A method of infrared thermographic image processing and analysis

Abstract

The application belongs to the technical field of infrared image processing, and specifically discloses a method for processing and analyzing infrared thermal imaging images, which comprises the following steps: obtaining a source image, obtaining original infrared thermal image data of a target device from a gimbal infrared thermal imaging camera of a power inspection robot; calculating temperature values of pixels corresponding to the infrared thermal image data according to a temperature measurement algorithm according to the infrared thermal image data; performing temperature correction on the original infrared thermal image to obtain a temperature-corrected infrared thermal image; performing contour extraction on the temperature-corrected infrared thermal image to obtain a plurality of fault regions; obtaining fault determination data of each fault region, and obtaining a fault analysis result according to the fault determination data. The application solves the problems of high labor cost, low detection efficiency and low fault analysis accuracy caused by the inability to observe the details of the fault region in the prior art.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of image processing, and particularly relates to an infrared thermal imaging image processing and analysis method. BACKGROUND

[0002] Power equipment infrared thermal imaging is to detect the infrared radiation energy emitted by power equipment, convert the thermal signal into an electrical signal, and then obtain the thermal image of the power equipment after electrical signal processing. Power infrared detection has the characteristics of no power interruption, non-contact, mature technology, etc., and can find potential hidden dangers and faults of power equipment, and has been widely used in the field of power equipment thermal anomaly detection. Long-term operation or environmental factors of power equipment can cause problems such as poor contact and overload in key parts, thereby causing heating in some areas of the equipment. According to relevant data, more than half of the faulty power equipment will have abnormal heating phenomenon.

[0003] With the development of artificial intelligence, domestic and foreign researchers have carried out some researches on image fusion and defect recognition. Some are based on correlation vector machines for equipment classification and identification; some establish multiple power equipment template image libraries to determine the outline and position of the target area through the matching degree of the template and the image; some combine threshold segmentation mechanism, pixel segmentation algorithm, etc. to quickly segment the temperature abnormal connected region or equipment; some use convolutional neural network to extract the features of infrared fault images and train and learn.

[0004] Therefore, we propose an infrared thermal imaging image processing and analysis method to solve the above problems SUMMARY

[0005] The purpose of the present application is to provide an infrared thermal imaging image processing and analysis method to solve the problems raised in the background.

[0006] To this end, in order to achieve the above purpose, the present application provides the following technical scheme: an infrared thermal imaging image processing and analysis method, which uses an infrared thermal imaging device to obtain an infrared image of power equipment.

[0007] The technical scheme adopted by the present application is:

[0008] An infrared thermal imaging image processing and analysis method, comprising the following steps:

[0009] S1: Source image acquisition, obtaining original infrared thermal image data of a target device from a pan-tilt infrared thermal imaging camera of a power inspection robot;

[0010] S2: According to the infrared thermal image data, calculating the temperature value of the pixel corresponding to the infrared thermal image data according to the temperature measurement algorithm;

[0011] S3: correcting the original infrared thermal image according to the temperature value to obtain a temperature-corrected infrared thermal image;

[0012] S4: extracting contours from the temperature-corrected infrared thermal image to obtain a plurality of fault regions;

[0013] S5: obtaining fault determination data of each fault region, and obtaining a fault analysis result according to the fault determination data.

[0014] Further, the temperature data of step S1 includes a temperature maximum value of the original infrared thermal image and a preset temperature range value of interest.

[0015] Further, the specific steps of step S3 are:

[0016] S3-1: obtaining a power function transformation value of temperature correction according to the temperature data, and initializing the power function transformation value;

[0017] S3-2: correcting the original infrared thermal image according to the initialized power function transformation value to obtain a temperature-corrected infrared thermal image.

[0018] Further, in step S3-1, the formula of the power function transformation value of temperature correction is:

[0019] E=Ceil[(T max -T min ) / N_TOI]

[0020] In the formula, E is the power function transformation value; Ceil [*] is a minimum integer return function; T max , T min are the maximum and minimum values of the temperature of the original infrared thermal image in the temperature data respectively; and N_TOI is the preset temperature range value of interest of the original infrared thermal image in the temperature data.

[0021] Further, in step S3-1, the initialization formula of the power function transformation value is:

[0022]

[0023] In the formula, E is the power function transformation value.

