Intelligent strip steel width detection method, computer equipment and storage medium

Abstract

The invention provides an intelligent strip steel width detection method, computer equipment and a storage medium. The method comprises the steps that S1, an image is read online in real time; s2, carrying out the edge extraction of the image through a threshold segmentation method, and obtaining a strip steel left edge threshold and a strip steel right edge threshold; s3, carrying out secondary edge extraction on the image through an edge detection method, and obtaining a detection left edge detection and a detection right edge detection; and S4, comparing the extraction results of the steps S2 and S3 to obtain the positions of the left edge and the right edge of the strip steel and the width of the strip steel. The system has high stability and high real-time performance, so that field staff can check and generate statistical reports at any time, and real-time alarm reminding is realized.

Description

Technical Field

[0001] The present invention belongs to the field of online width detection, and in particular relates to an intelligent strip width detection method, a computer device and a storage medium. Background Art

[0002] During the production process of steel plates, whether in the rolling process, product inspection process or product delivery process, the real-time width is a very important quality parameter. The width of the steel plate directly determines the yield rate. Its importance is mainly reflected in the following aspects: 1. Performance influence: The width of hot-rolled steel plate is one of the important factors affecting the performance of steel plate. It directly affects the formability, strength, toughness, dimensional accuracy and other properties of the steel plate.

[0003] 2. Manufacturing cost: Appropriate steel plate width can reduce manufacturing costs. If the steel plate is too wide or too narrow, more subsequent processing may be required, such as cutting, welding, etc., which will increase manufacturing costs and time.

[0004] 3. Material utilization: Reasonable steel plate width can also improve material utilization. Too wide steel plates may contain too many useless parts, while too narrow steel plates may not meet certain application requirements.

[0005] 4. Processing difficulty: The width of the steel plate will also affect the processing difficulty. Steel plates with appropriate width can be more easily bent, cut, welded and other processing operations, thereby improving production efficiency.

[0006] The width defect of steel plate will cause customer complaints and cause irreversible impact on the enterprise. At the same time, with the increasing application of high-tech and real-time management systems in engineering practice, many platform management systems also need the real-time width of steel plate as a model parameter.

[0007] At present, a large part of rolling lines still use manual width detection methods. The measurement environment is harsh. Quality inspectors working in this environment cannot be well guaranteed for safety, and are prone to fatigue, which affects the quality of inspection. At the same time, in order to ensure safety, manual inspection requires stopping the machine for measurement, which greatly reduces production efficiency. Finally, manual measurement can only measure part of the steel plate, and a roll of steel plate is often thousands of meters long, so it is difficult to guarantee the overall quality. In addition, with the development of high technology, the demand for steel plate width indicators has increased, and manual measurement cannot meet the following requirements: 1) Manual measurement cannot detect real-time problems, cannot detect narrowband in time, and feedback information is very slow; 2) Manual measurement data cannot be accurately and timely fed back to other management and control systems as feedback values; 3) Manual measurement cannot produce bandwidth statistics in a timely and rapid manner.

[0008] There are also some rolling lines that use infrared measurement. However, with the improvement of production technology, especially in the final product inspection section, the traditional infrared measurement method can no longer meet the requirements due to the low temperature of the steel plate. The use of background light source measurement has greatly increased the maintenance workload of workers.

[0009] The width measurement method based on computer vision is real-time and efficient, and can be integrated with other monitoring platform alarm systems in real time to meet the needs of the site. However, the existing methods of real-time acquisition of steel plate images for visual analysis have the following problems: 1) Unstable illumination intensity at the scene: The illumination intensity varies greatly between day and night, and the grayscale of the collected images changes dramatically, making it difficult to achieve adaptive adjustment; 2) Diversified steel plate materials: The reflectivity of steel plates varies according to the material, which results in dramatic changes in the grayscale of the captured images and large changes in the contrast between the foreground and the background; 3) Influence of steel plate dirt: Dirt of varying sizes, depths and shapes on the steel plate will have a serious impact on image processing; 4) Fast rolling speed of steel plates: The rolling speed of steel plates on site is very fast. In order to meet the real-time requirements and ensure that no detection is missed, the complexity of the detection algorithm is very high; 5) Influence of steel plate background: To solve the influence of steel plate tilt and shaking during image acquisition, the acquisition system needs to face the roller. The roller as the background will cause great interference to image processing. Summary of the invention

[0010] In view of the above problems, the present invention provides an intelligent strip width detection method, a computer device and a storage medium.

