Method and system for evaluating pollution degree of insulator by using hyperspectral image

Abstract

The invention relates to a method and system for evaluating the pollution degree of an insulator by using a hyperspectral image, and the method comprises the steps: carrying out the pickup in an obtained hyperspectral image based on an insulator object, and obtaining an insulator hyperspectral image related to the insulator object; performing region division on the insulator hyperspectral image to obtain sub-insulator hyperspectral images; spectral band division is carried out in a set spectral band to obtain an extracted spectral band; extracting contents in the hyperspectral image of the sub-insulator by using an extraction spectral band to obtain a first pollution degree evaluation graph; and converging contents included in the first pollution degree evaluation graph to obtain a second pollution degree evaluation graph. According to the method and the system for evaluating the pollution degree of the insulator by using the hyperspectral image disclosed by the invention, the data processing amount is compressed through a combined processing mode of region division and processing mode transplantation, and meanwhile, interference is reduced through a convergence mode, so that a relatively accurate evaluation result is obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for evaluating the contamination degree of an insulator using a hyperspectral image. Background Art

[0002] The degree of insulator contamination refers to the degree of contamination on the surface of the insulator. The two commonly used evaluation indicators are equivalent salt density and equivalent ash density. The equivalent salt density refers to the amount of NaCl equivalent to the content of conductive substances in the contamination attached to the surface of the insulator per square centimeter (mg / cm 2 ), the equivalent salt density characterizes the conductivity of the insulator after the pollution on the surface is fully dissolved. The increase of the equivalent salt density will significantly reduce the pollution flashover voltage of the insulator.

[0003] Equivalent ash density refers to the mass of insoluble matter attached to the insulator surface per square centimeter (mg / cm 2 ). Ash density has a certain influence on the pollution flashover voltage of insulators. As the ash density increases, the pollution flashover voltage of insulators tends to decrease, but the influence is much weaker than that of salt density.

[0004] The specific measurement method is as follows Remove insulators or simulated contaminated strings from the line and clean and measure them on site; Remove the insulators or simulated contaminated strings from the line and transport them back to the laboratory for cleaning and measurement; Use a sampling towel to wipe the insulator directly on the tower to take samples, and bring the sampling towel back to the laboratory for immersion and testing.

[0005] These measurement methods are difficult to operate because they require manual sampling at fixed points. Currently, research has begun on unmanned sampling methods, such as drone photography sampling and hyperspectral image sampling, all of which can achieve automated sampling.

[0006] The better solution is hyperspectral image sampling, because the information of hyperspectral image sampling is richer, but the interference contained in hyperspectral image sampling is more, and how to solve it needs further research. In addition, the amount of information of hyperspectral image sampling is huge. If the hyperspectral image is processed directly, it is bound to face a huge amount of data, which will cause trouble for continuous monitoring. Summary of the invention

[0007] The present invention provides a method and system for evaluating the contamination degree of insulators using hyperspectral images, which compresses the data processing volume through a combined processing method of area division and processing method transplantation, and reduces interference through a convergence method, so as to obtain a more accurate evaluation result.

[0008] The above object of the present invention is achieved through the following technical solutions: In a first aspect, the present invention provides a method for evaluating the contamination degree of an insulator using a hyperspectral image, comprising: Based on the insulator object, the insulator object is picked up in the obtained hyperspectral image to obtain an insulator hyperspectral image associated with the insulator object, and the insulator object is located inside the insulator hyperspectral image; The insulator hyperspectral image is divided into regions to obtain a sub-insulator hyperspectral image, and the sub-insulator hyperspectral image is in a rectangular shape; Perform spectral band division within a given spectral band to obtain extracted spectral bands; Using the extracted spectral band to extract the content in the insulator hyperspectral image, a first pollution degree evaluation map is obtained; Converging the contents included in the first pollution degree evaluation graph to obtain a second pollution degree evaluation graph; The remaining insulator hyperspectral images are processed in the same manner to obtain the remaining second pollution degree evaluation map.

[0009] In a possible implementation manner of the first aspect, after obtaining the sub-insulator hyperspectral image, the method further includes classifying the sub-insulator hyperspectral image, and classifying the sub-insulator hyperspectral image includes: Acquire a captured image of an insulator object and divide the captured image into regions. The method of dividing the captured image into regions is the same as the method of dividing the insulator hyperspectral image into regions. Selecting at least one position reference point on the captured image after region division; Creating a position reference area on the captured image based on the position reference point; Calculate the position parameters of the pixel points in the position reference area and the corresponding position reference points, the position parameters including distance, relative position and pixel value difference; Classification of sub-insulator hyperspectral images using location parameters.

