Water leakage identification method, device and equipment for tunnel inspection

Abstract

The invention provides a water leakage identification method, device and equipment for tunnel inspection. The method comprises the following steps: acquiring real-time acquired image information of a target tunnel and standard image information of the target tunnel; preprocessing the real-time acquired image information to obtain an image processing result; comparing the image processing result with standard image information to obtain a target image marked with a difference selection box; performing image difference analysis on the target image marked with the difference selection box and the standard image information to obtain a difference image; and outputting an alarm of the difference image to obtain a tunnel water leakage identification result. According to the scheme, autonomous detection of the water leakage phenomenon in tunnel inspection can be realized, and the realization difficulty of a water leakage identification function in tunnel inspection is reduced.

Description

Technical Field

[0001] The present invention relates to the field of computer information technology, and in particular to a method, device and equipment for identifying water leakage in tunnel inspection. Background Art

[0002] In tunnel engineering, water leakage has always been a typical and common problem, especially for tunnels with water pipelines. In order to detect and treat the potential safety hazards of water leakage early, tunnel inspection is an indispensable measure. However, manual inspection has certain safety risks, so tunnel inspection technology came into being.

[0003] In order to realize the ability of tunnel inspection to autonomously discover safety hazards such as water leakage, existing methods mainly include: water leakage image recognition method based on target tracking algorithm, image processing method based on big data analysis, etc. However, the implementation code of these methods is highly complex and has high requirements for hardware parameters, which increases the difficulty of implementing the water leakage identification function of tunnel inspection. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a water leakage identification method, device and equipment for tunnel inspection, which can realize autonomous detection of water leakage phenomena in tunnel inspection and reduce the difficulty of realizing the water leakage identification function of tunnel inspection.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] A water leakage identification method for tunnel inspection, comprising:

[0007] Acquire real-time collected image information and standard image information of the target tunnel;

[0008] Preprocessing the real-time collected image information to obtain an image processing result;

[0009] Comparing the image processing result with the standard image information to obtain a target image marked with a difference selection box;

[0010] Performing image difference analysis on the target image marked with the difference selection box and the standard image information to obtain a difference image;

[0011] The difference image alarm is outputted to obtain a tunnel leakage identification result.

[0012] Optionally, preprocessing the real-time collected image information to obtain an image processing result includes:

[0013] Performing grayscale processing and smoothing operation processing on the real-time collected image information to obtain a first processing result;

[0014] Performing frame difference processing on the first processing result and the standard image information to obtain a second processing result;

[0015] performing binarization processing on the second processing result to obtain a third processing result;

[0016] Perform a dilation operation on the third processing result to obtain an image processing result.

[0017] Optionally, comparing the image processing result with standard image information to obtain a target image marked with a difference selection box includes:

[0018] Performing difference position contour search on the image processing result and standard image information to obtain the difference position contour;

[0019] Marking the difference position contour to obtain a marked contour;

[0020] A difference selection box is added to the marked contour to obtain a target image marked with the difference selection box.

[0021] Optionally, performing image difference analysis on the target image marked with the difference selection box and the standard image information to obtain a difference image includes:

[0022] Determine a brightness mean threshold, a distance threshold, a highlight brightness threshold, an area threshold and a feature value threshold respectively according to the standard image information;

[0023] The part of the target image covered by the difference selection box in the target image is compared with the brightness mean threshold, the distance threshold, the highlight brightness threshold, the area threshold and the characteristic value threshold respectively, to obtain the target image containing the difference selection box that meets the preset rules;

[0024] The target image containing the difference selection box that meets the preset rules is compared with a preset recognition image error library to obtain a difference image, wherein the difference image contains at least one difference selection box.

[0025] Optionally, a portion of the target image covered by the difference selection box in the target image is compared with the brightness mean threshold, the distance threshold, the highlight brightness threshold, the area threshold and the eigenvalue threshold respectively to obtain a target image containing the difference selection box that meets the preset rules, including:

[0026] Compare the brightness mean of the part of the target image covered by the difference selection box in the target image with the brightness mean threshold to obtain a first target image that is less than or equal to the brightness mean threshold;

[0027] Determine a distance between the difference selection box in the first target image and the center of the first target image, compare the distance with a distance threshold, and obtain a second target image that is less than or equal to the distance threshold;

[0028] Determine a brightness value of a portion covered by the difference selection box in the second target image, compare the brightness value with the highlight brightness threshold, and obtain a third target image that is less than or equal to the highlight brightness threshold;

[0029] Comparing the area of ​​the difference frame portion in the third target image with the area threshold to obtain a fourth target image that is greater than or equal to the area threshold;

[0030] The brightness values ​​of the ordinary image and the infrared thermal imaging image in the fourth target image are respectively compared with the characteristic value threshold to obtain a target image containing a difference selection box.

