Lapping rate detection method and device, equipment, storage medium and program product

Abstract

The invention discloses a coverage rate detection method and device, equipment, a storage medium and a program product, and relates to the technical field of cable coverage rate detection, and the method comprises the steps: obtaining a wrapping image of a cable semi-conductive band; inputting the wrapping image into a semantic segmentation model to obtain a mask image of the wrapping image; the mask image comprises a plurality of overlapped edge areas and non-overlapped edge areas; determining a plurality of corresponding to-be-detected areas from the plurality of overlapping edge areas; for each to-be-detected area, based on the contour information of the to-be-detected area, determining a detection line corresponding to the to-be-detected area; based on the detection distance of the target detection area and the width of the semi-conductive band, determining the overlapping rate of the cable semi-conductive band; the target detection area is any area in the plurality of to-be-detected areas, and the detection distance is a vertical distance between a detection line of the target detection area and a detection line of the to-be-detected area adjacent to the target detection area. According to the invention, the accuracy of cable overlapping rate detection can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of cable coverage detection, and in particular to a coverage detection method, device, equipment, storage medium and program product. Background Art

[0002] The cable semi-conductive tape wrapping process is a crucial step in ensuring cable product quality and controlling production costs. The overlap rate of the cable semi-conductive tape layer is a key indicator of the quality of the wrapping process. In related technologies, visual inspection of the cable overlap edge is typically performed using template matching to determine the overlap rate.

[0003] However, in practical applications, the above method usually uses a relatively fixed template for matching, and the template matching accuracy of the fixed template is more easily affected by external factors; for example, when environmental conditions (such as lighting, background, cable surface condition, etc.) change, the fixed template is difficult to adapt to different batches of cables, different production environments, and slight changes in the cable surface, and the template matching accuracy will drop significantly, thereby limiting the detection accuracy of the cable semi-conductive tape overlap rate. Summary of the Invention

[0004] The main purpose of this application is to provide a coverage rate detection method, device, equipment, storage medium and program product, aiming to solve the technical problem of limited cable coverage rate detection accuracy in related technologies.

[0005] To achieve the above objectives, the present application proposes a method for detecting an overlap rate, which includes:

[0006] Acquire a wrapping image of the semi-conductive tape of the cable;

[0007] Input the wrapping image into the semantic segmentation model to obtain a mask image of the wrapping image; the mask image includes multiple overlapping edge regions and non-overlapping edge regions;

[0008] Determining a corresponding plurality of areas to be detected from the plurality of overlapping edge areas;

[0009] For each area to be detected, determining a detection line corresponding to the area to be detected based on the contour information of the area to be detected;

[0010] The coverage rate of the cable semi-conductive tape is determined based on the detection distance of the target detection area and the width of the semi-conductive tape; the target detection area is any area among multiple areas to be detected, and the detection distance is the vertical distance between the detection line of the target detection area and the detection line of the area to be detected adjacent to the target detection area.

[0011] In one embodiment, the step of determining a detection line corresponding to the area to be detected based on the contour information of the area to be detected includes:

[0012] Determine the minimum circumscribed rectangle of the area to be detected based on the contour information of the area to be detected;

[0013] Determine the first coordinate point on the minimum circumscribed rectangle based on the geometric information of the minimum circumscribed rectangle; the geometric information includes the centroid, semi-axis length, and tilt angle;

[0014] Based on the line connecting the centroid and the first coordinate point, a detection line corresponding to the area to be detected is determined.

[0015] In one embodiment, before the step of determining a corresponding plurality of areas to be detected from the plurality of overlapping edge areas, the method further includes:

[0016] Based on the threshold segmentation algorithm, the mask image is binarized to obtain a binary mask image;

[0017] Based on the morphological algorithm, the binary mask image is subjected to image denoising to obtain an optimized binary mask image; the morphological algorithm includes dilation operation and erosion operation; the optimized binary mask image includes multiple optimized overlapping edge regions;

[0018] The step of determining a corresponding plurality of areas to be detected from the plurality of overlapping edge areas comprises:

[0019] A corresponding plurality of areas to be detected are determined from the plurality of optimized overlapping edge areas.

[0020] In one embodiment, the area to be inspected is a middle section of the overlapping edge area in the longitudinal direction; the longitudinal direction is a direction perpendicular to the extending direction of the cable.

[0021] In one embodiment, the step of acquiring a wrapping image of the semi-conductive tape of the cable includes:

[0022] When the cable wrapping machine is in a stable operating state and the encoder count reaches a preset threshold, a camera is used to capture the wrapping image of the cable semi-conductive tape; the encoder is set in the cable wrapping machine; the camera is an industrial camera that has completed the camera calibration operation, and the camera calibration operation includes the determination of the intrinsic parameter matrix, the extrinsic parameter matrix and the distortion correction parameters.

[0023] In one embodiment, after determining the overlap rate of the semi-conductive tape of the cable based on the detection line distance and the width of the semi-conductive tape in the target detection area, the method further includes:

[0024] Compare the overlap rate of the cable's semi-conductive tape with the preset overlap rate;

[0025] When the overlap rate of the cable semi-conductive tape is less than the preset overlap rate, the cable wrapping machine is controlled to reduce the speed;

[0026] When the overlapping rate of the cable semi-conductive tape is greater than the preset overlapping rate, the cable wrapping machine is controlled to increase the speed.

