Glass insulator string smudginess detection method, device, equipment and medium
Through a depth camera, the glass insulator string images are collected and combined with AI visual model, the type and location of dirty stains are automatically detected, which solves the problem of low dirt detection efficiency in the existing technology, and achieves efficient and accurate dirt detection and treatment.
Patent Information
- Application Number
- CN202411764132.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-03
- Publication Date
- 2025-03-28
AI Technical Summary
In the prior art, the stain detection efficiency of glass insulator strings is low. It requires manual confirmation of the type of stain before preparing a cleaning plan, which wastes labor costs and is inefficient.
The depth camera is used to collect images of glass insulator strings, and automatically detect dirty types and locations through partitioning processing and AI visual model training to achieve automatic detection.
It improves the accuracy and efficiency of dirty stain detection of glass insulator strings, reduces labor costs, and improves the efficiency of dirty treatment.
Smart Images
Figure CN119722595A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and medium for detecting contamination of a glass insulator string. Background Art
[0002] As an important component of power equipment, glass insulator strings play the role of isolating power equipment from the ground. However, after long-term use, a lot of dirt will accumulate on the surface of glass insulator strings due to environmental factors such as rain and dust. This dirt will reduce the insulation performance of the glass insulator strings, thereby increasing the risk of equipment failure.
[0003] In view of the above problems, the prior art mainly detects the dirt type of the glass insulator string manually. Therefore, it is necessary to manually confirm the dirt type each time and then prepare a corresponding cleaning plan, which not only wastes manpower costs, but also has low detection and cleaning efficiency.
[0004] In view of this, how to efficiently and accurately automatically detect the contamination of glass insulator strings has become an urgent problem to be solved. Summary of the invention
[0005] In view of the above, it is necessary to provide a method, device, equipment and medium for detecting contamination of a glass insulator string, aiming to solve the problem of low efficiency of detecting contamination of a glass insulator string.
[0006] In a first aspect, an embodiment of the present application provides a method for detecting contamination of a glass insulator string, the method comprising:
[0007] Acquire multiple glass insulator strings, use a depth camera to collect an image of each glass insulator string as each initial image, and perform partition processing on each glass insulator string to obtain a sub-region of each glass insulator string;
[0008] Detect the type and location of dirt on each glass insulator string;
[0009] Mark the dirt position information in each initial image according to the sub-region to which the dirt position on each glass insulator string belongs, and mark the dirt type corresponding to each initial image according to the dirt type on each glass insulator string;
[0010] Retrieving an AI visual model with a classification function, and using each marked initial image as a training sample to train the AI visual model, to obtain a glass insulator string contamination detection model;
[0011] In response to a dirt detection instruction for a target glass insulator string, collecting an image of the target glass insulator string as a target image;
[0012] The target image is input into the glass insulator string contamination detection model to obtain target contamination position information of the target glass insulator string.
[0013] In a second aspect, an embodiment of the present application further provides a glass insulator string dirt detection device, the glass insulator string dirt detection device comprising:
[0014] A partitioning unit is used to obtain a plurality of glass insulator strings, collect an image of each glass insulator string using a depth camera as each initial image, and perform partitioning processing on each glass insulator string to obtain a sub-region of each glass insulator string;
[0015] A detection unit, used to detect the type and location of dirt on each glass insulator string;
[0016] A marking unit, used to mark the dirt position information in each initial image according to the sub-region to which the dirt position on each glass insulator string belongs, and mark the dirt type corresponding to each initial image according to the type of dirt on each glass insulator string;
[0017] A training unit, used to call an AI visual model with a classification function, and train the AI visual model using each marked initial image as a training sample to obtain a glass insulator string contamination detection model;
[0018] A collection unit, configured to collect an image of the target glass insulator string as a target image in response to a dirt detection instruction for the target glass insulator string;
[0019] An input unit is used to input the target image into the glass insulator string contamination detection model to obtain target contamination position information of the target glass insulator string.
[0020] In a third aspect, an embodiment of the present application further provides a computer device, the computer device comprising:
[0021] a memory storing at least one instruction; and
[0022] The processor executes the instructions stored in the memory to implement the glass insulator string contamination detection method.
[0023] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, and the at least one instruction is executed by a processor in a computer device to implement the glass insulator string contamination detection method.
