Elevator sliding bearing surface defect detection method, device, equipment and medium

Abstract

The invention discloses an elevator sliding bearing surface defect detection method and device, equipment and a medium. The method comprises the steps that a surface image of an elevator sliding bearing is acquired, and seed points are selected based on the surface image; calculating an adjacent difference degree and a continuity degree of each pixel point in the surface image; constructing a growth criterion evaluation model based on the adjacent difference degree and the continuity degree of each pixel point; and performing defect detection on the surface image by using the seed points, a growth selection evaluation model and a region growth algorithm. According to the method and the device, the problem that when a region growth algorithm is used for defect detection, when seed points and growth criteria are set incorrectly, defect missing detection and defect error detection are caused is solved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and particularly to a method, device, equipment and medium for detecting surface defects of elevator sliding bearings. Background Art

[0002] Defects on the surface of elevator sliding bearings, such as scratches or cracks, will increase the friction of the bearings, resulting in accelerated wear and overheating of the bearings, shortening the bearing life, and even causing failures or outages, seriously affecting the safety and performance of the elevator.

[0003] Since elevator sliding bearings are usually made of metal, the reflective characteristics of the metal surface make the error larger when using conventional defect detection algorithms to detect surface defects of elevator sliding bearings. Compared with conventional defect detection algorithms, the region growing algorithm has better robustness and can accurately identify surface defects of elevator sliding bearings under changing lighting conditions. In the region growing algorithm, seed points need to be selected manually in advance. If the selection is inappropriate, the algorithm may not be able to accurately identify the defect area. In addition, the growth criterion also needs to be set manually in advance. If the criterion is set unreasonably, it may lead to missed detection or false detection of defects.

[0004] The above content is only used to assist in understanding the technical solution of the present application, and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of the present application is to provide a method, device, equipment and medium for detecting surface defects of elevator sliding bearings, aiming to solve the technical problem of missed detection and false detection of defects caused by inappropriate setting of seed points and growth criteria when using the region growing algorithm for defect detection.

[0006] To achieve the above purpose, the present application provides a method for detecting surface defects of elevator sliding bearings, including: obtaining a surface image of the elevator sliding bearing and selecting seed points based on the surface image; calculating the adjacent difference degree and continuity degree of each pixel point in the surface image; constructing a growth criterion evaluation model based on the adjacent difference degree and the continuity degree of each pixel point; and using the seed points, the growth criterion evaluation model and the region growing algorithm to detect defects in the surface image.

[0007] Optionally, the selecting seed points based on the surface image includes: calculating the gradient value of each pixel point in the surface image; and determining the seed points based on the gradient value of each pixel point.

[0008] Optionally, calculating the adjacent difference degree of each pixel point in the surface image includes: grading the grayscale of all pixel points in the surface image to obtain the grayscale level corresponding to each pixel point; calculating the number of consecutive rows and the number of consecutive columns of the grayscale level corresponding to each pixel point in the surface image; and determining the adjacent difference degree of each pixel point based on the number of consecutive rows and the number of consecutive columns.

[0009] Optionally, determining the adjacent difference degree of each pixel point based on the number of consecutive rows and the number of consecutive columns includes: calculating the continuity degree of each pixel point using the following formula (1):

[0010] δ i =|l ir -l' ir |+|l ic -l' ic | (1)

[0011] Wherein, δ i represents the adjacent difference degree of the i-th pixel point, l ir represents the number of consecutive columns of the i-th pixel point, l ic represents the number of consecutive rows of the i-th pixel point, l' ir represents the number of consecutive columns of the pixel point with the same grayscale level as the i-th pixel point and the smallest distance from the i-th pixel point in the same column, l' ic represents the number of consecutive rows of the pixel point with the same grayscale level as the i-th pixel point and the smallest distance from the i-th pixel point in the same row.

