obtained;

[0055] In a preset time interval, the final regional image data of each monitoring region is collected at the final shooting frequency, and all the final regional image data is analyzed to obtain the final deformation characteristic value of the tunnel to be monitored;

[0056] determine a deformation level of the tunnel to be monitored according to the final deformation characteristic value.

[0057] It can be understood that the computer vision-based tunnel deformation monitoring method and system have the same beneficial effects, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0058] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are included to provide a description of preferred embodiments, and are not meant to limit the present application. Furthermore, the same reference numerals are used throughout the several views of the drawings to designate the same or similar parts. In the drawings:

[0059] Figure 1 a structural block diagram of a computer vision-based tunnel deformation monitoring system provided by an embodiment of the present application;

[0060] Figure 2 a flowchart of a computer vision-based tunnel deformation monitoring method provided by an embodiment of the present application. DETAILED DESCRIPTION

[0061] Exemplary embodiments of the present disclosure will be described in detail with reference to the drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be accurately conveyed to those skilled in the art. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0062] Referring to Figure 1 As shown in the drawings, in some embodiments of the present application, the present embodiment provides a computer vision-based tunnel deformation monitoring system, comprising:

[0063] A determination module is configured to determine a tunnel to be monitored, divide the tunnel to be monitored into regions, and obtain a plurality of monitoring regions; erect a high-definition industrial camera in each monitoring region, collect basic parameters of each monitoring region, determine an initial shooting frequency of the high-definition industrial camera based on the basic parameters;

[0064] A primary judgment module is configured to collect initial regional image data of each monitoring region at the initial shooting frequency within a preset time interval, analyze the initial regional image data, and determine whether the monitoring region has deformation based on the analysis result;

[0065] The secondary judgment module is configured to, when judging that the deformation exists in the monitoring area, acquire an initial deformation characteristic value of the monitoring area, and judge whether to adjust the initial shooting frequency according to the initial deformation characteristic value;

[0066] The processing module is configured to, when judging that the initial shooting frequency is adjusted, determine an edge range with the geometric center of the monitoring area as a center and k as a radius, analyze deformation correlation of all the monitoring areas located in the edge range, determine an adjustment coefficient of the initial shooting frequency based on the deformation correlation, and acquire a final shooting frequency;

[0067] The grading module is configured to, within a preset time interval, acquire final area image data of each monitoring area at the final shooting frequency, analyze all the final area image data, acquire a final deformation characteristic value of the tunnel to be monitored, and determine a deformation grade of the tunnel to be monitored according to the final deformation characteristic value.

[0068] In the embodiment, k is preferably one-tenth of the length of the tunnel, so as to ensure that the deformation of the tunnel can be comprehensively and accurately captured.

[0069] It can be understood that the tunnel deformation monitoring system based on computer vision provided in the embodiment can realize real-time monitoring of the deformation of the tunnel and has high monitoring accuracy. Through the division of the tunnel into monitoring areas and the erection of high-definition industrial cameras in each monitoring area, comprehensive monitoring of each area of the tunnel can be realized. Meanwhile, the initial shooting frequency of the high-definition industrial camera is determined according to the basic parameters of the monitoring area, so as to reduce unnecessary shooting and improve efficiency while ensuring the monitoring accuracy. When it is preliminarily judged that the deformation exists in the monitoring area, the initial deformation characteristic value is further acquired, and it is judged whether to adjust the initial shooting frequency according to the initial deformation characteristic value, so as to ensure that the deformation can be accurately captured. In addition, by analyzing the deformation correlation of all the monitoring areas located in the edge range, the adjustment coefficient of the initial shooting frequency can be more accurately determined, so that a more suitable final shooting frequency is obtained. Finally, the deformation grade of the tunnel to be monitored is determined according to the final deformation characteristic value, which provides an important basis for the maintenance and management of the tunnel.

[0070] Specifically, when the basic parameters of each monitoring area are acquired and the initial shooting frequency of the high-definition industrial camera is determined based on the basic parameters, the following steps are included:

[0071] The basic parameters are analyzed to acquire the monitoring area, the importance degree and the actual distance of the high-definition industrial camera to the monitoring area;

[0072] The basic shooting frequency of the high-definition industrial camera is determined according to the importance degree;

[0073] determining an optimization coefficient of the basic shooting frequency according to the monitoring area and the actual distance;

[0074] multiplying the optimization coefficient by the basic shooting frequency to obtain the initial shooting frequency.

