Tunnel section contour extraction and analysis method and system

Abstract

The invention discloses a tunnel section contour extraction and analysis method and system, and relates to the technical field of tunnel section analysis, and the method comprises the steps: collecting and processing a tunnel section image through an image collection and processing module to obtain a comprehensive tunnel section image quality coefficient, determining whether the image can be subjected to contour extraction, and if not, carrying out the collection again; if yes, a section contour binary image is acquired through a contour extraction module, then section point cloud related data is acquired through a data acquisition module, and the section point cloud related data is processed and calculated through a data processing module to obtain a tunnel deformation index coefficient; a section deformation index target value is set through a deformation analysis module, an optimization degree proportion of the section deformation index target value is calculated, a deformation grade is determined based on an evaluation result after the proportion is evaluated, and then maintenance instructions of different grades are issued to an executor through a control center according to the deformation grade. The function of tunnel deformation analysis according to the tunnel section contour image after the tunnel section contour is extracted is realized.

Description

Technical Field

[0001] The invention relates to the technical field of tunnel section analysis, and in particular to a tunnel section profile extraction and analysis method and system. Background Art

[0002] With the continuous development of cities, the pressure on ground road traffic is increasing. In order to reduce the pressure on ground traffic, the application of subways is becoming more and more extensive. At the same time, the subway's convenience, speed, and high capacity make it one of the most popular public transportation. However, on the one hand, with the long-term use of subway tunnels, the tunnels will inevitably have problems such as aging and deformation; on the other hand, new buildings near subway tunnels may also cause deformation of the tunnels. The aging and deformation of the tunnel may further lead to the collapse of the tunnel, seriously endangering the safety of passengers' lives and property, and endangering the entire city's transportation system.

[0003] For tunnel deformation detection, the traditional method is mainly based on manual detection, and the accuracy and efficiency cannot be guaranteed. Summary of the invention

[0004] In order to solve the deficiencies mentioned in the above background technology, the purpose of the present invention is to provide a tunnel cross-section profile extraction and analysis method and system, which can extract the tunnel cross-section profile and perform tunnel deformation analysis based on the tunnel cross-section profile image.

[0005] In a first aspect, the purpose of the present invention can be achieved by the following technical solution: a tunnel section profile extraction and analysis system, comprising:

[0006] Image acquisition and processing module: used to acquire tunnel cross-sectional images, pre-process the tunnel cross-sectional images, perform binarization on the processed tunnel cross-sectional images, obtain tunnel cross-sectional binarization images, obtain tunnel cross-sectional image-related data based on the tunnel cross-sectional binarization images, use the tunnel cross-sectional image-related data to perform comprehensive image quality calculations, obtain a comprehensive tunnel cross-sectional image quality coefficient, set an image quality coefficient threshold, compare the comprehensive tunnel cross-sectional image quality coefficient with the image quality coefficient threshold, determine whether to perform contour extraction on the tunnel cross-sectional binarization image based on the comparison result, if contour extraction can be performed, send a contour extraction signal to the contour extraction module, if not, re-acquire, wherein the tunnel cross-sectional image-related data includes image frame rate data and image resolution data;

[0007] Contour extraction module: used to obtain the binary image of the tunnel section, and to depict the nodes of the contour curve through the process of pixel detection and connected domain marking to obtain the binary image of the cross-section contour;

[0008] Data acquisition module: used to collect the cross-section contour binary image using a three-dimensional laser ranging method to obtain cross-section point cloud related data, wherein the cross-section point cloud related data includes cross-section three-dimensional position data, reflection angle data and reflection intensity data, and send the cross-section point cloud related data to the data processing module;

[0009] Data processing module: used to mark the cross-section point cloud related data, calculate the tunnel deformation index using the marked cross-section point cloud related data, obtain the tunnel deformation index coefficient, and send the tunnel deformation index coefficient to the deformation analysis module;

[0010] Deformation analysis module: used to set the target value of the cross-section deformation index, optimize the cross-section deformation index coefficient, and calculate the optimization degree ratio of the cross-section deformation index target value obtained by optimizing the cross-section deformation index coefficient. The tunnel deformation degree is evaluated according to the optimization degree ratio of the cross-section deformation index target value, and different levels of deformation signals are sent to the control center based on the evaluation results.

