Tunnel lining apparent disease identification method and device

Through the joint recognition of apparent visible light and infrared images of tunnel lining, the problems of low image resolution and low signal-to-noise ratio in apparent disease recognition of tunnel lining are solved, the recognition accuracy is improved, error judgments and misses are reduced, and the disease is enhanced Features are highlighted.

CN118883584APending Publication Date: 2024-11-01CHINA ACADEMY OF RAILWAY SCI CORP LTD +2
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410876943.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-02
Publication Date
2024-11-01

AI Technical Summary

Technical Problem

In the prior art, in the recognition of apparent diseases of tunnel lining, the recognition results are inaccurate due to the low image resolution and low signal-to-noise ratio, and there are problems of error judgment and missed.

Method used

The joint recognition method of tunnel lining apparent visible light images and infrared images is adopted, and through image cropping, intelligent recognition algorithms and grayscale conversion, multi-dimensional image information is used to enhance disease characteristics to avoid error judgments and misses.

Benefits of technology

It improves the accuracy of the identification of apparent diseases of tunnel lining, reduces error judgments and misses, enhances the highlighting of disease characteristics, and ensures the reliability of identification results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118883584A_ABST
    Figure CN118883584A_ABST
Patent Text Reader

Abstract

The invention discloses a tunnel lining apparent disease identification method and device, and relates to the technical field of tunnel apparent disease identification, and the method comprises the steps: obtaining a collected visible light image and an infrared image; image cutting is carried out on the overlapping area of the visible light image and the infrared image, and a cut visible light image and a cut infrared image are obtained; performing tunnel lining apparent disease identification on the cut visible light image by using a preset first intelligent identification algorithm to determine a first identification result; performing tunnel lining apparent disease identification on the cut infrared image by using a preset second intelligent identification algorithm, and determining a second identification result; and according to the first identification result and the second identification result, tunnel lining apparent disease information is determined. According to the method, misjudgment and missing during tunnel lining apparent disease identification can be avoided, and the accuracy of a tunnel lining apparent disease identification result is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of tunnel apparent disease identification, and in particular to a method and device for identifying tunnel lining apparent disease. Background Art

[0002] This section is intended to provide a background or context for embodiments of the present invention. No description herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] The occurrence of apparent defects in tunnel lining will affect the traffic and driving safety of the tunnel, and ultimately reduce the service life of the tunnel. Therefore, it is necessary to monitor and detect structural defects in the tunnel throughout the operation stage, and carry out targeted maintenance to ensure traffic safety during the operation period.

[0004] Tunnel lining surface defects can be described in detail as lining cracks (cracks), peeling, water leakage, etc. At present, the identification of tunnel lining surface defects mainly uses non-contact visual detection, that is, obtaining tunnel lining surface images through high-definition industrial cameras, and then performing image processing on the tunnel lining surface images through recognition algorithms to identify tunnel surface defects such as cracks, peeling, water leakage, etc. However, due to the harsh tunnel scene, the acquired tunnel lining surface images have problems such as low image resolution and low signal-to-noise ratio. When the recognition algorithm recognizes the tunnel lining surface images, it cannot solve the problems of low image resolution and low signal-to-noise ratio, resulting in a large number of misjudgments and omissions, which in turn makes the identification results of tunnel lining surface defects inaccurate. Summary of the invention

[0005] The embodiment of the present invention provides a method for identifying apparent defects of tunnel lining, which is used to avoid misjudgment and omission in identifying apparent defects of tunnel lining, and improve the accuracy of the results of identifying apparent defects of tunnel lining. The method includes:

[0006] Acquire the collected tunnel lining surface image; the tunnel lining surface image includes a visible light image and an infrared image of the tunnel lining surface;

[0007] Performing image cropping on the overlapping area of ​​the visible light image and the infrared image to obtain a cropped visible light image and a cropped infrared image;

[0008] Using a preset first intelligent recognition algorithm, the cropped visible light image is used to identify apparent defects of the tunnel lining, and a first recognition result is determined;

[0009] Using the preset second intelligent recognition algorithm, the cropped infrared image is used to identify the apparent defects of the tunnel lining, and a second recognition result is determined, which includes: calculating the grayscale threshold according to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel; performing grayscale conversion on the cropped infrared image to obtain a grayscale image; mapping the grayscale image according to the grayscale threshold and a preset piecewise mapping function to obtain a new grayscale image; the new grayscale image includes a dry lining area, a wet lining area and a cracked lining area; performing image recognition on the new grayscale image to determine the second recognition result;

[0010] The apparent disease information of the tunnel lining is determined based on the first recognition result and the second recognition result.

[0011] The embodiment of the present invention further provides a tunnel lining apparent disease identification device, which is used to avoid misjudgment and omission in tunnel lining apparent disease identification and improve the accuracy of tunnel lining apparent disease identification results. The device includes:

[0012] An acquisition module is used to acquire a collected tunnel lining surface image; the tunnel lining surface image includes a visible light image and an infrared image of the tunnel lining surface;

[0013] A cropping module, used for cropping the overlapping area of ​​the visible light image and the infrared image to obtain a cropped visible light image and a cropped infrared image;

[0014] A first recognition module is used to identify tunnel lining surface defects on the cropped visible light image using a preset first intelligent recognition algorithm to determine a first recognition result;

[0015] The second recognition module is used to use a preset second intelligent recognition algorithm to identify tunnel lining surface defects on the cropped infrared image and determine a second recognition result, which includes: calculating a grayscale threshold according to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel; performing grayscale conversion on the cropped infrared image to obtain a grayscale image; mapping the grayscale image according to the grayscale threshold and a preset piecewise mapping function to obtain a new grayscale image; the new grayscale image includes a dry lining area, a wet lining area and a cracked lining area; performing image recognition on the new grayscale image to determine a second recognition result;

[0016] The disease information determination module is used to determine the apparent disease information of the tunnel lining according to the first recognition result and the second recognition result.

