A method and system for infrared imaging simulation dynamic enhancement

By calculating the smoothing factor and fusion coefficient, the layering processing and fusion of infrared images are adaptively performed, which solves the problem of lack of adaptability and feature considerations in the fusion process of traditional infrared image enhancement algorithms, and improves the enhancement effect of infrared images.

CN118710668BActive Publication Date: 2024-11-01NANJING GAOSHANG ELECTROMECHANICAL TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411194510.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-11-01
Estimated Expiration
2044-08-29

AI Technical Summary

Technical Problem

The traditional layered infrared image enhancement algorithm lacks adaptability and considers feature differences when fusing outline information images and texture information images, resulting in unsatisfactory enhancement effects.

Method used

By calculating the smoothing factor of each area, adjusting the bilateral filtering parameters, determining the background fusion coefficient of the contour information image based on the local dispersion and edge weights, combining the detail fusion index of the texture information image, adaptively performing pixel-level fusion, considering different scores layer characteristics and noise conditions.

Benefits of technology

It improves the enhancement effect of infrared images, improves adaptability, improves defects in the fusion process in traditional algorithms, and obtains clearer infrared images.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118710668B_ABST
    Figure CN118710668B_ABST
Patent Text Reader

Abstract

The present application relates to the field of image data processing technology, and specifically to a method and system for dynamic enhancement of infrared imaging simulation, the method comprising: obtaining an infrared grayscale image; constructing a smoothing factor for each area in the infrared grayscale image; obtaining a contour information image and a texture information image; determining a background fusion coefficient for each pixel in the contour information image; determining a detail fusion coefficient for each pixel in the texture information image; and obtaining an infrared imaging simulation image based on the background fusion coefficients of all pixels in the contour information image and the detail fusion coefficients of all pixels in the texture information image. The present application calculates the fusion weight of each pixel through different characteristics of different layered pixels in edge and texture complex areas, thereby improving the enhancement effect of infrared images.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of image data processing, and in particular to an infrared imaging simulation dynamic enhancement method and system. Background Art

[0002] Infrared imaging simulation refers to the use of computer simulation technology to simulate the infrared imaging process, so as to study and analyze the characteristics of infrared images without actual infrared imaging equipment. The resolution of infrared images is usually lower than that of visible light images, which makes the capture of details unclear; because infrared images reflect the thermal radiation intensity of objects, their contrast is usually lower than that of color images, which may make it difficult to distinguish different objects or features during image analysis, so it is necessary to further dynamically enhance the images obtained by infrared imaging simulation to obtain clearer infrared images.

[0003] Infrared image enhancement can be performed by decomposing the infrared image into a contour information image containing low-frequency temperature information and a texture information image containing high-frequency temperature information through the idea of ​​layering. The contour information image and the texture information image are then enhanced respectively, and finally the two enhanced layers are fused to obtain the final enhanced image. The key to fusing the two layers of components is to select a suitable fusion coefficient. Traditional layered infrared image enhancement algorithms usually fuse according to preset empirical values, without considering the characteristics of the two layers of components after being enhanced separately, resulting in unsatisfactory final enhancement effects. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide an infrared imaging simulation dynamic enhancement method and system, and the technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides an infrared imaging simulation dynamic enhancement method, the method comprising the following steps:

[0006] Preferably, the smoothing factor of each region is a result of merging the mean value of the gradient amplitude of all pixels in each region and the discrete degree of the grayscale values ​​of all pixels.

[0007] Preferably, the process of constructing the background fusion coefficient of each pixel in the contour information image is as follows:

[0008] The normalized results of the smoothing factors of all regions in the infrared grayscale image and the infrared grayscale image are used as inputs of the bilateral filtering algorithm to obtain a contour information image;

[0009] Analyze the distribution of gray values ​​of all pixels in the neighborhood of each pixel in the contour information image to obtain the local discreteness of each pixel in the contour information image;

[0010] Analyze the distribution of all pixels in the contour information image to determine the edge weight factor of each pixel in the contour information image;

[0011] The background fusion coefficient of each pixel in the contour information image is determined based on the local discreteness and the edge weight factor. The background fusion coefficient of each pixel in the contour information image is the result of the fusion of the local discreteness and the edge weight factor of each pixel in the contour information image.