[0024] Further, in step S3-2, the formula of temperature correction is:

[0025]

[0026] In the formula, N(i,j) is the temperature value of the temperature corrected infrared thermal image; F(i,j) is the temperature value of the original infrared thermal image; i and j are respectively the horizontal and vertical indicators; E is the power function transformation value; a is the setting parameter of the gray value offset; b is the setting parameter of the curve bending degree to stretch the degree; and c is the setting parameter of the temperature value offset.

[0027] Further, the specific method of step S4 is: pre-processing the temperature corrected infrared thermal image to obtain a pre-processed image, and performing contour extraction on the pre-processed image to obtain a plurality of fault regions.

[0028] Further, the pre-processing includes gray processing and binary processing performed on the temperature corrected infrared thermal image.

[0029] Further, the specific steps of step S5 are:

[0030] S5-1: performing filling extraction on each fault region to obtain a corresponding range region image;

[0031] S5-2: obtaining the area of the range region image to obtain corresponding fault determination data;

[0032] S5-3: obtaining corresponding fault levels according to the fault determination data;

[0033] S5-4: obtaining a fault analysis result according to the fault levels.

[0034] Further, in step S5-3, the specific method of pre-setting the fault levels is: obtaining historical fault determination data of all target devices, performing level division according to the historical fault determination data, and obtaining corresponding fault levels.

[0035] The present application has the following advantages:

[0036] The present application provides a method for processing and analyzing infrared thermal imaging images, which avoids manual inspection, reduces labor cost investment, and improves inspection efficiency. In the case of constant temperature interval, the method of stretching the temperature difference in the high temperature zone is used to make the temperature corrected infrared thermal image display more details of the high temperature part, so as to realize accurate fault positioning and intelligent fault analysis of the target device. The method realizes intelligentization and improves the fault analysis accuracy.

[0037] Other advantages of the present application will be described in detail in the specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced. Obviously, the accompanying drawings in the following description only represent some of the embodiments of the present application, and for those skilled in the art, other drawings can be obtained from these drawings without any creative effort.

[0039] Figure 1 is a flow chart of a device fault analysis method. DETAILED DESCRIPTION

[0040] The present application will be further described below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the description of these embodiments is used to help understand the present application, but does not constitute a limitation on the present application. The functional details disclosed in the present application are only used to describe the example embodiments of the present application. However, the present application can be embodied in many alternative forms, and should not be understood as being limited in the embodiments described in the present application.

[0041] It should be understood that the terms used in the present application are only used to describe specific embodiments, and are not intended to limit the example embodiments of the present application. If the terms "include", "includes", "contain" and / or "contained" are used in the present application, the existence of the declared features, integers, steps, operations, units and / or components is specified, and the existence or addition of one or more other features, quantities, steps, operations, units, components and / or their combinations is not excluded.

[0042] It should be understood that it should also be noted that in some alternative embodiments, the functions / acts appearing may not be in the order appearing in the drawings. For example, depending on the functions / acts involved, they can actually be performed substantially concurrently, or sometimes two consecutively shown figures can be performed in reverse order.

[0043] It should be understood that in the following description, specific details are provided to facilitate a full understanding of the example embodiments. However, those skilled in the art should understand that the example embodiments can be implemented without these specific details. For example, systems can be shown in block diagrams to avoid obscuring the examples with unnecessary details. In other instances, well-known processes, structures and techniques can not be shown in unnecessary detail to avoid obscuring the example embodiments.

[0044] Embodiment 1

[0045] In the embodiment, first, a device fault analysis system is established, the device fault analysis system comprises an infrared thermal imager, a microprocessor and a communication module arranged at each target device, and a data analysis center, the microprocessor is in communication connection with the infrared thermal imager and the communication module respectively, the communication module is in communication connection with the data analysis center, the infrared thermal imager is used for collecting original infrared thermal images of the target device and sending to the microprocessor, the microprocessor sends the original infrared thermal images to the data analysis center for device fault analysis through the communication module, manual inspection is avoided, human cost investment is reduced, and inspection efficiency is improved.

[0046] The infrared thermal imager is a device using infrared thermal imaging technology, detecting infrared radiation of a target, and through signal processing, photoelectric conversion and other means, converting the temperature distribution image of the target into a visible image. The infrared thermal imager accurately quantizes the actually detected heat to form a whole of the target in real time, so as to accurately identify a suspected fault area that is heating, and an operator can preliminarily judge heating conditions and a fault position through image color and hot spot tracking display on a screen, and strictly analyze, thereby embodying high efficiency and high accuracy in confirming problems.

