A catenary cable defect identification method, device, equipment and medium

Abstract

The application discloses a kind of catenary bearing cable defect identification method, device, equipment and medium, it is related to catenary defect identification technical field.The method comprises: obtaining catenary original image;Locate the position of bearing cable protection strip in the catenary original image, obtain the preliminary bearing cable protection strip possible area image;The preliminary bearing cable protection strip possible area image is filtered and handled, and the bearing cable protection strip connected domain image is extracted;Using second-order difference method, the defect determination of protection strip width is carried out to the bearing cable protection strip connected domain image, and whether there is protection strip loss result is obtained.The application can quickly and timely find the defect of bearing cable base loss protection strip, and the identification efficiency is high, and the risk of railway with catenary operation is excluded.

Description

Technical Field

[0001] This invention relates to the field of catenary defect identification technology, specifically to a method, device, equipment, and medium for identifying defects in catenary catenary cables. Background Technology

[0002] The railway overhead contact system is a crucial infrastructure component of railways. Its stable and normal operation is fundamental to ensuring the safe operation of trains. However, due to improper installation during construction or external factors such as vibration and shaking during daily operation, various defects can accumulate in the contact system over time, severely impacting normal train operation. Among these defects, the protective strips on the catenary cables, which are vital power supply lines, are prone to displacement and detachment, posing serious safety hazards. Currently, defect detection of the catenary cable base protective strips typically involves a combination of image data and manual analysis. However, due to the small size of the catenary cable base images, the low brightness of the protective strips, and the large number of catenary cable bases in the railway infrastructure, manual analysis is time-consuming, labor-intensive, and inefficient, easily leading to delayed or missed defect detection and safety risks. Currently, there is no satisfactory solution within the industry. Summary of the Invention

[0003] The purpose of this invention is to provide a method, device, equipment, and medium for identifying defects in catenary cables, so as to quickly and timely detect defects such as missing protective strips in the catenary cable base, achieve high identification efficiency, and eliminate the risk of catenary operation problems in railways.

[0004] This invention is achieved through the following technical solution:

[0005] In a first aspect, the present invention provides a method for identifying defects in catenary cables, the method comprising:

[0006] Obtain the original image of the overhead contact line as the image to be identified;

[0007] Position the catenary protection strip in the original image of the contact network to obtain a preliminary image of the possible area of ​​the catenary protection strip;

[0008] The preliminary image of the possible regions of the catenary protection strip is filtered to extract the connected component image of the catenary protection strip;

[0009] The second-order difference method is used to determine the defect of the protective strip width in the connected region image of the catenary protective strip, so as to obtain the result of whether there is a missing protective strip.

[0010] The working principle is as follows: Given the small size of the catenary base image, the low brightness of the catenary protective strip, and the large number of catenary bases in the railway network, existing manual analysis methods are time-consuming, labor-intensive, and inefficient, easily leading to delayed defect detection and omissions, thus posing safety hazards. Therefore, this invention designs a catenary defect identification method for overhead contact lines. It uses a deep learning-based object detection model to locate catenary base images in complex backgrounds; and uses image processing algorithms and statistical results to identify the state of missing protective strips on catenary bases. Specifically, first, the catenary protective strip is located, i.e., its initial position in the image is determined; then, connected component extraction of the protective strip is performed, i.e., the correct protective strip is extracted; finally, the width of the protective strip is determined, i.e., whether the catenary protective strip exists. This invention can quickly and timely detect defects such as missing protective strips on catenary bases, with high identification efficiency, eliminating potential risks to the operation of the railway overhead contact line.

[0011] Furthermore, by locating the position of the catenary protection strip in the original image of the contact network, a preliminary image of the possible area of ​​the catenary protection strip is obtained, specifically including:

[0012] The catenary base is extracted from the original image of the overhead contact system using a Yolov5-based target detection model.

[0013] The area of ​​the catenary base is enlarged to obtain an enlarged image of the catenary base area; the enlarged image of the catenary base area includes the image area of ​​the catenary base protective strip;

[0014] From the enlarged image of the catenary base area, the possible areas of the catenary protection strip are extracted to obtain a preliminary image of the catenary protection strip.

[0015] Furthermore, the enlargement of the area of ​​the catenary base is specifically as follows:

[0016] The area of ​​the catenary base is extended vertically by several catenary base diagrams, but not exceeding the height of the original catenary image.

