Method, system and equipment for identifying number of aluminum wires of power transmission bare conductor, medium and program product

Abstract

The invention discloses a power transmission bare conductor aluminum wire strand number identification method, system and device, a medium and a program product. The method comprises the steps that a power transmission bare conductor image is acquired and preprocessed; inputting the preprocessed power transmission bare conductor image into a bare conductor segmentation model to obtain a bare conductor outer layer aluminum wire binary mask image; performing skeleton extraction on the binary mask pattern to obtain a bare conductor outer layer aluminum wire skeleton pattern; traversing the binary mask pattern, and searching a twill vanishing point; drawing a vertical line at the twill elimination point in a direction perpendicular to the length direction of the binary mask pattern, counting the number n of skeleton lines passed by the vertical line, and judging whether an intersection point of the vertical line and the other side of the binary mask pattern is a twill vanishing point or not; if yes, the number of strands of the aluminum wires is 2n, and if not, the number of strands of the aluminum wires is 2n-1. According to the method, the power transmission bare conductor image shot by the unmanned aerial vehicle can be used for directly segmenting the bare conductor and identifying the number of outer-layer aluminum conductor strands of the bare conductor, and uninterrupted and non-contact bare conductor strand number identification of a power transmission line is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid inspection, and in particular to a method, system, equipment, medium and program product for identifying the strand number of bare aluminum wires of power transmission conductors. Background Art

[0002] Transmission lines are an important part of the electric power industry. Accurately identifying and counting the types of bare conductors in existing transmission systems is extremely critical for transmission line inspections and is vital to power security for social production and people's daily lives.

[0003] Existing bare wire identification relies on manual labor. Only when the line is out of power, the inspectors can climb the pole to count the number of aluminum wires on the outer layer of the bare wire to determine the bare wire model. Manual pole climbing and naked eye identification can only be performed after the power is turned off. It is not only inefficient and has safety hazards, but also causes large-scale power outages in the operating area, affecting production and life. Therefore, it is of great significance for circuit inspection work to develop a technology that can identify the number of bare wires on a daily basis. Summary of the invention

[0004] In view of the deficiencies in the above-mentioned prior art, the purpose of the present invention is to provide a method, system, equipment, medium and program product for identifying the number of aluminum wire strands of bare power transmission conductors, so as to efficiently and safely identify the number of aluminum wire strands of bare power transmission conductors.

[0005] In a first aspect, a method for identifying the number of strands of bare aluminum wires of a power transmission conductor is provided, comprising the following steps:

[0006] S1: Acquire the photographed bare power transmission wire image and perform preprocessing;

[0007] S2: Input the preprocessed transmission bare wire image into the pre-trained bare wire segmentation model to obtain a binary mask image of the outer aluminum wire of the bare wire;

[0008] S3: extracting the skeleton of the binary mask image of the outer aluminum wire of the bare conductor to obtain a skeleton image of the outer aluminum wire of the bare conductor;

[0009] S4: traverse the binary mask image of the outer aluminum wire of the bare conductor to find the vanishing point of the diagonal lines;

[0010] S5: Draw a vertical line at the twill elimination point in the vertical direction of the length direction of the binary mask image of the outer aluminum wire of the bare conductor, count the number of skeleton lines n that the vertical line passes through, and determine whether the intersection of the vertical line and the other side of the binary mask image of the outer aluminum wire of the bare conductor is the twill vanishing point; if so, the number of strands of the outer aluminum wire of the bare conductor is 2n, if not, the number of strands of the outer aluminum wire of the bare conductor is 2n-1.

[0011] Furthermore, in step S1, the preprocessing process includes:

[0012] A bare wire area is extracted from the photographed bare wire image of the power transmission line, and a bare wire image of a preset size is intercepted from the extracted bare wire area.

[0013] Furthermore, in step S2, the bare wire segmentation model is obtained by the following method:

[0014] Collect images of bare power transmission wires;

[0015] Mark the boundary of the outer aluminum wire of the bare conductor in the transmission bare conductor image, obtain the corresponding mask image, and then construct a sample data set;

[0016] The semantic segmentation network is trained based on the sample data set to obtain the bare wire segmentation model.

[0017] Furthermore, after constructing the sample data set, the method further includes: performing data enhancement processing on the sample data set to expand the sample data set.

