Steel wire rope ratio detection method and device, hoisting equipment and processor

Abstract

Embodiments of the present application provide a steel wire rope ratio detection method, device, hoisting equipment and processor. The detection method is applied to the hoisting equipment, the hoisting equipment comprises an arm support, an image acquisition device is installed at the end of the arm support, and the detection method comprises the following steps: acquiring a hook image of the hoisting equipment through the image acquisition device, determining the outer contour of a pulley in the hook image, a fitting area where the pulley is located and a rope area corresponding to the steel wire rope, and the rope area comprising a plurality of rope sub-areas. The fitting area is divided into a plurality of pulley sub-areas, and based on the proximity points of each rope sub-area and the outer contour of the pulley in the hook image, the target pulley sub-area where each proximity point is located is determined to determine the target pulley sub-area corresponding to each rope sub-area. Then, the number of steel wire ropes in each rope sub-area is calculated, and the steel wire rope ratio of each target pulley sub-area corresponding to the rope sub-area is determined to determine the steel wire rope ratio of the hoisting equipment. Based on the image processing of the hook image, the automatic identification of the steel wire rope ratio can be realized, and the detection accuracy is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of engineering machinery, and in particular to a detection method and device for wire rope ratio, a hoisting device, a storage medium and a processor. BACKGROUND

[0002] In the field of engineering machinery, for large load hoisting tasks, the hoisting system uses multiple wire ropes for lifting operation, and the number of wire ropes used is the wire rope ratio. As one of the important safety monitoring objects of the hoisting safety system, the wire rope ratio directly affects the lifting capacity of the crane. In order to ensure the safe and stable operation of the hoisting operation, the crane working load range is usually limited within a specified range according to the wire rope ratio. However, the traditional detection of the wire rope ratio relies on manual input, which is prone to missed detection and false detection, thereby failing to ensure the safety of the hoisting work. SUMMARY

[0003] The purpose of the embodiments of the present application is to provide a detection method and device for wire rope ratio, a hoisting device, a storage medium and a processor.

[0004] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a detection method for wire rope ratio, which is applied to a hoisting device including a boom, and an image acquisition device is installed at the end of the boom. The detection method comprises the following steps:

[0005] obtaining a hook image of the hoisting device by the image acquisition device, wherein the hook image includes a pulley and a wire rope;

[0006] determining the outer contour of the pulley, the fitting area where the pulley is located, and the rope area corresponding to the wire rope in the hook image, wherein the rope area includes a plurality of rope sub-areas;

[0007] determining the number of wire ropes in each rope sub-area respectively;

[0008] determining the adjacent points corresponding to each rope sub-area, wherein the adjacent points refer to the pixel points closest to the outer contour of the pulley in the rope sub-area;

[0009] dividing the fitting area into a plurality of pulley sub-areas;

[0010] determining the pulley sub-area where the adjacent points corresponding to the rope sub-area are located as the pulley sub-area corresponding to the rope sub-area;

[0011] determining the wire rope ratio of the hoisting device according to the corresponding relationship between the rope sub-area and the pulley sub-area, and the number of wire ropes in each rope sub-area.

[0012] In the embodiments of the present application, before the adjacent point corresponding to the rope sub-region is determined to be in the pulley sub-region corresponding to the rope sub-region, the method further comprises: obtaining the boundary endpoint coordinates of each pulley sub-region and the coordinates of the adjacent point; and determining the pulley sub-region in which the adjacent point is located based on the boundary endpoint coordinates of each pulley sub-region and the coordinates of the adjacent point by using the cross product method.

[0013] In the embodiments of the present application, the steel wire rope ratio of the hoisting device is determined according to the correspondence between the rope sub-region and the pulley sub-region and the number of steel wire ropes in each rope sub-region, which comprises: determining the number of steel wire ropes in each pulley sub-region according to the correspondence between the rope sub-region and the pulley sub-region and the number of steel wire ropes in each rope sub-region, respectively, wherein the plurality of pulley sub-regions comprise a first pulley sub-region, a second pulley sub-region and a third pulley sub-region arranged in sequence along the radial direction of the pulley; and determining the steel wire rope ratio of the hoisting device according to the sum of the maximum of twice the number of steel wire ropes in the first pulley sub-region and the number of steel wire ropes in the third pulley sub-region and the number of steel wire ropes in the second pulley sub-region.

[0014] In the embodiments of the present application, determining the outer contour of the pulley in the hook image, the fitting region where the pulley is located and the rope region corresponding to the steel wire rope comprises: determining the matching region where the pulley is located from the hook image; determining the outer contour of the pulley in the matching region based on an image segmentation algorithm; and performing minimum rectangle fitting on the outer contour of the pulley to obtain the fitting region where the pulley is located; wherein determining the matching region where the pulley is located from the hook image comprises at least one of the following:

[0015] obtaining a plurality of template images of the pulley, matching the template images with the hook image to determine the matching region where the pulley is located;

[0016] inputting the hook image into a deep learning model to determine the matching region where the pulley is located by the deep learning model.

[0017] In the embodiments of the present application, determining the outer contour of the pulley in the hook image, the fitting region where the pulley is located and the rope region corresponding to the steel wire rope comprises: determining the target contour endpoint in the pixels corresponding to the outer contour; determining the first region where the steel wire rope is located according to the target contour endpoint; determining the search region of the steel wire rope by removing the region occupied by the outer contour in the first region; extracting the roughness feature value of the search region; and determining the rope region according to the roughness feature value.

[0018] In the embodiments of the present application, the roughness feature value of the search area is extracted, including: determining a first image feature of the search area, the first image feature including at least one of a color feature, a brightness feature, and a texture feature; segmenting the search area into a plurality of search sub-areas according to the first image feature based on a superpixel segmentation algorithm; and extracting a roughness feature value of each search sub-area based on an edge extraction algorithm.

[0019] In the embodiments of the present application, the rope area is determined according to the roughness feature value, including: determining a search sub-area in the search area with a roughness feature value greater than a preset feature value as a background area in the search area; setting a pixel value of each pixel contained in the background area as a preset pixel value to obtain a target search area corresponding to the search area; determining a gray value of each pixel contained in the target search area; and determining a region formed by a pixel point with a gray value greater than a preset gray value in the target search area as the rope area.

