Infrared image non-uniformity correction method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of image processing, and discloses an infrared image non-uniformity correction method and device, electronic equipment and a storage medium, and the method comprises the steps: calculating the target gray value of an infrared image under different irradiation; constructing a gray value correction equation set according to the target gray value; solving the gray value correction equation set by a least square method to obtain a correction coefficient; and correcting the to-be-corrected infrared image by using the correction coefficient to obtain a target infrared image. Through the implementation of the invention, the correction coefficient with stronger generalization ability can be obtained, the accuracy of the non-uniformity correction of the infrared image is improved, meanwhile, each pixel point of the infrared image to be corrected can be corrected by utilizing the correction coefficient, the non-uniformity correction effect of the infrared image is effectively improved, and a more accurate target infrared image is obtained.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an infrared image non-uniformity correction method, device, electronic equipment and storage medium. Background Art

[0002] The grayscale value of each pixel of an infrared image is captured by an infrared photosensitive unit. Many infrared photosensitive units form a surface array. The infrared photosensitive surface array can generate a two-dimensional infrared image. For example, the number of units of the infrared photosensitive surface array corresponding to an infrared image with a resolution of 800×640 is 800×640. However, due to the manufacturing process and other reasons, the infrared photosensitive units in the infrared photosensitive surface array cannot respond to infrared light in a completely consistent manner, resulting in different pixel values ​​output by different photosensitive units for the same infrared light. When the infrared photosensitive surface array captures a scene image with the same grayscale value everywhere (for example, when a plastic plate with uniform color and temperature is covered in front of the infrared photosensitive surface array), the actual infrared image grayscale value is not equal everywhere, but there is non-uniform noise, resulting in poor accuracy of the infrared image.

[0003] The existing method for correcting noise in infrared images is the two-point calibration method. The two-point calibration method assumes that the response of the infrared photosensitive unit to infrared light is a linear mapping, and the image is corrected by using a linear model. However, the performance of the two-point correction method depends on whether the infrared photosensitive unit has a linear response. In actual scenes, the response of the infrared photosensitive unit is often nonlinear, resulting in poor correction effect of the infrared image. Therefore, how to improve the correction accuracy of the infrared image and obtain a more accurate infrared image has become a problem to be solved urgently. Summary of the invention

[0004] The present invention provides an infrared image non-uniformity correction method, device, electronic equipment and storage medium, the main purpose of which is to solve the problem of poor accuracy of infrared image non-uniformity correction provided in the related art.

[0005] To achieve the above-mentioned purpose, the present invention provides a method for non-uniform correction of infrared images, comprising: acquiring infrared images under different irradiation conditions, and calculating a target grayscale value of each infrared image; constructing a grayscale value correction equation group of the infrared image according to the target grayscale value; solving the grayscale value correction equation group by the least square method to obtain a correction coefficient; and correcting the infrared image to be corrected using the correction coefficient to obtain a target infrared image.

[0006] The present invention also provides an infrared image non-uniformity correction device, comprising: a target gray value calculation module, used to obtain infrared images under different irradiation conditions and calculate the target gray value of each infrared image; a gray value correction equation group construction module, used to construct the gray value correction equation group of the infrared image according to the target gray value; a correction coefficient solving module, used to solve the gray value correction equation group by the least square method to obtain the correction coefficient; and an image correction module, used to correct the infrared image to be corrected using the correction coefficient to obtain the target infrared image.

[0007] The present invention also provides an electronic device, comprising: a memory communicatively connected to at least one processor; wherein the processor is used to execute a computer program stored in the memory; the memory stores a computer program executable by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the above-mentioned infrared image non-uniformity correction method.

[0008] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any one of the above-mentioned infrared image non-uniformity correction methods.

