Method and device for determining bending radius of cable and computer equipment

Abstract

The invention relates to a cable bending radius determination method and device and computer equipment. The method comprises the steps of obtaining a plurality of cable sub-images in an original cable image based on the original cable image of a to-be-detected cable, performing center line fitting on cable sections in the cable sub-images, obtaining position information of effective center points in the cable sections, determining bending radiuses of the cable sections according to the position information of the effective center points in the cable sections, and determining the bending radiuses of the cable sections according to the bending radiuses of the cable sections. Wherein different cable sub-images comprise different cable sections in the to-be-detected cable. By adopting the method, manual participation is not needed, so that the determination efficiency of the bending radius of the cable can be improved, the determination accuracy of the bending radius of the cable can be improved, manpower resources required in the determination process can be reduced, and the manpower resource cost is reduced.

Description

Technical Field

[0001] This application relates to the field of power electronics technology, and particularly to a method, device, and computer device for determining the bending radius of a cable. Background Art

[0002] With the development of power electronics technology, power cables, as an important carrier for power transmission, are widely used in power systems. To ensure the safe and stable operation of the power system, it is particularly important to determine the bending radius of power cables.

[0003] In the related art, the bending radius of power cables is mainly determined by combining manual measurement methods.

[0004] However, in the related art, there is a problem of low efficiency in determining the bending radius of power cables. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide a method, device, and computer device for determining the bending radius of a cable that can improve the efficiency of determining the bending radius of a power cable.

[0006] In a first aspect, this application provides a method for determining the bending radius of a cable, including:

[0007] Based on the original cable image of the cable to be measured, obtain multiple cable sub-images in the original cable image; different cable sub-images include different cable segments in the cable to be measured;

[0008] Perform centerline fitting on the cable segments in each cable sub-image to obtain the position information of the effective center points in each cable segment;

[0009] Determine the bending radius of each cable segment according to the position information of the effective center points in each cable segment.

[0010] In one embodiment, based on the original cable image of the cable to be measured, obtaining multiple cable sub-images in the original cable image includes:

[0011] Perform preprocessing on the original cable image to obtain a preprocessed image; the preprocessing includes at least one of denoising processing, enhancement processing, grayscale processing, color space conversion processing, and normalization processing;

[0012] Perform feature extraction on the preprocessed image to obtain the key feature information of the cable to be measured;

[0013] Obtain each cable sub-image according to the key feature information and the preprocessed image.

[0014] In one embodiment, performing feature extraction on the preprocessed image to obtain the key feature information of the cable to be measured includes:

[0015] Based on the local attention mechanism, perform local feature extraction on the preprocessed image to obtain the local feature information of the cable to be measured; and, perform global feature extraction on the preprocessed image to obtain the global feature information of the cable to be measured;

[0016] Perform fusion processing on the local feature information and the global feature information to obtain the key feature information.

[0017] In one embodiment, according to the key feature information and the preprocessed image, obtain each cable sub-image, including:

[0018] According to the key feature information, perform segmentation processing on the preprocessed image to obtain each cable sub-image.

[0019] In one embodiment, according to the key feature information and the preprocessed image, obtain each cable sub-image, including:

[0020] Perform edge detection processing on the cable to be measured in the preprocessed image to obtain the cable region image in the preprocessed image;

[0021] According to the key feature information, perform segmentation processing on the cable region image to obtain each cable sub-image.

[0022] In one embodiment, perform centerline fitting on the cable segments in each cable sub-image to obtain the position information of the effective center points in each cable segment, including:

[0023] Perform centerline fitting on the cable segments in each cable sub-image to obtain the position information of the original center points in each cable segment;

[0024] Perform anomaly detection on the position information of the original center points in each cable segment to determine the position information of the effective center points in each cable segment.

[0025] In one embodiment, the above method further includes:

[0026] Obtain the three-dimensional cable model of the cable to be measured;

[0027] Based on the three-dimensional cable model, perform correction processing on the bending radius of each cable segment in the cable to be measured to obtain the corrected bending radius of each cable segment.

[0028] In one embodiment, the above method further includes:

[0029] Detect whether the corrected bending radius of each cable segment is within the standard bending radius range;

[0030] In the case that at least one of the corrected bending radii of each cable segment is not within the standard bending radius range, a warning message indicating that the cable under test does not meet the cable design standard is output.

[0031] In a second aspect, the present application also provides a device for determining the bending radius of a cable, including:

[0032] An image acquisition module, configured to obtain a plurality of cable sub-images in the original cable image based on the original cable image of the cable under test; different cable sub-images include different cable segments in the cable under test;

[0033] A center line fitting module, configured to perform center line fitting on the cable segments in each cable sub-image to obtain the position information of the effective center points in each cable segment;

[0034] A determination module, configured to determine the bending radius of each cable segment according to the position information of the effective center points in each cable segment.

