Method and apparatus for processing infrared thermal images

Abstract

The embodiments of this disclosure generally relate to the field of infrared thermal imaging technology, and specifically to a method and apparatus for processing infrared thermal images. The method includes acquiring an infrared thermal image and corresponding extreme temperature information, wherein the infrared thermal image includes pixel values ​​of each pixel, and the extreme temperature information includes the highest temperature value of the infrared thermal image, the highest temperature coordinate corresponding to the highest temperature value, the lowest temperature value, and the lowest temperature coordinate corresponding to the lowest temperature value. It also includes determining the highest temperature pixel value corresponding to the highest temperature value and the lowest temperature pixel value corresponding to the lowest temperature value in the infrared thermal image based on the highest and lowest temperature coordinates. Furthermore, it includes determining the temperature value of each pixel in the infrared thermal image based on the pixel values, the highest temperature pixel value, and the lowest temperature pixel value. This approach can reduce the computational load and storage file size of the infrared imaging terminal.

Description

Technical Field

[0001] The embodiments disclosed herein generally relate to the field of infrared thermal imaging technology, and specifically to a method and apparatus for processing infrared thermal images. Background Technology

[0002] When an infrared terminal captures an infrared thermal image, it can store the temperature or temperature data of each pixel for analysis. However, this method significantly increases the computational load on the infrared terminal and results in excessively large stored infrared thermal image files. Summary of the Invention

[0003] Embodiments of this disclosure provide a method and apparatus for processing thermal images, aimed at solving one or more of the above-mentioned problems and other potential problems.

[0004] According to a first aspect of this disclosure, a method for processing an infrared thermal image is provided. The method includes acquiring the infrared thermal image and corresponding extreme temperature information, wherein the infrared thermal image includes pixel values ​​for each pixel, and the extreme temperature information includes the highest temperature value, the highest temperature coordinate corresponding to the highest temperature value, the lowest temperature value, and the lowest temperature coordinate corresponding to the lowest temperature value in the infrared thermal image. The method further includes determining, based on the highest and lowest temperature coordinates, the highest temperature pixel value corresponding to the highest temperature value and the lowest temperature pixel value corresponding to the lowest temperature value in the infrared thermal image. Furthermore, the method includes determining the temperature value of each pixel in the infrared thermal image based on the pixel values, the highest temperature pixel value, and the lowest temperature pixel value.

[0005] According to a second aspect of this disclosure, an apparatus for processing infrared thermal images is provided. The apparatus includes an acquisition module configured to acquire an infrared thermal image and corresponding extreme temperature information, wherein the infrared thermal image includes pixel values ​​for each pixel, and the extreme temperature information includes the highest temperature value of the infrared thermal image, the highest temperature coordinate corresponding to the highest temperature value, the lowest temperature value, and the lowest temperature coordinate corresponding to the lowest temperature value. The apparatus further includes a matching module configured to determine, based on the highest and lowest temperature coordinates, the highest temperature pixel value corresponding to the highest temperature value and the lowest temperature pixel value corresponding to the lowest temperature value in the infrared thermal image. Furthermore, the apparatus includes a calculation module configured to determine the temperature value of each pixel in the infrared thermal image based on the highest temperature value, the lowest temperature value, and the pixel values ​​of each pixel in the infrared thermal image.

[0006] According to a third aspect of this disclosure, a computer program product is provided. The computer program product includes a computer program that is executed by a processor to implement the method according to the first aspect.

[0007] According to a fourth aspect of this disclosure, an electronic device is provided. The electronic device includes one or more processors. Furthermore, the electronic device includes a memory associated with the one or more processors, the memory for storing program instructions that, when read and executed by the one or more processors, perform the steps of the method according to the first aspect. Attached Figure Description

[0008] The above and other objects, features, and advantages of embodiments of the present disclosure will become readily apparent from the following detailed description taken in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated in the drawings by way of example and not limitation.

[0009] Figure 1 The diagram illustrates an example environment in which embodiments of the present disclosure may be implemented.