[0011] Control center: used to send different levels of maintenance instructions to executors based on different levels of deformation signals.

[0012] In combination with the first aspect, in some implementations of the first aspect, the system further includes: a processing process of the image acquisition processing module is as follows:

[0013] The image frame rate data is marked as Zi, and the image resolution data is marked as Fi, where i is the number of acquisition times of the image acquisition processing module, and i=1, 2, 3, ..., n, and n is the total number of acquisition times of the image acquisition processing module;

[0014] Using the formula The comprehensive tunnel section image quality coefficient Lhi is calculated, where Z0 is the preset standard image frame rate coefficient, F0 is the preset standard image resolution coefficient, K1 is the image frame rate correlation coefficient, K2 is the image resolution correlation coefficient, and t is the preset section profile correlation coefficient.

[0015] In combination with the first aspect, in some implementations of the first aspect, the system further includes: the image acquisition processing module sets an image quality coefficient threshold Lh0, and compares the comprehensive tunnel section image quality coefficient Lhi with the image quality coefficient threshold Lh0:

[0016] If Lhi ≥ Lh0, a contour extraction signal is sent to the contour extraction module;

[0017] If Lhi<Lh0, the image is collected again, and when Lhi≥Lh0, the contour extraction signal is sent to the contour extraction module.

[0018] In combination with the first aspect, in some implementations of the first aspect, the system further includes: the extraction process of the contour extraction module includes:

[0019] Pixel detection is performed based on the binary image of the tunnel section, and the area with a pixel value of 0 is taken as the contour boundary. Based on the contour boundary, a single pixel point is removed to obtain the contour boundary after removal, and the connected domain is marked according to the contour boundary after removal to obtain the contour connected domain. The nodes of the contour curve are determined based on the contour connected domain, and the contour curve is depicted according to the nodes to obtain a binary image of the section contour.

[0020] In combination with the first aspect, in some implementations of the first aspect, the system further includes: the data processing module marks the cross-section three-dimensional position data as Wj, marks the reflection angle data as Dj, and marks the reflection intensity data as Qj, where j is the number of acquisition times of the data acquisition module, and j=1, 2, 3, ..., m, and m is the total number of acquisition times of the data acquisition module;

[0021] Using the formula The tunnel deformation index coefficient Bxj is calculated, where D0 is the preset standard reflection angle coefficient, r1 is the section position influence coefficient, r2 is the reflection influence coefficient, and α is the preset proportional coefficient.

[0022] In combination with the first aspect, in some implementations of the first aspect, the system further includes: the deformation analysis module sets a cross-sectional deformation index target value Bx0, and performs parameter optimization on the cross-sectional deformation index coefficient to obtain an optimization degree ratio of the cross-sectional deformation index target value, and the calculation is as follows:

[0023]

[0024] Where Yj is the optimization degree ratio of the target value of the cross-section deformation index, and β is the preset ratio correlation coefficient.

[0025] In combination with the first aspect, in some implementations of the first aspect, the system further includes: an analysis process of the deformation analysis module is as follows:

[0026] If Yj is less than 20%, the deformation analysis module sends a low-level deformation signal to the control center;

[0027] If Yj is not less than 20% but less than 55%, the deformation analysis module sends an intermediate deformation signal to the control center;

[0028] If Yj is not less than 55%, the deformation analysis module sends a high-level deformation signal to the control center.

[0029] In a second aspect, in order to achieve the above-mentioned object, the present invention discloses a tunnel cross-section profile extraction and analysis method, the method comprising the following steps:

[0030] Acquire a tunnel cross-section image, perform preprocessing on the processed tunnel cross-section image, perform binarization processing on the processed tunnel cross-section image, obtain a tunnel cross-section binarization image, and acquire tunnel cross-section image related data based on the tunnel cross-section binarization image, wherein the tunnel cross-section image related data includes image frame rate data and image resolution data;

[0031] The tunnel section image related data is marked, and the image quality is comprehensively calculated using the marked tunnel section image related data to obtain a comprehensive tunnel section image quality coefficient, and the image quality coefficient threshold is set, and the comprehensive tunnel section image quality coefficient is compared with the image quality coefficient threshold, and whether the tunnel section binary image is to be subjected to contour extraction is determined according to the comparison result;