[0011] The intelligent strip steel width detection method provided by the present invention comprises the steps of: S1. Reading an image online in real time, wherein the image is an image of a steel strip taken by an image acquisition system facing a roller on a rolling line, wherein the steel strip in the image is in an up-and-down direction, and has a left edge and a right edge; S2. Extracting edges of the image by threshold segmentation method to obtain a threshold left edge threshold_left_edge and a threshold right edge threshold_right_edge of the steel strip; S3, performing a second edge extraction on the image by edge detection method to obtain a detection left edge detection_left_edge and a detection right edge detection_right_edge of the strip; S4. Compare the extraction results of steps S2 and S3 to obtain the positions of the left edge and the right edge of the steel strip and the width of the steel strip.

[0012] further, The step S2 includes three steps: filtering, binarization, and finding the border. in, The specific process of the binarization is threshold segmentation, that is, by setting a threshold, setting the pixel points whose grayscale value is greater than or equal to the threshold to white, and setting the pixel points whose grayscale value is less than the threshold to black, wherein the threshold is adaptively adjusted in an adaptive adjustment mode according to the average grayscale value of the image, including the steps of: Three grayscale thresholds are set according to empirical values: a high threshold Thresh_high, an average threshold Thresh_avg, and a low threshold Thresh_low, wherein the three grayscale thresholds satisfy Thresh_high>Thresh_avg>Thresh_low; After the adaptive adjustment mode is triggered, the average gray value Gray_avg of the area of ​​interest of the currently acquired image, that is, the steel plate covered area, is calculated at predetermined time intervals, and the threshold is denoted as Threshold. The threshold is updated according to the following formula: further, If extreme conditions occur, the technical staff will manually adjust the threshold online according to the working conditions. The extreme situations include: the light is extremely bright or extremely dark, that is, the light brightness exceeds the first predetermined threshold or is lower than the second predetermined threshold, or the interference is very large, that is, the noise amplitude exceeds the third predetermined threshold. The first predetermined threshold, the second predetermined threshold, and the third predetermined threshold are set by technical personnel according to specific working conditions.

[0013] further, The step of finding the border comprises: A grayscale threshold Thresh_Gray is set according to specific working conditions. For each column of pixels in the image after binarization, find the first pixel column A whose average grayscale value is greater than the grayscale threshold Thresh_Gray from left to right. The position of the pixel column A is the left edge position of the strip measured in step S2, recorded as the threshold left edge threshold_left_edge. Similarly, find the first pixel column B whose average grayscale value is greater than the grayscale threshold Thresh_Gray from right to left. The position of the pixel column B is the right edge position of the strip measured in step S2, recorded as the threshold right edge threshold_right_edge.

[0014] further, In step S3, the edge detection method includes bilateral filtering and edge detection. in, The edge detection is to detect the edge of the steel strip by calculating the grayscale of the image using a first-order Sobel operator, wherein the left edge and the right edge of the steel strip are separated and the edge detection is performed separately, and the left edge position and the right edge position of the steel strip measured in step S3 are respectively obtained, which are recorded as the detection left edge detection_left_edge and the detection right edge detection_right_edge respectively.