[0035] In a third aspect, the present application also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0036] An image acquisition module, configured to obtain a plurality of cable sub-images in the original cable image based on the original cable image of the cable under test; different cable sub-images include different cable segments in the cable under test;

[0037] A center line fitting module, configured to perform center line fitting on the cable segments in each cable sub-image to obtain the position information of the effective center points in each cable segment;

[0038] A determination module, configured to determine the bending radius of each cable segment according to the position information of the effective center points in each cable segment.

[0039] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0040] An image acquisition module, configured to obtain a plurality of cable sub-images in the original cable image based on the original cable image of the cable under test; different cable sub-images include different cable segments in the cable under test;

[0041] A center line fitting module, configured to perform center line fitting on the cable segments in each cable sub-image to obtain the position information of the effective center points in each cable segment;

[0042] A determination module, configured to determine the bending radius of each cable segment according to the position information of the effective center points in each cable segment.

[0043] In a fifth aspect, the present application also provides a computer program product, including a computer program, which when executed by a processor, implements the following steps:

[0044] An image acquisition module, configured to obtain a plurality of cable sub-images in the original cable image based on the original cable image of the cable to be measured; different cable sub-images include different cable segments in the cable to be measured;

[0045] A center line fitting module, configured to perform center line fitting on the cable segments in each cable sub-image to obtain the position information of the effective center points in each cable segment;

[0046] A determination module, configured to determine the bending radius of each cable segment according to the position information of the effective center points in each cable segment.

[0047] The above cable bending radius determination method, device and computer device include: obtaining a plurality of cable sub-images in the original cable image based on the original cable image of the cable to be measured, performing center line fitting on the cable segments in each cable sub-image to obtain the position information of the effective center points in each cable segment, and determining the bending radius of each cable segment according to the position information of the effective center points in each cable segment, where different cable sub-images include different cable segments in the cable to be measured. The above method can be carried out without manual participation, which can not only improve the determination efficiency of the cable bending radius, but also improve the accuracy of the cable bending radius determination, and can also reduce the human resources required in the determination process and lower the human resource cost; at the same time, the above method does not need to be implemented based on an online model, so it will not be affected by the network environment during the cable bending radius determination process and has no limitations on the usage scenarios, which can not only reduce the requirements for computing resources during the processing process and lower the cable bending radius determination cost, but also improve the wide applicability of the cable bending radius determination method. Description of the Drawings

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required to be used in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0049] Figure 1 It is an application environment diagram of the cable bending radius determination method in an embodiment;

[0050] Figure 2 It is a flowchart of the cable bending radius determination method in an embodiment;

[0051] Figure 3Schematic flowchart of a method for determining the bending radius of a cable in another embodiment;

[0052] Figure 4 Schematic flowchart of a method for determining the bending radius of a cable in another embodiment;

[0053] Figure 5 Schematic flowchart of a method for determining the bending radius of a cable in another embodiment;

[0054] Figure 6 Schematic flowchart of a method for determining the bending radius of a cable in another embodiment;

[0055] Figure 7 Schematic flowchart of a method for determining the bending radius of a cable in another embodiment;

[0056] Figure 8 Schematic flowchart of a method for determining the bending radius of a cable in another embodiment;

[0057] Figure 9 Block diagram of the structure of a device for determining the bending radius of a cable in an embodiment;

[0058] Figure 10 Internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0059] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] The method for determining the bending radius of a cable provided by the embodiments of the present application can be applied to, for example Figure 1In the application environment shown, the cable bending radius determination system includes a computer device and an image acquisition device. Among them, the image acquisition device communicates with the computer device through a network, and this communication method can be Wi-Fi, mobile network, Bluetooth connection, etc. Among them, the computer device can be, but is not limited to, various personal computers, laptops, smartphones, tablets, servers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc.; the portable wearable devices can be smart watches, smart bracelets, etc.; the above-mentioned server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services; the above-mentioned image acquisition device can be a camera, a camera, an infrared sensor, and can also be an electronic device with an image acquisition function such as a mobile phone, an ipad, a smart bracelet, a smart watch, etc.; the embodiments of the present application do not limit the specific forms of the computer device and the image acquisition device.

[0061] In an exemplary embodiment, as Figure 2 shown, a method for determining the cable bending radius is provided. Taking the computer device in Figure 1 as an example for illustration. The method includes the following steps:

[0062] S100. Based on the original cable image of the cable to be measured, obtain multiple cable sub-images in the original cable image. Among them, different cable sub-images include different cable segments in the cable to be measured.

[0063] Among them, the above-mentioned original cable image may include the cable to be measured and the background information around the location where the cable to be measured is located. In the embodiments of the present application, neither the length nor the shape of the cable to be measured is limited.

[0064] It should be noted here that the bending radii of different cable segments in the cable to be measured may be equal or unequal. In the embodiments of the present application, the case where the bending radii of different cable segments in the cable to be measured are unequal is taken as an example for illustration. Specifically, the bending radii of different cable segments in the cable to be measured can be determined respectively to improve the accuracy of the cable bending radius determination result.

