Steel wire rope diameter measuring method and system based on machine vision, medium and terminal

Abstract

The invention discloses a steel wire rope diameter measurement method and system based on machine vision, a medium and a terminal, and the method comprises the following steps: collecting an image of a steel wire rope through an area-array camera, and carrying out the preprocessing of the collected image; automatically adjusting a threshold value according to image characteristics, performing adaptive binarization processing on the preprocessed image, and extracting an effective area of the steel wire rope; extracting the edge information of the steel wire rope in the image of the effective area by adopting a Canny operator, and detecting the central axis of the steel wire rope in the image by using Hough transformation; the edge information and the central axis position serve as new image feature vectors to be input into a trained support vector machine SVM model, and a decision function is used for calculating a predicted diameter value; according to the method, the threshold value is automatically adjusted according to the image characteristics through self-adaptive binaryzation, the accuracy of edge detection is improved, the measurement of the diameter of the steel wire rope is optimized through the SVM algorithm, and the precision, efficiency and repeatability of measurement and the generalization ability of the model are improved.

Description

Technical Field

[0001] The present invention relates to the field of elevator safety technology, and more specifically to a wire rope diameter measurement method, system, medium and terminal based on machine vision. Background Art

[0002] Due to the wide application of wire ropes and the importance of safety in use, on-site inspection of wire ropes is very necessary. During use, traction wire ropes will have defects such as internal and external wire breakage, wear or rust, and the rope diameter will shrink due to the elongation surface. Wire breakage and outer diameter changes are key parameters for evaluating the degree of damage to the wire rope.

[0003] Traditional measurement methods such as caliper measurement and vernier caliper measurement have the following shortcomings: Insufficient accuracy: Manual measurement is easily affected by the operator's skills and experience, resulting in low accuracy of the measurement results; Low efficiency: Traditional measurement methods require a lot of time and manpower, and are not suitable for large-scale or rapid measurement needs; Poor repeatability: Due to the subjectivity of the measurement process, the measurement results of different operators or the same operator at different times may vary significantly; Inconvenient data recording: Traditional measurement methods make it difficult to achieve automatic recording and analysis of data, which is not conducive to subsequent data analysis and decision support.

[0004] With the development of machine vision technology, measurement methods based on machine vision have gradually become a research hotspot. There are some methods that combine machine vision to measure wire rope diameter, but there are still some shortcomings: for example, they are sensitive to environmental conditions, feature extraction relies on preset rules, and have high requirements on image quality. When facing different types of wire ropes or measurement environments, they may need to readjust parameters or retrain models, and have poor adaptability. During feature extraction and image processing, the computational complexity may be high, affecting the speed and efficiency of measurement. Traditional diameter calculation methods rely on fixed algorithms and are susceptible to noise and edge discontinuities.

[0005] Therefore, how to combine machine vision technology to improve the measurement accuracy and efficiency of wire rope diameter is an urgent problem that technical personnel in this field need to solve. Summary of the invention

[0006] In view of this, the present invention provides a wire rope diameter measurement method, system, medium and terminal based on machine vision to solve some of the technical problems mentioned in the background technology.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] A method for measuring the diameter of a steel wire rope based on machine vision comprises the following steps:

[0009] S1. Use an array camera to collect images of the wire rope and preprocess the collected images;

[0010] S2. According to the image characteristics, the threshold is automatically adjusted, and the pre-processed image is adaptively binarized to extract the effective area of ​​the wire rope;

[0011] S3. Use the Canny operator to extract the edge information of the wire rope in the image of the effective area, and use the Hough transform to detect the central axis of the wire rope in the image;

[0012] S4. Input the edge information and the central axis position as the new image feature vector into the trained support vector machine (SVM) model, and use the decision function to calculate the predicted diameter value.

[0013] Preferably, preprocessing of the captured images includes image standardization, filtering and denoising, and adaptive lighting adjustment; wherein the adaptive lighting adjustment includes lighting detection, lighting compensation, automatic exposure adjustment, contrast enhancement, and dynamic range compression.