[0075] It can be understood that the higher the importance of the monitoring area, the higher the basic shooting frequency is set to ensure more frequent monitoring of the area. The larger the monitoring area or the farther the actual distance from the high-definition industrial camera to the monitoring area, the higher the optimization coefficient is set to increase the shooting frequency to capture more detail changes. Such a design can flexibly adjust the shooting frequency of the high-definition industrial camera according to actual monitoring needs, ensuring the comprehensiveness of monitoring and improving monitoring efficiency. At the same time, by optimizing the initial shooting frequency, the service life of the high-definition industrial camera can be extended to a certain extent, and the monitoring cost can be reduced.

[0076] Specifically, when determining the basic shooting frequency of the high-definition industrial camera according to the importance, the method comprises:

[0077] The importance includes a high level, a medium level and a low level;

[0078] When the importance is the high level, the basic shooting frequency is determined as a first shooting frequency;

[0079] When the importance is the medium level, the basic shooting frequency is determined as a second shooting frequency, and the second shooting frequency is lower than the first shooting frequency;

[0080] When the importance is the low level, the basic shooting frequency is determined as a third shooting frequency, and the third shooting frequency is lower than the second shooting frequency.

[0081] It can be understood that by setting different basic shooting frequencies for monitoring areas of different importance, monitoring resources can be more reasonably allocated. For areas of higher importance, such as key structural parts of tunnels or areas with a larger history of deformation, a higher shooting frequency is used to timely discover and respond to deformation conditions to ensure the safety of the tunnel. For areas of lower importance, the shooting frequency is appropriately reduced to ensure a certain monitoring accuracy while reducing data volume and processing burden, improving the overall efficiency of the system.

[0082] Specifically, when determining the optimization coefficient of the basic shooting frequency according to the monitoring area and the actual distance, the method comprises:

[0083] respectively comparing the monitoring area with a monitoring area threshold and comparing the actual distance with an actual distance threshold, and determining the optimization coefficient according to the comparison results.

[0084] determining the optimization coefficient as a first optimization coefficient when the monitoring area is greater than or equal to the monitoring area threshold and the actual distance is greater than or equal to the actual distance threshold;

[0085] determining the optimization coefficient as a second optimization coefficient when the monitoring area is greater than or equal to the monitoring area threshold and the actual distance is less than the actual distance threshold;

[0086] determining the optimization coefficient as a third optimization coefficient when the monitoring area is less than the monitoring area threshold and the actual distance is greater than or equal to the actual distance threshold;

[0087] determining the optimization coefficient as a fourth optimization coefficient when the monitoring area is less than the monitoring area threshold and the actual distance is less than the actual distance threshold.

[0088] It can be understood that the first optimization coefficient is preferably the highest value to ensure that more detail changes can be captured in the case of a large monitoring area and a long distance. The second optimization coefficient is slightly lower than the first optimization coefficient and is suitable for the case of a large monitoring area and a short distance. Although the distance is short, the monitoring area is large, so a relatively high shooting frequency is still needed. The third optimization coefficient is suitable for the case of a small monitoring area and a long distance. Since the distance is long, the shooting frequency needs to be increased to capture details, but the monitoring area is small, so the frequency can be relatively low. The fourth optimization coefficient is the lowest value and is suitable for the case of a small monitoring area and a short distance. At this time, the detail changes are easy to capture, and the shooting frequency can be appropriately reduced. Through such optimization coefficient setting, the shooting frequency of the high-definition industrial camera can be adjusted more finely, ensuring the comprehensiveness and accuracy of monitoring and improving the overall efficiency of the system.

[0089] Specifically, when the initial area image data is analyzed and it is determined whether the monitoring area is deformed based on the analysis result, the method comprises:

[0090] analyzing the initial area image data to obtain deformation parameters of the monitoring area, the deformation parameters comprising displacement, strain value and inclination angle;

[0091] comparing the deformation parameters with a preset deformation threshold, and if any one or more of the deformation parameters exceeds the deformation threshold, it is determined that the monitoring area is deformed;

[0092] otherwise, it is determined that the monitoring area is not deformed.

