Method and system for insulator contamination level evaluation using hyperspectral images

Abstract

The application relates to a method and system for evaluating insulator contamination degree using hyperspectral images, the method comprising picking up insulator objects in obtained hyperspectral images, obtaining insulator hyperspectral images associated with the insulator objects; dividing the insulator hyperspectral images into regions to obtain sub-insulator hyperspectral images; dividing the insulator hyperspectral images into spectral bands in a given spectral band to obtain extracted spectral bands; extracting the contents of the sub-insulator hyperspectral images using the extracted spectral bands to obtain a first contamination degree evaluation map; and converging the contents included in the first contamination degree evaluation map to obtain a second contamination degree evaluation map. The method and system for evaluating insulator contamination degree using hyperspectral images disclosed by the application compress the data processing amount through the combined processing mode of region division and processing mode transplantation, and reduce the interference through the convergence mode, so that more accurate evaluation results can be obtained.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a method and system for evaluating insulator contamination degree using hyperspectral images. BACKGROUND

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

[0003] The equivalent dust density refers to the mass (mg / cm 2 ) of non-conductive substances attached to each square centimeter of the surface of the insulator. The dust density has a certain influence on the insulator flashover voltage, and as the dust density increases, the insulator flashover voltage tends to decrease, but the influence is much weaker than that of the salt density.

[0004] The specific measurement methods are as follows

[0005] The insulator or simulated contamination string is removed from the line, and is cleaned and measured on site.

[0006] The insulator or simulated contamination string is removed from the line and transported back to the laboratory for cleaning and measurement.

[0007] The sampling cloth is directly used to wipe the insulator on the tower, and the sampling cloth is taken back to the laboratory for soaking and testing.

[0008] These measurement methods are relatively difficult to operate, as manual point sampling is required. At present, unmanned sampling methods such as unmanned aerial vehicle photography and hyperspectral image sampling have been studied, which can realize automatic sampling.

[0009] Among them, the more optimal solution is hyperspectral image sampling, because the information quantity expressed by hyperspectral image sampling is more abundant, but there are more interferences in hyperspectral image sampling, and further research is needed to solve the problem. In addition, the information quantity of hyperspectral image sampling is huge, and if the hyperspectral image is directly processed, it will inevitably face huge data quantity, which will cause trouble for continuous monitoring. SUMMARY

[0010] The present application provides a method and system for evaluating insulator contamination degree using hyperspectral images, which compresses the data processing quantity by combining the regional division and processing methods, and reduces the interference by using the convergence method, so as to obtain more accurate evaluation results.

[0011] The above object of the present application is achieved by the following technical solutions.

[0012] In a first aspect, the present application provides a method for evaluating the contamination degree of an insulator using a hyperspectral image, comprising:

[0013] Based on the insulator object obtained in the hyperspectral image, an insulator hyperspectral image associated with the insulator object is obtained, and the insulator object is located inside the insulator hyperspectral image;

[0014] The insulator hyperspectral image is regionally divided to obtain a sub-insulator hyperspectral image, and the shape of the sub-insulator hyperspectral image is rectangular;

[0015] Spectral band division is performed within a predetermined spectral band to obtain an extracted spectral band;

[0016] The content in the sub-insulator hyperspectral image is extracted using the extracted spectral band to obtain a first contamination degree evaluation map;

[0017] The content included in the first contamination degree evaluation map is converged to obtain a second contamination degree evaluation map;

[0018] The remaining sub-insulator hyperspectral images are processed using the same method to obtain the remaining second contamination degree evaluation maps.

[0019] In a possible implementation manner of the first aspect, after obtaining the sub-insulator hyperspectral image, the method further comprises classifying the sub-insulator hyperspectral image, and the classifying the sub-insulator hyperspectral image comprises:

[0020] A shooting image of the insulator object is obtained, and the shooting image is regionally divided, and the regional division manner of the shooting image is the same as that of the insulator hyperspectral image;

[0021] At least one position reference point is selected on the regionally divided shooting image;

[0022] A position reference region is created on the shooting image based on the position reference point;

[0023] The position parameters of the pixel points in the position reference region and the corresponding position reference points are calculated, and the position parameters include distance, relative position, and pixel value difference;

[0024] The sub-insulator hyperspectral image is classified using the position parameters.

[0025] In a possible implementation manner of the first aspect, the classifying the sub-insulator hyperspectral image using the position parameters comprises:

[0026] The distance, relative position and pixel value difference are converted into a vector, 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;

[0027] The vectors are grouped according to the length, and the orientation distribution of the vectors in each group is counted;

[0028] The sub-insulation hyperspectral image is classified 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 further includes assigning a value to the vectors in the group, the value including a positive value and a negative value.