[0015] further, In step S4, If the absolute value of the difference between the threshold left edge threshold_left_edge and the detected left edge detection_left_edge is less than the first expected minimum value, that is, the threshold left edge threshold_left_edge and the detected left edge detection_left_edge are close, then the threshold left edge threshold_left_edge is selected as the measured left edge of the strip. Similarly, if the absolute value of the difference between the threshold right edge threshold_right_edge and the detected right edge detection_right_edge is less than the second expected minimum value, that is, the threshold right edge threshold_right_edge and the detected right edge detection_right_edge are close, then the threshold right edge threshold_right_edge is selected as the measured right edge of the strip.

[0016] further, In step S4, The strip width obtained by the threshold left edge threshold_left_edge and the threshold right edge threshold_right_edge is recorded as the threshold width threshold_width, and the strip width obtained by the detection left edge detection_left_edge and the detection right edge detection_right_edge is recorded as the detection width detection_width. If the threshold width threshold_width and the detection width detection_width are both greater than or less than the standard bandwidth of the strip, the one that is closer to the standard bandwidth of the strip is taken as the measured strip width.

[0017] further, If one of the threshold width threshold_width and the detection width detection_width is greater than the standard bandwidth of the strip, and the other is less than the standard bandwidth of the strip, then the one whose absolute value of the difference between the strip width and the actual measured result of the previous image is less than the third expected minimum value, that is, the one that is closer to the strip width in the actual measured result of the previous image is selected as the measured strip width.

[0018] The present invention also provides a computer device, which includes a memory, a first processor, and a first computer program stored in the memory and executable on the first processor, wherein the first computer program implements the above-mentioned intelligent strip width detection method when executed by the first processor.

[0019] The present invention also provides a computer-readable storage medium, which is used to store a second computer program. The second computer program can be executed by at least one second processor to enable the at least one second processor to execute the above-mentioned intelligent strip width detection method.

[0020] With regard to the existing problems 1), 2) and 3) of the above-mentioned existing methods for real-time acquisition of steel plate images for visual analysis, the present invention proposes to simultaneously perform edge detection using an improved threshold segmentation method based on grayscale threshold and an edge detection method based on grayscale gradient changes. By comparing and selecting the two results, the influence of the grayscale gradient caused by the grayscale change and dirt on the steel plate is effectively suppressed. With regard to the above-mentioned problem 4), the present invention uses a first-order Sobel operator and simple matrix addition and multiplication operations, which have fast computing speed and high efficiency, and can effectively achieve the purpose of real-time. With regard to the above-mentioned problem 5), the image processed by the present invention is an image of the steel strip taken by the image acquisition system facing the rollers on the rolling line, which effectively ensures that the camera is facing the steel plate and eliminates the influence of the tilt and jitter of the steel plate.

[0021] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] 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 some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1A flow chart of an intelligent strip steel width detection method according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" in the specification and claims of the present application and the above-mentioned drawings and any variations thereof are intended to cover non-exclusive inclusions. The terms "first", "second", "third", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order or a primary and secondary relationship. "Multiple" appearing in this application refers to more than two (including two).

[0026] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0027] Figure 1 This is a flow chart of the intelligent strip steel width detection method provided by the present invention. Figure 1 The intelligent strip steel width detection method is used to detect the actual strip steel width on the rolling line, and includes the following steps.

[0028] S1. Read the image online in real time. The image is an image of the steel strip taken by the image acquisition system facing the rollers on the rolling line, so as to avoid the problem of "large near and small far" in the acquired image due to the inclination and shaking of the steel strip during the rolling process. The steel strip in the image is in an up-and-down direction, and has a left edge and a right edge.

[0029] S2, extracting the edge of the collected image by threshold segmentation method to obtain the threshold left edge threshold_left_edge and the threshold right edge threshold_right_edge of the strip. Edge extraction includes three steps: filtering, binarization, and finding the border.

[0030] The filtering refers to preprocessing the image using a practical filtering technique such as Gaussian filtering to remove noise in the image.