[0093] It can be understood that the deformation parameters are obtained by analyzing the initial area image data by using an image processing tool. The image processing tool can identify feature points in the image and calculate displacement, strain value and inclination angle and other deformation parameters based on the changes of the feature points. These deformation parameters can directly reflect the deformation of the monitoring area. If any one or more of the deformation parameters exceeds the deformation threshold, it means that there may be a safety hazard in the monitoring area, and further monitoring and analysis need to be carried out in time. Such a design can realize rapid response to tunnel deformation and provide strong support for the maintenance and management of the tunnel.

[0094] Specifically, when judging whether to adjust the initial shooting frequency according to the initial deformation characteristic value, the method comprises:

[0095] comparing the initial deformation characteristic value with a deformation standard value, and judging whether to adjust the initial shooting frequency according to the comparison result;

[0096] when the initial deformation characteristic value is greater than or equal to the deformation standard value, it is determined to adjust the initial shooting frequency;

[0097] otherwise, it is determined not to adjust the initial shooting frequency.

[0098] In the embodiment, the initial deformation characteristic value is preferably one of the average value or the maximum value of the displacement, the strain value and the inclination angle.

[0099] It can be understood that when the initial deformation characteristic value reaches or exceeds the preset deformation standard value, it means that the deformation of the monitoring area may be more serious, and more intensive monitoring is needed to capture the deformation details, so the initial shooting frequency needs to be adjusted to improve the accuracy and timeliness of the monitoring.

[0100] Specifically, when analyzing the deformation correlation of all the monitoring areas located in the edge range, the method comprises:

[0101] comparing the deformation characteristic values of all the monitoring areas located in the edge range to determine the deformation difference degree between adjacent monitoring areas;

[0102] calculating the deformation correlation coefficient between the monitoring areas according to the deformation difference degree;

[0103] determining the deformation correlation according to the deformation correlation coefficient.

[0104] It can be understood that in the process of calculating the deformation correlation coefficient, first, the deformation characteristic values of all monitoring areas located in the edge range are obtained, and the deformation difference degrees between any two adjacent monitoring areas are compared to obtain the deformation difference degrees. The deformation difference degree can be represented as the absolute value or weighted distance of the displacement amount difference, strain value difference or inclination angle difference between adjacent areas. Then, based on the set of deformation difference degrees of all adjacent areas, the deformation correlation coefficient is calculated using the normalized average or correlation function model. Specifically, the deformation correlation coefficient can be calculated by the following formula:

[0105]

[0106] Wherein, p represents the deformation correlation coefficient, the value range is [0, 1]; Δi is the deformation difference degree of the ith pair of adjacent monitoring areas, n is the total number of adjacent area pairs in the edge range, and θ is the preset maximum allowable deformation difference threshold.

[0107] It can be understood that when the deformation correlation coefficient is used to determine the deformation correlation, if the deformation correlation coefficient p is close to 1, it means that the deformation of the monitoring areas located in the edge range is highly consistent, and the deformation correlation is strong. This may mean that these areas are jointly affected by some external factors or internal stress, resulting in similar deformation patterns. At this time, the system can further analyze the reasons for these common deformations to provide more specific guidance for the maintenance and management of the tunnel. On the contrary, if the deformation correlation coefficient p is low, close to 0, it means that the deformation of the monitoring areas located in the edge range is quite different, and the deformation correlation is weak. This may mean that the deformation of these areas is caused by different factors or stress, or the deformation is unevenly distributed in space. For this case, the system needs to analyze each monitoring area in depth to determine the specific deformation reason and take corresponding maintenance measures.

[0108] In this embodiment, each deformation correlation coefficient corresponds to a deformation correlation, for example, when the deformation correlation coefficient is 0.3, the deformation correlation is determined to be 30; when the deformation correlation coefficient is 0.5, the deformation correlation is determined to be 50.