[0031] Optionally, the target image containing the difference selection box that meets the preset rule is compared with a preset recognition image error library to obtain a difference image, including:

[0032] The part covered by the difference selection box in the target image is compared with a preset recognition image error library. When the target image covered by the difference selection box is not compared in the preset recognition image error library, the target image is output to obtain a difference image.

[0033] Optionally, outputting the difference image alarm to obtain a tunnel leakage identification result includes:

[0034] Retrieving and analyzing the difference image, and determining the position of the difference selection box in the difference image;

[0035] The position of the difference selection box and the difference image alarm are output to obtain a tunnel leakage identification result.

[0036] The present invention also provides a water leakage identification device for tunnel inspection, comprising:

[0037] An acquisition module, used to acquire real-time collected image information and standard image information of the target tunnel;

[0038] The processing module is used to pre-process the real-time collected image information to obtain an image processing result; compare the image processing result with the standard image information to obtain a target image marked with a difference selection box; perform image difference analysis on the target image marked with a difference selection box and the standard image information to obtain a difference image; output the difference image alarm to obtain a tunnel leakage identification result.

[0039] The present invention also provides a computing device, comprising: a processor and a memory storing a computer program, wherein when the computer program is run by the processor, the method as described above is executed.

[0040] The present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the above method.

[0041] The above solution of the present invention includes at least the following beneficial effects:

[0042] The above scheme of the present invention obtains the real-time collected image information and the standard image information of the target tunnel; pre-processes the real-time collected image information to obtain the image processing result; compares the image processing result with the standard image information to obtain the target image marked with a difference selection box; performs image difference analysis between the target image marked with a difference selection box and the standard image information to obtain a difference image; outputs the difference image alarm to obtain the tunnel leakage identification result. It can realize the autonomous detection of water leakage in tunnel inspection and reduce the difficulty of realizing the tunnel inspection water leakage identification function. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a first flow chart of a water leakage identification method for tunnel inspection according to an embodiment of the present invention;

[0044] Figure 2 1 is a second flow chart of a water leakage identification method for tunnel inspection according to an embodiment of the present invention;

[0045] Figure 3 is a schematic diagram of image difference analysis of a water leakage identification method for tunnel inspection according to an embodiment of the present invention;

[0046] Figure 4 It is a schematic diagram of the structure of a tunnel information processing device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0048] like Figure 1 As shown, an embodiment of the present invention provides a water leakage identification method for tunnel inspection, comprising:

[0049] Step 11, obtaining real-time collected image information of the target tunnel and standard image information of the target tunnel;

[0050] Here, the real-time image information is the real-time image information of the target tunnel collected during the inspection process, and is the real-time image collection of the risk areas of water leakage one by one in sequence according to the inspection task. The real-time image information includes ordinary image collection based on conventional cameras and infrared thermal imaging image collection based on infrared cameras. The standard image information is the image collection of the target tunnel where there may be a risk of water leakage when the water pipeline of the target tunnel is operating normally. The collected standard images are included in the standard image library in the order of inspection, and the characteristic information such as the location and time of the standard images are marked.

[0051] Step 12, preprocessing the real-time collected image information to obtain an image processing result;

[0052] Here, the preprocessing mainly refers to grayscale processing, smoothing operations, etc. of the common image information and infrared thermal imaging image information in the real-time collected image information, so as to obtain image processing results that meet the requirements. The image processing results include common image information processing results and infrared thermal imaging image information processing results.

[0053] Step 13, comparing the image processing result with the standard image information to obtain a target image marked with a difference selection box;

[0054] Here, it means comparing the image processing result with the standard image information, finding the difference position information in the image, and marking and outputting the found difference position information. The final target image may have one or more difference selection boxes depending on the number of difference positions.

[0055] Step 14, performing image difference analysis between the target image marked with the difference selection box and the standard image information to obtain a difference image;

[0056] Here, it means that the difference position framed by the difference selection box is subjected to difference analysis with the same position in the standard image information. According to the preset difference analysis rules, when the difference selection box does not meet the preset rules, the difference selection box is discarded, which means that the difference position framed by the discarded difference selection box has no water leakage. When the position of the difference selection box meets the preset rules, the difference image containing the difference selection box is output, which means that the position of the difference selection box in the difference image has water leakage.

