Power tube well section hole site occupation identification method, device and equipment and medium

Abstract

The invention belongs to the technical field of power cables, and particularly relates to a power tube well section hole site occupation identification method, device and equipment and a medium, and the method comprises the steps: collecting a plurality of images at different angles in a cable tube well; preprocessing the image to obtain preprocessed image data; a Harris-Sobel algorithm is adopted, and angular points of the preprocessed image data are calculated; reconstructing a plurality of images according to the angular points to obtain a target image, and extracting multi-scale edge features of the target image; and inputting the multi-scale edge features into a pre-constructed standard template library, outputting a matched placeholder result map, and confirming the hole site placeholder condition according to the placeholder result map. According to the method, the multi-view images are collected for optimal processing, the target image is reconstructed, hole site occupation identification is performed after the internal condition of the cable tube well is restored, and the problems of missing detection, false detection and repetition are avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of power cables, and in particular relates to a method, device, equipment and medium for identifying the occupancy of a hole in a cross section of a power pipe well. Background Art

[0002] Cable manholes are a crucial component of the power system. With the continuous development of power systems and the accelerated pace of urbanization, urban distribution networks are primarily cable-based, with a high cableization rate. Furthermore, to implement the concept of "equal development with electricity" and improve regional power supply reliability, a large number of business expansion and renovation projects require the laying of new cables within existing manholes each year. This requires precise understanding of the hole occupancy within the manhole cross-section. Therefore, improving the accuracy of identifying underground hole occupancy has become a pressing issue.

[0003] Cable wells are built to facilitate cable laying, connection, and line maintenance by operators. Some cable wells have a high density of cables, and some cables' outer sheaths are not entirely flame-retardant, making them easily ignited. Therefore, a short circuit in a cable line within a well can easily cause a fire, resulting in widespread power outages and immeasurable losses for power companies. Furthermore, prolonged immersion of cables in water can lead to water ingress into cable joints, causing insulation breakdown and threatening the normal operation of the power system. Therefore, timely and reliable monitoring of key cable status parameters and hole occupancy within wells is crucial for regional power companies.

[0004] Currently, to ensure the safe and reliable operation of underground cables, operations management departments primarily rely on manual inspections. However, due to the cramped, dark, damp, and low visibility conditions of cable tunnels, trenches, and manholes, coupled with perennial waterlogging, the presence of toxic gases, animal activity, and other unsafe factors, routine cable maintenance inspections and management present challenges. In areas prone to abnormalities, even if operations management departments increase personnel inspections, they cannot conduct real-time inspections, and when abnormalities occur, they cannot provide early warnings or respond efficiently and quickly. Traditional manual inspections and simple information-based monitoring are no longer sufficient to meet the requirements for lean management and control of distribution network cables.

[0005] Currently, most image recognition technologies used mainly use cameras or industrial-grade endoscopes to capture images of the interior of pipe wells, and combine them with target detection algorithms to identify cable distribution. However, the lighting conditions inside cable pipe wells are complex, with reflections and dark areas, which pose a great challenge to the quality of cameras. At the same time, existing recognition methods use a single image for detection, but the underground cables are seriously obscured. Using only a single image will lead to incomplete detection and inaccurate recognition due to obstruction of the hole position, resulting in problems such as incomplete detection and inaccurate recognition. As a result, manual secondary inspection is still required, resulting in a decline in the quality and efficiency of daily operation and maintenance. Summary of the Invention

[0006] The purpose of the present invention is to provide a method, device, equipment and medium for identifying the occupancy of hole positions in the cross section of a power pipe shaft, so as to solve the problem in the background technology that the internal conditions of the pipe shaft are complex and the hole positions are blocked, resulting in incomplete detection and inaccurate identification.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a method for collecting multiple images from different angles within a cable well; Preprocessing the image to obtain preprocessed image data; Harris-Sobel algorithm is used to calculate the corner points of the preprocessed image data; splicing and cropping multiple images according to corner points to obtain a cropped image, and extracting multi-scale edge features of the cropped image; The multi-scale edge features are input into the pre-built standard template library, and the matching occupancy result map is output. The hole occupancy status is confirmed according to the occupancy result map.