[0109] Specifically, when the deformation correlation is used to determine the adjustment coefficient of the initial shooting frequency and obtain the final shooting frequency, it includes:

[0110] Comparing the deformation correlation with the preset correlation threshold to determine the correlation strength level;

[0111] Determining the adjustment coefficient of the initial shooting frequency according to the correlation strength level;

[0112] The product value of the adjustment coefficient and the initial shooting frequency is taken as the final shooting frequency.

[0113] It can be understood that the stronger the deformation correlation is, the more similar the deformation conditions between the monitoring areas are, and more intensive monitoring may be needed to capture potential deformation details, so the adjustment coefficient can be set relatively high. Conversely, when the deformation correlation is weak, the adjustment coefficient can be set relatively low, because the deformation conditions of each monitoring area can be relatively independent, and intensive monitoring is not needed. Through such adjustment coefficient setting, monitoring resources can be more reasonably allocated, ensuring the comprehensiveness and accuracy of monitoring, and avoiding unnecessary resource waste.

[0114] Specifically, when determining the deformation level of the tunnel to be monitored according to the final deformation characteristic value, the method comprises:

[0115] comparing the final deformation characteristic value with a first deformation value and a second deformation value, and determining the deformation level of the tunnel to be monitored according to the comparison result; wherein the first deformation value is less than the second deformation value;

[0116] when the final deformation characteristic value is less than or equal to the first deformation value, it is determined that the deformation level of the tunnel to be monitored is a first level;

[0117] when the final deformation characteristic value is greater than the first deformation value and less than or equal to the second deformation value, it is determined that the deformation level is a second level;

[0118] when the final deformation characteristic value is greater than the second deformation value, it is determined that the deformation level is a third level.

[0119] In this embodiment, the final deformation characteristic value is obtained by analyzing all final area image data and performing weighted summation on all obtained deformation characteristic values.

[0120] In this embodiment, the deformation characteristic value is preferably a comprehensive evaluation value obtained by normalizing displacement, strain value and inclination angle and performing weighted summation, which can comprehensively reflect the deformation condition of the tunnel.

[0121] It can be understood that the first level represents that the tunnel deformation is slight, there may be some slight deformation or displacement, but it will not have a significant impact on the structure and safety of the tunnel. At this time, it can be recommended to take routine maintenance and monitoring measures to ensure the normal operation of the tunnel. The second level represents that the tunnel deformation is moderate, which may have caused some impact on the structure of the tunnel, but has not reached a dangerous level. For this case, it is necessary to strengthen the monitoring and analysis of the tunnel, and take appropriate maintenance measures in time to prevent the deformation from further developing. The third level is the most serious level, which represents that the tunnel deformation is serious, which may pose a serious threat to the structure and safety of the tunnel. At this time, emergency measures need to be taken immediately to conduct a comprehensive inspection and repair of the tunnel to ensure the safety and stable operation of the tunnel. Through such classification of deformation levels, more specific and targeted guidance can be provided for the maintenance and management of the tunnel to ensure the safety and reliability of the tunnel.

[0122] Referring to Figure 2 In some embodiments of the present application, the present embodiment provides a computer vision-based tunnel deformation monitoring method, comprising the following steps:

[0123] S100: determining a tunnel to be monitored, dividing the tunnel to be monitored into regions, and obtaining a plurality of monitoring regions;

[0124] S200: erecting a high-definition industrial camera in each of the monitoring regions, collecting basic parameters of each of the monitoring regions, determining an initial shooting frequency of the high-definition industrial camera based on the basic parameters;

[0125] S300: collecting initial regional image data of each of the monitoring regions at the initial shooting frequency within a preset time interval, and analyzing the initial regional image data, judging whether there is deformation in the monitoring region based on the analysis result;

[0126] S400: when it is determined that there is deformation in the monitoring region, obtaining an initial deformation characteristic value of the monitoring region, and determining whether to adjust the initial shooting frequency according to the initial deformation characteristic value;

[0127] S500: when it is determined to adjust the initial shooting frequency, determining an edge range with the geometric center of the monitoring region as the center and k as the radius, analyzing the deformation correlation of all the monitoring regions located in the edge range, determining an adjustment coefficient of the initial shooting frequency based on the deformation correlation, and obtaining a final shooting frequency;

[0128] S600: collecting final regional image data of each of the monitoring regions at the final shooting frequency within a preset time interval, and analyzing all the final regional image data, obtaining a final deformation characteristic value of the tunnel to be monitored;

[0129] S700: determining the deformation level of the tunnel to be monitored according to the final deformation characteristic value.