[0014] Preferably, in step S2, the specific contents of the adaptive binarization processing include:

[0015] S21. Determine the window size according to the image resolution and the size of the target object;

[0016] S22. For each pixel in the image, calculate the average brightness in the surrounding window by sliding the window;

[0017] S23. Calculate the local threshold of each pixel based on the local average brightness;

[0018] S24. Convert each pixel in the image into a binary image according to the calculated local threshold;

[0019] S25. After binarization, post-processing such as morphological operations and connected domain analysis is performed to further improve image quality.

[0020] Preferably, in step S3, the specific content of using the Canny operator to extract the edge information of the wire rope in the image of the effective area is:

[0021] Apply Gaussian filter to remove noise from the effective area image of the wire rope;

[0022] Calculate the gradient magnitude and direction of the image;

[0023] Apply non-maximum suppression to retain the local maximum gradient;

[0024] A dual threshold detection and edge tracking algorithm is applied to determine the final edge.

[0025] Preferably, in step S3, the specific content of using Hough transform to detect the central axis of the wire rope in the image is:

[0026] Map the points in the image space to the parameter space defined by angle and distance, and create an accumulator matrix; for each edge point in the image, calculate all possible (θ, r) based on the coordinates, and for each (θ, r), add 1 to the corresponding position in the accumulator matrix;

[0027] Set a threshold based on the maximum or average value in the accumulator matrix and detect the line based on the accumulator matrix and (θ, r);

[0028] The straight line representing the central axis of the wire rope is selected from the detected straight lines by analyzing the geometric features of the straight lines, and the selected straight lines are fitted to obtain the central axis of the wire rope.

[0029] Preferably, the training method of the support vector machine SVM model is specifically as follows:

[0030] Take images of the wire rope at different positions and under different lighting conditions, manually annotate the captured images, and measure and record the diameter of the wire rope;

[0031] Preprocess the image and perform adaptive binarization to extract the effective area of ​​the wire rope. Use the Canny operator to extract the edge information of the wire rope in the image of the effective area, and use the Hough transform to detect the central axis of the wire rope in the image.

[0032] The diameter measurement value is used as a label, and the edge information and the image features of the central axis are used as feature vectors to form a training data set and a validation data set;

[0033] Select radial basis function RBF as the kernel function to map the data into a high-dimensional space for linear separability;

[0034] Initialize the SVM model using the training data set, select the penalty parameter and kernel function parameter, find the solution that maximizes the interval, i.e. the support vector, by solving the optimization problem, and calculate the decision function;

[0035] The new image feature vector is input into the trained SVM model, the decision function is used to calculate the predicted wire rope diameter value, the cross-validation method is used to evaluate the performance of the model, the penalty parameters and kernel function parameters are adjusted to optimize the model to obtain the best performance, and the error between the predicted result and the actual value is calculated for model verification.

[0036] Preferably, the decision function is:

[0037]

[0038] Where N is the number of support vectors, y iis the label of the i-th support vector, α i is the corresponding Lagrange multiplier, b is the bias term;

[0039] The predicted wire rope diameter is:

[0040]

[0041] in, is the predicted diameter value, x new is the new image feature vector.

[0042] A wire rope diameter measurement system based on machine vision, based on the wire rope diameter measurement method based on machine vision, comprising: an array camera, a preprocessing module, an effective area extraction module, an edge detection module, a central axis detection module and a trained support vector machine SVM model;

[0043] An area array camera is used to capture images of the wire rope;

[0044] A preprocessing module, used for preprocessing the collected images;

[0045] The effective area extraction module is used to automatically adjust the threshold according to the image characteristics, perform adaptive binarization processing on the pre-processed image, and extract the effective area of ​​the wire rope;

[0046] An edge detection module is used to extract edge information of the wire rope in the image of the effective area using the Canny operator;

[0047] A central axis detection module is used to detect the central axis of the wire rope in the image using Hough transform;

[0048] The trained support vector machine (SVM) model is used to input the edge information and the center axis position as a new image feature vector, and use the decision function to calculate the output predicted wire rope diameter value.

