CN109448009A - Infrared Image Processing Method and device for transmission line faultlocating - Google Patents

Abstract

A kind of Infrared Image Processing Method and device for transmission line faultlocating, wherein method includes: the infrared image for obtaining transmission line faultlocating scene；Infrared image is pre-processed, pretreated infrared image is generated；Temperature field dividing processing is carried out to pretreated infrared image, extracts corresponding temperature field data；Corresponding Characteristics of Temperature Field is extracted according to temperature field data.Infrared Image Processing Method and device provided in an embodiment of the present invention for transmission line faultlocating, pretreatment is carried out by the infrared image to transmission line of electricity and Characteristics of Temperature Field is extracted, the automatic detection and identification to infrared image are realized, the working efficiency of electric inspection process is conducive to provide.

Description

Infrared image processing method and device for power transmission line detection

Technical Field

The invention relates to the technical field of power inspection, in particular to an infrared image processing method and device for power transmission line detection.

Background

With the development of national economy and the continuous improvement of the living standard of people, the investment scale of the power grid is continuously enlarged, and the network structure is more and more complex. The reliable operation of the power grid line and the power grid equipment directly influences the production safety and social benefits of power enterprises and influences the stability of the power grid. In order to ensure the normal operation of power facilities, an electric power department makes a patrol plan every month, and dispatchers patrol power supply facilities including towers, wires, transformers, capacitors and the like so as to find equipment defects and potential safety hazards in time and collect the operation conditions and defect information of the equipment and perform regular analysis and statistics. The workload of power grid inspection and maintenance is more and more large, and the traditional manual inspection operation mode of the power transmission line and the transformer substation cannot meet the high-efficiency power grid inspection work requirement. Therefore, the application work of unmanned aerial vehicle line inspection and robot substation inspection is widely popularized by national grid companies, real-time data acquisition and state monitoring are carried out on electric power facilities through intelligent equipment such as application robots and unmanned aerial vehicles, defects are found in time, the efficiency of electric power maintenance and overhaul is practically improved, the grid state management and control capacity and lean management level are effectively improved, and the safety and stability of a power grid are guaranteed.

At present, the national network operation and inspection department populates intelligent inspection service application on a large scale. In recent two years, national network companies apply small rotor unmanned aerial vehicles to inspect 4825-base towers in common, apply medium unmanned helicopters to inspect 832-base towers in common, apply large unmanned helicopters to inspect 562-base towers in common, apply fixed wing unmanned aerial vehicles to inspect 4221.9 kilometers in common, and have preliminarily established new modes of cooperative inspection of helicopters, unmanned aerial vehicles and workers. Along with the large-scale use of intelligent equipment such as unmanned aerial vehicle, robot in the electric wire netting is patrolled and examined, state net company's production intelligent degree has obtained improving, also provides higher requirement to equipment is patrolled and examined the intelligent processing of data collection simultaneously. At the present stage, the unmanned aerial vehicle and the helicopter have low inspection return data quality, large data volume and low classification and query processing efficiency, return data mainly comprises video images, and the ubiquitous problem is that: the method has the advantages of large quantity of repeated shot pictures, incapability of eliminating low-quality images, large data quantity and complex data content, and is very time-consuming for screening, analyzing and processing the acquired data by means of manual or common image processing calculation.

Disclosure of Invention

In view of this, the present application provides an infrared image processing method and apparatus for power transmission line detection, so as to achieve automatic detection of infrared images of a power transmission line detection site, and improve work efficiency of power transmission line inspection.

According to a first aspect, an embodiment of the present invention provides an infrared image processing method for power transmission line detection, including: acquiring an infrared image of a power transmission line detection site; preprocessing the infrared image to generate a preprocessed infrared image; carrying out temperature field division processing on the preprocessed infrared image, and extracting corresponding temperature field data; and extracting corresponding temperature field characteristics according to the temperature field data.

With reference to the first aspect, in a first implementation of the first aspect, the temperature field characteristic includes a defect center point.

With reference to the first embodiment of the first aspect, in a second embodiment of the first aspect, the defect center point is determined according to the following formula:

wherein,representing a grey value of a pixel in the temperature field data;averepresenting a gray scale average of pixels in the temperature field data;stdrepresenting a standard deviation of pixel gray levels in the temperature field data;kis a scaling factor.