[0027] In addition, to achieve the above-mentioned purpose, the present application also proposes an overlapping rate detection device, which includes:

[0028] An image acquisition module, used for acquiring an image of the wrapping of the semi-conductive tape of the cable;

[0029] An image segmentation module is used to input the wrapping image into a semantic segmentation model to obtain a mask image of the wrapping image; the mask image includes a plurality of overlapping edge regions and non-overlapping edge regions;

[0030] A detection area determination module, configured to determine a corresponding plurality of areas to be detected from a plurality of overlapping edge areas;

[0031] A detection line determination module is used to determine, for each area to be detected, a detection line corresponding to the area to be detected based on the contour information of the area to be detected;

[0032] The overlap rate determination module is used to determine the overlap rate of the cable semi-conductive tape based on the detection line distance and the width of the semi-conductive tape in the target detection area; the target detection area is any area among multiple areas to be detected, and the detection line distance is the vertical distance between the detection line of the target detection area and the detection line of the area to be detected adjacent to the target detection area.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes an overlapping rate detection device, which includes: a memory, a processor, and a computer program stored in the memory and runnable on the processor, and the computer program is configured to implement the steps of the overlapping rate detection method as described above.

[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the overlap rate detection method as described above are implemented.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the overlapping rate detection method as described above are implemented.

[0036] One or more technical solutions proposed in this application have at least the following technical effects:

[0037] In the overlap rate detection method proposed in the present application, the wrapping image of the cable semi-conductive tape can be input into the semantic segmentation model. After a lot of training, the semantic segmentation model can learn the edge texture features of the wrapping image. Compared with fixed template matching, it has a higher generalization ability and is more accurate in identifying the overlapping edge area. Then, the corresponding multiple areas to be detected are determined from the multiple overlapping edge areas, and the detection lines of the areas to be detected are further determined. With the help of the distance between the detection lines and the width of the semi-conductive tape, the overlap rate of the cable semi-conductive tape can be accurately determined. The overlapping edge area is accurately identified by the semantic segmentation model, and the corresponding detection line is generated according to the actual overlapping edge area to assist in calculating the overlap rate of the cable semi-conductive tape. It can adapt to the changes of external factors in the detection process in real time, thereby improving the stability and accuracy of the overlap rate detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0040] Figure 1 A flow chart of the first embodiment of the overlap detection method of this application is provided;

[0041] Figure 2 is a schematic diagram of an example wrapping image;

[0042] Figure 3 for Figure 2 Schematic diagram of the mask image of the wrapped image;

[0043] Figure 4 Schematic diagram of the optimized binary mask image;

[0044] Figure 5 This is a schematic diagram of screening the A1 region with the largest area;

[0045] Figure 6 is a schematic diagram of the range to be detected;

[0046] Figure 7 is a schematic diagram of multiple areas to be detected;

[0047] Figure 8 Determine the principle schematic diagram for the detection line;

[0048] Figure 9 Schematic diagram of the detection line effect;

[0049] Figure 10 This is a schematic diagram of the vertical line effect;

[0050] Figure 11 This is a schematic diagram of the calculation principle of the coverage rate;

[0051] Figure 12 A schematic diagram of a simplified flow chart of the overlapping rate detection method provided in Example 1 of the present application;

[0052] Figure 13 This is a schematic diagram of the module structure of the overlapping rate detection device according to an embodiment of the present application;

[0053] Figure 14 Schematic diagram of the device structure of the hardware operating environment involved in the coverage rate detection method in the embodiment of the present application.

[0054] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0056] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0057] The main solution of the embodiment of the present application is: obtaining a wrapping image of the cable semi-conductive tape; inputting the wrapping image into a semantic segmentation model to obtain a mask image of the wrapping image; the mask image includes multiple overlapping edge areas and non-overlapping edge areas; determining multiple corresponding areas to be detected from the multiple overlapping edge areas; for each area to be detected, determining the detection line corresponding to the area to be detected based on the contour information of the area to be detected; determining the overlapping rate of the cable semi-conductive tape based on the detection distance of the target detection area and the width of the semi-conductive tape; the target detection area is any area among the multiple areas to be detected, and the detection distance is the vertical distance between the detection line of the target detection area and the detection line of the area to be detected adjacent to the target detection area.

[0058] As a key shielding structure, the cable's semi-conductive tape layer performs the dual functions of isolating external electromagnetic interference and protecting the insulation layer, playing a vital role in maintaining the stability of the cable's insulation performance. Therefore, accurately testing the overlap rate involved in the cable's semi-conductive tape wrapping process is a key technical step in ensuring cable product quality stability and controlling production costs.