[0020] In the embodiments of the present application, the number of steel wire ropes in each rope sub-area is determined respectively, including: for each rope sub-area, obtaining an initial straight line in the rope sub-area through straight line fitting; screening the initial straight line according to a slope and a length characteristic of the initial straight line to determine a target straight line in the rope sub-area; for each rope sub-area, clustering the slopes of all target straight lines through a clustering algorithm to determine a number of straight line categories contained in the rope sub-area; and determining the number of straight line categories of each rope sub-area as the number of steel wire ropes of each rope sub-area.

[0021] The second aspect of the present application provides a processor configured to execute the steel wire rope ratio detection method described above.

[0022] The third aspect of the present application provides a steel wire rope ratio detection device, which is applied to a hoisting device, and includes:

[0023] an image acquisition device, which is installed at the end of an arm support of the hoisting device and is used to acquire an image of a hook of the hoisting device;

[0024] a processor configured to execute the steel wire rope ratio detection method described above.

[0025] The fourth aspect of the present application provides a hoisting device, including:

[0026] an arm support, which is used to perform a hoisting operation;

[0027] a pulley, which is connected with the arm support through a steel wire rope and is used to articulate the steel wire rope; and

[0028] a detection device configured to execute the steel wire rope ratio detection method described above.

[0029] The fifth aspect of the present application provides a machine readable storage medium, which stores instructions, and the instructions, when executed by a processor, cause the processor to be configured to perform the steel wire rope ratio detection method described above.

[0030] Through the above technical solution, the hook image is collected by the image acquisition device, and the fitting area of the pulley and the rope area of the steel wire rope in the hook image are extracted. The adjacent points of each rope sub-area and the outer contour are determined, and the pulley area is divided into a plurality of pulley sub-areas. The pulley sub-area corresponding to each rope sub-area can be determined, so that the pulley sub-area corresponding to each rope sub-area is found. Then, the number of steel wire ropes of each rope sub-area is calculated, and then the steel wire rope ratio of the hook device can be calculated according to the number of steel wire ropes of each rope sub-area and the rope sub-area corresponding to each pulley sub-area. Based on the image processing of the hook image, the contour finding in the complex scene of the hook is completed, and the detection of the steel wire rope ratio is completed. The automatic identification of the steel wire rope ratio can be realized, and the accuracy of the detection of the steel wire rope ratio is improved.

[0031] Other features and advantages of the embodiments of the present application will be described in detail in the following specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0032] The accompanying drawings are included to provide a further understanding of the embodiments of the present application, and constitute a part of the specification, and are used to explain the embodiments of the present application together with the following specific embodiments, but do not constitute a limitation of the embodiments of the present application. In the drawings:

[0033] Figure 1 A flowchart of a steel wire rope ratio detection method according to an embodiment of the present application is schematically shown;

[0034] Figure 2 A schematic diagram of a hook image according to an embodiment of the present application is schematically shown;

[0035] Figure 3 A schematic diagram of a pulley sub-area according to an embodiment of the present application is schematically shown;

[0036] Figure 4 A schematic diagram of a matching area according to an embodiment of the present application is schematically shown;

[0037] Figure 5 A schematic diagram of a search area according to an embodiment of the present application is schematically shown;

[0038] Figure 6a A schematic diagram of a superpixel segmentation process according to an embodiment of the present application is schematically shown;

[0039] Figure 6bSchematically illustrates a schematic diagram of edge extraction algorithm processing according to an embodiment of the present application;

[0040] Figure 6c A schematic diagram illustrating processing of roughness characteristic values ​​according to an embodiment of the present application is shown;

[0041] Figure 7a A schematic diagram of grayscale feature extraction processing according to an embodiment of the present application is schematically shown;

[0042] Figure 7b Schematically shows a schematic diagram of a rope area according to an embodiment of the present application;

[0043] Figure 8 The following schematically shows a structural block diagram of a device for detecting a wire rope ratio according to an embodiment of the present application;

[0044] Figure 9 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0045] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0046] Figure 1 The following schematically shows a flow chart of a method for detecting the wire rope ratio according to an embodiment of the present application. Figure 1 As shown, in one embodiment of the present application, a method for detecting a wire rope ratio is provided, which is applied to a hoisting device. The hoisting device includes a boom, and an image acquisition device is installed at the end of the boom. The detection method includes the following steps:

[0047] S102, acquiring an image of a hook of a lifting device through an image acquisition device, where the image of the hook includes a pulley and multiple connection points between the wire rope and the pulley.

[0048] The image acquisition device is any one of a camera, a video camera, a scanner, or other devices with a camera function (mobile phone, tablet computer, etc.). The image acquisition device is installed at the end of the boom to ensure that the captured hook image is clear and visible. The hook of the lifting equipment is often suspended on a wire rope with the help of a pulley block and other components. The processor can obtain the hook image of the lifting equipment based on the image acquisition device. Figure 2As shown, the hook image refers to an image including the pulley and the wire rope captured by the image capture device installed at the end of the boom.

[0049] S104: Determine the outer contour of the pulley, the fitting area where the pulley is located, and the rope area corresponding to the wire rope in the hook image, where the rope area includes a plurality of rope sub-areas.

[0050] S106, determining the number of steel wire ropes in each rope sub-area.

[0051] The fitting region is a regular shape with the smallest area that includes all pixels in the pulley area. Examples include a rectangle, circle, triangle, etc. The rope region is the area within the hook image where the wire ropes are located. Each wire rope has its own corresponding rope subregion, and each rope subregion contains at least one wire rope. The processor uses the hook image to determine the outer contour of the pulley, the fitting region where the pulley resides, and the rope region corresponding to the wire ropes, thereby determining the number of wire ropes in each rope subregion.

[0052] S108 , determining adjacent points corresponding to each rope sub-region, where adjacent points refer to pixels in the rope sub-region that are closest to the pixels corresponding to the outer contour of the pulley.