With reference to the first aspect or the first or second implementation manner of the first aspect, in a third implementation manner of the first aspect, the performing temperature field division processing on the preprocessed infrared image to extract corresponding temperature field data includes: carrying out gray level processing on the preprocessed infrared image to generate a corresponding gray level image; performing morphological closed operation and connected domain calculation on the gray level image to generate corresponding temperature field data; the temperature field data includes isotherms and connected domains in the grayscale image.

With reference to the first aspect or any one of the first to third embodiments of the first aspect, in a fourth embodiment of the first aspect, the preprocessing the infrared image includes mean filtering and/or median filtering.

With reference to the first aspect or any one of the first to the third implementation manners of the first aspect, in a fifth implementation manner of the first aspect, the infrared image processing method for power transmission line detection further includes: acquiring a visible light image of the power transmission line detection site; and identifying fault equipment according to the visible light image.

According to a second aspect, an embodiment of the present invention provides an infrared image processing apparatus for power transmission line detection, including: the infrared image acquisition unit is used for acquiring an infrared image of a power transmission line detection site; the preprocessing unit is used for preprocessing the infrared image and generating a preprocessed infrared image; the temperature field segmentation unit is used for carrying out temperature field segmentation processing on the preprocessed infrared image and extracting corresponding temperature field data; and the temperature field characteristic extraction unit is used for extracting corresponding temperature field characteristics according to the temperature field data.

According to a third aspect, an embodiment of the present invention provides a server, including: a memory for storing a program; a processor configured to implement the method according to the first aspect or any of the embodiments of the first aspect by executing a program stored in the memory.

According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which includes a program, where the program is executable by a processor to implement the method according to the first aspect or any of the embodiments of the first aspect.

According to the infrared image processing method and device for power transmission line detection, provided by the embodiment of the invention, the infrared image of the power transmission line is subjected to preprocessing and temperature field characteristic extraction, so that the infrared image is automatically detected and identified, and the power transmission line detection working efficiency is favorably improved. In addition, because the infrared spectrum of the equipment mainly reflects the distribution rule of temperature and the detail of the characteristic of the equipment is not obvious, the infrared image processing method and the infrared image processing device for detecting the power transmission line provided by the embodiment of the invention can automatically process the infrared image, acquire the corresponding visible light image, identify the fault equipment information in the visible light image, establish a bidirectional equipment type marking model, and record the characteristic of a typical fault by comparing the visible light identification information with the infrared spectrum identification information in a linking manner.

Drawings

Fig. 1 is a flowchart illustrating a specific example of an infrared image processing method for power transmission line detection in an embodiment of the present invention;

fig. 2 is a schematic structural diagram illustrating a specific example of an infrared image processing apparatus for power transmission line detection in an embodiment of the present invention;

fig. 3 is a schematic structural diagram showing a specific example of a server in the embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the following detailed description and accompanying drawings. Wherein like elements in different embodiments are numbered with like associated elements. In the following description, numerous details are set forth in order to provide a better understanding of the present application. However, those skilled in the art will readily recognize that some of the features may be omitted or replaced with other elements, materials, methods in different instances. In some instances, certain operations related to the present application have not been shown or described in detail in order to avoid obscuring the core of the present application from excessive description, and it is not necessary for those skilled in the art to describe these operations in detail, so that they may be fully understood from the description in the specification and the general knowledge in the art.

Furthermore, the features, operations, or characteristics described in the specification may be combined in any suitable manner to form various embodiments. Also, the various steps or actions in the method descriptions may be transposed or transposed in order, as will be apparent to one of ordinary skill in the art. Thus, the various sequences in the specification and drawings are for the purpose of describing certain embodiments only and are not intended to imply a required sequence unless otherwise indicated where such sequence must be followed.

At present, an infrared detection device has a function of automatically judging temperature, but is limited to points in a fixed angle picture, and possible fault points of equipment are various and complex. And the equipment to which the point belongs still needs manual judgment. Therefore, for equipment fault diagnosis by using the infrared map, the infrared map is preprocessed, and then the temperature field segmentation based on the isotherm is carried out to determine the defect center position of the infrared map. And then carrying out identification matching on the visible light image so as to carry out fault diagnosis.