[0010] Figure 2 A flowchart illustrating a method for processing infrared thermal images according to an embodiment of the present disclosure is shown.

[0011] Figure 3 A schematic diagram illustrating the calculation process of the composite pixel value according to an embodiment of the present disclosure is shown.

[0012] Figure 4 A flowchart illustrating another method for processing infrared thermal images according to an embodiment of the present disclosure is shown.

[0013] Figure 5 A schematic diagram is shown illustrating the generation of temperature calibration estimates using a two-stream convolutional neural network according to an embodiment of the present disclosure.

[0014] Figure 6 A schematic block diagram of an example apparatus according to an embodiment of the present disclosure is shown.

[0015] Figure 7 A block diagram of an example device according to an embodiment of the present disclosure is shown.

[0016] In the various figures, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Implementation

[0017] Preferred embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While preferred embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art.

[0018] The term "comprising" and its variations as used herein signify an open-ended inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "at least partially based on". The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". Terms such as "upper", "lower", "front", and "rear", indicating placement or positional relationship, are based on the orientation or positional relationship shown in the accompanying drawings and are used only for the purpose of describing the principles of this disclosure, and are not intended to indicate or imply that the elements referred to must have a specific orientation, be constructed or operated in a specific orientation, and therefore should not be construed as limiting this disclosure.

[0019] As mentioned earlier, storing the temperature or temperature data of each pixel in an infrared terminal would significantly increase its computational load and result in excessively large stored infrared thermal imaging files. However, in fields such as industrial inspection, energy loss assessment, and fire monitoring, it is necessary to measure the temperature value of each pixel using infrared thermal imaging to accurately locate fault areas, heat leak points, and fire sources.

[0020] To address this, according to embodiments of this disclosure, a method for processing infrared thermal images is provided. This method may include: acquiring an infrared thermal image and corresponding extreme temperature information, wherein the infrared thermal image includes pixel values ​​for each pixel, and the extreme temperature information includes the highest temperature value, the highest temperature coordinate corresponding to the highest temperature value, the lowest temperature value, and the lowest temperature coordinate corresponding to the lowest temperature value in the infrared thermal image. The method may further include determining the highest temperature pixel value corresponding to the highest temperature value and the lowest temperature pixel value corresponding to the lowest temperature value in the infrared thermal image based on the highest and lowest temperature coordinates. Furthermore, the method includes determining the temperature value of each pixel in the infrared thermal image based on the pixel values, the highest temperature pixel value, and the lowest temperature pixel value. Using this method according to embodiments of this disclosure, a secondary analysis of the infrared thermal image can be performed to calculate the temperature of all pixels in the infrared thermal image, thus reducing the computational load and storage file size of the infrared imaging terminal.

[0021] Figure 1 A schematic diagram is shown illustrating an example environment 100 that can be implemented according to embodiments of the present disclosure. Figure 1As shown, in one or more embodiments of this disclosure, the infrared imaging terminal can calculate the highest and lowest temperature values ​​in the infrared thermal imaging image 101 it captures, and associate the highest temperature value with its coordinate position in the infrared thermal imaging image (i.e., the highest temperature coordinate) and the lowest temperature value with its coordinate position in the infrared thermal imaging image (i.e., the lowest temperature coordinate) as extreme temperature information 102 of the infrared thermal imaging image. In some embodiments, the infrared thermal imaging image can be stored in formats such as JPEG, TIFF, and PNG files, which include the pixel values ​​of each pixel (which can be single-channel grayscale values, or multiple channel values ​​such as R channel, G channel, and B channel). The extreme temperature information can be stored in another data file using 16-bit byte code in a certain content order (e.g., highest temperature value, highest temperature coordinate x, highest temperature coordinate y, lowest temperature value, lowest temperature coordinate x, lowest temperature coordinate y). The infrared imaging terminal can store the infrared thermal imaging image and the data file containing the extreme temperature information in the same folder to associate the two. The computing device 103 may include, but is not limited to, personal computers, server computers, handheld or laptop devices, mobile devices (such as mobile phones, personal digital assistants (PDAs), media players, etc.), multiprocessor systems, consumer electronics, wearable electronic devices, smart home devices, minicomputers, mainframe computers, edge computing devices, and distributed computing systems that include any one of the above systems or devices. Figure 1 In the example, computing device 103 can directly or indirectly acquire the infrared thermal image 101 and corresponding extreme temperature information 102 of the infrared imaging terminal via wired or wireless means, and determine the temperature value 104 of each pixel in the infrared thermal image based on the infrared thermal image 101 and the extreme temperature information 102. In this way, the infrared imaging terminal does not need to calculate the temperature value of all pixels, which not only reduces the amount of computation of the infrared imaging terminal, but also reduces the size of the infrared imaging terminal's storage file.