[0031] The binarization refers to setting the grayscale value of the pixel points on the image to 0 or 255, so that the entire image presents an obvious black and white effect. After the binarization, the grayscale value of each pixel point of the image can only be 0 or 255, representing black and white respectively. The specific process of binarization is threshold segmentation, that is, by setting a threshold, the pixel points with grayscale values ​​greater than or equal to the threshold are set to white (that is, the grayscale value is 255), and the pixel points with grayscale values ​​less than the threshold are set to black (that is, the grayscale value is 0).

[0032] The difficulty of binarization is how to select the threshold. The present invention adaptively adjusts the threshold in an adaptive adjustment mode according to the average gray value of the image, specifically including the steps of: First, three grayscale thresholds are set according to empirical values: high threshold Thresh_high, average threshold Thresh_avg, and low threshold Thresh_low. These three thresholds satisfy Thresh_high>Thresh_avg>Thresh_low. Then, after the adaptive adjustment mode is triggered, the average gray value Gray_avg of the region of interest (ROI area) of the currently acquired image, the area covered by the steel plate, is calculated at predetermined time intervals such as 10 seconds, and the threshold Threshold is updated according to the following formula:

[0033] If extreme situations occur, the technicians will manually adjust the thresholds online according to the working conditions. The extreme situations include: the light is extremely bright or extremely dark, that is, the light brightness exceeds the first predetermined threshold or is lower than the second predetermined threshold, or the interference is very large, that is, the noise amplitude exceeds the third predetermined threshold. The first predetermined threshold, the second predetermined threshold, and the third predetermined threshold are set by the technicians according to the specific working conditions.

[0034] Finding the border means determining the outermost contour of the steel strip, and then determining the left and right edge positions of the steel strip. The present invention directly finds the outermost contour of the steel strip through the traditional findCounters contour detection method. Considering that the image of the steel strip is obtained by the image acquisition system shooting the rollers on the rolling line, sometimes the tiny white spots on the rollers will just appear on the edge of the steel strip. Therefore, in this step, the present invention sets a grayscale threshold Thresh_Gray that can be adjusted according to the specific working conditions, and then determines the left and right edge positions by judging the average grayscale value of each column of pixels (i.e., pixel column) of the binary image and the grayscale threshold Thresh_Gray to eliminate the influence of the white spots on the rollers. Specifically, for the binary image, For each column of pixels in the binarized image (i.e., the image after binarization), find the first pixel column A from left to right whose average grayscale value is greater than the grayscale threshold Thresh_Gray, then the position of pixel column A is the left edge position of the strip measured in this step, recorded as the threshold left edge threshold_left_edge. Similarly, find the first pixel column B from right to left whose average grayscale value is greater than the grayscale threshold Thresh_Gray, then the position of pixel column B is the right edge position of the strip measured in this step, recorded as the threshold right edge threshold_right_edge.

[0035] S3, performing a second edge extraction on the collected image by edge detection method to obtain detection_left_edge and detection_right_edge of the strip. The edge detection method includes bilateral filtering and edge detection.

[0036] The bilateral filtering is to use a bilateral filter to preprocess the image to obtain the image to be detected, so as to highlight the edge gradient of the strip and reduce the gradient of the non-edge part.

[0037] The edge detection is to detect the edge of the steel strip by calculating the grayscale of the image using a first-order Sobel operator (size 3*3). Since the first-order gradient of the right edge of the steel strip is negative (the grayscale changes from light to dark), the present invention separates the left edge of the steel strip and the right edge of the steel strip and performs edge detection separately, and obtains the left edge position and the right edge position of the steel strip measured in this step, which are respectively recorded as the detection left edge detection_left_edge and the detection right edge detection_right_edge.

[0038] S4. Compare the extraction results of steps S2 and S3 to obtain the positions of the left edge and the right edge of the steel strip and the width of the steel strip.

