Method, system and equipment for checking stripping process of high-voltage cable and medium

Abstract

The invention discloses a high-voltage cable stripping process checking method, system and device and a medium, and the method comprises the steps: carrying out the key point detection of an obtained cable image of a high-voltage cable, obtaining a plurality of stripping and cutting key points, carrying out the stripping and cutting material checking based on each stripping and cutting key point, and obtaining a corresponding stripping and cutting layer material checking result; performing edge feature extraction on the cable image to obtain an edge feature set; based on the edge feature set and each stripping and cutting key point, determining a corresponding stripping and cutting layer length, and performing stripping and cutting length checking on the stripping and cutting layer length to obtain a corresponding stripping and cutting layer length checking result; and based on the stripping and cutting layer length checking result and the stripping and cutting layer material checking result, obtaining a stripping process checking result of the high-voltage cable. According to the invention, the high-voltage cable stripping process can be automatically checked, and the accuracy and efficiency of the checking of the stripping process are improved.

Description

Technical Field

[0001] The present application relates to the field of wire stripping verification, and particularly to a method, system, device and medium for verifying the wire stripping process of high-voltage cables. Background Art

[0002] During the process of manufacturing the terminal head and intermediate joint of a high-voltage cable, wire stripping is a crucial step, which is directly related to the electrical connection performance and insulation safety level of the cable joint. Therefore, it is necessary to verify the wire stripping process of high-voltage cables to ensure the precise stripping of key parts such as the cable conductor, semiconductor shielding layer, and insulation layer, which is crucial for forming a good electrical connection.

[0003] However, in the current wire stripping process, manual verification is mainly relied on, lacking automated verification means. Workers often need to operate based on experience and feel during the wire stripping process. This method is easily affected by human factors, resulting in difficult-to-guarantee wire stripping accuracy and consistency, and low efficiency at the same time. Therefore, in order to reduce the adverse effects brought by human factors, it is necessary to introduce automated verification means to improve the accuracy and efficiency of wire stripping process verification.

[0004] Application Content

[0005] The present application provides a method, system, device and medium for verifying the wire stripping process of high-voltage cables, which can automatically verify the wire stripping process of high-voltage cables and improve the accuracy and efficiency of wire stripping process verification.

[0006] In a first aspect, the present application provides a method for verifying the wire stripping process of high-voltage cables, including:

[0007] Performing key point detection on the obtained cable image of the high-voltage cable to obtain a plurality of stripping key points, and performing stripping material verification based on each of the stripping key points to obtain corresponding stripping layer material verification results;

[0008] Extracting edge features from the cable image to obtain an edge feature set;

[0009] Based on the edge feature set and each of the stripping key points, determining the corresponding stripping layer length, and performing stripping length verification on the stripping layer length to obtain corresponding stripping layer length verification results;

[0010] Based on the stripping layer length verification result and the stripping layer material verification result, obtaining the wire stripping process verification result of the high-voltage cable.

[0011] In the embodiments of the present application, by performing key point detection on the cable image of the high-voltage cable obtained, the key points of the high-voltage cable can be accurately determined, facilitating subsequent verification of the stripping material and determination of the length of the stripping layer; by extracting edge features from the cable image, the required edge feature points can be accurately extracted and the amount of data calculation can be reduced, thereby improving the accuracy and efficiency of subsequent verification of the stripping process; based on the edge feature set and each of the stripping key points, the corresponding length of the stripping layer is determined, and the length of the stripping layer of the high-voltage cable can be accurately and quickly determined, facilitating subsequent verification of the stripping length; based on the verification result of the stripping layer length and the verification result of the stripping layer material, the stripping process of the high-voltage cable can be automatically verified, and the verification result of the stripping process of the high-voltage cable can be accurately and quickly obtained. Compared with the prior art, the present application can automatically verify the stripping process of the high-voltage cable, improving the accuracy and efficiency of the stripping process verification.

[0012] Further, the key point detection is performed on the cable image of the high-voltage cable obtained to obtain a plurality of stripping key points, specifically:

[0013] Obtain the cable image of the stripping part of the high-voltage cable, and determine the corresponding number of stripping layers based on the cable image;

[0014] Combined with the number of stripping layers, and perform key point detection on the cable image through a preset key point detection algorithm to obtain a plurality of the stripping key points.

[0015] In this way, by performing key point detection on the cable image of the high-voltage cable obtained, the key points of the high-voltage cable can be accurately determined, facilitating subsequent verification of the stripping material and determination of the length of the stripping layer.

[0016] Further, the verification of the stripping material is performed based on each of the stripping key points to obtain the corresponding verification result of the stripping layer material, specifically:

[0017] Determine a corresponding number of first center points for each of the stripping key points;

[0018] Based on each of the first center points, determine the corresponding number of image color values, and calculate the number of color distances between each of the image color values and the material reference color value;

[0019] Judge whether each of the color distances meets the preset color distance threshold to obtain the corresponding verification result of the stripping layer material.