[0018] Furthermore, the process of marking the boundary of the outer aluminum wire of the bare wire in the transmission bare wire image includes:

[0019] The watershed algorithm is used to segment the transmission bare wire image, and only the bare wire area is retained;

[0020] Cut out a bare wire image of a preset size from the bare wire area;

[0021] The boundaries of each aluminum wire on the outer layer of the bare wire in the intercepted bare wire image are manually marked.

[0022] Furthermore, step S4 specifically includes:

[0023] The binary mask image of the outer aluminum wire of the bare conductor is traversed in the column / row direction of the bare conductor length, and the pixel point with a pixel value of 1 on the outermost side is obtained, and the number of pixel points with a pixel value of 1 in the 3×3 area centered on the pixel point is counted;

[0024] If the number of pixels with a pixel value of 1 is 4, then the point is the diagonal vanishing point.

[0025] In a second aspect, a system for identifying the number of strands of bare aluminum wires of a power transmission conductor is provided, comprising:

[0026] An image acquisition module is used to acquire the photographed image of the bare power transmission wire and perform preprocessing;

[0027] An image segmentation module is used to input the preprocessed transmission bare wire image into a pre-trained bare wire segmentation model to obtain a binary mask image of the outer aluminum wire of the bare wire;

[0028] A skeleton extraction module is used to extract the skeleton of the binary mask image of the outer aluminum wire of the bare conductor to obtain a skeleton image of the outer aluminum wire of the bare conductor;

[0029] The module for extracting the vanishing point of the twill is used to traverse the binary mask image of the outer aluminum wire of the bare conductor to find the vanishing point of the twill;

[0030] The aluminum wire strand number extraction module is used to draw a vertical line at the twill elimination point in the vertical direction of the length direction of the binary mask image of the outer aluminum wire of the bare conductor, count the number of skeleton lines n passed by the vertical line, and determine whether the intersection of the vertical line and the other side of the binary mask image of the outer aluminum wire of the bare conductor is the twill vanishing point; if so, the number of aluminum wire strands of the outer aluminum wire of the bare conductor is 2n, if not, the number of aluminum wire strands of the outer aluminum wire of the bare conductor is 2n-1.

[0031] In a third aspect, an electronic device is provided, including:

[0032] Memory on which computer programs or instructions are stored;

[0033] The processor is used to load and execute the computer program or instructions to implement the method for identifying the number of aluminum wire strands of a bare power transmission conductor as described above.

[0034] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the method for identifying the number of aluminum wire strands of a bare power transmission conductor as described above is implemented.

[0035] In a fifth aspect, a computer program product is provided, wherein a computer program or instruction is stored in the computer program product, and when the computer program or instruction is executed by a processor, the method for identifying the strand number of bare aluminum wires of a power transmission conductor as described above is implemented.

[0036] The present invention proposes a method, system, device, medium and program product for identifying the strand number of aluminum wires of a bare power transmission conductor. The method can use images of bare power transmission conductors taken by drones to directly segment the bare wires and identify the strand number of the outer aluminum wires of the bare wires, thereby realizing non-interruption and contactless bare wire model identification of the transmission line, reducing the risks brought by climbing and power outages, greatly saving manpower, and improving the efficiency of identifying the strand number of the outer aluminum wires of the bare wires. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 This is a flow chart of a method for identifying the strand number of bare aluminum wires of a power transmission conductor provided by an embodiment of the present invention;

[0039] Figure 21 is a schematic diagram of statistical results of finding the vanishing point of diagonal stripes provided by an embodiment of the present invention; wherein (a) is a schematic diagram of statistical results when the number of pixel points with a pixel value of 1 is 3, and (b) is a schematic diagram of statistical results when the number of pixel points with a pixel value of 1 is 4;

[0040] Figure 3 1 is a statistical schematic diagram of the number of vertical lines passing through the skeleton wires provided by the embodiments of the present invention; wherein (a) is a statistical schematic diagram of the vertical line passing through the bare wire with 6 outer aluminum wires, and (b) is a statistical schematic diagram of the vertical line passing through the bare wire with 7 outer aluminum wires;

