A method for improving the accuracy of infrared simulation images in infrared imaging simulation system

Abstract

The present invention relates to the technical field of data image processing, and in particular to a method for improving the accuracy of infrared simulation images in an infrared imaging simulation system, the method comprising: obtaining an infrared image to be corrected and a previous frame of historical infrared image corresponding to a target bullet during flight, determining a grayscale change factor and a possible bullet index corresponding to each pixel point in the infrared image to be corrected; screening out target bullet points, dividing a target bullet area formed by all target bullet points, and screening out target bullet points representing the apex of the bullet head; determining a temperature influence factor corresponding to each target bullet point; correcting the infrared image to be corrected according to the temperature influence factor corresponding to the target bullet point; and performing infrared simulation processing on the target image to obtain an infrared simulation image. The present invention generates an infrared simulation image by processing the infrared image to be corrected and a previous frame of historical infrared image, and improves the accuracy of generating the infrared simulation image.

Description

Technical Field

[0001] The present invention relates to the technical field of data image processing, and in particular to a method for improving the accuracy of infrared simulation images in an infrared imaging simulation system. Background Art

[0002] Infrared imaging technology is a technology that converts infrared radiation from the environment and the target into recognizable infrared images. This technology can obtain important information about the target and the background, and has significant advantages in detecting and tracking targets. The infrared imaging simulation system can predict the performance of the infrared imaging system in the early stages of design by simulating infrared images under different conditions. The accuracy of the simulated image is often directly related to the reliability of the prediction result, which in turn affects the overall design and optimization of the system.

[0003] In the process of testing with infrared imaging simulation system, it is necessary to use infrared simulation images for specific analysis and judgment to provide comprehensive data support for testing and verification. In this case, the accuracy of infrared simulation images is particularly important. At present, the method of obtaining infrared simulation images of objects is usually: collecting infrared images of objects to capture the thermal radiation of the target, and generating infrared simulation images of objects based on the infrared images.

[0004] However, when generating infrared simulation images of bullets based on infrared images of bullets collected during the flight of bullets, the following technical problems often occur:

[0005] The speed of a bullet is relatively fast during flight, and the degree of friction between different parts and the air is often different, resulting in different temperatures in different parts of the bullet. In addition, the temperature of the air behind the bullet often rises during flight, and infrared simulation images are often generated based on the infrared radiation of the bullet, which is related to temperature. Therefore, it is often difficult to clearly display the shape of the bullet in the collected infrared image of the bullet. For example, the trailing area caused by the increase in the temperature of the air behind the bullet may be misjudged as the area in the real bullet, resulting in the infrared simulation image generated by the bullet during flight being difficult to display the real visual situation, which in turn leads to the poor accuracy of the generated infrared simulation image of the bullet. Summary of the invention

[0006] In order to solve the technical problem that the accuracy of the infrared simulation image of the generated bullet is poor, the present invention proposes a method for improving the accuracy of the infrared simulation image in the infrared imaging simulation system.

[0007] In a first aspect, the present invention provides a method for improving the accuracy of infrared simulation images in an infrared imaging simulation system, the method comprising:

[0008] Acquire the infrared image to be corrected and the previous frame of historical infrared image corresponding to the target bullet in the flight process, and determine the grayscale change factor corresponding to each pixel point in the infrared image to be corrected based on the infrared image to be corrected and the previous frame of historical infrared image;

[0009] Determine the possible bullet index corresponding to each pixel in the infrared image to be corrected according to the difference between the grayscale change factor corresponding to each pixel in the infrared image to be corrected and the pixel in the preset direction, and the grayscale distribution in the preset window corresponding to each pixel in the infrared image to be corrected;

[0010] According to the possible indicators of the bullet, the target bullet points are screened out from the infrared image to be corrected, the target bullet area formed by all the target bullet points is divided to obtain a reference area representing the bullet head or the bullet body, and the target bullet point representing the bullet head vertex is screened out from all the target bullet points as the target vertex;

[0011] Determine the temperature influence factor corresponding to each target bullet point according to the target vertex, the gray value corresponding to each target bullet point, the area-to-volume ratio of the actual bullet part represented by the reference area to which it belongs, and the flight speed of the target bullet;

[0012] According to the temperature influence factor corresponding to the target bullet point in the infrared image to be corrected, the infrared image to be corrected is corrected to obtain the target image;

[0013] Perform infrared simulation processing on the target image to obtain an infrared simulation image.

[0014] In combination with the first aspect above, in a possible implementation, determining the grayscale change factor corresponding to each pixel in the infrared image to be corrected based on the infrared image to be corrected and its previous frame of historical infrared image includes:

[0015] Determine any pixel point in the infrared image to be corrected as a marked pixel point, and select a pixel point with the same position as the marked pixel point from a previous frame of historical infrared image of the infrared image to be corrected as a reference pixel point;

[0016] The difference between the grayscale value corresponding to the marked pixel and the grayscale value corresponding to the reference pixel is determined as the grayscale change factor corresponding to the marked pixel.

[0017] In combination with the first aspect above, in a possible implementation, determining the possible bullet index corresponding to each pixel in the infrared image to be corrected according to the difference between the grayscale change factor corresponding to each pixel in the infrared image to be corrected and the pixel in a preset direction, and the grayscale distribution in a preset window corresponding to each pixel in the infrared image to be corrected, includes:

[0018] Determine the grayscale fluctuation performance factor of each pixel in the infrared image to be corrected in each preset direction according to the difference between the grayscale variation factors corresponding to each pixel in the infrared image to be corrected and a preset number of pixels in each preset direction;

[0019] According to the grayscale fluctuation performance factor of each pixel in the infrared image to be corrected in all preset directions and the grayscale distribution in a preset window corresponding to each pixel in the infrared image to be corrected, the possible bullet index corresponding to each pixel in the infrared image to be corrected is determined.

[0020] In combination with the first aspect, in a possible implementation, determining the grayscale fluctuation performance factor of each pixel in the infrared image to be corrected in each preset direction according to the difference between the grayscale variation factors corresponding to each pixel in the infrared image to be corrected and a preset number of pixels in each preset direction thereof includes:

[0021] Determine any pixel point in the infrared image to be corrected as a marked pixel point, and determine any preset direction as a marked direction;

[0022] A target straight line is drawn through the marked pixel point and in the marked direction, taking the marked direction as the straight line direction;

[0023] Selecting a preset number of pixels closest to the marked pixel point on the target straight line as candidate pixels, and obtaining a set of candidate pixels of the marked pixel point in the marked direction;

[0024] The absolute value of the difference between the grayscale change factors corresponding to every two candidate pixel points in the candidate pixel point set is determined as the target difference, and the target difference set of the marked pixel point in the marked direction is obtained;

[0025] The mean value of all target differences in the target difference set is determined as the grayscale fluctuation representation factor of the marked pixel point in the marked direction.