[0009] The embodiment of the present invention calculates the target grayscale value of the infrared image under different irradiation, and can construct a grayscale value correction equation group through the target grayscale value. The number of equations in the grayscale value correction equation group is greater than the number of correction coefficients, and a correction coefficient with stronger generalization ability can be obtained, thereby improving the accuracy of infrared image non-uniformity correction; the correction coefficient can be used to correct each pixel point of the infrared image to be corrected, effectively improving the infrared image non-uniformity correction effect, and obtaining a more accurate target infrared image. Therefore, the infrared image non-uniformity correction method, device, electronic device and storage medium proposed by the present invention can solve the problem of poor accuracy of infrared image non-uniformity correction. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of a flow chart of a method for non-uniformity correction of infrared images provided by an embodiment of the present invention;

[0011] Figure 2 A schematic diagram of the non-uniformity of an infrared image provided by an embodiment of the present invention;

[0012] Figure 3 A schematic diagram of a nonlinear response of an infrared photosensitive unit provided by an embodiment of the present invention;

[0013] Figure 4 A schematic diagram of the structure of an infrared image non-uniformity correction device provided by an embodiment of the present invention;

[0014] Figure 5A schematic diagram of the structure of an electronic device for implementing a method for non-uniform correction of infrared images provided by an embodiment of the present invention.

[0015] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0016] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0017] The embodiment of the present application provides a method for non-uniformity correction of infrared images, and the execution subject of the method for non-uniformity correction of infrared images includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, a method for non-uniformity correction of infrared images can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0018] Reference Figure 1 FIG. 1 is a flow chart of a method for non-uniformity correction of infrared images provided by an embodiment of the present invention, which specifically includes the following process:

[0019] S1. Obtain infrared images under different irradiation conditions and calculate the target grayscale value of each infrared image.

[0020] In one embodiment, in infrared imaging technology, objects radiate infrared rays due to their internal heat energy. The difference in radiation energy can be converted into a visible image by an infrared imaging system. The irradiation of different infrared images refers to the infrared radiation energy received by the surface of the object. The grayscale values ​​of the same pixel points in the infrared image under different irradiations are different, resulting in non-uniform pixel values ​​in the infrared image. The image has non-uniform noise. For example, see Figure 2 As shown, Figure 2 (a) represents the infrared image when uniform. Figure 2 (b) represents the stripe non-uniformity image when there is stripe non-uniform noise in the infrared image. Figure 2 (c) represents the patch non-uniformity image when patchy non-uniform noise exists in the infrared image.

[0021] In one embodiment, the existing infrared image non-uniformity correction method is a two-point calibration method, that is, assuming that the response of the infrared photosensitive unit that shoots the infrared image to the infrared light belongs to a linear mapping, the infrared image can be corrected using a linear model.

[0022] Among them, if the gray value of the pixel at the coordinate (m, n) of the original infrared image output by the infrared surface array composed of infrared photosensitive units is I(m, n), and the gray value of the pixel at the coordinate (m, n) of the infrared image after two-point calibration correction is J(m, n), then I(m, n) and J(m, n) have the following linear mapping relationship:

[0023] J(m,n)=a(m,n)×I(m,n)+b(m,n)

[0024] Among them, a(m,n) is the linear correction coefficient at the coordinate (m,n), and b(m,n) is the constant correction coefficient at the coordinate (m,n). Therefore, for each pixel in the infrared image, there is a pair of correction coefficients a(m,n) and b(m,n). For example, for an infrared image with a resolution of 800x640, there are 800x640 correction coefficients a(m,n) and b(m,n), and the set of all a(m,n) and the set of all b(m,n) each constitute a surface array of correction coefficients.

[0025] Specifically, for each pixel point there are two unknown correction coefficients a(m, n) and b(m, n). Two equations are required to solve the two unknowns. Therefore, the infrared images under two different irradiations of the infrared surface array to be corrected are used to construct two equations to solve the correction coefficients a(m, n) and b(m, n) at the coordinates (m, n), which is the meaning of "two" in the two-point correction method.