[0053] The pulley's outer contour is the boundary between the pulley area and the non-pulley area in the hook image, and is composed of multiple pixels. The rope sub-region also contains multiple pixels. For each rope sub-region, the processor calculates the distance between each pixel in that rope sub-region and the pixel corresponding to the outer contour. The pixel in the rope sub-region with the smallest distance is then determined as the neighboring point to the outer contour. Using this method, neighboring points within each rope sub-region can be found.

[0054] S110: Divide the fitting area into a plurality of pulley sub-areas.

[0055] The processor can divide the fitting area into multiple pulley sub-areas. The pulley has multiple wire rope connection areas. For example, Figure 2 As shown in the figure, the hook image captured by the image acquisition device shows three wire rope connection areas. Typically, wire ropes are wound around the upper and lower areas, and the number of wire ropes connected to the upper area is equal to the number of wire ropes connected to the lower area. However, in some cases, a single wire rope may be connected to the middle area. Assuming the fitting area is a rectangle, the rectangular area can be divided into three rectangular sub-areas: upper, middle, and lower.

[0056] S112: Determine the pulley sub-region where the adjacent point corresponding to the rope sub-region is located as the pulley sub-region corresponding to the rope sub-region.

[0057] The processor can determine, according to the pixel position of each neighboring point in the hook image, in which pulley sub-region the neighboring point is located. Then, the pulley sub-region is the pulley sub-region of the neighboring point. Then, the rope sub-region containing the neighboring point also corresponds to the pulley sub-region. It can be understood that, through the above process, it can be determined that the steel wire rope is wound out from which part of the pulley.

[0058] In S114, according to the correspondence between the rope sub-region and the pulley sub-region, and the number of steel wire ropes in each rope sub-region, the steel wire rope ratio of the hoisting device is determined.

[0059] The processor can determine the number of steel wire ropes in each rope sub-region. After determining the pulley sub-region corresponding to each rope sub-region, the number of rope sub-regions contained in each pulley sub-region can be determined. Then, the processor can determine the steel wire rope ratio of the hoisting device according to the number of steel wire ropes in the rope sub-region corresponding to each pulley sub-region. For example, the number of rope sub-regions corresponding to the pulley sub-region A is 2, wherein the rope sub-region a contains 3 steel wire ropes, and the rope sub-region b contains 4 steel wire ropes. Then, the number of steel wire ropes corresponding to the pulley sub-region A is 7. According to the 7 steel wire ropes corresponding to the pulley sub-region A, the steel wire rope ratio of the hoisting device can be further determined.

[0060] In one embodiment, before determining, as the pulley sub-region corresponding to the rope sub-region, the pulley sub-region in which the neighboring point corresponding to the rope sub-region is located, the method further comprises: obtaining the coordinate of the boundary endpoint of each pulley sub-region and the coordinate of the neighboring point; and determining, based on the coordinate of the boundary endpoint of each pulley sub-region and the coordinate of the neighboring point, the pulley sub-region in which the neighboring point is located by using the cross multiplication method.

[0061] The processor can obtain the coordinate of the endpoint of the fitting region and the coordinate of the neighboring point, and determine whether the neighboring point is in the fitting region by using the cross multiplication method. For example, the fitting region is a rectangular region, and the four endpoints of the rectangular region are A, B, C and D. The neighboring point is P. Specifically, the cross multiplication method is shown in the following formula (1):

[0062]

[0063] wherein, x A is the horizontal coordinate of the endpoint A of the fitting region, y A is the vertical coordinate of the endpoint A of the fitting region, y B is the vertical coordinate of the endpoint B of the fitting region, x B is the horizontal coordinate of the endpoint B of the fitting region, x C is the horizontal coordinate of the endpoint C of the fitting region, y C is the vertical coordinate of the endpoint C of the fitting region, x Dis a horizontal coordinate of an end point D of the fitting region, y D is a vertical coordinate of the end point D of the fitting region, x P is a horizontal coordinate of the adjacent point P, y P is a vertical coordinate of the adjacent point P, L1, L2, L3, L4 are intermediate constraint parameters of the cross multiplication method.

[0064] Since, when the rope region of the hook image is extracted through image processing, the region where the non-steel wire rope is located can be determined as the rope region. Only when L1 x L2 >= 0 and L3 x L4 >= 0 are satisfied at the same time, it can be determined that the adjacent point is in the fitting region. In this way, other parts of the image can be avoided from being circled as the rope region, and the calculation error of the steel wire rope multiplier can be reduced.

[0065] Further, in the case where it is determined that the adjacent point is in the fitting region, the processor can obtain the boundary end point coordinates of each pulley sub-region and the coordinates of the adjacent point, and determine the pulley sub-region where the adjacent point is located by using the cross multiplication method. Specifically, the processor can also use the calculation method of the cross multiplication method used in formula (1) to calculate which pulley sub-region the adjacent point is in.

[0066] In one embodiment, determining the steel wire rope multiplier of the hoisting device according to the correspondence between the rope sub-region and the pulley sub-region and the number of steel wire ropes of each rope sub-region includes: determining the number of steel wire ropes of each pulley sub-region according to the correspondence between the rope sub-region and the pulley sub-region and the number of steel wire ropes of each rope sub-region, respectively, wherein the plurality of pulley sub-regions include a first pulley sub-region, a second pulley sub-region, and a third pulley sub-region arranged in sequence along the radial direction of the pulley; and determining the steel wire rope multiplier of the hoisting device according to the sum of the maximum of the number of steel wire ropes of the first pulley sub-region and the number of steel wire ropes in the third pulley sub-region and twice and the number of steel wire ropes of the second pulley sub-region.