[0008] Preferably, the step of preprocessing the image to obtain preprocessed image data includes: The image is a BGR image, and channel conversion is performed on the BGR image to obtain a YUV image; Perform histogram equalization on the Y channel of the YUV image to obtain a histogram-equalized YUV image; The YUV image after histogram equalization is used to adjust the brightness details of the Y channel using phase consistency analysis, and then the adjusted Y channel is merged with the original U / V channels of the YUV image to obtain a YUV image with optimized brightness details; Convert the brightness detail optimized YUV image into a BGR image to obtain a brightness detail optimized BGR image; The BGR image with optimized brightness details is subjected to block gamma correction to obtain a BGR image with optimized local brightness as the preprocessed image data.

[0009] Preferably, the step of calculating the corner points of the pre-processed image data using the Harris-Sobel algorithm includes: The Sobel operator is used to extract the horizontal and vertical gradient information of the preprocessed image data: ; ; in, is the horizontal gradient information, is the vertical gradient information, is the horizontal Sobel operator, is the longitudinal Sobel operator, Represents convolution calculation; Based on the gradient information, the covariance matrix of the preprocessed image data is constructed: ; in, is the Gaussian window function; Based on the covariance matrix, the Harris algorithm is used to calculate the corner points of the preprocessed image data. : ; in, , , is an empirical parameter, when >τ is a corner point.

[0010] Preferably, in the step of calculating the corner points of the preprocessed image data using the Harris-Sobel algorithm, after the corner points are calculated, the response value of each corner point is calculated using the non-maximum suppression method, and the corner point with the local maximum response value is retained.

[0011] Preferably, the step of splicing and cropping multiple images according to corner points to obtain a cropped image includes: Extract pixel information around each corner point of multiple images and generate feature descriptors of the images through feature description algorithms; Match the feature descriptors of multiple images in pairs and calculate the similarity of the feature descriptors. The pair with the highest similarity is the best match. The images are concatenated and cropped based on the best matching pairs to obtain a cropped image.

[0012] Preferably, extracting multi-scale edge features of the cropped image includes: Perform geometric transformation on the cropped image to obtain a geometrically transformed image; Perform multi-layer downsampling on the geometrically transformed image to generate a Gaussian pyramid: Calculate the Gaussian difference images of adjacent scales of the Gaussian pyramid to obtain a Gaussian difference image sequence: The Canny edge detection method is used to calculate the binary edge features of each layer of Gaussian difference image sequence to obtain multi-layer binary edge features; Multi-layer binary edge features are upsampled to obtain multi-scale edge features.

[0013] Preferably, the multi-scale edge features are input into a pre-built standard template library, a matching occupancy result map is output, and the hole occupancy status is confirmed according to the occupancy result map, including: The standard template library is provided with a vacancy template picture, and a vacancy edge feature of the vacancy template picture is obtained; Preset vacancy threshold; The matching degree between multi-scale edge features and vacancy edge features is calculated based on normalized cross correlation (NCC). When the matching degree is greater than the vacancy threshold, it indicates that the well position is not occupied; when the matching degree is not greater than the vacancy threshold, it indicates that the well position is occupied. Record the hole position information and mark the cropped image, and output the marked image as the position result image; Confirm the vacancy status according to the marks on the occupancy result map.

[0014] In a second aspect, the present invention provides a device for identifying the occupancy of a hole in a cross section of a power pipe shaft, comprising: An acquisition module is used to collect multiple images from different angles inside the cable well; A preprocessing module is used to preprocess the image to obtain preprocessed image data; A calculation module, used to calculate the corner points of the pre-processed image data using the Harris-Sobel algorithm; A cropping module, configured to stitch and crop multiple images according to corner points to obtain a cropped image, and extract multi-scale edge features of the cropped image; The recognition module is used to input multi-scale edge features into a pre-built standard template library, output a matching occupancy result map, and confirm the hole occupancy status based on the occupancy result map.

[0015] According to a third aspect of the present invention, an electronic device is provided, comprising a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the method for identifying the occupancy of a hole in a cross section of a power pipe shaft.

[0016] A fourth aspect of the present invention provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the method for identifying the occupancy of a hole in a cross-section of a power pipe shaft is implemented.