[0026] In combination with the first aspect above, in a possible implementation, determining the possible bullet index corresponding to each pixel in the infrared image to be corrected according to the grayscale fluctuation performance factor of each pixel in the infrared image to be corrected in all preset directions and the grayscale distribution in a preset window corresponding to each pixel in the infrared image to be corrected includes:

[0027] Determine the target fluctuation index corresponding to each pixel point in the infrared image to be corrected according to the grayscale fluctuation performance factor of each pixel point in the infrared image to be corrected in all preset directions, wherein the grayscale fluctuation performance factor is positively correlated with the target fluctuation index;

[0028] Acquire a preset number of frames of historical infrared images before the infrared image to be corrected, and determine the target fluctuation index corresponding to each pixel point in each frame of the historical infrared image;

[0029] Determine the overall change degree factor corresponding to each pixel point in the infrared image to be corrected according to the target fluctuation index corresponding to the pixel point in the infrared image to be corrected and the target fluctuation index corresponding to the pixel point in the historical infrared image of a preset number of frames before the infrared image to be corrected;

[0030] Determine the variance of the grayscale values ​​corresponding to all the pixels in the preset window corresponding to each pixel in the infrared image to be corrected as the grayscale distribution factor corresponding to each pixel in the infrared image to be corrected;

[0031] According to the overall change degree factor and the gray distribution factor corresponding to each pixel point in the infrared image to be corrected, the possible bullet index corresponding to each pixel point in the infrared image to be corrected is determined.

[0032] In combination with the first aspect above, in a possible implementation, determining the overall change degree factor corresponding to each pixel in the infrared image to be corrected according to the target fluctuation index corresponding to the pixel in the infrared image to be corrected and the target fluctuation index corresponding to the pixel in the historical infrared image of a preset number of frames before the infrared image to be corrected includes:

[0033] Determine any pixel point in the infrared image to be corrected as a marked pixel point, and select pixels with the same position as the marked pixel point from a preset number of frames of historical infrared images before the infrared image to be corrected as undetermined pixels, and obtain a set of undetermined pixels corresponding to the marked pixel point;

[0034] The target fluctuation index corresponding to the marked pixel point and the average value of the target fluctuation indexes corresponding to all the pending pixel points in the corresponding pending pixel point set are determined as the overall change degree factor corresponding to the marked pixel point.

[0035] In combination with the first aspect above, in a possible implementation, the step of selecting target bullet points from the infrared image to be corrected according to possible bullet indicators includes:

[0036] If the bullet possibility index corresponding to the pixel point is greater than the preset bullet suspicion threshold, the pixel point is determined as a suspected bullet pixel point, wherein the suspected bullet pixel point represents the real position point of the bullet or the position point of the bullet tail;

[0037] According to the gray value corresponding to the suspected bullet pixel and the possible index of the bullet, the formula for determining the real bullet feature value corresponding to the suspected bullet pixel is:

[0038] ;in, It is The real bullet feature value corresponding to the suspected bullet pixel point; is the serial number of the pixel suspected to be a bullet; is the normalization function; It is Gray value corresponding to the pixel point suspected of being a bullet; It is the mean of the gray values ​​corresponding to all suspected bullet pixels; It is The possible bullet indicators corresponding to the suspected bullet pixels; It is the preset bullet suspicion threshold;

[0039] If the real bullet feature value corresponding to the suspected bullet pixel point is greater than the preset real bullet threshold, the suspected bullet pixel point is determined as the target bullet point, wherein the target bullet point represents the real position point of the bullet.

[0040] In combination with the first aspect, in a possible implementation, determining the temperature influence factor corresponding to each target bullet point according to the target vertex, the gray value corresponding to each target bullet point, the area-to-volume ratio of the actual bullet part represented by the reference area to which it belongs, and the flight speed of the target bullet includes:

[0041] Connecting the target vertex and each target bullet point to obtain a target line segment corresponding to each target bullet point;

[0042] The number of pixel points on the target line segment corresponding to each target bullet point is determined as the number of targets corresponding to each target bullet point;

[0043] According to the gray value and target number corresponding to the target bullet point, the area-to-volume ratio of the actual bullet part represented by the reference area to which it belongs, and the flight speed of the target bullet, the formula corresponding to the temperature influence factor corresponding to the target bullet point is determined as follows:

[0044] ;in, It is Temperature influence factor corresponding to each target bullet point; is the serial number of the target bullet point; is the normalization function; It is The gray value corresponding to the target bullet point; is the mean of the grayscale values ​​corresponding to all target bullet points; It is The reference area to which the target bullet point belongs represents the surface area of ​​the actual bullet part; the actual bullet part represents the warhead of the target bullet or the body of the target bullet; It is The volume of the actual bullet site represented by the reference area to which the target bullet point belongs; It is The area-to-volume ratio of the actual bullet site represented by the reference area to which the target bullet point belongs; It is The flight speed of the target bullet at the time of collection corresponding to each target bullet point; It is an exponential function with a natural constant as base; It is The number of targets corresponding to each target bullet point.

[0045] In combination with the first aspect above, in a possible implementation, the step of correcting the infrared image to be corrected according to the temperature influence factor corresponding to the target bullet point in the infrared image to be corrected to obtain the target image includes:

[0046] Determine the pixels other than the suspected bullet pixels in the infrared image to be corrected as environmental pixels, and determine the suspected bullet pixels other than the target bullet pixels among all the suspected bullet pixels as bullet tail pixels;

[0047] The average of the grayscale values ​​corresponding to all the environmental pixels in the preset neighborhood corresponding to all the pixels on the edge of the area formed by all the bullet tail pixels is determined as the environmental representative grayscale index;

[0048] According to the grayscale value and temperature influence factor corresponding to each target bullet point, determine the target grayscale index corresponding to each target bullet point;

[0049] The grayscale values ​​corresponding to all bullet tailing pixels in the infrared image to be corrected are updated to the environmental representative grayscale index, and the grayscale value corresponding to each target bullet point in the infrared image to be corrected is updated to its corresponding target grayscale index, and the updated infrared image to be corrected is determined as the target image.

[0050] In combination with the first aspect above, in a possible implementation, the formula corresponding to the target grayscale index corresponding to the target bullet point is:

[0051] ;in, It is The target gray index corresponding to each target bullet point; is the serial number of the target bullet point; It is The gray value corresponding to the target bullet point is equal to the gray value of the first target bullet point in the infrared image to be corrected before updating. The gray value corresponding to the target bullet point; It is Temperature influence factor corresponding to each target bullet point; It is the mean of the grayscale values ​​corresponding to all target bullet points.