[0059] In related technologies, the overlap rate of semi-conductive tape can be detected using two methods: manual inspection and visual inspection based on template matching. Manual inspection relies primarily on the operator's experience and visual observation, and suffers from technical drawbacks such as inconsistent inspection standards, poor repeatability, and low efficiency, making it difficult to meet the needs of modern large-scale production. Visual inspection based on template matching, on the other hand, primarily uses an industrial camera to capture background and production images, extracts the cable area using an image difference algorithm, and generates a binary image. The cable pixel diameter is then determined based on angle information, and the pixel-to-space diameter conversion ratio is calculated. Finally, template matching technology is used to detect the edge of the semi-conductive tape wrap and calculate the overlap rate. However, in practical applications, template matching-based visual inspection methods typically use a relatively fixed template for matching, and the matching accuracy of fixed templates is easily affected by external factors. For example, when environmental conditions (such as lighting, background, and cable surface conditions) change, the fixed template cannot adapt to different batches of cables, different production environments, and even slight changes in the cable surface. Template matching accuracy can significantly decrease, thus limiting the accuracy of detecting the overlap rate of the cable semi-conductive tape.

[0060] The present application provides a solution that can input the wrapping image of the cable semi-conductive tape into a semantic segmentation model. After a lot of training, the semantic segmentation model can learn the edge texture features of the wrapping image. Compared with fixed template matching, it has a higher generalization ability and is more accurate in identifying overlapping edge areas. Then, from the multiple overlapping edge areas, corresponding multiple areas to be detected are determined, and the detection lines of the areas to be detected are further determined. With the help of the distance between the detection lines and the width of the semi-conductive tape, the overlap rate of the cable semi-conductive tape can be accurately determined. The semantic segmentation model accurately identifies the overlapping edge area, and generates corresponding detection lines based on the actual overlapping edge area to assist in calculating the overlap rate of the cable semi-conductive tape. It can adapt to changes in external factors during the detection process in real time, thereby improving the stability and accuracy of the overlap rate detection.

[0061] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of performing the above functions. The following uses the overlap rate detection device as an example to illustrate this embodiment and the following embodiments.

[0062] Based on this, the present application embodiment provides a method for detecting overlapping rate, referring to Figure 1 , Figure 1 This is a flow chart of Example 1 of the overlap rate detection method of this application.

[0063] In this embodiment, the overlapping rate detection method includes steps S100 to S500:

[0064] Step S100: Acquire a wrapping image of the semi-conductive tape of the cable.

[0065] Step S200: input the wrapping image into a semantic segmentation model to obtain a mask image of the wrapping image; the mask image includes a plurality of overlapping edge regions and non-overlapping edge regions.

[0066] Step S300: determining a corresponding plurality of areas to be detected from a plurality of overlapping edge areas.

[0067] Step S400 : for each area to be detected, determining a detection line corresponding to the area to be detected based on the contour information of the area to be detected.

[0068] Step S500, determining the overlap rate of the cable semi-conductive tape based on the detection distance of the target detection area and the width of the semi-conductive tape; the target detection area is any area among multiple areas to be detected, and the detection distance is the vertical distance between the detection line of the target detection area and the detection line of the area to be detected adjacent to the target detection area.

[0069] Specifically, an image of the cable's semi-conductive tape can be captured using an image acquisition device such as a camera; the image should clearly show the cable's surface and the tape's wrapping structure. In one feasible embodiment, the image of the cable's semi-conductive tape can be captured using a camera while the cable wrapping machine is operating stably and an encoder count reaches a preset threshold. The encoder is located in the cable wrapping machine, and the camera is an industrial camera that has undergone a calibration process, including determining an intrinsic parameter matrix, an extrinsic parameter matrix, and distortion correction parameters.

[0070] After the cable wrapping machine is in a stable operating state, the encoder count can be used to trigger the industrial camera to capture the image of the semi-conductive tape layer. For example, the encoder can be set on the cable traction wheel of the wrapping equipment during the cable operation. When the cable wrapping machine is turned on, the encoder can be reset. After the cable is put into the equipment and the wrapping operation officially begins, the encoder starts counting. The encoder count is related to the linear displacement of the cable. When the encoder count reaches the preset threshold, the camera can be triggered to capture the image. Figure 2 The wrapping image shown; the above preset threshold can be set according to actual needs and is not specifically limited. The setting of triggering the camera for image acquisition through encoder counting can ensure that image acquisition is performed after the cable reaches a fixed wrapping distance, ensuring the consistency of each image acquisition. Before the camera captures the image, camera calibration is required. Camera calibration mainly uses mathematical models to establish the mapping relationship between 3D world coordinates and 2D image pixel coordinates. Specifically, it can include intrinsic calibration (camera internal parameters) and extrinsic calibration (camera posture); the specific calibration process is as follows:

[0071] In the above calibration process, the external parameter matrix consists of the rotation matrix R and t, which is used to describe the transformation from the world coordinate system to the camera coordinate system: X c =R·X w +t; where X c is the 3D coordinate point in the camera coordinate system, X w is the 3D coordinate point in the world coordinate system.

[0072] The above intrinsic parameter matrix K is used to describe the focal length, principal point coordinates and inter-axis tilt of the camera:

[0073]

[0074] Among them, f x is the pixel focal length along the x-axis of the image, f y is the pixel focal length along the y-axis of the image, c x is the pixel coordinate of the principal point on the x-axis of the image, c y is the pixel coordinate of the principal point on the y-axis of the image, and s is the inter-axis tilt coefficient.