[0020] In this way, by calculating the color distance between the image color value and the reference color value, and judging whether each of the color distances meets the preset color distance threshold, the stripping material of the high-voltage cable can be accurately verified based on the color of the stripping layer.

[0021] Further, the edge feature extraction of the cable image to obtain an edge feature set is specifically as follows:

[0022] Perform instance segmentation on the cable image to obtain an initial instance segmentation result, and perform dilation processing on the initial instance segmentation result to obtain a target instance segmentation result;

[0023] Perform grayscale processing on the cable image to obtain a corresponding grayscale image, and perform edge feature extraction on the grayscale image to obtain corresponding edge features;

[0024] Determine a corresponding edge feature set based on the target instance segmentation result and the edge features.

[0025] In this way, by performing edge feature extraction on the cable image, the required edge feature points can be accurately extracted and the data calculation amount can be reduced, thereby improving the accuracy and efficiency of subsequent stripping process verification.

[0026] Further, the determination of the corresponding stripping layer length based on the edge feature set and each of the stripping key points is specifically as follows:

[0027] For each of the stripping key points, determine a corresponding number of second center points, and expand the line segments between the second center points to obtain expanded line segments;

[0028] Based on the expanded line segments and the edge feature set, obtain a first point set;

[0029] Perform clustering on the first point set to obtain a second point set and a third point set;

[0030] Calculate the first distance between the second point set and the third point set, and use the two points with the smallest first distance as the stripping layer demarcation points, and determine the corresponding stripping layer length based on the stripping layer demarcation points.

[0031] In this way, by determining the corresponding stripping layer length based on the edge feature set and each of the stripping key points, the stripping layer length of the high-voltage cable can be accurately and quickly determined, which is convenient for subsequent verification of the stripping length.

[0032] Further, the obtaining of the first point set based on the expanded line segments and the edge feature set is specifically as follows:

[0033] Calculate the projection lengths of each point in the edge feature set on the expanded line segments;

[0034] Determine the second distance from each point to the expanded line segments based on the projection lengths;

[0035] If the second distance meets a preset distance threshold, add the points that meet the preset distance threshold to the first point set until the edge feature set is traversed to obtain the first point set.

[0036] In this way, by calculating the intersection of the extended line segment and the edge feature set, it is convenient to subsequently determine the corresponding stripping layer demarcation point, and further convenient to determine the length of the stripping layer.

[0037] Further, clustering the first point set to obtain a second point set and a third point set specifically includes:

[0038] Randomly determine two first clustering centers;

[0039] Calculate the third distance between each point and the first clustering center, and assign each point to the first clustering center with the closest third distance;

[0040] Continuously calculate the coordinate mean value of each point in the first clustering center, and iteratively update the second clustering center based on the coordinate mean value until the current iterated second clustering center meets the preset conditions, then determine the second point set and the third point set based on the second clustering center.

[0041] In this way, by clustering the first point set, the first point set can be divided into a second point set and a third point set, which is convenient to subsequently determine the corresponding stripping layer demarcation point, and further convenient to determine the length of the stripping layer.

[0042] In a second aspect, the present application provides a stripping process verification system for a high-voltage cable, including: a first verification module, an extraction module, a second verification module, and a third verification module;

[0043] The first verification module is used to perform key point detection on the cable image of the high-voltage cable obtained, obtain a plurality of stripping key points, and perform stripping material verification based on each of the stripping key points to obtain a corresponding stripping layer material verification result;

[0044] The extraction module is used to extract edge features from the cable image to obtain an edge feature set;

[0045] The second verification module is used to determine the corresponding stripping layer length based on the edge feature set and each of the stripping key points, and perform stripping length verification on the stripping layer length to obtain a corresponding stripping layer length verification result;

[0046] The third verification module is used to obtain a stripping process verification result of the high-voltage cable based on the stripping layer length verification result and the stripping layer material verification result.

[0047] In the embodiment of the present application, by performing key point detection on the obtained cable image of the high-voltage cable, the key points of the high-voltage cable can be accurately determined, which is convenient for subsequent verification of the stripping material and determination of the stripping layer length; by extracting edge features from the cable image, the required edge feature points can be accurately extracted and the data calculation amount can be reduced, thereby improving the accuracy and efficiency of subsequent stripping process verification; based on the edge feature set and each of the stripping key points, the corresponding stripping layer length can be determined, and the stripping layer length of the high-voltage cable can be accurately and quickly determined, which is convenient for subsequent verification of the stripping length; based on the stripping layer length verification result and the stripping layer material verification result, the stripping process of the high-voltage cable can be automatically verified, and the stripping process verification result of the high-voltage cable can be accurately and quickly obtained. Compared with the prior art, the present application can automatically verify the stripping process of the high-voltage cable, improving the accuracy and efficiency of the stripping process verification.