[0024] The embodiments of the present application provide a method, device, equipment and medium for detecting contamination of a glass insulator string. The method has the following beneficial effects: by using a depth camera to collect images of each glass insulator string as each initial image, a more comprehensive and more accurate image of the glass insulator string can be collected; each glass insulator string is partitioned so as to perform targeted contamination detection according to the transmittance and position of different sub-regions, thereby improving the accuracy of the detection result; an AI visual model is trained by combining images of glass insulator strings marked with contamination position information and contamination type, and the contamination detection model of the glass insulator string obtained by training is used for contamination detection, which can realize automatic detection of the contamination position of the glass insulator string by combining artificial intelligence means, thereby not only reducing labor costs, but also improving the efficiency of contamination treatment. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0026] Figure 1 It is a flow chart of a preferred embodiment of the glass insulator string contamination detection method of the present application;
[0027] Figure 2 is a schematic diagram of a glass insulator string of the present application;
[0028] Figure 3 It is a partition diagram of the glass insulator string of the present application;
[0029] Figure 4 It is a schematic diagram of the severity level of dirtiness of the glass insulator string of the present application;
[0030] Figure 5 This is a functional module diagram of a preferred embodiment of the glass insulator string dirt detection device of the present application;
[0031] Figure 6 It is a structural schematic diagram of a computer device of a preferred embodiment of the present application for implementing a method for detecting contamination of a glass insulator string. DETAILED DESCRIPTION
[0032] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0033] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.
[0034] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.
[0035] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0036] The embodiments of the present application provide a method, device, equipment and medium for detecting contamination of a glass insulator string, wherein the method can be applied to a server.
[0037] The executor of the glass insulator string contamination detection method may be the glass insulator string contamination detection device provided in the embodiment of the present application, or an electronic device integrating the glass insulator string contamination detection device, wherein the glass insulator string contamination detection device may be implemented in hardware or software, and the electronic device may be a server, specifically a control device in the server, or a terminal having a communication connection with the control device.
[0038] See also Figure 1 , Figure 1 This is a flow chart of a preferred embodiment of the glass insulator string contamination detection method of the present application. Specifically, the glass insulator string contamination detection method includes the following steps S110-S160.
[0039] S110, obtaining a plurality of glass insulator strings, using a depth camera to collect an image of each glass insulator string as each initial image, and performing a partitioning process on each glass insulator string to obtain a sub-region of each glass insulator string.
[0040] See also Figure 2 , Figure 2Schematic diagram of the glass insulator string of the present application. The glass insulator string is a component composed of two or more glass insulator elements, which is used to suspend the conductor and insulate the conductor from the tower and the ground. The glass insulator string is usually composed of glass insulators, steel caps, bolts and other components. The glass insulator string is widely used in transmission lines, mainly used to increase the creepage distance and ensure the electrical insulation between the conductor and the tower. The voltage level of the transmission line can also be identified by the glass insulator string. Generally, the longer the glass insulator string is, the higher the voltage level of the transmission line is.
[0041] After long-term use, the glass insulator string will reduce its insulation performance due to dirt accumulation on the surface, thereby increasing the risk of equipment failure. Therefore, it is necessary to perform timely and effective dirt detection on the glass insulator string to reduce safety risks.
[0042] In this embodiment, when the depth camera is used to collect the image of each glass insulator string, each glass insulator string needs to be fully photographed from various angles to ensure the diversity and comprehensiveness of the data.
[0043] In this embodiment, the partitioning process for each glass insulator string to obtain a sub-region of each glass insulator string includes:
[0044] For each glass insulator string, project from any one surface to the other surface to obtain the concentric circles corresponding to each glass insulator string;
[0045] The corresponding glass insulator string is partitioned according to each ring in each concentric circle to obtain a sub-region of each glass insulator string.
[0046] For example: See Figure 3 , Figure 3 It is a schematic diagram of the partitioning of the glass insulator string of the present application. Figure 3 The upper middle figure is a side view of the glass insulator string. From the side view, it can be seen that whether projecting from left to right (i.e., from the convex surface to the concave surface) or from right to left (i.e., from the concave surface to the convex surface), the concentric circles in the figure below can be obtained, and each ring in the concentric circles is a sub-area.