[0039] When making comparisons in this step, if the absolute value of the difference between the threshold left edge threshold_left_edge and the detection left edge detection_left_edge is less than the first expected minimum value (determined by the technician according to the working conditions), that is, the threshold left edge threshold_left_edge and the detection left edge detection_left_edge are close, then the threshold left edge threshold_left_edge is selected as the measured left edge of the strip. Similarly, if the absolute value of the difference between the threshold right edge threshold_right_edge and the detection right edge detection_right_edge is less than the second expected minimum value (determined by the technician according to the working conditions), that is, the threshold right edge threshold_right_edge and the detection right edge detection_right_edge are close, then the threshold right edge threshold_right_edge is selected as the measured right edge of the strip. The measured left edge of the strip, the measured right edge of the strip, and the strip width determined by the two are the measured results.

[0040] The strip width obtained by the threshold left edge threshold_left_edge and the threshold right edge threshold_right_edge is recorded as the threshold width threshold_width, and the strip width obtained by detecting the left edge detection_left_edge and the right edge detection_right_edge is recorded as the detection width detection_width. If the threshold width threshold_width and the detection width detection_width are both greater than or less than the standard bandwidth of the strip, the one that is closer to the standard bandwidth of the strip is taken as the measured strip width, and the strip width and the corresponding measured strip left edge position and strip right edge position (respectively as the measured left edge of the strip and the measured right edge of the strip) are the measured results. If one of the threshold width threshold_width and the detection width detection_width is greater than the standard bandwidth of the strip, and the other is less than the standard bandwidth, the one whose absolute value of the difference between the strip width and the actual measurement result of the previous image is less than the third expected minimum value (determined by the technician according to the working conditions), that is, the one closer to the strip width in the actual measurement result of the previous image is selected as the measured strip width, and the strip width and the corresponding measured left edge position and right edge position of the strip (respectively as the measured left edge of the strip and the measured right edge of the strip) are the measured results. If the image at this time is the first image, that is, there is a large deviation in the threshold selection when the system is just started, the threshold can be manually set by the on-site personnel to obtain accurate detection results.

[0041] The present invention also provides a computer device, which includes a memory, a first processor, and a first computer program stored in the memory and executable on the first processor, wherein the first computer program implements the above-mentioned intelligent strip width detection method when executed by the first processor.

[0042] The present invention also provides a computer-readable storage medium, which is used to store a second computer program. The second computer program can be executed by at least one second processor to enable the at least one second processor to execute the above-mentioned intelligent strip width detection method.

[0043] The present invention organically combines the threshold segmentation method and the edge detection method, selects the best result through a selector, and calculates the actual bandwidth according to the ratio of the pixel point to the actual distance. It has high stability and high real-time performance, thereby ensuring that on-site staff can view and generate statistical reports at any time, and realize real-time alarm reminders.

[0044] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent strip steel width detection method, characterized in that: Includes steps: S1. Reading an image online in real time, wherein the image is an image of a steel strip taken by an image acquisition system facing a roller on a rolling line, wherein the steel strip in the image is in an up-and-down direction, and has a left edge and a right edge; S2. Extracting edges of the image by threshold segmentation method to obtain a threshold left edge threshold_left_edge and a threshold right edge threshold_right_edge of the steel strip; S3, performing a second edge extraction on the image by edge detection method to obtain a detection left edge detection_left_edge and a detection right edge detection_right_edge of the strip; S4. Compare the extraction results of steps S2 and S3 to obtain the positions of the left edge and the right edge of the steel strip and the width of the steel strip.