[0017] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for identifying apparent defects in tunnel lining is implemented.

[0018] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the above-mentioned method for identifying apparent defects in tunnel lining is implemented.

[0019] In an embodiment of the present invention, a collected tunnel lining surface image is obtained; the tunnel lining surface image includes a visible light image and an infrared image of the tunnel lining surface; the overlapping area of ​​the visible light image and the infrared image is cropped to obtain a cropped visible light image and a cropped infrared image; a preset first intelligent recognition algorithm is used to identify tunnel lining surface defects on the cropped visible light image to determine a first recognition result; a preset second intelligent recognition algorithm is used to identify tunnel lining surface defects on the cropped infrared image to determine a second recognition result, which includes: calculating a grayscale threshold according to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel; grayscale conversion is performed on the cropped infrared image to obtain a grayscale image; the grayscale image is mapped according to the grayscale threshold and a preset piecewise mapping function to obtain a new grayscale image; the new grayscale image includes a dry lining area, a wet lining area and a cracked lining area; image recognition is performed on the new grayscale image to determine a second recognition result; and tunnel lining surface defect information is determined according to the first recognition result and the second recognition result. Compared with the existing method for identifying apparent defects of tunnel lining, the embodiment of the present invention uses the visible light image and infrared image of the tunnel lining surface to jointly identify the apparent defects of the tunnel lining. Through multi-dimensional image information, the characteristics of the apparent defects of the lining can be enhanced, misjudgment and omission can be avoided, and the accuracy of the identification results of the apparent defects of the tunnel lining can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] 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 prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0021] Figure 1 A flow chart of a method for identifying apparent defects in a tunnel lining provided in an embodiment of the present invention;

[0022] Figure 2 A flow chart of a method for identifying tunnel lining surface defects on a cropped visible light image using a preset first intelligent recognition algorithm and determining a first recognition result provided in an embodiment of the present invention;

[0023] Figure 3 A flow chart of a method for performing image recognition on a new grayscale image and determining a second recognition result provided in an embodiment of the present invention;

[0024] Figure 4 A flow chart of a method for determining an optimal image segmentation threshold according to a second grayscale threshold, the number of pixels in a damaged lining area, and a grayscale value corresponding to each pixel in the damaged lining area provided in an embodiment of the present invention;

[0025] Figure 5 A schematic diagram of a tunnel lining surface disease identification device provided in an embodiment of the present invention;

[0026] Figure 6 A schematic diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0028] In the description of this specification, the terms "include", "including", "have", "contain", etc. are all open terms, which mean including but not limited to. The descriptions with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", etc. mean that the specific features, structures or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. The order of steps involved in each embodiment is used to schematically illustrate the implementation of the present application, and the order of steps is not limited and can be appropriately adjusted as needed.

[0029] According to research, the current identification of tunnel lining surface defects mainly uses non-contact visual inspection, that is, obtaining tunnel lining surface images through high-definition industrial cameras, and then processing the tunnel lining surface images through recognition algorithms to identify tunnel surface defects such as cracks, falling blocks, and water leakage. However, due to the harsh tunnel scene, the acquired tunnel lining surface images have problems such as low image resolution and low signal-to-noise ratio. When the recognition algorithm recognizes the tunnel lining surface images, it cannot solve these problems, resulting in a large number of misjudgments and omissions, which in turn makes the identification results of tunnel lining surface defects inaccurate.

[0030] In response to the above research, an embodiment of the present invention provides a tunnel lining surface disease identification solution, which identifies tunnel lining surface diseases by combining visible light images and infrared images of the tunnel lining surface, thereby improving the accuracy of tunnel lining surface disease identification results.

[0031] Figure 1 A flow chart of a method for identifying apparent defects in a tunnel lining provided by an embodiment of the present invention, the method may include the following steps:

[0032] Step 101, acquiring a collected tunnel lining surface image; the tunnel lining surface image includes a visible light image and an infrared image of the tunnel lining surface;

[0033] Step 102, cropping the overlapping area of ​​the visible light image and the infrared image to obtain a cropped visible light image and a cropped infrared image;

[0034] Step 103, using a preset first intelligent recognition algorithm, performing tunnel lining surface disease recognition on the cropped visible light image to determine a first recognition result;

[0035] Step 104, using a preset second intelligent recognition algorithm, the cropped infrared image is subjected to tunnel lining surface disease recognition to determine a second recognition result, which includes: calculating a grayscale threshold according to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel; performing grayscale conversion on the cropped infrared image to obtain a grayscale image; mapping the grayscale image according to the grayscale threshold and a preset piecewise mapping function to obtain a new grayscale image; the new grayscale image includes a dry lining area, a wet lining area and a cracked lining area; performing image recognition on the new grayscale image to determine a second recognition result;

[0036] Step 105: Determine the tunnel lining surface defect information based on the first recognition result and the second recognition result.

[0037] In an embodiment of the present invention, a collected tunnel lining surface image is obtained; the tunnel lining surface image includes a visible light image and an infrared image of the tunnel lining surface; the overlapping area of ​​the visible light image and the infrared image is cropped to obtain a cropped visible light image and a cropped infrared image; a preset first intelligent recognition algorithm is used to identify tunnel lining surface defects on the cropped visible light image to determine a first recognition result; a preset second intelligent recognition algorithm is used to identify tunnel lining surface defects on the cropped infrared image to determine a second recognition result, which includes: calculating a grayscale threshold according to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel; grayscale conversion is performed on the cropped infrared image to obtain a grayscale image; the grayscale image is mapped according to the grayscale threshold and a preset piecewise mapping function to obtain a new grayscale image; the new grayscale image includes a dry lining area, a wet lining area and a cracked lining area; image recognition is performed on the new grayscale image to determine a second recognition result; and tunnel lining surface defect information is determined according to the first recognition result and the second recognition result. Compared with the existing method for identifying apparent defects of tunnel lining, the embodiment of the present invention uses the visible light image and infrared image of the tunnel lining surface to jointly identify the apparent defects of the tunnel lining. Through multi-dimensional image information, the characteristics of the apparent defects of the lining can be enhanced, misjudgment and omission can be avoided, and the accuracy of the identification results of the apparent defects of the tunnel lining can be improved.