[0067] As shown in FIG. 1, the fitting region is a rectangular region, and the plurality of pulley sub-regions included in the rectangular region include a first pulley sub-region, a second pulley sub-region, and a third pulley sub-region. The three pulley sub-regions are divided into rectangular regions along the radial direction of the pulley. Moreover, each pulley sub-region shares two end points with adjacent pulley sub-regions. The end points of the first pulley sub-region are A, B, M, and N, the end points of the second pulley sub-region are M, N, G, and H, and the end points of the third pulley sub-region are G, H, C, and D. Figure 3 Specifically, the processor can divide the fitting region into a plurality of pulley sub-regions by calculating the end points of each pulley sub-region according to the four end points of the rectangular region through the following formula (2):

[0068]

[0069] ​

[0070] wherein x A denotes the abscissa of the end point A, y A denotes the ordinate of the end point A, y B denotes the ordinate of the end point B, x B denotes the abscissa of the end point B, x C denotes the abscissa of the end point C, y C denotes the ordinate of the end point C, x D denotes the abscissa of the end point D, y D denotes the ordinate of the end point D, x M denotes the abscissa of the end point A, y M denotes the ordinate of the end point M, x N denotes the abscissa of the end point N, y N denotes the ordinate of the end point N, x G denotes the abscissa of the end point G, y G denotes the ordinate of the end point G, x H denotes the abscissa of the end point H, y H denotes the ordinate of the end point H.

[0071] Further, the processor can determine the wire rope ratio of the hoisting device according to the number of wire ropes of each target pulley sub-region corresponding to the rope sub-region. Specifically, the processor can determine the number of wire ropes of each rope sub-region respectively, to determine the number of wire ropes of the target pulley sub-region corresponding to each rope sub-region. Then, according to the maximum value of the number of wire ropes in the first pulley sub-region and the third pulley sub-region, and the sum of the maximum value of the number of wire ropes and the number of wire ropes of the second pulley sub-region, the sum is taken as the wire rope ratio of the hoisting device. Wherein, the wire rope ratio of the hoisting device can be calculated according to formula (3) as follows:

[0072] N SUM = Max(N up , N down ) x 2 + N middle (3)

[0073] wherein N SUM denotes the wire rope ratio of the hoisting device, N up denotes the number of wire ropes of the first pulley sub-region, N down denotes the number of wire ropes of the second pulley sub-region, N middle denotes the number of wire ropes of the third pulley sub-region. Generally, the wire rope is symmetrical on both sides when it is threaded out of the pulley. If the wire rope is threaded out from the middle, it will interfere with the calculation of the wire rope ratio. However, through the above scheme, the wire rope ratio can be accurately calculated.

[0074] In one embodiment, determining the outer contour of the pulley in the hook image, the fitting area where the pulley is located, and the rope area corresponding to the wire rope includes: determining the matching area where the pulley is located from the hook image; determining the outer contour of the pulley in the matching area based on an image segmentation algorithm; performing minimum rectangle fitting on the outer contour of the pulley to obtain the fitting area where the pulley is located; wherein, determining the matching area where the pulley is located from the hook image includes at least one of the following: obtaining multiple template images of the pulley, matching the template images with the hook image to determine the matching area where the pulley is located; inputting the hook image into a deep learning model to determine the matching area where the pulley is located through the deep learning model.

[0075] Based on the hook image captured by the image acquisition device, the processor can determine the fitting area where the pulley is located in the hook image. First, a matching template library of pulleys can be constructed based on template images of various types of pulleys. According to the pulley used in the lifting operation, the template image of the corresponding matching template library is selected. The processor can match the hook image with the template image according to the nearest neighbor matching method (Flann algorithm) to select the matching area where the pulley is located in the hook image. Figure 4 As shown in the figure, by utilizing the differences in image features between the matching and non-matching areas in the hook image, the processor can extract the clear outline of the pulley through image segmentation algorithms (GrabCut algorithm) and fitting algorithms, completing accurate detection of the pulley's outer contour. The processor then fits a minimum bounding rectangle to the matching area based on the pulley's outer contour to determine the rectangle's four endpoints. Based on these four endpoints, the minimum rectangular area containing the area occupied by the outer contour is obtained.

[0076] In another embodiment, for the matching area and outer contour extraction steps, the processor can also build a lightweight deep learning model by training the feature data of multiple types of hook images. For example, the Yolov5 network model is lightweight and has a fast detection speed. The processor can input the image data of the hook image into the deep learning model to determine the matching area where the pulley is located through the deep learning model to complete the selection of the matching area. The GrabCut algorithm is then used to complete the extraction of the outer contour of the pulley. The network model trained with a large amount of data has better performance than traditional image processing algorithms.

[0077] In one embodiment, the outer contour of a pulley in a hook image, the fitting area where the pulley is located, and the rope area corresponding to the wire rope are determined, including: determining a target contour endpoint in a pixel corresponding to the outer contour; determining a first area where the wire rope is located based on the target contour endpoint; determining an area in the first area excluding the outer contour as a search area for the wire rope; extracting a roughness characteristic value of the search area; and determining the rope area based on the roughness characteristic value.

[0078] According to the hook image collected by the image collection device, the processor can determine the rope region corresponding to the steel wire rope in the hook image. Then, the processor can first determine the target contour endpoint of the pixel corresponding to the outer contour. After the position of the image collection device is fixed, the steel wire rope always appears in a certain direction in the hook image. In the coordinate system of the hook image, the outer contour corresponds to a plurality of pixels, and the target contour endpoint refers to the pixel whose absolute value of the sum of the horizontal coordinate and the vertical coordinate is the maximum or the minimum among the plurality of pixels corresponding to the outer contour, and is located at the opposite angle of the position of the steel wire rope. As shown in Figure 5 , the steel wire rope appears in the lower right of the hook image, and then the target contour endpoint is the leftmost contour left endpoint (O) in the hook image. Specifically, the processor can find the leftmost contour left endpoint (O) of the outer contour according to the following formula (4):

[0079] O(x O ,y O )=Min(x i +y j ),(x i ,y i )∈S hook (4)

[0080] wherein O refers to the leftmost contour left endpoint of the pixel occupied by the outer contour, (x O ,y O ) refers to the image coordinates of the leftmost contour left endpoint, (x i ,y i ) refers to the pixel coordinates of the i-th pixel occupied by the outer contour, and S hook refers to the pixel set of the pixel points occupied by the outer contour. Then, after traversing the pixel coordinates of all the pixel points of the outer contour, the pixel point with the minimum sum of the horizontal and vertical coordinates is taken as the leftmost contour left endpoint (O).