[0075] The above distortion correction is mainly divided into radial distortion and tangential distortion, which are used to correct the ideal image coordinates. Among them, radial distortion is caused by the shape of the lens:

[0076] x corrected1 =x(1+k1r 2 +k2r 4 +k3r 6 )

[0077] y corrected1 =y(1+k1r 2 +k2r 4 +k3r 6 )

[0078] Tangential distortion is mainly caused by lens installation errors:

[0079] x corrected2 =x+2p1xy+p2(r 2 +2x 2 )

[0080] y corrected2 =y+p1(r 2 +2y 2 )+2p2xy

[0081] Among them, x is the ideal horizontal coordinate, y is the ideal vertical coordinate, and x corrected1 is the horizontal coordinate after radial distortion correction, y corrected1 is the ordinate after radial distortion correction, r2 =x 2 +y 2 , k1, k2, k3 are radial distortion coefficients; x corrected2 is the horizontal coordinate after tangential distortion correction, y corrected2 is the vertical coordinate after tangential distortion correction, p1 and p2 are the tangential distortion coefficients; in practical applications, the Zhang Zhengyou method can be used to calculate the camera parameters. After obtaining the corresponding camera parameters, the distorted image is corrected by the internal parameters to obtain a more accurate wrapping image.

[0082] The above-mentioned method of automatically capturing wrapping images through industrial cameras can greatly improve detection efficiency, meet the needs of rapid detection in modern large-scale production, and help improve the overall efficiency of the production process. In addition, by triggering the camera for image acquisition through encoder counting, manual intervention is reduced, avoiding the problems of inconsistent standards and poor repeatability of results caused by manual acquisition, realizing the standardization and automation of the detection process and improving the reliability and consistency of the detection results.

[0083] The obtained wrapping image is then input into the semantic segmentation model for image recognition; the semantic segmentation model can assign each pixel in the image to a specific category, thereby classifying different areas in the image, and each pixel block will be labeled as a specific category, and all pixel blocks form a mask image through category labeling. The semantic segmentation model in this application can be obtained by iterative training based on a large number of cable semi-conductive tape wrapping images. During the training process, the number of iterations of model training can be set to 500 or more to improve the recognition accuracy of the model; the wrapping image is input into the trained semantic segmentation model, and the semantic segmentation model can infer the output of the mask image of the wrapping image through the image features learned during the training process. The image pixel values ​​in the mask image include 0 or 1; wherein, a pixel value of 1 represents an overlapping edge area, and a pixel value of 0 represents a non-overlapping edge area (such as a background area, etc.), thereby quickly and accurately separating the overlapping edge area from the wrapping image; in an example, the image is collected as follows Figure 2 The wrapped image shown in FIG, the wrapped image is input into the semantic segmentation model, and the following Figure 3 The mask image diagram shown is Figure 3The pixel values ​​corresponding to the white areas (A, B, C, D, E) in the figure are all 1; that is, areas A to E are multiple overlapping edge areas obtained by processing the semantic segmentation model. The remaining black areas are non-overlapping edge areas. By introducing a semantic segmentation model that has undergone 500 or more rounds of iterative training, the overlapping edge areas can be accurately separated from the wrapping image. Compared with the existing visual inspection method based on template matching, it can overcome the problem that the accuracy of template matching is greatly affected by environmental factors, significantly improve the edge detection accuracy, and obtain more accurate overlapping rate calculation results, thereby better meeting the high-precision requirements of the cable industry for production quality control; and the semantic segmentation model is a deep learning model with strong generalization ability. It can operate stably under different environmental conditions such as lighting and background, and can ensure the stability of the overlapping rate detection process.

[0084] After obtaining the overlapping edge area based on the semantic segmentation model, a corresponding plurality of areas to be detected can be determined from the plurality of overlapping edge areas for detection and calculation of the overlapping rate. It is understandable that, since the semi-conductive tape will present a spiral overlap when wrapped, a plurality of periodic overlapping edges (i.e., overlapping edge areas) can be captured in the wrapping image. Due to the influence of factors such as cable bending and tension fluctuations, overlapping edges at different positions may have local distortion or edge blurring. Therefore, in order to further improve the detection accuracy of the overlapping rate, the mask image output by the semantic segmentation model can be refined; in a feasible embodiment, the mask image can be binarized based on a threshold segmentation algorithm to obtain a binary mask image; based on a morphological algorithm, the binary mask image is subjected to image denoising to obtain an optimized binary mask image; the morphological algorithm includes an expansion operation and an erosion operation; the optimized binary mask image includes a plurality of optimized overlapping edge areas; in this embodiment, step S300 can specifically include: determining a corresponding plurality of areas to be detected from a plurality of optimized overlapping edge areas.

[0085] Specifically, pixel values ​​of 0 and 255 can more clearly represent image boundaries, thereby improving the accuracy and reliability of edge detection. In practical applications, image processing algorithms typically require the pixel values ​​of the input image to be between 0 and 255. Therefore, to improve the effectiveness and efficiency of subsequent image processing, we can first use the threshold segmentation algorithm shown in Expression 1 to binarize the mask image output by the semantic segmentation model to obtain the corresponding binary mask image.