[0010] In a possible implementation manner of the first aspect, classifying the sub-insulator hyperspectral image using the position parameter includes: Convert the distance, relative position and pixel value difference into a vector, where the starting point of the vector is the position reference point corresponding to the position parameter and the length of the vector is the pixel value difference; Group the vectors according to their length and count the orientation distribution of the vectors in each group; The sub-insulator hyperspectral images are classified according to the orientation distribution. The orientation distribution of the vectors in the two groups should be the same or similar. The classification process also includes assigning numerical values ​​to the vectors in the groups, and the numerical values ​​include positive and negative values.

[0011] In a possible implementation manner of the first aspect, converging the content included in the first pollution degree evaluation graph includes: Decomposing the first pollution degree evaluation graph by using wavelet decomposition to obtain a waveform group; Determine the main waveform in the waveform group based on the length; Determining a derivative waveform associated with the main waveform according to the main waveform; Using the derived waveform obtained to construct a deletion range, the deletion range is constructed using the frequency of the derived waveform; Delete the waveforms in the waveform group that are within the deletion range.

[0012] In a possible implementation manner of the first aspect, determining, according to the main waveform, a derivative waveform associated with the main waveform includes: Determine the endpoints of the main waveform, the endpoints include a starting position endpoint and a cutting position endpoint; Select a waveform associated with the endpoint and record it as a suspected derivative waveform, and the endpoint is located between the starting position point and the ending position point of the suspected derivative waveform; The suspected derivative waveforms are screened using the amplitude to obtain the derivative waveforms, where the amplitude of the derivative waveform is smaller than the amplitude of the main waveform.

[0013] In a possible implementation manner of the first aspect, after deleting the waveforms in the waveform group that are within the deletion range, the method further includes: Comparing the clarity of the first pollution degree evaluation graph and the second pollution degree evaluation graph to obtain a clarity comparison result; The deletion range is adjusted according to the clarity comparison result, and the adjustment of the deletion range includes expanding the deletion range and reducing the deletion range.

[0014] In a possible implementation manner of the first aspect, when the hyperspectral image of the remaining sub-insulator is processed in the same manner, the method further includes: Comparing the clarity of the first pollution degree evaluation graph and the second pollution degree evaluation graph to obtain a clarity comparison result; Adjust the deletion range according to the clarity comparison result, and the adjustment of the deletion range includes expanding the deletion range and reducing the deletion range; The expanded and adjusted deletion range is assigned to other first pollution degree evaluation graphs to obtain second pollution degree evaluation graphs associated with the other first pollution degree evaluation graphs.

[0015] In a second aspect, the present invention provides a device for evaluating the contamination degree of an insulator using a hyperspectral image, comprising: A picking unit is used to pick up the insulator object in the obtained hyperspectral image based on the insulator object to obtain the insulator hyperspectral image associated with the insulator object, wherein the insulator object is located inside the insulator hyperspectral image; A region division unit is used to divide the insulator hyperspectral image into regions to obtain a sub-insulator hyperspectral image, wherein the sub-insulator hyperspectral image is in a rectangular shape; A band division unit is used to divide the spectrum band within a given spectrum band to obtain an extracted spectrum band; A content extraction unit, used for extracting content in the insulator hyperspectral image by using an extracted spectral band to obtain a first pollution degree evaluation map; A convergence processing unit, used for converging the content included in the first pollution degree evaluation graph to obtain a second pollution degree evaluation graph; The first processing unit is used to process the remaining sub-insulator hyperspectral images in the same manner to obtain the remaining second pollution degree evaluation map.

[0016] In a third aspect, the present invention provides a system for evaluating the degree of insulator contamination using a hyperspectral image, the system comprising: one or more memories for storing instructions; and One or more processors, used to call and run the instructions from the memory to execute the method as described in the first aspect and any possible implementation of the first aspect.

[0017] In a fourth aspect, the present invention provides a computer-readable storage medium, the computer-readable storage medium comprising: Program, when the program is executed by a processor, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0018] In a fifth aspect, the present invention provides a computer program product, comprising program instructions, and when the program instructions are executed by a computing device, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0019] In a sixth aspect, the present invention provides a chip system comprising a processor for implementing the functions involved in the above aspects, for example, generating, receiving, sending, or processing the data and / or information involved in the above methods.

[0020] The chip system may be composed of chips, or may include chips and other discrete devices.