In view of this, an embodiment of the present invention provides an infrared image processing method for power transmission line detection, and as shown in fig. 1, the infrared image processing method may include the following steps:

step S11: and acquiring an infrared image of the transmission line detection site. In order to enable a user to simultaneously observe an ultraviolet image, a visible light image and an infrared image of the same position on a power transmission line, the field of view of the infrared image should be parallel to the fields of view of the visible light image and the ultraviolet image.

Step S12: and preprocessing the infrared image to generate a preprocessed infrared image. The infrared heat spectrum has the following characteristics:

a. due to reasons of scene heat balance, light wave wavelength, long transmission distance, atmospheric attenuation and the like, the infrared image has strong spatial correlation, low contrast and fuzzy visual effect;

b. the infrared thermal image represents the temperature distribution of the scenery, is a gray image and has no color or shadow, so that the resolution ratio is low and the resolution potential is poor for human eyes;

c. the detection capability and the spatial resolution of the thermal imaging system are lower than those of the visible light CCD array, so that the definition of an infrared image is lower than that of a visible light image;

d. random interference of the external environment and imperfection of the thermal imaging system bring various noises such as thermal noise, shot noise, photon and electron fluctuation noise to the infrared image. The distributed complex noises make the signal-to-noise ratio of the infrared image lower than that of the common television image;

e. due to the reasons of inconsistent response characteristics of all detection units of the infrared detector, defects of an optical machine scanning system and the like, non-uniformity of an infrared image is caused and is reflected as fixed pattern noise, crosstalk, distortion and the like of the image.

From the above analysis, it can be known that the infrared image is generally darker, the contrast between the target image and the background is low, the edge is blurred, the noise is large, and the like. According to the characteristics of the infrared spectrum, firstly, a mean filtering algorithm and a median filtering algorithm are adopted to achieve the purpose of preprocessing the infrared spectrum for smoothly removing noise.

The mean filtering is a typical linear filtering algorithm, and means that a template is given to a target pixel on an image, and the template comprises adjacent pixels around the target pixel and the target pixel. The average value of all pixels in the template is then used instead of the original pixel value. The mean filtering is also called linear filtering, and the main method adopted by the mean filtering is a neighborhood averaging method. The basic principle of linear filtering is to replace each pixel value in the original image with a mean value, i.e. to-be-processed current pixel (x, y), select a template, the template is composed of a plurality of pixels adjacent to the template, find the mean value of all pixels in the template, then assign the mean value to the current pixel (x, y), as the gray value g (x, y) of the processed image at the point, i.e. g (x, y) =1/m Σ f (x, y), m is the total number of pixels including the current pixel in the template. The mean filtering can effectively filter additive noise in the image, but the mean filtering has inherent defects, namely the image details cannot be well protected, and the detail part of the image is damaged while the image is denoised, so that the image becomes fuzzy. The mean filtering mainly comprises arithmetic mean filtering, geometric mean filtering, harmonic mean filtering and inverse harmonic mean filtering, and the project is intended to verify the noise reduction effect of the arithmetic mean filtering, the geometric mean filtering and the inverse harmonic mean filtering.

The median filter is a common nonlinear smoothing filter, the basic principle is that the value of a point in a digital image or a digital sequence is replaced by the median of each point value in a neighborhood of the point, and the median filter has the main function of changing the pixel with larger difference of the gray value of the surrounding pixels into the value close to the value of the surrounding pixels, so that the isolated noise point can be eliminated, and the median filter is very effective for filtering the salt and pepper noise of the image. The conventional median filter can play a good smoothing effect on the noise of the long-tail probability distribution. Moreover, the method has the advantage of protecting boundary information while eliminating noise, and plays a role in protecting certain details in the image, so that the method is widely applied to image denoising processing. The performance of removing impulse noise by the conventional median filtering is greatly influenced by the size of a filtering window, and certain contradiction exists between the aspects of inhibiting image noise and protecting details; conversely, the larger the filtering window is, the more the noise suppression capability is enhanced, but the detail protection capability is weakened. This discrepancy is particularly apparent when the noise interference is large in the image. According to experience: the effect of conventional median filtering appears unsatisfactory when the impulse noise strength is greater than 0.2. Therefore, the conventional median filtering method alone is far from sufficient for image denoising application, and a new improved algorithm needs to be searched to solve the contradiction. The filtering mode of the self-adaptive median filter is the same as that of the conventional median filter, and a window Sxy of a rectangular area is used, except that in the filtering process, the size of the filtering window can be changed (namely increased) by the self-adaptive median filter according to a certain set condition, and meanwhile, when the pixel in the center of the filtering window is judged to be noise, the value is replaced by the median, otherwise, the current pixel value is not changed. The output of the filter is thus substituted for the value at pixel (x, y), i.e. the coordinates of the centre of the current filter window. The optimized median filtering algorithm can process impulse noise with higher noise probability and can better keep image details.

