Image gain identification method and system based on temperature field distribution of tunnel seepage water

Abstract

The application provides an image gain identification method and system based on a temperature field distribution of tunnel seepage water, which comprises the following steps: acquiring an infrared thermal image of a suspected seepage water area of a tunnel; extracting a temperature value of each pixel in the infrared thermal image; extracting an inflection point temperature of a thermal image gray mapping piecewise function based on the extracted temperature value of the pixel; obtaining a piecewise function based on the inflection point temperature; re-performing thermal image gray mapping based on the piecewise function, compressing the gray mapping of a background area, i.e. a non-crack damage area, stretching the gray mapping of an identification target area, i.e. a crack damage area, and constructing a piecewise function gain gray mapping image; solving an optimal segmentation threshold value of the piecewise function gain gray mapping image, and binarizing the gain gray mapping image; and performing contour detection on the binarized image to identify a crack damage form of a lining in the seepage water area.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of tunnel disease detection, and particularly relates to an image gain recognition method and system based on tunnel seepage water temperature field distribution. BACKGROUND

[0002] The statements in this section merely provide background information related to the present application and do not necessarily constitute prior art.

[0003] The infrared thermal image reflects the spatial distribution of the infrared radiation of the identification target and background, and the image brightness distribution is mainly determined by the temperature and emissivity of the observed object, so the infrared thermal image approximately reflects the temperature difference of the object.

[0004] Seepage water is a common disease of tunnels, and due to the difference in thermal conductivity between concrete and water in the tunnel, the seepage water in the tunnel will break the temperature balance of the cracked and damaged area of the tunnel lining. The identification and positioning of the seepage water in the lining crack based on the infrared image needs to consider two main factors of the identification algorithm for extracting the features of the cracked area:

[0005] (1) target contrast;

[0006] (2) background interference.

[0007] The seepage water in the tunnel lining is often a long development and accumulation process, and the relatively stable temperature environment of the tunnel causes the surface temperature of the cracked area of the lining to be smaller than the surface temperature of the intact area. This phenomenon reduces the clarity of the cracked target in the infrared thermal image and intensifies the noise interference of the background area, which in turn leads to low accuracy of the identification of the seepage water in the lining crack based on the infrared image. SUMMARY

[0008] In order to overcome the shortcomings of the prior art, the present application provides an image gain recognition method based on the temperature field distribution of tunnel seepage water, which processes the gain of the infrared image, enhances the contrast of the infrared image, and suppresses the background interference to reduce the difficulty of image recognition.

[0009] To achieve the above object, one or more embodiments of the present application provide the following technical solutions:

[0010] In a first aspect, an image gain recognition method based on the temperature field distribution of tunnel seepage water is disclosed, comprising:

[0011] obtaining an infrared thermal image of a suspected seepage water area of a tunnel;

[0012] extracting the temperature value of each pixel in the infrared thermal image, extracting the inflection point temperature of the thermal image gray mapping piecewise function based on the extracted temperature value of the pixel, and obtaining the piecewise function based on the inflection point temperature;

[0013] The segmented function is used to re-map the thermal image gray scale, compress the gray scale of the background area, i.e. the non-crack area, stretch the gray scale of the target area, i.e. the crack area, and construct a segmented function gain gray scale mapping image.

[0014] The optimal segmentation threshold of the segmented function gain gray scale mapping image is solved, and the gain gray scale mapping image is binarized.

[0015] The binarized image is subjected to contour detection to identify the crack form of the lining in the leaking water area.

[0016] As a further technical solution, the inflection point temperature of the thermal image gray scale mapping segmented function is extracted based on the extracted temperature values of the pixels, specifically:

[0017] The temperature value of each pixel of the infrared thermal image is extracted, and the average temperature value of the entire infrared thermal image is used as the parameter of the first inflection point.

[0018] The average temperature value of the pixels in the area with a temperature less than the first inflection point is used as the parameter of the second inflection point.