[0021] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wired or wireless means, or the processor and the memory can also be coupled on the same device. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1The present invention provides a method for evaluating the degree of insulator contamination using a hyperspectral image.

[0023] Figure 2 It is a schematic diagram of an insulator object provided by the present invention being located inside an insulator hyperspectral image.

[0024] Figure 3 It is a principle schematic diagram of obtaining a hyperspectral image of an insulator provided by the present invention.

[0025] Figure 4 It is a schematic diagram of selecting position reference points and pixel points provided by the present invention.

[0026] Figure 5 It is a schematic diagram of the relative positions of a derived waveform and a main waveform provided by the present invention. DETAILED DESCRIPTION

[0027] In order to more clearly understand the technical solution of the present invention, the relevant contents are first introduced.

[0028] Simply put, a hyperspectral image is a superposition of multiple grayscale images, each of which represents a spectral band.

[0029] For example, a general two-dimensional image representation has 255*255 pixels, which means that the image has 255*255 pixels. It can be a grayscale image or a color image, and the relevant information is contained in each pixel.

[0030] If a hyperspectral image of the same size contains information of 200 spectral bands, it should be represented as 255*255*200, which means that each pixel has 200-dimensional spectral domain information, just like 200 255*255 two-dimensional images are superimposed together. The grayscale values ​​of pixels at the same position in the 200 images are plotted as a curve to represent the spectral domain information of this pixel. For the same position, correct information and interference information may be generated at the same time. The reasons for the interference information are scattering, refraction, reflection and other reasons.

[0031] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings.

[0032] The present invention discloses a method for evaluating the degree of insulator contamination using hyperspectral images. Figure 1 In some examples, the method for evaluating the degree of insulator contamination using hyperspectral images disclosed in the present invention includes the following steps: S101, based on picking up an insulator object in the obtained hyperspectral image, an insulator hyperspectral image associated with the insulator object is obtained, and the insulator object is located inside the insulator hyperspectral image; S102, dividing the insulator hyperspectral image into regions to obtain a sub-insulator hyperspectral image, where the sub-insulator hyperspectral image is in a rectangular shape; S103, performing spectrum band division within a predetermined spectrum band to obtain an extracted spectrum band; S104, extracting the content in the insulator hyperspectral image using the extracted spectral band to obtain a first pollution degree evaluation map; S105, converge the content included in the first pollution degree evaluation graph to obtain a second pollution degree evaluation graph; S106, processing the remaining sub-insulator hyperspectral images in the same manner to obtain the remaining second pollution degree evaluation graphs.

[0033] In general, in step S101, firstly, the insulator object is picked up in the obtained hyperspectral image to obtain an insulator hyperspectral image associated with the insulator object. The insulator object is located inside the insulator hyperspectral image. The insulator object here refers to the insulator object obtained by ordinary photography.

[0034] By using the insulator object to pick up in the obtained hyperspectral image, the picking range of the hyperspectral image can be directly compressed, and the hyperspectral image content to be processed can be limited to the range corresponding to the insulator object.

[0035] See also Figure 2 At this time, the obtained insulator object is located inside the insulator hyperspectral image. There is a gap between the edge of the insulator object and the edge of the insulator hyperspectral image. Generally, the width of the gap is recommended to be 1-2 mm.

[0036] In step S102, the insulator hyperspectral image is divided into regions to obtain a sub-insulator hyperspectral image. The sub-insulator hyperspectral image is in a rectangular shape, such as Figure 3 As shown, the purpose of region division is to first process a sub-insulator hyperspectral image and then transplant the processing process to the processing process of other sub-insulator hyperspectral images.

[0037] In this way, parameter optimization and parameter fixing can be performed in the first processing process, and parameter re-optimization can be performed in subsequent processing processes.

[0038] In step S103, spectral band division is performed within a predetermined spectral band to obtain extracted spectral bands. The predetermined spectral bands correspond to spectral bands corresponding to possible contamination on the insulators. In the first processing, spectral band division is first performed within the predetermined spectral bands because it is impossible to determine what type of contamination is present on the insulators.

[0039] The extracted spectral bands obtained at this time are generally divided into equal lengths.

[0040] In step S104, the content in the insulator hyperspectral image is extracted using the extracted spectral band to obtain a first pollution degree evaluation map, and then in step S105, the content included in the first pollution degree evaluation map is converged to obtain a second pollution degree evaluation map.

[0041] Finally, in step S106, the remaining sub-insulator hyperspectral images are processed in the same manner to obtain the remaining second pollution degree evaluation map.