[0052] In a second aspect, the present invention provides a system for improving the accuracy of infrared simulation images in an infrared imaging simulation system, the system comprising:

[0053] An image acquisition factor determination module is used to obtain the infrared image to be corrected and its previous frame of historical infrared image corresponding to the target bullet during flight, and determine the grayscale change factor corresponding to each pixel point in the infrared image to be corrected based on the infrared image to be corrected and its previous frame of historical infrared image;

[0054] The bullet possible index determination module is used to determine the bullet possible index corresponding to each pixel in the infrared image to be corrected according to the difference between the grayscale change factor corresponding to each pixel in the infrared image to be corrected and the pixel in the preset direction, and the grayscale distribution in the preset window corresponding to each pixel in the infrared image to be corrected.

[0055] The screening and division module is used to screen out target bullet points from the infrared image to be corrected according to possible bullet indicators, divide the target bullet area formed by all target bullet points, obtain a reference area representing the bullet head or the bullet body, and screen out the target bullet point representing the bullet head vertex from all target bullet points as the target vertex;

[0056] A temperature influence factor determination module is used to determine the temperature influence factor corresponding to each target bullet point according to the target vertex, the gray value corresponding to each target bullet point, the area-to-volume ratio of the actual bullet part represented by the reference area to which it belongs, and the flight speed of the target bullet;

[0057] An image correction module is used to correct the infrared image to be corrected according to the temperature influence factor corresponding to the target bullet point in the infrared image to be corrected, so as to obtain a target image;

[0058] The image construction module is used to perform infrared simulation processing on the target image to obtain an infrared simulation image.

[0059] In a third aspect, a server is provided, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes the method in the first aspect or any possible implementation of the first aspect.

[0060] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0061] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation manner of the first aspect.

[0062] The present invention has the following beneficial effects:

[0063] The present invention provides a method for improving the accuracy of infrared simulation images in an infrared imaging simulation system. By processing an infrared image to be corrected and a previous frame of historical infrared image, an infrared simulation image is generated, thereby solving the technical problem of poor accuracy of the infrared simulation image of the generated bullet and improving the accuracy of the infrared simulation image generation. Compared with directly generating an infrared simulation image of a bullet based on a collected infrared image of the bullet, the present invention comprehensively considers a plurality of features related to bullet region identification, such as grayscale variation factor, grayscale distribution and possible bullet indexes, so as to screen out target bullet points representing the real bullet position, which can reduce the misjudgment of the real bullet region caused by the bullet tailing to a certain extent, and also considers the different temperature performances of different parts of the bullet during its flight, for example, considering the target vertex, the grayscale value corresponding to the target bullet point, the area-to-volume ratio of the actual bullet part represented by the reference area to which it belongs, and the flight speed of the target bullet, and based on the temperature influence factor corresponding to the target bullet point, correcting the infrared image to be corrected, which can reduce the visual display error caused by the different temperature performances of different parts of the bullet during its flight to a certain extent, thereby improving the authenticity of the infrared simulation image generation of the bullet, retaining the shape characteristics of the bullet to a certain extent, and further improving the accuracy of the infrared simulation image generation of the bullet, for example, the visual display error caused by the different temperature performances of different parts of the bullet during its flight can be a visual display error that the color of the same bullet is often uniform, but the different temperature performances of different parts of the bullet may cause the grayscale of the bullet displayed on the infrared image to be uneven. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0065] Figure 1 A flow chart of a method for improving the accuracy of infrared simulation images in an infrared imaging simulation system of the present invention;

[0066] Figure 2 A schematic diagram of the structure of a system for improving the accuracy of infrared simulation images in an infrared imaging simulation system according to the present invention;

[0067] Figure 3 The figure is a schematic diagram of the structure of a computer device of the present invention. DETAILED DESCRIPTION

[0068] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the technical solutions proposed by the present invention are described in detail below 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.

[0069] 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 invention belongs.

[0070] refer to Figure 1 , shows the process of some embodiments of a method for improving the accuracy of infrared simulation images in an infrared imaging simulation system according to the present invention. The method for improving the accuracy of infrared simulation images in an infrared imaging simulation system comprises the following steps:

[0071] Step S1, obtaining the infrared image to be corrected and its previous frame of historical infrared image corresponding to the target bullet during flight, and determining the grayscale change factor corresponding to each pixel in the infrared image to be corrected based on the infrared image to be corrected and its previous frame of historical infrared image.

[0072] The target bullet may be a bullet to be subjected to infrared imaging simulation. The infrared image to be corrected may be an infrared image to be subjected to bullet imaging correction. The historical infrared image may be an infrared image of the target bullet collected before the infrared image to be corrected.

[0073] As an example, this step may include the following steps:

[0074] The first step is to obtain the infrared image to be corrected corresponding to the target bullet during flight and its previous frame of historical infrared image.

[0075] For example, an infrared thermal imager can be used to collect infrared images of a target bullet at each moment in its flight in real time, and any infrared image frame except the first infrared image frame can be determined as the infrared image to be corrected, and the previous infrared image frame of the infrared image to be corrected is the previous historical infrared image frame of the infrared image to be corrected, wherein the time length between adjacent collection moments can be 0.1 second.

[0076] It should be noted that the infrared thermal imager can be used to track bullets. During the infrared image acquisition process of the bullet, the same part of the bullet can be mapped to the same position in different frames of infrared images in a short time, that is, the regional position representing the bullet in different frames of infrared images can remain unchanged. Since the bullet is flying, the environment around the bullet is often different at different times. Therefore, the grayscale change degree of the region representing the environment in different frames of infrared images is often large, while the grayscale change degree of the region representing the bullet part is often small. The environment for the bullet flight in the embodiment of the present invention can change with different positions. Secondly, the bullet flight process in the embodiment of the present invention can be the process of the bullet flying quickly. For example, after the bullet reaches a certain height, the process of free fall due to the loss of power is not the bullet flight process mentioned in the embodiment of the present invention. The bullet flight process in the embodiment of the present invention is the flight process of the bullet before the free fall.

[0077] In the second step, any pixel point in the above infrared image to be corrected is determined as a marked pixel point, and the pixel point with the same position as the marked pixel point is screened out from the previous frame of historical infrared image of the above infrared image to be corrected as a reference pixel point.

[0078] For example, if the marked pixel is a pixel located at the center of the infrared image to be corrected, the reference pixel may be a pixel located at the center of a previous historical infrared image of the infrared image to be corrected.

[0079] In the third step, the difference between the grayscale value corresponding to the marked pixel point and the grayscale value corresponding to the reference pixel point is determined as the grayscale change factor corresponding to the marked pixel point.