[0017] Furthermore, the step of filtering the possible region image of the preliminary catenary protection strip and extracting the connected component image of the catenary protection strip specifically includes:

[0018] The image of the possible region of the preliminary load-bearing cable protection strip is subjected to histogram equalization processing to obtain the equalized image;

[0019] The equalized image is then subjected to Gaussian smoothing to obtain a smoothed image.

[0020] The smoothed image is binarized using a fixed threshold method to obtain a binarized result image.

[0021] The morphological image processing method of opening operation is used to perform opening operation on the binary result image to remove isolated small regions and obtain the opening operation result image;

[0022] A morphological image processing method using closing operation is employed to perform a closing operation on the opening operation result image, filling the small gaps inside the protective strip caused by binarization using a fixed threshold method, thus obtaining the closing operation result image.

[0023] Extract the largest connected component from the image of the closing operation result;

[0024] By determining the average width of the connected regions, the largest connected region is filtered a second time to obtain the image of the connected regions of the catenary protection strip (i.e., the actual connected region of the protection strip).

[0025] Furthermore, the second-order difference method is used to determine the defect of the protective strip width in the connected region image of the catenary protective strip, and to obtain the result of whether the protective strip is missing. Specifically, this includes:

[0026] Based on the connected region image of the catenary protection strip, calculate the strip width sequence row by row;

[0027] The second-order difference method is used to perform second-order difference calculation on the width sequence of the protective strip to obtain the second-order difference sequence;

[0028] Perform absolute value processing on the elements in the second-order difference sequence to obtain the element with the largest absolute value;

[0029] The element with the largest absolute value is judged: if the element with the largest absolute value is greater than a preset value, then there is a protective strip in the connected region image of the catenary protection strip; if the element with the largest absolute value is less than or equal to the preset value, then there is no protective strip in the connected region image of the catenary protection strip, that is, the protective strip is missing.

[0030] Furthermore, the calculation of the protective strip width sequence by row is specifically as follows:

[0031] Count the number of pixels X = (x1, x2, x3, ..., x4) in each row of the connected component image of the catenary protection strip. n ), where x i (1≤i≤n) represents the number of pixels, and n represents the number of rows in the connected component image.

[0032] Secondly, the present invention provides a contact wire defect identification device, which supports the aforementioned contact wire defect identification method; the device includes:

[0033] The acquisition unit is used to acquire the original image of the overhead contact line as the image to be identified.

[0034] The preliminary protection strip possible area image positioning unit is used to locate the position of the catenary protection strip in the original image of the contact network, and obtain the preliminary catenary protection strip possible area image;

[0035] The protection strip connected component extraction unit is used to filter the possible region image of the preliminary catenary protection strip and extract the connected component image of the catenary protection strip;

[0036] The protective strip defect determination unit is used to determine the width of the protective strip in the connected region image of the catenary protective strip using the second-order difference method, and to obtain the result of whether there is a missing protective strip.

[0037] Furthermore, the execution process of the preliminary protection strip possible area image localization unit is as follows:

[0038] The catenary base is extracted from the original image of the overhead contact system using a Yolov5-based target detection model.

[0039] The area of ​​the catenary base is enlarged to obtain an enlarged image of the catenary base area; the enlarged image of the catenary base area includes the image area of ​​the catenary base protective strip;

[0040] From the enlarged image of the catenary base area, the possible areas of the catenary protection strip are extracted to obtain a preliminary image of the catenary protection strip.

[0041] Thirdly, the present invention also provides 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 computer program to implement the aforementioned method for identifying defects in catenary cables.

[0042] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned method for identifying defects in catenary cables.

[0043] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0044] This invention discloses a method, apparatus, equipment, and medium for identifying defects in catenary cables. It utilizes a deep learning-based object detection model to locate catenary cable base images in complex backgrounds. It then employs image processing algorithms and statistical correlation results to identify the state of missing protective strips on the catenary cable base. Specifically, the invention first locates the catenary cable protective strip, i.e., positions it initially in the image; then, it extracts the connected components of the protective strip to identify the correct strip; finally, it determines the width of the protective strip to ascertain its presence. This invention enables rapid and timely detection of defects such as missing protective strips on catenary cable bases, achieving high identification efficiency and mitigating potential operational risks to the railway catenary system. Attached Figure Description

[0045] The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and form part of this application, do not constitute a limitation thereof. In the drawings:

[0046] Figure 1 This is a flowchart of a method for identifying defects in catenary cables according to the present invention.

[0047] Figure 2 This is a detailed flowchart of step 2 in an embodiment of the present invention.