[0042] The contents of step 104 to step S106 are to first process a sub-insulator hyperspectral image, and then apply the processing process to the processing of other sub-insulator hyperspectral images. This processing method can compress the data processing amount.

[0043] In some examples, after obtaining the sub-insulator hyperspectral image, the sub-insulator hyperspectral image is further classified. The specific method of classifying the sub-insulator hyperspectral image is: S201, acquiring a captured image of an insulator object and dividing the captured image into regions, wherein the method of dividing the captured image into regions is the same as the method of dividing the insulator hyperspectral image into regions; S202, selecting at least one position reference point on the captured image after region division; S203, creating a position reference area on the captured image based on the position reference point; S204, calculating position parameters of the pixel points in the position reference area and the corresponding position reference points, the position parameters including distance, relative position and pixel value difference; S205, classifying the sub-insulator hyperspectral image using the position parameter.

[0044] In step S201 to step S205, firstly, a captured image of the insulator object is obtained and the captured image is divided into regions. The method of dividing the captured image into regions is the same as the method of dividing the insulator hyperspectral image into regions, which will not be repeated here. Figure 3 shown.

[0045] See also Figure 4, then select at least one position reference point on the captured image after region division, and then create a position reference area on the captured image based on the position reference point. The shape of the reference area can be circular, rectangular, or other shapes.

[0046] Then, the position parameters of the pixels in the position reference area and the corresponding position reference points are calculated. The pixels in the position reference area are randomly selected, and the number is not limited, but the selected number needs to be the same.

[0047] Position parameters include distance, relative position and pixel value difference.

[0048] After obtaining the position parameters, the position parameters are used to classify the insulator hyperspectral image. The specific method is as follows: S301, converting the distance, relative position and pixel value difference into a vector, where the starting point of the vector is a position reference point corresponding to the position parameter, and the length of the vector is the pixel value difference; S302, grouping the vectors according to their lengths and counting the orientation distribution of the vectors in each group; S303, classifying the sub-insulator hyperspectral image according to the orientation distribution, the orientation distribution of the vectors in the two groups should be the same or similar, and the classification process also includes assigning numerical values ​​to the vectors in the groups, and the numerical values ​​include positive values ​​and negative values.

[0049] The content in step S301 to step S303 is to convert the position parameters into vector representation. At this time, the vectors have the same starting point but different ending points.

[0050] After obtaining the vectors, the vectors are grouped according to their length and the orientation distribution of the vectors in each group is counted. The length of the vectors in each group is within a given range. Finally, the sub-insulator hyperspectral images are classified according to the orientation distribution. The orientation distribution of the vectors in the two groups should be the same or similar. The specific method is: The starting points of two sets of vectors belonging to the same given range are overlapped, and then one of the sets of vectors is rotated to determine whether the two sets of vectors can overlap. The basis for judging the overlap is that the two vectors in the two sets of vectors can completely overlap or the angle between them is within the set range.

[0051] Finally, the ratio of the number of vectors in one group that can be overlapped to the number of all vectors in the group is calculated. When the ratio is greater than or equal to a set value, it is considered that the orientation distributions of the two groups of vectors are consistent.

[0052] When the orientation distribution results of all vector groups are determined, the ratio of the group with consistent orientation distribution to all groups is calculated. When the ratio is greater than or equal to another set value, it is considered that the two sub-insulator hyperspectral images corresponding to the two groups of vectors should be classified into one category.

[0053] Through the above method, the sub-insulator hyperspectral image can be further subdivided, and the sub-insulator hyperspectral image in each category has a higher similarity. Using the processing and transplantation method mentioned in the previous article, more accurate results can be obtained.

[0054] When considering whether the orientation distribution is consistent, it is also necessary to introduce length as a reference value. In addition to the angle, the basis for judging the overlap is the length, and the length difference also needs to be within a set range.

[0055] At the same time, the above classification process also includes assigning values ​​to the vectors in the group, including positive and negative values. The way to assign values ​​is to adjust the length of the vectors in the group. This is because for two groups, one group may be significantly longer than the other. This is because when the position reference points are randomly selected in the early stage, the consistency of the position reference points is low. Once the consistency of the position reference points is improved by assigning values ​​to the vectors in the group.