[0038] Below Figure 1 The method for identifying apparent defects in tunnel linings shown in the figure is described in detail.

[0039] In the above step 101, the tunnel lining surface image collected by the vehicle-mounted tunnel lining surface disease infrared imaging detection device can be obtained. The tunnel lining surface image can include a visible light image and an infrared image of the tunnel lining surface.

[0040] During specific implementation, the vehicle-mounted tunnel lining surface disease infrared imaging detection device includes an image acquisition module, which includes an infrared image acquisition module and a visible light image acquisition module. The infrared image acquisition module can acquire infrared images of the tunnel lining surface, and the visible light image acquisition module can acquire visible light images of the tunnel lining surface.

[0041] In the above step 102, the overlapping area of ​​the visible light image and the infrared image may be cropped to obtain a cropped visible light image and a cropped infrared image.

[0042] In a specific implementation, in order to obtain a visible light image and an infrared image at the same position and in the same field of view, the overlapping area of ​​the visible light image and the infrared image may be cropped to obtain a cropped visible light image and a cropped infrared image.

[0043] In one embodiment, the above step 102 may specifically include:

[0044] Based on the preset image registration algorithm, the visible light image and the infrared image are registered;

[0045] The overlapping area of ​​the registered visible light image and the infrared image is intercepted to obtain a cropped visible light image and a cropped infrared image.

[0046] In a specific implementation, the visible light image and the infrared image can be registered by an image registration algorithm, and then the overlapping area of ​​the registered visible light image and the infrared image can be intercepted to obtain a cropped visible light image and a cropped infrared image. The image registration algorithm can be based on a feature point matching method or a pixel point matching method, which is not specifically limited here. In this way, the visible light image and the infrared image at the same position and in the same field of view can be accurately obtained.

[0047] In the above steps 103 and 104, the first intelligent recognition algorithm is used to identify the apparent defects of the tunnel lining in the cropped visible light image to determine a first recognition result, and the second intelligent recognition algorithm is used to identify the apparent defects of the tunnel lining in the cropped infrared image to determine a second recognition result.

[0048] In specific implementation, the dual-channel intelligent recognition algorithm (i.e., the first intelligent recognition algorithm and the second intelligent recognition algorithm) can be used to identify tunnel lining surface defects on the cropped visible light image and the cropped infrared image. The first intelligent recognition algorithm is based on the visible light image to complete the defect identification of cracks and falling blocks; the second intelligent recognition algorithm is based on the infrared image to complete the defect identification of water leakage.

[0049] Therefore, in one embodiment, the first identification result may include damage information of cracks and falling blocks; the second identification result may include lining crack damage and water leakage information.

[0050] In one embodiment, Figure 2 This is a flow chart of a method for identifying tunnel lining surface defects on a cropped visible light image using a preset first intelligent recognition algorithm and determining a first recognition result, as provided in an embodiment of the present invention. Figure 2 As shown, it may specifically include:

[0051] Step 201, using a Gaussian filtering algorithm to perform noise reduction processing on the cropped visible light image;

[0052] Step 202, binarizing the visible light image after the noise reduction process to obtain a visible light binarized image;

[0053] Step 203, using the Canny edge detection algorithm to perform edge detection on the visible light binary image to determine contour information of the visible light image;

[0054] Step 204: Determine a first recognition result according to the contour information of the visible light image.

[0055] In specific implementation, first, in step 201, a Gaussian filtering algorithm may be used to smooth the cropped visible light image, and weighted average pixels within a certain range around each pixel in the image may be performed to reduce the impact of noise.

[0056] Then, in step 202, the visible light image after the noise reduction processing is binarized, which can be specifically: the grayscale value of the pixel on the visible light image after the noise reduction processing is set to 0 or 255, that is, the entire image presents an obvious black and white effect, and a visible light binarized image is obtained. In this way, the binarization processing greatly reduces the amount of data in the image, so that the outline of the target can be highlighted.

[0057] In step 203, the Canny edge detection algorithm may be used to perform edge detection on the visible light binary image to determine contour information of the visible light image. Specifically, the Canny edge detection algorithm may include the following process:

[0058] 1. Grayscale processing: convert the input color visible light binary image into a grayscale image;

[0059] 2. Gaussian filtering: Use Gaussian filter to smooth the grayscale image to reduce the impact of noise;

[0060] 3. Calculate image gradient: Use the Sobel operator to calculate the gradient values ​​of the grayscale image in the horizontal and vertical directions, so as to obtain the gradient intensity and direction of each pixel;

[0061] 4. Non-maximum suppression: For each pixel, compare the gradient values ​​of the two adjacent pixels in the gradient direction, and only retain the pixels with the largest gradient values ​​in the gradient direction, which is helpful to eliminate the blur effect on the edge;

[0062] 5. Double threshold processing: Pixels are divided into three categories: strong edge, weak edge, and non-edge; when the gradient value of a pixel is higher than the higher threshold, it is classified as a strong edge. When the gradient value of a pixel is lower than the lower threshold, it is classified as a non-edge. When the gradient value of a pixel is between the higher and lower thresholds, it is classified as a weak edge.