[0081] Further, the processor can determine the first region where the steel wire rope is located according to the target contour endpoint. For example, the processor can take the region between the leftmost contour left endpoint (O) and the lower right endpoint of the hook image as the first region. That is, as shown in Figure 5 the rectangular region at the lower right corner. Then, the region occupied by the outer contour in the first region is removed, and the remaining region is the search region of the steel wire rope. The search region refers to the ROI region of the steel wire rope in the hook image. That is, as shown in Figure 5 the white region at the lower right corner.

[0082] Furthermore, the processor can extract a roughness feature value from the search area. The roughness feature is a measure of the granularity of the image texture and can be represented by pixel values, i.e., the roughness feature value. The processor can then classify the search area based on the roughness feature value to distinguish between rope areas and background areas (non-rope areas).

[0083] In each search sub-region, the processor can determine the rope region in the search region based on the roughness characteristic value, retain the region with a roughness characteristic value greater than a preset characteristic value, and eliminate the non-rope region with a roughness characteristic value less than or equal to the preset characteristic value.

[0084] In one embodiment, extracting the roughness feature value of the search area includes: determining a first image feature of the search area, the first image feature including at least one of a color feature, a brightness feature, and a texture feature; based on a superpixel segmentation algorithm, dividing the search area into multiple search sub-areas according to the first image feature; and extracting the roughness feature value of each search sub-area based on an edge extraction algorithm.

[0085] The processor may determine a first image feature of the search area, where the first image feature includes at least one of a color feature, a brightness feature, and a texture feature. Figure 6a , using the superpixel segmentation method, the processor can divide the search area into several search sub-areas according to the first image feature. Figure 6b As shown, based on the edge extraction algorithm (canny operator), the edge of each search area is extracted to extract the roughness feature value of each search sub-area in the search area. Therefore, each search sub-area can be classified based on the roughness feature value.

[0086] In one embodiment, determining the rope area based on the roughness characteristic value includes: determining the search sub-area in the search area whose roughness characteristic value is greater than the preset characteristic value as the background area in the search area; setting the pixel value of each pixel contained in the background area to the preset pixel value to obtain a target search area corresponding to the search area; determining the grayscale value of each pixel contained in the target search area; and determining the area composed of pixel points in the target search area whose grayscale values ​​are greater than the preset grayscale value as the rope area.

[0087] The background area refers to the area in the hook image that does not contain a wire rope, that is, the non-rope area. The processor can determine the search sub-area in the search area whose roughness characteristic value is greater than the preset characteristic value as the background area in the search area. For each search sub-area, the roughness characteristic value refers to the sum of the pixel values ​​of all pixels in the search sub-area. Specifically, the processor can first determine the roughness characteristic values ​​of all pixels in each search sub-area, and the number of pixels n contained in each search area. For each search sub-area, the processor can calculate whether the sum of the pixel values ​​of all pixels therein is greater than the preset characteristic value. Among them, the preset characteristic value corresponds to the number of pixels n in each search sub-area, and can be set to 255n. Then, the background area can be determined according to the following formula (5):

[0088] ∑ n P n (x t ,y t ) / n>ε1 (5)

[0089] Among them, (x t ,y t ) refers to the pixel position of the t-th pixel in the search sub-region, n refers to the number of pixels in the search sub-region, P n (x t ,y t ) refers to the pixel value of the t-th pixel in the search sub-region, and ε1 is the pixel threshold, which can be set to 255. If the sum of the pixel values ​​of all pixels in the search sub-region is greater than 255n, the search sub-region is determined to be the background region.

[0090] Then, the processor can set the pixel value of each pixel contained in the background area to a preset pixel value to obtain a target search area corresponding to the search area. The preset pixel value can be 255. That is, after the pixel value of each pixel in the background area is set to 255, the color of each background area is white. Figure 6c The schematic diagram shown. Figure 6c The schematic diagram of processing the roughness characteristic value according to the embodiment of the present application is shown schematically. Through the above process, when searching for the rope area in the search area, the interference caused by the background area can be removed.

[0091] Furthermore, in the target search area, the processor may determine the grayscale value of each pixel in the target search area. Figure 7a Based on the adaptive threshold segmentation algorithm, the processor can extract the grayscale value of each pixel in the target search area. Pixels with grayscale values ​​greater than the preset grayscale value will be retained, and pixels with grayscale values ​​less than or equal to the preset grayscale value will be removed. Through the above process, the area formed by the retained pixels is determined as the rope area. Figure 7b As stated,Figure 7b A schematic diagram of a steel wire rope region according to an embodiment of the present application is shown schematically. Through the above scheme, the region of the steel wire rope in the hook image can be accurately extracted, so as to facilitate the subsequent calculation of the steel wire rope magnification.

[0092] In one embodiment, determining the number of steel wire ropes in each rope sub-region respectively comprises: for each rope sub-region, obtaining an initial straight line in the rope sub-region through straight line fitting; screening the initial straight line according to the slope and length characteristics of the initial straight line to determine a target straight line in the rope sub-region; for each rope sub-region, clustering the slopes of all target straight lines through a clustering algorithm to determine the number of straight line categories contained in the rope sub-region; and determining the number of straight line categories of each rope sub-region as the number of steel wire ropes in each rope sub-region.

[0093] Since there is a steel wire rope overlap phenomenon in a single rope sub-region, and considering the complexity of the image background region, the reinforcing bars and long strip shadows in the crane operating environment are easy to interfere with the detection of the steel wire rope. For each rope sub-region, the processor can obtain an initial straight line in the rope sub-region through straight line fitting. Specifically, the processor can use the Hough straight line fitting method according to the pixel points of each rope sub-region to find the fitted initial straight line in the steel wire rope sub-region. Since multiple initial straight lines are obtained for each steel wire rope sub-region, the target straight line of the rope sub-region needs to be extracted using the slope and length characteristics of the initial straight line. The target straight line can be one or more. Specifically, the following formula (6) can be used for calculation:

[0094] (6)

[0095] Wherein, (1 lines[i] ,1 lines[i] ) and (2 lines[i] ,2 lines[i] ) are the end point coordinates of the two end points of the i-th straight line of the rope sub-region through Hough straight line fitting, and ε3, ε4, and ε5 are preset constant values. L max is the long side of the rectangle obtained by fitting the rectangle of the steel wire rope sub-region.