[0056] In some examples, the specific method of converging the content included in the first pollution degree evaluation graph is: S401, decomposing the first pollution degree evaluation graph by using wavelet decomposition to obtain a waveform group; S402, determining a main waveform in the waveform group according to the length; S403, determining a derivative waveform associated with the main waveform according to the main waveform; S404, constructing a deletion range using the derived waveform obtained, wherein the deletion range is constructed using the frequency of the derived waveform; S405, deleting the waveforms in the waveform group that are within the deletion range.

[0057] Specifically, when the first pollution degree evaluation graph is decomposed using wavelet decomposition, each row or column is processed as an independent decomposition unit, and then the main waveform in the waveform group is determined according to the length. The main waveform is determined by screening according to the length. The selection of length here is a dynamic process.

[0058] A specific implementation method is to first give a length value, and use the waveforms greater than or equal to the length value as the main waveform in the waveform group, then determine the derivative waveform associated with the main waveform based on the main waveform, and finally use the obtained derivative waveform to construct a deletion range, and the deletion range is constructed using the frequency of the derivative waveform.

[0059] After the deletion range is obtained, the waveforms in the waveform group that are within the deletion range are deleted.

[0060] After the deletion process is completed, a signal-to-noise ratio can be obtained according to the number of deleted waveforms. At this time, the obtained signal-to-noise ratio is compared with the inherent signal-to-noise ratio of the device or a signal-to-noise ratio given based on experience. When the obtained signal-to-noise ratio is equal to the inherent signal-to-noise ratio of the device or a signal-to-noise ratio given based on experience, the deletion range does not need to be adjusted, otherwise the deletion range is adjusted.

[0061] The way to adjust the deletion range is to redefine the main waveform and then continue to execute the contents in step S404 and step S405.

[0062] The method of using the derived waveform to construct the deletion range is to determine the maximum frequency and the minimum frequency in the derived waveform, the starting point and the end point of the deletion range correspond to the minimum frequency and the maximum frequency respectively, and all waveforms in the waveform group whose frequencies are within the deletion range are deleted.

[0063] The specific method of determining the derived waveform associated with the main waveform based on the main waveform is as follows: Determine the endpoints of the main waveform, the endpoints include a starting position endpoint and a cutting position endpoint; Select a waveform associated with the endpoint and record it as a suspected derivative waveform, and the endpoint is located between the starting position point and the ending position point of the suspected derivative waveform; The suspected derivative waveforms are screened using the amplitude to obtain the derivative waveforms, where the amplitude of the derivative waveform is smaller than the amplitude of the main waveform.

[0064] See also Figure 5 In the above method, it is assumed that the derived waveform is located at the two end points of the main waveform and the end points of the main waveform are located between the starting position and the ending position of the suspected derived waveform. At the same time, the amplitude of the derived waveform is required to be smaller than the amplitude of the main waveform.

[0065] After deleting the waveforms in the deletion range in the waveform group, you also need to use the following method to process them: S501, comparing the clarity of the first pollution degree evaluation graph and the second pollution degree evaluation graph to obtain a clarity comparison result; S502, adjusting the deletion range according to the clarity comparison result, wherein adjusting the deletion range includes expanding the deletion range and reducing the deletion range.

[0066] In step S501 and step S502, the clarity of the first pollution degree evaluation graph and the second pollution degree evaluation graph are compared, and then the deletion range is adjusted according to the clarity comparison result, in order to make the deletion range more accurate.

[0067] The evaluation method of clarity is an existing technology, and can be evaluated using Brenner gradient function, Tenengrad gradient function, Laplacian gradient function, SMD (grayscale variance) function, SMD2 (grayscale variance product) function and variance function, etc., which will not be described here.

[0068] The result of comparing the clarity of the first pollution degree evaluation graph and the second pollution degree evaluation graph is a difference. When the difference is within a set difference range, there is no need to adjust the deletion range, otherwise the deletion range is adjusted.

[0069] In some examples, the same method is used to process the hyperspectral images of the remaining sub-insulators, and the following contents are added: S601, comparing the clarity of the first pollution degree evaluation graph and the second pollution degree evaluation graph to obtain a clarity comparison result; S602, adjusting the deletion range according to the clarity comparison result, wherein the adjustment of the deletion range includes expanding the deletion range and reducing the deletion range; S603, assigning the expanded and adjusted deletion range to other first pollution degree evaluation graphs to obtain second pollution degree evaluation graphs associated with the other first pollution degree evaluation graphs.

[0070] In step S601 to step S603, when the remaining sub-insulator hyperspectral images are processed in the same manner, the deletion range needs to be adjusted at the same time, and then the expanded and adjusted deletion range is assigned to other first contamination degree evaluation maps.