[0080] For example, the formula for determining the grayscale change factor corresponding to the pixel point in the infrared image to be corrected can be:

[0081] ;in, is the first The grayscale change factor corresponding to each pixel. is the first The gray value corresponding to each pixel. is the previous frame of the infrared image to be corrected and the first frame of the infrared image to be corrected The gray value corresponding to the pixel with the same pixel position; that is, the gray value of the pixel in the previous frame of the historical infrared image to be corrected The gray value corresponding to each pixel. It is the serial number of the pixel in the infrared image, that is, the serial number of the pixel in the infrared image to be corrected or its previous frame of historical infrared image.

[0082] It should be noted that when The smaller the value, the more likely it is that the infrared image to be corrected The pixel point and the previous frame of historical infrared image The smaller the grayscale difference between pixels, the smaller the grayscale difference between pixels. The pixel point and the previous frame of historical infrared image The more pixels represent the smaller the temperature change of the object.

[0083] Step S2, determining the possible bullet index corresponding to each pixel in the infrared image to be corrected based on the difference between the grayscale change factor corresponding to each pixel in the infrared image to be corrected and the pixel in the preset direction, and the grayscale distribution in the preset window corresponding to each pixel in the infrared image to be corrected.

[0084] The preset direction may be a preset direction for grayscale change analysis. The number of preset directions may be a preset number. For example, if there are two preset directions, the two preset directions may be a horizontal direction and a vertical direction, respectively. The preset window may be a preset rectangular window. The pixel point may be located at the center of its corresponding preset window. For example, the preset window may be a 5×5 window.

[0085] As an example, this step may include the following steps:

[0086] The first step is to determine the grayscale fluctuation performance factor of each pixel in the infrared image to be corrected in each preset direction according to the difference between the grayscale change factors corresponding to each pixel in the infrared image to be corrected and a preset number of pixels in each preset direction.

[0087] The preset number may be a preset number for selecting pixel points. For example, the preset number may be 11.

[0088] For example, determining the grayscale fluctuation performance factor of each pixel in each preset direction may include the following sub-steps:

[0089] In the first sub-step, any pixel point in the infrared image to be corrected is determined as a marked pixel point, and any preset direction is determined as a marked direction.

[0090] In the second sub-step, a target straight line is drawn through the marked pixel point and along the marked direction as the straight line direction.

[0091] In the third sub-step, a preset number of pixels closest to the marked pixel point are selected from the target straight line as candidate pixels, and a candidate pixel set of the marked pixel point in the marked direction is obtained.

[0092] The candidate pixel point set of the marked pixel point in the marked direction may include: a preset number of pixels closest to the marked pixel point on the target straight line of the marked pixel point in the marked direction, and the candidate pixel point set may include the marked pixel point.

[0093] For example, if the preset number is 11 and the marking direction is horizontal, the candidate pixel point set for the marked pixel point in the marking direction may include: the marked pixel point, the 5 pixel points closest to the marked pixel point on the left side of the marked pixel point, and the 5 pixel points closest to the marked pixel point on the right side of the marked pixel point.

[0094] In the fourth sub-step, the absolute value of the difference between the grayscale change factors corresponding to every two candidate pixel points in the candidate pixel point set is determined as the target difference, and the target difference set of the marked pixel points in the marked direction is obtained.

[0095] In a fifth sub-step, the mean value of all target differences in the target difference set is determined as the grayscale fluctuation expression factor of the marked pixel point in the marked direction.

[0096] For example, the formula corresponding to the grayscale fluctuation performance factor of the pixel point in the infrared image to be corrected in the preset direction can be:

[0097] ;in, is the first The pixel at Grayscale fluctuation performance factor under a preset direction. It is the serial number of the pixel in the infrared image to be corrected. is the sequence number of the preset direction. is the preset quantity. and is the first The pixel at The sequence numbers of different candidate pixels in a set of candidate pixels under a preset direction. It is the absolute value function. is the first The pixel at In the set of candidate pixels under the preset direction, the The grayscale change factor corresponding to the candidate pixel. is the first The pixel at In the set of candidate pixels under the preset direction, the The grayscale change factor corresponding to the candidate pixel. Characterize target differences.

[0098] It should be noted that the area representing the bullet in different frames of infrared images often remains unchanged. Since the bullet is flying, the environment around the bullet is often different at different times, which often means that the grayscale values ​​of the environment around the bullet mapped to the infrared image at different times are often different. Therefore, the grayscale value changes of the bullet mapped to the infrared image at different times are often similar, while the grayscale value changes of the environment around the bullet mapped to the infrared image at different times are often chaotic. The smaller the value, the more likely it is that the infrared image to be corrected The pixel at The closer the gray value changes between the pixels around the preset direction are, the closer the gray value changes are. The more pixels there are, the more likely it is that the bullet is at the location or the bullet tail is at the location. When the value is larger, it often indicates that the first The pixel at The more chaotic the grayscale value changes between the pixels around the preset direction are, the more likely it is that the first The more likely the pixel is an environmental pixel. The smaller the value, the more likely it is that the infrared image to be corrected The pixel at The closer the gray value changes between the pixels around the preset direction are, the closer the gray value changes are. The more pixels there are, the more likely it is that it is a bullet position point or a bullet tail position point.

[0099] The second step is to determine the possible bullet index corresponding to each pixel in the above-mentioned infrared image to be corrected based on the grayscale fluctuation performance factor of each pixel in the above-mentioned infrared image to be corrected in all preset directions and the grayscale distribution in the preset window corresponding to each pixel in the above-mentioned infrared image to be corrected.

[0100] For example, determining the possible bullet index corresponding to each pixel may include the following sub-steps:

[0101] In the first sub-step, according to the grayscale fluctuation performance factor of each pixel in the infrared image to be corrected in all preset directions, a target fluctuation index corresponding to each pixel in the infrared image to be corrected is determined.

[0102] Among them, the grayscale volatility performance factor can be positively correlated with the target volatility index.

[0103] For example, the cumulative multiplication value of the grayscale fluctuation performance factors of the pixel point in all preset directions can be determined as the target fluctuation index corresponding to the pixel point.

[0104] The second sub-step is to obtain a preset number of frames of historical infrared images before the infrared image to be corrected, and determine the target fluctuation index corresponding to each pixel point in each frame of the historical infrared image.

[0105] The preset number may be a preset number, for example, 5.

[0106] It should be noted that the method for acquiring a preset number of frames of historical infrared images before the infrared image to be corrected can be the same as the method for acquiring the historical infrared image before the infrared image to be corrected, and the method for determining the target fluctuation index corresponding to the pixel points in the historical infrared image can be the same as the method for determining the target fluctuation index corresponding to the pixel points in the infrared image to be corrected, which will not be repeated here.