[0026] Specifically, the two-point correction method assumes that the image resolution of the infrared image is M×N, and uses an infrared camera that has not undergone non-uniform correction to capture infrared images under high irradiance in a uniform environment. The grayscale value of the high irradiance infrared image at (m, n) is recorded as I h (m, n), an infrared image under low irradiance in a uniform environment is taken using an infrared camera that has not undergone non-uniformity correction. The grayscale value of the low irradiance infrared image at (m, n) is recorded as I l (m, n), through I h (m, n) and I l (m, n) Calculate the arithmetic mean of the grayscale values ​​in the high-irradiance and low-irradiance infrared images as the target grayscale value, that is:

[0027] The target grayscale value of high-irradiance infrared image is:

[0028]

[0029] The target grayscale value of low-irradiance infrared image is:

[0030]

[0031] It should be known that the infrared image in a uniform environment is uniform, and the grayscale value of each pixel is the same. However, since the infrared camera has not been corrected for non-uniformity, the pixel grayscale value of the high / low irradiance infrared image is J at each (m, n) coordinate. h / J l .

[0032] Furthermore, the correction coefficient equation of the infrared image at (m, n) is constructed according to the target gray value:

[0033]

[0034] Solving the correction coefficient equation, we can get the correction coefficient:

[0035]

[0036] After obtaining the correction coefficient, the grayscale value of the pixel at (m, n) of the infrared image after two-point correction can be obtained by the following formula:

[0037] J(m,n)=a(m,n)×I(m,n)+b(m,n)

[0038] However, since the performance of the two-point correction method depends on whether the infrared photosensitive unit has a linear response, in actual scenes, the response of the infrared photosensitive unit is often nonlinear and presents a curve, resulting in poor correction effect of the two-point correction method on infrared images.

[0039] For details, please refer to Figure 3 As shown, the response of the infrared photosensitive unit presents an "S"-shaped curve, in which represents the intensity of the incident infrared radiation, and V represents the response of the infrared photosensitive unit.

[0040] Specifically, the present invention uses the same target infrared camera that has not undergone non-uniform correction to shoot K infrared images with different irradiation in a uniform environment, where K≥P+1, P is the number of nonlinear terms of the correction coefficient, and the number of nonlinear terms can be preset.

[0041] Specifically, the target grayscale value of each infrared image is calculated, including:

[0042] Get the gray value of each pixel in each infrared image;

[0043] The target grayscale value of the corresponding infrared image is calculated according to the grayscale value of each pixel.

[0044] Specifically, the target grayscale value of each infrared image is calculated using the preset target grayscale value formula:

[0045]

[0046] Among them, J k represents the target grayscale value of the kth infrared image, E represents the total number of pixels in the horizontal direction of the kth infrared image, F represents the total number of pixels in the vertical direction of the kth infrared image, and I k (e, f) represents the gray value of the pixel at the coordinate (e, f) of the kth infrared image.

[0047] In one embodiment, the total number of pixels of the infrared image in the horizontal and vertical directions represents the resolution of the infrared image, that is, the number of units of the corresponding infrared photosensitive surface array in the target infrared camera. For example, the number of units of the infrared photosensitive surface array corresponding to the infrared image with a resolution of 800x640 is 800x640. The infrared images under different irradiation are obtained by taking pictures with the same target infrared camera, so the resolutions of the infrared images under different irradiation are the same. At the same time, since the infrared image is uniform, the grayscale values ​​of the pixels of the target infrared image are equal everywhere, that is, the grayscale values ​​of the pixels of the k-th infrared image are J at each coordinate. k .

[0048] S2. Construct a grayscale correction equation group of the infrared image according to the target grayscale value.

[0049] In one embodiment, in actual situations, the response of the infrared photosensitive unit presents a curve. Therefore, the infrared image can be nonlinearly corrected by a function that is close to the nonlinear response of the infrared photosensitive unit. For example, the response of the infrared photosensitive unit presents an "s"-shaped curve. The inverse sine function (y=arcsin(x)) can be used to perform nonlinear correction on the non-uniformity of the infrared image.

[0050] In one embodiment, a grayscale correction equation group of an infrared image is constructed according to a target grayscale value, including:

[0051] The grayscale correction equation of each infrared image is constructed according to the target grayscale value using a preset correction formula;

[0052] The gray value correction equations are combined to obtain a gray value correction equation group.