[0032] If contour extraction is performed, the nodes of the contour curve are depicted through the process of pixel detection and connected domain marking to obtain a cross-section contour binary map. A three-dimensional laser ranging method is used for the cross-section contour binary map to obtain cross-section point cloud related data, wherein the cross-section point cloud related data includes cross-section three-dimensional position data, reflection angle data and reflection intensity data;

[0033] The cross-section point cloud related data are marked, and the marked cross-section point cloud related data are used to calculate the tunnel deformation index to obtain the tunnel deformation index coefficient, set the cross-section deformation index target value, and calculate the cross-section deformation index coefficient to perform parameter optimization to obtain the optimization degree ratio of the cross-section deformation index target value. The tunnel deformation grade is determined according to the optimization degree ratio of the cross-section deformation index target value.

[0034] Beneficial effects of the present invention:

[0035] The present invention collects tunnel cross-sectional images through an image acquisition and processing module and processes them to obtain a comprehensive tunnel cross-sectional image quality coefficient, and determines whether the image can be subjected to contour extraction. If not, the image is re-collected; if so, a cross-sectional contour binary map is obtained through the contour extraction module, and then the cross-sectional point cloud related data is collected through the data acquisition module, and the cross-sectional point cloud related data is processed and calculated through the data processing module to obtain the tunnel deformation index coefficient, and the cross-sectional deformation index target value is set through the deformation analysis module and the optimization degree ratio of the cross-sectional deformation index target value is calculated, and after evaluating the ratio, the deformation level is determined based on the evaluation result, and then different levels of maintenance instructions are issued to the executor according to the deformation level through the control center, thereby realizing the function of being able to perform tunnel deformation analysis according to the tunnel cross-sectional contour image after extracting the tunnel cross-sectional contour. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0038] Figure 2 It is a schematic flow chart of the method of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] Embodiment 1:

[0041] The following is an introduction to the relevant terms involved in the embodiments of the present application:

[0042] Binarization: Binarization (English: Thresholding) is one of the simplest methods for image segmentation. Binarization can convert grayscale images into binary images. The grayscale of pixels greater than a certain critical grayscale value is set to the grayscale maximum value, and the grayscale of pixels less than this value is set to the grayscale minimum value, thereby achieving binarization. Depending on the selection of the threshold, the binarization algorithm is divided into fixed threshold and adaptive threshold. The more commonly used binarization methods are: bimodal method, P parameter method, iteration method and OTSU method.

[0043] Parameter optimization: Parameter optimization is a method to achieve design goals. By parameterizing the design goals, using optimization methods, and continuously adjusting the design variables, the design results are constantly approaching the parameterized target values.

[0044] Pixel value: The pixel value is the value assigned by the computer when the original image is digitized. It represents the average brightness information of a small square in the original, or the average reflection (transmission) density information of the small square. When converting a digital image into a halftone image, the dot area rate (dot percentage) is directly related to the pixel value (grayscale value) of the digital image, that is, the dot represents the average brightness information of a small square in the original with its size.

[0045] like Figure 1 As shown, a tunnel section profile extraction and analysis system comprises:

[0046] Image acquisition and processing module, contour extraction module, data acquisition module, data processing module, deformation analysis module and control center;

[0047] The image acquisition and processing module is used to acquire tunnel cross-sectional images and pre-process the tunnel cross-sectional images to obtain processed tunnel cross-sectional images;

[0048] The tunnel cross-section image preprocessing process includes: deblurring and denoising. Specifically, in the specific implementation process, the image deblurring includes image enhancement, image restoration and super-resolution reconstruction. The image denoising is processed by a spatial domain filtering method. The spatial domain filtering method achieves image denoising by directly analyzing the relationship between image pixels and their neighboring pixels. This method smoothes the image by applying a series of filters or convolution kernels in the two-dimensional space of the image, thereby reducing the impact of noise on the image.

[0049] The processed tunnel cross-section image is binarized to obtain a tunnel cross-section binarized image. It should be noted that the methods for binarizing the processed tunnel cross-section image include a global threshold method, an Otsu threshold method, a local threshold method, and an adaptive threshold method. Specifically, in the present application, the global threshold method is used for binarization because this method is simple and fast. It is assumed that within the entire image range, pixels with brightness higher than a certain threshold should be marked as foreground (white), and pixels with brightness lower than the threshold should be marked as background (black). Finally, a tunnel cross-section binarized image is obtained.