[0048] Figure 3 This is a schematic diagram of the detection results in step a of step 2 in an embodiment of the present invention.

[0049] Figure 4 This is a schematic diagram of the load-bearing cable base according to an embodiment of the present invention.

[0050] Figure 5 This is a schematic diagram of the area containing the protective strip in the catenary of an embodiment of the present invention.

[0051] Figure 6 This is a pixel accumulation value distribution diagram according to an embodiment of the present invention.

[0052] Figure 7 This is a schematic diagram of the protective strip area extracted in step 1 of an embodiment of the present invention.

[0053] Figure 8 This is a flowchart of step 3 of an embodiment of the present invention, which is the extraction of the connected domain image of the catenary protection strip.

[0054] Figure 9 This is a schematic diagram of intermediate results when the protective strip is present in an embodiment of the present invention.

[0055] Figure 10 This is a schematic diagram of an intermediate result when the protective strip is missing in an embodiment of the present invention.

[0056] Figure 11 This is a detailed flowchart of step 4 in an embodiment of the present invention.

[0057] Figure 12 This is a schematic diagram illustrating the width change and width difference change when the protective strip is present in an embodiment of the present invention.

[0058] Figure 13 This is a schematic diagram illustrating the width change and width difference change when the protective strip is missing in an embodiment of the present invention.

[0059] Figure 14 This is a schematic diagram of the original contact wire image according to an embodiment of the present invention.

[0060] Figure 15 This is a schematic diagram of a normal protective strip (the protective strip is not missing from the base of the load-bearing cable) in an embodiment of the present invention.

[0061] Figure 16 This is a schematic diagram of an abnormal protective strip (missing protective strip on the base of the load-bearing cable) in an embodiment of the present invention.

[0062] Figure 17 This is a schematic diagram of the interference image in an embodiment of the present invention.

[0063] Figure 18 This is a schematic diagram of the structure of a catenary cable defect identification device according to the present invention. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0065] Example 1

[0066] Due to the small size of the catenary base image, the low brightness of the catenary protective strip, and the large number of catenary bases in the railway infrastructure network, existing manual analysis methods are time-consuming, labor-intensive, and inefficient, easily leading to untimely defect detection and omissions, thus posing safety hazards. Therefore, this invention designs a catenary defect identification method for overhead contact lines. It uses a deep learning-based object detection model to locate catenary base images in complex backgrounds; and uses image processing algorithms and statistical results to identify the state of missing protective strips on catenary bases. Specifically, firstly, the catenary protective strip is located, i.e., its initial position in the image is determined; then, connected component extraction of the protective strip is performed, i.e., the correct protective strip is extracted; finally, the width of the protective strip is determined, i.e., whether the catenary protective strip exists. This invention can quickly and timely detect defects such as missing protective strips on catenary bases, with high identification efficiency, eliminating potential risks to the operation of the railway overhead contact line.

[0067] like Figures 1 to 17As shown, the present invention provides a method for identifying defects in catenary cables, such as... Figure 1 As shown, the method includes:

[0068] Step 1: Obtain the original image of the overhead contact line as the image to be identified; the original image of the overhead contact line is shown below. Figure 14 As shown.

[0069] Step 2: Locate the position of the catenary protection strip in the original image of the catenary to obtain a preliminary image of the possible area of ​​the catenary protection strip; the purpose of step 2 is to roughly obtain the possible position of the protection strip in the complex original image of the catenary.

[0070] like Figure 2 As shown, step 2 specifically includes:

[0071] Step a: Using a Yolov5-based target detection model, extract the catenary base from the original catenary image;

[0072] This is because the original image of the overhead contact line is quite complex, and the image of the catenary cable base is small. Therefore, the YOLOv5 algorithm, optimized for small target detection, is used to extract the catenary cable base from the image. A schematic diagram of the detection results is shown below. Figure 3 As shown, the area enclosed in the box is the base of the load-bearing cable.

[0073] Step b involves enlarging the area of ​​the catenary base to obtain an enlarged image of the catenary base area; the enlarged image of the catenary base area includes the image area of ​​the catenary base protective strip; specifically:

[0074] The area of ​​the base of the load-bearing cable ( Figure 4 The image area is expanded by three small images of the catenary bases on both the top and bottom, and does not exceed the height of the original image of the contact network itself, to obtain an image area that includes the protective strip of the catenary base. Figure 5 ).

[0075] Step c: Extract the possible area of ​​the catenary protection strip from the enlarged image of the catenary base area to obtain a preliminary image of the catenary protection strip.