[0096] Further, for each rope sub-region, the processor can cluster the slopes of all target straight lines through a clustering algorithm to determine the number of straight line categories contained in the rope sub-region. Then, the number of straight line categories of each rope sub-region is determined as the number of steel wire ropes in the rope sub-region.

[0097] For example, the clustering algorithm can be a DBSCAN clustering algorithm. First, Hough line fitting can be performed on each i-th rope sub-region. Then, N initial straight lines can be fitted in the i-th rope sub-region. According to the image coordinates of the two end points of each initial straight line, the slope of each initial straight line can be obtained where n refers to the number of the initial straight line in the i-th rope sub-region. The slopes of all initial straight lines in the i-th rope sub-region are counted as the input data of clustering. Wherein, ε refers to a custom threshold value used to increase the difference between data in the clustering algorithm. The number of straight line categories in the i-th rope sub-region can be obtained by the DBSCAN clustering algorithm, and the number of straight line categories is taken as the detection result of the number of straight lines. Then, the number of straight lines in each rope sub-region, i.e., the steel wire rope ratio of the i-th rope sub-region.

[0098] In an embodiment, for each rope sub-region, the processor can calculate the distance between each pixel point in the rope sub-region and the pixel point corresponding to the outer contour. Then, the pixel point of the rope sub-region corresponding to the minimum distance is determined as the adjacent point adjacent to the outer contour. At the same time, the adjacent point can be found out the adjacent point in each rope sub-region. Specifically, the adjacent point can be determined according to the following formula (7):

[0099]

[0100]

[0101] where (x hook ,y hook ) represents a point on the pixel set S hook occupied by the outer contour of the hook region, the pixel coordinates of the point of the i-th rope sub-region W i , dis i represents the minimum distance between the pixel points of the i-th rope sub-region and the outer contour. Further, when dis i > ε2, the point corresponding to the minimum distance is determined as a pseudo-contour and is excluded. When dis i ≤ ε2, the point is retained as the adjacent point of the i-th rope sub-region, and ε2 is a distance threshold value.

[0102] ​Using the above technical solution, an image acquisition device is installed at the end of the boom to capture an image of the lifting equipment hook. A template image from a matching template library is matched with the hook image, and a matching area containing the pulley is selected. Using image segmentation and fitting algorithms, a clear outer contour of the pulley in the matching area can be accurately extracted. A minimum circumscribed rectangle is fitted to the outer contour to obtain the minimum rectangular area within which the outer contour resides. This rectangular area is then divided into a first pulley sub-area, a second pulley sub-area, and a third pulley sub-area. The first region containing the wire rope is determined based on the target contour endpoints within the outer contour. The area within the first region, excluding the outer contour, is then defined as the search area for the wire rope. Furthermore, using superpixel segmentation, the image is processed using first image features such as color, brightness, and texture to segment the search area into several search sub-regions. The search sub-regions are classified based on their roughness feature value and number of pixels, thereby identifying the background region within the search area. The pixel value of each pixel in the background region is set to 255. An adaptive threshold segmentation algorithm determines the grayscale value of each pixel, eliminating the background area within the search region and extracting the rope region where the wire rope resides. This process removes the complex background from the hook image, accurately extracting the wire rope region and facilitating subsequent calculation of the wire rope ratio. For each rope subregion within the rope region, Hough linear fitting and the DBSCAN clustering algorithm are used to calculate the number of wire ropes within each subregion. This method can identify overlapping wire ropes and partially eliminate background interference, ensuring the accuracy of the final wire rope ratio detection. For each rope subregion, the distance between the pixel corresponding to the outer contour and the pixel in the rope subregion is calculated to identify the point with the smallest distance as the neighboring point. A cross multiplication method is then used to determine whether the neighboring point is within the fitting region, verifying that the rope subregion corresponding to the neighboring point is the true rope subregion. The cross multiplication method is then used to determine the pulley subregion where the neighboring point resides, thereby determining the pulley subregion corresponding to the rope subregion corresponding to the neighboring point. In this way, each rope sub-region can be divided into corresponding pulley sub-regions. The number of wire ropes in each rope sub-region is determined separately to determine the wire rope ratio of the target pulley sub-region corresponding to each rope sub-region. The maximum number of wire ropes in the first and third pulley sub-regions, plus the sum of the number of wire ropes in the second pulley sub-region, is then used as the wire rope ratio of the hoisting equipment. By dividing the fitting area into three pulley sub-regions, the accuracy of the ratio detection and the applicability of the algorithm can be improved. This effectively solves the problem of inaccurate wire rope ratio detection results caused by wire rope overlap and background interference.

[0103] Figure 1FIG. 1 is a flow chart of a method for detecting a wire rope ratio in one embodiment. It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0104] Figure 8 The following schematically shows a flow chart of a method for detecting the wire rope ratio according to an embodiment of the present application. Figure 8 As shown, in one embodiment of the present application, a wire rope multiplier detection device 800 is provided. The detection device is applied to a hoisting device. The detection device 800 includes:

[0105] The image acquisition device 810 is installed at the end of the boom of the lifting equipment and is used to acquire images of the hook of the lifting equipment.

[0106] Processor 820 is configured to execute the above-mentioned method for detecting the wire rope ratio. After acquiring the hook image of the lifting equipment through the image acquisition device, the fitting area where the pulley is located and the rope area corresponding to the wire rope in the hook image are determined. Then, based on the number of wire ropes in each rope sub-area in the rope area, the adjacent points of each rope sub-area and the outer contour of the pulley in the hook image are determined. Then, the processor can divide the fitting area into multiple pulley sub-areas, determine the target pulley sub-area where each adjacent point is located, and determine the target pulley sub-area corresponding to each rope sub-area. Then, the processor can determine the wire rope ratio of the lifting equipment based on the number of wire ropes in the rope sub-area corresponding to each target pulley sub-area.