[0050] Based on the tunnel cross-section binary image, the tunnel cross-section image related data is acquired, and the tunnel cross-section image related data is marked to obtain the marked tunnel cross-section image related data. The marked tunnel cross-section image related data is used to perform comprehensive image quality calculation to obtain a comprehensive tunnel cross-section image quality coefficient, wherein the tunnel cross-section image related data includes image frame rate data and image resolution data. Specifically, the processing process of the image acquisition processing module is as follows:

[0051] The image frame rate data is marked as Zi, and the image resolution data is marked as Fi, where i is the number of acquisition times of the image acquisition processing module, and i=1, 2, 3, ..., n, and n is the total number of acquisition times of the image acquisition processing module;

[0052] Using the formula The comprehensive tunnel section image quality coefficient Lhi is calculated, where Z0 is the preset standard image frame rate coefficient, F0 is the preset standard image resolution coefficient, K1 is the image frame rate correlation coefficient, K2 is the image resolution correlation coefficient, and t is the preset section profile correlation coefficient;

[0053] Furthermore, in the specific implementation process, the preset standard image frame rate coefficient and the preset standard image resolution coefficient are obtained by collecting image frame rate data and image resolution data daily, and then performing multiple simulation calculations and taking data averages;

[0054] Among them, in this embodiment, the image frame rate correlation coefficient and the image resolution correlation coefficient are obtained by comprehensive evaluation and calculation based on external and internal related factors when the application obtains the image frame rate data and the image resolution data on a daily basis, including human factors, image related factors and environment related factors. The image related factors include factors such as image clarity, image color depth and image distortion degree;

[0055] The preset cross-sectional profile correlation coefficient is relevant data that affects whether a clear profile can be drawn in an image, and is obtained by performing comprehensive processing after collecting images that can draw a clear profile multiple times.

[0056] The image quality coefficient threshold Lh0 is set, and the calculated comprehensive tunnel section image quality coefficient Lhi is compared with the image quality coefficient threshold Lh0, and whether the quality of the tunnel section binary image meets the outline drawing standard is determined according to the comparison result, so as to determine whether to perform outline extraction;

[0057] Specific comparison process:

[0058] If Lhi ≥ Lh0, it means that the quality of the tunnel cross-section image meets the outline drawing standard, and the image acquisition and processing module sends a contour extraction signal to the contour extraction module;

[0059] If Lhi<Lh0, it means that the quality of the tunnel cross-section image does not meet the outline drawing standard, and the image acquisition and processing module re-acquires the image, and when Lhi≥Lh0, the outline extraction signal is sent to the outline extraction module;

[0060] After receiving the contour extraction signal sent by the image acquisition processing module, the contour extraction module performs contour extraction. Specifically, the extraction process of the contour extraction module includes the following steps:

[0061] Obtain a binarized image of the tunnel section in the image acquisition and processing module, perform pixel detection based on the binarized image of the tunnel section, use an area with a pixel value of 0 as a contour boundary, remove a single pixel point based on the contour boundary to obtain a contour boundary after removal, mark a connected domain based on the contour boundary after removal, obtain a contour connected domain, determine the nodes of the contour curve based on the contour connected domain, and depict the nodes of the contour curve to obtain a binarized image of the cross-section contour;

[0062] Wherein, in the specific implementation process, the area with a pixel value of 0 is the black area on the binary image of the tunnel section;

[0063] The pixel detection based on the binary image of the tunnel section and the subsequent connected domain marking process are obtained by operating with an eight-neighborhood algorithm;

[0064] Send the cross-section contour binary image to the data acquisition module for data acquisition;

[0065] After receiving the cross-section contour binary image sent by the contour extraction module, the data acquisition module determines the internal position of the cross-section contour based on the cross-section contour binary image, and then uses a three-dimensional laser ranging method to obtain cross-section point cloud related data, and sends the cross-section point cloud related data to the data processing module, wherein the cross-section point cloud related data includes cross-section three-dimensional position data, reflection angle data and reflection intensity data;

[0066] Specifically, in this embodiment, the data collection process performed by the data collection module is as follows:

[0067] The laser is emitted to the surface of the object through a laser transmitter. After the laser irradiates the surface of the section, the reflected laser signal is converted into an electrical signal using a photoelectric converter, and the three-dimensional coordinates of the object surface are calculated through an algorithm to obtain point cloud data as section point cloud related data.