[0065] In practical applications, the computer device can obtain the original cable image of the cable to be measured sent by the image acquisition device, and then use an image segmentation algorithm to perform segmentation processing on the original cable image to divide the original cable image into multiple cable sub-images. Optionally, the above-mentioned image segmentation algorithm can be a threshold-based segmentation algorithm, an edge-based segmentation algorithm, a region-based segmentation algorithm, a clustering analysis-based segmentation algorithm, etc., and the embodiments of the present application do not limit this.

[0066] It should be noted here that when the image acquisition device acquires the original cable image of the cable to be tested, the cable to be tested and the image acquisition device are not in different positions on the same level, and there is a certain angle between the horizontal plane where the cable to be tested is located and the image acquisition device, so that the original cable image of the cable to be tested acquired by the image acquisition device includes the bending radius information of the cable to be tested.

[0067] In addition, the computer device can use a feature extraction algorithm to extract features from the original cable image, and then divide the original cable image into multiple cable sub-images according to the acquired feature extraction information. Optionally, the feature extraction algorithm can be a scale-invariant feature transformation algorithm, an accelerated robust feature algorithm, a local binary pattern algorithm, a corner detection algorithm, etc., which is not limited in the embodiments of the present application.

[0068] S200: Perform centerline fitting on the cable segments in each cable sub-image to obtain position information of the effective center point in each cable segment.

[0069] Specifically, for any cable sub-image, the computer device can use a fitting method to perform centerline fitting on the cable segment in the cable sub-image to obtain the position information of the effective center point in the cable segment. Optionally, the effective center point in any cable segment can be a plurality of spaced center points. Optionally, the above fitting method can be but is not limited to the least squares method, the exponential fitting method, the logarithmic fitting method. In the embodiment of the present application, the above fitting method can be a B-spline curve fitting method, a polynomial fitting method, etc.

[0070] In addition, the computer device can pre-train a centerline fitting model, and then input the cable sub-image into the centerline fitting model, and the centerline fitting model outputs the position information of the effective center point in the cable segment in the cable sub-image. Optionally, the centerline fitting model can be at least one of a convolutional neural network model, a fully connected neural network model, a long short-term memory neural network model, a residual neural network model, etc.

[0071] S300: Determine the bending radius of each cable segment according to the position information of the effective center point in each cable segment.

[0072] Among them, the computer device can pre-train an algorithm model, and then for any cable segment, the position information of the effective center point in the cable segment is input into the algorithm model, and the algorithm model outputs the bending radius of the cable segment.

[0073] In addition, the computer device can substitute the position information of the effective center point in the cable segment into the standard equation of the circle, and then use the radius obtained by solving the equation group based on multiple equations as the bending radius of the cable segment.

[0074] Further, in the embodiments of the present application, the reciprocal of the bending radius of each cable segment in the cable under test can be obtained to get the curvature of each cable segment in the cable under test.

[0075] The technical solution in the embodiments of the present application is based on the original cable image of the cable under test, obtains a plurality of cable sub-images in the original cable image, fits the center line of the cable segments in each cable sub-image, obtains the position information of the effective center points in each cable segment, and determines the bending radius of each cable segment according to the position information of the effective center points in each cable segment, where different cable sub-images include different cable segments in the cable under test; the above method does not require manual participation, so it can not only improve the determination efficiency of the cable bending radius, but also improve the accuracy of the cable bending radius determination, and can also reduce the human resources required in the determination process and lower the human resource cost; at the same time, the above method does not need to be implemented based on an online model, so it will not be affected by the network environment during the cable bending radius determination process and has no limitations on the usage scenario, thus it can not only reduce the requirements for computing resources during the processing process and lower the cable bending radius determination cost, but also improve the wide applicability of the cable bending radius determination method.

[0076] The process of obtaining a plurality of cable sub-images in the original cable image based on the original cable image of the cable under test will be described below. In one embodiment, as Figure 3 shown, the steps in the above S100 may include:

[0077] S110. Preprocess the original cable image to obtain a preprocessed image. Among them, the preprocessing includes at least one of denoising processing, enhancement processing, grayscale processing, color space conversion processing, and normalization processing.

[0078] In practical applications, the computer device can pre-train a preprocessing model in advance, and then input the original cable image into the preprocessing model, and the preprocessing model outputs the preprocessed image corresponding to the original cable image.

[0079] In the embodiments of the present application, the computer device can use at least one algorithm of denoising processing, enhancement processing, grayscale processing, color space conversion processing, and normalization processing to preprocess the original cable image to obtain the preprocessed image corresponding to the original cable image, so as to provide high-quality basic information for the subsequent accuracy of obtaining the cable bending radius.

[0080] S120. Extract features from the preprocessed image to obtain the key feature information of the cable under test.