Step S13: and carrying out temperature field division processing on the preprocessed infrared image, and extracting corresponding temperature field data. The infrared image characteristics refer to parameters such as gradient of a temperature field, shape of an isotherm, temperature grade and the like in an infrared image, have a very close relationship with the type and fault position of the thermal fault of the power equipment, and research finds out the shape parameters of the temperature field and extracts an identification area by an image processing method. The purpose of extracting the infrared image characteristic information is to perform image matching and further find out the similarity between a thermal image to be diagnosed and a previous fault form through the image matching, and the purpose of image temperature field segmentation is to establish a thermal fault infrared image sample database of the power equipment. The infrared atlas has rich colors which gradually change according to rules, the gradually changing area is a main mark for dividing an isotherm, and in order to identify the isotherm and further finish the segmentation of a temperature field, the infrared image needs to be subjected to gray processing firstly, so that the morphological characteristics of the temperature field are more clearly expressed. Then, morphological closing operation is performed, and the isotherm is highlighted as needed. And finally, calculating a connected domain, and carrying out segmentation identification on the similar temperature fields. The algorithm used in the process can be briefly described as follows:

a. image graying processing

Because the photos are all color images and all adopt an RGB color mode, when the images are processed, the RGB components are respectively processed, and actually the RGB cannot reflect the morphological characteristics of the images, and only the color is blended in an optical principle.

There are many other color modes, such as the HSI mode, where HSI represents color by three components, hue, saturation and brightness. HSI is more consistent with human visual characteristics than RGB.

The color of each pixel in the color image is determined by R, G, B three components, and 255 median values are desirable for each component, so that a pixel can have a range of 1600 tens of thousands (255 x 255) of colors. The gray image is a special color image with R, G, B components being the same, wherein the variation range of one pixel point is 255, so that in digital image processing, images in various formats are generally converted into gray images, so that the calculation amount of subsequent images is reduced. The description of a grayscale image, like a color image, still reflects the distribution and characteristics of the chrominance and luminance levels, both globally and locally, of the entire image.

The method is that according to YUV color space, the physical meaning of Y component is the brightness of point, the brightness level is reflected by the value, and according to the change relation of RGB and YUV color space, the correspondence of brightness Y and R, G, B three color components can be established: y =0.3R +0.59G +0.11B, and the gradation value of the image is expressed in this luminance value.

b. Morphological closed-loop operation

Morphological closing operations are used to eliminate small objects, separate objects at fine points, smooth the boundaries of larger objects, and do not significantly change their area. The morphological erosion operation is a process of eliminating boundary points and shrinking the boundaries inward. Can be used to eliminate small and meaningless objects, and specifically, each pixel of the image can be scanned with a 3 × 3 structuring element; carrying out AND operation on the structural elements and the binary image covered by the structural elements; if both are 1, the pixel of the resulting image is 1. Otherwise, the value is 0; the binary image may be reduced by one turn. Dilation is the process of merging all background points in contact with an object into the object, expanding the boundary outward. The method can be used for filling up the holes in the object, and specifically, each pixel of the image can be scanned by using a 3x3 structural element; carrying out AND operation on the structural elements and the binary image covered by the structural elements; if both are 0, the pixel of the resulting image is 0. Otherwise, the value is 1; the binary image can be enlarged by one turn. And performing an expansion algorithm and then performing a corrosion algorithm on the image to complete the morphological closed operation.

c. Connected domain computation

The connected domain refers to a set consisting of a plurality of pixels, the gray levels of all the pixels in the set are ① less than or equal to the level of the connected domain, ② the pixels in the same connected domain are connected in pairs, namely a path completely consisting of elements of the set exists between any two pixels, the connected domain mark refers to that the pixels meeting a certain connection rule in an image are marked as the same target, a proper data structure is designed to store the mark number of the target to which each pixel belongs, and the attribute of the related target is stored.