[0041] Figure 4 It is a schematic diagram of the structure of a system for identifying the strand number of bare aluminum wires of a power transmission conductor provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0043] Existing bare wire identification relies on manual labor. Only when the line is out of power can the inspectors climb the pole to count the number of aluminum wire strands on the outer layer of the bare wire, so as to determine the model of the bare wire. Manual climbing the pole to identify with the naked eye can only be performed after the power is cut off. It is not only inefficient and has potential safety hazards, but also causes large-scale power outages in the operating area, affecting production and life. Therefore, the present invention provides a method, system, equipment, medium and program product for identifying the number of aluminum wire strands of power transmission bare conductors. By segmenting the power transmission bare conductor images collected by drones and extracting the number of aluminum wire strands on the outer layer of the bare conductors, the number of aluminum wire strands of the power transmission bare conductors can be efficiently and safely identified. The technical solution of the present invention is described in detail below in conjunction with specific embodiments.

[0044] like Figure 1 As shown, an embodiment of the present invention provides a method for identifying the number of strands of bare aluminum wires of a power transmission conductor, comprising the following steps:

[0045] S1: Acquire the captured image of the bare power transmission wire and perform preprocessing.

[0046] In the specific implementation, the image of the bare power transmission wire is taken by a drone. It should be noted that when the image of the bare power transmission wire is taken by a drone, the drone and the bare wire are in a parallel position, and the bare wire needs to be in a horizontal or vertical direction in the image to facilitate the subsequent segmentation of the bare wire.

[0047] In this embodiment, the preprocessing process includes: extracting a bare wire area from the photographed transmission bare wire image, and intercepting a bare wire image of a preset size from the extracted bare wire area.

[0048] In one or more embodiments, the bare wire area in the photographed bare power transmission wire image is extracted by a watershed algorithm. The principle of the watershed algorithm is as follows:

[0049] The basic idea of ​​the watershed algorithm is to regard the image as a topological landform in geodesy. The gray value of each pixel in the image represents the altitude of the point. Each local minimum and its affected area are called a catchment basin, and the boundary of the catchment basin forms a watershed. The concept and formation of a watershed can be explained by simulating the immersion process: when the water level rises to a certain height, the water will overflow the current valley. A dam can be built on the watershed to avoid the water from the two valleys from converging. In this way, the image is divided into two pixel sets, one is the flooded valley pixel set, and the other is the watershed line pixel set; finally, the lines formed by these dams partition the entire image, thus realizing the image segmentation.

[0050] Specifically in this embodiment, the process of extracting the bare wire area in the photographed transmission bare wire image by using the watershed algorithm is as follows:

[0051] S11: Compare the average grayscale value of the global pixels of the bare power transmission wire image with the minimum grayscale value h min The difference c is used as the threshold;

[0052] S12: Select the minimum gray value h in the image of bare power transmission wire min The pixels of are used as the starting points of the immersion process. These pixels represent the deepest places, and the simulated water expands outward from these points.

[0053] S13: Water level from h min Start to rise gradually and increase gradually until it reaches the maximum grayscale value h max ;Whenever the water level rises, the grayscale value of the pixels in the image of the bare power transmission wire is also taken into account, and as the water level gradually rises, different areas are gradually "flooded";

[0054] S14: If the gray value of a pixel is equal to h at the current water level min If the difference is less than the threshold c, the pixel is considered to belong to the same catchment basin and is classified as a "flooded" area; if the difference is greater than c, the pixel is considered to be located between different catchment basins and is marked as a "watershed boundary", that is, a bare wire boundary, thereby extracting and retaining the bare wire area.

[0055] It should be noted that if the bare wire in the image of the bare power transmission wire taken by the drone is not in a horizontal or vertical direction, the pre-processed image needs to be rotated so that the bare wire is in a horizontal or vertical direction.

[0056] S2: Input the preprocessed transmission bare wire image into the pre-trained bare wire segmentation model to obtain a binary mask image of the outer aluminum wire of the bare wire.

[0057] Specifically, the bare wire segmentation model is obtained by the following method:

[0058] S21: Collect images of bare power transmission wires using drones.