[0047] The above-mentioned partitioning process can facilitate subsequent targeted dirt detection according to the characteristics of different sub-areas.
[0048] S120, detecting the type and position of dirt on each glass insulator string.
[0049] In this embodiment, the detecting the type and location of dirt on each glass insulator string includes:
[0050] For each glass insulator string, detect the transmittance, pixel value and reflectivity of each sub-region in the initial image corresponding to the glass insulator string, and obtain the transmittance threshold corresponding to each sub-region in the initial image corresponding to the glass insulator string;
[0051] When there is a target area in any sub-area whose transmittance is less than a transmittance threshold corresponding to the arbitrary sub-area, the transmittance of the target area is determined as a target transmittance, and the target area is determined as a dirty area in the arbitrary sub-area;
[0052] Acquire the contour coordinates of the dirty area, and generate the location of the dirt on the glass insulator string according to the contour coordinates and the arbitrary sub-area;
[0053] Acquire the pixel value of the dirty area as the target pixel value, acquire the reflectivity of the dirty area as the target reflectivity, and acquire the reflectivity threshold value;
[0054] When the target pixel value satisfies the first pixel value range and the target reflectivity is less than the reflectivity threshold, determining that the target dirt in the dirty area is bird excrement;
[0055] When the target pixel value satisfies the second pixel value range and the target reflectivity is less than the reflectivity threshold, determining that the target dirt in the dirty area is dust;
[0056] When the target pixel value satisfies the second pixel value range and the target reflectivity is greater than or equal to the reflectivity threshold, determining that the target dirt in the dirty area is oil dirt;
[0057] The type of dirt on the glass insulator string is determined according to the target dirt and the target light transmittance.
[0058] For example: See Figure 4 , Figure 4 Schematic diagram of the severity of contamination of the glass insulator string of the present application. Figure 4In the glass insulator string in , there is an obvious decrease in transmittance in the two sub-regions corresponding to the two circular rings outside the concentric circles, that is, a dirty region with a transmittance threshold value corresponding to the two sub-regions. Therefore, the location of the dirt on the glass insulator string can be generated according to the contour coordinates of the dirty region and the sub-region to which it belongs, such as region A (x, y, z), region B (x1, y1, z1), etc. Further, since the colors and reflectivity of different dirt are different, bird excrement, dust, or oil dirt among the common dirt on the glass insulator string can be further detected according to the pixel value and reflectivity of the dirty region. Obviously, bird excrement will have obvious color characteristics, so the pixel value will meet the first pixel value range, but the reflectivity will be less than a certain reflectivity threshold; the pixel value of dust meets the second pixel value range, and is similar to the reflectivity of bird excrement, and is also less than a certain reflectivity threshold; the pixel value of oil dirt also meets the second pixel value range, but the reflectivity will be significantly higher, greater than or equal to a certain reflectivity threshold.
[0059] Further, determining the type of contamination on the glass insulator string according to the target contamination and the target light transmittance includes:
[0060] Obtaining a dirt type mapping table corresponding to each sub-region in the initial image corresponding to the glass insulator string; wherein the dirt type mapping table is used to record the corresponding relationship between dirt, dirt severity level and transmittance range in each sub-region;
[0061] Traversing the dirt type mapping table using the target dirt and the target light transmittance;
[0062] Determining the traversed dirt severity level as the target dirt severity level corresponding to the target dirt;
[0063] The type of contamination on the glass insulator string is generated according to the target contamination and the target contamination severity level.
[0064] For example: Please continue to Figure 4. The severity of the dirt is related to the transmittance. The more serious the dirt, the lower the transmittance. At the same time, for the sub-areas corresponding to different circular rings, due to the different overlaps after mapping, the transmittance of each sub-area is also different. Obviously, the closer the circular rings are to the center of the concentric circles, the higher the overlap of the sub-areas corresponding to the sub-areas, and the lower their own transmittance. Conversely, the farther the circular rings are from the center of the concentric circles, the lower the overlap of the sub-areas corresponding to the sub-areas, and the higher their own transmittance. Therefore, this embodiment establishes a correspondence between the dirt severity level, dirt and transmittance range of each sub-area according to the transmittance of different sub-areas, and forms a dirt type mapping table, so that the corresponding target dirt severity level can be directly matched in the dirt type mapping table according to the detected target dirt and target transmittance, and the type of dirt on the corresponding glass insulator string is generated according to the target dirt and the target dirt severity level. Figure 4 Taking the severity level of oil pollution in the example, the outermost area has the lowest transmittance, which can be judged as heavy oil pollution, the middle area has a higher transmittance, which can be judged as light oil pollution, and the innermost area can be judged as moderate oil pollution. The judgment result conforms to the corresponding relationship between the transmittance range of oil pollution in each sub-area and the severity level of dirt pollution.