[0081] In practical applications, a computer device can use a feature extraction algorithm to extract features from the preprocessed image and directly obtain the key feature information of the cable to be measured. Among them, the key feature information of the cable to be measured can include the starting points and terminals of different cable segments in the cable to be measured and the diameters of each cable segment, etc.

[0082] In addition, the computer device can use a feature extraction algorithm to extract features from the preprocessed image to obtain the original feature information of the cable to be measured, and then perform screening processing on the original feature information to obtain the key feature information of the cable to be measured.

[0083] S130. According to the key feature information and the preprocessed image, obtain each cable sub-image.

[0084] Among them, the computer device can pre-train an algorithm model in advance, and then input both the key feature information of the cable to be measured and the preprocessed image into the algorithm model, and the algorithm model outputs multiple cable sub-images in the original cable image.

[0085] Alternatively, the computer device can perform operations such as analysis processing and segmentation processing on the preprocessed image according to the key feature information of the cable to be measured to obtain multiple cable sub-images in the original cable image.

[0086] In one embodiment, the step of obtaining each cable sub-image according to the key feature information and the preprocessed image in the above S130 may include: performing segmentation processing on the preprocessed image according to the key feature information to obtain each cable sub-image.

[0087] Specifically, the computer device can perform segmentation processing on the preprocessed image based on a deep learning segmentation model according to the key feature information of the cable to be measured, that is, input both the key feature information of the cable to be measured and the preprocessed image into the deep learning segmentation model to output multiple cable sub-images in the original cable image.

[0088] In the embodiments of the present application, the above deep learning segmentation model can be implemented by at least one of a U-Net convolutional neural network model and a Mask R-CNN neural network model, etc.

[0089] The technical solution in the embodiments of the present application preprocesses the original cable image to obtain a preprocessed image, extracts features from the preprocessed image to obtain the key feature information of the cable to be measured, and obtains each cable sub-image according to the key feature information and the preprocessed image; the above method can first preprocess the original cable image to make preparations for subsequent obtaining of a cable bending radius with higher accuracy, and can also obtain multiple cable sub-images in the original cable image to make preparations for subsequent obtaining of the bending radii of different cable segments in the cable to be measured, so as to greatly improve the accuracy of the finally obtained bending radius of the cable to be measured.

[0090] The process of extracting key feature information of the cable to be measured from the preprocessed image described above will be described below. In one embodiment, as Figure 4 shown, the steps in S120 above can be implemented in the following manner:

[0091] S121. Based on the local attention mechanism, perform local feature extraction on the preprocessed image to obtain local feature information of the cable to be measured; and perform global feature extraction on the preprocessed image to obtain global feature information of the cable to be measured.

[0092] In the embodiment of the present application, the computer device can use a feature extraction model constructed based on the local attention mechanism to perform local feature extraction on the preprocessed image to obtain local feature information of the cable to be measured.

[0093] At the same time, the computer device can use a global feature extraction algorithm to perform global feature extraction on the preprocessed image to obtain global feature information of the cable to be measured. Optionally, the above global feature extraction algorithm can be implemented by at least one of a color feature extraction algorithm, a texture feature extraction algorithm, a shape feature extraction algorithm, etc. In the embodiment of the present application, the above feature extraction model can be a neural network model constructed by a convolutional neural network model and a local attention mechanism Transformer.

[0094] S122. Perform fusion processing on the local feature information and the global feature information to obtain key feature information.

[0095] Specifically, the computer device can use a feature fusion method to perform fusion processing on the local feature information and the global feature information to obtain key feature information of the cable to be measured.

[0096] Optionally, the above feature fusion algorithm can be at least one of a principal component analysis method, a kernel principal component analysis method, a linear discriminant analysis method, an independent component analysis method, etc.

[0097] In the embodiment of the present application, the computer device can use a multi-scale feature fusion method or a feature fusion network model constructed based on the attention mechanism to perform fusion processing on the local feature information and the global feature information to obtain key feature information of the cable to be measured.

[0098] In the technical solution of the embodiment of the present application, based on the local attention mechanism, local feature extraction is performed on the preprocessed image to obtain the local feature information of the cable to be measured, and global feature extraction is performed on the preprocessed image to obtain the global feature information of the cable to be measured, and the local feature information and the global feature information are fused to obtain the key feature information; the above method can respectively obtain the local feature information and the global feature information of the cable to be measured, and then fuse the local feature information and the global feature information of the cable to be measured, so that the finally obtained key feature information of the cable to be measured is more comprehensive and accurate, so as to prepare for obtaining a higher-precision cable bending radius subsequently.

[0099] The following describes another implementation manner of the process of obtaining each cable sub-image according to the key feature information and the preprocessed image. In one embodiment, as Figure 5 shown, the steps in S130 above can be implemented in the following manner:

[0100] S131. Perform edge detection processing on the cable to be measured in the preprocessed image to obtain the cable region image in the preprocessed image.