[0086] Expression 1 is: Where I(x, y) is the pixel value corresponding to the pixel block with coordinates (x, y) in the mask image, and T(x, y) is the binary pixel value corresponding to the pixel block with coordinates (x, y). T0 is 1. That is, overlapping edge regions with pixel values ​​of 1 in the mask image are assigned a pixel value of 255, and non-overlapping edge regions with pixel values ​​of 0 in the mask image are assigned a binary pixel value of 0. The 0 / 1 mask image output by the semantic segmentation model is converted to a 0 / 255 binary mask image through binarization for subsequent morphological algorithm processing.

[0087] Then, the binary mask image is denoised based on the morphological algorithm shown in Expression 2 to obtain an optimized binary mask image. The morphological algorithm shown in Expression 2 is a closing operation, that is, a dilation operation is first performed on the binary mask image, and then an erosion operation is performed to fill the small holes and connection breakpoints in the overlapping edge area of ​​the binary mask image, thereby obtaining multiple optimized overlapping edge areas. Expression 2 is: Among them, M is the binary mask image, and N is the structural element. In addition, there may be some incomplete overlapping edge areas during the processing (such as Figure 3 Therefore, after completing the above binarization and morphological denoising, the incomplete overlapping edge region can be removed based on the area or length of the overlapping edge region; Figure 3 After the mask image shown is binarized, processed by morphological algorithm and region screening, the following can be obtained: Figure 4 Schematic diagram of the optimized binary mask image shown; Figure 4 A1, B1, C1, D1 and E1 in Figure 3 The five overlapping edge regions A, B, C, D and E correspond to five optimized overlapping edge regions respectively; and then a corresponding plurality of areas to be detected are determined from the plurality of optimized overlapping edge regions.

[0088] Since the cable is cylindrical in shape, its overlapping boundary line presents a certain curvature on the image. Therefore, in order to ensure the accuracy of detection, the area to be detected can be the middle section of the overlapping edge area in the longitudinal direction; the longitudinal direction is the direction perpendicular to the extension direction of the cable. In other words, the middle section of the overlapping edge area is used as the area to be detected. The curvature of the middle section on the image is smaller than that of the upper and lower sections, and can be approximated as a straight line. Therefore, the middle section can be used for overlap detection calculation to avoid the curvature of the overlapping boundary area on the image affecting the accuracy of overlap calculation. In practical applications, it can be obtained from Figure 4 Among the five areas A1 to E1 shown, the largest area A1 is selected as the reference area, and then the middle section of the A1 area is selected as the reference area to be detected. Figure 5The diagram of the A1 region with the largest area is shown in FIG. 2 . Then, based on the vertical coordinates v1 and v2 of the two coordinate points (u1, v1) and (u2, v2) in the middle section of the reference area to be detected, the range of the interval to be detected is determined by extending horizontally to both sides. Figure 6 As shown, Figure 6 is a schematic diagram of the range of the interval to be detected; then, the interval segments within the range of the interval to be detected are intercepted from the areas A1, B1, C1, D1 and E1 as their corresponding areas to be detected A2, B2, C2, D2 and E2 respectively; Figure 7 As shown, Figure 7 Schematic diagram of multiple areas to be detected.

[0089] By processing the mask image output by the semantic segmentation model and setting the optimal area to be detected as the middle section of the image based on the cylindrical morphological characteristics of the cable, compared with the non-optimal area detection that may exist in related technologies, the overlap rate detection method in this embodiment can more accurately reflect the actual overlap of the semi-conductive tape, further improving the accuracy of the detection results.

[0090] Then, for each area to be detected, based on the contour information of the area to be detected, the detection line corresponding to the area to be detected is determined. Edge detection or contour analysis technology (such as Hough transform or least squares fitting) can be used to determine the contour of each area to be detected, and the corresponding detection line is extracted from the contour. The detection line is used to further analyze the overlap rate; or in a feasible embodiment, step S400 can specifically include steps S410 to S430:

[0091] Step S410: determining the minimum bounding rectangle of the area to be detected based on the contour information of the area to be detected.

[0092] Step S420 : determining a first coordinate point on the minimum circumscribed rectangle based on geometric information of the minimum circumscribed rectangle; the geometric information includes a centroid, a semi-axis length, and an inclination angle.

[0093] Step S430 : determining a detection line corresponding to the area to be detected based on a line connecting the centroid and the first coordinate point.

[0094] Specifically, for each area to be detected, the contour information can be used to use an algorithm to determine the minimum bounding rectangle of the area to be detected; the minimum bounding rectangle is a rectangle with the smallest area that can completely surround the area to be detected. The first coordinate point on the minimum bounding rectangle can be determined by the centroid, semi-axis length, and tilt angle of the minimum bounding rectangle. The line connecting the first coordinate point and the centroid can be used to determine the detection line that assists in calculating the overlap rate. For easier understanding, please refer to the following example. Figure 8 Schematic diagram of the detection line determination principle shown. Figure 8Where (x1, y1) is the centroid of the minimum circumscribed moment, α is the tilt angle of the minimum circumscribed rectangle, and l is the semi-axis length of the minimum circumscribed rectangle. The first coordinate point (x2, y2) can be determined according to Expression 3, which is: On this basis, the detection line of the area to be detected can be determined by connecting the first coordinate point and the centroid ( Figure 8 The dotted line in the image); Under ideal conditions, the detection line and the overlap line boundary in the wrapping image can be tangent. Figure 7 By processing the multiple detection areas shown in FIG. Figure 9 The detection line effect diagram shown is as follows. Figure 9 The middle detection lines 1 to 5 correspond to the detection lines of the areas A2 to E2 to be detected, respectively.