[0053] Specifically, the correction formula is expressed as:

[0054]

[0055] Where i(e, f) is the gray value of the pixel at the pixel coordinate (e, f) of the infrared image to be corrected, J(e, f) is the gray value of the pixel after correction at the pixel coordinate (e, f), P is the total number of nonlinear terms, and a p (e, f) is the pth nonlinear term coefficient, b(e, f) is the bias correction coefficient, α p With α p are the preset algorithm hyperparameters respectively.

[0056] Specifically, the gray value correction equation group is expressed as:

[0057]

[0058] Among them, a p (e, f) represents the pth nonlinear term coefficient at the infrared image pixel coordinate (e, f), α p With β p are the preset algorithm hyperparameters, b(e, f) represents the bias correction coefficient at the infrared image pixel coordinate (e, f), P represents the total number of nonlinear term coefficients, K represents the total number of infrared images, and I K (e, f) represents the gray value of the pixel at the pixel coordinate (e, f) of the Kth infrared image.

[0059] In one embodiment, by performing non-uniform correction on the infrared image using a nonlinear function that is inverse to the response of the infrared photosensitive unit, a better correction effect can be achieved using fewer correction coefficients, thereby improving the accuracy of infrared image correction.

[0060] S3. Solve the gray value correction equation group using the least square method to obtain the correction coefficient.

[0061] In one embodiment, the gray value correction equation group is a linear equation group, and therefore, the gray value correction equation group can be solved according to the least square method to obtain the correction coefficient a 1 (e, f), a 2 (e, f), ..., a P (e, f), b(e, f).

[0062] In one embodiment, the gray value correction equation group is solved by least square method to obtain the correction coefficient, including:

[0063] Convert the gray value correction equations into a matrix and get the matrix equation:

[0064] The least square method is used to solve the matrix equation and obtain the correction coefficient.

[0065] In one embodiment, α p With β pis the preset algorithm hyperparameter, and the grayscale correction equation group can be rewritten according to the target grayscale value as follows:

[0066]

[0067] Among them, u kp (m, n) = arcsin(α p ×I k (m, n)+β p ), the rewritten grayscale value correction equation group can be converted into a matrix to obtain a matrix equation.

[0068] Specifically, the matrix equation is expressed as:

[0069] UA=J

[0070] J=[J 1 , J 2 , ..., J k , ..., J K ] T

[0071] A=[a 1 (e, f), a 2 (e, f), ..., a p (e, f), ..., a P (e, f), b(e, f)] T

[0072]

[0073] u kp (e, f) = arcsin(α p ×I k (e,f)+β p )

[0074] Among them, J k represents the target grayscale value of the kth infrared image, K represents the total number of infrared images, K represents the total number of infrared images, a p (e, f) represents the pth nonlinear term coefficient at the pixel coordinate (e, f), α p With β p is the preset algorithm hyperparameter, I k (e, f) represents the gray value of the kth infrared image at the pixel coordinate (e, f), P represents the total number of nonlinear terms, and b(e, f) represents the bias correction coefficient at the pixel coordinate (e, f).

[0075] In one embodiment, the matrix A composed of the correction coefficients is solved by UA=J, that is, A=pinv(U)J, pinv(U)=(U H U)-1 U H

[0076] Among them, U H represents the conjugate transposed matrix of the matrix U, (U H U) -1 Denotes the matrix U H The inverse of U.

[0077] In one embodiment, the number of grayscale correction equations in the grayscale correction equation group is greater than the number of correction coefficients, so that correction coefficients with stronger generalization ability can be obtained, thereby improving the accuracy of infrared image non-uniformity correction.

[0078] S4. Correct the infrared image to be corrected using the correction coefficient to obtain a target infrared image.

[0079] In one embodiment, the correction coefficient is calculated from multiple infrared images under different irradiation conditions. Therefore, the correction coefficient has good generalization ability for the target infrared camera. The correction coefficient can be used to more accurately correct the infrared image that needs to be corrected, wherein the infrared image to be corrected is a non-uniform infrared image taken by the same target infrared camera.

[0080] In one embodiment, the grayscale value of the pixel at each coordinate in the infrared image to be corrected can be corrected using the correction coefficient corresponding to each coordinate, thereby obtaining a uniform target infrared image.