[0101] In practical applications, the computer device can use a pre-trained edge detection network model, input the preprocessed image into the edge detection network model, and the edge detection network model performs edge detection processing on the cable to be measured in the preprocessed image and outputs the cable region image in the preprocessed image.

[0102] In addition, the computer device can use an edge detection algorithm to perform edge detection processing on the cable to be measured in the preprocessed image to obtain the cable region image in the preprocessed image.

[0103] In the embodiment of the present application, the above edge detection algorithm can be a multi-level edge detection algorithm (an algorithm based on the Canny operator), an edge detection algorithm based on the first derivative (an algorithm based on the Sobel operator), an edge detection algorithm based on the second derivative (an algorithm based on the Laplacian operator), a gradient-based edge detection algorithm, a deep learning-based edge detection algorithm, etc. At the same time, the cable region image in the above preprocessed image can be understood as the region image after removing the background region other than the cable to be measured in the preprocessed image.

[0104] S132. Perform segmentation processing on the cable region image according to the key feature information to obtain each cable sub-image.

[0105] Specifically, the computer device can perform segmentation processing on the cable area image based on the deep learning segmentation model, that is, input the key feature information of the cable to be measured and the cable area image into the deep learning segmentation model to output multiple cable sub-images in the cable area image.

[0106] In the technical solution of this application embodiment, edge detection is performed on the cable to be measured in the preprocessed image to obtain the cable area image in the preprocessed image, and segmentation processing is performed on the cable area image according to the key feature information to obtain each cable sub-image; the above method can first obtain the cable area image from the preprocessed image, which can reduce the data volume of each obtained cable sub-image, further reduce the calculation amount in the subsequent processing process, and speed up the subsequent processing speed.

[0107] The process of obtaining the position information of the effective center points in each cable segment by fitting the center line of the cable segments in each cable sub-image will be described below. In one embodiment, as Figure 6 shown, the steps in S200 above may include:

[0108] S210. Fit the center line of the cable segments in each cable sub-image to obtain the position information of the original center points in each cable segment.

[0109] In practical applications, for any cable sub-image, the computer device can use the fitting method to fit the center line of the cable segment in the cable sub-image to obtain the position information of the original center point in the cable segment. Among them, the original center point in any cable segment may include multiple points.

[0110] S220. Perform anomaly detection on the position information of the original center points in each cable segment to determine the position information of the effective center points in each cable segment.

[0111] Among them, for any cable segment, the computer device can use the anomaly point detection method to perform anomaly detection on the position information of the original center point in the cable segment to determine the position information of the effective center point in the cable segment. Optionally, the above anomaly point detection method can be a discrete value detection method, a distance-based detection method, a clustering-based detection method, etc., and this application embodiment does not make any limitations in this regard.

[0112] In addition, the computer device can perform anomaly detection on the position information of the original center points in the cable segment according to the preset anomaly point elimination method, so as to eliminate the position information of the anomaly points from the position information of the original center points in the cable segment to obtain the position information of the effective center points in the cable segment.

[0113] In an embodiment of the present application, the computer device may use the Random Sample Consensus (RANSAC) algorithm to perform anomaly detection on the position information of the original center points in the cable segments, and obtain the position information of the valid center points in the cable segments.

[0114] In the technical solution of the embodiment of the present application, the center lines of the cable segments in each cable sub-image are fitted to obtain the position information of the original center points in each cable segment, and anomaly detection is performed on the position information of the original center points in each cable segment to determine the position information of the valid center points in each cable segment; the above method can fit the center lines of the cable segments in each cable sub-image and perform anomaly detection, so that the quality of the position information of the valid center points in each cable segment of the cable to be measured finally obtained is higher, providing accurate basic information for obtaining a higher-precision cable bending radius subsequently.

[0115] In some scenarios, there may be some calculation errors, resulting in slightly lower accuracy of the bending radii of the cable segments in the cable to be measured obtained through the above steps. Based on this, the bending radii of the cable segments in the cable to be measured obtained above can be corrected to obtain more accurate bending radii of the cable segments in the cable to be measured. The process of correcting the bending radii of the cable segments in the cable to be measured is described below. In one embodiment, after performing the steps in S300 above, as Figure 7 shown, the above method may further include the following steps:

[0116] S400. Obtain the three-dimensional cable model of the cable to be measured.

[0117] In practical applications, the computer device may use three-dimensional modeling methods to perform three-dimensional modeling on the cable to be measured to obtain the three-dimensional cable model of the cable to be measured. Optionally, the above three-dimensional modeling methods may be surface modeling methods, parametric modeling methods, volume modeling methods, point cloud modeling methods, etc., which are not limited in the embodiment of the present application.

[0118] S500. Based on the three-dimensional cable model, perform correction processing on the bending radii of the cable segments in the cable to be measured to obtain the corrected bending radii of the cable segments.

[0119] Furthermore, the computer device may obtain the true bending radii of the cable segments in the cable to be measured based on the three-dimensional cable model of the cable to be measured, and then use the error correction method to perform correction processing on the bending radii of the cable segments in the cable to be measured according to the true bending radii of the cable segments in the cable to be measured to obtain the corrected bending radii of the cable segments.