[0107] The third sub-step, according to the target fluctuation index corresponding to the pixel point in the above-mentioned infrared image to be corrected and the target fluctuation index corresponding to the pixel point in the historical infrared image of a preset number of frames before the above-mentioned infrared image to be corrected, determines the overall change degree factor corresponding to each pixel point in the above-mentioned infrared image to be corrected, which may include the following steps:

[0108] First, any pixel point in the above-mentioned infrared image to be corrected is determined as a marked pixel point, and the pixel points with the same position as the marked pixel point are screened out from a preset number of frames of historical infrared images before the above-mentioned infrared image to be corrected as the pending pixel points, and a set of pending pixel points corresponding to the above-mentioned marked pixel points is obtained.

[0109] For example, if the marked pixel point is a pixel point located at the center of the infrared image to be corrected, the undetermined pixel point set corresponding to the marked pixel point may include: pixel points located at the center of a preset number of frames of historical infrared images before the infrared image to be corrected.

[0110] Next, the target fluctuation index corresponding to the marked pixel point and the average value of the target fluctuation index corresponding to all the pending pixel points in the corresponding pending pixel point set are determined as the overall change degree factor corresponding to the marked pixel point.

[0111] For example, if the set of pending pixel points corresponding to the marked pixel point includes: a first pending pixel point and a second pending pixel point, the average of the target fluctuation index corresponding to the marked pixel point, the target fluctuation index corresponding to the first pending pixel point, and the target fluctuation index corresponding to the second pending pixel point can be determined as the overall change degree factor corresponding to the marked pixel point.

[0112] It should be noted that when the target fluctuation index corresponding to the pixel point is smaller, it often means that the gray value changes between the pixels around the preset direction of the pixel point are closer, which often means that the pixel point is more likely to be a bullet position point or a bullet tail position point. Therefore, when the overall change degree factor corresponding to the marked pixel point is smaller, it often means that the marked pixel point is more likely to be a bullet position point or a bullet tail position point.

[0113] In the fourth sub-step, the variance of the grayscale values ​​corresponding to all the pixels in the preset window corresponding to each pixel in the infrared image to be corrected is determined as the grayscale distribution factor corresponding to each pixel in the infrared image to be corrected.

[0114] The fifth sub-step is to determine the possible bullet index corresponding to each pixel in the infrared image to be corrected according to the overall change degree factor and gray distribution factor corresponding to each pixel in the infrared image to be corrected.

[0115] For example, the formula for determining the possible bullet index corresponding to the pixel point in the infrared image to be corrected can be:

[0116] ;in, is the first The bullet may be the index corresponding to each pixel. It is the serial number of the pixel in the infrared image to be corrected. It is an exponential function with a natural constant as its base. is the first The overall change factor corresponding to each pixel. is the first The grayscale distribution factor corresponding to a pixel point and the variance of the grayscale distribution factors corresponding to all the pending pixel points in the corresponding pending pixel point set. The grayscale distribution factor corresponding to the pending pixel point can be obtained in the same way as the grayscale distribution factor corresponding to the pixel point in the infrared image to be corrected.

[0117] It should be noted that when The smaller the value, the more likely it is that the infrared image to be corrected The more pixels there are, the more likely they are the bullet position or the bullet tail position. In reality, during the bullet's flight, the bullet's surroundings often change with time. Therefore, the grayscale distribution of the environment in different infrared images often differs, while the grayscale distribution of the bullet in different infrared images is often similar. The smaller the value, the smaller the value. The closer the grayscale distribution around the pixel is, the closer it is to the pixel point. The more pixels there are, the more likely they are to represent the bullet position. When the value is larger, it often indicates that the first The more pixels there are, the more likely it is that the bullet is located.

[0118] Step S3, according to the possible indicators of the bullet, the target bullet points are screened out from the infrared image to be corrected, the target bullet area formed by all the target bullet points is divided to obtain a reference area representing the bullet head or the bullet body, and the target bullet point representing the bullet head vertex is screened out from all the target bullet points as the target vertex.

[0119] As an example, this step may include the following steps:

[0120] In the first step, if the bullet possibility index corresponding to the pixel point is greater than the preset bullet suspicion threshold, the pixel point is determined as a suspected bullet pixel point.

[0121] The preset bullet suspected threshold may be a threshold pre-set for screening suspected bullet pixels. For example, the preset bullet suspected threshold may be 0.7, and its value range may be (0, 1). The suspected bullet pixel may represent the real position of the bullet or the position of the bullet tail.

[0122] It should be noted that during the bullet's flight, the flying bullet may cause the temperature of the air behind it to rise, resulting in a trailing area in the infrared image. Therefore, the suspected bullet pixel may be a position point on the target bullet or a position point in the trailing area.

[0123] In the second step, according to the gray value corresponding to the suspected bullet pixel and the possible index of the bullet, the formula corresponding to the real bullet feature value corresponding to the suspected bullet pixel is determined as follows:

[0124] ;in, It is The real bullet feature value corresponding to the suspected bullet pixel point. It is the serial number of the pixel point suspected to be a bullet. is a normalization function. It is The gray value corresponding to the pixel point suspected to be a bullet. It is the mean of the gray values ​​corresponding to all suspected bullet pixels. It is The possible bullet indicators corresponding to the suspected bullet pixels. It is the preset bullet suspicion threshold.

[0125] It should be noted that when The larger the The more pixels suspected of being bullets, the more likely they are to be bullet locations. In reality, a bullet flying past often results in a higher air temperature behind it, causing a tail to appear on the infrared image. Generally, the tail temperature is often lower than the bullet area temperature, and the grayscale of the tail area mapped on the infrared image is often lower than the bullet area grayscale. The larger the The more suspected bullet pixels there are, the more likely they are bullet locations. The larger the The more suspected bullet pixels there are, the more likely they are bullet locations.

[0126] In the third step, if the real bullet feature value corresponding to the suspected bullet pixel point is greater than the preset real bullet threshold, the suspected bullet pixel point is determined as the target bullet point.

[0127] The preset real bullet threshold may be a preset threshold. For example, the preset real bullet threshold may be 0.2. The target bullet point may represent the real position point of the bullet.

[0128] The fourth step is to divide the target bullet area formed by all target bullet points to obtain a reference area representing the bullet head and a reference area representing the bullet body, and select the target bullet point representing the bullet head vertex from all target bullet points as the target vertex.

[0129] For example, the area representing the bullet head and the area representing the bullet body can be screened out from the area formed by all target bullet points through threshold segmentation or neural network recognition methods, both of which are recorded as reference areas, and the screened pixel points representing the bullet head vertices are recorded as target vertices.

[0130] Step S4, determining the temperature influence factor corresponding to each target bullet point according to the target vertex, the gray value corresponding to each target bullet point, the area-to-volume ratio of the actual bullet part represented by the reference area to which it belongs, and the flight speed of the target bullet.