[0048] In a third aspect, the present application further provides a terminal device, including: one or more processors; a memory coupled to the processor for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the stripping process verification method of the high-voltage cable as described in the present application.

[0049] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the stripping process verification method of the high-voltage cable as described in the present application is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a schematic flowchart of an embodiment of the stripping process verification method of the high-voltage cable provided by the present application;

[0051] Figure 2 is a schematic diagram of the key point format provided by the present application;

[0052] Figure 3 is a schematic diagram of the determination process of the first center provided by the present application;

[0053] Figure 4 is Figure 1 the schematic flowchart of step S102 in

[0054] Figure 5 is Figure 1 the schematic flowchart of step S103 in

[0055] Figure 6 is a schematic diagram of the determination process of the second center provided by the present application;

[0056] Figure 7It is a schematic flowchart of another embodiment of the stripping process verification method for high-voltage cables provided by this application;

[0057] Figure 8 It is a schematic structural diagram of an embodiment of the stripping process verification system for high-voltage cables provided by this application;

[0058] Figure 9 It is a schematic structural diagram of the terminal device provided by this application. Detailed implementation manners

[0059] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the protection scope of this application.

[0060] It should be understood that the step numbers used in the text are only for convenience of description and do not limit the order of execution of the steps.

[0061] It should be understood that the terms used in the specification of this invention are only for the purpose of describing specific embodiments and are not intended to limit this invention. As used in the specification of this invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0062] The terms "include" and "comprise" indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0063] The term " / or" refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0064] During the process of manufacturing the terminal head and the intermediate joint of the high-voltage cable, stripping is a key step, which is directly related to the electrical connection performance and insulation safety level of the cable joint. Therefore, it is necessary to verify the stripping process to ensure the precise stripping of the conductor, semiconductor shielding layer, and insulation layer. However, in the current stripping link, manual verification is mainly relied on, lacking automated verification means, and it is difficult to ensure the accuracy and efficiency of the stripping process verification. Therefore, automated verification means need to be introduced to improve the accuracy and efficiency of the stripping process verification.

[0065] Next, the nouns involved in this application will be analyzed:

[0066] A depth camera is a 3D imaging camera that can achieve 3D imaging on the X, Y, and Z axes. It can not only obtain the planar visible light image (X-axis, Y-axis) of the object being photographed, but also obtain the distance (Z-axis) of the object being photographed. A typical method for measuring distance is the Time of Flight (ToF) method. By continuously emitting light pulses (generally invisible light) onto the object to be observed, and then receiving the light pulses reflected from the object, the distance between the object and the camera is calculated based on the round-trip time of the light pulses.

[0067] Clustering Algorithms are core technologies in data mining and pattern recognition. They group the objects in a dataset so that the objects within the same group have a high degree of similarity, while the objects in different groups have a low degree of similarity. These algorithms can be widely applied in fields such as image processing, market analysis, and bioinformatics. Through clustering, people can understand the structure and characteristics of the data, discover the patterns and rules hidden in the data, and thus perform more effective data analysis and decision-making.

[0068] Dilation is a morphological operation that can expand the mask area to include more adjacent pixels.

[0069] The Canny operator is a popular edge detection algorithm that can achieve a good balance between noise suppression and edge detection.

[0070] Based on this, the embodiments of the present application provide a method, system, device, and medium for verifying the wire stripping process of high-voltage cables, which can automatically verify the wire stripping process of high-voltage cables and improve the accuracy and efficiency of wire stripping process verification.

[0071] The method, system, device, and medium for verifying the wire stripping process of high-voltage cables provided by the embodiments of the present application are specifically described through the following embodiments. First, the method for verifying the wire stripping process of high-voltage cables in the embodiments of the present application is described.

[0072] The wire stripping process verification method for high-voltage cables provided by the embodiments of the present application relates to the field of wire stripping verification. The wire stripping process verification method for high-voltage cables provided by the embodiments of the present application can be applied to terminals, can also be applied to server sides, or can be software running on terminals or server sides. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, can also be configured as a server cluster or a distributed system composed of multiple physical servers, or can also be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the wire stripping process verification method for high-voltage cables, etc., but is not limited to the above forms.

[0073] The present application can also be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, small computers, large computers, distributed computing environments including any of the above systems or devices, and so on. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0074] Embodiment 1

[0075] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of an embodiment of the wire stripping process verification method for high-voltage cables provided by the present application, including steps S101 to S104;

[0076] Step S101, perform key point detection on the obtained cable image of the high-voltage cable to obtain a number of stripping key points, and perform stripping material verification based on each of the stripping key points to obtain the corresponding stripping layer material verification result;

[0077] In some embodiments, the cable image not only stores the position distance corresponding to the pixel coordinates and the camera, but also stores the three-dimensional coordinates of the position corresponding to the pixel coordinates in the camera coordinate system.