[0063] 6. Edge connection: Connect the weak edge with the strong edges around it to form a complete edge.

[0064] In step 204, the first recognition result may be determined based on the contour information of the visible light image output by the Canny edge detection algorithm, that is, the information on apparent cracks and chipping defects of the tunnel lining may be obtained.

[0065] In this way, the apparent disease information of the tunnel lining in the visible light image can be obtained through the above method.

[0066] In specific implementation, in the above step 104, the second intelligent recognition algorithm may specifically include: first, it is necessary to calculate the grayscale threshold according to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel, and the grayscale threshold is used to divide the infrared image into regions; then, the cropped infrared image is gray-converted to obtain a grayscale image, and the grayscale image is mapped according to the grayscale threshold and a preset piecewise mapping function to obtain a new grayscale image. The new grayscale image includes a dry lining area, a wet lining area, and a cracked lining area; image recognition is performed on the new grayscale image to determine the second recognition result.

[0067] In one embodiment, the grayscale threshold may include a first grayscale threshold and a second grayscale threshold;

[0068] According to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel, the grayscale threshold is calculated, which may specifically include:

[0069] Calculate first average temperature data according to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel, and use the first average temperature data as a first grayscale threshold;

[0070] Determine, from the temperature data corresponding to each pixel of the cropped infrared image, a pixel whose temperature data is less than a first grayscale threshold;

[0071] The second average temperature data is calculated according to the temperature data of the pixels whose temperature data is less than the first grayscale threshold and the number of pixels, and the second average temperature data is used as the second grayscale threshold.

[0072] In a specific implementation, each pixel of the infrared image corresponds to a temperature data, and the average temperature of the cropped infrared image, that is, the first average temperature data, can be used as the first grayscale threshold.

[0073] In one embodiment, the first average temperature data may be calculated according to the following formula (1):

[0074]

[0075] Among them, D1 represents the first average temperature data, m represents the number of pixels of the cropped infrared image in the x-axis direction, n represents the number of pixels of the cropped infrared image in the y-axis direction, and N(x, y) represents the temperature data corresponding to the pixel with coordinates (x, y).

[0076] In a specific implementation, the average temperature of pixels in the cropped infrared image whose temperature is less than D1, that is, the second average temperature data, can be used as the second grayscale threshold.

[0077] In one embodiment, the second average temperature data may be calculated according to the following formula (2):

[0078]

[0079] Wherein, D2 represents the second average temperature data, N(x, y)<D1 represents the pixels whose temperature data is less than the first grayscale threshold, and h represents the number of pixels satisfying N(x, y)<D1.

[0080] In one embodiment, the formula of the preset piecewise mapping function may be formula (3):

[0081]

[0082] Among them, t(x, y) represents the grayscale value corresponding to the pixel with coordinates (x, y) in the new grayscale image, g(x, y) represents the grayscale value corresponding to the pixel with coordinates (x, y) in the grayscale image, Hmin represents the minimum grayscale value in the grayscale image; D2 represents the second grayscale threshold; D1 represents the first grayscale threshold, Hmax represents the maximum grayscale value in the grayscale image; k represents the stretching strength factor.

[0083] In specific implementation, the piecewise mapping function is set according to the distribution characteristics of the temperature field of the infrared image of water leakage from the cracked lining, that is, the piecewise mapping is performed through the above-mentioned first grayscale threshold and the second grayscale threshold. The piecewise mapping function compresses the background grayscale mapping range and stretches the target grayscale mapping range, and divides the entire image into three areas according to the grayscale: background area (dry lining area), transition area (wet lining area) and target area (cracked lining area).

[0084] In specific implementation, in the above step 104, for the disease identification based on the infrared image, the cropped infrared image can also be converted into grayscale to represent the temperature distribution of the scene in the form of a grayscale image. It should be noted that in the grayscale image, each pixel corresponds to a grayscale value.

[0085] In specific implementation, in the above step 104, the grayscale image can be mapped according to the first grayscale threshold, the second grayscale threshold and the preset piecewise mapping function, so that the image can be processed by graphic gain to improve the grayscale contrast of the lining crack area.

[0086] In specific implementation, according to the formula (3) of the above-mentioned piecewise mapping function, when the grayscale value g(x, y) corresponding to each pixel of the grayscale image is mapped to the grayscale value t(x, y) corresponding to the pixel of the new grayscale image, different grayscale mappings are adopted for different temperature zones. The background area is forced to be compressed, that is, t(x, y) = Hmin, to weaken the grayscale response of the dry lining; the transition area is subjected to grayscale linear compression mapping, that is, t(x, y) = g(x, y)-D2, which can maintain the grayscale level of image details while reducing the grayscale interference of the wet lining; the target area is subjected to grayscale stretching mapping, that is, The grayscale intensity of the cracked lining area can be improved to achieve a strong contrast grayscale response of the detection target with a low size ratio and a small temperature difference. Among them, the grayscale stretching mapping of the target area adopts a sine function, whose derivative is smooth and has good grayscale stretching performance. k is the stretching strength factor. The increase of k value increases the grayscale change speed. For general infrared image enhancement processing, the k value is 1 to 6, which can be selected according to the actual enhancement needs and is not limited here.

[0087] In one embodiment, each pixel of the cropped infrared image corresponds to a temperature data; Figure 3 FIG. 1 is a flow chart of a method for performing image recognition on a new grayscale image and determining a second recognition result provided in an embodiment of the present invention. Figure 3 As shown, it may specifically include:

[0088] Step 301, determining an optimal image segmentation threshold according to a second grayscale threshold, the number of pixels in the damaged lining area, and the grayscale value corresponding to each pixel in the damaged lining area;

[0089] Step 302, using the optimal image segmentation threshold, binarizes the new grayscale image to obtain an infrared binary image;

[0090] Step 303, using the Canny edge detection algorithm to perform edge detection on the infrared binary image to determine the contour information of the infrared image;

[0091] Step 304: Determine a second recognition result according to the contour information of the infrared image.