[0012] Preferably, the local discreteness of each pixel in the contour information image is the discreteness of the grayscale values ​​of all pixels in the neighborhood of each pixel in the contour information image.

[0013] Preferably, the method for determining the edge weight factor of each pixel in the contour information image is:

[0014] The distance from each pixel in the contour information image to all pixels in its neighborhood is analyzed, and the edge weight factor of each pixel in the contour information image is the reciprocal of the minimum value of the distance.

[0015] Preferably, the method for determining the detail fusion coefficient of each pixel in the texture information image is:

[0016] Obtaining the LBP values ​​of all pixels in the texture information image, analyzing the difference between the LBP value of each pixel in the texture information image and the average distribution of the LBP values ​​of all pixels to determine the fusion index of each pixel in the texture information image;

[0017] Analyze the difference between the third quartile and the first quartile of the LBP value of all pixels in the texture information image, and record it as the fusion difference;

[0018] A detail fusion index of each pixel in the texture information image is determined based on the fusion index and the fusion difference.

[0019] Preferably, the fusion index of each pixel in the texture information image is the difference between the LBP value of each pixel in the texture information image and the first quartile of the LBP values ​​of all pixels.

[0020] Preferably, the detail fusion index of each pixel in the texture information image is the ratio of the fusion index of each pixel in the texture information image to the fusion difference.

[0021] Preferably, the process of acquiring the infrared imaging simulation image is:

[0022] The product of the gray value of each pixel in the contour information image and the corresponding background fusion coefficient is recorded as the first gray value of each pixel in the contour information image;

[0023] The product of the gray value of each pixel in the texture information image and the corresponding detail fusion coefficient is recorded as the second gray value of each pixel in the contour information image;

[0024] The sum of the first grayscale value and the second grayscale value of the pixel points at the same position in the contour information image and the texture information image is used as the grayscale value of each pixel point in the infrared imaging simulation image.

[0025] In a second aspect, an embodiment of the present application further provides an infrared imaging simulation dynamic enhancement system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned methods when executing the computer program.

[0026] The present application has at least the following beneficial effects: the present application segments the infrared image, calculates the smoothing factor according to the grayscale change degree of each area, adjusts the parameters of the bilateral filter according to the smoothing factor, and obtains different filtering effects for different areas; by calculating the smoothing factor, the background fusion weight and the detail fusion weight, the fusion weight can be adaptively changed according to different infrared images, so as to obtain a better fusion effect and improve the adaptability of infrared image enhancement; the present application layers the infrared image through bilateral filtering, enhances the different layers and then fuses them, takes into account the noise in the texture information image, calculates the fusion weight of each pixel through the different characteristics of the pixels of different layers at the edges and complex texture areas, and finally performs pixel-level fusion, thereby improving the defect of the traditional algorithm that directly fuses different layers according to the preset weights and improves the enhancement effect of the infrared image. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 A flowchart of the steps of a method for simulating dynamic enhancement of infrared imaging;

[0029] Figure 2 This is a diagram of the acquisition process of the infrared imaging simulation image;

[0030] Figure 3 Schematic diagram of the dynamic enhancement process of infrared imaging. DETAILED DESCRIPTION

[0031] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the infrared imaging simulation dynamic enhancement method and system proposed in the present application, its specific implementation, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0032] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0033] The specific scheme of an infrared imaging simulation dynamic enhancement method and system provided by the present application is described in detail below with reference to the accompanying drawings.

[0034] See also Figure 1 , which shows a flowchart of a method for dynamic enhancement of infrared imaging simulation provided by an embodiment of the present application, the method comprising the following steps:

[0035] Step S1: Acquire an infrared imaging simulation image and perform preprocessing.

[0036] The infrared image output by the infrared imaging simulation system is obtained, and the image is filtered and denoised to obtain a preprocessed infrared image. Further, the infrared image is gray-scaled to obtain an infrared grayscale image.