[0071] Specifically, with respect to the deletion range, in step S601 to step S603, if a larger deletion range is obtained, the larger deletion range will be used to process or reprocess all of the first contamination degree evaluation graphs to regenerate the second contamination degree evaluation graphs.

[0072] The purpose of this method is mainly to take into account that there is a certain amount of error in the deletion range. When only the endpoints are considered, omissions are prone to occur. Therefore, when a larger deletion range is obtained in the subsequent process, this larger deletion range is used as the basis to regenerate the second pollution degree evaluation diagram.

[0073] The content expressed by the second pollution degree evaluation map is described from the perspective of pixels. Each pixel has a value. The number of extracted spectral bands is the number of complete second pollution degree evaluation maps obtained in the end. These complete second pollution degree evaluation maps are superimposed together, and the pollution degree on the insulator can be reflected by the depth of color.

[0074] In addition, if the complete second pollution degree evaluation diagrams are not superimposed, the attachment amounts of different pollutants on the insulator can be reflected according to the types of pollutants corresponding to the extracted spectral bands.

[0075] The present invention also provides a device for evaluating the contamination degree of an insulator using a hyperspectral image, comprising: A picking unit is used to pick up the insulator object in the obtained hyperspectral image based on the insulator object to obtain the insulator hyperspectral image associated with the insulator object, wherein the insulator object is located inside the insulator hyperspectral image; A region division unit is used to divide the insulator hyperspectral image into regions to obtain a sub-insulator hyperspectral image, wherein the sub-insulator hyperspectral image is in a rectangular shape; A band division unit is used to divide the spectrum band within a given spectrum band to obtain an extracted spectrum band; A content extraction unit, used for extracting content in the insulator hyperspectral image by using an extracted spectral band to obtain a first pollution degree evaluation map; A convergence processing unit, used for converging the content included in the first pollution degree evaluation graph to obtain a second pollution degree evaluation graph; The first processing unit is used to process the remaining sub-insulator hyperspectral images in the same manner to obtain the remaining second pollution degree evaluation map.

[0076] Furthermore, it also includes: A second processing unit is used to obtain a captured image of the insulator object and divide the captured image into regions. The method of dividing the captured image into regions is the same as the method of dividing the insulator hyperspectral image into regions. A position reference point selection unit, used to select at least one position reference point on the captured image after the area division; A position reference area creating unit, used to create a position reference area on the captured image based on the position reference point; A calculation unit, used to calculate position parameters of a pixel point in a position reference area and a corresponding position reference point, the position parameters including distance, relative position and pixel value difference; The first classification unit is used to classify the sub-insulator hyperspectral image using the position parameter.

[0077] Furthermore, it also includes: A vector conversion unit, used to convert the distance, relative position and pixel value difference into a vector, the starting point of the vector is the position reference point corresponding to the position parameter, and the length of the vector is the pixel value difference; A grouping and statistics unit, used to group the vectors according to their lengths and to count the orientation distribution of the vectors in each group; The second classification unit is used to classify the sub-insulator hyperspectral image according to the orientation distribution. The orientation distribution of the vectors in the two groups should be the same or similar. The classification process also includes assigning numerical values ​​to the vectors in the groups, and the numerical values ​​include positive values ​​and negative values.

[0078] Furthermore, it also includes: A decomposition processing unit, used for decomposing the first pollution degree evaluation graph by using a wavelet decomposition method to obtain a waveform group; A main waveform determining unit, used to determine the main waveform in the waveform group according to the length; A derivative waveform determining unit, used to determine a derivative waveform associated with the main waveform according to the main waveform; A deletion range construction unit, used for constructing a deletion range using the obtained derivative waveform, wherein the deletion range is constructed using the frequency of the derivative waveform; The deletion processing unit is used to delete the waveforms in the waveform group that are within the deletion range.

[0079] Furthermore, it also includes: An endpoint determination unit, used to determine the endpoints of the main waveform, the endpoints including a starting position endpoint and a cut-off position endpoint; A suspected derivative waveform selection unit is used to select a waveform associated with an endpoint, which is recorded as a suspected derivative waveform, and the endpoint is located between a starting position point and a cutoff position point of the suspected derivative waveform; The derivative waveform selection unit is used to screen the suspected derivative waveforms by using the amplitude to obtain the derivative waveforms, wherein the amplitude of the derivative waveform is smaller than the amplitude of the main waveform.