[0076] Need to be from Figure 5 In obtaining the correct image of the catenary protection strip area, interference from structures such as cantilever arms, contact lines, center anchors, bases, and nuts is encountered (interference images are shown in the image). Figure 17 As shown in the figure, statistical methods are required to extract the area of ​​the catenary protection strip.

[0077] Typically, an image is an 8-bit grayscale image, where each pixel has a value between 0 and 244. Figure 6For an image, sum the pixel values ​​of each row, row by row. If the sum of pixel values ​​in a continuous interval is less than 5000, and the interval length is greater than 0.2 times the image height, it is considered a normal guard strip area. Figure 5 Taking the image as an example, the obtained pixel accumulation value curve is as follows: Figure 6 As shown, Figure 6 The horizontal axis represents the row index of the grayscale image, and the vertical axis represents the sum of the pixel values ​​in the current row. Figure 7 The area enclosed in the middle frame.

[0078] Step 3: Filter the image of the possible regions of the preliminary catenary protection strip and extract the connected component image of the catenary protection strip;

[0079] Figure 7 The obtained image only roughly indicates the possible location of the protective strip. Due to the influence of the camera's shooting angle, the exact location may vary. Figure 7 The obtained area may be affected by interference from related structures such as contact wires, cantilever arms, cantilever supports, and center anchors, and may not be entirely certain as the area of ​​the catenary protection strip. Further filtering is needed to ensure that the obtained area is the actual protection strip and that the data is readily available for subsequent defect assessment. The flowchart is as follows: Figure 8 As shown.

[0080] Step 3 specifically includes:

[0081] Step A, Histogram Equalization: The image of the possible area of ​​the preliminary catenary protection strip is subjected to histogram equalization processing to obtain the equalized image; Step A takes into account that the catenary area is far from the camera light source and underexposed, so histogram equalization is used to enhance the image quality.

[0082] Step B, Gaussian smoothing: The equalized image is subjected to Gaussian smoothing to obtain a smoothed image; Step B uses Gaussian blur to smooth the image, reduce jagged edges, and improve the accuracy of subsequent binarization.

[0083] Step C, Binarization: The smoothed image is binarized using a fixed threshold method to obtain a binarized image. This invention uses a fixed threshold (threshold is 40) to binarize the image, which facilitates the extraction of connected components of the catenary protection strip.

[0084] Step D, Opening operation: The morphological image processing method of opening operation is used to perform opening operation on the binary result image to remove isolated small regions (in practice, this is used to process the bolts that are divided at the top or bottom of the region) and obtain the opening operation result image.

[0085] Step E, Closing Operation: Using the morphological image processing method of closing operation, the opening operation result image is subjected to closing operation, which can fill the small gaps inside the protective strip caused by binarization with a fixed threshold method, and obtain the closing operation result image.

[0086] Step F, Extract the maximum connected component: Extract the maximum connected component from the closed operation result image to ensure that the region is an image of a cable.

[0087] Step G, Secondary Filtering of the Maximum Connected Component: By determining the average width of the connected components, secondary filtering is performed on the maximum connected components to obtain the connected component image of the catenary protection strip (i.e., the actual connected area of ​​the protection strip). Step G is necessary because the camera is shooting upwards from below the catenary, and there is interference such as the contact wire near the catenary area. The contact wire is usually wider than the catenary and closer to the camera, so it will appear wider than the catenary in the image. To avoid the obtained maximum connected component area being formed by the contact wire, it is necessary to determine the average width of the connected component. According to statistical calculations, the average connected component width of the catenary (including the protection strip) area does not exceed 60 pixels.

[0088] Figure 9 , Figure 10 The intermediate results of the above process are shown for two types of load-bearing cables: one with a normal protection strip and the other without a protection strip. Each image contains seven sub-images from left to right: the original undetermined protection strip region, the histogram equalization enhancement result image, the Gaussian smoothing result image, the binarization result image, the opening operation result image, the closing operation result image, the maximum connected component result image, and the maximum connected component secondary filtering result image.

[0089] Step 4: Using the second-order difference method, the width of the protective strip in the connected region image of the catenary protective strip is determined to obtain the result of whether there is a missing protective strip.

[0090] like Figure 11 As shown, step 4 specifically includes:

[0091] Based on the connected region image of the catenary protection strip, calculate the strip width sequence row by row; count the connected regions of the catenary protection strip (i.e., Figure 9 The white bar portion (in the image) contains the number of pixels belonging to the connected component in each row (i.e., the image with a pixel value of 255). X = (x1, x2, x3, ..., x...) n ), where x i (1≤i≤n) represents the number of pixels, and n represents the number of rows in the connected component image.