[0037] It should be noted that there are many commonly used filtering algorithms. In this embodiment, Gaussian filtering is used to reduce the noise of infrared images. The implementer can also use median filtering, mean filtering and other algorithms for noise reduction according to the specific situation. This embodiment does not impose any special restrictions.

[0038] Gaussian filtering, median filtering and mean filtering are all well-known technologies, and their specific denoising processes are not described in detail.

[0039] Step S2: Obtain a contour information image according to the smoothing factors of all regions in the infrared grayscale image and the infrared grayscale image; and perform an AND operation on the infrared grayscale image and the contour information image to obtain a texture information image.

[0040] The infrared grayscale image enhancement method based on layering decomposes the infrared grayscale image into contour information image and texture information image, then performs different enhancement processing on the contour information image and the texture information image, and finally fuses the contour information image and the texture information image to obtain the enhanced infrared grayscale image. Therefore, the bilateral filtering algorithm is used to layer the image. The specific process is as follows:

[0041] S201: Segment the infrared grayscale image, calculate the smoothing factor according to the statistical characteristics of each area, and adjust the parameters of the bilateral filter to layer the image.

[0042] The image is layered using the bilateral filtering algorithm. The bilateral filtering algorithm uses the weighted average of surrounding pixels to obtain the best estimate of the target pixel. The weight takes into account the Euclidean distance between the target pixel and the surrounding pixels and the grayscale difference between pixels. The bilateral filtering can control the degree of filtering of the image by adjusting the parameters.

[0043] in, It represents the standard deviation of the range Gaussian function in the bilateral filtering algorithm, which is used to control the sensitivity of pixel differences. The smaller its value is, the greater the weight of the pixel that is closer to the target pixel grayscale during filtering, thereby better preserving the edge because the pixel grayscale difference on both sides of the edge is large; on the contrary, The larger the value is, the greater the weight of the pixel with a larger grayscale difference from the target pixel. After filtering, the grayscale value is more average and fewer details are retained.

[0044] Since the pixels in each area of ​​the infrared grayscale image are different, it is necessary to set adaptive parameters to achieve a balance between retaining edges and retaining details, retaining edge information in the contour information image, and filtering details and noise into the texture information image to achieve a better layering effect and make the calculation of subsequent fusion parameters more accurate.

[0045] Therefore, by analyzing the change of the gray value of all pixels in each area and the degree of discreteness, the smoothing factor of each area is constructed to achieve the stratification of the infrared grayscale image, specifically:

[0046] (1) Segment the infrared grayscale image.

[0047] Since different areas in the infrared grayscale image have different grayscale ranges, for example, the grayscale range of the sky is very small, so a smaller The grayscale of the grass changes dramatically, contains more detailed textures, and requires a larger Filter details into texture information images.

[0048] Therefore, segmenting the infrared grayscale image can set adaptive parameters in different areas to achieve better stratification effect.

[0049] It should be noted that there are many commonly used image segmentation algorithms. In this embodiment, a superpixel segmentation algorithm is used to segment the infrared grayscale image. The implementer may also use a watershed segmentation algorithm, a graph-based algorithm, or other segmentation algorithms. This embodiment does not impose any special restrictions.

[0050] Among them, the superpixel segmentation algorithm, the watershed segmentation algorithm, and the Graph-based algorithm are all well-known technologies, and the specific process of segmenting the image will not be repeated here.

[0051] (2) Different parameters are assigned to the filtering algorithm according to the differences between different regions in the infrared grayscale image.

[0052] The smoothing factor of each region in the infrared grayscale image is determined based on the change and discrete degree of the grayscale values ​​of all pixels in each region of the infrared grayscale image. The smoothing factor of each region is the result of the fusion of the mean of the gradient amplitude of all pixels in each region and the discrete degree of the grayscale values ​​of all pixels.

[0053] It should be noted that there are many methods for obtaining gradients. In this embodiment, the Sobel operator is used to obtain the gradient of each region. The implementer may also use the Prewitt operator, Scharr operator, Laplacian operator, etc. to calculate the gradient of each region. This embodiment does not impose any special restrictions.