[0029] In a possible implementation manner of the first aspect, the converging of the content included in the first contamination degree evaluation map includes:

[0030] The first contamination degree evaluation map is decomposed by using a wavelet decomposition method to obtain a waveform group;

[0031] The main waveform in the waveform group is determined according to the length;

[0032] The derivative waveform associated with the main waveform is determined according to the main waveform;

[0033] The obtained derivative waveform is used to construct a deletion range, and the deletion range is constructed by using the frequency of the derivative waveform;

[0034] The waveforms in the waveform group located in the deletion range are deleted.

[0035] In a possible implementation manner of the first aspect, the derivative waveform associated with the main waveform is determined according to the main waveform, and includes:

[0036] The end points of the main waveform are determined, and the end points include a starting position end point and an ending position end point;

[0037] The waveform associated with the end point is selected and recorded as a suspected derivative waveform, and the end point is located between the starting position point and the ending position point of the suspected derivative waveform;

[0038] The suspected derivative waveform is screened by using the amplitude, and the derivative waveform is obtained, and the amplitude of the derivative waveform is smaller than the amplitude of the main waveform.

[0039] In a possible implementation manner of the first aspect, after the waveforms in the waveform group located in the deletion range are deleted, the method further includes:

[0040] The definition of the first contamination degree evaluation map and the second contamination degree evaluation map is compared to obtain a definition comparison result;

[0041] The deletion range is adjusted according to the definition comparison result, and the adjustment of the deletion range includes expanding the deletion range and reducing the deletion range.

[0042] In a possible implementation manner of the first aspect, when the remaining sub-insulator hyperspectral images are processed using the same manner, the method further includes:

[0043] comparing the clarity of the first contamination degree evaluation map and the second contamination degree evaluation map to obtain a clarity comparison result;

[0044] adjusting the deletion range according to the clarity comparison result, the adjusting of the deletion range including expanding the deletion range and reducing the deletion range;

[0045] assigning the expanded deletion range to other first contamination degree evaluation maps to obtain second contamination degree evaluation maps associated with the other first contamination degree evaluation maps.

[0046] In a second aspect, the present application provides a device for evaluating contamination degree of insulators using hyperspectral images, including:

[0047] a picking unit configured to pick up insulator objects in the obtained hyperspectral images to obtain insulator hyperspectral images associated with the insulator objects, the insulator objects being located inside the insulator hyperspectral images;

[0048] a region division unit configured to divide the insulator hyperspectral images into regions to obtain sub-insulator hyperspectral images, the sub-insulator hyperspectral images being in the shape of a rectangle;

[0049] a waveband division unit configured to divide the insulator hyperspectral images into wavebands in a predetermined spectral waveband to obtain extracted spectral wavebands;

[0050] a content extraction unit configured to extract contents in the sub-insulator hyperspectral images using the extracted spectral wavebands to obtain first contamination degree evaluation maps;

[0051] a convergence processing unit configured to converge the contents included in the first contamination degree evaluation maps to obtain second contamination degree evaluation maps;

[0052] a first processing unit configured to process remaining sub-insulator hyperspectral images using the same manner to obtain remaining second contamination degree evaluation maps.

[0053] In a third aspect, the present application provides a system for evaluating contamination degree of insulators using hyperspectral images, including:

[0054] one or more memories configured to store instructions; and

[0055] one or more processors configured to call and run the instructions from the memories to perform the method as described in the first aspect and any possible implementation manner of the first aspect.

[0056] In a fourth aspect, the present application provides a computer readable storage medium comprising:

[0057] A program which, when executed by a processor, causes the method according to the first aspect and any possible implementation of the first aspect to be performed.

[0058] In a fifth aspect, the present application provides a computer program product comprising program instructions which, when executed by a computing device, cause the method according to the first aspect and any possible implementation of the first aspect to be performed.

[0059] In a sixth aspect, the present application provides a chip system comprising a processor for implementing the functions involved in the above aspects, such as generating, receiving, sending, or processing the data and / or information involved in the above method.

[0060] The chip system can be composed of a chip, or can include a chip and other discrete devices.

[0061] In a possible design, the chip system further includes a memory, which is configured to store necessary program instructions and data. The processor and the memory can be decoupled and arranged on different devices, and connected through a wired or wireless manner, or the processor and the memory can be coupled on the same device. BRIEF DESCRIPTION OF DRAWINGS

[0062] Figure 1 is a schematic block diagram of a step flow of a method for evaluating the pollution degree of an insulator using a hyperspectral image provided by the present application.