[0120] At the same time, the computer device may output the corrected bending radii of the cable segments in the cable to be measured in the form of pictures, numbers, charts, etc.

[0121] In the technical solution of the embodiment of the present application, a three-dimensional cable model of the cable to be measured is obtained, and based on the three-dimensional cable model, the bending radius of each cable segment in the cable to be measured is corrected to obtain the corrected bending radius of each cable segment. The above method can correct the bending radius of each cable segment in the cable to be measured to obtain a more accurate bending radius of each cable segment in the cable to be measured, so that the bending radius of each cable segment in the finally obtained cable to be measured is closer to the actual data.

[0122] In some scenarios, the above method is executed during the quality inspection of power cables before they leave the factory, so as to further determine whether the quality inspection result of the power cable can pass according to the corrected bending radius of each cable segment in the obtained power cable. The following is the process of performing operations when it is determined that the quality inspection fails according to the corrected bending radius of each cable segment in the power cable. In one embodiment, after performing the steps in S500 above, as Figure 8 shown, the above method may further include the following steps:

[0123] S510. Detect whether the corrected bending radius of each cable segment is within the standard bending radius range.

[0124] Among them, the above standard bending radius range may be a cable bending radius range set in advance according to different types of power cables.

[0125] In practical applications, the computer device can detect whether the corrected bending radius of each cable segment in the cable to be measured is within the standard bending radius range.

[0126] S520. When at least one of the corrected bending radii of each cable segment is not within the standard bending radius range, output a warning message that the cable to be measured does not meet the cable design standard.

[0127] Specifically, when the computer device determines that at least one of the cable segments to be measured is not within the standard bending radius range, it indicates that the cable to be measured does not meet the cable design standard. At this time, a warning message of the cable to be measured can be output to remind the user that the quality inspection of the cable to be measured fails and it cannot be used after leaving the factory.

[0128] In the technical solution of the embodiment of the present application, it is detected whether the corrected bending radius of each cable segment is within the standard bending radius range, and when at least one of the corrected bending radii of each cable segment is not within the standard bending radius range, a warning message that the cable to be measured does not meet the cable design standard is output. The above method can determine whether the power cable meets the cable design standard according to the corrected bending radius of each cable segment in the obtained power cable, so as to ensure that the quality of the finally produced power cable meets the standard.

[0129] In one embodiment, the embodiment of the present application further provides a method for determining the bending radius of a cable, which is applied to a computer device. The method includes the following processes:

[0130] (1) Preprocess the original cable image to obtain a preprocessed image; the preprocessing includes at least one of denoising processing, enhancement processing, grayscale processing, color space conversion processing, and normalization processing;

[0131] (2) Based on the local attention mechanism, extract local features from the preprocessed image to obtain the local feature information of the cable to be measured; and, extract global features from the preprocessed image to obtain the global feature information of the cable to be measured;

[0132] (3) Fuse the local feature information and the global feature information to obtain key feature information;

[0133] (4) According to the key feature information and the preprocessed image, obtain multiple cable sub-images in the original cable image; different cable sub-images include different cable segments in the cable to be measured;

[0134] Among them, the above step (4) can be implemented in two ways:

[0135] The first way includes:

[0136] (41) According to the key feature information, segment the preprocessed image to obtain each cable sub-image;

[0137] The second way includes:

[0138] (42) Perform edge detection on the cable to be measured in the preprocessed image to obtain the cable region image in the preprocessed image;

[0139] (43) According to the key feature information, segment the cable region image to obtain each cable sub-image;

[0140] (5) Fit the center line of the cable segments in each cable sub-image to obtain the position information of the original center points in each cable segment;

[0141] (6) Perform anomaly detection on the position information of the original center points in each cable segment to determine the position information of the effective center points in each cable segment;

[0142] (7) According to the position information of the effective center points in each cable segment, determine the bending radius of each cable segment;

[0143] (8) Obtain the three-dimensional cable model of the cable to be measured;

[0144] (9) Based on the three-dimensional cable model, perform correction processing on the bending radii of each cable segment in the cable to be measured to obtain the corrected bending radii of each cable segment;

[0145] (10) Detect whether the corrected bending radii of each cable segment are all within the standard bending radius range;

[0146] (11) In the case where at least one of the corrected bending radii of each cable segment is not within the standard bending radius range, output a warning message indicating that the cable to be measured does not meet the cable design standard.

[0147] The execution processes of the above (1) to (11) can specifically refer to the descriptions of the above embodiments. Their implementation principles and technical effects are similar, and will not be elaborated here.