The temperature field data of different temperatures can be obtained by carrying out graying processing on the infrared image, then carrying out morphological closed operation and then carrying out connected domain calculation, wherein the temperature field data comprises parameters such as the gradient of a temperature field in the infrared image, the shape of an isotherm, the temperature grade and the like.

Step S14: and extracting corresponding temperature field characteristics according to the temperature field data. Generally, a fault infrared spectrum has a small area which is the area with the highest temperature, a temperature field with a temperature grade is formed by radiating temperature from the area to the periphery, and the highest temperature is a point or a small area, and the point is called as the highest temperature point or a defect central point. The thermal infrared imager expresses the temperature by color, and the darker the color is, the lower the temperature is, and the whiter the color is, the higher the temperature is. In infrared fault diagnosis, a fault location device can be generally determined by using a defect center, according to characteristics of an infrared image, the defect center often corresponds to a point with highest or lowest pixel contrast of the image, and after the infrared image is grayed, the defect center is a region or a point with the largest gray value, so that a search formula can be expressed as:

wherein,representing a grey value of a pixel in the temperature field data; ave represents the gray scale average value of the pixels in the temperature field data; std represents a standard deviation of a pixel gradation in the temperature field data; k is a scaling factor, which may be, for example, 1. It can be seen from the infrared spectrum that the gray levels of most regions are the same, in order to quickly locate the defect center, in practical application, the average gray level of the image should be obtained first, and then the pixel points with the gray levels larger than the average gray level are searched and compared according to the condition that the gray level of the defect center is the maximum, so as to quickly find out the defect center. The coordinates of the region point with the highest temperature can be easily found out through the processing of the algorithm, and then the coordinates are calibrated on an original image and subjected to feature extraction processing, so that the identification of the infrared spectrum fault center point is obtained.

Because the infrared spectrum of the equipment mainly reflects the distribution rule of the temperature, the detail of the characteristic of the equipment is not obvious. Therefore, for the identification of the infrared spectrum of the power equipment, the equipment needs to be identified and labeled through visible light, and a bidirectional equipment type labeling model is established. For this purpose, the following steps may be added after step S11 to identify the malfunctioning device:

step S15: and identifying the fault equipment according to the visible light image. For the image with the text label in the image area, the visible light image can be preprocessed, including image denoising, edge enhancement, edge detection and the like, the digital image is positioned and an interested area is cut out through an image processing algorithm, and on the basis of the interested area, the related structure is continuously segmented and extracted according to the specific task requirement. Secondly, feature extraction is carried out on the image, feature vector extraction is carried out on the discrete character digital image, and the key is to extract feature vectors with high character distinguishing degree. And thirdly, pattern recognition is carried out on the characteristic vectors, the extracted characteristic vectors are input, characters are correctly distinguished through pattern matching algorithm recognition and description, and an image processing task is completed. And finally, labeling the image according to the identification result, thereby determining the fault equipment.

For the image without the text label in the image area, firstly, the image processing technology is utilized to extract the bottom layer visual characteristics of the equipment image, including color, texture, shape, space information and the like, as the metadata of the image. When an image of the power equipment is labeled, the labeling problem is regarded as an image classification problem and mainly divided into two stages:

i) label model training phase (training classifier with large number of classified images): submitting an image representing the specific visual requirement of the project, and constructing a depth network mapping model which is iterated layer by layer and abstracted layer by layer from the bottom visual feature of the image to the high-level semantic feature by using the labeled image set;

ii) an image annotation stage: and calculating the similarity with all images in the training library, returning the image most similar to the image, classifying the image into a predefined class according to the visual information of the test image, and regarding each keyword as an independent class name and corresponding to a classifier, thereby more accurately labeling the power equipment image of the unknown sample.

The fault equipment information identified according to the visible light image is associated with the defect center identified according to the infrared image, so that the fault equipment and the fault point thereof can be conveniently and quickly found, and convenience is provided for equipment first-aid repair.

An embodiment of the present invention further provides an infrared image processing apparatus for detecting a power transmission line, and as shown in fig. 2, the infrared image processing apparatus may include: an infrared image acquisition unit 21, a preprocessing unit 22, a temperature field division unit 23 and a temperature field feature extraction unit 24.

The infrared image acquisition unit 21 is configured to acquire an infrared image of a power transmission line detection site; the specific working method can be seen in step S11 in the above method embodiment.