[0078] In some embodiments, key point detection is performed on the cable image of the high-voltage cable obtained, and a number of stripping key points are obtained, including: obtaining the cable image of the stripped part of the high-voltage cable, and determining the corresponding number of stripping layers based on the cable image; combining the number of stripping layers, and performing key point detection on the cable image through a preset key point detection algorithm to obtain a number of the stripping key points. Specifically, first, for the high-voltage cable that has been stripped, the cable image of the stripped part of the high-voltage cable can be taken, but not limited to, by a high-resolution camera, professional equipment or depth camera; second, after the cable image is obtained, the hierarchical structure of the cable image is analyzed through an image analysis algorithm, and the number of stripping layers is determined according to the cross-sectional structure, color, texture and other characteristics of the cable image; finally, since the corresponding key point format has been pre-constructed according to the number of stripping layers, when a key point detection algorithm is selected to perform key point detection on the cable image, a number of stripping key points will be output according to the corresponding key point format, where the stripping key points are usually located at the junction of the stripping layers or at positions with significant characteristics, and the key point detection algorithm can be, but not limited to, YOLO, OpenPose, etc.

[0079] In this way, by performing key point detection on the cable image of the high-voltage cable obtained, the key points of the high-voltage cable can be accurately determined, which is convenient for subsequent verification of the stripping material and determination of the stripping layer length.

[0080] In some embodiments, the stripped part of the high-voltage cable in the cable image is located in the central part of the image.

[0081] In some embodiments, the image analysis algorithm includes, but is not limited to, edge detection algorithms and contour extraction algorithms, etc., and this application does not make restrictions.

[0082] In some embodiments, for a high-voltage cable that needs to be stripped i layers, a key point format of 2×(i + 1) points is constructed. Exemplarily, for a cable that needs to be stripped 3 layers, the key point format diagram as shown in Figure 2 is constructed, that is, a key point format of 8 points.

[0083] In some embodiments, based on each of the stripping key points, stripping material verification is performed to obtain the corresponding stripping layer material verification result, including: determining a number of first center points corresponding to each of the stripping key points; determining a number of image color values corresponding to each of the first center points, and calculating a number of color distances between each of the image color values and the material reference color value; determining whether each of the color distances satisfies a preset color distance threshold to obtain the corresponding stripping layer material verification result. Specifically, first, according to the structure of each determined stripping key point, the center of each stripping layer, that is, the first center point, is determined. The determination process of the first center is as follows Figure 3As shown, connect the stripping key point 0 and the stripping key point 5, and then connect the stripping key point 1 and the stripping key point 4. The two line segments intersect at point A 1 This point is the center point of the first stripping layer. Similarly, connect the stripping key point 1 and the stripping key point 6, and then connect the stripping key point 2 and the stripping key point 5. The two line segments intersect at point A 2 This point is the center point of the second stripping layer. Connect the stripping key point 2 and the stripping key point 7, and then connect the stripping key point 3 and the stripping key point 6. The two line segments intersect at point A 3 This point is the center point of the third stripping layer, that is, A 1 、A 2 and A 3 are the first center points; Secondly, use the first center points (A 1 、A 2 and A 3 ) as the pixel feature points of the corresponding stripping layers (the first stripping layer, the second stripping layer, and the third stripping layer), and obtain the image color values corresponding to each pixel feature point Then, calculate each image color value and the material reference color value to obtain several color distances That is Finally, compare this color distance with the preset color distance threshold d cth If the color distance is less than the color distance threshold d cth , the material of this stripping layer passes the verification, otherwise the material of this stripping layer fails the verification. If the color distances between the image color values corresponding to each first center point and the material reference color value are all less than the preset color threshold d cth , the materials of all stripping layers pass the verification. If the materials of all stripping layers pass the verification, the stripping layer materials of this high-voltage cable meet the requirements. If the material of any one stripping layer fails the verification, the stripping layer materials of this high-voltage cable do not meet the requirements.

[0084] In some embodiments, if the shooting angle is inclined, the first center point obtained by the intersection of the above key points may not necessarily fall on the corresponding stripping layer. At this time, first, edge features of the cable image need to be extracted to obtain an edge feature set. Second, for each of the stripping key points, a corresponding number of second center points are determined, and the line segments between the second center points are expanded to obtain expanded line segments. Then, based on the expanded line segments and the edge feature set, a first point set is obtained, and the first point set is clustered to obtain a second point set and a third point set. Finally, a first distance between the second point set and the third point set is calculated, and the two points with the smallest first distance are used as the stripping layer demarcation points, and the midpoint of the connection line of the stripping layer demarcation points is used as the pixel feature point of the corresponding stripping layer. Further, the material of the stripping layer is verified based on the image color value of this point. It should be noted that the determination process of the stripping layer demarcation points will be elaborated in detail in step S103 below.