[0049] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements a method for measuring the diameter of a steel wire rope based on machine vision.

[0050] A processing terminal comprises a memory and a processor. The memory stores a computer program that can be run on the processor. When the processor executes the computer program, a wire rope diameter measurement method based on machine vision is implemented.

[0051] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a wire rope diameter measurement method, system, medium and terminal based on machine vision, which automatically adjusts the threshold according to the image characteristics through adaptive binarization to improve the accuracy of edge detection, and optimizes the measurement of wire rope diameter by adopting the SVM algorithm, thereby improving the measurement accuracy, efficiency and repeatability. The SVM model can be used to adapt to different measurement environments and conditions by adjusting parameters to improve the generalization ability of the model. In addition, the center axis and edge information of the wire rope are used as feature vectors instead of the initial image features as SVM input, thereby further improving the accuracy and reliability of model prediction, and providing an efficient and reliable measurement method for elevator manufacturing and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0053] Figure 1 A schematic diagram of a wire rope diameter measurement method based on machine vision provided by the present invention;

[0054] Figure 2 A schematic diagram of the adaptive binarization process provided by the present invention;

[0055] Figure 3 This is a schematic diagram of the support vector machine (SVM) model training method provided by the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] The embodiment of the present invention discloses a method for measuring the diameter of a steel wire rope based on machine vision, comprising the following steps:

[0058] S1. Use an array camera to collect images of the wire rope and preprocess the collected images;

[0059] S2. According to the image characteristics, the threshold is automatically adjusted, and the pre-processed image is adaptively binarized to extract the effective area of ​​the wire rope;

[0060] S3. Use the Canny operator to extract the edge information of the wire rope in the image of the effective area, and use the Hough transform to detect the central axis of the wire rope in the image;

[0061] S4. Input the edge information and the central axis position as the new image feature vector into the trained support vector machine (SVM) model, and use the decision function to calculate the predicted diameter value.

[0062] In order to further implement the above technical solution, the collected images are preprocessed including image standardization, filtering and denoising, and adaptive lighting adjustment; wherein the adaptive lighting adjustment includes lighting detection, lighting compensation, automatic exposure adjustment, contrast enhancement, and dynamic range compression.

[0063] Specific:

[0064] Light detection: Use histogram analysis, local variance calculation and other methods to evaluate the light level of the image; Light compensation: Compensate the image according to the detected light conditions to reduce the impact of uneven lighting, for example, adjust the brightness and contrast of the entire image for global compensation, and compensate the dark and bright areas of the image separately to maintain details;

[0065] Automatic exposure adjustment: Automatically adjust the exposure of the image to adapt to different lighting environments, such as histogram-based adjustment: Automatically adjust the exposure parameters according to the histogram distribution of the image to make the histogram more balanced; area-based adjustment: Identify the highlight and shadow areas in the image and adjust the exposure separately to preserve details;

[0066] Contrast enhancement: Enhance the contrast of the image to make the outline of the wire rope clearer, such as histogram equalization: By adjusting the histogram of the image, the pixel value distribution is more even, thereby enhancing the contrast; adaptive histogram equalization: only perform histogram equalization on specific areas of the image (such as dark areas or bright areas);

[0067] Dynamic range compression: compressing the dynamic range of an image to adapt to different display devices and viewing conditions; for example, gamma correction: adjusting the gamma value of an image to change the response curve of brightness and contrast; HDR technology: using high dynamic range imaging technology to merge images of different exposures to obtain a wider dynamic range;

[0068] Adaptive illumination adjustment can effectively improve the illumination conditions of wire rope images, such as traction elevator wire ropes in elevator shafts, and improve the accuracy and reliability of measurements.