[0065] Among them, the transmittance threshold, the first pixel value range, the second pixel value range, the reflectance threshold, the dirt, dirt severity level, and transmittance range in the dirt type mapping table can all be configured according to actual conditions.
[0066] Through the above embodiments, the type and position of dirt on each glass insulator string can be automatically detected according to the transmittance properties of different sub-regions and the characteristics of each dirt type.
[0067] S130, marking the dirt position information in each initial image according to the sub-region to which the dirt position on each glass insulator string belongs, and marking the dirt type corresponding to each initial image according to the dirt type on each glass insulator string.
[0068] In the above embodiment, the dirt position information and dirt type in each initial image are marked to serve as training targets for subsequent model training.
[0069] S140, calling an AI (Artificial Intelligence) visual model with a classification function, and using each marked initial image as a training sample to train the AI visual model, to obtain a glass insulator string contamination detection model.
[0070] In this embodiment, the AI vision model may include, but is not limited to: Convolutional Neural Networks (CNN), Residual Network (ResNet), YOLO (You Only Look Once) series models, etc.
[0071] In this embodiment, during the training process, the label of each training sample can be used as a training target, and the AI visual model can be trained through continuous iteration until the model parameters converge and the training is stopped, and the currently obtained model is determined as the glass insulator string contamination detection model.
[0072] S150, in response to a dirt detection instruction for a target glass insulator string, collecting an image of the target glass insulator string as a target image.
[0073] In this embodiment, the dirt detection instruction can be triggered by relevant staff according to actual detection requirements.
[0074] In this embodiment, a depth camera may be used to capture an image of the target glass insulator string as the target image.
[0075] S160, inputting the target image into the glass insulator string contamination detection model to obtain target contamination position information of the target glass insulator string.
[0076] Through the above embodiments, effective detection of dirt can be achieved.
[0077] Of course, in other embodiments, in order to deal with dirt in a timely manner, the optimal dirt treatment method corresponding to the model output can also be used simultaneously.
[0078] Specifically, the method further includes:
[0079] Obtain historical glass insulator string contamination treatment data;
[0080] According to the type and location of the dirt on each glass insulator string, a corresponding processing method is obtained from the historical glass insulator string dirt processing data to obtain the dirt processing method on each glass insulator string;
[0081] Mark the dirt treatment method corresponding to each initial image according to the dirt treatment method on each glass insulator string;
[0082] Using each marked initial image as a training sample to perform supplementary training on the glass insulator string contamination detection model to obtain an updated glass insulator string contamination detection model;
[0083] The target image is input into the updated glass insulator string contamination detection model to obtain target contamination position information and a target contamination treatment method of the target glass insulator string.
[0084] For example: for light dust, clean water can be used for cleaning, for moderate oil stains, detergent can be used for cleaning, and for heavy bird droppings, high-pressure cleaning can be used.
[0085] Through the above embodiments, the best treatment method corresponding to each type of dirt can be selected according to historical data.
[0086] In this embodiment, after obtaining the target contamination position information and the target contamination treatment method of the target glass insulator string, the method further includes:
[0087] Determine a target cleaning device according to the target dirt position information and the target dirt treatment method;
[0088] Generate a dirt cleaning prompt according to the target dirt location information, the target dirt treatment method and the target cleaning device;
[0089] The dirt cleaning reminder is sent to a designated terminal device.
[0090] The designated terminal device may be a mobile phone, computer or other terminal of the relevant staff member.
[0091] Wherein, the target cleaning device may be a high-pressure cleaning device or the like.
[0092] Through the above embodiments, relevant staff can be notified in time to assist them in responding quickly, thereby further improving the cleaning efficiency.