[0059] S22: Annotate the boundary of the outer aluminum wire of the bare wire in the transmission bare wire image, obtain the corresponding mask image, and then construct a sample data set. The process of annotating the boundary of the outer aluminum wire of the bare wire in the transmission bare wire image includes:

[0060] The watershed algorithm is used to segment the transmission bare wire image, and only the bare wire area is retained;

[0061] Cut out a bare wire image of a preset size from the bare wire area;

[0062] The boundaries of each aluminum wire on the outer layer of the bare wire in the intercepted bare wire image are manually marked.

[0063] S23: Perform data enhancement processing on the sample data set to expand the sample data set. Data enhancement processing includes cropping, rotation, color conversion, etc. The enhancement of the sample data set can make the trained model more robust.

[0064] S24: Train the semantic segmentation network based on the sample data set to obtain a bare wire segmentation model.

[0065] In this embodiment, the semantic segmentation network adopts a fully convolutional neural network. During the training process, the stochastic gradient descent method is used for optimization, and the loss function Loss used is:

[0066]

[0067] In the formula, This is the loss of the upsampling part, where M is the total number of upsampling layers, is the weight of the mth upsampling layer, is the loss value of the mth upsampling layer, and the loss of the mth upsampling layer It is calculated based on the difference between the output of layer m and the true label (Ground Truth, GT for short); This is the loss of the final fusion step, where is the weight of the fusion step, It is the loss value of the fusion step, which measures the difference between the probability map finally output by the model and the true label (Ground Truth, GT for short). The fusion step combines the high-level features extracted in the downsampling path with the features in the upsampling path to generate the final segmentation map.

[0068] S3: Perform skeleton extraction on the binary mask image of the outer aluminum wire of the bare conductor to obtain a skeleton image of the outer aluminum wire of the bare conductor.

[0069] In specific implementation, the skeleton extraction method includes but is not limited to the HilditchThin algorithm, the Rosenfeld algorithm, and the thinning algorithm in OpenCV_Contrib.

[0070] S4: Traverse the binary mask image of the outer aluminum wire of the bare conductor to find the vanishing point of the diagonal lines. Specifically include:

[0071] S41: Traverse the binary mask image of the outer aluminum wire of the bare conductor in the column / row direction of the bare conductor length to obtain the pixel point with a pixel value of 1 on the outermost side, and count the number of pixel points with a pixel value of 1 in a 3×3 area centered on the pixel point.

[0072] It should be noted that when the length direction of the bare wire is horizontal, it is traversed column by column from left to right or from right to left, and the pixel point with a pixel value of 1 at the top or at the bottom is selected as the center for pixel point statistics. When the length direction of the bare wire is vertical, it is traversed row by row from top to bottom or from bottom to top, and the pixel point with a pixel value of 1 at the leftmost or at the rightmost is selected as the center for pixel point statistics.

[0073] S42: If the number of pixel points with a pixel value of 1 is 3, it is considered that the point is not a twill vanishing point; if the number of pixel points with a pixel value of 1 is 4, the point is a twill vanishing point.

[0074] like Figure 2 As shown in (a), when the length direction of the bare wire is horizontal, the statistical result is 3. The three pixels are connected in a straight line, and there are no bifurcated pixels, indicating that this is not a twill vanishing point. It should be noted that the situation where there are only three pixels with a pixel value of 1 in the statistical area and they are not located on the same straight line does not exist in the actual process. Therefore, there will be no situation where the statistical result is 3 but there are bifurcated pixels.

[0075] like Figure 2As shown in (b), when the length direction of the bare wire is horizontal, the statistical result is 4, where 3 pixels are connected to form a straight line, and 1 pixel intersects the straight line, and there are bifurcated pixels, indicating that this is the diagonal vanishing point. It should be noted that the situation where there are only 4 pixels with a pixel value of 1 in the statistical area and no 3 pixels are located on the same straight line does not exist in the actual process.

[0076] S5: Draw a vertical line at the twill elimination point in the vertical direction of the length direction of the binary mask image of the outer aluminum wire of the bare conductor, count the number of skeleton lines n that the vertical line passes through, and determine whether the intersection of the vertical line and the other side of the binary mask image of the outer aluminum wire of the bare conductor is the twill vanishing point; if so, the number of strands of the outer aluminum wire of the bare conductor is 2n, if not, the number of strands of the outer aluminum wire of the bare conductor is 2n-1.