[0019] As a further technical solution, the thermal image gray scale mapping is re-performed based on the segmented function, specifically:

[0020] Based on the obtained first and second inflection points, the thermal image gray scale mapping is re-performed by the segmented function to obtain a gain infrared thermal image.

[0021] The first segment of the segmented function is a parallel line mapping, which plays a role in forcibly compressing the image gray scale; the second segment is a normal linear mapping for reducing the gray scale, which plays a role in suppressing the gray scale intensity of the area; and the third segment is a sinusoidal function mapping, which plays a role in stretching the gray scale intensity of the area.

[0022] As a further technical solution, the first inflection point forcibly filters out the gray scale response of part of the dry lining.

[0023] The infrared thermal image pixels with a temperature less than the second inflection point include part of the wet lining and the crack lining, and the gray scale value corresponding to the second inflection point of the temperature is set as the lower limit of the image segmentation threshold.

[0024] As a further technical solution, the gray scale value of the crack lining is higher than the threshold lower limit determined by the temperature mean value of the wet lining with a large proportion.

[0025] As a further technical solution, the threshold lower limit divides the image into two parts, the gray scale mean value of the sinusoidal function stretching mapping area of the infrared thermal image is calculated as the threshold upper limit, n is the total number of pixels in the area, and the optimal threshold range is determined based on the threshold upper limit and the threshold lower limit.

[0026] As a further technical solution, the Ostu algorithm is used to solve the optimal segmentation threshold based on the upper threshold and the lower threshold, and the infrared thermal image is binarized.

[0027] As a further technical solution, the Canny edge detection algorithm is used to detect the contour of the binarized image, and the crack form of the lining is identified.

[0028] In a second aspect, an image gain identification system based on the temperature field distribution of tunnel water leakage is disclosed, comprising:

[0029] The infrared thermal image acquisition module is configured to acquire an infrared thermal image of a suspected water leakage area of the tunnel;

[0030] The piecewise function acquisition module is configured to extract the temperature value of each pixel in the infrared thermal image, extract the inflection point temperature of the thermal image gray mapping piecewise function based on the extracted temperature value of the pixel, and obtain the piecewise function based on the inflection point temperature.

[0031] The gain gray mapping image construction module is configured to perform thermal image gray mapping again based on the piecewise function, compress the gray mapping of the background area, i.e., the non-crack area, stretch the gray mapping of the identification target area, i.e., the crack area, and construct a piecewise function gain gray mapping image.

[0032] The binarization module is configured to solve the optimal segmentation threshold of the piecewise function gain gray mapping image, and binarize the gain gray mapping image.

[0033] The water leakage area identification module is configured to detect the contour of the binarized image, and identify the crack form of the lining in the water leakage area.

[0034] The above one or more technical solutions have the following beneficial effects:

[0035] The technical solution of the present application is based on the feature that the temperature distribution of each area of the tunnel water leakage area conforms to the piecewise linear function, and through the piecewise function gray gain mapping, the gray mapping of the background area, i.e., the non-crack area, is compressed, and the gray mapping of the identification target area, i.e., the crack area, is stretched, the image contrast of the crack lining area is enhanced, the redundant and invalid water mark area infrared thermal imaging data is indirectly filtered out, the workload of image analysis is greatly reduced, and the image recognition efficiency and speed are improved. The image segmentation threshold is solved through the gain image, the accuracy of image segmentation is improved, and the lining crack identification accuracy is improved.

[0036] The advantages of the additional aspects of the present application will be partially given in the following description, partially will become apparent from the following description, or will be understood by the practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0037] The accompanying drawings, which form a part of this specification, are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification. The embodiments of the application, and their

[0038] Figure 1 A segmented gray scale mapping curve schematic diagram of an image gain recognition method based on tunnel seepage water temperature field distribution characteristics provided by an embodiment of the application;

[0039] Figure 2 A general flowchart schematic diagram of an image gain recognition method based on tunnel seepage water temperature field distribution characteristics provided by an embodiment of the application;

[0040] Figure 3 A specific flowchart schematic diagram of an image gain recognition method based on tunnel seepage water temperature field distribution characteristics provided by an embodiment of the application;

[0041] Figure 4 A display effect diagram of an image gain recognition method based on tunnel seepage water temperature field distribution characteristics provided by an embodiment of the application. DETAILED DESCRIPTION

[0042] It should be noted that the following detailed description is merely exemplary in nature and is intended to provide further description of the application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0043] It is to be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments consistent with the present application.