[0080] Furthermore, it also includes: A first comparison processing unit, used for comparing the clarity of the first pollution degree evaluation image and the second pollution degree evaluation image to obtain a clarity comparison result; The first deletion range adjustment unit is used to adjust the deletion range according to the clarity comparison result, and the adjustment of the deletion range includes expanding the deletion range and reducing the deletion range.

[0081] Furthermore, it also includes: A first comparison processing unit, used for comparing the clarity of the first pollution degree evaluation image and the second pollution degree evaluation image to obtain a clarity comparison result; A second deletion range adjustment unit is used to adjust the deletion range according to the clarity comparison result, and the adjustment of the deletion range includes expanding the deletion range and reducing the deletion range; The regeneration unit is used to assign the expanded and adjusted deletion range to other first pollution degree evaluation graphs to obtain second pollution degree evaluation graphs associated with the other first pollution degree evaluation graphs.

[0082] In one example, the unit in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0083] For another example, when the units in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0084] Various objects such as various messages / information / equipment / network elements / systems / devices / actions / operations / processes / concepts that may appear in the present invention are named. It can be understood that these specific names do not constitute a limitation on the relevant objects. The names assigned may change with factors such as scenarios, contexts or usage habits. The understanding of the technical meaning of the technical terms in the present invention should be mainly determined from the functions and technical effects embodied / executed in the technical scheme.

[0085] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0086] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0087] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0088] Those skilled 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, or a combination of computer software and electronic hardware. 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 the present invention.

[0089] It should also be understood that in various embodiments of the present invention, the first, second, etc. are only used to indicate that multiple objects are different. For example, the first time window and the second time window are only used to indicate different time windows. They should not have any impact on the time window itself, and the first, second, etc. mentioned above should not impose any limitations on the embodiments of the present invention.

[0090] It should also be understood that in the various embodiments of the present invention, unless otherwise specified or there is any logical conflict, the terms and / or descriptions between the different embodiments are consistent and can be referenced to each other, and the technical features in the different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0091] If the functions 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 this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a computer-readable storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0092] The present invention also provides a system for evaluating the contamination degree of insulators using hyperspectral images, the system comprising: one or more memories for storing instructions; and One or more processors are used to call and run the instructions from the memory to execute the method as described above.

[0093] The present invention also provides a computer program product, which includes instructions. When the instructions are executed, the terminal device and the network device perform operations of the terminal device and the network device corresponding to the above method.

[0094] The present invention also provides a chip system, which includes a processor for implementing the functions involved in the above content, such as generating, receiving, sending, or processing the data and / or information involved in the above method.

[0095] The chip system may be composed of chips, or may include chips and other discrete devices.

[0096] The processor mentioned in any of the above places can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for executing programs for controlling the above-mentioned feedback information transmission method.

[0097] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wire or wireless means to support the chip system to implement various functions in the above embodiments. Alternatively, the processor and the memory can also be coupled on the same device.

[0098] Optionally, the computer instructions are stored in a memory.

[0099] Optionally, the memory is a storage unit within the chip, such as a register, a cache, etc. The memory can also be a storage unit within the terminal located outside the chip, such as a ROM or other types of static storage devices that can store static information and instructions, RAM, etc.

[0100] It can be understood that the memory in the present invention can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0101] The nonvolatile memory may be a ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory.

[0102] The volatile memory may be a RAM, which is used as an external cache. There are many different types of RAM, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory.

[0103] The embodiments of this specific implementation method are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for evaluating the contamination degree of insulators using hyperspectral images, characterized in that: include: Based on the insulator object, the insulator object is picked up in the obtained hyperspectral image to obtain an insulator hyperspectral image associated with the insulator object, and the insulator object is located inside the insulator hyperspectral image; The insulator hyperspectral image is divided into regions to obtain a sub-insulator hyperspectral image, and the sub-insulator hyperspectral image is in a rectangular shape; Perform spectral band division within a given spectral band to obtain extracted spectral bands; Using the extracted spectral band to extract the content in the insulator hyperspectral image, a first pollution degree evaluation map is obtained; Converging the contents included in the first pollution degree evaluation graph to obtain a second pollution degree evaluation graph; The remaining insulator hyperspectral images are processed in the same manner to obtain the remaining second pollution degree evaluation map.