[0077] When the number of aluminum wire strands on the outer layer of the bare conductor is an even number, the vanishing points of the diagonal lines on both sides are symmetrical. Therefore, the number of aluminum wire strands on the outer layer of the bare conductor is twice the number of skeleton wires through which the vertical line passes. Figure 3 As shown in (a), the number of skeleton wires that the vertical line passes through is 3, and the actual number of strands of the outer layer of the bare conductor is 6. When the number of strands of the outer layer of the bare conductor is an odd number, the vanishing points of the diagonal lines on both sides are asymmetric. Therefore, the number of strands of the outer layer of the bare conductor is twice the number of skeleton wires that the vertical line passes through. Figure 3 As shown in (b), the number of skeleton wires that the vertical line passes through is 4, which is equivalent to the vertical line passing through 3.5 aluminum wires, and the actual number of aluminum wire strands on the outer layer of the bare conductor is 7.

[0078] The method for identifying the number of aluminum wire strands in a bare power transmission conductor proposed in the above embodiment can directly segment the bare power transmission conductor and identify the number of aluminum wire strands in the outer layer of the bare power transmission conductor using images of the bare power transmission conductor taken by a drone, thereby realizing uninterrupted and contactless bare wire model identification of the transmission line, reducing the risks brought by climbing and power outages, greatly saving manpower, and improving the efficiency of identifying the number of aluminum wire strands in the outer layer of the bare power conductor.

[0079] like Figure 4 As shown, an embodiment of the present invention further provides a system for identifying the number of strands of bare aluminum wires of a power transmission conductor, comprising:

[0080] An image acquisition module is used to acquire the photographed image of the bare power transmission wire and perform preprocessing;

[0081] An image segmentation module is used to input the preprocessed transmission bare wire image into a pre-trained bare wire segmentation model to obtain a binary mask image of the outer aluminum wire of the bare wire;

[0082] A skeleton extraction module is used to extract the skeleton of the binary mask image of the outer aluminum wire of the bare conductor to obtain a skeleton image of the outer aluminum wire of the bare conductor;

[0083] The module for extracting the vanishing point of the twill is used to traverse the binary mask image of the outer aluminum wire of the bare conductor to find the vanishing point of the twill;

[0084] The aluminum wire strand number extraction module is used to draw a vertical line at the twill elimination point in the vertical direction of the length direction of the binary mask image of the outer aluminum wire of the bare conductor, count the number of skeleton lines n passed by the vertical line, and determine whether the intersection of the vertical line and the other side of the binary mask image of the outer aluminum wire of the bare conductor is the twill vanishing point; if so, the number of aluminum wire strands of the outer aluminum wire of the bare conductor is 2n, if not, the number of aluminum wire strands of the outer aluminum wire of the bare conductor is 2n-1.

[0085] It should be understood that the functional unit modules in various embodiments of the present invention may be concentrated in one processing unit, or each unit module may exist physically separately, or two or more unit modules may be integrated in one unit module, and may be implemented in the form of hardware or software.

[0086] An embodiment of the present invention further provides an electronic device, including:

[0087] Memory on which computer programs or instructions are stored;

[0088] A processor is used to load and execute the computer program or instructions to implement the method for identifying the number of aluminum wire strands of a bare power transmission conductor as described in the above embodiment.

[0089] An embodiment of the present invention further provides a computer-readable storage medium having a computer program or instruction stored thereon. When the computer program or instruction is executed by a processor, the method for identifying the number of aluminum wire strands of a bare power transmission conductor described in the aforementioned embodiment is implemented.

[0090] An embodiment of the present invention further provides a computer program product, in which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the method for identifying the number of aluminum wire strands of a bare power transmission conductor described in the above embodiment is implemented.