[0107] In one embodiment, a lifting device is provided, comprising:

[0108] Boom, used to perform lifting operations.

[0109] The pulley is connected to the boom through a wire rope and is used to articulate the wire rope.

[0110] The detection device includes an image acquisition device and a processor. The image acquisition device is installed at the end of the boom of the lifting equipment and is used to capture images of the hook of the lifting equipment. The processor is configured to execute the above-mentioned wire rope ratio detection method.

[0111] Specifically, the processor can acquire a hook image of a hoisting device through an image acquisition device, the hook image including a pulley and a steel wire rope. A plurality of template images of the pulley are acquired, the template images are matched with the hook image to determine a matching region where the pulley is located; or the hook image is input into a deep learning model to determine the matching region where the pulley is located through the deep learning model. An outer contour of the pulley in the matching region is determined through an image segmentation algorithm and a fitting algorithm. The matching region is fitted according to the outer contour to determine a fitting region containing the outer contour. The fitting region is determined as the fitting region where the pulley is located in the hook image. A target contour endpoint in pixels corresponding to the outer contour is determined, a region in a first region corresponding to the target contour endpoint and occupied by the outer contour is removed, and a search region of the steel wire rope is determined. A first image feature of the search region is determined, the first image feature including at least one of a color feature, a brightness feature and a texture feature. The search region is segmented into a plurality of search sub-regions according to the first image feature based on a superpixel segmentation algorithm. A roughness feature value of each search sub-region is extracted based on an edge extraction algorithm. A search sub-region in the search region with a roughness feature value greater than a preset feature value is determined as a background region in the search region; a pixel value of each pixel contained in the background region is set as a preset pixel value to obtain a target search region corresponding to the search region; a gray value of each pixel contained in the target search region is determined; and a region formed by pixel points with a gray value greater than a preset gray value in the target search region is determined as a rope region. The rope region includes a plurality of rope sub-regions, a neighboring point of each rope sub-region and the outer contour of the pulley in the hook image is determined, the neighboring point being a pixel point closest to the pixel point corresponding to the outer contour in the rope sub-region. The fitting region is divided into a plurality of pulley sub-regions, the fitting region being a rectangular region, boundary endpoint coordinates of each pulley sub-region and coordinates of the neighboring point are acquired; the neighboring point is determined to be in a pulley sub-region based on the boundary endpoint coordinates of each pulley sub-region and the coordinates of the neighboring point by using a cross multiplication method. In a case where the neighboring point is determined to be in the fitting region, the pulley sub-region where the neighboring point is located is determined as a target pulley sub-region of the neighboring point. Also, the target pulley sub-region can be determined as a target pulley sub-region corresponding to each rope sub-region. The number of steel wire ropes of each pulley sub-region is determined according to a corresponding relationship between the rope sub-region and the pulley sub-region and the number of steel wire ropes of each rope sub-region, wherein the plurality of pulley sub-regions include a first pulley sub-region, a second pulley sub-region and a third pulley sub-region arranged in sequence along a radial direction of the pulley. For each rope sub-region, an initial straight line where each steel wire rope in the rope sub-region is located is determined. For each rope sub-region, the slopes of all the initial straight lines are clustered through a clustering algorithm to determine the number of straight line categories contained in the rope sub-region. The number of straight line categories of each rope sub-region is determined as the number of steel wire ropes of each rope sub-region. Then, the steel wire rope ratio of the target pulley sub-region corresponding to each rope sub-region is determined.The steel wire ratio of the hoisting device is determined according to the maximum value of the number of steel wires in the first pulley sub-area and twice the number of steel wires in the third pulley sub-area and the number of steel wires in the second pulley sub-area. Based on image processing of the hook image, contour finding in the complex scene of the hook, the detection of the steel wire ratio is completed. The automatic identification of the steel wire ratio can be realized, and the accuracy of the steel wire ratio detection is improved.

[0112] The processor includes a core, and the core retrieves corresponding program units in the memory. The core can be one or more, and the detection method of the steel wire ratio is realized by adjusting the core parameters.

[0113] The memory can include a non-permanent memory in a computer readable medium, a random access memory (RAM) and / or a non-volatile memory such as a read-only memory (ROM) or a flash memory (flash RAM), and the memory includes at least one memory chip.

[0114] The embodiment of the application provides a storage medium having a program stored thereon, and the program is executed by a processor to realize the detection method of the steel wire ratio.

[0115] The embodiment of the application provides a processor for running a program, wherein the program is executed to perform the detection method of the steel wire ratio.

[0116] In one embodiment, a computer device can be provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 9 The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected through a system bus. The processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02 and a database (not shown in the figure). The internal memory A03 provides an environment for the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store the detection data of the steel wire ratio. The network interface A02 of the computer device is used to communicate with the external terminal through the network connection. The computer program B02 is executed by the processor A01 to realize a detection method of the steel wire ratio.

[0117] Those skilled in the art can understand that, Figure 9The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0118] The embodiment of the present application provides a device, which comprises a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps of the steel wire rope magnification detection method are implemented.

[0119] The present application also provides a computer program product adapted to execute the program of the steps of the steel wire rope magnification detection method when executed on a data processing device.

[0120] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage media, etc.) containing computer-usable program code.

[0121] The present application is described with reference to flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device implemented in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the function specified by one or more blocks

[0122] These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction means, which implements the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the function specified by one or more blocks

[0123] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 Figure 1

[0124] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0125] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the processor can execute instructions. The memory can also include non-volatile memory, such as read only memory (ROM), electrically programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), erasable programmable read only memory (EPROM), flash memory, or a combination of non-volatile memories in different types. The memory can also include a compact disk read only memory (CD-ROM), digital versatile disk (DVD), Blu-ray, or another non-transitory computer readable medium, which is non-volatile and non-transitory in nature, but volatile in that it can lose its content if the power to the computer is turned off or if the computer crashes. The memory is an example of a computer readable medium.