[0095] By calculating the detection line of the minimum circumscribed rectangle, the detection error can be reduced. Under ideal conditions, the inspection line can be approximately tangent to the actual overlapping boundary line, providing a more reliable basis for the accurate calculation of the overlapping rate. Compared with the template matching detection method in related technologies, it can more accurately determine the overlapping boundary, thereby more accurately calculating the overlapping rate, effectively reducing the detection error, and providing more accurate data support for quality control in the production process.

[0096] Then, based on the detection distance of the target detection area and the width of the semi-conductive tape, the coverage rate of the cable semi-conductive tape is calculated; the target detection area can be any area among multiple areas to be detected, and the detection distance is the vertical distance between the detection line of the target detection area and the detection line of the area to be detected adjacent to the target detection area. In practical applications, starting from the centroid of the target detection area, a vertical line can be drawn to the detection line of the area to be detected adjacent to the target detection area, that is, the vertical distance between the centroid of the target detection area and the detection line of the adjacent area to be detected is used as the detection distance. Figure 10 As shown, Figure 10 This is a schematic diagram of the vertical line effect. Taking detection line 1 as an example, a vertical line can be drawn from its corresponding centroid to the adjacent detection line 2, and we can get Figure 10 The vertical line T1 shown in the figure is the same as the vertical line T2 to T4. The length of the vertical line can be used as the detection distance for the overlap calculation. Figure 11 As shown, Figure 11 This is a schematic diagram of the calculation principle of the coverage rate. Figure 11Where L is the detection distance (i.e., the vertical distance between two adjacent detection lines) and W is the width of the semi-conductive tape. The overlap ratio of the cable's semi-conductive tape can be determined based on Expression 4: δ = (WL) / W, where δ is the overlap ratio. In practical applications, the overlap ratios calculated based on different detection lines may vary to some extent. The maximum overlap ratio can be selected as the final cable semiconductor overlap ratio, or the average of the calculated overlap ratios can be taken as the final cable semiconductor overlap ratio. The specific choice can be set according to actual needs and is not subject to excessive restrictions here.

[0097] In addition, after determining the coverage rate of the cable semi-conductive tape based on the detection line distance and the width of the semi-conductive tape in the target detection area, the coverage rate of the cable semi-conductive tape can be compared with the preset coverage rate; when the coverage rate of the cable semi-conductive tape is less than the preset coverage rate, the cable wrapping machine is controlled to slow down; when the coverage rate of the cable semi-conductive tape is greater than the preset coverage rate, the cable wrapping machine is controlled to speed up.

[0098] The above-mentioned preset overlap rate is usually the standard overlap rate in the production process, which can be a specific value or a range of overlap rates that fluctuates up and down based on the standard value. When the overlap rate of the cable semi-conductive tape is less than the preset overlap rate, it indicates that the semi-conductive tape fails to meet the standard coverage requirements. At this time, the running speed of the wrapping machine can be automatically adjusted to reduce its rotation speed or adjust the tension of the cable. By controlling the wrapping machine to run at a reduced speed, the wrapping time can be increased, which helps to enhance the overlap of the cable semi-conductive tape and thus improve the overlap rate of the cable semi-conductive tape. When the overlap rate of the cable semi-conductive tape is greater than the preset overlap rate, it indicates that the semi-conductive tape is over-covered, which may lead to material waste or other quality problems. At this time, the cable wrapping machine can be controlled to run at a higher speed to reduce the overlap rate. The speed increase and decrease control range of the cable wrapping machine can be determined based on the degree of deviation between the overlap rate and the preset overlap rate. If the difference between the two is large, the speed adjustment range can be appropriately increased. For example, if the overlap rate deviation exceeds 5%, the speed can be reduced or increased by 20% to 30%. If the difference between the two is small, the speed adjustment range can be relatively small. For example, if the overlap rate deviation is less than 2%, the speed can be reduced or increased by 5% to 10% to maintain production stability. By automatically controlling the operating speed of the wrapping machine through the comparison of the overlap rate, the cable wrapping process can be precisely controlled to ensure that the overlap rate of the semi-conductive tape is within the preset standard range, thereby ensuring the stability of the cable quality.

[0099] It is not difficult to understand that the overlap rate detection method provided in the embodiment of the present application can input the wrapping image of the cable semi-conductive tape into the semantic segmentation model. After a lot of training, the semantic segmentation model can learn the edge texture features of the wrapping image. Compared with fixed template matching, it has a higher generalization ability and is more accurate in identifying the overlapping edge area. Then, the corresponding multiple areas to be detected are determined from the multiple overlapping edge areas, and the detection lines of the areas to be detected are further determined. With the help of the distance between the detection lines and the width of the semi-conductive tape, the overlap rate of the cable semi-conductive tape can be accurately determined. Accurately identify the overlapping edge area through the semantic segmentation model, and generate corresponding detection lines according to the actual overlapping edge area to assist in calculating the overlap rate of the cable semi-conductive tape. It can adapt to the changes of external factors in the detection process in real time, thereby improving the stability and accuracy of the overlap rate detection.