[0012] Optionally, calculating the continuity degree of each pixel point in the surface image includes: calculating the entropy value of the gray-level co-occurrence matrix of each pixel point in a preset area; and determining the continuity degree of each pixel point based on the difference between the entropy value of each pixel point and the entropy value of its adjacent pixel points.

[0013] Optionally, constructing a growth criterion evaluation model based on the adjacent difference degree and the continuity degree of each pixel point includes: determining a difference measurement factor based on the adjacent difference degree and the continuity degree of each pixel point; and constructing a growth criterion evaluation model based on the difference measurement factor of each pixel point.

[0014] Optionally, after using the seed points, the growth criterion evaluation model, and the region growing algorithm to perform defect detection on the surface image, the method further includes: marking the defect detection result on the surface image; and verifying the defect detection result using a preset algorithm.

[0015] In addition, to achieve the above object, the present application further provides a surface defect detection device for an elevator sliding bearing, including: a seed point selection module for obtaining a surface image of the elevator sliding bearing and selecting seed points based on the surface image; a feature calculation module for calculating the adjacent difference degree and the continuity degree of each pixel point in the surface image; a model construction module for constructing a growth criterion evaluation model based on the adjacent difference degree and the continuity degree of each pixel point; and a defect detection module for performing defect detection on the surface image by using the seed points, the growth criterion evaluation model, and the region growing algorithm.

[0016] The present application further provides a surface defect detection device for an elevator sliding bearing, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the above-mentioned surface defect detection method for an elevator sliding bearing.

[0017] The present application further provides a computer-readable storage medium, including: a computer program stored therein, and when the computer program is executed by a processor, the above-mentioned surface defect detection method for an elevator sliding bearing is implemented.

[0018] A surface defect detection method, device, device, and medium for an elevator sliding bearing proposed by the present application calculate the adjacent difference degree and the continuity degree of each pixel point in the surface image and construct a growth criterion evaluation model based on the adjacent difference degree and the continuity degree of each pixel point. The adjacent difference degree and the continuity degree can both characterize the possibility that each pixel point belongs to the same region as the texture difference degree of the surrounding area, that is, both belong to the normal region or both belong to the defect region. This solves the problem of defect omission and defect misdetection caused by improper setting of seed points and growth criteria when using the region growing algorithm for defect detection. It realizes the accurate identification and complete elimination of defect regions, thereby improving the accuracy and reliability of defect detection. Description of the Drawings

[0019] Figure 1 It is a flowchart of a surface defect detection method for an elevator sliding bearing according to an embodiment of the present application;

[0020] Figure 2 It is a structural block diagram of a surface defect detection device for an elevator sliding bearing according to an embodiment of the present application;

[0021] Figure 3 It is a structural schematic diagram of a surface defect detection device for an elevator sliding bearing according to an embodiment of the present application.

[0022] The realization, functional features, and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. Detailed implementation manners

[0023] 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.

[0024] The present application provides a solution. The seed points of the region growing algorithm are determined according to the defect features. At the same time, based on the similarity of the textures inside the defect region, the similarity of the textures inside the normal region, and the texture difference between the two, a growth criterion evaluation model is constructed. Then, based on the seed points and the growth criterion evaluation model and using the region growing algorithm, the surface image of the elevator sliding bearing is defect detected, solving the technical problems of easy defect omission and misdetection when the seed points and growth criteria are set inappropriately.

[0025] The following details the solution of the present application.

[0026] Figure 1 FIG. is a flowchart of a method for detecting surface defects of an elevator sliding bearing according to an embodiment of the present application. The method for detecting surface defects of the elevator sliding bearing can be executed by a defect detection device with data processing capabilities. The defect detection device can be, for example, a device for detecting surface defects of an elevator sliding bearing. Referring to Figure 1 ..., the method for detecting surface defects of the elevator sliding bearing may include the following steps:

[0027] S1. Obtain the surface image of the elevator sliding bearing and select seed points based on the surface image.