[0069] In order to further implement the above technical solution, in step S2, the specific contents of the adaptive binarization processing include:

[0070] S21. Determine the window size according to the image resolution and the size of the target object;

[0071] S22. For each pixel in the image, calculate the average brightness in the surrounding window by sliding the window;

[0072] S23. Calculate the local threshold of each pixel based on the local average brightness;

[0073] S24. Convert each pixel in the image into a binary image according to the calculated local threshold;

[0074] S25. After binarization, post-processing such as morphological operations and connected domain analysis is performed to further improve image quality.

[0075] In this embodiment, in step S21, selecting a suitable window size is the key to adaptive binarization. If the window size is too large, details may be lost, and if the window size is too small, the threshold may fluctuate greatly. Usually, the window size is set to 1 / 4 to 1 / 2 of the diameter of the target object in the image.

[0076] In step S22, for each pixel point (x, y), its local average brightness I(x, y) can be expressed as:

[0077]

[0078] Where W and H are the width and height of the window respectively, and I(i, j) is the grayscale value of the pixel in the window;

[0079] In step S23, in the adaptive binarization, a local threshold T(x, y) is calculated for each window:

[0080]

[0081] Among them, min(I(x, y)) is the minimum grayscale value of the pixel in the window;

[0082] In step S24, for each pixel (x, y), if its grayscale value I(i, j) is greater than or equal to the local threshold T(x, y), it is set to white (255), otherwise it is set to black (0);

[0083] In step S25, morphological operations include dilation, erosion, opening and closing operations to remove small noise points or fill small holes; connected domain analysis is to identify and process connected regions in the image to extract target objects.

[0084] In this embodiment, the adaptive binarization process is applied to the actual wire rope image, which can effectively extract the edge of the wire rope and provide an accurate basis for the subsequent diameter measurement. An adaptive binarization method can be implemented, which can automatically adjust the threshold according to the local characteristics of the image and improve the accuracy of edge detection. It is particularly suitable for images with complex backgrounds and uneven brightness such as wire ropes.

[0085] In order to further implement the above technical solution, in step S3, the specific content of using the Canny operator to extract the edge information of the wire rope in the image of the effective area is:

[0086] Apply Gaussian filter to remove noise from the effective area image of the wire rope;

[0087] Calculate the gradient magnitude and direction of the image;

[0088] Apply non-maximum suppression to retain the local maximum gradient;

[0089] A dual threshold detection and edge tracking algorithm is applied to determine the final edge.

[0090] In order to further implement the above technical solution, in step S3, the specific content of using Hough transform to detect the central axis of the wire rope in the image is:

[0091] Map the points in the image space to the parameter space defined by angle and distance, create an accumulator matrix, the size of the accumulator matrix depends on the angle range and distance range of the line, the angle range is usually from 0 to 180 degrees, and the distance range is determined according to the image size; for each edge point in the image, calculate all possible (θ, r) according to the coordinates, which is implemented by the following formula:

[0092] r=xcos(θ)+ysin(θ)

[0093] For each (θ, r), add 1 to the corresponding position in the accumulator matrix;

[0094] A threshold is set based on the maximum value or average value in the accumulator matrix, and the straight line is detected based on the accumulator matrix and (θ, r). In the accumulator matrix, the (θ, r) pairs corresponding to all positions with values ​​greater than or equal to the threshold represent the detected straight line.

[0095] The straight line representing the central axis of the wire rope is selected from the detected straight lines by analyzing the geometric features of the straight lines, and the selected straight lines are fitted to obtain the central axis of the wire rope.

[0096] In order to further implement the above technical solution, the training method of the support vector machine SVM model is specifically as follows:

[0097] Take images of the wire rope at different positions and under different lighting conditions, manually annotate the captured images, and measure and record the diameter of the wire rope;

[0098] Preprocess the image and perform adaptive binarization to extract the effective area of ​​the wire rope. Use the Canny operator to extract the edge information of the wire rope in the image of the effective area, and use the Hough transform to detect the central axis of the wire rope in the image.