[0093] In this embodiment, the method further includes:
[0094] When a new type of dirt is detected, images of glass insulator strings corresponding to the new type of dirt are collected to construct a supplementary training set;
[0095] The glass insulator string contamination detection model is supplementarily trained using the supplementary training set.
[0096] Through the above embodiments, the model can be supplemented with training for newly added dirt types, thereby improving the generalization ability.
[0097] It can be seen from the above technical solutions that the present application can use a depth camera to capture an image of each glass insulator string as each initial image, and can capture a more comprehensive and more accurate glass insulator string image; perform partitioning on each glass insulator string so as to perform targeted dirt detection according to the transmittance and position of different sub-areas, thereby improving the accuracy of the detection results; train an AI visual model based on the image of the glass insulator string marked with dirt location information and dirt type, and use the trained glass insulator string dirt detection model to perform dirt detection, which can combine artificial intelligence means to realize automatic detection of the dirt position of the glass insulator string, which not only reduces labor costs, but also improves the efficiency of dirt treatment.
[0098] Figure 5 is a schematic block diagram of a glass insulator string dirt detection device provided in an embodiment of the present application. Figure 5 As shown, corresponding to the above glass insulator string contamination detection method, the present application also provides a glass insulator string contamination detection device. The glass insulator string contamination detection device includes a unit for executing the above glass insulator string contamination detection method, and the device can be configured on a server. Specifically, please refer to Figure 5 The glass insulator string dirt detection device 500 includes a partition unit 501, a detection unit 502, a marking unit 503, a training unit 504, a collection unit 505, and an input unit 506, wherein:
[0099] The partitioning unit 501 is used to obtain multiple glass insulator strings, use a depth camera to collect an image of each glass insulator string as each initial image, and perform partitioning processing on each glass insulator string to obtain a sub-region of each glass insulator string;
[0100] The detection unit 502 is used to detect the type and location of dirt on each glass insulator string;
[0101] The marking unit 503 is used to mark the dirt position information in each initial image according to the sub-region to which the dirt position on each glass insulator string belongs, and mark the dirt type corresponding to each initial image according to the type of dirt on each glass insulator string;
[0102] The training unit 504 is used to retrieve an AI visual model with a classification function, and train the AI visual model using each marked initial image as a training sample to obtain a glass insulator string contamination detection model;
[0103] The acquisition unit 505 is used to acquire an image of the target glass insulator string as a target image in response to a dirt detection instruction for the target glass insulator string;
[0104] The input unit 506 is used to input the target image into the glass insulator string contamination detection model to obtain target contamination position information of the target glass insulator string.
[0105] It can be seen from the above technical solutions that the present application can use a depth camera to capture an image of each glass insulator string as each initial image, and can capture a more comprehensive and more accurate glass insulator string image; perform partitioning on each glass insulator string so as to perform targeted dirt detection according to the transmittance and position of different sub-areas, thereby improving the accuracy of the detection results; train an AI visual model based on the image of the glass insulator string marked with dirt location information and dirt type, and use the trained glass insulator string dirt detection model to perform dirt detection, which can combine artificial intelligence means to realize automatic detection of the dirt position of the glass insulator string, which not only reduces labor costs, but also improves the efficiency of dirt treatment.
[0106] The above-mentioned glass insulator string dirt detection device can be implemented in the form of a computer program. The computer program can be used in Figure 6 The electronic device shown is running.
[0107] See also Figure 6 , Figure 6 600 is a schematic block diagram of an electronic device provided in an embodiment of the present application. The electronic device 600 may be a server, specifically a control device in the server, or a terminal having a communication connection with the control device.
[0108] See also Figure 6 The electronic device 600 includes a processor 602 , a memory and a network interface 605 connected via a system bus 601 , wherein the memory may include a non-volatile storage medium 603 and an internal memory 604 .
[0109] The non-volatile storage medium 603 can store an operating system 6031 and a computer program 6032. The computer program 6032 includes program instructions, and when the program instructions are executed, the processor 602 can execute a glass insulator string contamination detection method.
[0110] The processor 602 is used to provide computing and control capabilities to support the operation of the entire electronic device 600 .