[0022] The following combination Figure 2 A method flow for processing infrared thermal images according to embodiments of the present disclosure is described. Figure 2 A flowchart of a method 200 for processing an infrared thermal image according to an embodiment of the present disclosure is shown. In some embodiments, in Figure 1 In the example environment 100 shown, method 200 can be executed by computing device 103. It should be understood that method 200 may also include additional actions not shown and / or actions shown may be omitted; the scope of this disclosure is not limited in this respect. Method 200 can be executed on any suitable computing device. Figure 2As shown in block 202, the computing device can acquire an infrared thermal image and the corresponding extreme temperature information. In one or more embodiments of this disclosure, the infrared thermal image and the corresponding extreme temperature information can be stored in an infrared imaging terminal, a mobile storage device (e.g., an SD card, a USB flash drive, etc.), or uploaded to a cloud storage terminal. The computing device can directly acquire the infrared thermal image and its extreme temperature information stored in the infrared imaging terminal via wired or wireless communication, or indirectly acquire the infrared thermal image and its extreme temperature information from a mobile storage device or a cloud storage terminal via wired or wireless communication.

[0023] In box 204, the computing device can determine the highest temperature pixel value corresponding to the highest temperature value and the lowest temperature pixel value corresponding to the lowest temperature value in the infrared thermal imaging image based on the highest temperature coordinate and the lowest temperature coordinate. In one or more embodiments of this disclosure, the computing device can decode the acquired infrared thermal imaging image to obtain the width and height of the infrared thermal imaging image. In one or more embodiments of this disclosure, the pixel value storage location of the pixel point corresponding to the highest temperature coordinate and the lowest temperature coordinate can be found by combining the width and height of the infrared thermal imaging image, thereby obtaining the highest temperature pixel value corresponding to the highest temperature coordinate and the lowest temperature pixel value corresponding to the lowest temperature coordinate. In one or more embodiments of this disclosure, for a single-channel infrared thermal imaging image, the pixel value corresponding to the pixel point can be a single value such as a grayscale value. The grayscale value of the infrared thermal imaging image can reflect the surface radiation intensity of the object, and the radiation intensity is directly related to the temperature. Therefore, the pixel value of the pixel point corresponding to the highest temperature coordinate can be directly used as the highest temperature pixel value. The pixel value of the pixel corresponding to the lowest temperature coordinate is taken as the lowest temperature pixel value. .

[0024] In block 206, the computing device can determine the temperature value of a pixel in the infrared thermal imaging image based on the pixel value, the highest temperature pixel value, and the lowest temperature pixel value of the pixel. In one or more embodiments of this disclosure, for a single-channel infrared thermal imaging image, the pixel value corresponding to a pixel can be a single numerical value such as a grayscale value. The grayscale value of the infrared thermal imaging image can reflect the surface radiation intensity of an object, and radiation intensity is directly related to temperature. Generally, the higher the temperature, the greater the radiation intensity, and the higher the corresponding grayscale value. Therefore, the size of the pixel value can, to a certain extent, reflect the relative temperature at the corresponding pixel location in the infrared thermal imaging image. The computing device can determine the temperature value of the pixel corresponding to the highest temperature pixel. Subtract the lowest temperature value The temperature difference in the infrared thermal image was obtained. Subsequently, the computing device can iterate through the pixel values ​​of each pixel in the infrared thermal image, based on the pixel value of the highest temperature. Lowest temperature pixel value The pixel value of the i-th pixel The temperature value corresponding to the i-th pixel is calculated according to the following formula (1). :