[0081] Specifically, the correction formula is expressed as:

[0082]

[0083] Among them, G(i, j) represents the gray value of the pixel at the pixel coordinate (i, J) of the target infrared image, and a p (i, j) represents the pth nonlinear term coefficient at the pixel coordinate (i, j), P is the total number of nonlinear terms, α p With β p are preset algorithm hyperparameters, L(i, j) represents the grayscale value of the pixel at the pixel coordinate (i, j) of the infrared image to be corrected, and b(i, J) represents the bias correction coefficient at the pixel coordinate (i, J).

[0084] Preferably, the inverse sine function y=arcsin(x) can be replaced by other types of nonlinear functions, such as a polynomial function (according to Taylor series expansion, a nonlinear function similar to the inverse sine function curve can be constructed by a polynomial function, which can be used to replace the inverse sine function in the present invention.

[0085] In one embodiment, the infrared images to be corrected taken by the same target infrared camera have the same resolution. Therefore, the correction coefficient can correct each pixel point, and can accurately perform targeted correction on the infrared image to be corrected, effectively improve the infrared image non-uniformity correction effect, and obtain a more accurate target infrared image.

[0086] The embodiment of the invention calculates the target grayscale value of the infrared image under different irradiation, and can construct a grayscale value correction equation group through the target grayscale value. The number of equations in the grayscale value correction equation group is greater than the number of correction coefficients, and a correction coefficient with stronger generalization ability can be obtained to improve the accuracy of infrared image non-uniformity correction; the correction coefficient can be used to correct each pixel point of the infrared image to be corrected, effectively improving the infrared image non-uniformity correction effect, and obtaining a more accurate target infrared image. Therefore, the infrared image non-uniformity correction method proposed by the present invention can solve the problem of poor accuracy of infrared image non-uniformity correction.

[0087] like Figure 4 As shown, it is a schematic diagram of the structure of an infrared image non-uniformity correction device 400 provided by an embodiment of the present invention. The device includes a target gray value calculation module 401, which is used to obtain infrared images under different irradiation and calculate the target gray value of each infrared image; a gray value correction equation group construction module 402, which is used to construct a gray value correction equation group of the infrared image according to the target gray value; a correction coefficient solution module 403, which is used to solve the gray value correction equation group by the least square method to obtain the correction coefficient; and an image correction module 404, which is used to correct the infrared image to be corrected using the correction coefficient to obtain the target infrared image.

[0088] In detail, in one embodiment, the infrared image non-uniformity correction device 400 adopts the same technical means as an infrared image non-uniformity correction method in the accompanying drawings when used, and can produce the same technical effect, which will not be repeated here.

[0089] like Figure 5 FIG. 1 is a schematic diagram of the structure of an electronic device for implementing an infrared image non-uniformity correction method provided by an embodiment of the present invention.

[0090] The electronic device 500 may include a processor 501 , a memory 502 , a communication bus 503 , and a communication interface 504 , and may also include a computer program stored in the memory 502 and executable on the processor 501 , such as an infrared image non-uniformity correction program.

[0091] Among them, the processor 501 can be composed of an integrated circuit in some embodiments, for example, it can be composed of a single packaged integrated circuit, or it can be composed of multiple integrated circuits packaged with the same function or different functions, including one or more central processing units (CPU), microprocessors, digital processing chips, graphics processors and a combination of various control chips.

[0092] The memory 502 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 502 may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device.

[0093] The communication bus 503 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 502 and at least one processor 501, etc.

[0094] The communication interface 504 is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface or a wireless interface.

[0095] Figure 5 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 5 The structure shown does not constitute a limitation on the electronic device 500 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0096] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited by this structure.

[0097] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it can implement an infrared image non-uniformity correction method of any of the above embodiments. It should be noted that the computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device that can carry computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM). In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0098] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0099] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0100] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for non-uniform correction of infrared images, It is characterized in that The method comprises: Acquire infrared images under different irradiation conditions, and calculate a target grayscale value of each infrared image; Constructing a grayscale value correction equation group of the infrared image according to the target grayscale value; Solving the grayscale value correction equation group using the least square method to obtain a correction coefficient; The correction coefficient is used to correct the infrared image to obtain the target infrared image.