[0131] As an example, this step may include the following steps:

[0132] The first step is to connect the above target vertex and each target bullet point to obtain the target line segment corresponding to each target bullet point.

[0133] In the second step, the number of pixel points on the target line segment corresponding to each target bullet point is determined as the number of targets corresponding to each target bullet point.

[0134] The third step is to determine the temperature influence factor corresponding to the target bullet point according to the gray value and target number corresponding to the target bullet point, the area-to-volume ratio of the actual bullet part represented by the reference area to which it belongs, and the flight speed of the target bullet:

[0135] ;in, It is The temperature influence factor corresponding to each target bullet point. It is the sequence number of the target bullet point. is a normalization function. It is The grayscale value corresponding to the target bullet point. It is the mean of the grayscale values ​​corresponding to all target bullet points. It is The reference area to which the target bullet point belongs represents the surface area of ​​the actual bullet part. The actual bullet part represents the bullet head or the body of the target bullet. It is The volume of the actual bullet site represented by the reference area to which the target bullet point belongs. It is The area-to-volume ratio of the actual bullet site represented by the reference area to which the target bullet point belongs. It is The flight speed of the target bullet at the time of collection corresponding to the target bullet point. The acquisition time corresponding to each target bullet point can be the time of acquiring the infrared image to be corrected. The flight speed of the target bullet can be acquired by continuous wave radar. It is an exponential function with a natural constant as its base. It is The number of targets corresponding to each target bullet point.

[0136] It should be noted that during the flight of a bullet, the temperature performance of different parts of the bullet is often different, which may cause some parts to be mapped too brightly in the infrared image, causing some areas on the generated infrared simulation image to lose their own shape characteristics and appear unreal, thus affecting the accuracy of the infrared simulation image generation. The color of the same bullet is often uniform, but due to the different temperature performance of different parts of the bullet, the grayscale of the bullet displayed on the infrared image may not be uniform. Therefore, in order to improve the accuracy of the infrared simulation image generation, the grayscale of the brighter mapped parts of the bullet can be appropriately reduced, and the grayscale of the relatively darker mapped parts can be appropriately increased to make the overall grayscale uniform, thereby improving the authenticity of the subsequent infrared simulation image generation. When The larger the The larger the gray value corresponding to the target bullet point, the more appropriate it is to In actual situations, bullets with relatively large areas and volumes, such as sharp bullet heads, have relatively large surface areas when flying at high speeds, and their contact areas with the air are relatively large. Therefore, they may be subject to greater air friction resistance, and their temperatures are often higher. Their brightness in the infrared image is often higher, which often indicates that their grayscale should be appropriately reduced. When the value is larger, it often means that the first The grayscale of the target bullet point is reduced. The larger the The greater the target bullet's flight speed at the time of acquisition corresponding to the target bullet point, the greater the friction generated at this time, which often means that the temperature of the target bullet is relatively high at this time, and the higher the brightness of its mapping in the infrared image, which often means that its grayscale should be appropriately reduced. The smaller the time, the more likely it is that The closer the target bullet point is to the sharp tip of the bullet, the higher the temperature of the corresponding bullet part is, which means that the first The grayscale of the target bullet point is reduced. When the value is larger, it often means that the first Reduce the grayscale of the target bullet points.

[0137] Step S5, correcting the infrared image to be corrected according to the temperature influence factor corresponding to the target bullet point in the infrared image to be corrected, to obtain the target image.

[0138] As an example, this step may include the following steps:

[0139] In the first step, the pixels other than the suspected bullet pixels in the infrared image to be corrected are determined as environmental pixels, and the suspected bullet pixels other than the target bullet pixels among all the suspected bullet pixels are determined as bullet tail pixels.

[0140] In the second step, the average of the grayscale values ​​corresponding to all the environmental pixels in the preset neighborhood corresponding to all the pixels on the edge of the area formed by all the bullet tail pixels is determined as the environmental representative grayscale index.

[0141] The preset neighborhood may be a pre-set neighborhood, for example, a 5×5 neighborhood.

[0142] In the third step, according to the grayscale value and temperature influence factor corresponding to each target bullet point, the formula corresponding to the target grayscale index corresponding to each target bullet point can be determined as follows:

[0143] ;in, It is The target grayscale index corresponding to each target bullet point. It is the sequence number of the target bullet point. It is The gray value corresponding to the target bullet point is equal to the gray value of the first target bullet point in the infrared image to be corrected before updating. The grayscale value corresponding to the target bullet point. It is The temperature influence factor corresponding to each target bullet point. It is the mean of the grayscale values ​​corresponding to all target bullet points.

[0144] It should be noted that when When the value is larger, it often means that the first The grayscale of the target bullet point is reduced. Can characterize the The grayscale value after adjustment of the target bullet points.

[0145] The fourth step is to update the grayscale values ​​corresponding to all the bullet tail pixels in the above infrared image to be corrected to the above environmental representative grayscale index, and update the grayscale value corresponding to each target bullet point in the above infrared image to be corrected to its corresponding target grayscale index, and determine the updated infrared image to be corrected as the target image.

[0146] It should be noted that, to a certain extent, the target image can show the true shape of the target bullet.

[0147] Step S6, performing infrared simulation processing on the target image to obtain an infrared simulation image.

[0148] As an example, infrared simulation software is used to perform simulation calculations on a target image, thereby generating an infrared simulation image.

[0149] It should be noted that after completing the grayscale adjustment of the pixels at different positions in the infrared image to be corrected, the grayscale value of the bullet area after correction can be converted into infrared radiation intensity based on the relationship between grayscale value-temperature-infrared radiation measured previously. Infrared radiation interacts with specific elements in the detector material to generate electrical signals, which are then transmitted to the display after amplification, filtering, and denoising to generate infrared simulation images, and finally infrared simulation images with improved authenticity are obtained. Authenticity is an important factor affecting the accuracy of infrared simulation images. Using more realistic infrared simulation images can help staff analyze simulation data and improve the accuracy of analysis results.