[0025]

[0026] In one or more embodiments of this disclosure, for a multi-channel infrared thermal image, the pixel value corresponding to a pixel point can be an array composed of individual channel values ​​(e.g., R channel values, G channel values, and B channel values). RGB infrared thermal images map temperature values ​​to visible light colors through pseudo-color encoding, thereby reflecting temperature distribution. In one or more embodiments of this disclosure, a computing device can transform an array including multiple channel values ​​to obtain a comprehensive pixel value that reflects temperature levels. For example, the R channel value of the i-th pixel point can be used as a basis for this transformation. G channel value and B channel value The comprehensive pixel value of the i-th pixel is calculated according to formula (2). :

[0027]

[0028] Overall pixel value The lower the value, the lower the temperature, which is related to the overall pixel value. A higher grayscale value indicates a higher temperature. The size of the grayscale value can, to some extent, reflect the relative temperature of the corresponding pixel location in the infrared thermal image.

[0029] Figure 3 A schematic diagram illustrating the calculation process of the composite pixel value according to an embodiment of the present disclosure is shown. For example... Figure 3 As shown, in one or more embodiments of this disclosure, at block 204, the computing device can decode the acquired infrared thermal image to obtain the width and height of the infrared thermal image. Combining the highest and lowest temperature coordinates, it finds the pixel value 311 of the pixel corresponding to the highest temperature coordinate 321 and the pixel value 312 of the pixel corresponding to the lowest temperature coordinate 322 in the infrared thermal image. Further, the comprehensive pixel value 313 of the pixel corresponding to the highest temperature coordinate can be calculated according to formula (2) as the highest temperature pixel value. The combined pixel value of 314, corresponding to the lowest temperature coordinate, is used as the highest temperature pixel value. .

[0030] In box 206, the computing device can display the highest temperature value. Subtract the lowest temperature value The temperature difference in the infrared thermal image was obtained. Subsequently, the computing device can iterate through the pixel values ​​of each pixel in the infrared thermal image, based on the pixel value of the highest temperature. Lowest temperature pixel value The comprehensive pixel value of the i-th pixel The temperature value corresponding to the i-th pixel is calculated according to the following formula (3). :

[0031]

[0032] In this way, it is possible to estimate the temperature value corresponding to each pixel in an infrared thermal image based solely on the extreme temperature information of the infrared thermal image, thereby obtaining the temperature data of each pixel in the infrared thermal image and a preliminary temperature matrix of the infrared thermal image. This enables quantitative temperature analysis of infrared thermal images.

[0033] Figure 4 A flowchart illustrating another method for processing infrared thermal images according to embodiments of the present disclosure is shown. In some embodiments, Figure 1 In the example environment 100, method 400 may be executed by computing device 103, and the infrared thermal image 101 also has corresponding environmental parameters. In one or more embodiments of this disclosure, the environmental parameters may include humidity information, temperature measurement distance information, and emissivity information detected by the infrared imaging terminal through sensors. The environmental parameters can be stored together with or separately from extreme temperature information and are associated with the infrared thermal image. Method 400 can combine the environmental parameters to make a more accurate estimate of the temperature of each pixel in the infrared thermal image, obtaining an enhanced temperature estimate corresponding to the infrared thermal image. It should be understood that method 400 may also include additional actions not shown and / or the actions shown may be omitted, and the scope of this disclosure is not limited in this respect. Figure 4 In the middle, boxes 402, 404, and 406 are respectively with Figure 1 The boxes 202, 04, and 206 in the text are the same, so they will not be described again here.