[0028] It should be noted that in this embodiment, for defect detection of the surface of the elevator sliding bearing, it is necessary to first collect the surface image of the elevator sliding bearing.

[0029] In the specific implementation process, first fix the acquisition camera on the production line of the elevator sliding bearing and communicatively connect the acquisition camera with the defect detection device. Use the acquisition camera to collect the surface image of the elevator sliding bearing.

[0030] Furthermore, perform preprocessing such as grayscale conversion, enhancement, and denoising on the surface image.

[0031] In one embodiment, in step S1, selecting seed points based on the surface image may specifically include:

[0032] S11. Calculate the gradient values of each pixel point in the surface image;

[0033] S12. Determine the seed points based on the gradient values of each pixel point.

[0034] Among them, in step S12, several seed points can be selected in the order of the gradient values of each pixel point from large to small.

[0035] It can be understood that in the surface image of the elevator sliding bearing, the gradient values of the pixel points in the defect area are larger than those of the pixel points in the normal area. Therefore, selecting seed points in the order of the gradient values from large to small can prevent the defect area from being missed during inspection.

[0036] S2. Calculate the adjacent difference degree and continuity degree of each pixel point in the surface image;

[0037] S3. Construct a growth criterion evaluation model based on the adjacent difference degree and the continuity degree of each pixel point;

[0038] S4. Use the seed points, the growth criterion evaluation model, and the region growing algorithm to detect defects in the surface image.

[0039] Among them, the adjacent difference degree can represent the texture difference degree between each pixel point and its surrounding area, and the continuity degree can represent the texture uniformity degree between each pixel point and its surrounding area. Both the adjacent difference degree and the continuity degree can represent the possibility that each pixel point and its surrounding area belong to the same area, that is, both belong to the normal area or both belong to the defect area.

[0040] In one embodiment, in step S2, calculating the adjacent difference degree of each pixel point in the surface image may specifically include:

[0041] S21. Perform gray level grading on all pixel points in the surface image to obtain the gray level corresponding to each pixel point;

[0042] S22. Calculate the row continuous number and column continuous number of the gray level corresponding to each pixel point in the surface image;

[0043] S23. Determine the adjacent difference degree of each pixel point based on the row continuous number and the column continuous number.

[0044] In a specific implementation process, first, the pixel points in the surface image are subjected to gray-level grading to obtain the gray levels corresponding to each pixel point. It can be understood that gray-level grading means dividing the gray values of each pixel point in the surface image into multiple levels according to a preset rule. Exemplarily, the gray values from 0 to 255 can be divided into 8 levels, and the range of each level is 32 gray values, that is, the gray value corresponding to gray level 1 is 0 - 31, the gray value corresponding to gray level 2 is 32 - 63, the gray value corresponding to gray level 3 is 64 - 95, the gray value corresponding to gray level 4 is 96 - 127, the gray value corresponding to gray level 5 is 128 - 159, the gray value corresponding to gray level 6 is 160 - 191, the gray value corresponding to gray level 7 is 192 - 223, and the gray value corresponding to gray level 8 is 224 - 255. Performing gray-level grading on the gray values of pixel points and then processing the gray values of each pixel point according to the gray levels can improve the processing efficiency and reduce the calculation amount.

[0045] Further, starting from the upper left corner of the surface image, the row consecutive count and column consecutive count of the gray level corresponding to each pixel point in the surface image are calculated in sequence from top to bottom and from left to right. It should be noted that taking the k-th column of the surface image as an example, starting from the first pixel point in the k-th column for traversal, the consecutive occurrence count of the gray level corresponding to the first pixel point is counted, that is, the column consecutive count of the first pixel point. When a pixel point with a gray level different from that of the first pixel point appears, this point is used as a new starting point and the consecutive occurrence count of the gray level corresponding to this pixel point is counted. It can be understood that the row consecutive count and column consecutive count of the gray level corresponding to each pixel point in the surface image are the row consecutive count and column consecutive count of each pixel point. If the next pixel point of the first pixel point in the k-th column has the same gray level as the first pixel point, then the column consecutive count of this pixel point is the same as that of the first pixel point.

