Wire rope disorder detection method, device, computer equipment and storage medium

Abstract

The present application relates to a method, device, computer equipment and storage medium for detecting disordered wire ropes. The method comprises: extracting brightness signal data corresponding to a predetermined wire rope area to be detected from a monitoring image of a wire rope operation site, and performing edge extraction on the pre-processed brightness signal data to obtain contour image data corresponding to the wire rope area to be detected. Delete isolated points in a binary image corresponding to the contour image data, generate a corresponding connected area to be detected, and perform statistics on the connected area to be detected. When it is determined that the number of boundary segments in the binary image of each connected area to be detected is greater than a preset value, the area points in the connected area to be detected whose width is greater than the preset wire rope width and forked towards both ends are determined as disordered rope areas. The present method can directly analyze and count the contour image data and identify the area, simplify the identification operation process, and improve the efficiency of identifying disordered ropes in the monitoring image of the wire rope operation site.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device, computer equipment and storage medium for detecting tangled wire ropes. Background Art

[0002] With the development of image processing technology and the widespread use of tower cranes in construction projects, the phenomenon of rope tangling is common in the working process of tower cranes. Among them, the phenomenon of rope tangling is the main reason for the rapid wear, deformation and structural damage of wire ropes. When the wear and wire breakage of wire ropes reach a certain level, the wire ropes will be scrapped and need to be replaced with new ones, which increases the operation cost and maintenance cost of the machinery. If the new wire ropes are not replaced in time and accidents occur, it will directly affect personal safety.

[0003] In order to know the actual situation of the wire rope in time, it is necessary to identify the tangled wire rope on the tower crane drum. At present, the identification of the tangled wire rope condition of the tower crane drum mainly relies on manual direct inspection or manual judgment through video monitoring. Usually, due to the negligence of the operator, the tangled wire rope condition cannot be eliminated in time, which easily leaves a major safety hazard to the construction project.

[0004] Therefore, the current method of direct manual on-site inspection or manual judgment based on surveillance videos has a high degree of manual reliance. Once the operator is negligent, it is easy to cause safety hazards and accidents, and the recognition efficiency is not high enough. Summary of the invention

[0005] Based on this, it is necessary to provide a wire rope tangled rope detection method, device, computer equipment and storage medium that can improve the efficiency of wire rope tangled rope identification in order to solve the above-mentioned technical problems.

[0006] A method for detecting disordered wire ropes, the method comprising:

[0007] Extracting brightness signal data corresponding to a predetermined wire rope area to be detected from a monitoring image of a wire rope operation site;

[0008] Preprocessing the brightness signal data;

[0009] Performing edge extraction on the preprocessed brightness signal data to obtain contour image data corresponding to the steel wire rope area to be detected;

[0010] Binarizing the contour image data to obtain a corresponding binary image;

[0011] Deleting isolated points in the binary image to generate corresponding connected regions to be detected;

[0012] Statistical analysis is performed on each of the connected areas to be detected. When it is determined that the number of boundary segments in the binary image of each of the connected areas to be detected is greater than a preset value, the area points in the connected area to be detected whose width is greater than the preset wire rope width and forked towards both ends are determined as tangled rope areas.

[0013] In one embodiment, the binarization of the contour image data to obtain a corresponding binary image includes:

[0014] Acquire edge lines of the contour image data;

[0015] Taking the edge line as the boundary, counting the grayscale gradient distribution of the contour image data;

[0016] According to the grayscale gradient distribution, a corresponding binary grayscale threshold is determined; the binary grayscale threshold corresponds to the wire rope and the gap respectively;

[0017] According to the binary grayscale threshold, the contour image data is subjected to binary filling processing to generate a corresponding binary image.

[0018] In one embodiment, the step of extracting brightness signal data corresponding to a predetermined wire rope area to be detected from a monitoring image of a wire rope operation site includes:

[0019] Performing sharpness enhancement processing on the monitoring image of the wire rope operation site;

[0020] Acquire a predetermined area parameter of the wire rope area to be detected; the area parameter includes an area size and a data signal type, and the data signal type includes a brightness signal;

[0021] According to the size of the area, performing area scaling processing on the surveillance image of the wire rope operation site after the sharpness enhancement processing;

[0022] According to the data signal type, the brightness signal data corresponding to the predetermined wire rope area to be detected is extracted from the monitoring image of the wire rope operation site after scaling processing.

[0023] In one embodiment, preprocessing the brightness signal data includes:

[0024] Get the pre-configured filter template;

[0025] Performing Gaussian filtering on the brightness signal data according to the filtering template;

[0026] Histogram statistics are performed on the brightness signal data after Gaussian filtering to generate grayscale distribution of the brightness signal data.

[0027] In one embodiment, the edge extraction is performed on the pre-processed brightness signal data to obtain the contour image data corresponding to the wire rope area to be detected, including:

[0028] Determining high and low grayscale thresholds of an edge extraction operator according to the grayscale distribution of the brightness signal data;

[0029] The edge extraction operator with determined high and low grayscale thresholds is used to perform edge extraction on the brightness signal data after Gaussian filtering to obtain contour image data corresponding to the wire rope area to be detected.

[0030] In one embodiment, performing binary filling processing on the contour image data according to the binary grayscale threshold to generate a corresponding binary image includes:

[0031] The area with a grayscale value less than the binary grayscale threshold and whose gradient increases toward the edge line is filled with a first preset value, and the area with a grayscale value greater than the binary grayscale threshold and whose gradient decreases toward the edge line and whose gradient increases away from the edge line is filled with a second preset value, to generate a binary image corresponding to the contour image data; the first preset value corresponds to the wire rope, and the second preset value corresponds to the gap.