[0148] It should be understood that although the steps in the flowcharts involved in the above embodiments are sequentially shown according to the arrows, these steps do not necessarily need to be executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps does not have a strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily need to be executed at the same time, but can be executed at different times. The execution order of these steps or stages does not necessarily need to be sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0149] Based on the same inventive concept, an embodiment of the present application further provides a cable bending radius determination device for implementing the cable bending radius determination method involved above. The implementation solution provided by this device for solving problems is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more embodiments of the cable bending radius determination device provided below can refer to the limitations on the cable bending radius determination method in the above text, and will not be elaborated here.

[0150] In an exemplary embodiment, as Figure 9 shown, a cable bending radius determination device is provided, including: an image acquisition module 11, a center line fitting module 12, and a determination module 13, where:

[0151] The image acquisition module 11 is used to obtain a plurality of cable sub-images in the original cable image based on the original cable image of the cable to be measured; different cable sub-images include different cable segments in the cable to be measured;

[0152] The center line fitting module 12 is used to perform center line fitting on the cable segments in each cable sub-image to obtain the position information of the effective center points in each cable segment;

[0153] A determination module 13, configured to determine the bending radius of each cable segment according to the position information of the effective center points in each cable segment.

[0154] The cable bending radius determination device provided by the embodiment of the present application can be used to execute the technical solutions in the above-mentioned cable bending radius determination method embodiments of the present application. The implementation principles and technical effects are similar and will not be elaborated here.

[0155] In one embodiment, the image acquisition module 11 includes: a preprocessing unit, a feature extraction unit, and an acquisition unit, where:

[0156] The preprocessing unit is configured to preprocess the original cable image to obtain a preprocessed image; the preprocessing includes at least one of denoising processing, enhancement processing, grayscale processing, color space conversion processing, and normalization processing;

[0157] The feature extraction unit is configured to extract features from the preprocessed image to obtain the key feature information of the cable to be measured;

[0158] The acquisition unit is configured to obtain each cable sub-image according to the key feature information and the preprocessed image.

[0159] The cable bending radius determination device provided by the embodiment of the present application can be used to execute the technical solutions in the above-mentioned cable bending radius determination method embodiments of the present application. The implementation principles and technical effects are similar and will not be elaborated here.

[0160] In one embodiment, the feature extraction unit is specifically configured to:

[0161] Based on a local attention mechanism, perform local feature extraction on the preprocessed image to obtain the local feature information of the cable to be measured; and perform global feature extraction on the preprocessed image to obtain the global feature information of the cable to be measured;

[0162] Perform fusion processing on the local feature information and the global feature information to obtain the key feature information.

[0163] The cable bending radius determination device provided by the embodiment of the present application can be used to execute the technical solutions in the above-mentioned cable bending radius determination method embodiments of the present application. The implementation principles and technical effects are similar and will not be elaborated here.

[0164] In one embodiment, the acquisition unit includes: an acquisition subunit, where:

[0165] The acquisition subunit is configured to perform segmentation processing on the preprocessed image according to the key feature information to obtain each cable sub-image.

[0166] The cable bending radius determination device provided by the embodiments of the present application can be used to implement the technical solutions in the above-mentioned cable bending radius determination method embodiments of the present application. The implementation principles and technical effects are similar and will not be elaborated here.

[0167] In one embodiment, the acquisition unit includes: an edge detection subunit and a segmentation processing subunit, where:

[0168] The edge detection subunit is configured to perform edge detection processing on the cable to be measured in the preprocessed image to obtain the cable region image in the preprocessed image;

[0169] The segmentation processing subunit is configured to perform segmentation processing on the cable region image according to the key feature information to obtain each cable sub-image.

[0170] The cable bending radius determination device provided by the embodiments of the present application can be used to implement the technical solutions in the above-mentioned cable bending radius determination method embodiments of the present application. The implementation principles and technical effects are similar and will not be elaborated here.

[0171] In one embodiment, the centerline fitting module 12 is specifically configured to:

[0172] Perform centerline fitting on the cable segments in each cable sub-image to obtain the position information of the original center points in each cable segment;

[0173] Perform anomaly detection on the position information of the original center points in each cable segment to determine the position information of the valid center points in each cable segment.

[0174] The cable bending radius determination device provided by the embodiments of the present application can be used to implement the technical solutions in the above-mentioned cable bending radius determination method embodiments of the present application. The implementation principles and technical effects are similar and will not be elaborated here.

[0175] In one embodiment, the cable bending radius determination device further includes: a model acquisition module and a calibration processing module, where:

[0176] The model acquisition module is configured to acquire the three-dimensional cable model of the cable to be measured;

[0177] The calibration processing module is configured to perform calibration processing on the bending radius of each cable segment in the cable to be measured based on the three-dimensional cable model to obtain the calibrated bending radius of each cable segment.

[0178] The cable bending radius determination device provided by the embodiments of the present application can be used to implement the technical solutions in the above-mentioned cable bending radius determination method embodiments of the present application. The implementation principles and technical effects are similar and will not be elaborated here.