2. The infrared image non-uniformity correction method according to claim 1, It is characterized in that The calculating of the target grayscale value of each infrared image comprises: Obtaining the grayscale value of each pixel in each of the infrared images; The target grayscale value of the corresponding infrared image is calculated according to the grayscale value of each pixel.

3. The infrared image non-uniformity correction method as claimed in claim 2, It is characterized in that Calculating the target grayscale value of the corresponding infrared image according to the grayscale value of each pixel point includes: The target grayscale value of each infrared image is calculated using a preset target grayscale value formula, wherein the target grayscale value formula is expressed as: Among them, J k represents the target grayscale value of the kth infrared image, E represents the total number of pixels in the horizontal direction of the kth infrared image, F represents the total number of pixels in the vertical direction of the kth infrared image, and I k (e, f) represents the gray value of the pixel at the coordinate (e, f) of the kth infrared image.

4. The infrared image non-uniformity correction method according to claim 1, It is characterized in that The grayscale value correction equation group of the infrared image is constructed according to the target grayscale value, comprising: Constructing a grayscale value correction equation for each of the infrared images according to the target grayscale value using a preset correction formula; The gray value correction equations are combined to obtain a gray value correction equation group.

5. The infrared image non-uniformity correction method according to claim 4, It is characterized in that The correction formula is expressed as: Where I(e,f) is the gray value of the pixel at the pixel coordinate (e,f) of the infrared image to be corrected, J(e,f) is the gray value of the pixel after correction at the pixel coordinate (e,f), P is the total number of nonlinear terms, and a p (e, f) is the pth nonlinear term coefficient, b(e, f) is the bias correction coefficient, α p With β p They are the preset algorithm hyperparameters; The gray value correction equation group is expressed as: Among them, a p (e, f) represents the pth nonlinear term coefficient at the infrared image pixel coordinate (e, f), α p With β p are the preset algorithm hyperparameters, b(e, f) represents the bias correction coefficient at the infrared image pixel coordinate (e, f), P represents the total number of nonlinear term coefficients, K represents the total number of infrared images, and I K (e, f) represents the gray value of the pixel at the pixel coordinate (e, f) of the Kth infrared image.

6. The infrared image non-uniformity correction method according to claim 1, It is characterized in that The least square method is used to solve the gray value correction equation group to obtain the correction coefficient, including: The gray value correction equation group is converted into a matrix to obtain the matrix equation: The matrix equation is solved using the least square method to obtain the correction coefficient.

7. The infrared image non-uniformity correction method according to claim 6, It is characterized in that The matrix equation is expressed as: UA=J J=[J 1 ,J 2 ,...,J k ,...,J K ] T A=[a 1 (e), f), a 2 (e,f),...,a p (e,f),...,a P (e,f),b(e,f)] T u kp (e,f)=arcsin(α p ×I k (e,f)+β p ) Among them, J k represents the target grayscale value of the kth infrared image, K represents the total number of infrared images, K represents the total number of infrared images, a p (e, f) represents the pth nonlinear term coefficient at the pixel coordinate (e, f), α p With β p is the preset algorithm hyperparameter, I k (e, f) represents the gray value of the kth infrared image at the pixel coordinate (e, f), P represents the total number of nonlinear terms, and b(e, f) represents the bias correction coefficient at the pixel coordinate (e, f).

8. An infrared image non-uniformity correction device, It is characterized in that The device comprises: A target gray value calculation module is used to obtain infrared images under different irradiation conditions and calculate a target gray value for each infrared image; A grayscale correction equation group construction module, used for constructing a grayscale correction equation group of the infrared image according to the target grayscale value; A correction coefficient solving module, used for solving the gray value correction equation group by the least square method to obtain the correction coefficient; The image correction module is used to correct the infrared image to be corrected by using the correction coefficient to obtain a target infrared image.

9. An electronic device, It is characterized in that The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The processor is used to execute the computer program stored in the memory; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the infrared image non-uniformity correction method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, It is characterized in that When the computer program is executed by a processor, the infrared image non-uniformity correction method described in any one of claims 1 to 7 is implemented.

Images