[0091] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0092] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0093] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0094] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0096] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for identifying the number of strands of bare aluminum wires of power transmission conductors, characterized in that: The steps include: S1: Acquire the photographed bare power transmission wire image and perform preprocessing; S2: Input the preprocessed transmission bare wire image into the pre-trained bare wire segmentation model to obtain a binary mask image of the outer aluminum wire of the bare wire; S3: extracting the skeleton of the binary mask image of the outer aluminum wire of the bare conductor to obtain a skeleton image of the outer aluminum wire of the bare conductor; S4: traverse the binary mask image of the outer aluminum wire of the bare conductor to find the vanishing point of the diagonal lines; S5: Draw a vertical line at the twill elimination point in the vertical direction of the length direction of the binary mask image of the outer aluminum wire of the bare conductor, count the number of skeleton lines n that the vertical line passes through, and determine whether the intersection of the vertical line and the other side of the binary mask image of the outer aluminum wire of the bare conductor is the twill vanishing point; if so, the number of strands of the outer aluminum wire of the bare conductor is 2n, if not, the number of strands of the outer aluminum wire of the bare conductor is 2n-1.

2. The method for identifying the number of strands of bare aluminum wires of power transmission conductors according to claim 1, characterized in that: In step S1, the preprocessing process includes: A bare wire area is extracted from the photographed bare wire image of the power transmission line, and a bare wire image of a preset size is intercepted from the extracted bare wire area.

3. The method for identifying the number of strands of bare aluminum wires of power transmission conductors according to claim 1, characterized in that: In step S2, the bare wire segmentation model is obtained by the following method: Collect images of bare power transmission wires; Mark the boundary of the outer aluminum wire of the bare conductor in the transmission bare conductor image, obtain the corresponding mask image, and then construct a sample data set; The semantic segmentation network is trained based on the sample data set to obtain the bare wire segmentation model.

4. The method for identifying the number of strands of bare aluminum wires of power transmission conductors according to claim 3, characterized in that: After constructing the sample data set, the method further includes: performing data enhancement processing on the sample data set to expand the sample data set.

5. The method for identifying the number of strands of bare aluminum wires of power transmission conductors according to claim 3, characterized in that: The process of marking the boundary of the outer aluminum wire of the bare wire in the transmission bare wire image includes: The watershed algorithm is used to segment the transmission bare wire image, and only the bare wire area is retained; Cut out a bare wire image of a preset size from the bare wire area; The boundaries of each aluminum wire on the outer layer of the bare wire in the intercepted bare wire image are manually marked.

6. The method for identifying the number of strands of bare aluminum wires of power transmission conductors according to claim 1, characterized in that: Step S4 specifically includes: The binary mask image of the outer aluminum wire of the bare conductor is traversed in the column / row direction of the bare conductor length, and the pixel point with a pixel value of 1 on the outermost side is obtained, and the number of pixel points with a pixel value of 1 in the 3×3 area centered on the pixel point is counted; If the number of pixels with a pixel value of 1 is 4, then the point is the diagonal vanishing point.

7. A system for identifying the number of strands of bare aluminum wires for power transmission, characterized in that: include: An image acquisition module is used to acquire the photographed image of the bare power transmission wire and perform preprocessing; An image segmentation module is used to input the preprocessed transmission bare wire image into a pre-trained bare wire segmentation model to obtain a binary mask image of the outer aluminum wire of the bare wire; A skeleton extraction module is used to extract the skeleton of the binary mask image of the outer aluminum wire of the bare conductor to obtain a skeleton image of the outer aluminum wire of the bare conductor; The module for extracting the vanishing point of the twill is used to traverse the binary mask image of the outer aluminum wire of the bare conductor to find the vanishing point of the twill; The aluminum wire strand number extraction module is used to draw a vertical line at the twill elimination point in the vertical direction of the length direction of the binary mask image of the outer aluminum wire of the bare conductor, count the number of skeleton lines n passed by the vertical line, and determine whether the intersection of the vertical line and the other side of the binary mask image of the outer aluminum wire of the bare conductor is the twill vanishing point; if so, the number of aluminum wire strands of the outer aluminum wire of the bare conductor is 2n, if not, the number of aluminum wire strands of the outer aluminum wire of the bare conductor is 2n-1.

8. An electronic device, characterized in that: include: Memory on which computer programs or instructions are stored; A processor is used to load and execute the computer program or instructions to implement the method for identifying the number of strands of bare aluminum wires of a power transmission conductor as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by the processor, the method for identifying the strand number of bare aluminum wires of a power transmission conductor as described in any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product stores a computer program or instructions, and when the computer program or instructions are executed by a processor, the method for identifying the strand number of bare aluminum wires of a power transmission conductor as described in any one of claims 1 to 6 is implemented.

Images