[0063] Figure 2 is a schematic diagram of an insulator object located inside a hyperspectral image of an insulator provided by the present application.

[0064] Figure 3 is a schematic diagram of a principle of obtaining a hyperspectral image of an insulator provided by the present application.

[0065] Figure 4 is a schematic diagram of selecting a position reference point and a pixel point provided by the present application.

[0066] Figure 5 is a schematic diagram of the relative positions of a derived waveform and a main waveform provided by the present application. DETAILED DESCRIPTION

[0067] In order to more clearly understand the technical solutions in the present application, first, the related content is introduced.

[0068] In simple terms, hyperspectral image is a lot of gray images superimposed together, and each gray image represents a spectral band.

[0069] For example, a general two-dimensional image representation, the image pixel is 255*255, that is, the image has 255*255 pixels, which can be a gray image or a color image, and the relevant information is contained in each pixel.

[0070] And the same size of hyperspectral image, if it contains 200 spectral band information, it should be represented as 255*255*200, which can be understood as 200-dimensional spectral domain information on each pixel, which is similar to 200 two-dimensional images of 255*255 superimposed together, and the gray value of the same position pixel in the 200 images is drawn 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, and the interference information is caused by scattering, refraction and reflection.

[0071] The technical solutions in the application will be further described in detail below with reference to the drawings.

[0072] The application discloses a method for evaluating the contamination degree of an insulator by using a hyperspectral image. Figure 1 In some examples, the method for evaluating the contamination degree of an insulator by using a hyperspectral image disclosed by the application comprises the following steps:

[0073] S101, based on the insulator object in the obtained hyperspectral image, the insulator hyperspectral image associated with the insulator object is obtained, and the insulator object is located in the inside of the insulator hyperspectral image;

[0074] S102, the insulator hyperspectral image is regionally divided to obtain a sub-insulator hyperspectral image, and the shape of the sub-insulator hyperspectral image is rectangular;

[0075] S103, spectral band division is performed in a given spectral band to obtain an extracted spectral band;

[0076] S104, the content in the sub-insulator hyperspectral image is extracted by using the extracted spectral band to obtain a first contamination degree evaluation map;

[0077] S105, the content included in the first contamination degree evaluation map is converged to obtain a second contamination degree evaluation map;

[0078] S106, the remaining sub-insulator hyperspectral images are processed by using the same method to obtain the remaining second contamination degree evaluation maps.

[0079] Overall, in step S101, first, based on the insulator object, the insulator hyperspectral image associated with the insulator object is obtained by picking up in the obtained hyperspectral image, and the insulator object is located inside the insulator hyperspectral image. Here, the insulator object refers to the insulator object obtained by ordinary shooting.

[0080] Using the insulator object to pick up in the obtained hyperspectral image can directly compress the picking range of the hyperspectral image, and limit the content of the hyperspectral image to be processed to the range corresponding to the insulator object.

[0081] Please refer to Figure 2 At this time, the obtained insulator object is located inside the insulator hyperspectral image, and 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 1-2mm.

[0082] In step S102, the insulator hyperspectral image is regionally divided to obtain a sub-insulator hyperspectral image, and the shape of the sub-insulator hyperspectral image is rectangular, as shown in Figure 3 The purpose of regional division is to first process a sub-insulator hyperspectral image, and then transplant the processing process to the processing of other sub-insulator hyperspectral images.

[0083] In this way, parameter optimization and parameter fixing can be performed in the first processing process, and parameter re-optimization can also be performed in the subsequent processing process.

[0084] In step S103, spectral band division is performed in a predetermined spectral band to obtain an extracted spectral band. The predetermined spectral band corresponds to the spectral band in which contamination on the insulator may exist. In the first processing process, spectral band division is first performed in the predetermined spectral band, because it is not determined what kind of contamination exists on the insulator.

[0085] At this time, the obtained extracted spectral band generally adopts an equal-length division method.

[0086] In step S104, the content in the sub-insulator hyperspectral image is extracted using the extracted spectral band to obtain a first contamination degree evaluation map. Then, in step S105, the content included in the first contamination degree evaluation map is converged to obtain a second contamination degree evaluation map.

[0087] Finally, in step S106, the remaining sub-insulator hyperspectral images are processed using the same method to obtain the remaining second contamination degree evaluation maps.