[0085] In this way, by calculating the color distance between the image color value and the reference color value and determining whether each color distance meets the preset color distance threshold, the stripping material of the high-voltage cable can be accurately verified based on the color of the stripping layer.

[0086] Step S102: Extract edge features of the cable image to obtain an edge feature set;

[0087] Please refer to Figure 4 , in some embodiments, step S102 includes but is not limited to steps S401 to S403;

[0088] Step S401: Perform instance segmentation on the cable image to obtain an initial instance segmentation result, and perform dilation processing on the initial instance segmentation result to obtain a target instance segmentation result;

[0089] Step S402: Perform grayscale processing on the cable image to obtain a corresponding grayscale image, and extract edge features of the grayscale image to obtain corresponding edge features;

[0090] Step S403: Determine a corresponding edge feature set based on the target instance segmentation result and the edge features.

[0091] In step S401 of some embodiments, the cable image is input into a pre-trained instance segmentation model to identify different objects (including high-voltage cables) in the cable image and generate a mask for each object, that is, to obtain an initial instance segmentation result. Subsequently, the initial instance segmentation result corresponding to the high-voltage cable is extracted from the initial instance segmentation result, and the initial instance segmentation result is dilated by a dilation algorithm to ensure that the initial instance segmentation result is dilated according to preset dilation parameters to obtain a target instance segmentation result. It should be noted that the dilation parameters can be set according to the actual situation of the cable area and the desired edge feature accuracy.

[0092] It should be noted that by collecting a large number of frontal color images of the cable stripping part, and then manually annotating the polygonal frames of the pixel areas where the cables are located to form a training dataset, and further training the selected instance segmentation algorithm model (which can but is not limited to using the yolov8-seg instance segmentation algorithm model) through supervised learning, so that the model has the ability to segment the pixel areas where the cables are located. Then, taking the cable image as the input and using the above model for inference, the initial instance segmentation result can be obtained.

[0093] It should be noted that in order to avoid the problem that the instance segmentation algorithm may cause the loss of the high-voltage cable edge, the mask boundary can be expanded by dilation to ensure that the mask can contain the cable edge and avoid losing important edge feature points.

[0094] In step S402 of some embodiments, the cable image is converted into a grayscale image to simplify the subsequent edge detection process, and two thresholds (a low threshold and a high threshold) are set through an edge detection algorithm. The low threshold is used to determine which pixels in the grayscale image belong to the edge, and the high threshold is used to connect these pixels to form a complete edge. After being processed by the edge detection algorithm, a binary image will be obtained, where white pixels represent the edge and black pixels represent non-edge. From this binary image, the edge features can be extracted. It should be noted that the edge detection algorithm can be but is not limited to the Canny edge detection operator.

[0095] In step S403 of some embodiments, the intersection of the target instance segmentation result and the edge features is calculated. By checking whether each edge feature point is located within the target instance segmentation result area, after the intersection calculation, an edge feature set overlapping with the target instance segmentation result will be obtained. These point sets represent the edge features of the high-voltage cable area and can reduce the interference of the background.

[0096] It should be noted that the edge feature extraction algorithm will also extract useless edge feature points of the background, resulting in an increase in subsequent calculation complexity. By calculating the intersection, the edge feature points within the target instance segmentation result will be retained, while the edge feature points outside the target instance segmentation result will be eliminated.

[0097] In this way, by performing edge feature extraction on the cable image, the required edge feature points can be accurately extracted and the data calculation amount can be reduced, thereby improving the accuracy and efficiency of subsequent stripping process verification.

[0098] Step S103: Based on the edge feature set and each of the stripping key points, determine the corresponding stripping layer length, and perform stripping length verification on the stripping layer length to obtain the corresponding stripping layer length verification result;

[0099] Please refer to Figure 5 , in some embodiments, step S103 includes but is not limited to steps S501 to S504;

[0100] Step S501: For each of the stripping key points, determine the corresponding several second center points, and expand the line segments between the second center points to obtain expanded line segments;

[0101] Step S502: Based on the expanded line segments and the edge feature set, obtain a first point set;

[0102] Step S503: Cluster the first point set to obtain a second point set and a third point set;

[0103] Step S504: Calculate the first distance between the second point set and the third point set, and use the two points with the smallest first distance as the stripping layer demarcation points, and determine the corresponding stripping layer length based on the stripping layer demarcation points.