[0032] In one embodiment, the method further comprises:

[0033] Merging the adjacent chaotic rope areas to obtain a corresponding abnormal area collection;

[0034] Displaying the abnormal area collection on a display device;

[0035] Output the warning prompt information generated according to the abnormal area collection.

[0036] A wire rope disorder detection device, the device comprising:

[0037] A brightness signal data extraction module is used to extract brightness signal data corresponding to a predetermined wire rope area to be detected from a monitoring image of a wire rope operation site;

[0038] A preprocessing module, used for preprocessing the brightness signal data;

[0039] A contour image data generating module, used for performing edge extraction on the pre-processed brightness signal data to obtain contour image data corresponding to the steel wire rope area to be detected;

[0040] A binarization processing module, used for performing binarization processing on the contour image data to obtain a corresponding binary image;

[0041] A connected region generation module to be detected, used to delete isolated points in the binary image and generate corresponding connected regions to be detected;

[0042] The module for determining the tangled rope area is used to perform statistical analysis on each of the connected areas to be detected. When it is determined that the number of boundary segments in the binary image of each of the connected areas to be detected is greater than a preset value, the area points in the connected area to be detected with a width greater than a preset wire rope width and forked towards both ends are determined as tangled rope areas.

[0043] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0044] Extracting brightness signal data corresponding to a predetermined wire rope area to be detected from a monitoring image of a wire rope operation site;

[0045] Preprocessing the brightness signal data;

[0046] Performing edge extraction on the preprocessed brightness signal data to obtain contour image data corresponding to the steel wire rope area to be detected;

[0047] Binarizing the contour image data to obtain a corresponding binary image;

[0048] Deleting isolated points in the binary image to generate corresponding connected regions to be detected;

[0049] Statistical analysis is performed on each of the connected areas to be detected. When it is determined that the number of boundary segments in the binary image of each of the connected areas to be detected is greater than a preset value, the area points in the connected area to be detected whose width is greater than the preset wire rope width and forked towards both ends are determined as tangled rope areas.

[0050] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0051] Extracting brightness signal data corresponding to a predetermined wire rope area to be detected from a monitoring image of a wire rope operation site;

[0052] Preprocessing the brightness signal data;

[0053] Performing edge extraction on the preprocessed brightness signal data to obtain contour image data corresponding to the steel wire rope area to be detected;

[0054] Binarizing the contour image data to obtain a corresponding binary image;

[0055] Deleting isolated points in the binary image to generate corresponding connected regions to be detected;

[0056] Statistical analysis is performed on each of the connected areas to be detected. When it is determined that the number of boundary segments in the binary image of each of the connected areas to be detected is greater than a preset value, the area points in the connected area to be detected whose width is greater than the preset wire rope width and forked towards both ends are determined as tangled rope areas.

[0057] The above-mentioned wire rope disorder detection method, device, computer equipment and storage medium extract the brightness signal data corresponding to the predetermined wire rope area to be detected from the monitoring image of the wire rope operation site, and pre-process the brightness signal data. By performing edge extraction on the pre-processed brightness signal data, the contour image data corresponding to the wire rope area to be detected is obtained, and the contour image data is binarized to obtain the corresponding binary image, and then the isolated points in the binary image are deleted to generate the corresponding connected area to be detected. By performing statistical analysis on each connected area to be detected, when it is determined that the number of boundary segments in the binary image of each connected area to be detected is greater than a preset value, the area points in the connected area to be detected whose width is greater than the preset wire rope width and forked towards both ends are determined as disordered rope areas. It realizes direct analysis, statistics and area recognition of contour image data obtained according to brightness signal data, without relying on models trained according to a large amount of sample image data for recognition, avoiding the problem of low recognition success probability due to insufficient sample data in traditional recognition methods, and has good adaptability to changes in environmental brightness. At the same time, on the basis of simplifying the recognition operation process, it further improves the efficiency of tangled rope recognition in monitoring images of wire rope operation sites. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 Schematic diagram of the application environment of a method for detecting tangled wire ropes in one embodiment;

[0059] Figure 2 A schematic diagram of a process of detecting a wire rope disorder in one embodiment;

[0060] Figure 3 A schematic diagram of a filter template for detecting a wire rope disorder in an embodiment;

[0061] Figure 4 A schematic diagram of a Gaussian filter processing result of brightness signal data in one embodiment;

[0062] Figure 5 Schematic diagram of a connected area to be detected in a method for detecting tangled wire ropes in one embodiment;

[0063] Figure 6 A schematic diagram of the detection result of a wire rope disorder detection method in one embodiment;

[0064] Figure 7 A schematic diagram of a flow chart of a method for detecting a disordered wire rope in another embodiment;

[0065] Figure 8 1 is a structural block diagram of a wire rope disorder detection device in one embodiment;

[0066] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0068] The wire rope tangled rope detection method provided in this application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. By extracting the brightness signal data corresponding to the predetermined wire rope area to be detected from the monitoring image of the wire rope operation site, and preprocessing the brightness signal data. Among them, the monitoring image of the wire rope operation site can be stored locally in the terminal 102. Considering the small local storage capacity, it can also be uploaded to the cloud storage of the server 104. When it is necessary to detect the disordered rope, the corresponding monitoring image of the wire rope operation site is obtained from the cloud storage of the server 104. By performing edge extraction on the preprocessed brightness signal data, the contour image data corresponding to the wire rope area to be detected is obtained, and the contour image data is binarized to obtain the corresponding binary image, and then the isolated points in the binary image are deleted to generate the corresponding connected area to be detected. By performing statistical analysis on each connected area to be detected, when it is determined that the number of boundary segments in the binary image of each connected area to be detected is greater than the preset value, the area points in the connected area to be detected whose width is greater than the preset wire rope rope width and forked towards both ends are determined as disordered rope areas. The determined tangled rope area can be displayed on a display device set on the terminal 102. The terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones and tablet computers, and the server 104 can be implemented as an independent server or a server cluster composed of multiple servers.