[0092] During specific implementation, in the above step 301, the optimal image segmentation threshold may be determined according to the second grayscale threshold, the number of pixels in the damaged lining area, and the grayscale value corresponding to each pixel in the damaged lining area.

[0093] In one embodiment, Figure 4 Flow chart of a method for determining an optimal image segmentation threshold according to a second grayscale threshold, the number of pixels in a damaged lining area, and the grayscale value corresponding to each pixel in the damaged lining area provided in an embodiment of the present invention, as shown in FIG. Figure 4 As shown, it may specifically include:

[0094] Step 401, using the second gray threshold as the lower limit of the image segmentation threshold;

[0095] Step 402, determining the upper limit of the image segmentation threshold according to the number of pixels in the cracked lining area and the gray value corresponding to each pixel in the cracked lining area;

[0096] Step 403, determining the image segmentation threshold range according to the lower limit and the upper limit of the image segmentation threshold;

[0097] Step 404: Use the OTSU algorithm to solve the image segmentation threshold range and determine the optimal image segmentation threshold.

[0098] In specific implementation, in order to ensure complete segmentation of the target, the second grayscale threshold D2 can be used as the lower limit of the image segmentation threshold; and the upper limit of the image segmentation threshold is calculated based on the number of pixels in the cracked lining area of ​​the new grayscale image and the grayscale value corresponding to each pixel in the cracked lining area.

[0099] In one embodiment, the upper limit of the image segmentation threshold can be determined according to the following formula (4):

[0100]

[0101] Among them, Tmax is the upper limit of the image segmentation threshold, Tmin is the lower limit of the image segmentation threshold, t(x, y)>Tmin represents the cracked lining area, t(x, y) represents the grayscale value corresponding to the pixel with coordinates (x, y) in the cracked lining area, and z represents the number of pixels in the cracked lining area.

[0102] In specific implementation, after obtaining the lower limit and the upper limit of the image segmentation threshold, the image segmentation threshold range can be determined as [Tmin, Tmax]. Then, the image segmentation threshold range [Tmin, Tmax] is solved based on the OTSU algorithm to determine the optimal image segmentation threshold T.

[0103] In the above steps 302, 303 and 304, the optimal image segmentation threshold can be used to perform binarization processing on the new grayscale image to obtain an infrared binary image; the Canny edge detection algorithm can be used to perform edge detection on the infrared binary image to determine the contour information of the infrared image; based on the contour information of the infrared image, the second recognition result is determined, that is, the lining crack and water leakage information is determined.

[0104] In the above step 105, the tunnel lining apparent disease information can be determined according to the first recognition result and the second recognition result.

[0105] In specific implementation, the first recognition result and the second recognition result can be combined to obtain the tunnel lining apparent disease information.

[0106] In one embodiment, in order to ensure the accuracy of the identified tunnel lining apparent disease information, in the above step 105, the cropped visible light image and the cropped infrared image can also be combined to jointly compare the first recognition result and the second recognition result in the same position and the same field of view. If one recognition result identifies a defect, it is marked as a defect, and the tunnel lining apparent disease information is summarized and output.

[0107] In one embodiment, after the above step 105, the following steps may also be included:

[0108] Issue early warning information based on apparent tunnel lining disease information.

[0109] In specific implementation, data analysis can be performed on the apparent disease information of the tunnel lining to issue early warning information and form a detection report.

[0110] In summary, based on the above-mentioned tunnel lining apparent disease recognition method, the tunnel lining apparent disease is jointly identified by using the visible light image and infrared image of the tunnel lining surface. Through multi-dimensional image information, the characteristics of the lining apparent disease can be enhanced, misjudgment and omission can be avoided, and the accuracy of the tunnel lining apparent disease recognition results can be improved.

[0111] The present invention also provides a tunnel lining apparent disease identification device, as described in the following embodiments. Since the principle of the device to solve the problem is similar to the tunnel lining apparent disease identification method, the implementation of the device can refer to the implementation of the tunnel lining apparent disease identification method, and the repeated parts will not be repeated.

[0112] like Figure 5 FIG. 1 is a schematic diagram of a tunnel lining surface defect identification device provided by an embodiment of the present invention, and the device may include:

[0113] The acquisition module 501 is used to acquire the collected tunnel lining surface image; the tunnel lining surface image includes a visible light image and an infrared image of the tunnel lining surface;

[0114] A cropping module 502 is used to crop the overlapping area of ​​the visible light image and the infrared image to obtain a cropped visible light image and a cropped infrared image;

[0115] The first recognition module 503 is used to identify tunnel lining surface defects on the cropped visible light image using a preset first intelligent recognition algorithm to determine a first recognition result;

[0116] The second recognition module 504 is used to use a preset second intelligent recognition algorithm to perform tunnel lining surface disease recognition on the cropped infrared image and determine a second recognition result, which includes: calculating a grayscale threshold according to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel; performing grayscale conversion on the cropped infrared image to obtain a grayscale image; mapping the grayscale image according to the grayscale threshold and a preset piecewise mapping function to obtain a new grayscale image; the new grayscale image includes a dry lining area, a wet lining area and a cracked lining area; performing image recognition on the new grayscale image to determine a second recognition result;

[0117] The disease information determination module 505 is used to determine the apparent disease information of the tunnel lining according to the first recognition result and the second recognition result.

[0118] In one embodiment, the cropping module 502 may be specifically configured to:

[0119] Based on the preset image registration algorithm, the visible light image and the infrared image are registered;

[0120] The overlapping area of ​​the registered visible light image and the infrared image is intercepted to obtain a cropped visible light image and a cropped infrared image.