[0130] Those skilled in the art will understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0131] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams can be realized by computer program instructions, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the functions specified in the flow(s) or block(s).

[0132] These computer program instructions can also be stored in a computer-readable memory capable of guiding the computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction means, which implements the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the functions specified in the flow(s) or block(s).

[0133] These computer program instructions can also be loaded into a computer or other programmable data processing device, so that a series of operation steps are performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide a process for implementing the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the functions specified in the flow(s) or block(s).

[0134] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application but not to limit it. Although the present application has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that the specific embodiments of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and any modification or equivalent replacement without departing from the spirit and scope of the present application should be covered in the protection scope of the claims of the present application.

Claims

1. A tunnel deformation monitoring system based on computer vision, characterized in that, include: The determination module is configured to determine the tunnel to be monitored, divide the tunnel to be monitored into regions, and obtain several monitoring regions; A high-definition industrial camera is installed in each of the monitoring areas to collect basic parameters of each monitoring area, and the initial shooting frequency of the high-definition industrial camera is determined based on the basic parameters. The primary judgment module is configured to acquire initial area image data of each monitoring area at the initial shooting frequency within a preset time interval, analyze the initial area image data, and determine whether the monitoring area has deformation based on the analysis result. The secondary judgment module is configured to, when it is determined that there is deformation in the monitoring area, obtain the initial deformation feature value of the monitoring area, and determine whether to adjust the initial shooting frequency based on the initial deformation feature value; The processing module is configured to, when it is determined that the initial shooting frequency needs to be adjusted, determine the edge range with the geometric center of the monitoring area as the center and k as the radius, analyze the deformation correlation of all monitoring areas within the edge range, determine the adjustment coefficient of the initial shooting frequency based on the deformation correlation, and obtain the final shooting frequency. The grading module is configured to acquire final area image data of each monitoring area at the final shooting frequency within a preset time interval, and to analyze all the final area image data to obtain the final deformation feature value of the tunnel to be monitored. The deformation level of the tunnel to be monitored is determined based on the final deformation characteristic value.

2. The tunnel deformation monitoring system based on computer vision according to claim 1, characterized in that, When collecting basic parameters for each monitoring area and determining the initial shooting frequency of the high-definition industrial camera based on the basic parameters, the process includes: The basic parameters are analyzed to obtain the monitoring area, importance, and actual distance from the high-definition industrial camera to the monitoring area. The basic shooting frequency of the high-definition industrial camera is determined based on the degree of importance. The optimization coefficient of the basic shooting frequency is determined based on the monitored area and the actual distance; The product of the optimization coefficient and the base shooting frequency is used as the initial shooting frequency.

3. The tunnel deformation monitoring system based on computer vision according to claim 2, characterized in that, When determining the base shooting frequency of the high-definition industrial camera based on the aforementioned importance, the following are included: The level of importance is categorized into high, medium, and low. When the importance level is high, the basic shooting frequency is determined to be the first shooting frequency; When the importance level is medium, the base shooting frequency is determined to be the second shooting frequency, which is lower than the first shooting frequency. When the importance level is low, the base shooting frequency is determined to be the third shooting frequency, which is lower than the second shooting frequency.

4. The tunnel deformation monitoring system based on computer vision according to claim 3, characterized in that, When determining the optimization coefficient of the basic shooting frequency based on the monitored area and the actual distance, the following are included: The monitored area is compared with the monitored area threshold, and the actual distance is compared with the actual distance threshold. The optimization coefficient is determined based on the comparison results. When the monitored area is greater than or equal to the monitored area threshold, and the actual distance is greater than or equal to the actual distance threshold, the optimization coefficient is determined to be the first optimization coefficient. When the monitored area is greater than or equal to the monitored area threshold, and the actual distance is less than the actual distance threshold, the optimization coefficient is determined to be the second optimization coefficient. When the monitored area is less than the monitored area threshold and the actual distance is greater than or equal to the actual distance threshold, the optimization coefficient is determined to be the third optimization coefficient. When the monitored area is less than the monitored area threshold and the actual distance is less than the actual distance threshold, the optimization coefficient is determined to be the fourth optimization coefficient.