[0069] In one embodiment, Figure 2 As shown, a method for detecting disordered wire ropes is provided, and the method is applied to Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0070] Step S202: extracting brightness signal data corresponding to a predetermined wire rope area to be detected from the monitoring image of the wire rope operation site.

[0071] When performing the tangled rope detection operation for the first time, the staff needs to install the equipment and pre-set the area parameters of the wire rope area to be detected, including the area size, data signal type and preset wire rope width. The signal data type indicates that the signal data that needs to be paid attention to during the tangled rope detection operation is the brightness signal data.

[0072] Specifically, the edge contrast of the monitoring image of the wire rope operation site is improved by performing sharpness enhancement processing on the monitoring image of the wire rope operation site. Then, by obtaining the predetermined area size of the wire rope area to be detected, the monitoring image of the wire rope operation site after the sharpness enhancement processing is performed on the area scaling processing to extract the wire rope area to be detected that meets the area size requirements.

[0073] Furthermore, according to the predetermined data signal type, corresponding brightness signal data is extracted from the monitoring image of the wire rope operation site after scaling, that is, from the wire rope area to be detected that meets the area size requirement.

[0074] In one embodiment, the chip that performs the tangled rope detection operation is set with a processing capacity limit. Taking the maximum pixel value of the area that the chip can process as 720 high and 640 wide as an example, when the wire rope selection area does not exceed the processing capacity of 720 wide and 640 high, there is no need to perform a scaling operation, and the next operation can be performed directly. If the width exceeds 720, the width is scaled to 720, and if the height exceeds 640, the height is scaled to 640, so that the selected area meets the preset area size.

[0075] Step S204: pre-process the brightness signal data.

[0076] Specifically, a pre-configured filter template is obtained, and the brightness signal data is filtered according to the filter template, and histogram statistics are performed on the brightness signal data after the Gaussian filter processing to generate the grayscale distribution of the brightness signal data.

[0077] Among them, the pre-configured Figure 3 The 5X5 filter template shown in the figure performs filtering on the brightness signal data to eliminate some noise of the brightness signal data, and obtains the following Figure 4 The brightness signal data after Gaussian filtering is shown.

[0078] In one embodiment, the statistical result of the histogram statistical operation is calculated using the following formula (1):

[0079]

[0080] Among them, I(i,j) represents the input brightness signal data after Gaussian filtering, I out (x) represents the histogram statistics, that is, the grayscale distribution of the brightness signal data. Gaussian filtering represents the process of weighted averaging of the entire image. The value of each pixel is obtained by weighted averaging the value of itself and other pixels in the neighborhood.

[0081] Furthermore, the grayscale histogram statistics represent the frequency of occurrence of all pixels in the digital image according to the size of the grayscale value. The grayscale histogram is a function of grayscale, which represents the number of pixels with a certain grayscale in the image, and reflects the frequency of occurrence of a certain grayscale in the image. In this embodiment, the grayscale statistics of the brightness signal data are performed using the histogram, that is, the number of pixels occupied by each grayscale in the input brightness signal data is counted respectively, and the total number of points with a grayscale value of 0 and a grayscale value of 1 in the brightness signal data is determined, and the grayscale value is counted in sequence until it reaches 255. In the statistical results, the statistical values ​​of the wire rope area and the gap area are relatively concentrated. Since the grayscale value of the wire rope is higher and the grayscale value of the gap is lower, the corresponding low grayscale value concentrated area center and high grayscale value concentrated center can be obtained. Among them, the low grayscale threshold is the difference between the low grayscale center and the high and low grayscale centers, and the high grayscale threshold is the difference between the high grayscale center and the low grayscale center.

[0082] Step S206, performing edge extraction on the pre-processed brightness signal data to obtain contour image data corresponding to the wire rope area to be detected.

[0083] Specifically, according to the grayscale distribution of the brightness signal data, the high and low grayscale thresholds of the edge extraction operator are determined, and the edge extraction operator with the determined high and low grayscale thresholds is used to perform edge extraction on the brightness signal data after Gaussian filtering to obtain contour image data corresponding to the wire rope area to be detected.

[0084] Furthermore, in this embodiment, the canny edge extraction algorithm is used to extract the edge of the brightness signal data. Specifically, based on the grayscale distribution of the brightness signal data, the high and low grayscale thresholds of the canny edge extraction operator are determined, and the edge extraction operator with the determined high and low grayscale thresholds is used to extract the edge of the brightness signal data after Gaussian filtering, and the edge contour points of the input image, i.e., the brightness signal data, are determined, and each edge contour point is connected to generate the contour image data corresponding to the wire rope area to be detected. Among them, edge detection operators such as the Sobel operator and the Laplacian operator can also be used to realize the edge extraction of the brightness signal data.

[0085] Step S208, binarizing the contour image data to obtain a corresponding binary image.

[0086] Specifically, by obtaining the edge line of the contour image data, and taking the edge line as the boundary, the grayscale gradient distribution of the contour image data is statistically analyzed, and then the corresponding binary grayscale threshold is determined according to the grayscale gradient distribution, and further according to the binary grayscale threshold, the contour image data is binary filled to generate the corresponding binary image. Among them, the binary grayscale thresholds correspond to the wire rope and the gap respectively.