[0034] In box 408, the computing device can base its calculations on the temperature values ​​of all pixels in the infrared thermal image (i.e., the preliminary temperature matrix). The system uses the highest temperature coordinates corresponding to the highest temperature value, the lowest temperature coordinates corresponding to the lowest temperature value, and environmental parameters to generate a temperature calibration estimate for the infrared thermal image. This temperature calibration estimate takes into account the environmental parameters during the infrared thermal image capture, enabling environmentally adaptive temperature mapping and accurate temperature estimation under more environmental conditions. In one or more embodiments of this disclosure, the infrared imaging terminal can collect humidity H, temperature measurement distance D, and emissivity values ​​in real time during the acquisition of the infrared thermal image. One or more of the parameters are stored as environmental parameters corresponding to the infrared thermal image. In one or more embodiments of this disclosure, the temperature distribution of the infrared thermal image and the environmental parameters can be dynamically fused through a two-stream convolutional neural network to adapt to temperature estimation under different environmental parameters and generate a temperature calibration estimate of the infrared thermal image. Figure 5 A schematic diagram illustrating the principle of generating temperature calibration estimates using a two-stream convolutional neural network according to an embodiment of the present disclosure is shown. Figure 5 As shown, in one or more embodiments of this disclosure, the initial temperature matrix can be processed by a convolutional neural network 5311. Processing is performed to generate temperature feature vectors corresponding to the infrared thermal image. ,in This represents the initial temperature matrix of the infrared thermal image. Simultaneously, the highest temperature coordinates corresponding to the highest temperature value are obtained through a text embedding model (5312). The lowest temperature coordinates corresponding to the lowest temperature value and environmental parameters The vectors are concatenated and encoded using a fully connected network (MLP) 5313 to generate the environmental feature vector E corresponding to the infrared thermal image. Subsequently, the temperature feature vector is... The temperature flow and environmental feature vector E are input into the attention gating module 5314. The weights of the temperature flow and environmental flow are dynamically adjusted through attention gating to obtain the dynamically weighted temperature calibration function. Finally, the temperature values ​​of each pixel in the infrared thermal image are calibrated based on a temperature calibration function to generate a calibrated temperature matrix of the infrared thermal image. That is, the temperature calibration estimate corresponding to the infrared thermal image. The calculation formula is as follows:

[0035]

[0036] In one or more embodiments of this disclosure, the initial temperature matrix input to the convolutional neural network can also be... Standardization processes can be performed, such as temperature value normalization to accelerate neural network training and prevent numerical overflow, histogram equalization to enhance the contrast of temperature estimates, median filtering or Gaussian noise filtering to remove noise, and standardization to a homogeneity of 0 and a variance of 1. In this way, dynamic calibration of infrared thermal images can be achieved by fusing visual features and environmental parameters.

[0037] In box 410, the computing device can perform temperature calibration estimation based on the temperature corresponding to the infrared thermal image. The maximum temperature coordinates corresponding to the maximum temperature value, the minimum temperature coordinates corresponding to the minimum temperature value, and environmental parameters are used to generate a non-uniform interpolated temperature estimate corresponding to the infrared thermal image. In one or more embodiments of this disclosure, an approximate solution to the heat diffusion equation can be constructed based on the maximum and minimum temperature coordinates.

[0038]

[0039] Wherein, λ is a dynamic correction factor for the thermal diffusivity, used to simulate the influence of environmental factors on the heat conduction path and velocity. In one or more embodiments of this disclosure, the computing device can adjust the parameters according to a humidity correction function. Temperature measurement distance correction function Emittance correction function Calculate the thermal diffusivity λ:

[0040]

[0041] in, The reference thermal diffusivity can be, for example, the thermal conductivity of air; H is the humidity value in the environmental parameters of the infrared thermal image; and D is the temperature measurement distance in the environmental parameters of the infrared thermal image. Emissivity is the environmental parameter in the infrared thermal image.

[0042] In one or more embodiments of this disclosure, the temperature correction function It can be:

[0043]

[0044] Where H represents the humidity value in the environmental parameters of the infrared thermal image. The baseline humidity is (e.g., 50%). The temperature sensitivity coefficient calibrated for the experiment (e.g., ).