[0046] Further, based on the differences in the row consecutive count and column consecutive count of different pixel points, the adjacent difference degree of each pixel point is determined.

[0047] Specifically, taking the i-th pixel point as an example, the adjacent difference degree δ of the i-th pixel point can be calculated using the following formula (1) i :

[0048] δ i =|l ir -l' ir |+|l ic -l' ic | (1)

[0049] Where, l ir represents the column consecutive count of the i-th pixel point, l ic represents the row consecutive count of the i-th pixel point, and l' irDenote the column consecutive count of the pixel point with the smallest distance and in the same column as the \(i\)-th pixel point among the pixel points with the same gray level as the \(i\)-th pixel point, \(l'\) ic Denote the row consecutive count of the pixel point with the smallest distance and in the same row as the \(i\)-th pixel point among the pixel points with the same gray level as the \(i\)-th pixel point.

[0050] It should be noted that the column consecutive count and the row consecutive count can reflect the texture features of each pixel point, and further \(\delta\) i can reflect the texture difference between the \(i\)-th pixel point and its neighboring points. When the \(i\)-th pixel point and its neighboring points belong to the same region, that is, both belong to the normal region or both belong to the defective region, since the texture difference within the same region is small, further \(\delta\) i is small; on the contrary, when the \(i\)-th pixel point and its neighboring points belong to different regions, \(\delta\) i is large. It can be understood that the neighboring points refer to the pixel points with the same gray level as this pixel point, in the same column or the same row as this pixel point and with the smallest distance.

[0051] In one embodiment, in step S2, calculating the continuity degree of each pixel point in the surface image may specifically include:

[0052] S24. Calculate the entropy value of the gray-level co-occurrence matrix of each pixel point in the preset region;

[0053] S25. Determine the continuity degree of each pixel point based on the difference between the entropy value of each pixel point and the entropy value of its adjacent pixel points.

[0054] Among them, when calculating the gray-level co-occurrence matrix of each pixel point in the preset region, replace the gray value of each pixel point with the gray level corresponding to this pixel point. Its adjacent pixel points refer to the 8-neighborhood pixel points of each pixel point.

[0055] In the specific implementation process, calculate the entropy value of the gray-level co-occurrence matrix of each pixel point in the region with the size of \(M\times M\) centered on this pixel point, where \(M\) is a positive integer.

[0056] It should be noted that the entropy value of the gray-level co-occurrence matrix can reflect the uniformity degree of the texture in the image. When the difference in the number of different gray levels in the region with the size of \(M\times M\) is small, the texture distribution in this region is more uniform, and this region may be all normal regions or all defective regions. On the contrary, when the difference in the number of different gray levels in the region with the size of \(M\times M\) is large, it indicates that this region may contain both normal regions and defective regions.

[0057] Further, calculate the absolute value of the difference between the entropy value of each pixel point and the entropy value of the 8-neighborhood pixel points of that pixel point, and sum the 8 obtained absolute values of the differences to obtain the continuity degree of that pixel point. It can be understood that the entropy value of each pixel point refers to the entropy value of the gray-level co-occurrence matrix of that pixel point within a preset area.

[0058] It should be noted that the continuity degree can reflect the possibility that each pixel point and its adjacent pixel points belong to the same area, that is, both belong to the normal area or both belong to the defect area.

[0059] In one embodiment, in step S3, constructing a growth criterion evaluation model based on the adjacent difference degree and the continuity degree of each pixel point may specifically include:

[0060] S31. Determine a difference measure factor based on the adjacent difference degree and the continuity degree of each pixel point;

[0061] S32. Construct a growth criterion evaluation model based on the difference measure factor of each pixel point.

[0062] Among them, the difference measure factor can reflect the difference degree between each pixel point and its surrounding area.