[0047] As shown in Figure 1 , the embodiment provides a method for processing and analyzing an infrared thermal imaging image, comprising the following steps:

[0048] S1: source image acquisition, acquiring original infrared thermal image data of a target device from a pan-tilt infrared thermal imaging camera of a power inspection robot;

[0049] S2: according to the infrared thermal image data, calculating a temperature value of a pixel corresponding to the infrared thermal image data according to a temperature measurement algorithm;

[0050] The temperature data comprises a temperature maximum value of the original infrared thermal image and a preset temperature range value of interest;

[0051] S3: according to the temperature data, performing temperature correction on the original infrared thermal image to obtain a temperature-corrected infrared thermal image, and the specific steps are as follows:

[0052] S3-1: according to the temperature data, acquiring a power function transformation value for temperature correction, and initializing the power function transformation value;

[0053] The formula of the power function transformation value for temperature correction is:

[0054] E=Ceil[(T max -T min ) / N_TOI]

[0055] In the formula, E is the power function transformation value; Ceil [*] is a minimum integer return function; T max, T min respectively are the maximum and minimum temperature values of the original infrared thermal image in the temperature data; N_TOI is a preset temperature range value of the original infrared thermal image in the temperature data;

[0056] The initialization formula of the power function transformation value is:

[0057]

[0058] In the formula, E is the power function transformation value;

[0059] S3-2: According to the initialized power function transformation value, the temperature of the original infrared thermal image is corrected to obtain a temperature-corrected infrared thermal image, which enhances the display range of the high-temperature area of the original infrared thermal image, so that the corrected thermal image can show more details of the high-temperature part. In a normal case, the mapping of the temperature value and the gray value is an average mapping in the temperature interval. In the present scheme, the function transformation is used to revise the temperature value, stretch the temperature difference in the high-temperature area, and compress the temperature difference in the low-temperature area.

[0060] The formula for temperature correction is:

[0061]

[0062] In the formula, N(i,j) is the temperature value of the temperature-corrected infrared thermal image; F(i,j) is the temperature value of the original infrared thermal image; i and j are respectively the horizontal and vertical indicators; E is the power function transformation value; a is a setting parameter of the gray value offset; b is a setting parameter of the bending degree of the curve to the stretching degree; and c is a setting parameter of the temperature value offset.

[0063] S4: The temperature-corrected infrared thermal image is preprocessed to obtain a preprocessed image, and the preprocessed image is profiled to obtain a plurality of fault areas.

[0064] The preprocessing includes gray processing and binarization processing of the temperature-corrected infrared thermal image.

[0065] The gray processing maps the corrected temperature value to the gray value, which can display more details of the high-temperature part of the original infrared thermal image, and then the binarization processing is performed to facilitate subsequent profile extraction.

[0066] The binary image is traversed to determine a non-zero point as a starting point, and then the non-zero values in the adjacent 8 pixels are sequentially searched and used as subsequent traversal points. The same method is continuously used for searching, and at the same time, special cases such as intersection and overlap of the profile line are screened and merged. Finally, the adjacent connected regions are spliced to obtain the profile of the fault area, and according to the profile, a plurality of fault areas are obtained.

[0067] S5: Obtain fault determination data of each fault region, and obtain fault analysis result according to the fault determination data, and the specific steps are as follows:

[0068] S5-1: Fill and extract each fault region in the temperature corrected infrared thermal image to obtain a corresponding range area image, in this embodiment, the range area image is taken as a region array, if there are multiple range area images, they are extracted as multiple region arrays respectively;

[0069] S5-2: Obtain the area of the range area image, and calculate the area and morphology of the single region array respectively to obtain corresponding fault determination data;

[0070] S5-3: Obtain corresponding fault level according to the fault determination data;

[0071] The specific method of the preset fault level is as follows: obtain historical fault determination data of all target devices, divide the levels according to the historical fault determination data, and obtain corresponding fault levels, as shown in Table 1;

[0072] Table 1

[0073] Failure class Failure description S Critical defect, must stop A Major defect, pending manual confirmation B Minor defect, can be temporarily ignored, must be counted in statistics C Normal

[0074] S5-4: Obtain fault analysis result according to the fault level, that is, obtain fault description of the current target device according to each fault level in Table 1, so that the staff can obtain the specific fault condition of the current target device, in this scheme, the temperature difference stretching method of the high temperature area is adopted, so that the temperature corrected infrared thermal image can show more details of the high temperature part, so as to realize accurate fault positioning and intelligent fault analysis of the target device, while realizing intelligentization, the fault analysis accuracy is improved.