[0088] The contents in steps 104 to 106 are to firstly process one sub-insulator hyperspectral image, and then apply the processing to other sub-insulator hyperspectral images, which can compress the data processing amount.

[0089] In some examples, after obtaining the sub-insulator hyperspectral image, the sub-insulator hyperspectral image is further classified, and the specific way of classifying the sub-insulator hyperspectral image is as follows:

[0090] S201, obtaining a shooting image of an insulator object and performing region division on the shooting image, and the way of performing region division on the shooting image is the same as the way of performing region division on the insulator hyperspectral image;

[0091] S202, selecting at least one position reference point on the region-divided shooting image;

[0092] S203, creating a position reference region on the shooting image based on the position reference point;

[0093] S204, calculating the position parameters of the pixel points in the position reference region and the corresponding position reference points, the position parameters including distance, relative position and pixel value difference;

[0094] S205, classifying the sub-insulator hyperspectral image using the position parameters.

[0095] In steps S201 to S205, firstly, the shooting image of the insulator object is obtained and region division is performed on the shooting image, and the way of performing region division on the shooting image is the same as the way of performing region division on the insulator hyperspectral image, which will not be described here, as shown in Figure 3

[0096] Please refer to Figure 4 , then at least one position reference point is selected on the region-divided shooting image, and then a position reference region is created on the shooting image based on the position reference point, and the shape of the reference region can be circular, rectangular, or other shapes.

[0097] Then, the position parameters of the pixel points in the position reference region and the corresponding position reference points are calculated, the pixel points in the position reference region are randomly selected, and the number is not limited, but the number needs to be the same.

[0098] The position parameters include three parameters of distance, relative position and pixel value difference.

[0099] After obtaining the position parameters, the sub-insulator hyperspectral image is classified using the position parameters, and the specific way is as follows:

[0100] ​S301, 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;

[0101] S302, group the vectors according to the length and count the orientation distribution of the vectors in each group;

[0102] S303, classify the sub-insulator hyperspectral images 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 a value to the vectors in the group, the value including positive and negative values.

[0103] The contents in steps S301 to S303 are to convert the position parameter into a vector representation, and the vectors at this time have the same starting point but different ending points.

[0104] After obtaining the vectors, the vectors are grouped according to the length and the orientation distribution of the vectors in each group is counted, and the length of the vectors in each group is within a certain 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, and the specific way is:

[0105] The starting points of the two groups of vectors belonging to the same certain range are coincided, and then one of the two groups of vectors is rotated to determine whether the two groups of vectors can be coincided, and the coincidence is determined according to whether the two vectors in the two groups of vectors can be completely coincided or the included angle is within a certain range.

[0106] Finally, the ratio of the number of vectors in a group that can be coincided to the number of all vectors in the group is calculated, and when the ratio is greater than or equal to a certain value, it is considered that the orientation distribution of the two groups of vectors is consistent.

[0107] When the orientation distribution of all groups of vectors is determined, the ratio of the groups with consistent orientation distribution to all groups is calculated, and when the ratio is greater than or equal to another certain value, it is considered that the two sub-insulator hyperspectral images corresponding to the two groups of vectors should be classified into one category.

[0108] Through the above method, the sub-insulator hyperspectral images can be further subdivided, and the sub-insulator hyperspectral images in each category have higher similarity, and more accurate results can be obtained by using the processing method mentioned in the foregoing.

[0109] When considering whether the orientation distribution is consistent, the length also needs to be introduced as a reference value, and in addition to the included angle, the length difference also needs to be within a certain range.

[0110] Meanwhile, in the above classification process, a value is assigned to the vector in the group, and the value includes a positive value and a negative value. The value is assigned by adjusting the length of the vector in the group, because for two groups, the length of one group can be obviously greater than the length of the other group, because the consistency of the position reference point is low when the position reference point is randomly selected in the early stage, and the consistency of the position reference point is improved by assigning the value to the vector in the group.

[0111] In some examples, the specific way of converging the content included in the first contamination degree evaluation map is:

[0112] S401, the first contamination degree evaluation map is decomposed by using a wavelet decomposition method to obtain a waveform group;

[0113] S402, a main waveform in the waveform group is determined according to the length;

[0114] S403, a derived waveform associated with the main waveform is determined according to the main waveform;

[0115] S404, a deletion range is constructed using the derived waveform obtained, and the deletion range is constructed using the frequency of the derived waveform;

[0116] S405, the waveforms in the waveform group located in the deletion range are deleted.