The preprocessing unit 22 is configured to preprocess the infrared image and generate a preprocessed infrared image; the specific working method can be seen in step S12 in the above method embodiment.

The temperature field segmentation unit 23 is configured to perform temperature field segmentation processing on the preprocessed infrared image, and extract corresponding temperature field data; the specific working method can be seen in step S13 in the above method embodiment.

The temperature field characteristic extracting unit 24 is configured to extract corresponding temperature field characteristics according to the temperature field data, and the specific working method thereof can be shown in step S14 in the above method embodiment.

An embodiment of the present invention further provides a server, as shown in fig. 3, the server may include a processor 501 and a memory 502, where the processor 501 and the memory 502 may be connected by a bus or in another manner, and fig. 3 takes the connection by the bus as an example.

Processor 501 may be a Central Processing Unit (CPU). The Processor 501 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or combinations thereof.

The memory 502, which is a non-transitory computer-readable storage medium, may be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules corresponding to the infrared image processing method for power transmission line detection in the embodiment of the present invention (for example, the infrared image acquisition unit 21, the pre-processing unit 22, the temperature field segmentation unit 23, and the temperature field feature extraction unit 24 shown in fig. 2). The processor 501 executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory 502, that is, implements the management and control method based on the operation inspection service in the above method embodiments.

The memory 502 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor 501, and the like. Further, the memory 502 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 502 optionally includes memory located remotely from processor 501, which may be connected to processor 501 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The one or more modules are stored in the memory 502, and when executed by the processor 501, perform the infrared image processing method for power transmission line detection in the embodiment shown in fig. 1.

The details of the server may be understood with reference to the corresponding related description and effects in the embodiment shown in fig. 1, and are not described herein again.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.

The present invention has been described in terms of specific examples, which are provided to aid understanding of the invention and are not intended to be limiting. For a person skilled in the art to which the invention pertains, several simple deductions, modifications or substitutions may be made according to the idea of the invention.

Claims (9)

1. An infrared image processing method for power transmission line detection is characterized by comprising the following steps:

acquiring an infrared image of a power transmission line detection site;

preprocessing the infrared image to generate a preprocessed infrared image;

carrying out temperature field division processing on the preprocessed infrared image, and extracting corresponding temperature field data;

and extracting corresponding temperature field characteristics according to the temperature field data.

2. The infrared image processing method for power transmission line detection according to claim 1, wherein the temperature field characteristic includes a defect center point.

3. The infrared image processing method for power transmission line detection according to claim 2, wherein the defect center point is determined according to the following formula:

wherein,representing a grey value of a pixel in the temperature field data;averepresenting a gray scale average of pixels in the temperature field data;stdrepresenting a standard deviation of pixel gray levels in the temperature field data;kis a scaling factor.

4. The infrared image processing method for power transmission line detection according to any one of claims 1 to 3, wherein the performing temperature field division processing on the preprocessed infrared image and extracting corresponding temperature field data comprises:

carrying out gray level processing on the preprocessed infrared image to generate a corresponding gray level image;

performing morphological closed operation and connected domain calculation on the gray level image to generate corresponding temperature field data; the temperature field data includes isotherms and connected domains in the grayscale image.

5. The infrared image processing method for power transmission line detection according to any one of claims 1 to 4, wherein the preprocessing the infrared image comprises mean filtering and/or median filtering.

6. The infrared image processing method for power transmission line detection according to any one of claims 1 to 4, further comprising:

acquiring a visible light image of the power transmission line detection site;

and identifying fault equipment according to the visible light image.

7. An infrared image processing device for power transmission line detection is characterized by comprising:

the infrared image acquisition unit is used for acquiring an infrared image of a power transmission line detection site;

the preprocessing unit is used for preprocessing the infrared image and generating a preprocessed infrared image;

the temperature field segmentation unit is used for carrying out temperature field segmentation processing on the preprocessed infrared image and extracting corresponding temperature field data;

and the temperature field characteristic extraction unit is used for extracting corresponding temperature field characteristics according to the temperature field data.

8. A server, comprising:

a memory for storing a program;

a processor for implementing the method of any one of claims 1-6 by executing a program stored by the memory.

9. A computer-readable storage medium, characterized by comprising a program executable by a processor to implement the method of any one of claims 1-6.