[0057] Step 15, outputting the difference image alarm to obtain a tunnel leakage identification result.

[0058] In this embodiment, the tunnel has unique environmental characteristics. The internal space of the tunnel is closed or semi-closed, the humidity is at a high level, the air humidity is high, and the tunnel wall is often accompanied by condensation; the tunnel light conditions are poor, and a continuous artificial lighting system is required to maintain a certain degree of visibility; the temperature inside the tunnel is relatively constant, and is less affected by the external environment, and water has an obvious temperature characteristic value.

[0059] In view of the environmental characteristics of the above-mentioned tunnels, a water leakage identification method suitable for tunnel inspection is proposed. It has low implementation difficulty and low construction cost, and can realize the identification and detection of water leakage in the tunnel. It mainly includes such Figure 2 The five parts shown are image acquisition, image processing, image difference annotation, image difference analysis, and result output. Image acquisition realizes the acquisition of real-time image information and standard image information of the target tunnel, image processing performs preprocessing on the collected real-time image information, image difference annotation determines the difference position between the real-time image information and the standard image information, and determines the area where water leakage may occur, image difference analysis further analyzes the marked difference position to determine whether water leakage occurs, and result output outputs the difference image alarm of water leakage that is finally analyzed.

[0060] In an optional embodiment of the present invention, step 12 may include:

[0061] Step 121, performing grayscale processing and smoothing operation processing on the real-time collected image information to obtain a first processing result;

[0062] Step 122, performing frame difference processing on the first processing result and the standard image information to obtain a second processing result;

[0063] Step 123, performing binarization processing on the second processing result to obtain a third processing result;

[0064] Step 124, performing a dilation operation on the third processing result to obtain an image processing result.

[0065] In this embodiment, the ordinary image and infrared thermal imaging image collected in real time are processed, and the image is firstly grayscale processed and smoothed to obtain a first processing result. The grayscale processing refers to the process of converting a color image into a grayscale image, which mainly includes adjusting the three components of R, G, and B in the image. Grayscale processing can simplify the data volume of the image and improve the operation speed. The smoothing operation can eliminate random noise in the image, reduce the high-frequency components in the image, and reduce the contrast of the image while maintaining the overall appearance of the image. Through the image smoothing operation, the random noise in the image can be reduced or eliminated, and the details of the image can be reduced.

[0066] Then, the frame difference processing is performed on the standard image and the real-time image of the same water leakage risk area through the frame difference method, and the difference image is output, which is the second processing result. The frame difference processing is a method of obtaining the contour of the moving target by performing a difference operation on two consecutive frames of the video image sequence. When abnormal target movement occurs in the monitoring scene, there will be a more obvious difference between the two adjacent frames. The two frames are subtracted to obtain the absolute value of the pixel value difference at the corresponding position of the image, and it is determined whether it is greater than a certain threshold, and then the object motion characteristics of the video or image sequence are analyzed.

[0067] The difference image is binarized and the binarization result is output; the binarization sets the grayscale value of the pixel on the image to 0 or 255, that is, the entire image presents an obvious black and white effect. Thus, the object in the image is separated from the background. Finally, the binarization result is expanded and the image processing result is output. The expansion operation widens the object in the image by extending the pixels on the image boundary. This is achieved by considering the neighborhood of each pixel and setting its value to the maximum value of all pixels in the neighborhood. For a binary image, if the value of any adjacent pixel is 1, the output pixel is also set to 1.

[0068] In an optional embodiment of the present invention, step 13 may include:

[0069] Step 131, searching for a difference position contour between the image processing result and the standard image information to obtain a difference position contour;

[0070] Step 132, marking the difference position contour to obtain a marked contour;

[0071] Step 133: adding a difference selection box to the marked contour to obtain a target image marked with the difference selection box.

[0072] In this embodiment, the difference position contours between the image processing result and the standard image information are first searched, then the searched difference position contours are marked, a rectangle is drawn on the marked contours, and a difference selection box is added to them. Finally, the target images of the ordinary image and the infrared thermal imaging image are output respectively.

[0073] In an optional embodiment of the present invention, step 14 may include:

[0074] Step 141, determining a brightness mean threshold, a distance threshold, a highlight brightness threshold, an area threshold and a feature value threshold respectively according to the standard image information;

[0075] Step 142, comparing the portion of the target image covered by the difference selection box in the target image with the brightness mean threshold, distance threshold, highlight brightness threshold, area threshold and feature value threshold respectively, to obtain a target image containing the difference selection box that meets the preset rules;

[0076] Step 143 : Compare the target image that meets the preset rule and contains the difference selection box with a preset recognition image error library to obtain a difference image, wherein the difference image contains at least one difference selection box.