[0117] Specifically, when the first contamination degree evaluation map is decomposed by using a wavelet decomposition method, each row or each column is taken as an independent decomposition unit for processing, then the main waveform in the waveform group is determined according to the length, and the main waveform is determined by screening according to the length. Here, the selection of the length is a dynamic process.

[0118] A specific implementation is that a length value is first given, waveforms greater than or equal to the length value are all taken as the main waveforms in the waveform group, then the derived waveform associated with the main waveform is determined according to the main waveform, and finally the deletion range is constructed using the derived waveform obtained, and the deletion range is constructed using the frequency of the derived waveform.

[0119] After the deletion range is obtained, the waveforms in the waveform group located in the deletion range are deleted.

[0120] After the deletion processing 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 an empirical signal-to-noise ratio, when the obtained signal-to-noise ratio is equal to the inherent signal-to-noise ratio of the device or the empirical signal-to-noise ratio, the deletion range does not need to be adjusted, otherwise the deletion range is adjusted.

[0121] The way to adjust the deletion range is to re-determine the main waveform, and then continue the contents in steps S404 and S405.

[0122] The way to use the obtained derivative waveform to construct the deletion range is to determine the maximum frequency and the minimum frequency in the derivative waveform, and the start point and the end point of the deletion range correspond to the minimum frequency and the maximum frequency respectively, and all the waveforms in the waveform group whose frequencies are located in the deletion range are deleted.

[0123] The specific way to determine the derivative waveform associated with the main waveform according to the main waveform is as follows:

[0124] Determine the end points of the main waveform, including the start position end point and the end position end point;

[0125] Select the waveform associated with the end point, denoted as the suspected derivative waveform, and the end point is located between the start position point and the end position point of the suspected derivative waveform;

[0126] Use the amplitude to screen the suspected derivative waveform to obtain the derivative waveform, and the amplitude of the derivative waveform is less than the amplitude of the main waveform.

[0127] Please refer to Figure 5 In the above-mentioned way, it is considered that the derivative waveform is located at the two end point positions of the main waveform, and the end points of the main waveform are located between the start position point and the end position point of the suspected derivative waveform, and at the same time, the amplitude of the derivative waveform is less than the amplitude of the main waveform.

[0128] After deleting the waveforms in the deletion range in the waveform group, the following way is still needed for processing:

[0129] S501, compare the sharpness of the first contamination degree evaluation map and the second contamination degree evaluation map to obtain a sharpness comparison result;

[0130] S502, adjust the deletion range according to the sharpness comparison result, which includes expanding the deletion range and reducing the deletion range.

[0131] In steps S501 and S502, the sharpness of the first contamination degree evaluation map and the second contamination degree evaluation map will be compared, and then the deletion range will be adjusted according to the sharpness comparison result, so as to make the deletion range more accurate.

[0132] The evaluation method of sharpness is the prior art, which can use Brenner gradient function, Tenengrad gradient function, Laplacian gradient function, SMD (gray scale variance) function, SMD2 (gray scale variance product) function and variance function for evaluation, which will not be described here.

[0133] The result of comparing the definition of the first contamination degree evaluation map and the second contamination degree evaluation map is a difference value, when the difference value is within a set difference value range, the deletion range does not need to be adjusted, otherwise the deletion range is adjusted.

[0134] In some examples, when the remaining sub-insulator hyperspectral images are processed in the same way, the following content is added:

[0135] S601, comparing the definition of the first contamination degree evaluation map and the second contamination degree evaluation map, obtaining a definition comparison result;

[0136] S602, adjusting the deletion range according to the definition comparison result, the adjustment of the deletion range includes expanding the deletion range and reducing the deletion range;

[0137] S603, assigning the expanded deletion range to other first contamination degree evaluation maps to obtain second contamination degree evaluation maps associated with the other first contamination degree evaluation maps.

[0138] In steps S601 to S603, when the remaining sub-insulator hyperspectral images are processed in the same way, the adjustment of the deletion range is needed, and then the expanded deletion range is assigned to other first contamination degree evaluation maps.

[0139] Specifically, for the deletion range, in steps S601 to S603, if a larger deletion range is obtained, the larger deletion range is used to process or reprocess all the first contamination degree evaluation maps to regenerate the second contamination degree evaluation maps.

[0140] The purpose of this method is mainly to consider that there is a certain amount of error in the deletion range, and when only considering the end point, it is easy to miss, so when a larger deletion range is obtained in the subsequent process, the larger deletion range is used as the basis to regenerate the second contamination degree evaluation maps.