[0068] After receiving the crack-related index data sent by the data acquisition module, the data processing module performs data processing. Specifically, the processing process of the data processing module includes the following steps:

[0069] The cross-section point cloud related data is marked, and the marked cross-section point cloud related data is used to calculate the tunnel deformation index to obtain the tunnel deformation index coefficient. The specific process is as follows:

[0070] The cross-section three-dimensional position data is marked as Wj, the reflection angle data is marked as Dj, and the reflection intensity data is marked as Qj, where j is the number of acquisition times of the data acquisition module, and j=1, 2, 3, ..., m, and m is the total number of acquisition times of the data acquisition module;

[0071] Using the formula The tunnel deformation index coefficient Bxj is calculated, where D0 is the preset standard reflection angle coefficient, r1 is the section position influence coefficient, r2 is the reflection influence coefficient, and α is the preset proportional coefficient;

[0072] Among them, in this embodiment, the cross-section position influence coefficient and the reflection influence coefficient are obtained by comprehensive evaluation and calculation based on the influence of external factors when the application obtains the cross-section three-dimensional position data, reflection angle data and reflection intensity data on a daily basis, including human factors, machine detection and environmental factors, etc.; human factors are some factors caused by human operation or improper scanning;

[0073] Send the calculated cross-section deformation index coefficient to the deformation analysis module for deformation analysis;

[0074] After receiving the cross-sectional deformation index coefficient sent by the data processing module, the deformation analysis module performs deformation analysis. Specifically, the analysis process of the deformation analysis module includes the following steps:

[0075] The cross-sectional deformation index target value Bx0 is set, and the cross-sectional deformation index coefficient is optimized so that the cross-sectional deformation index coefficient gradually approaches the cross-sectional deformation index target value until the cross-sectional deformation index target value is obtained by optimization. The optimization degree ratio of the cross-sectional deformation index coefficient obtained by parameter optimization is calculated as follows:

[0076]

[0077] Where, Yj is the optimization degree ratio of the target value of the cross-section deformation index, and β is the preset ratio correlation coefficient;

[0078] The tunnel deformation degree is evaluated based on the calculated optimization degree ratio Yj of the target value of the cross-section deformation index, and different levels of deformation signals are sent to the control center based on the evaluation results. The specific process is as follows:

[0079] If Yj is less than 20%, it is determined that the tunnel deformation is low at this time, and the deformation analysis module sends a low-level deformation signal to the control center;

[0080] If Yj is not less than 20% but less than 55%, it is determined that the tunnel deformation is moderate at this time, and the deformation analysis module sends a medium deformation signal to the control center;

[0081] If Yj is not less than 55%, it is determined that the tunnel deformation is high at this time, and the deformation analysis module sends a high-level deformation signal to the control center;

[0082] After receiving the deformation signals of different levels sent by the deformation analysis module, the control center sends maintenance instructions of different levels for the maintenance of the tunnel according to the deformation of different levels. Specifically, the scheme of the present invention is further described below through embodiments:

[0083] After receiving the low-level deformation signal, the control center sends a first-level maintenance instruction to the execution personnel;

[0084] After receiving the intermediate deformation signal, the control center sends a secondary maintenance instruction to the execution personnel;

[0085] After receiving the high-level deformation signal, the control center sends a third-level maintenance instruction to the executor.

[0086] Embodiment 2: A tunnel cross-section profile extraction and analysis method, the method comprising the following steps:

[0087] S101: Acquire a tunnel cross-section image, perform preprocessing, perform binarization processing on the processed tunnel cross-section image to obtain a tunnel cross-section binarization image, and acquire tunnel cross-section image related data based on the tunnel cross-section binarization image, wherein the tunnel cross-section image related data includes image frame rate data and image resolution data;

[0088] S102: marking the tunnel section image related data, using the marked tunnel section image related data to perform comprehensive image quality calculation, obtaining a comprehensive tunnel section image quality coefficient, setting an image quality coefficient threshold, comparing the comprehensive tunnel section image quality coefficient with the image quality coefficient threshold, and determining whether to perform contour extraction on the tunnel section binary image according to the comparison result;