[0017] Compared with the prior art, the beneficial effects of the present invention are as follows: Collect images from multiple perspectives, crop and splice them, restore the internal situation of the cable well, and then identify the hole occupancy to avoid missed detection, false detection and duplication. The Harris-Sobel algorithm is used to calculate the corner points of the preprocessed image data, and dense corner points are removed through NMS. This ensures the scale invariance of the corner points while increasing the density of feature points and reducing the amount of traversal calculations for template matching. Perform channel conversion on the image, adjust the global contrast through histogram equalization, adjust the brightness through phase consistency, and finally adjust the brightness of the local image with adaptive gamma correction to suppress brightness contrast interference and effectively reduce the feature mismatch rate caused by sudden changes in illumination. Based on the construction of Gaussian pyramid, geometric transformation is introduced. By performing edge enhancement on Gaussian difference image and combining it with Canny operator for threshold detection, multi-scale edge features are extracted, which significantly improves the detection probability of tiny holes. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are intended to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings: Figure 1 This is a flowchart of the method for identifying the hole position of a power pipe well cross section according to an embodiment of the present invention. Figure 2 This is a flow chart of a method for identifying hole occupancy in a cross-section of a power pipe shaft according to embodiment 1 of the present invention; Figure 3 This is a structural block diagram of a device for identifying hole occupancy in a cross-section of a power pipe shaft according to embodiment 2 of the present invention; Figure 4 This is a structural block diagram of an electronic device according to embodiment 3 of the present invention. DETAILED DESCRIPTION

[0019] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0020] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise indicated, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit the exemplary embodiments according to the present invention.

[0021] Example 1 The method for identifying hole occupancy in a cross-section of a power pipe shaft includes: S1, collect multiple images from different angles in the cable well; Specifically, a high-resolution visible light image acquisition device is used to shoot multi-angle videos of the cable well to obtain multiple images of the cable well at different angles.

[0022] S2. Preprocess the image to obtain preprocessed image data; Specifically, the image is a BGR image, and channel conversion is performed on the BGR image to obtain a YUV image; Perform histogram equalization on the Y channel of the YUV image to obtain a histogram-equalized YUV image; The YUV image after histogram equalization is used to adjust the brightness details of the Y channel using phase consistency analysis, and then the adjusted Y channel is merged with the original U / V channels of the YUV image to obtain a YUV image with optimized brightness details; Convert the brightness detail optimized YUV image into a BGR image to obtain a brightness detail optimized BGR image; The BGR image with optimized brightness details is subjected to block gamma correction to obtain a BGR image with optimized local brightness as the preprocessed image data.

[0023] Histogram equalization processing: ; in, is the image grayscale, yes The number of grayscale pixels, is the total number of pixels, Is grayscale Equalization result, the image is After mapping, the equalization result is obtained; Phase congruency brightness correction: ; in, is an even filter, is an odd filter, is the real part of the complex filter, is the imaginary part of the complex filter, and multiple directions can be selected. Calculate the multi-directional sum and get The value is between [0,1].

[0024] Adaptive gamma correction processing: ; ; ; in, is the standard deviation after equalization, is the average image intensity, , is the regulating factor, is the equalized image, is the correction output, is the normalization constant.

[0025] S3, using Harris-Sobel algorithm to calculate the corner points of the preprocessed image data; Specifically, the Sobel operator is used to extract the horizontal and vertical gradient information of the preprocessed image data: ; ; in, is the horizontal gradient information, is the vertical gradient information, is the horizontal Sobel operator, is the longitudinal Sobel operator, Represents convolution calculation; Based on the gradient information, the neighborhood gradient is weighted by the Gaussian window to construct the covariance matrix of the preprocessed image data: ; in, is the Gaussian window function; Based on the covariance matrix, Harris algorithm is used to extract corner points; Corner point response value calculation:

[0026] in, , , k is an empirical parameter; The non-maximum suppression method (NMS) is used to extract dense corner points, perform threshold filtering on the dense corner points, and retain the corner points with the local maximum response value as candidate corner points: >τ; Among them, τ is the preset threshold; For each candidate corner point, check whether there is a larger If not set, it will be retained as the final corner point.

[0027] S4, stitching and cropping multiple images according to corner points to obtain a cropped image, and extracting multi-scale edge features of the cropped image; Specifically, pixel information of the area around each corner point of multiple images is extracted, and a feature descriptor of the image is generated through a feature description algorithm; Match the feature descriptors of multiple images in pairs and calculate the similarity of the feature descriptors. The pair with the highest similarity is the best match. The edge parts of the images are fused using the mean method. splicing images and cropping based on the best matching pairs to obtain a cropped image; Perform geometric transformation on the cropped image to obtain the geometrically transformed image: ; in, , , , , , is the transformation factor, , is the original coordinate, , are the transformed coordinates.