[0099] The diameter measurement value is used as a label, and the edge information and the image features of the central axis are used as feature vectors to form a training data set and a validation data set;

[0100] Select radial basis function RBF as the kernel function to map the data into a high-dimensional space for linear separability;

[0101] Initialize the SVM model using the training data set, select the penalty parameter and kernel function parameter, find the solution that maximizes the interval, i.e. the support vector, by solving the optimization problem, and calculate the decision function;

[0102] The new image feature vector is input into the trained SVM model, the decision function is used to calculate the predicted wire rope diameter value, the cross-validation method is used to evaluate the performance of the model, the penalty parameters and kernel function parameters are adjusted to optimize the model to obtain the best performance, and the error between the predicted result and the actual value is calculated for model verification.

[0103] In order to further implement the above technical solution, the decision function is:

[0104]

[0105] Where N is the number of support vectors, y i is the label of the i-th support vector, α i is the corresponding Lagrange multiplier, b is the bias term;

[0106] The radial basis function RBF as a kernel function is:

[0107]

[0108] Among them, x and y are two eigenvectors, γ is the parameter of the kernel function, which controls the width of the function;

[0109] The predicted wire rope diameter is:

[0110]

[0111] in, is the predicted diameter value, x new is the new image feature vector.

[0112] The present invention utilizes the SVM algorithm to learn features under different environments and different image quality conditions through training, thereby improving the generalization ability and measurement robustness of the model; the optimal feature extraction method can be automatically learned through training, reducing dependence on preset rules; the measurement results of different operators at different times can be ensured to be highly consistent through training, thereby improving the repeatability of measurement; after the training is completed, the computational complexity of the prediction stage is relatively low, thereby improving the speed and efficiency of measurement.

[0113] A wire rope diameter measurement system based on machine vision, based on a wire rope diameter measurement method based on machine vision, comprising: an array camera, a preprocessing module, an effective area extraction module, an edge detection module, a central axis detection module and a trained support vector machine SVM model;

[0114] An area array camera is used to capture images of the wire rope;

[0115] A preprocessing module, used for preprocessing the collected images;

[0116] The effective area extraction module is used to automatically adjust the threshold according to the image characteristics, perform adaptive binarization processing on the pre-processed image, and extract the effective area of ​​the wire rope;

[0117] An edge detection module is used to extract edge information of the wire rope in the image of the effective area using the Canny operator;

[0118] A central axis detection module is used to detect the central axis of the wire rope in the image using Hough transform;

[0119] The trained support vector machine (SVM) model is used to input the edge information and the center axis position as a new image feature vector, and use the decision function to calculate the output predicted wire rope diameter value.

[0120] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements a wire rope diameter measurement method based on machine vision.

[0121] A processing terminal comprises a memory and a processor. The memory stores a computer program that can be run on the processor. When the processor executes the computer program, a wire rope diameter measurement method based on machine vision is implemented.

[0122] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0123] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A wire rope diameter measurement method based on machine vision, characterized in that: The following steps are involved: S1. Use an array camera to collect images of the wire rope and preprocess the collected images; S2. According to the image characteristics, the threshold is automatically adjusted, and the pre-processed image is adaptively binarized to extract the effective area of ​​the wire rope; S3. Use the Canny operator to extract the edge information of the wire rope in the image of the effective area, and use the Hough transform to detect the central axis of the wire rope in the image; S4. Input the edge information and the central axis position as the new image feature vector into the trained support vector machine (SVM) model, and use the decision function to calculate the predicted diameter value.

2. The method for measuring the diameter of a steel wire rope based on machine vision according to claim 1, characterized in that: Preprocessing of the collected images includes image normalization, filtering and denoising, and adaptive illumination adjustment; Adaptive lighting adjustment includes lighting detection, lighting compensation, automatic exposure adjustment, contrast enhancement and dynamic range compression.

3. The method for measuring the diameter of a steel wire rope based on machine vision according to claim 1, characterized in that: In step S2, the specific contents of the adaptive binarization process include: S21. Determine the window size according to the image resolution and the size of the target object; S22. For each pixel in the image, calculate the average brightness in the surrounding window by sliding the window; S23. Calculate the local threshold of each pixel based on the local average brightness; S24. Convert each pixel in the image into a binary image according to the calculated local threshold; S25. After binarization, post-processing such as morphological operations and connected domain analysis is performed to further improve image quality.