[0044] In the case of no conflict, the embodiments in the application and the features in the embodiments can be combined with each other.

[0045] Embodiment one

[0046] The embodiment discloses an image gain recognition method based on tunnel seepage water temperature field distribution, and the overall steps include:

[0047] Referring to the accompanying drawings Figure 2 As shown in the drawings, first, an infrared thermal image of a suspected seepage water area of a tunnel is acquired;

[0048] The temperature value of each pixel of the thermal image is extracted to obtain temperature field data of the seepage water lining;

[0049] Based on the temperature field data, the inflection point temperature of the thermal image gray scale mapping segmented function is extracted;

[0050] By using a piecewise function, the grayscale mapping of the thermal image is re-performed based on the piecewise function. The grayscale mapping of the background area, i.e., the non-cracked area, is compressed, while the grayscale mapping of the target area, i.e., the cracked area, is stretched. A piecewise function gain grayscale mapping image is constructed to improve the recognizability of the target area.

[0051] Then, the optimal segmentation threshold of the gain thermal image is solved based on the temperature field, and the infrared thermal image is binarized.

[0052] Finally, contour detection was performed using the Canny edge detection algorithm to identify the lining crack patterns.

[0053] For more details, see the appendix. Figure 3 As shown, this embodiment discloses an image gain recognition method based on the temperature field distribution of tunnel seepage water. The overall steps include:

[0054] Step 1: Obtain infrared thermal images of the suspected water leakage area in the tunnel. Extract the temperature value of each pixel in the infrared thermal image. Use the average temperature value of the entire infrared thermal image as the parameter for inflection point 1, as shown in Equation 1. Use the average temperature value of pixels in areas with temperatures lower than the temperature value of inflection point 1 as the parameter for inflection point 2, as shown in Equation 2, where m is the temperature... (x，y) The number of pixels less than or equal to inflection point 1.

[0055]

[0056]

[0057] Where M is the total number of pixels in the X direction of the infrared image, and N is the total number of pixels in the Y direction of the infrared image.

[0058] Step 2: Based on the obtained piecewise inflection points, the infrared thermal image grayscale mapping is re-performed using the piecewise function shown in Equation 3, combined with... Figure 1 As shown, according to Formula 3, a gain infrared thermal image is obtained by segmented mapping. This gain infrared thermal image is used to make the target area more obvious.

[0059] See appendix Figure 1 As shown, the first segment of the piecewise function is a parallel line mapping, which forcibly compresses the grayscale of the infrared thermal image; the second segment is a normal linear mapping that reduces grayscale, which suppresses the grayscale intensity of the affected area, i.e., the lining crack area; the third segment is a sine function mapping, which stretches the grayscale intensity of the affected area. Inflection point 1 is both the corresponding temperature value and the grayscale value of that temperature value in the classical linear mapping. Gray1 represents the parameter of inflection point 1, and gray2 represents the parameter of inflection point 2; gray... min The minimum grayscale value of the infrared image temperature field is obtained through a classical linear mapping function.

[0060]

[0061] Where, f(x, y) is the classical linear mapping function. Gray min is the minimum gray value of the infrared image temperature field through the classical linear mapping function, and gray max is the maximum gray value of the infrared image temperature field through the classical linear mapping function. K is the stretching intensity factor, and is generally taken as 1-6 based on experimental verification.

[0062] Step three: through the gray gain mapping of the infrared thermal image temperature field distribution, the temperature inflection point 1 forces the gray response of part of the dry lining to be filtered out. Through the analysis of the heat transfer process of the tunnel water leakage lining, the infrared thermal image pixels with a temperature less than the inflection point 2 include part of the wet lining and the cracked lining. In order to ensure the complete segmentation of the target, the gray value corresponding to the temperature inflection point 2 is set as the lower limit of the image segmentation threshold T min .