[0045] Temperature measurement distance correction function It can be:

[0046]

[0047] Where D is the temperature measurement distance in the environmental parameters of the infrared thermal image. This represents the maximum effective temperature measurement distance of the infrared imaging terminal. For distance sensitivity coefficient (e.g., ).

[0048] Emittance correction function It can be:

[0049]

[0050] in, The emissivity in the environmental parameters of an infrared thermal image is typically the emissivity of the object being photographed in the image. . For emissivity sensitivity coefficient (e.g., ).

[0051] Based on environmental parameters H, D, The thermal diffusivity λ is updated and substituted into the iterative calculation of the thermal diffusivity equation in formula (5) to obtain the temperature calibration estimate. The thermal field approximation solution. In one or more embodiments of this disclosure, the thermal field approximation solution, the highest temperature coordinates, the lowest temperature coordinates, and the temperature calibration estimate can be combined. An adaptive interpolation algorithm is used to perform non-uniform interpolation, resulting in a non-uniform interpolated temperature estimate. .

[0052] In this way, the impact of environmental factors on the heat diffusion path can be simulated more accurately, and thermal infrared imaging temperature interpolation in complex scenarios can be better adapted. Furthermore, the accuracy at the highest and lowest temperature values ​​can be preserved first, while smoothing out noise in other areas.

[0053] In box 412, the computing device can estimate the temperature based on the non-uniform interpolation corresponding to the infrared thermal image. In addition to environmental parameters, it generates enhanced temperature estimates corresponding to infrared thermal images. In one or more embodiments of this disclosure, the initial temperature matrix can be based on the temperature values ​​of all pixels in the infrared thermal image. This generates high-frequency features and low-frequency features of the infrared thermal image. In one or more embodiments of this disclosure, a Gaussian low-pass filter can be used to... Smoothing is performed to obtain low-frequency features. :

[0054]

[0055] in, It is a Gaussian kernel. It can be dynamically adjusted according to the resolution of the infrared thermal image (e.g., ).

[0056] In one or more embodiments of this disclosure, high-frequency features can be separated from a preliminary temperature matrix by subtraction:

[0057]

[0058] In one or more embodiments of this disclosure, it is also possible to... and Normalization was performed to obtain low-frequency features that eliminated temperature range differences. and high frequency characteristics .

[0059] In one or more embodiments of this disclosure, high-frequency characteristics, low-frequency characteristics, and non-uniform interpolated temperature estimates can be determined based on environmental parameters. The fusion weights are used to obtain the enhanced temperature estimate. For example, the low-frequency weights. High-frequency weights Non-uniform interpolation weights The calculation formula is as follows:

[0060]

[0061] Low frequency characteristics and non-uniform interpolation temperature estimation We obtain the normalized temperature estimate by weighting the fusion according to the fusion weights. :

[0062]

[0063] The normalized temperature estimate after fusion Mapping back to the original temperature range yields an enhanced temperature estimate of the infrared thermal image. :

[0064]

[0065] In this way, low-frequency features can preserve the global temperature distribution trend, while high-frequency features can enhance local temperature details, thus compensating for the low contrast of infrared thermal images. Dynamically adjusting weights based on environmental parameters allows for temperature estimation to adapt to different environmental conditions. Furthermore, non-uniform interpolation results are used to correct the non-uniformity of the infrared imaging terminal, improving the reliability of temperature distribution estimation.

[0066] Figure 6A schematic block diagram of an example device 600 according to some embodiments of the present disclosure is shown. Device 600 can be implemented by software, hardware, or a combination of both. Figure 6 As shown, the device 600 includes an acquisition module 601, a matching module 602, and a calculation module 603.