[0092] The second-order difference method is used to perform second-order difference calculations on the width sequence of the protective strip, resulting in a second-order difference sequence; that is, X = (x1, x2, x3, ..., x...). n We obtain ΔX = (x3-x1, x4-x2, x5-x3, ..., xn -x n-2 ), that is, the second-order difference sequence.

[0093] Perform absolute value processing on the elements in the second-order difference sequence to obtain the element with the largest absolute value; that is, obtain max(abs(x)). j -x j-2 ), (3≤j≤n), denoted as A.

[0094] The element with the largest absolute value is judged: if the element with the largest absolute value is greater than a preset value, then a protective strip exists in the connected region image of the catenary protection strip; if the element with the largest absolute value is less than or equal to the preset value, then a protective strip does not exist in the connected region image of the catenary protection strip, i.e., the protective strip is missing. This is because the value of A represents the degree of abrupt change in the width of the connected region of the protective strip. Typically, the preset value is 5.

[0095] Figure 12 and Figure 13 The presence of protective bars was displayed respectively. Figure 12 ) and missing protection strip ( Figure 13 In the case of a guard bar, the image of the ΔX sequence clearly shows that: when the guard bar is present, the ΔX sequence has large jumps and the curve is not smooth; when the guard bar is missing, the ΔX sequence curve has small jumps and the curve is smooth. Figure 12 The horizontal axis represents the row index of the largest connected component image, and the vertical axis represents the number of pixels in the current row that belong to the largest connected component. Figure 13 The horizontal axis represents the row index of the largest connected component image, and the vertical axis represents the number of pixels in the current row that belong to the largest connected component.

[0096] The diagram shows a normal protective strip (without missing protective strips on the catenary base). Figure 15 As shown in the diagram, the abnormal protective strip (the protective strip on the base of the catenary cable is missing) is illustrated below. Figure 16 As shown.

[0097] This invention first locates the catenary protection strip, i.e., positions the strip initially in the image; then, it extracts the connected components of the protection strip to identify the correct strip; finally, it determines the width of the protection strip to ascertain its presence. This invention can quickly and promptly detect defects such as missing protection strips at the catenary base, offering high identification efficiency and eliminating the risk to the operation of the railway's overhead contact system.

[0098] Example 2

[0099] like Figure 18 As shown, the difference between this embodiment and Embodiment 1 is that this embodiment provides a catenary cable defect identification device, which supports the catenary cable defect identification method described in Embodiment 1; the device includes:

[0100] The acquisition unit is used to acquire the original image of the overhead contact line as the image to be identified.

[0101] The preliminary protection strip possible area image positioning unit is used to locate the position of the catenary protection strip in the original image of the contact network, and obtain the preliminary catenary protection strip possible area image;

[0102] The protection strip connected component extraction unit is used to filter the possible region image of the preliminary catenary protection strip and extract the connected component image of the catenary protection strip;

[0103] The protective strip defect determination unit is used to determine the width of the protective strip in the connected region image of the catenary protective strip using the second-order difference method, and to obtain the result of whether there is a missing protective strip.

[0104] As a further implementation, the execution process of the preliminary protection strip possible area image localization unit is as follows:

[0105] The catenary base is extracted from the original image of the overhead contact system using a Yolov5-based target detection model.

[0106] The area of ​​the catenary base is enlarged to obtain an enlarged image of the catenary base area; the enlarged image of the catenary base area includes the image area of ​​the catenary base protective strip;

[0107] From the enlarged image of the catenary base area, the possible areas of the catenary protection strip are extracted to obtain a preliminary image of the catenary protection strip.

[0108] The execution process of each unit can be carried out according to the steps of the catenary cable defect identification method described in Example 1, and will not be repeated in this example.

[0109] Meanwhile, the present invention also provides 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 computer program to implement the aforementioned method for identifying defects in catenary cables.

[0110] Meanwhile, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the aforementioned method for identifying defects in catenary cables.

[0111] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied 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.

[0112] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0113] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0114] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0115] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. 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 within the scope of protection of the present invention.