[0150] refer to Figure 2Based on the same inventive concept as the above method embodiment, the present invention provides a system for improving the accuracy of infrared simulation images in an infrared imaging simulation system, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the above computer program is executed by the processor, the steps of a method for improving the accuracy of infrared simulation images in an infrared imaging simulation system may specifically include:

[0151] The image acquisition factor determination module 201 is used to obtain the infrared image to be corrected and the previous frame of historical infrared image corresponding to the target bullet during flight, and determine the grayscale change factor corresponding to each pixel in the infrared image to be corrected based on the infrared image to be corrected and the previous frame of historical infrared image;

[0152] The bullet possible index determination module 202 is used to determine the bullet possible index corresponding to each pixel in the infrared image to be corrected according to the difference between the grayscale change factor corresponding to each pixel in the infrared image to be corrected and the pixel in the preset direction, and the grayscale distribution in the preset window corresponding to each pixel in the infrared image to be corrected;

[0153] The screening and dividing module 203 is used to screen out target bullet points from the infrared image to be corrected according to possible bullet indicators, divide the target bullet area formed by all target bullet points, obtain a reference area representing the bullet head or the bullet body, and screen out the target bullet point representing the bullet head vertex from all target bullet points as the target vertex;

[0154] The temperature influence factor determination module 204 is used to determine the temperature influence factor corresponding to each target bullet point according to the target vertex, the gray value corresponding to each target bullet point, the area-to-volume ratio of the actual bullet part represented by the reference area to which it belongs, and the flight speed of the target bullet;

[0155] The image correction module 205 is used to correct the infrared image to be corrected according to the temperature influence factor corresponding to the target bullet point in the infrared image to be corrected, so as to obtain the target image;

[0156] The image construction module 206 is used to perform infrared simulation processing on the target image to obtain an infrared simulation image.

[0157] Figure 3 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. Figure 3As shown, the computer device 300 includes: a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302, wherein when the processor 302 executes the computer program 303, the computer device can execute any one of the methods introduced above to improve the accuracy of infrared simulation images in an infrared imaging simulation system.

[0158] Based on the same inventive concept as the above method embodiment, the present invention provides a server, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes any of the above methods for improving the accuracy of infrared simulation images in an infrared imaging simulation system.

[0159] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer program product, which includes: computer program code, when the computer program code runs on a computer, enables the computer to execute any one of the above-mentioned methods for improving the accuracy of infrared simulation images in an infrared imaging simulation system.

[0160] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer-readable storage medium, which stores a computer program code. When the computer program code runs on a computer, the computer executes any one of the above-mentioned methods for improving the accuracy of infrared simulation images in an infrared imaging simulation system.

[0161] In summary, compared with directly generating an infrared simulation image of a bullet based on the collected infrared image of the bullet, the present invention comprehensively considers multiple features related to bullet area identification, such as grayscale change factor, grayscale distribution and possible indicators of the bullet, so as to screen out the target bullet point that represents the real bullet position, which can reduce the misjudgment of the real bullet area caused by the bullet tailing to a certain extent, and also considers the different temperature performances of different parts of the bullet during its flight, for example, the target vertex, the grayscale value corresponding to the target bullet point, the area-to-volume ratio of the actual bullet part represented by the reference area to which it belongs, and the flight speed of the target bullet, and based on the temperature influence factor corresponding to the target bullet point, the infrared image to be corrected is corrected, which can reduce the visual display error caused by the different temperature performances of different parts of the bullet during its flight to a certain extent, thereby improving the accuracy of generating the infrared simulation image of the bullet.

[0162] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for improving the accuracy of infrared simulation images in an infrared imaging simulation system, characterized in that: The following steps are involved: Acquire the infrared image to be corrected and the previous frame of historical infrared image corresponding to the target bullet in the flight process, and determine the grayscale change factor corresponding to each pixel point in the infrared image to be corrected based on the infrared image to be corrected and the previous frame of historical infrared image; Determine the possible bullet index corresponding to each pixel in the infrared image to be corrected according to the difference between the grayscale change factor corresponding to each pixel in the infrared image to be corrected and the pixel in the preset direction, and the grayscale distribution in the preset window corresponding to each pixel in the infrared image to be corrected; According to the possible indicators of the bullet, the target bullet points are screened out from the infrared image to be corrected, the target bullet area formed by all the target bullet points is divided to obtain a reference area representing the bullet head or the bullet body, and the target bullet point representing the bullet head vertex is screened out from all the target bullet points as the target vertex; Determine the temperature influence factor corresponding to each target bullet point according to the target vertex, the gray value corresponding to each target bullet point, the area-to-volume ratio of the actual bullet part represented by the reference area to which the target bullet point belongs, and the flight speed of the target bullet; According to the temperature influence factor corresponding to the target bullet point in the infrared image to be corrected, the infrared image to be corrected is corrected to obtain the target image; Perform infrared simulation processing on the target image to obtain an infrared simulation image; The method of determining the temperature influence factor corresponding to each target bullet point according to the target vertex, the gray value corresponding to each target bullet point, the area-to-volume ratio of the actual bullet part represented by the reference area to which the target bullet point belongs, and the flight speed of the target bullet includes: Connecting the target vertex and each target bullet point to obtain a target line segment corresponding to each target bullet point; The number of pixel points on the target line segment corresponding to each target bullet point is determined as the number of targets corresponding to each target bullet point; According to the gray value and target number corresponding to the target bullet point, the area-to-volume ratio of the actual bullet part represented by the reference area to which it belongs, and the flight speed of the target bullet, the formula corresponding to the temperature influence factor corresponding to the target bullet point is determined as follows: ;in, It is Temperature influence factor corresponding to each target bullet point; is the serial number of the target bullet point; is the normalization function; It is The gray value corresponding to the target bullet point; is the mean of the grayscale values ​​corresponding to all target bullet points; It is The reference area to which the target bullet point belongs represents the surface area of ​​the actual bullet part; the actual bullet part represents the warhead of the target bullet or the body of the target bullet; It is The volume of the actual bullet site represented by the reference area to which the target bullet point belongs; It is The area-to-volume ratio of the actual bullet site represented by the reference area to which the target bullet point belongs; It is The flight speed of the target bullet at the time of collection corresponding to each target bullet point; It is an exponential function with a natural constant as base; It is The number of targets corresponding to each target bullet point.

2. The method for improving the accuracy of infrared simulation images in an infrared imaging simulation system according to claim 1, characterized in that: The step of determining the grayscale change factor corresponding to each pixel in the infrared image to be corrected based on the infrared image to be corrected and the previous frame of historical infrared image thereof includes: Determine any pixel point in the infrared image to be corrected as a marked pixel point, and select a pixel point with the same position as the marked pixel point from a previous frame of historical infrared image of the infrared image to be corrected as a reference pixel point; The difference between the grayscale value corresponding to the marked pixel and the grayscale value corresponding to the reference pixel is determined as the grayscale change factor corresponding to the marked pixel.