[0067] In some embodiments, the acquisition module 601 can be configured to acquire an infrared thermal image and corresponding extreme temperature information, wherein the infrared thermal image includes pixel values ​​of each pixel, and the extreme temperature information includes the highest temperature value of the infrared thermal image, the highest temperature coordinates corresponding to the highest temperature value, the lowest temperature value, and the lowest temperature coordinates corresponding to the lowest temperature value. The matching module 602 can be configured to determine the highest temperature pixel value corresponding to the highest temperature value and the lowest temperature pixel value corresponding to the lowest temperature value in the infrared thermal image based on the highest temperature coordinates and the lowest temperature coordinates. The calculation module can be configured to determine the temperature value of each pixel in the infrared thermal image based on the highest temperature value, the lowest temperature value, and the pixel values ​​of each pixel in the infrared thermal image.

[0068] Figure 6 The device 600 can be used to achieve the above-mentioned combination. Figures 1 to 5 For the sake of brevity, the process described will not be repeated here.

[0069] The division of modules or units in the embodiments of this disclosure is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. Furthermore, the functional units in the disclosed embodiments may be integrated into one unit, exist as separate physical entities, or two or more units may be integrated into one unit. The integrated unit described above can be implemented in hardware or as a software functional unit.

[0070] Figure 7 A block diagram of an example device 700 that can be used to implement embodiments of the present disclosure is shown. It should be understood that... Figure 7 The device 700 shown is merely an example and should not be construed as limiting the functionality and scope of the implementation described herein. For example, device 700 can be used to perform the functions described above. Figures 1 to 6 The process described.

[0071] like Figure 7As shown, device 700 is in the form of a general-purpose computing device. Components of computing device 700 may include, but are not limited to, one or more processors or processing units 701, memory 702, storage device 703, one or more communication units 704, one or more input devices 705, and one or more output devices 706. Processing unit 701 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 702. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of computing device 700.

[0072] Computing device 700 typically includes multiple computer storage media. Such media can be any available media accessible to computing device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 702 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof). Storage device 703 can be removable or non-removable media and may include machine-readable media, such as flash drives, disks, or any other media capable of storing information and / or data (e.g., training data for training) and accessible within computing device 700.

[0073] The computing device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 7 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 702 may include computer program product 721 having one or more program modules configured to perform various methods or actions of various implementations of this disclosure.

[0074] The communication unit 704 enables communication with other computing devices via a communication medium. Additionally, the components of the computing device 700 can function as a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the computing device 700 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0075] Input device 705 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 706 can be one or more output devices, such as a monitor, speaker, printer, etc. Computing device 700 can also communicate with one or more external devices (not shown) via communication unit 704 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with computing device 700, or with any device that enables computing device 700 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication can be performed via an input / output (I / O) interface (not shown).

[0076] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is provided that stores a computer program thereon, which, when executed by a processor, implements the methods described above.

[0077] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0078] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0079] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0080] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0081] Various implementations of this disclosure have been described above. The foregoing description is exemplary and not exhaustive, nor is it limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for processing infrared thermal images, characterized in that, include: The infrared thermal image and the extreme temperature information corresponding to the infrared thermal image are obtained. The infrared thermal image includes the pixel values ​​of each pixel. The extreme temperature information includes the highest temperature value of the infrared thermal image, the highest temperature coordinate corresponding to the highest temperature value, the lowest temperature value, and the lowest temperature coordinate corresponding to the lowest temperature value. The infrared thermal image also has corresponding environmental parameters, which include at least the humidity information, temperature measurement distance information, and emissivity information corresponding to the infrared thermal image. Based on the highest temperature coordinates and the lowest temperature coordinates, determine the highest temperature pixel value corresponding to the highest temperature value and the lowest temperature pixel value corresponding to the lowest temperature value in the infrared thermal image; The temperature value of the pixel in the infrared thermal image is determined based on the pixel value of the pixel, the highest temperature pixel value, and the lowest temperature pixel value in the infrared thermal image. Based on the temperature values ​​of all pixels in the infrared thermal image, the highest temperature coordinates corresponding to the highest temperature value, the lowest temperature coordinates corresponding to the lowest temperature value, and the environmental parameters, a temperature calibration estimate corresponding to the infrared thermal image is generated. Based on the temperature calibration estimate corresponding to the infrared thermal image, the highest temperature coordinate corresponding to the highest temperature value, the lowest temperature coordinate corresponding to the lowest temperature value, and the environmental parameters, a non-uniform interpolation temperature estimate corresponding to the infrared thermal image is generated. as well as Based on the non-uniform interpolated temperature estimate corresponding to the infrared thermal image and the environmental parameters, an enhanced temperature estimate corresponding to the infrared thermal image is generated. Furthermore, the step of generating a temperature calibration estimate corresponding to the infrared thermal image based on the temperature values ​​of all pixels in the infrared thermal image, the highest temperature coordinate corresponding to the highest temperature value, the lowest temperature coordinate corresponding to the lowest temperature value, and the environmental parameters includes: Based on the temperature values ​​of all pixels in the infrared thermal image, a temperature feature vector corresponding to the infrared thermal image is generated through a convolutional neural network. Based on the highest temperature coordinates corresponding to the highest temperature value, the lowest temperature coordinates corresponding to the lowest temperature value, and the environmental parameters, an environmental feature vector corresponding to the infrared thermal image is generated through a fully connected network; and Based on the temperature feature vector and the environmental feature vector, a temperature calibration estimate corresponding to the infrared thermal image is generated through an attention-gated fusion module.