[0111] The internal memory 604 provides an environment for the operation of the computer program 6032 in the non-volatile storage medium 603. When the computer program 6032 is executed by the processor 602, the processor 602 can execute a method for detecting contamination of a glass insulator string.
[0112] The network interface 605 is used to communicate with other devices over the network. Figure 6 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device 600 to which the scheme of the present application is applied. The specific electronic device 600 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0113] The processor 602 is used to run a computer program 6032 stored in the memory to implement the following steps:
[0114] Acquire multiple glass insulator strings, use a depth camera to collect an image of each glass insulator string as each initial image, and perform partition processing on each glass insulator string to obtain a sub-region of each glass insulator string;
[0115] Detect the type and location of dirt on each glass insulator string;
[0116] Mark the dirt position information in each initial image according to the sub-region to which the dirt position on each glass insulator string belongs, and mark the dirt type corresponding to each initial image according to the dirt type on each glass insulator string;
[0117] Retrieving an AI visual model with a classification function, and using each marked initial image as a training sample to train the AI visual model, to obtain a glass insulator string contamination detection model;
[0118] In response to a dirt detection instruction for a target glass insulator string, collecting an image of the target glass insulator string as a target image;
[0119] The target image is input into the glass insulator string contamination detection model to obtain target contamination position information of the target glass insulator string.
[0120] It should be understood that in the embodiment of the present application, the processor 602 may be a central processing unit (CPU), and the processor 602 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0121] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.
[0122] Therefore, the present application also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the following steps:
[0123] Acquire multiple glass insulator strings, use a depth camera to collect an image of each glass insulator string as each initial image, and perform partition processing on each glass insulator string to obtain a sub-region of each glass insulator string;
[0124] Detect the type and location of dirt on each glass insulator string;
[0125] Mark the dirt position information in each initial image according to the sub-region to which the dirt position on each glass insulator string belongs, and mark the dirt type corresponding to each initial image according to the dirt type on each glass insulator string;
[0126] Retrieving an AI visual model with a classification function, and using each marked initial image as a training sample to train the AI visual model, to obtain a glass insulator string contamination detection model;
[0127] In response to a dirt detection instruction for a target glass insulator string, collecting an image of the target glass insulator string as a target image;
[0128] The target image is input into the glass insulator string contamination detection model to obtain target contamination position information of the target glass insulator string.
[0129] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.
[0130] It should be noted that the data involved in this application were obtained legally.
[0131] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0132] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.
[0133] The steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present application can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0134] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for an electronic device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.
[0135] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A method for detecting contamination of a glass insulator string, characterized in that: The glass insulator string contamination detection method comprises: Acquire multiple glass insulator strings, use a depth camera to collect an image of each glass insulator string as each initial image, and perform partition processing on each glass insulator string to obtain a sub-region of each glass insulator string; Detect the type and location of dirt on each glass insulator string; Mark the dirt position information in each initial image according to the sub-region to which the dirt position on each glass insulator string belongs, and mark the dirt type corresponding to each initial image according to the dirt type on each glass insulator string; Retrieving an AI visual model with a classification function, and using each marked initial image as a training sample to train the AI visual model, to obtain a glass insulator string contamination detection model; In response to a dirt detection instruction for a target glass insulator string, collecting an image of the target glass insulator string as a target image; The target image is input into the glass insulator string contamination detection model to obtain target contamination position information of the target glass insulator string.
2. The method for detecting contamination of a glass insulator string according to claim 1, characterized in that: The partitioning process for each glass insulator string to obtain a sub-region of each glass insulator string includes: For each glass insulator string, project from any one surface to the other surface to obtain the concentric circles corresponding to each glass insulator string; The corresponding glass insulator string is partitioned according to each ring in each concentric circle to obtain a sub-region of each glass insulator string.