4. The method for measuring the diameter of a steel wire rope based on machine vision according to claim 1, characterized in that: In step S3, the specific content of the edge information of the wire rope in the image of the effective area is extracted using the Canny operator: Apply Gaussian filter to remove noise from the effective area image of the wire rope; Calculate the gradient magnitude and direction of the image; Apply non-maximum suppression to retain the local maximum gradient; A dual threshold detection and edge tracking algorithm is applied to determine the final edge.

5. The method for measuring the diameter of a steel wire rope based on machine vision according to claim 1, characterized in that: In step S3, the specific content of using Hough transform to detect the central axis of the wire rope in the image is: Map the points in the image space to the parameter space defined by angle and distance, and create an accumulator matrix; for each edge point in the image, calculate all possible (θ, r) based on the coordinates, and for each (θ, r), add 1 to the corresponding position in the accumulator matrix; Set a threshold based on the maximum or average value in the accumulator matrix and detect the line based on the accumulator matrix and (θ, r); The straight line representing the central axis of the wire rope is selected from the detected straight lines by analyzing the geometric features of the straight lines, and the selected straight lines are fitted to obtain the central axis of the wire rope.

6. The method for measuring the diameter of a steel wire rope based on machine vision according to claim 1, characterized in that: The training method of the support vector machine SVM model is as follows: Take images of the wire rope at different positions and under different lighting conditions, manually annotate the captured images, and measure and record the diameter of the wire rope; Preprocess the image and perform adaptive binarization to extract the effective area of ​​the wire rope. Use the Canny operator to extract the edge information of the wire rope in the image of the effective area, and use the Hough transform to detect the central axis of the wire rope in the image. The diameter measurement value is used as a label, and the edge information and the image features of the central axis are used as feature vectors to form a training data set and a validation data set; Select radial basis function RBF as the kernel function to map the data into a high-dimensional space for linear separability; Initialize the SVM model using the training data set, select the penalty parameter and kernel function parameter, find the solution that maximizes the interval, i.e. the support vector, by solving the optimization problem, and calculate the decision function; The new image feature vector is input into the trained SVM model, the decision function is used to calculate the predicted wire rope diameter value, the cross-validation method is used to evaluate the performance of the model, the penalty parameters and kernel function parameters are adjusted to optimize the model to obtain the best performance, and the error between the predicted result and the actual value is calculated for model verification.

7. The method for measuring the diameter of a steel wire rope based on machine vision according to claim 5, characterized in that: The decision function is: Where N is the number of support vectors, y i is the label of the i-th support vector, α i is the corresponding Lagrange multiplier, b is the bias term; The predicted wire rope diameter is: in, is the predicted diameter value, x new is the new image feature vector.

8. A wire rope diameter measurement system based on machine vision, characterized in that: A wire rope diameter measurement method based on machine vision according to any one of claims 1 to 7, comprising: an array camera, a preprocessing module, an effective area extraction module, an edge detection module, a central axis detection module and a trained support vector machine SVM model; An area array camera is used to capture images of the wire rope; A preprocessing module, used for preprocessing the collected images; The effective area extraction module is used to automatically adjust the threshold according to the image characteristics, perform adaptive binarization processing on the pre-processed image, and extract the effective area of ​​the wire rope; An edge detection module is used to extract edge information of the wire rope in the image of the effective area using the Canny operator; A central axis detection module is used to detect the central axis of the wire rope in the image using Hough transform; The trained support vector machine (SVM) model is used to input the edge information and the center axis position as a new image feature vector, and use the decision function to calculate the output predicted wire rope diameter value.

9. 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 measuring the diameter of a steel wire rope based on machine vision as described in any one of claims 1 to 7 is implemented.

10. A processing terminal, comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, a wire rope diameter measurement method based on machine vision as described in any one of claims 1 to 7 is implemented.

Images