[0089] S103: If contour extraction is performed, the nodes of the contour curve are depicted through the process of pixel detection and connected domain labeling to obtain a cross-section contour binary map. A three-dimensional laser ranging method is used for the cross-section contour binary map to obtain cross-section point cloud related data, wherein the cross-section point cloud related data includes cross-section three-dimensional position data, reflection angle data, and reflection intensity data;

[0090] S104: marking the cross-section point cloud related data, using the marked cross-section point cloud related data to calculate the tunnel deformation index, obtaining the tunnel deformation index coefficient, setting the cross-section deformation index target value, and calculating the cross-section deformation index coefficient to perform parameter optimization to obtain the optimization degree ratio of the cross-section deformation index target value, and determining the tunnel deformation grade according to the optimization degree ratio of the cross-section deformation index target value.

[0091] Based on the same inventive concept, the present invention also provides a computer device, which includes: one or more processors, and a memory for storing one or more computer programs; the program includes program instructions, and the processor is used to execute the program instructions stored in the memory. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is used to implement one or more instructions, specifically for loading and executing one or more instructions in a computer storage medium to implement the above method.

[0092] It needs to be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium, on which a computer program is stored, and the computer program is executed by a processor to execute the above method. The storage medium can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electrical, magnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0093] The above formulas are all calculated by removing dimensions and taking their numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0094] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0095] The above shows and describes the basic principles, main features and advantages of the present disclosure. Those skilled in the art should understand that the present disclosure is not limited by the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present disclosure. Without departing from the spirit and scope of the present disclosure, the present disclosure may have various changes and improvements, and these changes and improvements fall within the scope of the present disclosure to be protected.

Claims

1. A tunnel section profile extraction and analysis system, characterized in that: include: Image acquisition and processing module: used to acquire tunnel cross-sectional images, pre-process the tunnel cross-sectional images, perform binarization on the processed tunnel cross-sectional images, obtain tunnel cross-sectional binarization images, obtain tunnel cross-sectional image-related data based on the tunnel cross-sectional binarization images, use the tunnel cross-sectional image-related data to perform comprehensive image quality calculations, obtain a comprehensive tunnel cross-sectional image quality coefficient, set an image quality coefficient threshold, compare the comprehensive tunnel cross-sectional image quality coefficient with the image quality coefficient threshold, determine whether to perform contour extraction on the tunnel cross-sectional binarization image based on the comparison result, if contour extraction can be performed, send a contour extraction signal to the contour extraction module, if not, re-acquire, wherein the tunnel cross-sectional image-related data includes image frame rate data and image resolution data; Contour extraction module: used to obtain the binary image of the tunnel section, and to depict the nodes of the contour curve through the process of pixel detection and connected domain marking to obtain the binary image of the cross-section contour; Data acquisition module: used to collect the cross-section contour binary image using a three-dimensional laser ranging method to obtain cross-section point cloud related data, wherein the cross-section point cloud related data includes cross-section three-dimensional position data, reflection angle data and reflection intensity data, and send the cross-section point cloud related data to the data processing module; Data processing module: used to mark the cross-section point cloud related data, calculate the tunnel deformation index using the marked cross-section point cloud related data, obtain the tunnel deformation index coefficient, and send the tunnel deformation index coefficient to the deformation analysis module; Deformation analysis module: used to set the target value of the cross-section deformation index, optimize the cross-section deformation index coefficient, and calculate the optimization degree ratio of the cross-section deformation index target value obtained by optimizing the cross-section deformation index coefficient. The tunnel deformation degree is evaluated according to the optimization degree ratio of the cross-section deformation index target value, and different levels of deformation signals are sent to the control center based on the evaluation results. Control center: used to send different levels of maintenance instructions to executors based on different levels of deformation signals.

2. A tunnel cross-section profile extraction and analysis system according to claim 1, characterized in that: The processing process of the image acquisition processing module is as follows: The image frame rate data is marked as Zi, and the image resolution data is marked as Fi, where i is the number of acquisition times of the image acquisition processing module, and i=1, 2, 3, ..., n, and n is the total number of acquisition times of the image acquisition processing module; Using the formula The comprehensive tunnel section image quality coefficient Lhi is calculated, where Z0 is the preset standard image frame rate coefficient, F0 is the preset standard image resolution coefficient, K1 is the image frame rate correlation coefficient, K2 is the image resolution correlation coefficient, and t is the preset section profile correlation coefficient.