[0075] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present application can be realized by a general computing device, which can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and can be realized by program code executable by the computing device, so that they can be stored in the storage device and executed by the computing device, or they can be made into each integrated circuit module, or multiple modules or steps can be made into a single integrated circuit module. Thus, the present application is not limited to any specific hardware and software combination.

[0076] The above-described embodiments are merely illustrative for the present application, if the units described as separated components can be or can not be physically separated; if the components described as units can be or can not be physical units, i.e. can be located in one place or can be distributed to multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0077] The above embodiments are only used to illustrate the technical solutions of the present application, but not to limit it; although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified or some technical features can be replaced by equivalents. The modification or replacement does not make the essence of the corresponding technical solution deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

[0078] The present application is not limited to the above-mentioned optional embodiments, and anyone can derive other various forms of products under the inspiration of the present application. The above specific embodiments should not be understood as limiting the protection scope of the present application, and the protection scope of the present application should be defined by the claims, and the specification can be used to explain the claims.

Claims

1. A method of infrared thermographic image processing and analysis, characterized by: It comprises the following steps: S1: source image acquisition, obtaining the original infrared thermal image data of the target device from the infrared thermal imaging camera of the power inspection robot; S2: according to the infrared thermal image data, the temperature value of the corresponding pixel of the infrared thermal image data is calculated according to the temperature measurement algorithm; S3: according to the temperature value, the original infrared thermal image is corrected, and the temperature corrected infrared thermal image is obtained; The specific steps of step S3 are: S3-1: according to the temperature data, the power function transformation value of temperature correction is obtained, and the power function transformation value is initialized; S3-2: according to the initialized power function transformation value, the original infrared thermal image is corrected, and the temperature corrected infrared thermal image is obtained; In step S3-1, the formula of the power function transformation value of temperature correction is: E = Ceil[(T max -T min ) / N_TOI] In the formula, E is a power function transformation value; Ceil[*] is a minimum integer return function; T max , T min are the maximum and minimum values of the temperature of the original infrared thermal image in the temperature data, respectively; N_TOI is a preset temperature range value of the original infrared thermal image in the temperature data. In step S3-2, the formula of temperature correction is: In the formula, N(i,j) is the temperature value of the temperature corrected infrared thermal image; F(i,j) is the temperature value of the original infrared thermal image; I, j are respectively the horizontal and vertical indicators; E is the power function transformation value; a is the setting parameter of the gray value offset; b is the setting parameter of the curve bending degree to stretch the degree; c is the setting parameter of the temperature value offset; S4: contour extraction is carried out on the temperature corrected infrared thermal image, and a plurality of fault regions are obtained; S5: the fault determination data of each fault region is obtained, and the fault analysis result is obtained according to the fault determination data.

2. The method of claim 1, wherein: The temperature data of step S1 includes the temperature maximum value of the original infrared thermal image and the preset temperature range value of interest.

3. The method of claim 1, wherein: In step S3-1, the initialization formula of the power function transformation value is: In the formula, E is the power function transformation value.

4. The method of claim 1, wherein: The specific method of step S4 is: the temperature corrected infrared thermal image is preprocessed to obtain the preprocessed image, and the preprocessed image is contour extracted to obtain a plurality of fault regions.

5. The method of claim 4, wherein: The preprocessing includes gray processing and binary processing of the temperature corrected infrared thermal image.

6. The method of claim 1, wherein: The specific steps of step S5 are: S5-1: filling extraction is carried out on each fault region to obtain the corresponding range area image; S5-2: the area of the range area image is obtained, and the corresponding fault determination data is obtained; S5-3: according to the fault determination data, the corresponding fault level is obtained; S5-4: according to the fault level, the fault analysis result is obtained.

7. The method of claim 6, wherein: In step S5-3, the specific method of presetting the fault level is: obtaining the historical fault determination data of all target devices, and dividing the levels according to the historical fault determination data to obtain the corresponding fault level.

Images