[0100] For example, to help understand the implementation process of the overlap rate detection method provided in this embodiment, please refer to Figure 12 , Figure 12 A brief flowchart of an overlapping rate detection method is provided, specifically:

[0101] An encoder is set on the wrapping machine equipment, and the encoder is cleared before wrapping begins. After the cable is put into the wrapping operation, the encoder starts counting and judging the count value. When the count value reaches the preset threshold, the camera is triggered to collect images and obtain the wrapping image; while obtaining the image, the encoder can be cleared again for the next image acquisition; the wrapping image is input into the semantic segmentation model for model inference to obtain a mask image, and the mask image is then binarized and morphologically processed to obtain an optimized binarized mask image; then, a better target area (i.e., the area to be detected) for overlap rate calculation is screened out from the binarized mask image; and the minimum enclosing rectangle of the target area is further determined, and the corresponding detection line is determined according to the geometric information of the minimum enclosing rectangle to calculate the overlap rate; the specific screening and calculation processing process can be referred to the description of the aforementioned embodiment, and will not be repeated here. The control strategy of the cable wrapping machine is determined according to the overlap rate. When the overlap rate is less than the preset overlap rate, the wrapping machine can be controlled to run at a reduced speed; when the overlap rate is greater than the preset overlap rate, the wrapping machine is controlled to run at a higher speed to maintain the cable overlap rate within a reasonable range and ensure the production quality of the cable.

[0102] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the overlap rate detection method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0103] This application also provides a coverage rate detection device, please refer to Figure 13 The above-mentioned overlapping rate detection device includes:

[0104] An image acquisition module 10 is used to acquire an image of the wrapping of the semi-conductive tape of the cable;

[0105] An image segmentation module 20 is configured to input the wrapping image into a semantic segmentation model to obtain a mask image of the wrapping image; the mask image includes a plurality of overlapping edge regions and non-overlapping edge regions;

[0106] A detection area determination module 30 is used to determine a corresponding plurality of to-be-detected areas from a plurality of overlapping edge areas;

[0107] A detection line determination module 40 is configured to determine, for each area to be detected, a detection line corresponding to the area to be detected based on contour information of the area to be detected;

[0108] The overlap rate determination module 50 is used to determine the overlap rate of the cable semi-conductive tape based on the detection line distance and the width of the semi-conductive tape in the target detection area; the target detection area is any area among multiple areas to be detected, and the detection line distance is the vertical distance between the detection line of the target detection area and the detection line of the area to be detected adjacent to the target detection area.

[0109] The overlap rate detection device provided in this application, which utilizes the overlap rate detection method described in the aforementioned embodiment, can resolve the technical problem of limited cable overlap rate detection accuracy in the related art. Compared to the related art, the beneficial effects of the overlap rate detection device provided in this application are the same as those of the overlap rate detection method described in the aforementioned embodiment. Other technical features of the overlap rate detection device described in this application are the same as those disclosed in the aforementioned embodiment and are not further elaborated here.

[0110] The present application provides an overlapping rate detection device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the overlapping rate detection method in the above-mentioned embodiment one.

[0111] Reference below Figure 14 , which shows a schematic diagram of the structure of an overlap detection device suitable for implementing the embodiments of the present application. The overlap detection device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), etc., and fixed terminals such as desktop computers, etc. Figure 14 The overlapping rate detection device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0112] like Figure 14 As shown, the overlap detection device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the overlap detection device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007, such as a touch screen, touchpad, keyboard, mouse, image sensor, microphone, etc.; output devices 1008, such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003, such as a magnetic tape, hard disk, etc.; and communication device 1009. Communication device 1009 can allow the coverage detection device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a coverage detection device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0113] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0114] The overlap rate detection device provided in this application, which utilizes the overlap rate detection method described in the above embodiment, can resolve the technical problem of limited cable overlap rate detection accuracy in the related art. Compared with the related art, the beneficial effects of the overlap rate detection device provided in this application are the same as those of the overlap rate detection method described in the above embodiment, and the other technical features of the overlap rate detection device are the same as those disclosed in the method described in the above embodiment, and are not further described here.

[0115] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0116] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0117] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer program) stored thereon, and the computer-readable program instructions are used to execute the overlapping rate detection method in the above embodiment.

[0118] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0119] The computer-readable storage medium may be included in the overlap rate detection device; or may exist independently without being assembled into the overlap rate detection device.

[0120] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the overlap rate detection device, the overlap rate detection device is enabled to: obtain a wrapping image of the cable semi-conductive tape; input the wrapping image into a semantic segmentation model to obtain a mask image of the wrapping image; the mask image includes multiple overlapping edge areas and non-overlapping edge areas; determine a corresponding multiple areas to be detected from the multiple overlapping edge areas; for each area to be detected, determine the detection line corresponding to the area to be detected based on the contour information of the area to be detected; determine the overlap rate of the cable semi-conductive tape based on the detection distance of the target detection area and the width of the semi-conductive tape; the target detection area is any area among the multiple areas to be detected, and the detection distance is the vertical distance between the detection line of the target detection area and the detection line of the area to be detected adjacent to the target detection area.