[0087] Among them, the Canny edge extraction algorithm extracts an edge map, which is a white contour map. It is necessary to fill in a new binary image based on the obtained white contour map. Among them, the binary image represents that the brightness value has only two states: black (0) and white (255). The image is marked by two states of black and white. In this embodiment, the white area of ​​the binary image represents the wire rope, and the black area represents the gap. The basis for filling the white contour map is to calculate the grayscale change of the original input image at the contour line position. If the gradient decreases or increases, the grayscale of the wire rope area must increase toward the center of the area, while the grayscale of the gap area decreases toward the center of the area. Among them, the contour map and the original image position correspond one to one.

[0088] Furthermore, the step of performing binary filling processing on the contour image data according to the binary grayscale threshold to generate a corresponding binary image specifically includes:

[0089] A binary image corresponding to the contour image data is generated by filling the area whose grayscale value is less than the binary grayscale threshold and whose gradient increases toward the edge line with a first preset value, and filling the area whose grayscale value is greater than the binary grayscale threshold and whose gradient decreases toward the edge line and whose gradient increases away from the edge line with a second preset value.

[0090] Among them, the first preset value corresponds to the wire rope, and the second preset value corresponds to the gap, that is, the first preset value is 0, corresponding to the gap, and displayed as black in the binary image, and the second preset value is 255, corresponding to the wire rope, and displayed as white in the binary image.

[0091] Step S210, deleting isolated points in the binary image and generating corresponding connected regions to be detected.

[0092] Specifically, by performing an erosion operation on the binary image, the following Figure 4 The isolated points shown in , that is, the isolated points displayed in black, are used to obtain the corresponding connected areas to be detected. The schematic diagram of the connected areas to be detected composed of the obtained white areas is as follows Figure 5 shown.

[0093] Step S212, performing statistical analysis on each connected area to be detected, when it is determined that the number of boundary segments in the binary image of each connected area to be detected is greater than a preset value, the area points in the connected area to be detected whose width is greater than the preset wire rope width and forked towards both ends are determined as tangled rope areas.

[0094] Among them, by performing statistical analysis on each connected area to be detected, the size between the width of each connected area to be detected and 2 times the preset wire rope width is determined. When there are connected areas to be detected with a width less than 2 times the preset wire rope width, these connected areas to be detected are directly eliminated to achieve pre-filtering of the connected areas to be detected.

[0095] Specifically, when it is determined that the width of each connected area to be detected is greater than 2 times the preset wire rope width, that is, the number of black and white segments is greater than or equal to 5, a certain confidence level is met, and then each connected area to be detected is cross-detected. Among them, there is an obvious black and white gap in the connected area to be detected, the white segment represents the wire rope, and the black segment represents the shadow or gap. When the distribution of black and white segments in the connected area to be detected is determined according to the wire rope width of the connected area to be detected, and the number of demarcation segments is greater than the preset value, the connected area to be detected is scanned from top to bottom, and each area with a width value greater than the preset wire rope width is determined from the connected area to be detected, and a corresponding set of areas greater than the preset wire rope width is obtained according to each area.

[0096] Furthermore, by determining the area with gaps in the area set larger than the wire rope width in a monotonically increasing trend, that is, the area points that fork towards the two ends, it is determined that there are wire rope intersections in the connected area to be detected, that is, the situation of tangled ropes occurs, and thus the area points in the connected area to be detected with a width greater than the preset wire rope width and forked towards the two ends are determined as tangled rope areas. Among them, the preset value is the number of wire ropes × 2 + 1.

[0097] In one embodiment, Figure 6 As shown, Figure 6 A schematic diagram of the detection results of a wire rope disorder detection method is provided. Figure 6 , three large areas are marked, including area 1, area 2 and area 3. Among them, area 1 represents the rope arrangement under normal conditions, areas 2 and 3 both have disordered ropes, area 4 located in area 2 represents disordered ropes caused by rope clamping, and areas 5 and 6 located in area 3 represent disordered ropes caused by empty slots. Among them, areas 4 to 6 represent areas with a width greater than the preset wire rope width. Through the detection operation of the connected area to be detected, it can be determined that areas 4 to 6 are all disordered rope areas, and further it can be determined that areas 2 and 3 with larger areas are also disordered rope areas.

[0098] The above-mentioned wire rope disorder detection method extracts the brightness signal data corresponding to the predetermined wire rope area to be detected from the monitoring image of the wire rope operation site, and pre-processes the brightness signal data. The contour image data corresponding to the wire rope area to be detected is obtained by edge extraction of the pre-processed brightness signal data, and the contour image data is binarized to obtain the corresponding binary image, and then the isolated points in the binary image are deleted to generate the corresponding connected area to be detected. By performing statistical analysis on each connected area to be detected, when it is determined that the number of boundary segments in the binary image of each connected area to be detected is greater than a preset value, the area points in the connected area to be detected whose width is greater than the preset wire rope width and forked towards both ends are determined as disordered rope areas. It realizes direct analysis, statistics and area recognition of contour image data obtained according to brightness signal data, without relying on models trained according to a large amount of sample image data for recognition, avoiding the problem of low recognition success probability due to insufficient sample data in traditional recognition methods, and has good adaptability to changes in environmental brightness. At the same time, on the basis of simplifying the recognition operation process, it further improves the efficiency of tangled rope recognition in monitoring images of wire rope operation sites.

[0099] In one embodiment, after statistical analysis is performed on each connected area to be detected, when it is determined that the number of boundary segments in the binary image of each connected area to be detected is greater than a preset value, the area points within the connected area to be detected with a width greater than a preset wire rope width and forked toward both ends are determined as a tangled rope area, the method further includes:

[0100] Merge adjacent chaotic rope areas to obtain the corresponding abnormal area collection;

[0101] Displaying the abnormal area collection on a display device;

[0102] Output warning information generated based on the collection of abnormal areas.