[0054] It should be noted that there are many methods for measuring the degree of discreteness. In this embodiment, the degree of discreteness is measured by analyzing the variance of all grayscale values ​​in each region. The implementer may also use methods such as standard deviation and mean difference to measure the degree of discreteness, and this embodiment does not impose any special restrictions.

[0055] It should be understood that fusion refers to combining two or more indicators by adding or multiplying them together in order to obtain a comprehensive indicator, thereby more comprehensively and accurately evaluating a phenomenon or problem. This fusion method is not limited to simple arithmetic operations, but can also include more complex statistical models and analysis methods. The implementer can choose according to the specific situation, and this embodiment does not impose any special restrictions.

[0056] Preferably, as an embodiment of the present application, the smoothing factor of each region in the infrared grayscale image is the product of the mean of the gradient amplitudes of all pixels in each region and the degree of discreteness of the grayscale values ​​of all pixels.

[0057] Preferably, as another embodiment of the present application, the smoothing factor of each area in the infrared grayscale image is an exponential function value with a natural constant as the base, and the result of adding the mean of the gradient amplitude of all pixels in each area and the discrete degree of the grayscale values ​​of all pixels as the independent variable.

[0058] Further, the value of the parameter is adjusted according to the smoothing factor, and the normalized result of the smoothing factor is used as the parameter of the bilateral filtering algorithm. The infrared grayscale image is filtered to obtain the contour information image.

[0059] The larger the value of the smoothing factor is, the more obvious the grayscale changes in the area are and the richer the details are. The value of will enhance the filtering effect and filter the details into the texture information image; on the contrary, it will reduce Better preserve edge information.

[0060] S202: Perform an AND operation on the infrared grayscale image and the contour information image to obtain a texture information image.

[0061] The texture information image contains the detail information and complex texture of the original image. Therefore, the infrared grayscale image needs to be layered to obtain the texture information image, so as to better analyze the detail features in the infrared grayscale image and enhance the detail features. The process of obtaining the texture information image is as follows:

[0062] The contour information image is binarized to generate a contour mask. As an embodiment of the present application, in this embodiment, the grayscale values ​​greater than or equal to the mean of all grayscale values ​​in the contour information image are set to 1, and the other grayscale values ​​are set to 0.

[0063] It should be noted that there are many methods for binarizing an image, and the implementer may also use a global threshold algorithm, a local threshold algorithm, etc. to binarize the image according to specific circumstances, and this embodiment does not impose any special restrictions.

[0064] The contour mask and the infrared grayscale image are ANDed to obtain the texture information image.

[0065] At this point, the contour information image and the texture information image are obtained.

[0066] Step S3: Analyze the distribution of grayscale values ​​of all pixels in the neighborhood of each pixel in the contour information image, and the distance from each pixel to all pixels in its neighborhood to determine the background fusion coefficient of each pixel in the contour information image.

[0067] Since the traditional layered infrared grayscale image usually uses a preset fusion weight in the process of fusing the contour information image and the texture information image, the features of the enhanced contour information image and the texture information image are not taken into account, resulting in an unsatisfactory fusion effect. Therefore, based on step S2, the contour information image is obtained, and in order to achieve an ideal fusion effect, the contour information image is analyzed, specifically:

[0068] First, since the contour information image contains edge information and scene information, and usually has a low contrast, the contrast enhancement is mainly performed on the contour information image.

[0069] It should be noted that there are many commonly used image enhancement methods. In this embodiment, histogram equalization is used to enhance the contour information image. The implementer may also use other image enhancement methods, and this embodiment does not impose any special restrictions.

[0070] Secondly, an edge detection algorithm is used to extract the image edges in the enhanced contour information image, and morphological operations are performed on the image edges to make the edges smooth and connected.

[0071] Among them, there are many commonly used edge detection algorithms and morphological algorithms. In this embodiment, the Canny edge detection algorithm is used to extract the edges in the contour information image, and the expansion algorithm is used to connect the edges. The implementer can also use other edge detection algorithms and morphological algorithms in the prior art, and this embodiment does not make any special restrictions.