3. A tunnel cross-section profile extraction and analysis system according to claim 2, characterized in that: The image acquisition processing module sets an image quality coefficient threshold Lh0, and compares the comprehensive tunnel section image quality coefficient Lhi with the image quality coefficient threshold Lh0: If Lhi ≥ Lh0, a contour extraction signal is sent to the contour extraction module; If Lhi<Lh0, the image is collected again, and when Lhi≥Lh0, the contour extraction signal is sent to the contour extraction module.

4. A tunnel section profile extraction and analysis system according to claim 1, characterized in that: The extraction process of the contour extraction module includes: Pixel detection is performed based on the binary image of the tunnel section, and the area with a pixel value of 0 is taken as the contour boundary. Based on the contour boundary, a single pixel point is removed to obtain the contour boundary after removal, and the connected domain is marked according to the contour boundary after removal to obtain the contour connected domain. The nodes of the contour curve are determined based on the contour connected domain, and the contour curve is depicted according to the nodes to obtain a binary image of the section contour.

5. The tunnel section profile extraction and analysis system according to claim 1, characterized in that: The data processing module marks the cross-section three-dimensional position data as Wj, the reflection angle data as Dj, and the reflection intensity data as Qj, where j is the number of acquisition times of the data acquisition module, and j=1, 2, 3, ..., m, and m is the total number of acquisition times of the data acquisition module; Using the formula The tunnel deformation index coefficient Bxj is calculated, where D0 is the preset standard reflection angle coefficient, r1 is the section position influence coefficient, r2 is the reflection influence coefficient, and α is the preset proportional coefficient.

6. A tunnel section profile extraction and analysis system according to claim 1, characterized in that: The deformation analysis module sets the cross-sectional deformation index target value Bx0, and performs parameter optimization on the cross-sectional deformation index coefficient to obtain the cross-sectional deformation index target value. The optimization degree ratio is calculated as follows: Where Yj is the optimization degree ratio of the target value of the cross-section deformation index, and β is the preset ratio correlation coefficient.

7. A tunnel cross-section profile extraction and analysis system according to claim 6, characterized in that: The analysis process of the deformation analysis module is as follows: If Yj is less than 20%, the deformation analysis module sends a low-level deformation signal to the control center; If Yj is not less than 20% but less than 55%, the deformation analysis module sends an intermediate deformation signal to the control center; If Yj is not less than 55%, the deformation analysis module sends a high-level deformation signal to the control center.

8. A tunnel section profile extraction and analysis method, characterized in that: The method comprises the following steps: Acquire a tunnel cross-section image, perform preprocessing on the processed tunnel cross-section image, perform binarization processing on the processed tunnel cross-section image, obtain a tunnel cross-section binarization image, and acquire tunnel cross-section image related data based on the tunnel cross-section binarization image, wherein the tunnel cross-section image related data includes image frame rate data and image resolution data; The tunnel section image related data is marked, and the image quality is comprehensively calculated using the marked tunnel section image related data to obtain a comprehensive tunnel section image quality coefficient, and the image quality coefficient threshold is set, and the comprehensive tunnel section image quality coefficient is compared with the image quality coefficient threshold, and whether the tunnel section binary image is to be subjected to contour extraction is determined according to the comparison result; If contour extraction is performed, the nodes of the contour curve are depicted through the process of pixel detection and connected domain marking to obtain a cross-section contour binary map. A three-dimensional laser ranging method is used for the cross-section contour binary map to obtain cross-section point cloud related data, wherein the cross-section point cloud related data includes cross-section three-dimensional position data, reflection angle data and reflection intensity data; The cross-section point cloud related data are marked, and the marked cross-section point cloud related data are used to calculate the tunnel deformation index to obtain the tunnel deformation index coefficient, set the cross-section deformation index target value, and calculate the cross-section deformation index coefficient to perform parameter optimization to obtain the optimization degree ratio of the cross-section deformation index target value. The tunnel deformation grade is determined according to the optimization degree ratio of the cross-section deformation index target value.

Images