[0104] In step S501 of some embodiments, after obtaining the stripping key points, it is necessary to determine the corresponding stripping center points according to the stripping key points, that is, the second center points. The determination process of the second center is as Figure 6 shown. Among them, connect stripping key point 0 and stripping key point 4, and take the center point thereof, denoted as M 0 , connect stripping key point 1 and stripping key point 5, and take the center point thereof, denoted as M 1 , connect stripping key point 2 and stripping key point 6, and take the center point thereof, denoted as M 2 , connect stripping key point 3 and stripping key point 7, and take the center point thereof, denoted as M 3 , that is, M 0 , M 1 , M 2 and M 3as the second center point, and connect the second center to obtain a number of first line segments. Extend each of the first line segments outward by a preset distance to obtain extended line segments. Exemplarily, taking the length of the second stripping layer as an example, connect the second center point M 1 with M 2 to obtain the line segment M 1 M 2 and extend a distance l on both sides of the line segment respectively 0 to obtain the new line segment N 1 N 2 .

[0105] In step S502 of some embodiments, it includes: calculating the projection lengths of each point in the edge feature set on the extended line segments; determining the second distances from each point to the extended line segments based on the projection lengths; if the second distances meet the preset distance threshold, adding the points that meet the preset distance threshold to the first point set until the edge feature set is traversed to obtain the first point set. Specifically, calculate a certain point B M in the edge feature set B Mi to the projection length t of the extended line segment N 1 N 2 , that is the projection length t on , where where · represents the dot product of vectors; subsequently, judge the projection length t to determine the second distance, where the second distance is the shortest distance d M from a certain point B Mi in the edge feature set B 1 to the extended line segment N 2 N min . If the projection length t is greater than 1, at this time the second distance is the distance from B Mi to the point N 2 , that is: If the projection length t is less than 0, at this time the second distance is the distance from B Mi to the point N 1 , that is: If the projection length t is between 0 and 1, that is, 0 ≤ t ≤ 1, at this time the second distance is the vertical distance from B Mi to the extended line segment N 1 N 2 , that is: Finally, judge whether the second distance d min is less than 1. If the second distance d min is less than 1, add the point B Mi to the first point set I, otherwise do not add it until the edge feature set is traversed to obtain the first point set I to find all candidate stripping layer boundary points.

[0106] In step S503 of some embodiments, it includes: randomly determining two first clustering centers; calculating the third distance between each point and the first clustering centers, and allocating each point to the first clustering center with the closest third distance; continuously calculating the coordinate mean of each point in the first clustering centers, and iteratively updating the second clustering centers based on the coordinate mean until the currently iterated second clustering centers meet the preset conditions, then determining the second point set and the third point set based on the second clustering centers. Specifically, it is necessary to randomly determine two first clustering centers in advance, then calculate the third distance between each point and the first clustering centers, and make a comparison to allocate each point to the first clustering center with the closest third distance. Subsequently, continuously calculate the coordinate mean of each point in the first clustering centers, and use the coordinate mean as the second clustering center until the distance between the second clustering center and the first clustering center is less than or equal to the preset distance threshold, which indicates that the clustering center no longer changes significantly. In this way, the iteration can be stopped, and the final clustering centers are the second point set and the third point set. This step can divide the candidate boundary point sets on both sides of the stripping layer, facilitating the subsequent determination of the stripping layer boundary points.

[0107] In step S504 of some embodiments, first, using the exhaustive method, respectively take out a point i 1 (i 1 ∈I 1 ) and i 2 (i 2 ∈I 2 ) from the second point set and the third point set in a traversing manner. The pixel coordinates of these two points are and calculate the first distance between these two points where the first distance is the two-dimensional pixel distance; secondly, after obtaining the first distance, determine the two points B 1 and B 2 with the smallest first distance. These two points are the stripping layer boundary points; finally, after obtaining the stripping layer boundary points B 1 and B 2 , it is necessary to obtain the three-dimensional coordinates of the two points in the camera coordinate system according to the mapping relationship between the visible light image and the cable image and calculate their Euclidean distance This Euclidean distance is also the length of the stripping layer.

[0108] It should be noted that the mapping relationship between the visible light image and the cable image can be provided by the software development tool of the depth camera.

[0109] In some embodiments, checking the stripping layer length to obtain the corresponding stripping layer length check result includes: after determining the stripping layer length, the stripping layer length is compared with a preset length threshold d th . If the stripping layer length is less than the preset length threshold d th , the length of this stripping layer passes the check; otherwise, the length of this stripping layer fails the check. If the lengths of all stripping layers pass the check, the stripping layer length of this high-voltage cable meets the requirements; if the length of any one stripping layer fails the check, the stripping layer length of this high-voltage cable does not meet the requirements.

[0110] In this way, based on the edge feature set and each of the stripping key points, the corresponding stripping layer length can be determined accurately and quickly, facilitating subsequent checking of the stripping length.

[0111] Step S104: Obtain the wire stripping process check result of the high-voltage cable based on the stripping layer length check result and the stripping layer material check result.