[0077] In this embodiment, the threshold correction is first performed on the standard image information at different positions, and the standard image information of the same position more than 10 times is selected, and the thresholds of the standard image information more than 10 times are averaged to finally obtain the brightness mean threshold, distance threshold, highlight brightness threshold, area threshold and eigenvalue threshold.

[0078] like Figure 3 As shown, the various parameter values ​​of the difference selection box in the target image are determined, and the parameter values ​​are compared with the brightness mean threshold, distance threshold, highlight brightness threshold, area threshold, and feature value threshold respectively. According to the preset rules, some difference selection boxes that do not meet the preset rules are discarded, that is, the leakage risk of these discarded difference selection boxes is eliminated. Finally, a difference selection box that meets all the preset rules is obtained, and the position of the difference selection box is the leakage position determined by the preliminary analysis. The target image of the difference selection box that meets the preset rules is continued to be compared with the recognition image error library. When the match fails, the error risk can be eliminated, and it is finally determined that the difference image has leakage.

[0079] Specifically, step 142 may include:

[0080] Step 1421, comparing the brightness mean of the portion of the target image covered by the difference selection box in the target image with the brightness mean threshold, to obtain a first target image that is less than or equal to the brightness mean threshold;

[0081] Here, the image brightness mean of the difference selection box part in the target image is drawn, and the brightness mean value is compared with the brightness mean threshold of the standard image to determine whether the brightness mean value exceeds the threshold range. If it exceeds the threshold, the difference selection box is discarded to eliminate the recognition error caused by the brightness change.

[0082] Step 1422, determining the distance between the difference selection box in the first target image and the center of the first target image, comparing the distance with a distance threshold, and obtaining a second target image that is less than or equal to the distance threshold;

[0083] Here, the position of the difference selection box in the drawn image is analyzed. If it is at the edge of the image, that is, far away from the center of the image, and exceeds the distance threshold, the difference selection box is discarded to eliminate the recognition error caused by the positioning error factor.

[0084] Step 1423, determining the brightness value of the portion covered by the difference selection box in the second target image, comparing the brightness value with the highlight brightness threshold, and obtaining a third target image that is less than or equal to the highlight brightness threshold;

[0085] Here, it is determined whether the drawn image contains blocks in a highlight area. The highlight is the area where the lighting is located. If the brightness value exceeds a threshold, the blocks in the selection box are discarded.

[0086] Step 1424, comparing the area of ​​the difference frame portion in the third target image with the area threshold to obtain a fourth target image that is greater than or equal to the area threshold;

[0087] Here, it is identified whether the area of ​​the leaking region in the drawn image is smaller than a threshold. If it is smaller than the threshold, the selection box is discarded to eliminate the recognition error caused by condensation water formed by facilities such as tunnel walls.

[0088] Step 1425 , respectively compare the brightness values ​​of the ordinary image and the infrared thermal imaging image in the fourth target image with the characteristic value threshold to obtain a target image containing a difference selection box.

[0089] Here, a feature value comparison is performed. The image of water in the tunnel mainly has two feature values, one is the brightness value of the ordinary image, and the other is the brightness value of the infrared thermal imaging image. For the feature value of the ordinary image, it is necessary to calibrate the brightness value threshold range of different standard images. After the calibration is completed, if the brightness value of the real-time image is within this range, the next step of analysis is performed. If not, the collected image is discarded. For the feature value of the infrared thermal imaging image, it is necessary to perform brightness value analysis on the thermal imaging images of the corresponding positions in the tunnel environment in different seasons, and use the brightness feature values ​​of other objects in the tunnel (except water) as the brightness value comparison threshold range of the real-time thermal imaging image. If it is within this threshold range, it is discarded. If not, the next step of analysis is performed.

[0090] Specifically, step 143 may include:

[0091] Step 1431, compare the portion of the target image covered by the difference selection box with a preset recognition image error library. When the target image covered by the difference selection box is not matched in the preset recognition image error library, output the target image to obtain a difference image.