[0103] Specifically, two or more adjacent tangled rope areas are merged to obtain a corresponding abnormal area collection, and the merged abnormal area collection is displayed on a display device, while other non-adjacent tangled rope areas that cannot be merged are also displayed.

[0104] Among them, a plurality of display areas for displaying tangled rope areas are arranged on the display device of the terminal, and each display area does not limit the size of the tangled rope display area. It can be understood that when adjacent tangled rope areas are merged to obtain a collection of abnormal areas, multiple adjacent tangled rope areas can be displayed in the same display area, so that more non-adjacent tangled rope areas can be displayed, reducing the occupation of the display area by adjacent tangled rope areas.

[0105] In this embodiment, the corresponding abnormal area collection is obtained by merging adjacent tangled rope areas, and the abnormal area collection is displayed on the display device, and then the warning prompt information generated according to the abnormal area collection is output. The real-time display of the tangled rope area is realized, and the warning prompt information for prompting the user is output at the same time, so that the tangled rope situation in the tangled rope area can be handled in time, the wear of the wire rope is reduced, and the potential safety hazards are further reduced to ensure safe construction operations.

[0106] In one embodiment, Figure 7 As shown, another wire rope disorder detection method is provided, which specifically includes four parts: installation and adjustment, image data acquisition, image processing and result output, among which:

[0107] The first part, installation and adjustment, includes:

[0108] 1) Install the equipment.

[0109] 2) Determine the wire rope area to be inspected in advance.

[0110] 3) Determine the regional parameters, that is, predetermine and save the regional parameters of the wire rope area to be detected.

[0111] The region parameters include region size and data signal type, and the data signal type includes a brightness signal.

[0112] The second part, image data acquisition, includes:

[0113] 4) Obtain monitoring images of the wire rope operation site.

[0114] 5) Sharpness enhancement processing, that is, sharpness enhancement processing is performed on the monitoring image of the wire rope operation site.

[0115] 6) Obtaining regional parameters, that is, obtaining regional parameters of a predetermined steel wire rope area to be detected.

[0116] 7) Regional scaling processing, that is, performing regional scaling processing on the monitoring image of the wire rope operation site after sharpness enhancement processing according to the size of the area.

[0117] 8) Extracting brightness signal data, that is, according to the data signal type, extracting brightness signal data corresponding to a predetermined wire rope area to be detected from the monitoring image of the wire rope operation site after scaling of the original image data.

[0118] The third part, image processing, includes:

[0119] 9) Obtain a pre-configured filter template.

[0120] 10) Gaussian filtering, that is, performing Gaussian filtering on the brightness signal data according to the filtering template.

[0121] 11) Histogram statistics, that is, performing histogram statistics on the brightness signal data after Gaussian filtering to generate the grayscale distribution of the brightness signal data.

[0122] 12) Determine the high and low grayscale thresholds, that is, determine the high and low grayscale thresholds of the edge extraction operator according to the grayscale distribution of the brightness signal data.

[0123] 13) Generate contour image data, that is, use the edge extraction operator with determined high and low grayscale thresholds to perform edge extraction on the brightness signal data after Gaussian filtering to obtain contour image data corresponding to the wire rope area to be detected.

[0124] 14) Obtain edge lines of contour image data.

[0125] 15) Statistical grayscale gradient distribution, that is, taking the edge line as the boundary, statistically analyzing the grayscale gradient distribution of the contour image data.

[0126] 16) Determine the binary grayscale threshold, that is, determine the corresponding binary grayscale threshold according to the grayscale gradient distribution; the binary grayscale thresholds correspond to the wire rope and the gap respectively.

[0127] 17) Binary filling, that is, performing binary filling processing on the contour image data according to the binary grayscale threshold to generate a corresponding binary image.

[0128] 18) Image erosion, that is, performing image erosion on a binary image, deleting isolated points in the binary image, and generating corresponding connected areas to be detected.

[0129] 19) Determine the tangled rope area, that is, by performing statistical analysis on each connected area to be detected, when it is determined that the number of boundary segments in the binary image of each connected area to be detected is greater than a preset value, the area points in the connected area to be detected with a width greater than the preset wire rope width and forked towards both ends are determined as the tangled rope area.

[0130] The fourth part, result output, includes:

[0131] 20) Generate a collection of abnormal regions, that is, obtain a corresponding collection of abnormal regions by merging adjacent chaotic rope regions.

[0132] 21) Displaying the abnormal area collection, that is, displaying the abnormal area collection on a display device.

[0133] 22) Outputting warning information, that is, outputting warning information generated according to the abnormal area collection.

[0134] In this embodiment, the brightness signal data corresponding to the predetermined wire rope area to be detected is extracted from the monitoring image of the wire rope operation site, and the brightness signal data is preprocessed. The contour image data corresponding to the wire rope area to be detected is obtained by edge extraction of the preprocessed brightness signal data, and the contour image data is binarized to obtain the corresponding binary image, and then the isolated points in the binary image are deleted to generate the corresponding connected area to be detected. By statistically analyzing each connected area to be detected, when it is determined that the number of boundary segments in the binary image of each connected area to be detected is greater than a preset value, the area points in the connected area to be detected whose width is greater than the preset wire rope width and forked towards both ends are determined as the tangled rope area. It is realized that the contour image data obtained according to the brightness signal data is directly analyzed and statistically analyzed and the area is identified, without relying on the model obtained by training a large amount of sample image data for identification, avoiding the problem of low probability of successful identification due to insufficient sample data in the traditional identification method, and having good adaptability to changes in environmental brightness. At the same time, on the basis of simplifying the identification operation process, the efficiency of tangled rope identification of the monitoring image of the wire rope operation site is further improved.