[0121] In one embodiment, the first identification module 503 may be specifically used for:

[0122] The Gaussian filtering algorithm is used to reduce the noise of the cropped visible light image;

[0123] Binarizing the visible light image after the noise reduction process to obtain a visible light binary image;

[0124] The Canny edge detection algorithm is used to perform edge detection on the visible light binary image to determine the contour information of the visible light image;

[0125] A first recognition result is determined according to the contour information of the visible light image.

[0126] In one embodiment, the grayscale threshold may include a first grayscale threshold and a second grayscale threshold; the second recognition module 504 may also be used to:

[0127] Calculate first average temperature data according to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel, and use the first average temperature data as a first grayscale threshold;

[0128] Determine, from the temperature data corresponding to each pixel of the cropped infrared image, a pixel whose temperature data is less than a first grayscale threshold;

[0129] The second average temperature data is calculated according to the temperature data of the pixels whose temperature data is less than the first gray threshold and the number of pixels, and the second average temperature data is used as the second gray threshold.

[0130] In one embodiment, the second identification module 504 can also be used to

[0131] The first average temperature data is calculated according to the following formula:

[0132]

[0133] Among them, D1 represents the first average temperature data, m represents the number of pixels of the cropped infrared image in the x-axis direction, n represents the number of pixels of the cropped infrared image in the y-axis direction, and N(x, y) represents the temperature data corresponding to the pixel with coordinates (x, y).

[0134] In one embodiment, the second identification module 504 may also be used to:

[0135] The second average temperature data is calculated according to the following formula:

[0136]

[0137] Wherein, D2 represents the second average temperature data, N(x, y)<D1 represents the pixels whose temperature data is less than the first grayscale threshold, and h represents the number of pixels satisfying N(x, y)<D1.

[0138] In one embodiment, the formula of the preset piecewise mapping function may be:

[0139]

[0140] Among them, t(x, y) represents the grayscale value corresponding to the pixel with coordinates (x, y) in the new grayscale image, g(x, y) represents the grayscale value corresponding to the pixel with coordinates (x, y) in the grayscale image, Hmin represents the minimum grayscale value in the grayscale image; D2 represents the second grayscale threshold; D1 represents the first grayscale threshold, Hmax represents the maximum grayscale value in the grayscale image; k represents the stretching strength factor.

[0141] In one embodiment, each pixel of the cropped infrared image corresponds to a temperature data;

[0142] The second identification module 504 may be specifically used for:

[0143] Determine the optimal image segmentation threshold according to the second grayscale threshold, the number of pixels in the cracked lining area, and the grayscale value corresponding to each pixel in the cracked lining area;

[0144] Using the optimal image segmentation threshold, the new grayscale image is binarized to obtain an infrared binary image.

[0145] The Canny edge detection algorithm is used to perform edge detection on the infrared binary image to determine the contour information of the infrared image;

[0146] A second recognition result is determined according to the contour information of the infrared image.

[0147] In one embodiment, the second identification module 504 may also be used to:

[0148] The second grayscale threshold is used as the lower limit of the image segmentation threshold;

[0149] According to the number of pixels in the cracked lining area and the gray value corresponding to each pixel in the cracked lining area, the upper limit of the image segmentation threshold is determined;

[0150] Determine the image segmentation threshold range according to the lower limit and upper limit of the image segmentation threshold;

[0151] The OTSU algorithm is used to solve the image segmentation threshold range and determine the optimal image segmentation threshold.

[0152] In one embodiment, the second identification module 504 may also be used to:

[0153] The upper limit of the image segmentation threshold is determined according to the following formula:

[0154]

[0155] Among them, Tmax is the upper limit of the image segmentation threshold, Tmin is the lower limit of the image segmentation threshold, t(x, y)>Tmin represents the cracked lining area, t(x, y) represents the grayscale value corresponding to the pixel with coordinates (x, y) in the cracked lining area, and z represents the number of pixels in the cracked lining area.

[0156] In one embodiment, the first recognition result includes the damage information of cracks and falling blocks; the second recognition result includes the water leakage information of lining cracks.

[0157] The embodiment of the present invention also provides a computer device, such as Figure 6 As shown, it is a schematic diagram of a computer device in an embodiment of the present invention. The computer device 600 includes a memory 610, a processor 620, and a computer program 630 stored in the memory 610 and executable on the processor 620. When the processor 620 executes the computer program 630, the above-mentioned method for identifying apparent defects of tunnel lining is implemented.

[0158] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for identifying apparent defects in tunnel lining is implemented.

[0159] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the above-mentioned method for identifying apparent defects in tunnel lining is implemented.

[0160] In an embodiment of the present invention, a collected tunnel lining surface image is obtained; the tunnel lining surface image includes a visible light image and an infrared image of the tunnel lining surface; the overlapping area of ​​the visible light image and the infrared image is cropped to obtain a cropped visible light image and a cropped infrared image; a preset first intelligent recognition algorithm is used to identify tunnel lining surface defects on the cropped visible light image to determine a first recognition result; a preset second intelligent recognition algorithm is used to identify tunnel lining surface defects on the cropped infrared image to determine a second recognition result, which includes: calculating a grayscale threshold according to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel; grayscale conversion is performed on the cropped infrared image to obtain a grayscale image; the grayscale image is mapped according to the grayscale threshold and a preset piecewise mapping function to obtain a new grayscale image; the new grayscale image includes a dry lining area, a wet lining area and a cracked lining area; image recognition is performed on the new grayscale image to determine a second recognition result; and tunnel lining surface defect information is determined according to the first recognition result and the second recognition result. Compared with the existing method for identifying apparent defects of tunnel lining, the embodiment of the present invention uses the visible light image and infrared image of the tunnel lining surface to jointly identify the apparent defects of the tunnel lining. Through multi-dimensional image information, the characteristics of the apparent defects of the lining can be enhanced, misjudgment and omission can be avoided, and the accuracy of the identification results of the apparent defects of the tunnel lining can be improved.