[0141] The content expressed by the second contamination degree evaluation map is described from the perspective of pixel points, each pixel point has a numerical value, and the number of extracted spectral bands is the number of complete second contamination degree evaluation maps. The complete second contamination degree evaluation maps are superimposed together, and the contamination degree on the insulator can be reflected by the color depth.

[0142] In addition, if the complete second contamination degree evaluation maps are not superimposed together, the amount of different contaminants attached to the insulator can be reflected according to the contaminant species corresponding to the extracted spectral bands.

[0143] The application also provides a device for evaluating the contamination degree of insulators using hyperspectral images, comprising:

[0144] a picking unit configured to pick up the insulator object in the obtained hyperspectral image based on the insulator object, to obtain an insulator hyperspectral image associated with the insulator object, and to locate the insulator object inside the insulator hyperspectral image;

[0145] a region division unit configured to divide the insulator hyperspectral image into regions to obtain a sub-insulator hyperspectral image, and to shape the sub-insulator hyperspectral image as a rectangle;

[0146] a waveband division unit configured to divide a spectrum waveband in a predetermined spectrum waveband to obtain an extraction spectrum waveband;

[0147] a content extraction unit configured to extract content in the sub-insulator hyperspectral image using the extraction spectrum waveband to obtain a first contamination degree evaluation map;

[0148] a convergence processing unit configured to converge the content included in the first contamination degree evaluation map to obtain a second contamination degree evaluation map;

[0149] a first processing unit configured to process the remaining sub-insulator hyperspectral images using the same manner to obtain the remaining second contamination degree evaluation maps.

[0150] Further, the method further comprises:

[0151] a second processing unit configured to obtain a photographed image of the insulator object and to divide the photographed image into regions in the same manner as the manner of dividing the insulator hyperspectral image into regions;

[0152] a position reference point selection unit configured to select at least one position reference point on the photographed image after the photographed image is divided into regions;

[0153] a position reference region creation unit configured to create a position reference region on the photographed image based on the position reference point;

[0154] a calculation unit configured to calculate a position parameter of a pixel point in the position reference region and a corresponding position reference point, the position parameter including a distance, a relative position, and a pixel value difference;

[0155] a first classification unit configured to classify the sub-insulator hyperspectral image using the position parameter.

[0156] Further, the method further comprises:

[0157] a vector conversion unit configured to convert the distance, the relative position, and the pixel value difference into a vector, a starting point of the vector being the position reference point corresponding to the position parameter, and a length of the vector being the pixel value difference;

[0158] a grouping and counting unit configured to group the vectors according to the length and count the orientation distribution of the vectors in each group;

[0159] a second classification unit configured to classify the sub-insulation 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 further includes assigning a value to the vectors in the group, the value including a positive value and a negative value.

[0160] Further, the method further includes:

[0161] a decomposition processing unit configured to perform decomposition processing on the first contamination degree evaluation image using a wavelet decomposition method to obtain a wavelet group;

[0162] a main wave determination unit configured to determine a main wave in the wavelet group according to the length;

[0163] a derived wave determination unit configured to determine a derived wave associated with the main wave according to the main wave;

[0164] a deletion range construction unit configured to construct a deletion range using the obtained derived wave, the deletion range being constructed using the frequency of the derived wave;

[0165] a deletion processing unit configured to perform deletion processing on the waveforms in the wavelet group located in the deletion range.

[0166] Further, the method further includes:

[0167] an endpoint determination unit configured to determine an endpoint of the main wave, the endpoint including a start position endpoint and an end position endpoint;

[0168] a suspected derived wave selection unit configured to select a waveform associated with the endpoint, denoted as a suspected derived wave, the endpoint being located between the start position point and the end position point of the suspected derived wave;

[0169] a derived wave selection unit configured to screen the suspected derived wave using the amplitude to obtain the derived wave, the amplitude of the derived wave being smaller than the amplitude of the main wave.

[0170] Further, the method further includes:

[0171] a first comparison processing unit configured to compare the definition of the first contamination degree evaluation image and the second contamination degree evaluation image to obtain a definition comparison result;

[0172] a first deletion range adjustment unit configured to adjust the deletion range according to the definition comparison result, the adjustment of the deletion range including expanding the deletion range and reducing the deletion range.

[0173] Further, the method further includes:

[0174] The first comparison processing unit is configured to compare the definition of the first contamination degree evaluation map and the second contamination degree evaluation map to obtain a definition comparison result.

[0175] The second deletion range adjustment unit is configured to adjust the deletion range according to the definition comparison result, and the adjustment of the deletion range includes expansion of the deletion range and reduction of the deletion range.