[0135] It should be understood that although Figure 2 and Figure 7 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. Moreover, Figure 2 and Figure 7 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0136] In one embodiment, Figure 8 As shown, a wire rope disorder detection device is provided, comprising: a brightness signal data extraction module 802, a preprocessing module 804, a contour image data generation module 806, a binarization processing module 808, a connected area generation module 810 to be detected, and a disordered rope area determination module 812, wherein:

[0137] The brightness signal data extraction module 802 is used to extract brightness signal data corresponding to a predetermined wire rope area to be detected from the monitoring image of the wire rope operation site.

[0138] The preprocessing module 804 is used to preprocess the brightness signal data.

[0139] The contour image data generating module 806 is used to perform edge extraction on the pre-processed brightness signal data to obtain contour image data corresponding to the steel wire rope area to be detected.

[0140] The binarization processing module 808 is used to perform binarization processing on the contour image data to obtain a corresponding binary image.

[0141] The connected region to be detected generating module 810 is used to delete isolated points in the binary image and generate corresponding connected regions to be detected.

[0142] The tangled rope area determination module 812 is used to perform statistical analysis on each connected area to be detected. When it is determined that the number of boundary segments in the binary image of each connected area to be detected is greater than a preset value, the area points in the connected area to be detected with a width greater than a preset wire rope width and forked towards both ends are determined as tangled rope areas.

[0143] The above-mentioned wire rope disorder detection device extracts the brightness signal data corresponding to the predetermined wire rope area to be detected from the monitoring image of the wire rope operation site, and pre-processes the brightness signal data. By performing edge extraction on the pre-processed brightness signal data, the contour image data corresponding to the wire rope area to be detected is obtained, and the contour image data is binarized to obtain the corresponding binary image, and then the isolated points in the binary image are deleted to generate the corresponding connected area to be detected. By performing statistical analysis on each connected area to be detected, when it is determined that the number of boundary segments in the binary image of each connected area to be detected is greater than a preset value, the area points in the connected area to be detected whose width is greater than the preset wire rope width and forked towards both ends are determined as disordered rope areas. It realizes direct analysis, statistics and area recognition of contour image data obtained according to brightness signal data, without relying on models trained according to a large amount of sample image data for recognition, avoiding the problem of low recognition success probability due to insufficient sample data in traditional recognition methods, and has good adaptability to changes in environmental brightness. At the same time, on the basis of simplifying the recognition operation process, it further improves the efficiency of tangled rope recognition in monitoring images of wire rope operation sites.

[0144] In one embodiment, the wire rope tangling detection device further comprises:

[0145] A chaotic rope area merging module is used to merge adjacent chaotic rope areas to obtain a corresponding abnormal area collection;

[0146] An abnormal area collection display module is used to display the abnormal area collection on a display device;

[0147] The warning prompt information output module is used to output the warning prompt information generated according to the abnormal area collection.

[0148] In this embodiment, the corresponding abnormal area collection is obtained by merging adjacent tangled rope areas, and the abnormal area collection is displayed on the display device, and then the warning prompt information generated according to the abnormal area collection is output. The real-time display of the tangled rope area is realized, and the warning prompt information for prompting the user is output at the same time, so that the tangled rope situation in the tangled rope area can be handled in time, the wear of the wire rope is reduced, and the potential safety hazards are further reduced to ensure safe construction operations.

[0149] In one embodiment, the binarization processing module is further used for:

[0150] Obtain edge lines of contour image data;

[0151] Taking the edge line as the boundary, the gray gradient distribution of the contour image data is statistically analyzed;

[0152] According to the grayscale gradient distribution, the corresponding binary grayscale threshold is determined; the binary grayscale threshold corresponds to the wire rope and the gap respectively;

[0153] According to the binary grayscale threshold, the contour image data is binary filled to generate a corresponding binary image.

[0154] In one embodiment, the binarization processing module is further used for:

[0155] The area with a grayscale value less than the binary grayscale threshold and whose gradient increases toward the edge line is filled with the first preset value, and the area with a grayscale value greater than the binary grayscale threshold and whose gradient decreases toward the edge line and whose gradient increases away from the edge line is filled with the second preset value, to generate a binary image corresponding to the contour image data; the first preset value corresponds to the wire rope, and the second preset value corresponds to the gap.

[0156] In one embodiment, the brightness signal data extraction module is further used to:

[0157] Perform sharpness enhancement processing on monitoring images of wire rope operation sites;

[0158] Acquire the region parameters of the predetermined wire rope region to be detected; the region parameters include region size and data signal type, and the data signal type includes brightness signal;

[0159] According to the size of the area, the monitoring image of the wire rope operation site after the sharpness enhancement processing is performed with regional scaling processing;

[0160] According to the data signal type, the brightness signal data corresponding to the predetermined wire rope area to be detected is extracted from the monitoring image of the wire rope operation site after scaling processing.

[0161] In one embodiment, the preprocessing module is further used to:

[0162] Get the pre-configured filter template;

[0163] Perform Gaussian filtering on the brightness signal data according to the filtering template;

[0164] Perform histogram statistics on the brightness signal data after Gaussian filtering to generate the grayscale distribution of the brightness signal data.

[0165] In one embodiment, the contour image data generating module is further used to:

[0166] According to the grayscale distribution of the brightness signal data, the high and low grayscale thresholds of the edge extraction operator are determined;

[0167] Using the edge extraction operator with determined high and low grayscale thresholds, edge extraction is performed on the brightness signal data after Gaussian filtering to obtain contour image data corresponding to the wire rope area to be detected.