[0179] In one embodiment, the cable bending radius determination device further includes a detection module and an information output module, where:

[0180] The detection module is configured to detect whether the corrected bending radii of all cable segments are within the standard bending radius range;

[0181] The information output module is configured to output a warning message that the cable to be measured does not meet the cable design standard when at least one of the corrected bending radii of all cable segments is not within the standard bending radius range.

[0182] The cable bending radius determination device provided by the embodiments of the present application can be used to implement the technical solutions in the above-mentioned embodiments of the cable bending radius determination method of the present application. The implementation principle and technical effects are similar and will not be elaborated here.

[0183] For the specific limitations of the cable bending radius determination device, reference can be made to the limitations of the cable bending radius determination method in the above text, which will not be elaborated here. Each module in the above cable bending radius determination device can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0184] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 10 shown. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide processing capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the original cable images. The network interface of the computer device is used to communicate with an external endpoint through a network connection. The computer program, when executed by the processor, implements a cable bending radius determination method.

[0185] Those skilled in the art can understand that Figure 10 the structure shown in

[0186] In one embodiment, a computer device is further provided, which includes a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the technical solutions in the embodiments of the above-mentioned cable bending radius determination method of the present application are implemented, and the implementation principles and technical effects are similar, so they will not be described herein again.

[0187] In one embodiment, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the technical solutions of the above-mentioned cable bending radius determination method of the present application are implemented, and the implementation principles and technical effects are similar, so they will not be described herein again.

[0188] In one embodiment, a computer program product is further provided, which includes a computer program. When the computer program is executed by a processor, the technical solutions of the above-mentioned cable bending radius determination method of the present application are implemented, and the implementation principles and technical effects are similar, so they will not be described herein again.

[0189] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided by the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0190] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0191] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A method for determining the bending radius of a cable, characterized in that, The method includes: Based on the original cable image of the cable to be measured, obtaining a plurality of cable sub-images in the original cable image; different cable sub-images include different cable segments in the cable to be measured; Performing centerline fitting on the cable segments in each of the cable sub-images to obtain the position information of the effective center points in each cable segment; Determining the bending radius of each cable segment according to the position information of the effective center points in each cable segment.

2. The method according to claim 1, wherein The obtaining a plurality of cable sub-images in the original cable image based on the original cable image of the cable to be measured includes: Preprocessing the original cable image to obtain a preprocessed image; the preprocessing includes at least one of denoising processing, enhancement processing, grayscale processing, color space conversion processing, and normalization processing; Performing feature extraction on the preprocessed image to obtain the key feature information of the cable to be measured; Obtaining each cable sub-image according to the key feature information and the preprocessed image.

3. The method according to claim 2, wherein The performing feature extraction on the preprocessed image to obtain the key feature information of the cable to be measured includes: Based on a local attention mechanism, performing local feature extraction on the preprocessed image to obtain the local feature information of the cable to be measured; and, performing global feature extraction on the preprocessed image to obtain the global feature information of the cable to be measured; Performing fusion processing on the local feature information and the global feature information to obtain the key feature information.

4. The method according to claim 2, wherein The obtaining each cable sub-image according to the key feature information and the preprocessed image includes: Performing segmentation processing on the preprocessed image according to the key feature information to obtain each cable sub-image.

5. The method according to claim 2, wherein The obtaining each cable sub-image according to the key feature information and the preprocessed image includes: Performing edge detection processing on the cable to be measured in the preprocessed image to obtain a cable region image in the preprocessed image; Performing segmentation processing on the cable region image according to the key feature information to obtain each cable sub-image.

6. The method according to any one of claims 1-5, characterized in that, The performing centerline fitting on the cable segments in each of the cable sub-images to obtain the position information of the effective center points in each cable segment includes: Performing centerline fitting on the cable segments in each of the cable sub-images to obtain the position information of the original center points in each cable segment; Performing anomaly detection on the position information of the original center points in each cable segment to determine the position information of the effective center points in each cable segment.

7. The method according to any one of claims 1-5, characterized in that, The method further includes: Obtaining a three-dimensional cable model of the cable to be measured; Based on the three-dimensional cable model, performing correction processing on the bending radius of each cable segment in the cable to be measured to obtain the corrected bending radius of each cable segment.

8. The method according to claim 7, characterized in that, The method further includes: Detecting whether the corrected bending radius of each cable segment is within the standard bending radius range; In the case where at least one of the corrected bending radii of each cable segment is not within the standard bending radius range, outputting a warning message that the cable to be measured does not meet the cable design standard.

9. A device for determining the bending radius of a cable, characterized in that, The device includes: An image acquisition module, configured to obtain a plurality of cable sub-images in the original cable image based on the original cable image of the cable to be measured; different cable sub-images include different cable segments in the cable to be measured; A center line fitting module, configured to perform center line fitting on the cable segments in each of the cable sub-images to obtain the position information of the effective center points in each cable segment; A determination module, configured to determine the bending radius of each cable segment according to the position information of the effective center points in each cable segment.

10. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images