[0072] The contour information image mainly provides edge information in the final fusion. Therefore, the edges in the contour information image are obtained through edge detection. The weight of each pixel is calculated to indicate whether the pixel represents details or edges in the final fusion. If the pixel is near the edge and the pixel difference in the neighborhood of the pixel is greater, a larger weight is assigned, so that the contour information image obtains a larger weight near the edge and better retains the edge information.

[0073] Therefore, the background fusion coefficient of each pixel in the contour information image is determined based on the difference between the grayscale values ​​of each pixel in the contour information image and all the pixels in its neighborhood, and the distance between each pixel and all the pixels in its neighborhood, so as to retain the edge information, specifically:

[0074] First, W neighborhoods are divided with each pixel in the contour information image as the center. The local discreteness of each pixel in the contour information image is the discreteness of the grayscale values ​​of all pixels in the neighborhood of each pixel in the contour information image.

[0075] It should be noted that there are many methods to measure the degree of discreteness. In this embodiment, the degree of discreteness is measured by calculating the variance of the grayscale values ​​of all pixels in the neighborhood of each pixel. Implementers can also use methods such as standard deviation, mean deviation and interquartile range to measure the degree of discreteness. This embodiment does not impose any special restrictions.

[0076] The calculation processes of variance, standard deviation, mean deviation and interquartile range are all well-known techniques and will not be described in detail.

[0077] Secondly, the distance between each pixel point in the contour information image and all the pixels in its neighborhood is analyzed, and the edge weight factor of each pixel point in the contour information image is the reciprocal of the minimum distance value.

[0078] The background fusion coefficient of each pixel in the contour information image is determined based on the local discreteness and the edge weight factor. The background fusion coefficient of each pixel in the contour information image is the result of the fusion of the local discreteness and the edge weight factor of each pixel in the contour information image.

[0079] It should be understood that fusion refers to combining two or more indicators by adding or multiplying them together in order to obtain a comprehensive indicator, thereby more comprehensively and accurately evaluating a phenomenon or problem. This fusion method is not limited to simple arithmetic operations, but can also include more complex statistical models and analysis methods. The implementer can choose according to the specific situation, and this embodiment does not impose any special restrictions.

[0080] Preferably, as an embodiment of the present application, the background fusion coefficient of each pixel in the contour information image is the product of the local discreteness of each pixel in the contour information image and the edge weight factor.

[0081] Preferably, as another embodiment of the present application, the background fusion coefficient of each pixel in the contour information image is an exponential function value with a natural constant as the base and the sum of the local discreteness of each pixel in the contour information image and the edge weight factor as the independent variable.

[0082] The background fusion coefficient measures the importance of pixels near the edge from two aspects. The pixel that is closer to the edge and has a more dramatic grayscale change is given a larger weight, indicating that the pixel is more likely to be near the edge and contributes more to the grayscale value estimation of the edge pixel. Therefore, the weight it occupies in the final fusion should be larger. Conversely, the pixel that is farther from the edge and has a smoother grayscale change is given a smaller weight, indicating that the pixel is farther away from the edge, so the weight it occupies in the final fusion should be smaller.

[0083] Step S4: Analyze the difference between the LBP value of each pixel in the texture information image and the average distribution of the LBP values ​​of all pixels in the contour information image, as well as the discrete degree of the LBP values ​​of all pixels to determine the detail fusion coefficient of each pixel in the texture information image.

[0084] In order to better realize the fusion of contour information image and texture information image, in addition to the background fusion coefficient of each pixel obtained by analyzing the contour information image, the texture information image also contains a lot of detail information. Therefore, in order to better retain the detail information in the texture image, the difference between the gray value of each pixel in the texture information image and the average distribution of the gray values ​​of all pixels is analyzed, combined with the discrete degree of the gray values ​​of all pixels in the texture information image, to determine the detail fusion coefficient of each pixel in the texture information image, thereby realizing the enhancement of the detail information in the texture information image, specifically:

[0085] First of all, since the texture information image contains not only the details and complex textures of the infrared grayscale image, but also high-frequency noise, the texture information image needs to be denoised first.