[0168] For the specific definition of the wire rope disorder detection device, please refer to the definition of the wire rope disorder detection method mentioned above, which will not be repeated here. Each module in the above-mentioned wire rope disorder detection device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0169] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for detecting a disordered wire rope is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0170] Those skilled in the art will understand that Fig. 9The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0171] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0172] Extracting brightness signal data corresponding to a predetermined wire rope area to be detected from a monitoring image of a wire rope operation site;

[0173] Preprocessing the brightness signal data;

[0174] Perform edge extraction on the pre-processed brightness signal data to obtain contour image data corresponding to the wire rope area to be detected;

[0175] Binarization is performed on the contour image data to obtain a corresponding binary image;

[0176] Delete isolated points in the binary image and generate corresponding connected areas to be detected;

[0177] Statistical analysis is performed on each connected area to be detected. When it is determined that the number of boundary segments in the binary image of each connected area to be detected is greater than a preset value, the area points in the connected area to be detected with a width greater than the preset wire rope width and forked towards both ends are determined as tangled rope areas.

[0178] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0179] Obtain edge lines of contour image data;

[0180] Taking the edge line as the boundary, the gray gradient distribution of the contour image data is statistically analyzed;

[0181] According to the grayscale gradient distribution, the corresponding binary grayscale threshold is determined; the binary grayscale threshold corresponds to the wire rope and the gap respectively;

[0182] According to the binary grayscale threshold, the contour image data is binary filled to generate a corresponding binary image.

[0183] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0184] Perform sharpness enhancement processing on monitoring images of wire rope operation sites;

[0185] Acquire the region parameters of the predetermined wire rope region to be detected; the region parameters include region size and data signal type, and the data signal type includes brightness signal;

[0186] According to the size of the area, the monitoring image of the wire rope operation site after the sharpness enhancement processing is performed with regional scaling processing;

[0187] According to the data signal type, the brightness signal data corresponding to the predetermined wire rope area to be detected is extracted from the monitoring image of the wire rope operation site after scaling processing.

[0188] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0189] Get the pre-configured filter template;

[0190] Perform Gaussian filtering on the brightness signal data according to the filtering template;

[0191] Perform histogram statistics on the brightness signal data after Gaussian filtering to generate the grayscale distribution of the brightness signal data.

[0192] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0193] According to the grayscale distribution of the brightness signal data, the high and low grayscale thresholds of the edge extraction operator are determined;

[0194] Using the edge extraction operator with determined high and low grayscale thresholds, edge extraction is performed on the brightness signal data after Gaussian filtering to obtain contour image data corresponding to the wire rope area to be detected.

[0195] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0196] The area with a grayscale value less than the binary grayscale threshold and whose gradient increases toward the edge line is filled with the first preset value, and the area with a grayscale value greater than the binary grayscale threshold and whose gradient decreases toward the edge line and whose gradient increases away from the edge line is filled with the second preset value, to generate a binary image corresponding to the contour image data; the first preset value corresponds to the wire rope, and the second preset value corresponds to the gap.

[0197] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0198] Merge adjacent chaotic rope areas to obtain the corresponding abnormal area collection;

[0199] Displaying the abnormal area collection on a display device;

[0200] Output warning information generated based on the collection of abnormal areas.

[0201] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0202] Extracting brightness signal data corresponding to a predetermined wire rope area to be detected from a monitoring image of a wire rope operation site;

[0203] Preprocessing the brightness signal data;

[0204] Perform edge extraction on the pre-processed brightness signal data to obtain contour image data corresponding to the wire rope area to be detected;

[0205] Binarization is performed on the contour image data to obtain a corresponding binary image;

[0206] Delete isolated points in the binary image and generate corresponding connected areas to be detected;

[0207] Statistical analysis is performed on each connected area to be detected. When it is determined that the number of boundary segments in the binary image of each connected area to be detected is greater than a preset value, the area points in the connected area to be detected with a width greater than the preset wire rope width and forked towards both ends are determined as tangled rope areas.

[0208] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0209] Obtain edge lines of contour image data;

[0210] Taking the edge line as the boundary, the gray gradient distribution of the contour image data is statistically analyzed;

[0211] According to the grayscale gradient distribution, the corresponding binary grayscale threshold is determined; the binary grayscale threshold corresponds to the wire rope and the gap respectively;

[0212] According to the binary grayscale threshold, the contour image data is binary filled to generate a corresponding binary image.

[0213] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0214] Perform sharpness enhancement processing on monitoring images of wire rope operation sites;

[0215] Acquire the region parameters of the predetermined wire rope region to be detected; the region parameters include region size and data signal type, and the data signal type includes brightness signal;

[0216] According to the size of the area, the monitoring image of the wire rope operation site after the sharpness enhancement processing is performed with regional scaling processing;

[0217] According to the data signal type, the brightness signal data corresponding to the predetermined wire rope area to be detected is extracted from the monitoring image of the wire rope operation site after scaling processing.

[0218] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0219] Get the pre-configured filter template;

[0220] Perform Gaussian filtering on the brightness signal data according to the filtering template;

[0221] Perform histogram statistics on the brightness signal data after Gaussian filtering to generate the grayscale distribution of the brightness signal data.

[0222] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0223] According to the grayscale distribution of the brightness signal data, the high and low grayscale thresholds of the edge extraction operator are determined;

[0224] Using the edge extraction operator with determined high and low grayscale thresholds, edge extraction is performed on the brightness signal data after Gaussian filtering to obtain contour image data corresponding to the wire rope area to be detected.