[0176] The regeneration unit is configured to assign the expanded and adjusted deletion range to other first contamination degree evaluation maps to obtain second contamination degree evaluation maps associated with the other first contamination degree evaluation maps.

[0177] In one example, the units in any of the above apparatuses can be one or more integrated circuits configured to implement the above methods, for example, 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.

[0178] For another example, when the units in the apparatuses can be implemented in the form of a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can invoke programs. For another example, these units can be integrated together to be implemented in the form of a system-on-a-chip (SOC).

[0179] In the present application, various objects such as messages / information / devices / network elements / systems / apparatuses / actions / operations / processes / concepts, etc. that can occur in the present application are named. It can be understood that these specific names do not constitute a limitation on the related objects, and the assigned names can be changed according to factors such as scenarios, contexts, or usage habits. The technical meaning of the technical terms in the present application should be mainly determined from the function and technical effect embodied / implemented in the technical scheme.

[0180] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, apparatus, and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here again.

[0181] In several embodiments provided by the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic. For example, the division of the units is only a logical function division. There can be another division manner for the 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. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, or the among different units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0182] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. In actual implementation, some or all of the units can be selected according to the actual needs to achieve the purposes of the embodiments.

[0183] Those skilled in the art can understand that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solutions. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0184] It should also be understood that in various embodiments of the present application, first, second, etc. are only used to represent that a plurality of objects are different. For example, the first time window and the second time window are only used to represent different time windows. There should be no impact on the time window itself, and the above first, second, etc. should not cause any limitation to the embodiments of the present application.

[0185] It should also be understood that in various embodiments of the present application, the terms and / or descriptions of different embodiments have consistency and can be mutually referred to if there is no special description and logical conflict. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0186] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a computer readable storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned computer readable storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0187] The present application also provides a system for evaluating the contamination level of an insulator using hyperspectral images, the system comprising:

[0188] one or more memories for storing instructions; and

[0189] one or more processors for invoking and executing the instructions from the memories to perform the methods as described in the above.

[0190] The present application also provides a computer program product comprising instructions which, when executed, cause the terminal device and the network device to perform the operations of the terminal device and the network device corresponding to the above methods.

[0191] The present application also provides a chip system comprising a processor for implementing the functions involved in the above, such as generating, receiving, sending, or processing the data and / or information involved in the above methods.

[0192] The chip system can be composed of a chip or can include a chip and other discrete devices.

[0193] The processor mentioned in any of the above can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the programs of the above feedback information transmission method.

[0194] In a possible design, the chip system further includes a memory for storing necessary program instructions and data. The processor and the memory can be decoupled and arranged on different devices, connected through wired or wireless means to support the chip system to realize various functions in the above embodiments. Alternatively, the processor and the memory can also be coupled on the same device.

[0195] Optionally, the computer instructions are stored in a memory.

[0196] 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, outside the chip, such as a ROM or other type of static storage device that can store static information and instructions, a RAM, etc.

[0197] It can be understood that the memory in the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0198] The non-volatile memory can be a ROM, a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically EPROM (EEPROM), or a flash memory.

[0199] The volatile memory can 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 SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synch link DRAM (SLDRAM), and direct Rambus RAM (DRRAM).

[0200] The embodiments of the present specific implementation are the preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Therefore, any equivalent changes made in the structure, shape, and principle of the present application should be covered within the protection scope of the present application.

Claims

1. A method for evaluating the pollution level of insulators using hyperspectral imaging, characterized in that, include: Based on the insulator object being picked 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; The hyperspectral image of the insulator is divided into regions to obtain the hyperspectral image of the sub-insulator, which is rectangular in shape. Within a given spectral band, the spectral bands are divided to obtain the extracted spectral bands; The contents of the hyperspectral image of the sub-insulator are extracted using the extracted spectral bands to obtain the first pollution level evaluation map; The contents included in the first filth assessment graph are converged to obtain the second filth assessment graph; The remaining sub-insulator hyperspectral images were processed in the same way to obtain the remaining second pollution level evaluation map; After obtaining the hyperspectral image of the sub-insulator, the process also includes classifying the hyperspectral image of the sub-insulator. This classification includes: The 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 hyperspectral image of the insulator into regions. Select at least one location reference point on the captured image after it has been divided into regions; Create a location reference region on the captured image based on a location reference point; Calculate the position parameters of pixels in the position reference region and their corresponding position reference points. The position parameters include distance, relative position, and pixel value difference. Classification of hyperspectral images of sub-insulators using position parameters; Classification of hyperspectral images of sub-insulators using location parameters includes: The distance, relative position, and pixel value difference are converted 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. The vectors are grouped according to their length, and the orientation distribution of the vectors in each group is statistically analyzed. The hyperspectral images of insulators are classified according to their orientation distribution. The orientation distribution of vectors in two groups should be the same or similar. The classification process also includes assigning numerical values ​​to the vectors in the groups, including positive and negative values.