[0121] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0122] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0123] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0124] The computer-readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned overlap detection method. This computer-readable storage medium can address the technical issue of limited cable overlap detection accuracy in related technologies. Compared to related technologies, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the overlap detection method provided in the aforementioned embodiment, and are not further elaborated here.

[0125] The present application also provides a computer program product, comprising a computer program, which implements the steps of the overlapping rate detection method as described above when executed by a processor.

[0126] The computer program product provided in this application can solve the technical problem of limited accuracy in cable coverage detection in related technologies. Compared with related technologies, the beneficial effects of the computer program product provided in this application are the same as those of the coverage detection method provided in the above embodiment, and will not be repeated here.

[0127] The above descriptions are only some embodiments of the present application and do not limit the scope of protection. All equivalent structural transformations made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the scope of protection.

Claims

1. A method for detecting overlapping rate, characterized in that: The overlapping rate detection method comprises: Acquire a wrapping image of the semi-conductive tape of the cable; Inputting the wrapping image into a semantic segmentation model to obtain a mask image of the wrapping image; the mask image includes a plurality of overlapping edge regions and non-overlapping edge regions; Determining a corresponding plurality of areas to be detected from the plurality of overlapping edge areas; For each of the areas to be detected, determining a detection line corresponding to the area to be detected based on the contour information of the area to be detected; The overlap rate of the cable semi-conductive tape is determined based on the detection distance of the target detection area and the width of the semi-conductive tape; the target detection area is any area among the multiple areas to be detected, and the detection distance is the vertical distance between the detection line of the target detection area and the detection line of the area to be detected adjacent to the target detection area.

2. The overlapping rate detection method according to claim 1, wherein: The step of determining the detection line corresponding to the area to be detected based on the contour information of the area to be detected includes: Determining a minimum circumscribed rectangle of the area to be detected based on the contour information of the area to be detected; Determining a first coordinate point on the minimum circumscribed rectangle based on geometric information of the minimum circumscribed rectangle, wherein the geometric information includes a centroid, a semi-axis length, and an inclination angle; A detection line corresponding to the area to be detected is determined based on a line connecting the centroid and the first coordinate point.

3. The overlapping rate detection method according to claim 1, wherein: Before the step of determining a corresponding plurality of areas to be detected from the plurality of overlapping edge areas, the method further includes: Based on a threshold segmentation algorithm, binarizing the mask image to obtain a binary mask image; Based on a morphological algorithm, performing image denoising processing on the binary mask image to obtain an optimized binary mask image; the morphological algorithm includes a dilation operation and an erosion operation; the optimized binary mask image includes a plurality of optimized overlapping edge regions; The step of determining a corresponding plurality of areas to be detected from the plurality of overlapping edge areas comprises: A corresponding plurality of areas to be detected are determined from the plurality of optimized overlapping edge areas.

4. The overlapping rate detection method according to claim 1, wherein: The area to be detected is the middle section of the overlapping edge area in the longitudinal direction; the longitudinal direction is a direction perpendicular to the extending direction of the cable.

5. The overlapping rate detection method according to claim 1, wherein: The step of obtaining the wrapping image of the semi-conductive tape of the cable comprises: When the cable wrapping machine is in a stable operating state and the encoder count reaches a preset threshold, a camera is used to capture the wrapping image of the cable semi-conductive tape; the encoder is set in the cable wrapping machine; the camera is an industrial camera that has completed a camera calibration operation, and the camera calibration operation includes the determination of an intrinsic parameter matrix, an extrinsic parameter matrix and distortion correction parameters.

6. The overlapping rate detection method according to any one of claims 1 to 5, characterized in that: After the step of determining the overlap rate of the cable semi-conductive tape based on the detection line distance and the width of the semi-conductive tape in the target detection area, the method further includes: comparing the overlap rate of the semi-conductive tape of the cable with a preset overlap rate; When the overlap rate of the semi-conductive tape of the cable is less than a preset overlap rate, controlling the cable wrapping machine to slow down; When the overlapping rate of the semi-conductive tape of the cable is greater than the preset overlapping rate, the cable wrapping machine is controlled to increase the speed.

7. A device for detecting overlapping rate, characterized in that: The overlapping rate detection device comprises: An image acquisition module, used for acquiring an image of the wrapping of the semi-conductive tape of the cable; An image segmentation module, configured to input the wrapping image into a semantic segmentation model to obtain a mask image of the wrapping image; the mask image includes a plurality of overlapping edge regions and non-overlapping edge regions; A detection area determination module, configured to determine a corresponding plurality of areas to be detected from the plurality of overlapping edge areas; a detection line determination module, configured to determine, for each of the areas to be detected, a detection line corresponding to the area to be detected based on contour information of the area to be detected; The overlapping rate determination module is used to determine the overlapping rate of the cable semi-conductive tape based on the detection line distance and the width of the semi-conductive tape of the target detection area; the target detection area is any area of ​​the multiple areas to be detected, and the detection line distance is the vertical distance between the detection line of the target detection area and the detection line of the area to be detected adjacent to the target detection area.

8. An overlapping rate detection device, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the overlapping rate detection method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the overlapping rate detection method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the overlapping rate detection method according to any one of claims 1 to 6 are implemented.

Images