[0086] It should be noted that there are many commonly used filtering algorithms. In this embodiment, Gaussian filtering is used to remove noise in the texture information image. The implementer may also use filtering methods such as Wiener filtering, median filtering or mean filtering according to the specific situation. This embodiment does not impose any special restrictions.

[0087] Secondly, since the denoised texture information image mainly contains detail information, the texture information image is enhanced.

[0088] There are many commonly used image enhancement algorithms. In this embodiment, gamma transform is used to enhance the texture information image. The implementer may also use logarithmic transform or nonlinear S-curve transform to enhance the image according to the specific situation. This embodiment does not impose any special restrictions.

[0089] Furthermore, the LBP values ​​of all pixels in the texture information image are obtained, the difference between the gray value of each pixel in the texture information image and the average distribution of the gray values ​​of all pixels is analyzed, and the detail fusion coefficient of each pixel in the texture information image is determined in combination with the discrete degree of the gray values ​​of all pixels in the texture information image, which is specifically:

[0090] Analyze the difference between the LBP value of each pixel in the texture information image and the first quartile of the LBP values ​​of all pixels, and record it as the fusion index of each pixel in the texture information image;

[0091] Analyze the difference between the third quartile and the first quartile of the LBP values ​​of all pixels in the texture information image, and record it as the fusion difference of each pixel in the texture information image;

[0092] The detail fusion index of each pixel in the texture information image is the ratio of the fusion index of each pixel in the texture information image to the fusion difference.

[0093] It should be noted that there are many methods for measuring differences. This embodiment adopts the method of taking the absolute value of the difference to measure the difference between the LBP value of each pixel and the first quartile of the LBP values ​​of all pixels, and the difference between the third quartile and the first quartile of the LBP value. The implementer may also adopt other methods for measuring the difference, which is not particularly limited in this embodiment. Among them, the process of obtaining the LBP value is a well-known technology, and the specific process will not be repeated, and the obtained LBP value is a decimal number.

[0094] The larger the value of the detail fusion coefficient, the richer the texture features in the neighborhood of the pixel, and the more details should be retained, so it should have a larger weight in the final fusion; conversely, the smaller the value of the detail fusion coefficient, the smaller the weight given to the pixel in the final fusion.

[0095] Step S5: obtaining an infrared imaging simulation image based on the background fusion coefficients of all pixels in the contour information image of the infrared grayscale image and the detail fusion coefficients of all pixels in the texture information image.

[0096] The product of the gray value of each pixel in the contour information image and the corresponding background fusion coefficient is recorded as the first gray value of each pixel in the contour information image;

[0097] The product of the gray value of each pixel in the texture information image and the corresponding detail fusion coefficient is recorded as the second gray value of each pixel in the texture information image;

[0098] The sum of the first grayscale value and the second grayscale value of the pixel points at the same position in the contour information image and the texture information image is used as the grayscale value of each pixel point in the infrared imaging simulation image.

[0099] At this point, the enhanced infrared imaging simulation image is obtained.

[0100] Preferably, as an embodiment of the present application, the acquisition process of the infrared imaging simulation image is shown in FIG. Figure 2 shown.

[0101] Preferably, as an embodiment of the present application, the schematic diagram of the infrared imaging dynamic enhancement process is as follows: Figure 3 Based on the same inventive concept as the above method, the embodiment of the present application also provides an infrared imaging simulation dynamic enhancement system, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above infrared imaging simulation dynamic enhancement methods are implemented.