[0092] Here, the target image is compared with the preset recognition image error library. If the image exists in the preset recognition image error library, the rectangular selection box in the target image is discarded; if it does not exist, the target image is output. The preset recognition image error library is the recognition error that still appears in the recognition after excluding the above-mentioned brightness, positioning, highlight and condensation water. It is a library established by using all the recognition image error rectangular selection boxes that appear in long-term debugging and operation. The recognition image error library requires a large amount of debugging and operation data support; the recognition image error library can be based on a common database, and the error images of brightness values ​​and contour values ​​with similar characteristics to water seepage in the recognition error are stored and analyzed, especially the characteristic values ​​of condensation water images, and the accuracy of the final result output is improved through a large amount of data analysis. In addition, the brightness mean threshold, distance threshold, highlight brightness threshold, area threshold, and characteristic value threshold in the image difference analysis all need to be calibrated and set according to the template image features collected under different environments.

[0093] In an optional embodiment of the present invention, step 15 may include:

[0094] Step 151, searching and analyzing the difference image, and determining the position of the difference selection box in the difference image;

[0095] Step 152, outputting the position of the difference selection box and the difference image alarm to obtain a tunnel leakage identification result.

[0096] In this embodiment, the retrieval of the output results of the image difference analysis is completed, and the output image is named, and finally the result is output to the inspection log image library and the terminal. While the output results are retrieved and analyzed, the position of the difference selection box is determined, and an alarm signal is output, and the signal is also output to the terminal.

[0097] Combine the following Figure 2 , Figure 3 The specific implementation process of the above method is described as follows:

[0098] like Figure 2 As shown, the first step of image acquisition is to collect and produce a standard image library. When the tunnel water pipeline is operating normally, images of possible leakage risk areas in the tunnel are collected, and the collected standard images are included in the standard image library in the order of inspection, and the location, time and other characteristic information of the standard images are marked. The second step is real-time image acquisition during the inspection process. According to the inspection task, images of leakage risk areas are collected one by one in real time in sequence.

[0099] like Figure 2As shown in the figure, the image processing processes the ordinary image and infrared thermal imaging image collected in real time respectively. First, the image is gray-scaled and smoothed. Then, the frame difference operation is performed on the standard image and the real-time image of the same leakage risk part through the frame difference method to output the difference image; the difference image is binarized and the binarization result is output; finally, the binarization result is expanded and the image processing result is output.

[0100] like Figure 2 As shown, the image difference annotation is to first search for the contour of the difference position of the image processing result, then use the found contour to annotate, draw a rectangle for the annotated contour, and output the drawn images of the ordinary image and the infrared thermal imaging image.

[0101] Before the six steps of image difference analysis are performed, threshold calibration of template images at different positions is required. The brightness mean threshold, distance threshold, highlight brightness threshold, area threshold, and feature value threshold are set based on the acquisition results of more than 10 template images. For example, Figure 3 shown.

[0102] The first step is to compare the image brightness mean with the template image to determine whether the brightness mean exceeds the threshold range. If it does not exceed the threshold, the difference rectangle selection box is discarded;

[0103] The second step is to analyze the position of the difference rectangular selection box in the drawn image and discard the rectangular selection box if it exceeds the distance threshold;

[0104] The third step is to determine whether there is still a highlight area in the drawn image. If the brightness value exceeds the threshold, the rectangular selection box is discarded;

[0105] The fourth step is to identify whether the area of ​​the leaking area in the drawn image is smaller than the threshold. If it is smaller than the threshold, the rectangular selection box is discarded;

[0106] The fifth step is the feature value comparison. The image of water in the tunnel mainly has two feature values, one is the brightness value of the ordinary image, and the other is the brightness value of the infrared thermal imaging image. For the feature value of the ordinary image, it is necessary to calibrate the brightness value threshold range of different template images. After the calibration is completed, if the brightness value of the drawn image is within this range, the next step of analysis is carried out. If not, the collected image is discarded. For the feature value of the infrared thermal imaging image, it is necessary to analyze the brightness value of the thermal imaging images of the corresponding positions in the tunnel environment in different seasons. The brightness feature values ​​of other objects in the tunnel (except water) are used as the brightness value comparison threshold range of the real-time thermal imaging image. If it is within this threshold range, it is discarded. If not, the sixth step is carried out.

[0107] The sixth step is to compare the recognition image error library. If the error exists in the recognition image error library, the rectangular selection box in the recognition drawn image will be discarded, and the drawn image will not be output. The recognition image error library is the recognition error that still appears in the recognition after the above four error situations are eliminated. It is a library established using all the recognition image error rectangular selection boxes that appear in long-term debugging and running. This library requires a lot of debugging and running data support, and a large amount of data experiments need to be carried out during the debugging and running to form an error library containing a large number of recognition image error rectangular selection boxes.