[0225] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0226] The area with a grayscale value less than the binary grayscale threshold and whose gradient increases toward the edge line is filled with the first preset value, and the area with a grayscale value greater than the binary grayscale threshold and whose gradient decreases toward the edge line and whose gradient increases away from the edge line is filled with the second preset value, to generate a binary image corresponding to the contour image data; the first preset value corresponds to the wire rope, and the second preset value corresponds to the gap.

[0227] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0228] Merge adjacent chaotic rope areas to obtain the corresponding abnormal area collection;

[0229] Displaying the abnormal area collection on a display device;

[0230] Output warning information generated based on the collection of abnormal areas.

[0231] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0232] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0233] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for detecting tangled wire ropes, characterized in that: The method comprises: Extracting brightness signal data corresponding to a predetermined wire rope area to be detected from a monitoring image of a wire rope operation site; Preprocessing the brightness signal data; Performing edge extraction on the preprocessed brightness signal data to obtain contour image data corresponding to the steel wire rope area to be detected; Binarizing the contour image data to obtain a corresponding binary image; Deleting isolated points in the binary image to generate corresponding connected regions to be detected; Performing statistical analysis on each of the connected regions to be detected, when it is determined that the number of boundary segments in the binary image of each of the connected regions to be detected is greater than a preset value, determining the area points in the connected region to be detected that are wider than the preset wire rope width and forked towards both ends as a tangled rope area; The step of extracting brightness signal data corresponding to a predetermined wire rope area to be detected from the monitoring image of the wire rope operation site includes: Perform sharpness enhancement processing on the monitoring image of the wire rope operation site; obtain regional parameters of a predetermined wire rope area to be detected; the regional parameters include region size and data signal type, and the data signal type includes brightness signal; according to the region size, perform regional scaling processing on the monitoring image of the wire rope operation site after sharpness enhancement processing; according to the data signal type, extract brightness signal data corresponding to the predetermined wire rope area to be detected from the monitoring image of the wire rope operation site after scaling processing.

2. The method according to claim 1, characterized in that The binarization process of the contour image data to obtain a corresponding binary image includes: Acquire edge lines of the contour image data; Taking the edge line as the boundary, counting the grayscale gradient distribution of the contour image data; According to the grayscale gradient distribution, a corresponding binary grayscale threshold is determined; the binary grayscale threshold corresponds to the wire rope and the gap respectively; According to the binary grayscale threshold, the contour image data is subjected to binary filling processing to generate a corresponding binary image.

3. The method according to claim 1 or 2, characterized in that: Preprocessing the brightness signal data includes: Get the pre-configured filter template; Performing Gaussian filtering on the brightness signal data according to the filtering template; Histogram statistics are performed on the brightness signal data after Gaussian filtering to generate grayscale distribution of the brightness signal data.

4. The method according to claim 3, characterized in that The edge extraction is performed on the pre-processed brightness signal data to obtain contour image data corresponding to the steel wire rope area to be detected, including: Determining high and low grayscale thresholds of an edge extraction operator according to the grayscale distribution of the brightness signal data; The edge extraction operator with determined high and low grayscale thresholds is used to perform edge extraction on the brightness signal data after Gaussian filtering to obtain contour image data corresponding to the wire rope area to be detected.

5. The method according to claim 2, characterized in that: The step of performing binary filling processing on the contour image data according to the binary grayscale threshold to generate a corresponding binary image includes: The area with a grayscale value less than the binary grayscale threshold and whose gradient increases toward the edge line is filled with a first preset value, and the area with a grayscale value greater than the binary grayscale threshold and whose gradient decreases toward the edge line and whose gradient increases away from the edge line is filled with a second preset value, to generate a binary image corresponding to the contour image data; the first preset value corresponds to the wire rope, and the second preset value corresponds to the gap.

6. The method according to claim 1 or 2, characterized in that: The method further comprises: Merging the adjacent chaotic rope areas to obtain a corresponding abnormal area collection; Displaying the abnormal area collection on a display device; Output the warning prompt information generated according to the abnormal area collection.

7. A wire rope disorder detection device, characterized in that: The device comprises: A brightness signal data extraction module is used to extract brightness signal data corresponding to a predetermined wire rope area to be detected from a monitoring image of a wire rope operation site; A preprocessing module, used for preprocessing the brightness signal data; A contour image data generating module, used for performing edge extraction on the pre-processed brightness signal data to obtain contour image data corresponding to the steel wire rope area to be detected; A binarization processing module, used for performing binarization processing on the contour image data to obtain a corresponding binary image; A connected region generation module to be detected, used to delete isolated points in the binary image and generate corresponding connected regions to be detected; A tangled rope area determination module is used to perform statistical analysis on each of the connected areas to be detected. When it is determined that the number of boundary segments in the binary image of each of the connected areas to be detected is greater than a preset value, the area points within the connected area to be detected that are wider than a preset wire rope width and forked towards both ends are determined as tangled rope areas; The brightness signal data extraction module is also used to: perform sharpness enhancement processing on the monitoring image of the wire rope operation site; obtain the regional parameters of the predetermined wire rope area to be detected; the regional parameters include the area size and the data signal type, and the data signal type includes the brightness signal; according to the area size, perform regional scaling processing on the monitoring image of the wire rope operation site after the sharpness enhancement processing; according to the data signal type, extract the brightness signal data corresponding to the predetermined wire rope area to be detected from the monitoring image of the wire rope operation site after the scaling processing.

8. The device according to claim 7, characterized in that The binarization processing module is further used for: Acquire the edge line of the contour image data; take the edge line as the boundary, and count the grayscale gradient distribution of the contour image data; determine the corresponding binary grayscale threshold according to the grayscale gradient distribution; the binary grayscale thresholds correspond to the wire rope and the gap respectively; According to the binary grayscale threshold, the contour image data is subjected to binary filling processing to generate a corresponding binary image.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images