2. The method for evaluating the contamination degree of insulators using hyperspectral images according to claim 1, characterized in that: After obtaining the sub-insulator hyperspectral image, the sub-insulator hyperspectral image is classified. The classification of the sub-insulator hyperspectral image includes: Acquire a captured image of an insulator object and divide the captured image into regions. The method of dividing the captured image into regions is the same as the method of dividing the insulator hyperspectral image into regions. Selecting at least one position reference point on the captured image after region division; Creating a position reference area on the captured image based on the position reference point; Calculate the position parameters of the pixel points in the position reference area and the corresponding position reference points, the position parameters including distance, relative position and pixel value difference; Classification of sub-insulator hyperspectral images using location parameters.

3. The method for evaluating the contamination degree of insulators using hyperspectral images according to claim 2, characterized in that: Classification of sub-insulator hyperspectral images using location parameters includes: Convert the distance, relative position and pixel value difference into a vector, where the starting point of the vector is the position reference point corresponding to the position parameter and the length of the vector is the pixel value difference; Group the vectors according to their length and count the orientation distribution of the vectors in each group; The sub-insulator hyperspectral images are classified according to the orientation distribution. The orientation distribution of the vectors in the two groups should be the same or similar. The classification process also includes assigning numerical values ​​to the vectors in the groups, and the numerical values ​​include positive and negative values.

4. The method for evaluating the contamination degree of insulators using hyperspectral images according to any one of claims 1 to 3, characterized in that: Converging the contents of the first pollution degree evaluation graph includes: Decomposing the first pollution degree evaluation graph by using wavelet decomposition to obtain a waveform group; Determine the main waveform in the waveform group based on the length; Determining a derivative waveform associated with the main waveform according to the main waveform; Using the derived waveform obtained to construct a deletion range, the deletion range is constructed using the frequency of the derived waveform; Delete the waveforms in the waveform group that are within the deletion range.

5. The method for evaluating the contamination degree of insulators using hyperspectral images according to claim 2, characterized in that: Derivative waveforms associated with the main waveform are determined based on the main waveform: Determine the endpoints of the main waveform, the endpoints include a starting position endpoint and a cutting position endpoint; Select a waveform associated with the endpoint and record it as a suspected derivative waveform, and the endpoint is located between the starting position point and the ending position point of the suspected derivative waveform; The suspected derivative waveforms are screened using the amplitude to obtain the derivative waveforms, where the amplitude of the derivative waveform is smaller than the amplitude of the main waveform.

6. The method for evaluating the contamination degree of insulators using hyperspectral images according to claim 5, characterized in that: After deleting the waveforms in the deletion range in the waveform group, it also includes: Comparing the clarity of the first pollution degree evaluation graph and the second pollution degree evaluation graph to obtain a clarity comparison result; The deletion range is adjusted according to the clarity comparison result, and the adjustment of the deletion range includes expanding the deletion range and reducing the deletion range.

7. The method for evaluating the contamination degree of insulators using hyperspectral images according to claim 5, characterized in that: When the hyperspectral images of the remaining sub-insulators are processed in the same way, the following are also included: Comparing the clarity of the first pollution degree evaluation graph and the second pollution degree evaluation graph to obtain a clarity comparison result; Adjust the deletion range according to the clarity comparison result, and the adjustment of the deletion range includes expanding the deletion range and reducing the deletion range; The expanded and adjusted deletion range is assigned to other first pollution degree evaluation graphs to obtain second pollution degree evaluation graphs associated with the other first pollution degree evaluation graphs.

8. A device for evaluating the contamination degree of insulators using hyperspectral images, characterized in that: include: A picking unit is used to pick up the insulator object in the obtained hyperspectral image based on the insulator object to obtain the insulator hyperspectral image associated with the insulator object, wherein the insulator object is located inside the insulator hyperspectral image; A region division unit is used to divide the insulator hyperspectral image into regions to obtain a sub-insulator hyperspectral image, wherein the sub-insulator hyperspectral image is in a rectangular shape; A band division unit is used to divide the spectrum band within a given spectrum band to obtain an extracted spectrum band; A content extraction unit, used for extracting content in the insulator hyperspectral image by using an extracted spectral band to obtain a first pollution degree evaluation map; A convergence processing unit, used for converging the content included in the first pollution degree evaluation graph to obtain a second pollution degree evaluation graph; The first processing unit is used to process the remaining sub-insulator hyperspectral images in the same manner to obtain the remaining second pollution degree evaluation map.

9. A system for evaluating the contamination degree of insulators using hyperspectral images, characterized in that: The system comprises: one or more memories for storing instructions; and One or more processors, configured to call and execute the instructions from the memory to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer readable storage medium comprises: The program, when the program is executed by a processor, the method according to any one of claims 1 to 7 is executed.

Images