[0063] Specifically, taking the i-th pixel point as an example, the difference measure factor τ of the i-th pixel point can be determined based on the adjacent difference degree and the continuity degree of the i-th pixel point using the following formula (2) i :

[0064]

[0065] In the formula, δ i represents the adjacent difference degree of the i-th pixel point, represents the continuity degree of the i-th pixel point, α represents the first preset factor of the i-th pixel point, and β represents the second preset factor of the i-th pixel point.

[0066] It should be noted that since this embodiment uses the region growing algorithm to identify defects on the surface of the elevator sliding bearing, the set growth criterion and stop condition need to be able to distinguish the defect area and the normal area, that is, ensure that the textures within each segmented area are similar.

[0067] In a specific implementation process, when using the region growing algorithm to identify defects in the surface image, various sub - points are used as starting points to start region growing. When each region grows to any pixel point, the absolute value of the difference between the difference measurement factor between this pixel point and the previous growing pixel point in this region needs to be calculated as the difference factor of this pixel point. When the difference factor of this pixel point is not greater than the difference factor of the previous growing pixel point in this region, this pixel point is incorporated into this region; otherwise, the growth of this region stops.

[0068] It can be understood that the difference factor can represent the possibility that this pixel point and the previous growing pixel point in this region belong to the same region. When the difference factor of this pixel point is not greater than the difference factor of the previous growing pixel point in this region, it indicates that the possibility that this pixel point still belongs to this region is relatively large, and growth can continue at this time. On the contrary, when the difference factor of this pixel point is greater than the difference factor of the previous growing pixel point in this region, it indicates that this pixel point belongs to other regions, and growth should stop at this time.

[0069] In one embodiment, after using the seed points, the growth criterion evaluation model, and the region growing algorithm to detect defects in the surface image, the defect detection results can also be marked on the surface image, and a preset algorithm can be used to verify the defect detection results.

[0070] Among them, morphological operations can be used to process each region obtained by growth, further extract the boundaries of the defect regions, and then mark the defect results on the surface image.

[0071] A method for detecting surface defects of an elevator sliding bearing proposed in an embodiment of the present application calculates the adjacent difference degree and continuity degree of each pixel point in the surface image, and constructs a growth criterion evaluation model based on the adjacent difference degree and continuity degree of each pixel point. Both the adjacent difference degree and continuity degree can characterize the possibility that each pixel point and the surrounding region have the same texture difference degree, that is, both belong to the normal region or both belong to the defect region, solving the problem of defect omission and defect mis - detection when using the region growing algorithm for defect detection when the seed points and growth criteria are set improperly. It realizes the accurate identification and complete elimination of defect regions, thereby improving the accuracy and reliability of defect detection.

[0072] Based on the above - mentioned embodiment, Figure 2 For the structural block diagram of a device for detecting surface defects of an elevator sliding bearing according to an embodiment of the present application, as Figure 2 shown, the device for detecting surface defects of an elevator sliding bearing may include: a seed point selection module 210, a feature calculation module 220, a model construction module 230, and a defect detection module 240, where,

[0073] The seed point selection module 210 is used to obtain the surface image of the elevator sliding bearing and select seed points based on the surface image;

[0074] The feature calculation module 220 is used to calculate the adjacent difference degree and the continuity degree of each pixel point in the surface image;

[0075] The model construction module 230 is used to construct a growth criterion evaluation model based on the adjacent difference degree and the continuity degree of each pixel point;

[0076] The defect detection module 240 is used to perform defect detection on the surface image by using the seed points, the growth criterion evaluation model and the region growing algorithm.

[0077] In an exemplary embodiment, the seed point selection module 210 can also be used to calculate the gradient value of each pixel point in the surface image; and determine the seed points based on the gradient value of each pixel point.

[0078] In an exemplary embodiment, the feature calculation module 220 can also be used to perform gray level classification on all pixel points in the surface image to obtain the gray level corresponding to each pixel point; calculate the number of consecutive rows and the number of consecutive columns of the gray level corresponding to each pixel point in the surface image; and determine the adjacent difference degree of each pixel point based on the number of consecutive rows and the number of consecutive columns.