2. The intelligent strip steel width detection method according to claim 1 is characterized in that: The step S2 includes three steps: filtering, binarization, and finding the border. in, The specific process of the binarization is threshold segmentation, that is, by setting a threshold, setting the pixel points whose grayscale value is greater than or equal to the threshold to white, and setting the pixel points whose grayscale value is less than the threshold to black, wherein the threshold is adaptively adjusted in an adaptive adjustment mode according to the average grayscale value of the image, including the steps of: Three grayscale thresholds are set according to empirical values: a high threshold Thresh_high, an average threshold Thresh_avg, and a low threshold Thresh_low, wherein the three grayscale thresholds satisfy Thresh_high>Thresh_avg>Thresh_low; After the adaptive adjustment mode is triggered, the average gray value Gray_avg of the area of ​​interest of the currently acquired image, that is, the steel plate covered area, is calculated at predetermined time intervals, and the threshold is denoted as Threshold. The threshold is updated according to the following formula: 。 3. The intelligent strip steel width detection method according to claim 2 is characterized in that: If extreme conditions occur, the technical staff will manually adjust the threshold online according to the working conditions. The extreme situations include: the light is extremely bright or extremely dark, that is, the light brightness exceeds the first predetermined threshold or is lower than the second predetermined threshold, or the interference is very large, that is, the noise amplitude exceeds the third predetermined threshold. The first predetermined threshold, the second predetermined threshold, and the third predetermined threshold are set by technical personnel according to specific working conditions.

4. The intelligent strip steel width detection method according to claim 3 is characterized in that: The step of finding the border comprises: A grayscale threshold Thresh_Gray is set according to specific working conditions. For each column of pixels in the image after binarization, find the first pixel column A whose average grayscale value is greater than the grayscale threshold Thresh_Gray from left to right. The position of the pixel column A is the left edge position of the strip measured in step S2, recorded as the threshold left edge threshold_left_edge. Similarly, find the first pixel column B whose average grayscale value is greater than the grayscale threshold Thresh_Gray from right to left. The position of the pixel column B is the right edge position of the strip measured in step S2, recorded as the threshold right edge threshold_right_edge.

5. The intelligent strip steel width detection method according to claim 4 is characterized in that: In step S3, the edge detection method includes bilateral filtering and edge detection. in, The edge detection is to detect the edge of the steel strip by calculating the grayscale of the image using a first-order Sobel operator, wherein the left edge and the right edge of the steel strip are separated and the edge detection is performed separately, and the left edge position and the right edge position of the steel strip measured in step S3 are respectively obtained, which are recorded as the detection left edge detection_left_edge and the detection right edge detection_right_edge respectively.

6. The intelligent strip steel width detection method according to claim 5, characterized in that: In step S4, If the absolute value of the difference between the threshold left edge threshold_left_edge and the detected left edge detection_left_edge is less than the first expected minimum value, that is, the threshold left edge threshold_left_edge and the detected left edge detection_left_edge are close, then the threshold left edge threshold_left_edge is selected as the measured left edge of the strip. Similarly, if the absolute value of the difference between the threshold right edge threshold_right_edge and the detected right edge detection_right_edge is less than the second expected minimum value, that is, the threshold right edge threshold_right_edge and the detected right edge detection_right_edge are close, then the threshold right edge threshold_right_edge is selected as the measured right edge of the strip.

7. The intelligent strip steel width detection method according to claim 5, characterized in that: In step S4, The strip width obtained by the threshold left edge threshold_left_edge and the threshold right edge threshold_right_edge is recorded as the threshold width threshold_width, and the strip width obtained by the detection left edge detection_left_edge and the detection right edge detection_right_edge is recorded as the detection width detection_width. If the threshold width threshold_width and the detection width detection_width are both greater than or less than the standard bandwidth of the strip, the one that is closer to the standard bandwidth of the strip is taken as the measured strip width.

8. The intelligent strip steel width detection method according to claim 7, characterized in that: If one of the threshold width threshold_width and the detection width detection_width is greater than the standard bandwidth of the strip, and the other is less than the standard bandwidth of the strip, then the one whose absolute value of the difference between the strip width and the actual measured result of the previous image is less than the third expected minimum value, that is, the one that is closer to the strip width in the actual measured result of the previous image is selected as the measured strip width.

9. Computer device, characterized in that It includes a memory, a first processor, and a first computer program stored in the memory and executable on the first processor, wherein the first computer program implements the intelligent strip width detection method described in any one of claims 1 to 8 when executed by the first processor.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store a second computer program, and the second computer program can be executed by at least one second processor, so that the at least one second processor executes the intelligent strip width detection method according to any one of claims 1-10.

Images