[0028] The cropped image after geometric transformation is subjected to multi-layer downsampling to generate a multi-scale Gaussian pyramid. Each layer of the image is represented as: ; ; in, is the scale parameter, Indicates two times downsampling; Calculate the Gaussian difference images of adjacent scales of the Gaussian pyramid to obtain a Gaussian difference image sequence: ; in, is a multiple of the adjacent scale; The Canny edge detection method is used to calculate the binary edge features of each layer of Gaussian difference image sequence to obtain multi-layer binary edge features; Upsample the multi-layer binary edge features to obtain multi-scale edge features, which are edge pixels of the cropped image. .

[0029] S5. Input the multi-scale edge features into the pre-built standard template library, output the matching result map, and confirm the hole position occupancy according to the occupancy result map; The standard template library is provided with a vacancy template picture, and a vacancy edge feature of the vacancy template picture is obtained; Preset vacancy threshold; The matching degree of multi-scale edge features and vacancy edge features is calculated based on normalized cross correlation NCC: ; in, Is the empty template image at coordinates The pixel value at The cropped image is panning Back edge pixels The corresponding position pixel, 、 It is the mean of the local area of ​​the vacant template image and the cropped image, and the matching degree is normalized to [-1, 1]; When the matching degree is greater than the vacancy threshold, it indicates that the well position is not occupied; when the matching degree is not greater than the vacancy threshold, it indicates that the well position is occupied. Record the hole position information and mark the cropped image, and output the marked cropped image as the placeholder result image; Confirm the vacancy status according to the marks on the occupancy result map.

[0030] Example 2 like Figure 2 As shown, based on the same inventive concept as the above embodiment, the present invention also provides a device for identifying the hole position of a power pipe shaft cross section, comprising: An acquisition module is used to collect multiple images from different angles inside the cable well; A preprocessing module is used to preprocess the image to obtain preprocessed image data; A calculation module, used to calculate the corner points of the pre-processed image data using the Harris-Sobel algorithm; A cropping module, configured to stitch and crop multiple images according to corner points to obtain a cropped image, and extract multi-scale edge features of the cropped image; The recognition module is used to input multi-scale edge features into a pre-built standard template library, output a matching occupancy result map, and confirm the hole occupancy status based on the occupancy result map.

[0031] Example 3 like Figure 3 As shown, the present invention also provides an electronic device 100 for implementing a method for identifying hole occupancy in a cross-section of a power pipe well; The electronic device 100 includes a memory 101 , at least one processor 102 , a computer program 103 stored in the memory 101 and executable on the at least one processor 102 , and at least one communication bus 104 .

[0032] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the method for identifying the hole occupancy of the cross section of the power pipe well in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.

[0033] The memory 101 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data (such as audio data) created according to the use of the electronic device 100. In addition, the memory 101 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device.

[0034] The at least one processor 102 may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor. The processor 102 is the control center of the electronic device 100 and connects various parts of the entire electronic device 100 using various interfaces and lines.

[0035] The memory 101 in the electronic device 100 stores multiple instructions to implement a method for identifying the location of a hole in a cross section of a power pipe shaft. The processor 102 can execute the multiple instructions to implement: Collect multiple images from different angles inside the cable well; Preprocessing the image to obtain preprocessed image data; Harris-Sobel algorithm is used to calculate the corner points of the preprocessed image data; splicing and cropping multiple images according to corner points to obtain a cropped image, and extracting multi-scale edge features of the cropped image; The multi-scale edge features are input into the pre-built standard template library, and the matching occupancy result map is output. The hole occupancy status is confirmed according to the occupancy result map.

[0036] Example 4 If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. Computer-readable media may include: any entity or device that can carry computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0037] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0038] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts 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, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0039] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0040] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0041] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0042] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for identifying hole occupancy in a cross-section of a power pipe shaft, characterized in that: include: Collect multiple images from different angles inside the cable well; Preprocessing the image to obtain preprocessed image data; Harris-Sobel algorithm is used to calculate the corner points of the preprocessed image data; splicing and cropping multiple images according to corner points to obtain a cropped image, and extracting multi-scale edge features of the cropped image; The multi-scale edge features are input into the pre-built standard template library, and the matching occupancy result map is output. The hole occupancy status is confirmed according to the occupancy result map.