[0112] It can be understood that after obtaining the stripping layer material check result through step S101 and the stripping layer length check result through step S103, when both the stripping layer material check result and the stripping layer length check result meet the requirements, the wire stripping process of this high-voltage cable meets the requirements; if one of the check results does not meet the requirements or both check results do not meet the requirements, the wire stripping process of this high-voltage cable does not meet the requirements.

[0113] In the embodiment of the present application, by performing key point detection on the cable image of the obtained high-voltage cable, the key points of the high-voltage cable can be accurately determined, facilitating subsequent stripping material check and determination of the stripping layer length; by extracting edge features from the cable image, the required edge feature points can be accurately extracted and the data calculation amount can be reduced, thereby improving the accuracy and efficiency of subsequent wire stripping process check; based on the edge feature set and each of the stripping key points, the corresponding stripping layer length can be determined accurately and quickly, facilitating subsequent checking of the stripping length; based on the stripping layer length check result and the stripping layer material check result, the wire stripping process of the high-voltage cable can be automatically checked, and the wire stripping process check result of the high-voltage cable can be obtained accurately and quickly. Compared with the prior art, the present application can automatically check the wire stripping process of the high-voltage cable, improving the accuracy and efficiency of the wire stripping process check.

[0114] Embodiment 2

[0115] For easy understanding, please refer to Figure 7 , Figure 7It is a schematic flow diagram of another embodiment of the stripping process verification method for high-voltage cables provided by this application; it includes the following steps;

[0116] Step S701, perform key point detection on the cable image to obtain stripping key points;

[0117] Step S702, perform stripping material verification based on the stripping key points to obtain a stripping layer material verification result;

[0118] Step S703, extract edge features from the cable image to obtain corresponding edge features;

[0119] Step S704, perform instance segmentation on the cable image to obtain a corresponding target instance segmentation result;

[0120] Step S705, based on the edge features and the target instance segmentation result, obtain a corresponding edge feature set;

[0121] Step S706, based on the stripping key points and the edge feature set, determine the corresponding stripping layer length;

[0122] Step S707, perform stripping length verification based on the stripping layer length to obtain a stripping length verification result;

[0123] Step S707, based on the stripping layer length verification result and the stripping layer material verification result, obtain a stripping process verification result for the high-voltage cable.

[0124] It should be noted that steps S701 to S707 have been elaborated in detail in Embodiment 1, so they will not be repeated here.

[0125] Embodiment 3

[0126] Please refer to Figure 8 , Figure 8 It is a schematic structural diagram of an embodiment of the stripping process verification system for high-voltage cables provided by this application; it includes: a first verification module 100, an extraction module 200, a second verification module 300, and a third verification module 400;

[0127] The first verification module 100 is used to perform key point detection on the cable image of the high-voltage cable obtained, obtain a plurality of stripping key points, and perform stripping material verification based on each of the stripping key points to obtain a corresponding stripping layer material verification result;

[0128] The extraction module 200 is used to extract edge features from the cable image to obtain an edge feature set;

[0129] The second verification module 300 is configured to determine the corresponding stripping layer length based on the edge feature set and each of the stripping key points, and perform stripping length verification on the stripping layer length to obtain a corresponding stripping layer length verification result;

[0130] The third verification module 400 is configured to obtain a wire stripping process verification result of the high-voltage cable based on the stripping layer length verification result and the stripping layer material verification result.

[0131] Regarding the information interaction, execution process, etc. among the modules in the above wire stripping process verification system for high-voltage cables, since they are based on the same concept as the embodiments of the wire stripping process verification method for high-voltage cables in the first aspect of the present invention, the achieved technical effects are basically the same. For specific content, reference can be made to the description in Embodiment 1 of the method of the present invention, and details will not be repeated here.

[0132] The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separated, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the method of this embodiment.

[0133] Please refer to Figure 9 , Figure 9 which illustrates the hardware structure of a terminal device in another embodiment. The terminal device includes:

[0134] A processor 901, which can be implemented in ways such as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is configured to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0135] A memory 902, which can be implemented in forms such as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 902 and are called by the processor 901 to execute the dialogue risk assessment method based on a large model of the present application embodiments;

[0136] An input / output interface 903, which is configured to implement information input and output;

[0137] A communication interface 904 for implementing communication interaction between this device and other devices, which can achieve communication through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.);

[0138] A bus 905 for transmitting information between various components of the device (such as a processor 901, a memory 902, an input / output interface 903, and a communication interface 904);

[0139] Among them, the processor 901, the memory 902, the input / output interface 903, and the communication interface 904 achieve communication connections with each other inside the device through the bus 905.

[0140] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the method for dialogue risk assessment based on a large model as described in the first embodiment above.

[0141] Those of ordinary skill in the art can understand that all or part of the processes in implementing the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above embodiments of the various methods. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0142] Those of ordinary skill in the art can understand that all or part of the processes in implementing the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above embodiments of the various methods. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0143] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present application. It should be understood that the above are only specific embodiments of the present application and are not used to limit the protection scope of the present application.