[0079] In an exemplary embodiment, the feature calculation module 220 can also use the following formula (1) to calculate the continuity degree of each pixel point:

[0080] δ i =|l ir -l' ir |+|l ic -l' ic | (1)

[0081] Wherein, δ i represents the adjacent difference degree of the i-th pixel point, l ir represents the number of consecutive columns of the i-th pixel point, l ic represents the number of consecutive rows of the i-th pixel point, l' ir represents the number of consecutive columns of the pixel point with the same gray level as the i-th pixel point and the smallest distance from the i-th pixel point in the same column as the i-th pixel point, l' ic represents the number of consecutive rows of the pixel point with the same gray level as the i-th pixel point and the smallest distance from the i-th pixel point in the same row as the i-th pixel point.

[0082] In an exemplary embodiment, the feature calculation module 220 may further be configured to calculate the entropy value of the gray-level co-occurrence matrix of each pixel point within a preset region; and determine the continuity degree of each pixel point based on the difference between the entropy value of each pixel point and the entropy value of its adjacent pixel point.

[0083] In an exemplary embodiment, the defect detection module 240 may further be configured to determine a difference measurement factor based on the adjacent difference degree and the continuity degree of each pixel point; and construct a growth criterion evaluation model based on the difference measurement factor of each pixel point.

[0084] In an exemplary embodiment, the defect detection module 250 may further be configured to mark the defect detection result on the surface image; and verify the defect detection result by using a preset algorithm.

[0085] Those skilled in the art should understand that the division of each module in the embodiment is only a logical function division. In actual application, it can be fully or partially integrated into one or more actual carriers. And these modules can all be implemented in the form of software called by a processing unit, or all in the form of hardware, or in the form of a combination of software and hardware. It should be noted that each module in a surface defect detection device for an elevator sliding bearing in this embodiment corresponds one by one to each step in a surface defect detection method for an elevator sliding bearing in the foregoing embodiment. Therefore, the specific implementation manner of this embodiment may refer to the implementation manner of the foregoing surface defect detection method for an elevator sliding bearing, and details are not described herein again.

[0086] On the basis of the above embodiments, Figure 3 FIG. is a schematic structural diagram of a surface defect detection device for an elevator sliding bearing according to an embodiment of the present application. As Figure 3 shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communication interface 320, and the memory 330 complete mutual communication through the communication bus 340. The processor 310 may call logical instructions in the memory 330 to execute a surface defect detection method for an elevator sliding bearing. The method includes: obtaining a surface image of an elevator sliding bearing and selecting seed points based on the surface image; calculating the adjacent difference degree and the continuity degree of each pixel point in the surface image; constructing a growth criterion evaluation model based on the adjacent difference degree and the continuity degree of each pixel point; and performing defect detection on the surface image by using the seed points, the growth criterion evaluation model, and a region growing algorithm.

[0087] In addition, when the logical instructions in the above-mentioned memory 330 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0088] On the basis of the above embodiments, on the other hand, the present invention further provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the elevator sliding bearing surface defect detection method provided by the above-mentioned various methods. The method includes: obtaining a surface image of the elevator sliding bearing and selecting seed points based on the surface image; calculating the adjacent difference degree and the continuity degree of each pixel point in the surface image; constructing a growth criterion evaluation model based on the adjacent difference degree and the continuity degree of each pixel point; and using the seed points, the growth criterion evaluation model, and the region growing algorithm to perform defect detection on the surface image.

[0089] On the basis of the above embodiments, on the other hand, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the elevator sliding bearing surface defect detection method provided by the above-mentioned various methods. The method includes: obtaining a surface image of the elevator sliding bearing and selecting seed points based on the surface image; calculating the adjacent difference degree and the continuity degree of each pixel point in the surface image; constructing a growth criterion evaluation model based on the adjacent difference degree and the continuity degree of each pixel point; and using the seed points, the growth criterion evaluation model, and the region growing algorithm to perform defect detection on the surface image.