[0063] Based on the sine function stretching gray mapping, the gray value of the cracked area is sharply enhanced, and the gray contrast of the cracked lining and the wet lining is improved. Therefore, the gray value of the cracked lining must be higher than the threshold lower limit T min determined by the temperature mean value of the wet lining with a large proportion. The threshold lower limit T min The image is segmented into two parts, as shown in equation 4, and the gray mean value of the infrared thermal image sine function stretching mapping area (combined with the attached Figure 1 , the sine function stretching mapping area is the area corresponding to the third paragraph of formula 3) is taken as the threshold upper limit T max , and the total number of pixels in the area is n. The best threshold range is determined as [T min , T max ]; for the image after the gray mapping of the segmented function, based on the best threshold range, the best segmentation threshold T is solved by using the Ostu algorithm, and the infrared thermal image is binarized;

[0064]

[0065] The total number of pixels in the area is n, and the area is the area of the infrared image that meets the condition of formula 4, that is, the gray value obtained by the function g(x, y) mapping function is greater than T min , that is, the total number of all pixels that meet the condition.

[0066] The gray value of the infrared image of a certain pixel (x, y) mapped by the classical linear function f(x, y) is transformed into another gray value by the g(x, y) segmented function.

[0067] Binarization of the infrared thermal image: the gain of the infrared thermal image is binarized through the segmentation threshold T.

[0068] Step four: the contour detection of the binarized image is carried out through the Canny edge detection algorithm, and the cracking form of the lining is identified, including: point, horizontal line, vertical line, and diagonal line, as shown in the attachedFigure 4 As shown.

[0069] The technical solution of this invention can significantly improve the contrast between the cracked area and other areas, improve the speed and accuracy of lining crack detection, reduce the background noise of infrared images and the interference of wet lining, and realize rapid identification of cracks in water-leaking tunnels.

[0070] Example 2

[0071] The purpose of this embodiment is to provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the above-described method.

[0072] Example 3

[0073] The purpose of this embodiment is to provide a computer-readable storage medium.

[0074] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps of the above method.

[0075] Example 4

[0076] The purpose of this embodiment is to provide an image gain recognition system based on the temperature field distribution of tunnel seepage water, including:

[0077] The infrared thermal image acquisition module is configured to acquire infrared thermal images of areas in the tunnel suspected of water leakage.

[0078] The piecewise function acquisition module is configured to: extract the temperature value of each pixel in the infrared thermal image, extract the inflection point temperature of the grayscale mapping piecewise function of the thermal image based on the extracted pixel temperature value, and obtain the piecewise function based on the inflection point temperature.

[0079] The gain grayscale mapping image construction module is configured to: re-map the grayscale of the thermal image based on the piecewise function, compress the grayscale mapping of the background area (i.e., the non-cracked area), stretch the grayscale mapping of the target area (i.e., the cracked area), and construct the piecewise function gain grayscale mapping image.

[0080] The binarization module is configured to: solve for the optimal segmentation threshold of the piecewise function gain grayscale mapping image, and binarize the gain grayscale mapping image;

[0081] The leakage area identification module is configured to perform contour detection on the binarized image and identify the cracking patterns of the lining in the leakage area.

[0082] The steps and methods involved in the apparatuses of Embodiments 2, 3, and 4 above correspond to those in Embodiment 1. For specific implementation details, please refer to the relevant description section of Embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood as including any medium capable of storing, encoding, or carrying an instruction set for execution by a processor and enabling the processor to perform any of the methods in this invention.

[0083] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computer devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computer device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. The present invention is not limited to any particular combination of hardware and software.