[0126] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD), or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer readable media does not include transitory media such as modulated data signals and carriers.

[0127] It should also be noted that the terms "comprising," "including," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements recited, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0128] ​​The above merely provides an example of the present application, and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall fall into the scope of claims of the present application.

Claims

1. A method for detecting the ratio of a wire rope, characterized in that: The detection method is applied to a hoisting device, wherein the hoisting device includes a boom, and an image acquisition device is installed at the end of the boom. The detection method includes: Acquire a hook image of the lifting equipment by the image acquisition device, wherein the hook image includes a pulley and a wire rope; Determine an outer contour of the pulley, a fitting area where the pulley is located, and a rope area corresponding to the wire rope in the hook image, wherein the rope area includes a plurality of rope sub-areas; Determine the number of wire ropes for each rope sub-area separately; Determine adjacent points corresponding to each rope sub-region, where the adjacent points are pixels in the rope sub-region that are closest to the pixels corresponding to the outer contour of the pulley; dividing the fitting area into a plurality of pulley sub-areas; Determine the pulley sub-region where the adjacent point corresponding to the rope sub-region is located as the pulley sub-region corresponding to the rope sub-region; The wire rope ratio of the hoisting equipment is determined according to the corresponding relationship between the rope sub-areas and the pulley sub-areas, and the number of steel ropes in each rope sub-area.

2. The method for detecting the wire rope ratio according to claim 1, characterized in that: Before determining the pulley sub-region where the adjacent point corresponding to the rope sub-region is located as the pulley sub-region corresponding to the rope sub-region, the method further includes: Obtaining the coordinates of the boundary endpoints of each pulley sub-area and the coordinates of the adjacent points; Based on the coordinates of the boundary endpoints of each pulley sub-region and the coordinates of the adjacent points, the pulley sub-region where the adjacent points are located is determined by using a cross multiplication method.

3. The method for detecting the wire rope ratio according to claim 1, characterized in that: Determining the wire rope ratio of the hoisting equipment according to the correspondence between the rope sub-areas and the pulley sub-areas and the number of wire ropes in each rope sub-area includes: Determining the number of steel ropes in each pulley sub-area according to the correspondence between the rope sub-areas and the pulley sub-areas and the number of steel ropes in each rope sub-area, wherein the plurality of pulley sub-areas include a first pulley sub-area, a second pulley sub-area, and a third pulley sub-area sequentially arranged along the radial direction of the pulley; The wire rope ratio of the hoisting equipment is determined according to the sum of twice the maximum value of the number of wire ropes in the first pulley sub-area and the number of wire ropes in the third pulley sub-area and the number of wire ropes in the second pulley sub-area.

4. The method for detecting the wire rope ratio according to claim 1, characterized in that: Determining the outer contour of the pulley, the fitting area where the pulley is located, and the rope area corresponding to the wire rope in the hook image includes: Determine a matching area where the pulley is located from the hook image; determining an outer contour of the pulley in the matching area based on an image segmentation algorithm; Performing minimum rectangle fitting on the outer contour of the pulley to obtain a fitting area where the pulley is located; Wherein, determining the matching area where the pulley is located from the hook image includes at least one of the following: Acquire multiple template images of the pulley, and match the template images with the hook image to determine a matching area where the pulley is located; The hook image is input into a deep learning model to determine a matching area where the pulley is located through the deep learning model.

5. The method for detecting the wire rope ratio according to claim 4, characterized in that: The determining of the outer contour of the pulley, the fitting area where the pulley is located, and the rope area corresponding to the wire rope in the hook image includes: Determining target contour endpoints in pixels corresponding to the outer contour; Determine a first area where the steel wire rope is located according to the target contour endpoint; Determine the area in the first area except the area enclosed by the outer contour of the pulley as the search area corresponding to the steel wire rope; Extracting the roughness characteristic value of the search area; The rope area is determined based on the roughness characteristic value.

6. The method for detecting the wire rope ratio according to claim 5, characterized in that: The extracting the roughness characteristic value of the search area includes: Determining a first image feature of the search area, where the first image feature includes at least one of a color feature, a brightness feature, and a texture feature; Based on a superpixel segmentation algorithm, dividing the search area into a plurality of search sub-areas according to the first image feature; The roughness characteristic value of each search sub-region is extracted based on the edge extraction algorithm.

7. The method for detecting the wire rope ratio according to claim 6, characterized in that: Determining the rope area according to the roughness characteristic value includes: Determine a search sub-region in the search region whose roughness characteristic value is greater than a preset characteristic value as a background region in the search region; Setting the pixel value of each pixel included in the background area to a preset pixel value to obtain a target search area corresponding to the search area; Determine the grayscale value of each pixel contained in the target search area; The area formed by the pixel points whose grayscale values ​​in the target search area are greater than the preset grayscale value is determined as the rope area.

8. The method for detecting the wire rope ratio according to claim 1, characterized in that: Determining the number of steel wire ropes in each rope sub-area includes: For each rope sub-region, obtaining an initial straight line in the rope sub-region by straight line fitting; screening the initial straight lines according to the slope and length characteristics of the initial straight lines to determine a target straight line in the rope sub-area; For each rope sub-region, clustering the slopes of all target straight lines using a clustering algorithm to determine the number of straight line categories contained in the rope sub-region; The number of straight line categories in each rope sub-region is determined as the number of steel wire ropes in each rope sub-region.

9. A processor, characterized in that: The method is configured to perform the method for detecting the wire rope ratio according to any one of claims 1 to 8.

10. A wire rope ratio detection device, characterized in that: The detection device is applied to hoisting equipment, and the detection device includes: an image acquisition device, mounted at the end of the boom of the hoisting device, for acquiring an image of the hook of the hoisting device; and The processor of claim 9.

11. A hoisting device, characterized in that: include: Boom, used to perform lifting operations; a pulley connected to the arm via a steel wire rope and used for articulating the steel wire rope; as well as The wire rope ratio detection device as claimed in claim 10.

12. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the method for detecting the wire rope ratio according to any one of claims 1 to 8.

Images