3. The method for detecting contamination of a glass insulator string according to claim 1, characterized in that: The detection of the type and location of dirt on each glass insulator string includes: For each glass insulator string, detect the transmittance, pixel value and reflectivity of each sub-region in the initial image corresponding to the glass insulator string, and obtain the transmittance threshold corresponding to each sub-region in the initial image corresponding to the glass insulator string; When there is a target area in any sub-area whose transmittance is less than a transmittance threshold corresponding to the arbitrary sub-area, the transmittance of the target area is determined as a target transmittance, and the target area is determined as a dirty area in the arbitrary sub-area; Acquire the contour coordinates of the dirty area, and generate the location of the dirt on the glass insulator string according to the contour coordinates and the arbitrary sub-area; Acquire the pixel value of the dirty area as the target pixel value, acquire the reflectivity of the dirty area as the target reflectivity, and acquire the reflectivity threshold value; When the target pixel value satisfies the first pixel value range and the target reflectivity is less than the reflectivity threshold, determining that the target dirt in the dirty area is bird excrement; When the target pixel value satisfies the second pixel value range and the target reflectivity is less than the reflectivity threshold, determining that the target dirt in the dirty area is dust; When the target pixel value satisfies the second pixel value range and the target reflectivity is greater than or equal to the reflectivity threshold, determining that the target dirt in the dirty area is oil dirt; The type of dirt on the glass insulator string is determined according to the target dirt and the target light transmittance.
4. The method for detecting contamination of a glass insulator string according to claim 3, characterized in that: Determining the type of contamination on the glass insulator string according to the target contamination and the target light transmittance includes: Obtaining a dirt type mapping table corresponding to each sub-region in the initial image corresponding to the glass insulator string; wherein the dirt type mapping table is used to record the corresponding relationship between dirt, dirt severity level and transmittance range in each sub-region; Traversing the dirt type mapping table using the target dirt and the target light transmittance; Determining the traversed dirt severity level as the target dirt severity level corresponding to the target dirt; The type of contamination on the glass insulator string is generated according to the target contamination and the target contamination severity level.
5. The method for detecting contamination of a glass insulator string according to claim 1, characterized in that: The method further comprises: Obtain historical glass insulator string contamination treatment data; According to the type and location of the dirt on each glass insulator string, a corresponding processing method is obtained from the historical glass insulator string dirt processing data to obtain the dirt processing method on each glass insulator string; Mark the dirt treatment method corresponding to each initial image according to the dirt treatment method on each glass insulator string; Using each marked initial image as a training sample to perform supplementary training on the glass insulator string contamination detection model to obtain an updated glass insulator string contamination detection model; The target image is input into the updated glass insulator string contamination detection model to obtain target contamination position information and a target contamination treatment method of the target glass insulator string.
6. The method for detecting contamination of a glass insulator string according to claim 5, characterized in that: After obtaining the target contamination position information and the target contamination treatment method of the target glass insulator string, the method further includes: Determine a target cleaning device according to the target dirt location information and the target dirt treatment method; Generate a dirt cleaning prompt according to the target dirt location information, the target dirt treatment method and the target cleaning device; The dirt cleaning reminder is sent to a designated terminal device.
7. The method for detecting contamination of a glass insulator string according to claim 1, characterized in that: The method further comprises: When a new type of dirt is detected, images of glass insulator strings corresponding to the new type of dirt are collected to construct a supplementary training set; The glass insulator string contamination detection model is supplementarily trained using the supplementary training set.
8. A glass insulator string dirt detection device, characterized in that: The glass insulator string dirt detection device comprises: A partitioning unit is used to obtain a plurality of glass insulator strings, collect an image of each glass insulator string using a depth camera as each initial image, and perform partitioning processing on each glass insulator string to obtain a sub-region of each glass insulator string; A detection unit, used to detect the type and location of dirt on each glass insulator string; A marking unit, used to mark the dirt position information in each initial image according to the sub-region to which the dirt position on each glass insulator string belongs, and mark the dirt type corresponding to each initial image according to the type of dirt on each glass insulator string; A training unit, used to call an AI visual model with a classification function, and train the AI visual model using each marked initial image as a training sample to obtain a glass insulator string contamination detection model; A collection unit, configured to collect an image of the target glass insulator string as a target image in response to a dirt detection instruction for the target glass insulator string; An input unit is used to input the target image into the glass insulator string contamination detection model to obtain target contamination position information of the target glass insulator string.
9. A computer device, characterized in that: The computer device comprises: a memory storing at least one instruction; and A processor executes instructions stored in the memory to implement the glass insulator string contamination detection method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and the at least one instruction is executed by a processor in a computer device to implement the glass insulator string contamination detection method according to any one of claims 1 to 7.