[0084] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A tunnel leakage water temperature field distribution-based image gain identification method, characterized in that, The method comprises the following steps: acquiring an infrared thermal image of a suspected water leakage area of a tunnel; extracting temperature values of each pixel in the infrared thermal image, extracting an inflection point temperature of a thermal image grayscale mapping piecewise function based on the extracted temperature values of the pixels, and obtaining the piecewise function based on the inflection point temperature; re-performing thermal image grayscale mapping based on the piecewise function, compressing grayscale mapping of a background area, i.e., a non-crack damage area, stretching grayscale mapping of a target area, i.e., a crack damage area, and constructing a piecewise function gain grayscale mapping image, specifically as follows: extracting temperature values of each pixel in the infrared thermal image, and using an average temperature value of the entire infrared thermal image as a parameter of a first inflection point; using an average temperature value of pixels in a region with a temperature less than the first inflection point as a parameter of a second inflection point; re-performing thermal image grayscale mapping based on the obtained first and second inflection points, and obtaining a gain grayscale mapping image; wherein a first segment of the piecewise function is parallel line mapping, a second segment is normal linear mapping with reduced grayscale, and a third segment is sine function mapping; solving an optimal segmentation threshold value of the gain grayscale mapping image, and binarizing the gain grayscale mapping image through the segmentation threshold value; performing contour detection on the binarized image to identify a crack damage form of the lining in the water leakage area.

2. The tunnel seepage water temperature field distribution-based image gain identification method according to claim 1, characterized in that, The first inflection point filters out part of the grayscale response of dry lining; pixels of the infrared thermal image with a temperature less than the second inflection point include part of wet lining and crack damage lining, and a grayscale value corresponding to the second inflection point of the temperature is set as a lower limit of the image segmentation threshold value.

3. The tunnel seepage water temperature field distribution-based image gain identification method according to claim 2, characterized in that, using a grayscale mean value of a region stretched and mapped by the sine function of the gain grayscale mapping image as an upper limit of the threshold value, and determining an optimal threshold value range based on the upper limit of the threshold value and the lower limit of the threshold value.

4. The tunnel seepage water temperature field distribution-based image gain identification method according to claim 3, characterized in that, solving the optimal segmentation threshold value by using an Ostu algorithm based on the upper limit of the threshold value and the lower limit of the threshold value, and binarizing the gain grayscale mapping image through the segmentation threshold value.

5. The tunnel seepage water temperature field distribution-based image gain identification method according to claim 1, characterized in that, performing contour detection on the binarized image by using a Canny edge detection algorithm to identify the crack damage form of the lining.

6. An image gain recognition system based on temperature field distribution of tunnel seepage water, characterized in that, The method comprises the following steps: an infrared thermal image acquisition module configured to acquire an infrared thermal image of a suspected water leakage area of a tunnel; a piecewise function acquisition module configured to extract temperature values of each pixel in the infrared thermal image, extract an inflection point temperature of a thermal image grayscale mapping piecewise function based on the extracted temperature values of the pixels, and obtain the piecewise function based on the inflection point temperature; a gain grayscale mapping image construction module configured to re-perform thermal image grayscale mapping based on the piecewise function, compress grayscale mapping of a background area, i.e., a non-crack damage area, stretch grayscale mapping of a target area, i.e., a crack damage area, and construct a piecewise function gain grayscale mapping image, specifically as follows: extracting temperature values of each pixel in the infrared thermal image, and using an average temperature value of the entire infrared thermal image as a parameter of a first inflection point; using an average temperature value of pixels in a region with a temperature less than the first inflection point as a parameter of a second inflection point; re-performing thermal image grayscale mapping based on the obtained first and second inflection points, and obtaining a gain grayscale mapping image; wherein a first segment of the piecewise function is parallel line mapping, a second segment is normal linear mapping with reduced grayscale, and a third segment is sine function mapping; The binarization module is configured to solve an optimal segmentation threshold of the gain gray map image and binarize the gain gray map image through the segmentation threshold. The leaking water area identification module is configured to perform contour detection on the binarization image and identify a crack form of the lining in the leaking water area.

7. A computer apparatus comprising a memory, a processor, and a computer program stored on the memory and loadable on the processor, characterized in that, The processor executes the program to implement the steps of the method of any one of claims 1-5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to execute the steps of the method of any one of claims 1-5.

Images