[0161] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0162] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0163] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0164] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0165] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for identifying apparent defects in tunnel lining, characterized in that: include: Obtain the collected tunnel lining surface image; The tunnel lining surface image includes a visible light image and an infrared image of the tunnel lining surface; Performing image cropping on the overlapping area of ​​the visible light image and the infrared image to obtain a cropped visible light image and a cropped infrared image; Using a preset first intelligent recognition algorithm, the cropped visible light image is used to identify apparent defects of the tunnel lining, and a first recognition result is determined; Using the preset second intelligent recognition algorithm, the cropped infrared image is used to identify the apparent defects of the tunnel lining, and a second recognition result is determined, which includes: calculating the grayscale threshold according to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel; performing grayscale conversion on the cropped infrared image to obtain a grayscale image; mapping the grayscale image according to the grayscale threshold and a preset piecewise mapping function to obtain a new grayscale image; the new grayscale image includes a dry lining area, a wet lining area and a cracked lining area; performing image recognition on the new grayscale image to determine the second recognition result; The apparent disease information of the tunnel lining is determined based on the first recognition result and the second recognition result.

2. The method according to claim 1, characterized in that Perform image cropping on the overlapping area of ​​the visible light image and the infrared image to obtain a cropped visible light image and a cropped infrared image, including: Based on the preset image registration algorithm, the visible light image and the infrared image are registered; The overlapping area of ​​the registered visible light image and the infrared image is intercepted to obtain a cropped visible light image and a cropped infrared image.

3. The method according to claim 1, characterized in that Using the preset first intelligent recognition algorithm, the cropped visible light image is used to identify apparent defects in the tunnel lining, and a first recognition result is determined, including: The Gaussian filtering algorithm is used to reduce the noise of the cropped visible light image; Binarizing the visible light image after the noise reduction process to obtain a visible light binary image; The Canny edge detection algorithm is used to perform edge detection on the visible light binary image to determine the contour information of the visible light image; A first recognition result is determined according to the contour information of the visible light image.

4. The method according to claim 1, characterized in that The grayscale threshold includes a first grayscale threshold and a second grayscale threshold; According to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel, the grayscale threshold is calculated, including: Calculate first average temperature data according to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel, and use the first average temperature data as a first grayscale threshold; Determine, from the temperature data corresponding to each pixel of the cropped infrared image, a pixel whose temperature data is less than a first grayscale threshold; The second average temperature data is calculated according to the temperature data of the pixels whose temperature data is less than the first grayscale threshold and the number of pixels, and the second average temperature data is used as the second grayscale threshold.

5. The method according to claim 4, characterized in that Calculating first average temperature data according to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel; comprising: The first average temperature data is calculated according to the following formula: Among them, D1 represents the first average temperature data, m represents the number of pixels of the cropped infrared image in the x-axis direction, n represents the number of pixels of the cropped infrared image in the y-axis direction, and N(x, y) represents the temperature data corresponding to the pixel with coordinates (x, y).

6. The method according to claim 5, characterized in that Calculating second average temperature data according to the temperature data of pixels whose temperature data is less than the first grayscale threshold and the number of pixels includes: The second average temperature data is calculated according to the following formula: Wherein, D2 represents the second average temperature data, N(x, y)<D1 represents the pixels whose temperature data is less than the first grayscale threshold, and h represents the number of pixels satisfying N(x, y)<D1.

7. The method according to claim 6, characterized in that The formula of the preset piecewise mapping function is: Among them, t(x, y) represents the grayscale value corresponding to the pixel with coordinates (x, y) in the new grayscale image, g(x, y) represents the grayscale value corresponding to the pixel with coordinates (x, y) in the grayscale image, Hmin represents the minimum grayscale value in the grayscale image; D2 represents the second grayscale threshold; D1 represents the first grayscale threshold, Hmax represents the maximum grayscale value in the grayscale image; k represents the stretching strength factor.

8. The method according to claim 4, characterized in that Each pixel of the cropped infrared image corresponds to a temperature data; Performing image recognition on the new grayscale image to determine a second recognition result includes: Determine the optimal image segmentation threshold according to the second grayscale threshold, the number of pixels in the cracked lining area, and the grayscale value corresponding to each pixel in the cracked lining area; Using the optimal image segmentation threshold, the new grayscale image is binarized to obtain an infrared binary image. The Canny edge detection algorithm is used to perform edge detection on the infrared binary image to determine the contour information of the infrared image; A second recognition result is determined according to the contour information of the infrared image.

9. The method according to claim 8, characterized in that According to the second grayscale threshold, the number of pixels in the damaged lining area and the grayscale value corresponding to each pixel in the damaged lining area, an optimal image segmentation threshold is determined, including: The second grayscale threshold is used as the lower limit of the image segmentation threshold; According to the number of pixels in the cracked lining area and the gray value corresponding to each pixel in the cracked lining area, the upper limit of the image segmentation threshold is determined; Determine the image segmentation threshold range according to the lower limit and upper limit of the image segmentation threshold; The OTSU algorithm is used to solve the image segmentation threshold range and determine the optimal image segmentation threshold.

10. The method according to claim 9, characterized in that According to the number of pixels in the cracked lining area and the gray value corresponding to each pixel in the cracked lining area, the upper limit of the image segmentation threshold is determined, including: The upper limit of the image segmentation threshold is determined according to the following formula: Among them, Tmax is the upper limit of the image segmentation threshold, Tmin is the lower limit of the image segmentation threshold, t(x, y)>Tmin represents the cracked lining area, t(x, y) represents the grayscale value corresponding to the pixel with coordinates (x, y) in the cracked lining area, and z represents the number of pixels in the cracked lining area.