2. The method according to claim 1, characterized in that, The pixel value includes multiple channel values; and determining the highest temperature pixel value corresponding to the highest temperature value and the lowest temperature pixel value corresponding to the lowest temperature value in the infrared thermal image based on the highest temperature coordinate and the lowest temperature coordinate includes: Based on the highest temperature coordinates and the lowest temperature coordinates, determine the highest temperature pixel point and the lowest temperature pixel point in the infrared thermal image corresponding to the highest temperature value and the lowest temperature pixel point in the infrared thermal image corresponding to the lowest temperature value. Based on all channel values ​​of the highest temperature pixel and the lowest temperature pixel, respectively, determine the combined pixel value of the highest temperature pixel and the lowest temperature pixel; and Based on the combined pixel values ​​of the highest temperature pixel and the lowest temperature pixel, the highest temperature pixel value corresponding to the highest temperature value and the lowest temperature pixel value corresponding to the lowest temperature value are determined.

3. The method according to claim 2, characterized in that, Determining the temperature value of a pixel in the infrared thermal image based on the pixel value of the pixel in the infrared thermal image, the highest temperature pixel value, and the lowest temperature pixel value includes: Based on all channel values ​​of the pixels in the infrared thermal image, determine the comprehensive pixel value of the pixels; and The temperature value of the pixel is determined based on the combined pixel value, the highest temperature value, the lowest temperature value, the highest temperature pixel value, and the lowest temperature pixel value.

4. The method according to claim 3, characterized in that The step of generating a non-uniform interpolated temperature estimate corresponding to the infrared thermal image based on the temperature calibration estimate corresponding to the infrared thermal image, the highest temperature coordinate corresponding to the highest temperature value, the lowest temperature coordinate corresponding to the lowest temperature value, and the environmental parameters includes: Based on the environmental parameters, an approximate solution for the thermal field corresponding to the temperature calibration estimate is generated; and Based on the highest temperature coordinates corresponding to the highest temperature value, the lowest temperature coordinates corresponding to the lowest temperature value, and the thermal field approximation solution, a non-uniform interpolation temperature estimate corresponding to the infrared thermal image is generated.

5. The method according to claim 4, characterized in that, The step of generating the enhanced temperature estimate corresponding to the infrared thermal image based on the environmental parameters and the non-uniform interpolated temperature estimate corresponding to the infrared thermal image includes: Based on the temperature values ​​of all pixels in the infrared thermal image, high-frequency features and low-frequency features of the infrared thermal image are generated; and Based on the environmental parameters, the high-frequency and low-frequency characteristics of the infrared thermal image, and the non-uniform interpolation temperature estimation, an enhanced temperature estimate corresponding to the infrared thermal image is generated.

6. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-5.

7. Electronic devices, including: One or more processors, and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method described in any one of claims 1-5.

Images