[0108] like Figure 2 As shown, the result output is to complete the retrieval of the image difference analysis output results, complete the naming of the output image, and finally output the result to the inspection log image library and the terminal. At the same time, the output result is retrieved and analyzed to determine whether there is a rectangular selection box. If there is a rectangular selection box, an alarm signal is output and the signal is also output to the terminal.

[0109] The above method of the present invention meets the functional requirements of tunnel inspection for autonomous detection and analysis of water leakage such as leakage, seepage, etc., and reduces the difficulty of realizing the water leakage identification function of tunnel inspection. Tunnels have unique environmental characteristics. The internal space of the tunnel is closed or semi-closed, the humidity is at a high level all year round, the air humidity is high, and the cave wall is often accompanied by condensation water; the light conditions in the tunnel are poor, and a continuous artificial lighting system is required to maintain a certain visibility; the temperature inside the tunnel is relatively constant, and is less affected by the external environment, and water has an obvious temperature characteristic value. In view of the environmental characteristics of the tunnel, the water leakage identification method suitable for tunnel inspection of the present invention has low implementation difficulty and low construction cost, and mainly includes five parts: image acquisition, image processing, image difference annotation, image difference analysis, and result output. Image acquisition requires image acquisition hardware, which is mainly divided into standard image library acquisition and production and real-time image acquisition during the inspection process. Image acquisition covers ordinary image acquisition based on conventional cameras and infrared thermal imaging image acquisition based on infrared cameras. Image processing performs grayscale processing and smoothing operations on the acquired images. Image difference annotation is to search, annotate and output the difference position contour of the image processing results. Image difference analysis is the analysis of real-time captured images and corresponding template images, which is divided into six steps:

[0110] The first step is to compare the image brightness mean with the template image to determine whether the brightness mean exceeds the threshold range. If it exceeds the threshold, the difference selection box is discarded to eliminate the recognition error caused by brightness changes.

[0111] The second step is to analyze the position of the difference selection box in the drawn image. If the block at the edge of the image, that is, far from the center of the image, exceeds the distance threshold, the block in the selection box is discarded to eliminate the recognition error caused by the positioning error factor;

[0112] The third step is to determine whether there are any blocks in the highlighted area in the drawn image. The highlighted area is where the lighting is located. If the brightness value exceeds the threshold, the blocks in the selected box are discarded.

[0113] The fourth step is to identify whether the area of ​​the water leakage region in the drawn image is smaller than the threshold. If it is smaller than the threshold, the selection box is discarded to eliminate the recognition error caused by condensation water formed by facilities such as tunnel walls;

[0114] The fifth step is the feature value comparison. The image of water in the tunnel mainly has two feature values, one is the brightness value of the ordinary image, and the other is the brightness value of the infrared thermal imaging image. For the feature value of the ordinary image, it is necessary to calibrate the brightness value threshold range of different template images. After the calibration is completed, if the brightness value of the real-time image is within this range, the next step of analysis is carried out. If not, the collected image is discarded. For the feature value of the infrared thermal imaging image, it is necessary to analyze the brightness value of the thermal imaging images of the corresponding positions in the tunnel environment in different seasons. The brightness feature values ​​of other objects in the tunnel (except water) are used as the brightness value comparison threshold range of the real-time thermal imaging image. If it is within this threshold range, it is discarded. If not, the sixth step is carried out.

[0115] The sixth step is to compare the recognition image error library. If the recognition image error exists in the recognition image error library, the rectangular selection box in the recognition drawing image will be discarded. If it does not exist, the drawing image will be output. The recognition image error library is the recognition error that still appears in the recognition after the above four error conditions are eliminated. It is a library established by using all the recognition image error rectangular selection boxes that appear in long-term debugging and operation. The library requires a large amount of debugging and operation data support; the recognition image error library can be based on a common database, and the error images of brightness values ​​and contour values ​​with similar characteristics to water seepage in the recognition error are stored and analyzed, especially the characteristic values ​​of condensation water images, and the accuracy of the final result output is improved through a large amount of data analysis. In addition, the brightness mean threshold, distance threshold, highlight brightness threshold, area threshold, and characteristic value threshold in the image difference analysis all need to be calibrated and set according to the characteristics of the template images collected under different environments.

[0116] The result output requires a background processing terminal or server. The result output is to complete the retrieval of the image difference analysis output results and output them to the inspection log image library and terminal.