11. The method according to claim 1, characterized in that The first recognition result includes the damage information of cracks and falling blocks; the second recognition result includes the information of lining cracks and water leakage.

12. A tunnel lining surface disease identification device, characterized in that: include: An acquisition module, used for acquiring the collected tunnel lining surface image; The tunnel lining surface image includes a visible light image and an infrared image of the tunnel lining surface; A cropping module, used for cropping the overlapping area of ​​the visible light image and the infrared image to obtain a cropped visible light image and a cropped infrared image; A first recognition module is used to identify tunnel lining surface defects on the cropped visible light image using a preset first intelligent recognition algorithm to determine a first recognition result; The second recognition module is used to use a preset second intelligent recognition algorithm to identify tunnel lining surface defects on the cropped infrared image and determine a second recognition result, which includes: calculating a grayscale threshold according to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel; performing grayscale conversion on the cropped infrared image to obtain a grayscale image; mapping the grayscale image according to the grayscale threshold and a preset piecewise mapping function to obtain a new grayscale image; the new grayscale image includes a dry lining area, a wet lining area and a cracked lining area; performing image recognition on the new grayscale image to determine a second recognition result; The disease information determination module is used to determine the apparent disease information of the tunnel lining according to the first recognition result and the second recognition result.

13. The device according to claim 12, characterized in that The cropping module is specifically used for: Based on the preset image registration algorithm, the visible light image and the infrared image are registered; The overlapping area of ​​the registered visible light image and the infrared image is intercepted to obtain a cropped visible light image and a cropped infrared image.

14. The device according to claim 12, characterized in that The first identification module is specifically used for: The Gaussian filtering algorithm is used to reduce the noise of the cropped visible light image; Binarizing the visible light image after the noise reduction process to obtain a visible light binary image; The Canny edge detection algorithm is used to perform edge detection on the visible light binary image to determine the contour information of the visible light image; A first recognition result is determined according to the contour information of the visible light image.

15. The device according to claim 12, characterized in that The grayscale threshold includes a first grayscale threshold and a second grayscale threshold; the second recognition module is further used for: Calculate first average temperature data according to the number of pixels of the cropped infrared image and the temperature data corresponding to each pixel, and use the first average temperature data as a first grayscale threshold; Determine, from the temperature data corresponding to each pixel of the cropped infrared image, a pixel whose temperature data is less than a first grayscale threshold; The second average temperature data is calculated according to the temperature data of the pixels whose temperature data is less than the first grayscale threshold and the number of pixels, and the second average temperature data is used as the second grayscale threshold.

16. The device according to claim 15, characterized in that The second identification module is further used for: The first average temperature data is calculated according to the following formula: Among them, D1 represents the first average temperature data, m represents the number of pixels of the cropped infrared image in the x-axis direction, n represents the number of pixels of the cropped infrared image in the y-axis direction, and N(x, y) represents the temperature data corresponding to the pixel with coordinates (x, y).

17. The device according to claim 16, characterized in that The second identification module is further used for: The second average temperature data is calculated according to the following formula: Wherein, D2 represents the second average temperature data, N(x, y)<D1 represents the pixels whose temperature data is less than the first grayscale threshold, and h represents the number of pixels satisfying N(x, y)<D1.

18. The device according to claim 17, characterized in that The formula of the preset piecewise mapping function is: Among them, t(x, y) represents the grayscale value corresponding to the pixel with coordinates (x, y) in the new grayscale image, g(x, y) represents the grayscale value corresponding to the pixel with coordinates (x, y) in the grayscale image, Hmin represents the minimum grayscale value in the grayscale image; D2 represents the second grayscale threshold; D1 represents the first grayscale threshold, Hmax represents the maximum grayscale value in the grayscale image; k represents the stretching strength factor.

19. The device according to claim 15, characterized in that Each pixel of the cropped infrared image corresponds to a temperature data; The second identification module is specifically used for: Determine the optimal image segmentation threshold according to the second grayscale threshold, the number of pixels in the cracked lining area, and the grayscale value corresponding to each pixel in the cracked lining area; Using the optimal image segmentation threshold, the new grayscale image is binarized to obtain an infrared binary image. The Canny edge detection algorithm is used to perform edge detection on the infrared binary image to determine the contour information of the infrared image; A second recognition result is determined according to the contour information of the infrared image.

20. The device according to claim 19, characterized in that The second identification module is further used for: The second grayscale threshold is used as the lower limit of the image segmentation threshold; According to the number of pixels in the cracked lining area and the gray value corresponding to each pixel in the cracked lining area, the upper limit of the image segmentation threshold is determined; Determine the image segmentation threshold range according to the lower limit and upper limit of the image segmentation threshold; The OTSU algorithm is used to solve the image segmentation threshold range and determine the optimal image segmentation threshold.

21. The device according to claim 20, characterized in that The second identification module is further used for: The upper limit of the image segmentation threshold is determined according to the following formula: Among them, Tmax is the upper limit of the image segmentation threshold, Tmin is the lower limit of the image segmentation threshold, t(x, y)>Tmin represents the cracked lining area, t(x, y) represents the grayscale value corresponding to the pixel with coordinates (x, y) in the cracked lining area, and z represents the number of pixels in the cracked lining area.

22. The device according to claim 12, characterized in that The first recognition result includes the damage information of cracks and falling blocks; the second recognition result includes the information of lining cracks and water leakage.

23. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 11 is implemented.

24. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

25. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Citation Information

Cited By

  • Comprehensive detection method and device for tunnel defects and storage medium

    CN122048822A