[0090] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A method for detecting surface defects of an elevator sliding bearing, characterized in that, Including: Obtain the surface image of the elevator sliding bearing and select seed points based on the surface image; Calculate the adjacent difference degree and continuity degree of each pixel point in the surface image; Construct a growth criterion evaluation model based on the adjacent difference degree and the continuity degree of each pixel point; Use the seed points, the growth criterion evaluation model and the region growing algorithm to perform defect detection on the surface image.

2. The elevator sliding bearing surface defect detection method according to claim 1, characterized in that The selecting seed points based on the surface image includes: Calculate the gradient value of each pixel point in the surface image; Determine seed points based on the gradient values of each pixel point.

3. The elevator sliding bearing surface defect detection method according to claim 1, characterized in that, The calculating the adjacent difference degree of each pixel point in the surface image includes: Perform gray level grading on all pixel points in the surface image to obtain the gray level corresponding to each pixel point; Calculate the number of consecutive rows and the number of consecutive columns of the gray level corresponding to each pixel point in the surface image; Determine the adjacent difference degree of each pixel point based on the number of consecutive rows and the number of consecutive columns.

4. The elevator sliding bearing surface defect detection method according to claim 3, characterized in that, The determining the adjacent difference degree of each pixel point based on the number of consecutive rows and the number of consecutive columns includes: Use the following formula (1) to calculate the continuity degree of each pixel point: δ i = |l ir - l' ir | + |l ic - l' ic | (1) Among them, δ i represents the adjacent difference degree of the i-th pixel point, l ir represents the column consecutive number of the i-th pixel point, l ic represents the row consecutive number of the i-th pixel point, l′ ir represents the column consecutive number of the pixel point with the same gray level as the i-th pixel point and the smallest distance from the i-th pixel point in the same column as the i-th pixel point, l′ ic represents the row consecutive number of the pixel point with the same gray level as the i-th pixel point and the smallest distance from the i-th pixel point in the same row as the i-th pixel point.

5. The elevator sliding bearing surface defect detection method according to claim 1, characterized in that, The calculating the continuity degree of each pixel point in the surface image includes: Calculate the entropy value of the gray level co-occurrence matrix of each pixel point in the preset region; Determine the continuity degree of each pixel point based on the difference between the entropy value of each pixel point and the entropy value of its adjacent pixel points.

6. The method for detecting surface defects of an elevator sliding bearing according to claim 1, characterized in that, The constructing a growth criterion evaluation model based on the adjacent difference degree and the continuity degree of each pixel point includes: Determine a difference measure factor based on the adjacent difference degree and the continuity degree of each pixel point; Construct a growth criterion evaluation model based on the difference measure factors of each pixel point.

7. The elevator sliding bearing surface defect detection method according to claim 1, characterized in that, After the performing defect detection on the surface image using the seed points, the growth criterion evaluation model and the region growing algorithm, the method further includes: Mark the defect detection result on the surface image; Verify the defect detection result using a preset algorithm.

8. An elevator sliding bearing surface defect detection device, characterized in that Including: A seed point selection module, configured to obtain the surface image of the elevator sliding bearing and select seed points based on the surface image; A feature calculation module, configured to calculate the adjacent difference degree and the continuity degree of each pixel point in the surface image; A model construction module, configured to construct a growth criterion evaluation model based on the adjacent difference degree and the continuity degree of each pixel point; A defect detection module, configured to perform defect detection on the surface image using the seed points, the growth criterion evaluation model and the region growing algorithm.

9. An elevator sliding bearing surface defect detection device, characterized in that, Including: At least one processor; And, a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the elevator sliding bearing surface defect detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the elevator sliding bearing surface defect detection method according to any one of claims 1 to 7.

Images