Claims

1. A method for identifying defects in catenary cables, characterized in that, The method includes: Obtain the original image of the overhead contact line; Position the catenary protection strip in the original image of the contact network to obtain a preliminary image of the possible area of ​​the catenary protection strip; The preliminary image of the possible regions of the catenary protection strip is filtered to extract the connected component image of the catenary protection strip; The second-order difference method is used to determine the defect of the protective strip width in the connected region image of the catenary protective strip, so as to obtain the result of whether there is a missing protective strip; The method employs a second-order difference to determine the width defect of the protective strip in the connected region image of the catenary protective strip, thereby obtaining the result of whether a protective strip is missing. Specifically, this includes: Based on the connected region image of the catenary protection strip, calculate the strip width sequence row by row; The second-order difference method is used to perform second-order difference calculation on the width sequence of the protective strip to obtain the second-order difference sequence; Perform absolute value processing on the elements in the second-order difference sequence to obtain the element with the largest absolute value; The element with the largest absolute value is judged: if the element with the largest absolute value is greater than a preset value, then there is a protective strip in the connected domain image of the catenary protection strip; if the element with the largest absolute value is less than or equal to the preset value, then there is no protective strip in the connected domain image of the catenary protection strip, that is, the protective strip is missing. The calculation of the protective strip width sequence by row is specifically as follows: Count the number of pixels X = (x1, x2, x3, ..., x4) in each row of the connected component image of the catenary protection strip. n ), where x i (1≤i≤n) represents the number of pixels, and n represents the number of rows in the connected component image.

2. The method for identifying defects in catenary cables according to claim 1, characterized in that, The positioning of the catenary protection strip in the original image of the overhead contact line yields a preliminary image of the possible area of ​​the catenary protection strip, specifically including: The catenary base is extracted from the original image of the overhead contact system using a Yolov5-based target detection model. The area of ​​the catenary base is enlarged to obtain an enlarged image of the catenary base area; the enlarged image of the catenary base area includes the image area of ​​the catenary base protective strip; From the enlarged image of the catenary base area, the possible areas of the catenary protection strip are extracted to obtain a preliminary image of the catenary protection strip.

3. The method for identifying defects in catenary cables according to claim 2, characterized in that, The enlargement of the area of ​​the catenary base is specifically as follows: The area of ​​the catenary base is extended vertically by several catenary base diagrams, but not exceeding the height of the original catenary image.

4. The method for identifying defects in catenary cables according to claim 1, characterized in that, The step of filtering the possible region image of the preliminary catenary protection strip and extracting the connected component image of the catenary protection strip specifically includes: The image of the possible region of the preliminary load-bearing cable protection strip is subjected to histogram equalization processing to obtain the equalized image; The equalized image is then subjected to Gaussian smoothing to obtain a smoothed image. The smoothed image is binarized using a fixed threshold method to obtain a binarized result image. The binary result image is subjected to an opening operation using a morphological image processing method that employs opening operations to remove isolated regions, thereby obtaining the opening operation result image. A morphological image processing method using closing operation is employed to perform a closing operation on the opening operation result image, filling the gaps inside the protective strip caused by binarization using a fixed threshold method, thus obtaining the closing operation result image. Extract the largest connected component from the image of the closing operation result; By determining the average width of the connected regions, the largest connected region is filtered a second time to obtain the connected region image of the catenary protection strip.

5. A device for identifying defects in catenary cables, characterized in that, The device supports a catenary cable defect identification method as described in any one of claims 1 to 4; the device comprises: The acquisition unit is used to acquire the original image of the overhead contact line; The preliminary protection strip possible area image positioning unit is used to locate the position of the catenary protection strip in the original image of the contact network, and obtain the preliminary catenary protection strip possible area image; The protection strip connected component extraction unit is used to filter the possible region image of the preliminary catenary protection strip and extract the connected component image of the catenary protection strip; The protective strip defect determination unit is used to determine the width of the protective strip in the connected region image of the catenary protective strip using the second-order difference method, and to obtain the result of whether there is a missing protective strip.

6. The contact wire defect identification device according to claim 5, characterized in that, The execution process of the preliminary protection strip possible area image localization unit is as follows: The catenary base is extracted from the original image of the overhead contact system using a Yolov5-based target detection model. The area of ​​the catenary base is enlarged to obtain an enlarged image of the catenary base area; the enlarged image of the catenary base area includes the image area of ​​the catenary base protective strip; From the enlarged image of the catenary base area, the possible areas of the catenary protection strip are extracted to obtain a preliminary image of the catenary protection strip.

7. 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, it implements a method for identifying defects in catenary cables as described in any one of claims 1 to 4.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements a method for identifying defects in catenary cables as described in any one of claims 1 to 4.

Images