2. The method for identifying hole occupancy of a power pipe well section according to claim 1, characterized in that: The steps of preprocessing the image to obtain preprocessed image data include: The image is a BGR image, and channel conversion is performed on the BGR image to obtain a YUV image; Perform histogram equalization on the Y channel of the YUV image to obtain a histogram-equalized YUV image; The YUV image after histogram equalization is used to adjust the brightness details of the Y channel using phase consistency analysis, and then the adjusted Y channel is merged with the original U / V channels of the YUV image to obtain a YUV image with optimized brightness details; Convert the brightness detail optimized YUV image into a BGR image to obtain a brightness detail optimized BGR image; The BGR image with optimized brightness details is subjected to block gamma correction to obtain a BGR image with optimized local brightness as the preprocessed image data.

3. The method for identifying hole occupancy of a power pipe well section according to claim 1, characterized in that: The step of calculating the corner points of the pre-processed image data using the Harris-Sobel algorithm includes: The Sobel operator is used to extract the horizontal and vertical gradient information of the preprocessed image data: ； ； in, is the horizontal gradient information, is the vertical gradient information, is the horizontal Sobel operator, is the longitudinal Sobel operator, Represents convolution calculation; Based on the gradient information, the covariance matrix of the preprocessed image data is constructed: ； in, is the Gaussian window function; Based on the covariance matrix, the Harris algorithm is used to calculate the corner points of the preprocessed image data. : ； in, , , k is an empirical parameter, when >τ is a corner point.

4. The method for identifying hole occupancy of a power pipe shaft cross section according to claim 3 is characterized in that: In the step of calculating the corner points of the preprocessed image data using the Harris-Sobel algorithm, after the corner points are calculated, the response value of each corner point is calculated using the non-maximum suppression method, and the corner point with the local maximum response value is retained.

5. The method for identifying hole occupancy of a power pipe well section according to claim 1, characterized in that: The steps of stitching and cropping multiple images according to corner points to obtain a cropped image include: Extract pixel information around each corner point of multiple images and generate feature descriptors of the images through feature description algorithms; Match the feature descriptors of multiple images in pairs and calculate the similarity of the feature descriptors. The pair with the highest similarity is the best match. The images are concatenated and cropped based on the best matching pairs to obtain a cropped image.

6. The method for identifying hole occupancy of a power pipe shaft cross section according to claim 1, characterized in that: Extracting multi-scale edge features of the cropped image, including: Perform geometric transformation on the cropped image to obtain a geometrically transformed image; Perform multi-layer downsampling on the geometrically transformed image to generate a Gaussian pyramid: Calculate the Gaussian difference images of adjacent scales of the Gaussian pyramid to obtain a Gaussian difference image sequence: The Canny edge detection method is used to calculate the binary edge features of each layer of Gaussian difference image sequence to obtain multi-layer binary edge features; Multi-layer binary edge features are upsampled to obtain multi-scale edge features.

7. The method for identifying hole occupancy of a power pipe shaft cross section according to claim 1, characterized in that: Input the multi-scale edge features into the pre-built standard template library, output the matching occupancy result map, and confirm the hole occupancy status according to the occupancy result map, including: The standard template library is provided with a vacancy template picture, and a vacancy edge feature of the vacancy template picture is obtained; Preset vacancy threshold; The matching degree between multi-scale edge features and vacancy edge features is calculated based on normalized cross correlation (NCC). When the matching degree is greater than the vacancy threshold, it indicates that the well position is not occupied; when the matching degree is not greater than the vacancy threshold, it indicates that the well position is occupied. Record the hole position information and mark the cropped image, and output the marked image as the position result image; Confirm the vacancy status according to the marks on the occupancy result map.

8. The device for identifying the hole position of the power pipe well section is characterized by: include: An acquisition module is used to collect multiple images from different angles inside the cable well; A preprocessing module is used to preprocess the image to obtain preprocessed image data; A calculation module, used to calculate the corner points of the pre-processed image data using the Harris-Sobel algorithm; A cropping module, configured to stitch and crop multiple images according to corner points to obtain a cropped image, and extract multi-scale edge features of the cropped image; The recognition module is used to input multi-scale edge features into a pre-built standard template library, output a matching occupancy result map, and confirm the hole occupancy status based on the occupancy result map.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the method for identifying the hole position occupancy of a cross-section of a power pipe well as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by the processor, the method for identifying the occupancy of the hole position in the cross section of the power pipe shaft according to any one of claims 1 to 7 is implemented.

Images