[0144] It is particularly pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for verifying the stripping process of a high voltage cable, characterized in that: include: Perform key point detection on the acquired cable image of the high-voltage cable to obtain a number of stripping key points, and perform stripping material verification based on each of the stripping key points to obtain a corresponding stripping layer material verification result; Extracting edge features from the cable image to obtain an edge feature set; Based on the edge feature set and each of the stripping key points, a corresponding stripping layer length is determined, and a stripping length calibration is performed on the stripping layer length to obtain a corresponding stripping layer length calibration result; Based on the stripping layer length verification result and the stripping layer material verification result, a wire stripping process verification result of the high-voltage cable is obtained.

2. The method for verifying the stripping process of a high-voltage cable according to claim 1, characterized in that: The key point detection is performed on the acquired cable image of the high-voltage cable to obtain several stripping key points, specifically: Acquire the cable image of the stripped portion of the high-voltage cable, and determine the corresponding number of stripped layers based on the cable image; In combination with the number of stripped layers, key point detection is performed on the cable image using a preset key point detection algorithm to obtain a plurality of stripping key points.

3. The method for verifying the stripping process of a high-voltage cable according to claim 1, characterized in that: The stripping material verification is performed based on each of the stripping key points to obtain the corresponding stripping layer material verification result, which is specifically: Determining a number of corresponding first center points for each of the stripping key points; Determine a plurality of corresponding image color values ​​based on each of the first center points, and calculate a plurality of color distances between each of the image color values ​​and a material reference color value; It is determined whether each color distance meets a preset color distance threshold value, and a corresponding peeling layer material verification result is obtained.

4. The method for verifying the stripping process of a high-voltage cable according to claim 1, characterized in that: The edge feature extraction of the cable image is performed to obtain an edge feature set, specifically: Performing instance segmentation on the cable image to obtain an initial instance segmentation result, and performing expansion processing on the initial instance segmentation result to obtain a target instance segmentation result; Performing grayscale processing on the cable image to obtain a corresponding grayscale image, and performing edge feature extraction on the grayscale image to obtain corresponding edge features; A corresponding edge feature set is determined based on the target instance segmentation result and the edge feature.

5. The method for verifying the stripping process of a high-voltage cable according to claim 1, characterized in that: The determining of the corresponding stripping layer length based on the edge feature set and each of the stripping key points is specifically: Determine a plurality of corresponding second center points for each of the stripping key points, and expand the line segments between the second center points to obtain expanded line segments; Based on the outward expansion line segment and the edge feature set, a first point set is obtained; Clustering the first point set to obtain a second point set and a third point set; A first distance between the second point set and the third point set is calculated, and two points with the smallest first distance are used as peeling layer demarcation points, and a corresponding peeling layer length is determined based on the peeling layer demarcation points.

6. The method for verifying the stripping process of a high-voltage cable according to claim 5, characterized in that: The first point set is obtained based on the outward expansion line segment and the edge feature set, specifically: Calculate a number of projection lengths of each point in the edge feature set on the outward expansion line segment; Determine a second distance from each point to the outward expansion line segment based on each of the projection lengths; If the second distance meets a preset distance threshold, points meeting the preset distance threshold are added to the first point set until the edge feature set is traversed to obtain the first point set.

7. The method for verifying the stripping process of a high-voltage cable according to claim 5, characterized in that: The clustering of the first point set to obtain the second point set and the third point set is specifically as follows: Randomly determine two first cluster centers; Calculate the third distance between each point and the first cluster center, and assign each point to the first cluster center with the closest third distance; The coordinate mean of each point in the first cluster center is continuously calculated, and the second cluster center is iteratively updated based on the coordinate mean until the second cluster center of the current iteration meets the preset condition, and the second point set and the third point set are determined based on the second cluster center.

8. A high voltage cable stripping process verification system, characterized in that: include: A first checking module, an extraction module, a second checking module and a third checking module; The first verification module is used to perform key point detection on the acquired cable image of the high-voltage cable to obtain a plurality of stripping key points, and perform stripping material verification based on each of the stripping key points to obtain a corresponding stripping layer material verification result; The extraction module is used to extract edge features from the cable image to obtain an edge feature set; The second verification module is used to determine the corresponding stripping layer length based on the edge feature set and each of the stripping key points, and perform stripping length verification on the stripping layer length to obtain a corresponding stripping layer length verification result; The third verification module is used to obtain the wire stripping process verification result of the high-voltage cable based on the stripping layer length verification result and the stripping layer material verification result.

9. A terminal device, characterized in that: include: one or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the high-voltage cable stripping process verification method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for verifying the stripping process of a high-voltage cable as described in any one of claims 1 to 7 is implemented.

Images