[0117] Through the above steps, the functional requirements of tunnel inspection for autonomous detection and analysis of water leakage such as leakage, seepage, etc. are met, while the difficulty of realizing the water leakage identification function of tunnel inspection is reduced, providing a new idea for realizing the water leakage identification function of tunnel inspection. It is highly operable, and the water leakage identification function can be improved by simply embedding the above method code in the existing tunnel inspection system software. The construction cost is low, especially for the completed tunnel inspection system, which has high optimization value and benefits.

[0118] like Figure 4 As shown, an embodiment of the present invention further provides a water leakage identification device 40 for tunnel inspection, comprising:

[0119] An acquisition module 41 is used to acquire real-time collected image information of a target tunnel and standard image information of the target tunnel;

[0120] The processing module 42 is used to pre-process the real-time collected image information to obtain an image processing result; compare the image processing result with the standard image information to obtain a target image marked with a difference selection box; perform image difference analysis on the target image marked with a difference selection box and the standard image information to obtain a difference image; output the difference image alarm to obtain a tunnel leakage identification result.

[0121] Optionally, preprocessing the real-time collected image information to obtain an image processing result includes:

[0122] Performing grayscale processing and smoothing operation processing on the real-time collected image information to obtain a first processing result;

[0123] Performing frame difference processing on the first processing result and the standard image information to obtain a second processing result;

[0124] performing binarization processing on the second processing result to obtain a third processing result;

[0125] Perform a dilation operation on the third processing result to obtain an image processing result.

[0126] Optionally, comparing the image processing result with standard image information to obtain a target image marked with a difference selection box includes:

[0127] Performing difference position contour search on the image processing result and standard image information to obtain the difference position contour;

[0128] Marking the difference position contour to obtain a marked contour;

[0129] A difference selection box is added to the marked contour to obtain a target image marked with the difference selection box.

[0130] Optionally, performing image difference analysis on the target image marked with the difference selection box and the standard image information to obtain a difference image includes:

[0131] Determine a brightness mean threshold, a distance threshold, a highlight brightness threshold, an area threshold and a feature value threshold respectively according to the standard image information;

[0132] The part of the target image covered by the difference selection box in the target image is compared with the brightness mean threshold, the distance threshold, the highlight brightness threshold, the area threshold and the characteristic value threshold respectively, to obtain the target image containing the difference selection box that meets the preset rules;

[0133] The target image containing the difference selection box that meets the preset rules is compared with a preset recognition image error library to obtain a difference image, wherein the difference image contains at least one difference selection box.

[0134] Optionally, a portion of the target image covered by the difference selection box in the target image is compared with the brightness mean threshold, the distance threshold, the highlight brightness threshold, the area threshold and the eigenvalue threshold respectively to obtain a target image containing the difference selection box that meets the preset rules, including:

[0135] Compare the brightness mean of the part of the target image covered by the difference selection box in the target image with the brightness mean threshold to obtain a first target image that is less than or equal to the brightness mean threshold;

[0136] Determine a distance between the difference selection box in the first target image and the center of the first target image, compare the distance with a distance threshold, and obtain a second target image that is less than or equal to the distance threshold;

[0137] Determine a brightness value of a portion covered by the difference selection box in the second target image, compare the brightness value with the highlight brightness threshold, and obtain a third target image that is less than or equal to the highlight brightness threshold;

[0138] Comparing the area of ​​the difference frame portion in the third target image with the area threshold to obtain a fourth target image that is greater than or equal to the area threshold;

[0139] The brightness values ​​of the ordinary image and the infrared thermal imaging image in the fourth target image are respectively compared with the characteristic value threshold to obtain a target image containing a difference selection box.

[0140] Optionally, the target image containing the difference selection box that meets the preset rule is compared with a preset recognition image error library to obtain a difference image, including:

[0141] The part covered by the difference selection box in the target image is compared with a preset recognition image error library. When the target image covered by the difference selection box is not compared in the preset recognition image error library, the target image is output to obtain a difference image.

[0142] Optionally, outputting the difference image alarm to obtain a tunnel leakage identification result includes:

[0143] Retrieving and analyzing the difference image, and determining the position of the difference selection box in the difference image;

[0144] The position of the difference selection box and the difference image alarm are output to obtain a tunnel leakage identification result.

[0145] It should be noted that the device is a device corresponding to the above method, and all implementation methods in the above method embodiments are applicable to the embodiments of the device and can achieve the same technical effects.

[0146] The embodiment of the present invention further provides a computing device, comprising: a processor, a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0147] The embodiment of the present invention further provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the above method. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0148] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0149] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0150] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0151] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0152] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0153] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.