3. The method for improving the accuracy of infrared simulation images in an infrared imaging simulation system according to claim 1, characterized in that: The method of determining the possible bullet index corresponding to each pixel in the infrared image to be corrected according to the difference between the grayscale change factor corresponding to each pixel in the infrared image to be corrected and the pixel in the preset direction, and the grayscale distribution in the preset window corresponding to each pixel in the infrared image to be corrected, comprises: Determine the grayscale fluctuation performance factor of each pixel in the infrared image to be corrected in each preset direction according to the difference between the grayscale variation factors corresponding to each pixel in the infrared image to be corrected and a preset number of pixels in each preset direction; According to the grayscale fluctuation performance factor of each pixel in the infrared image to be corrected in all preset directions and the grayscale distribution in a preset window corresponding to each pixel in the infrared image to be corrected, the possible bullet index corresponding to each pixel in the infrared image to be corrected is determined.

4. The method for improving the accuracy of infrared simulation images in an infrared imaging simulation system according to claim 3, characterized in that: Determining the grayscale fluctuation performance factor of each pixel in the infrared image to be corrected in each preset direction according to the difference between the grayscale variation factors corresponding to each pixel in the infrared image to be corrected and a preset number of pixels in each preset direction thereof includes: Determine any pixel point in the infrared image to be corrected as a marked pixel point, and determine any preset direction as a marked direction; A target straight line is drawn through the marked pixel point and in the marked direction, taking the marked direction as the straight line direction; Selecting a preset number of pixels closest to the marked pixel point on the target straight line as candidate pixels, and obtaining a set of candidate pixels of the marked pixel point in the marked direction; The absolute value of the difference between the grayscale change factors corresponding to every two candidate pixel points in the candidate pixel point set is determined as the target difference, and the target difference set of the marked pixel point in the marked direction is obtained; The mean value of all target differences in the target difference set is determined as the grayscale fluctuation expression factor of the marked pixel point in the marked direction.

5. The method for improving the accuracy of infrared simulation images in an infrared imaging simulation system according to claim 3, characterized in that: The method of determining the possible bullet index corresponding to each pixel in the infrared image to be corrected according to the grayscale fluctuation performance factor of each pixel in the infrared image to be corrected in all preset directions and the grayscale distribution in a preset window corresponding to each pixel in the infrared image to be corrected comprises: Determine the target fluctuation index corresponding to each pixel point in the infrared image to be corrected according to the grayscale fluctuation performance factor of each pixel point in the infrared image to be corrected in all preset directions, wherein the grayscale fluctuation performance factor is positively correlated with the target fluctuation index; Acquire a preset number of frames of historical infrared images before the infrared image to be corrected, and determine the target fluctuation index corresponding to each pixel point in each frame of the historical infrared image; Determine the overall change degree factor corresponding to each pixel point in the infrared image to be corrected according to the target fluctuation index corresponding to the pixel point in the infrared image to be corrected and the target fluctuation index corresponding to the pixel point in the historical infrared image of a preset number of frames before the infrared image to be corrected; Determine the variance of the grayscale values ​​corresponding to all the pixels in the preset window corresponding to each pixel in the infrared image to be corrected as the grayscale distribution factor corresponding to each pixel in the infrared image to be corrected; According to the overall change degree factor and the gray distribution factor corresponding to each pixel point in the infrared image to be corrected, the possible bullet index corresponding to each pixel point in the infrared image to be corrected is determined.

6. The method for improving the accuracy of infrared simulation images in an infrared imaging simulation system according to claim 5, characterized in that: The method of determining the overall change degree factor corresponding to each pixel point in the infrared image to be corrected according to the target fluctuation index corresponding to the pixel point in the infrared image to be corrected and the target fluctuation index corresponding to the pixel point in the historical infrared image of a preset number of frames before the infrared image to be corrected comprises: Determine any pixel point in the infrared image to be corrected as a marked pixel point, and select pixels with the same position as the marked pixel point from a preset number of frames of historical infrared images before the infrared image to be corrected as undetermined pixels, and obtain a set of undetermined pixels corresponding to the marked pixel point; The target fluctuation index corresponding to the marked pixel point and the average value of the target fluctuation indexes corresponding to all the pending pixel points in the corresponding pending pixel point set are determined as the overall change degree factor corresponding to the marked pixel point.

7. The method for improving the accuracy of infrared simulation images in an infrared imaging simulation system according to claim 1, characterized in that: The method of selecting target bullet points from the infrared image to be corrected according to possible bullet indicators includes: If the bullet possibility index corresponding to the pixel point is greater than the preset bullet suspicion threshold, the pixel point is determined as a suspected bullet pixel point, wherein the suspected bullet pixel point represents the real position point of the bullet or the position point of the bullet tail; According to the gray value corresponding to the suspected bullet pixel and the possible index of the bullet, the formula for determining the real bullet feature value corresponding to the suspected bullet pixel is: ;in, It is The real bullet feature value corresponding to the suspected bullet pixel point; is the serial number of the pixel suspected to be a bullet; is the normalization function; It is Gray value corresponding to the pixel point suspected of being a bullet; It is the mean of the gray values ​​corresponding to all suspected bullet pixels; It is The possible bullet indicators corresponding to the suspected bullet pixels; It is the preset bullet suspicion threshold; If the real bullet feature value corresponding to the suspected bullet pixel point is greater than the preset real bullet threshold, the suspected bullet pixel point is determined as the target bullet point, wherein the target bullet point represents the real position point of the bullet.

8. The method for improving the accuracy of infrared simulation images in an infrared imaging simulation system according to claim 7, characterized in that: The method of correcting the infrared image to be corrected according to the temperature influence factor corresponding to the target bullet point in the infrared image to be corrected to obtain the target image includes: Determine the pixels other than the suspected bullet pixels in the infrared image to be corrected as environmental pixels, and determine the suspected bullet pixels other than the target bullet pixels among all the suspected bullet pixels as bullet tail pixels; The average of the grayscale values ​​corresponding to all the environmental pixels in the preset neighborhood corresponding to all the pixels on the edge of the area formed by all the bullet tail pixels is determined as the environmental representative grayscale index; According to the grayscale value and temperature influence factor corresponding to each target bullet point, determine the target grayscale index corresponding to each target bullet point; The grayscale values ​​corresponding to all bullet tailing pixels in the infrared image to be corrected are updated to the environmental representative grayscale index, and the grayscale value corresponding to each target bullet point in the infrared image to be corrected is updated to its corresponding target grayscale index, and the updated infrared image to be corrected is determined as the target image.

9. The method for improving the accuracy of infrared simulation images in an infrared imaging simulation system according to claim 8, characterized in that: The formula corresponding to the target gray index corresponding to the target bullet point is: ;in, It is The target gray index corresponding to each target bullet point; is the serial number of the target bullet point; It is The gray value corresponding to the target bullet point is equal to the gray value of the first target bullet point in the infrared image to be corrected before updating. The gray value corresponding to the target bullet point; It is Temperature influence factor corresponding to each target bullet point; It is the mean of the grayscale values ​​corresponding to all target bullet points.

Images