5. The tunnel deformation monitoring system based on computer vision according to claim 4, characterized in that, When analyzing the initial region image data and determining whether deformation exists in the monitored region based on the analysis results, the process includes: The initial region image data is analyzed to obtain the deformation parameters of the monitored region, including displacement, strain value and tilt angle. The deformation parameters are compared with a preset deformation threshold. If any one or more of the deformation parameters exceed the deformation threshold, it is determined that the monitoring area is deformed. Otherwise, it is determined that there is no deformation in the monitored area.

6. The tunnel deformation monitoring system based on computer vision according to claim 5, characterized in that, When determining whether to adjust the initial shooting frequency based on the initial deformation feature value, the following are included: The initial deformation feature value is compared with the deformation standard value, and the initial shooting frequency is adjusted based on the comparison result. When the initial deformation feature value is greater than or equal to the deformation standard value, it is determined that the initial shooting frequency should be adjusted. Otherwise, it is determined that the initial shooting frequency will not be adjusted.

7. The tunnel deformation monitoring system based on computer vision according to claim 6, characterized in that, When analyzing the deformation correlation of all monitored areas within the said edge range, the following is included: The deformation characteristic values ​​of all monitoring areas within the edge range are compared to determine the deformation difference between adjacent monitoring areas. Based on the deformation difference, calculate the deformation correlation coefficient between the monitoring areas; The deformation correlation is determined based on the deformation correlation coefficient.

8. The tunnel deformation monitoring system based on computer vision according to claim 7, characterized in that, When determining the adjustment coefficient of the initial shooting frequency based on the deformation correlation and obtaining the final shooting frequency, the process includes: The deformation correlation is compared with a preset correlation threshold to determine the correlation strength level. The adjustment coefficient for the initial shooting frequency is determined based on the correlation strength level. The product of the adjustment coefficient and the initial shooting frequency is taken as the final shooting frequency.

9. The tunnel deformation monitoring system based on computer vision according to claim 8, characterized in that, Determining the deformation level of the tunnel to be monitored based on the final deformation characteristic value includes: The final deformation characteristic value is compared with the first deformation value and the second deformation value, and the deformation level of the tunnel to be monitored is determined according to the comparison result; wherein, the first deformation value is less than the second deformation value; When the final deformation characteristic value is less than or equal to the first deformation value, the deformation level of the tunnel to be monitored is determined to be the first level. When the final deformation characteristic value is greater than the first deformation value and less than or equal to the second deformation value, the deformation level is determined to be the second level. When the final deformation characteristic value is greater than the second deformation value, the deformation level is determined to be the third level.

10. A computer vision-based tunnel deformation monitoring method, applied to the computer vision-based tunnel deformation monitoring system as described in any one of claims 1-9, characterized in that, include: The tunnel to be monitored is identified, and the tunnel to be monitored is divided into regions to obtain several monitoring areas; A high-definition industrial camera is installed in each of the monitoring areas to collect basic parameters of each monitoring area, and the initial shooting frequency of the high-definition industrial camera is determined based on the basic parameters. Within a preset time interval, initial area image data of each monitoring area is acquired at the initial shooting frequency, and the initial area image data is analyzed to determine whether there is deformation in the monitoring area based on the analysis results. When it is determined that there is deformation in the monitoring area, the initial deformation feature value of the monitoring area is obtained, and it is determined whether to adjust the initial shooting frequency based on the initial deformation feature value; When it is determined that the initial shooting frequency needs to be adjusted, the edge range is determined with the geometric center of the monitoring area as the center and k as the radius. The deformation correlation of all monitoring areas within the edge range is analyzed. Based on the deformation correlation, the adjustment coefficient of the initial shooting frequency is determined, and the final shooting frequency is obtained. Within a preset time interval, final area image data of each monitoring area is acquired at the final shooting frequency, and all the final area image data are analyzed to obtain the final deformation characteristic value of the tunnel to be monitored. The deformation level of the tunnel to be monitored is determined based on the final deformation characteristic value.

Images