[0154] In addition, it should be noted that in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it is understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0155] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code that implements the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

[0156] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A water leakage identification method for tunnel inspection, characterized in that: include: Acquire real-time collected image information and standard image information of the target tunnel; Preprocessing the real-time collected image information to obtain an image processing result; Comparing the image processing result with the standard image information to obtain a target image marked with a difference selection box; Performing image difference analysis on the target image marked with the difference selection box and the standard image information to obtain a difference image; The difference image alarm is outputted to obtain a tunnel leakage identification result.

2. The water leakage identification method for tunnel inspection according to claim 1 is characterized in that: Preprocessing the real-time collected image information to obtain an image processing result includes: Performing grayscale processing and smoothing operation processing on the real-time collected image information to obtain a first processing result; Performing frame difference processing on the first processing result and the standard image information to obtain a second processing result; performing binarization processing on the second processing result to obtain a third processing result; Perform a dilation operation on the third processing result to obtain an image processing result.

3. The water leakage identification method for tunnel inspection according to claim 1, characterized in that: Comparing the image processing result with the standard image information to obtain a target image marked with a difference selection box, including: Performing difference position contour search on the image processing result and standard image information to obtain the difference position contour; Marking the difference position contour to obtain a marked contour; A difference selection box is added to the marked contour to obtain a target image marked with the difference selection box.

4. The water leakage identification method for tunnel inspection according to claim 1, characterized in that: Performing image difference analysis on the target image marked with the difference selection box and the standard image information to obtain a difference image includes: Determine a brightness mean threshold, a distance threshold, a highlight brightness threshold, an area threshold and a feature value threshold respectively according to the standard image information; The part of the target image covered by the difference selection box in the target image is compared with the brightness mean threshold, the distance threshold, the highlight brightness threshold, the area threshold and the characteristic value threshold respectively, to obtain the target image containing the difference selection box that meets the preset rules; The target image containing the difference selection box that meets the preset rules is compared with a preset recognition image error library to obtain a difference image, wherein the difference image contains at least one difference selection box.

5. The water leakage identification method for tunnel inspection according to claim 4 is characterized in that: The part of the target image covered by the difference selection box in the target image is compared with the brightness mean threshold, the distance threshold, the highlight brightness threshold, the area threshold and the characteristic value threshold respectively, to obtain the target image containing the difference selection box that meets the preset rules, including: Compare the brightness mean of the part of the target image covered by the difference selection box in the target image with the brightness mean threshold to obtain a first target image that is less than or equal to the brightness mean threshold; Determine a distance between the difference selection box in the first target image and the center of the first target image, compare the distance with a distance threshold, and obtain a second target image that is less than or equal to the distance threshold; Determine a brightness value of a portion covered by the difference selection box in the second target image, compare the brightness value with the highlight brightness threshold, and obtain a third target image that is less than or equal to the highlight brightness threshold; Comparing the area of ​​the difference frame portion in the third target image with the area threshold to obtain a fourth target image that is greater than or equal to the area threshold; The brightness values ​​of the ordinary image and the infrared thermal imaging image in the fourth target image are respectively compared with the characteristic value threshold to obtain a target image containing a difference selection box.

6. The water leakage identification method for tunnel inspection according to claim 4, characterized in that: The target image containing the difference selection box that meets the preset rules is compared with a preset recognition image error library to obtain a difference image, including: The part covered by the difference selection box in the target image is compared with a preset recognition image error library. When the target image covered by the difference selection box is not compared in the preset recognition image error library, the target image is output to obtain a difference image.

7. The water leakage identification method for tunnel inspection according to claim 1, characterized in that: Outputting the difference image alarm to obtain the tunnel leakage identification result includes: Retrieving and analyzing the difference image, and determining the position of the difference selection box in the difference image; The position of the difference selection box and the difference image alarm are output to obtain a tunnel leakage identification result.

8. A water leakage identification device for tunnel inspection, characterized in that: include: An acquisition module, used to acquire real-time collected image information and standard image information of the target tunnel; The processing module is used to pre-process the real-time collected image information to obtain an image processing result; compare the image processing result with the standard image information to obtain a target image marked with a difference selection box; perform image difference analysis on the target image marked with a difference selection box and the standard image information to obtain a difference image; output the difference image alarm to obtain a tunnel leakage identification result.

9. A computing device, characterized in that include: A processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the method according to any one of claims 1 to 7 is performed.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

Images