[0102] It should be noted that the above sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above is a description of a specific embodiment of this specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0103] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0104] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for dynamic enhancement of infrared imaging simulation, characterized in that: The method comprises the following steps: Obtain an infrared grayscale image and divide it into multiple regions; According to the change of the gray value of all pixels in each area of ​​the infrared grayscale image and the degree of dispersion, a smoothing factor of each area is constructed; according to the smoothing factors of all areas in the infrared grayscale image and the infrared grayscale image, a contour information image is obtained; and the image obtained by performing an AND operation on the infrared grayscale image and the binarized contour information image is recorded as a texture information image; Analyze the distribution of gray values ​​of all pixels in the neighborhood of each pixel in the contour information image and the distribution of all pixels in the contour information image to determine the background fusion coefficient of each pixel in the contour information image; Analyze the difference between the gray value of each pixel in the texture information image and the average distribution of the gray values ​​of all pixels, and combine the discrete degree of the gray values ​​of all pixels in the texture information image to determine the detail fusion coefficient of each pixel in the texture information image; Based on the background fusion coefficient of all pixels in the contour information image and the detail fusion coefficient of all pixels in the texture information image, an infrared imaging simulation image is obtained; The smoothing factor of each region is a result of the fusion of the mean value of the gradient amplitude of all the pixels in each region and the discrete degree of the grayscale values ​​of all the pixels.

2. The infrared imaging simulation dynamic enhancement method according to claim 1, characterized in that: The process of constructing the background fusion coefficient of each pixel in the contour information image is as follows: The normalized results of the smoothing factors of all regions in the infrared grayscale image and the infrared grayscale image are used as inputs of the bilateral filtering algorithm to obtain a contour information image; Analyze the distribution of gray values ​​of all pixels in the neighborhood of each pixel in the contour information image to obtain the local discreteness of each pixel in the contour information image; Analyze the distribution of all pixels in the contour information image to determine the edge weight factor of each pixel in the contour information image; The background fusion coefficient of each pixel in the contour information image is determined based on the local discreteness and the edge weight factor. The background fusion coefficient of each pixel in the contour information image is the result of the fusion of the local discreteness and the edge weight factor of each pixel in the contour information image.

3. The infrared imaging simulation dynamic enhancement method according to claim 2, characterized in that: The local discreteness of each pixel in the contour information image is the discreteness of the grayscale values ​​of all pixels in the neighborhood of each pixel in the contour information image.

4. The infrared imaging simulation dynamic enhancement method according to claim 2, characterized in that: The method for determining the edge weight factor of each pixel in the contour information image is: The distance from each pixel in the contour information image to all pixels in its neighborhood is analyzed, and the edge weight factor of each pixel in the contour information image is the reciprocal of the minimum value of the distance.

5. The infrared imaging simulation dynamic enhancement method according to claim 1, characterized in that: The method for determining the detail fusion coefficient of each pixel in the texture information image is as follows: Obtaining the LBP values ​​of all pixels in the texture information image, analyzing the difference between the LBP value of each pixel in the texture information image and the average distribution of the LBP values ​​of all pixels to determine the fusion index of each pixel in the texture information image; Analyze the difference between the third quartile and the first quartile of the LBP value of all pixels in the texture information image, and record it as the fusion difference; A detail fusion index of each pixel in the texture information image is determined based on the fusion index and the fusion difference.

6. The infrared imaging simulation dynamic enhancement method according to claim 5, characterized in that: The fusion index of each pixel in the texture information image is the difference between the LBP value of each pixel in the texture information image and the first quartile of the LBP values ​​of all pixels.

7. The infrared imaging simulation dynamic enhancement method according to claim 5, characterized in that: The detail fusion index of each pixel in the texture information image is the ratio of the fusion index of each pixel in the texture information image to the fusion difference.

8. The infrared imaging simulation dynamic enhancement method according to claim 1, characterized in that: The acquisition process of the infrared imaging simulation image is as follows: The product of the gray value of each pixel in the contour information image and the corresponding background fusion coefficient is recorded as the first gray value of each pixel in the contour information image; The product of the gray value of each pixel in the texture information image and the corresponding detail fusion coefficient is recorded as the second gray value of each pixel in the contour information image; The sum of the first grayscale value and the second grayscale value of the pixel points at the same position in the contour information image and the texture information image is used as the grayscale value of each pixel point in the infrared imaging simulation image.

9. An infrared imaging simulation dynamic enhancement system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.