2. The method for evaluating insulator pollution using hyperspectral images according to claim 1, characterized in that, The content included in the first level of filth assessment graph is converged to include: The first pollution level evaluation image is decomposed using wavelet decomposition to obtain waveform groups; The main waveform in the waveform group is determined based on its length. Determine the derived waveforms associated with the main waveform based on the main waveform; The deletion range is constructed using the derived waveform, and the deletion range is constructed using the frequency of the derived waveform. Delete waveforms that fall within the deletion range in the waveform group.

3. The method for evaluating insulator pollution using hyperspectral images according to claim 1, characterized in that, The derived waveforms associated with the main waveform are determined based on the main waveform, including: Determine the endpoints of the main waveform, including the start position endpoint and the end position endpoint; Select the waveform associated with the endpoint and denot it as the suspected derived waveform. The endpoint is located between the start point and the end point of the suspected derived waveform. The amplitude is used to filter the suspected derived waveforms to obtain the derived waveforms, whose amplitudes are smaller than those of the main waveform.

4. The method for evaluating insulator pollution using hyperspectral images according to claim 2, characterized in that, After deleting waveforms within the deletion range from the waveform group, the process also includes: The clarity of the first and second filth assessment maps is compared to obtain the clarity comparison results. Adjust the deletion range based on the clarity comparison results. Adjusting the deletion range includes expanding the deletion range and shrinking the deletion range.

5. The method for evaluating insulator pollution using hyperspectral images according to claim 3, characterized in that, When processing the hyperspectral images of the remaining insulators in the same way, the following are also included: The clarity of the first and second filth assessment maps is compared to obtain the clarity comparison results. The deletion range is adjusted based on the clarity comparison results. Adjusting the deletion range includes expanding the deletion range and reducing the deletion range. The expanded and adjusted deletion range is assigned to other first filth rating maps to obtain a second filth rating map associated with the other first filth rating maps.

6. An apparatus for evaluating the pollution level of insulators using hyperspectral imaging, characterized in that, include: The picking unit is used to pick in the obtained hyperspectral image based on the insulator object to obtain the hyperspectral image of the insulator associated with the insulator object, wherein the insulator object is located inside the hyperspectral image of the insulator; The region division unit is used to divide the hyperspectral image of the insulator into regions to obtain the hyperspectral image of the sub-insulator. The shape of the hyperspectral image of the sub-insulator is rectangular. The band division unit is used to divide the spectral bands within a given spectral band to obtain the extracted spectral bands; The content extraction unit is used to extract the content from the hyperspectral image of the sub-insulator using the extraction spectral band to obtain the first pollution degree evaluation map; The convergence processing unit is used to converge the contents included in the first foulness evaluation map to obtain the second foulness evaluation map. The first processing unit is used to process the hyperspectral image of the remaining sub-insulators in the same way to obtain the remaining second pollution level evaluation map; After obtaining the hyperspectral image of the sub-insulator, the process also includes classifying the hyperspectral image of the sub-insulator. This classification includes: The 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 hyperspectral image of the insulator into regions. Select at least one location reference point on the captured image after it has been divided into regions; Create a location reference region on the captured image based on a location reference point; Calculate the position parameters of pixels in the position reference region and their corresponding position reference points. The position parameters include distance, relative position, and pixel value difference. Classification of hyperspectral images of sub-insulators using position parameters; Classification of hyperspectral images of sub-insulators using location parameters includes: The distance, relative position, and pixel value difference are converted 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. The vectors are grouped according to their length, and the orientation distribution of the vectors in each group is statistically analyzed. The hyperspectral images of insulators are classified according to their orientation distribution. The orientation distribution of vectors in two groups should be the same or similar. The classification process also includes assigning numerical values ​​to the vectors in the groups, including positive and negative values.

7. A system for evaluating insulator pollution using hyperspectral imaging, characterized in that, The system includes: One or more memories for storing instructions; and One or more processors are configured to retrieve and execute the instructions from the memory to perform the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes: The program, when run by a processor, executes the method as described in any one of claims 1 to 5.

Images