Infrared imaging simulation method and system based on data analysis

Abstract

The invention relates to the technical field of infrared thermal imaging, in particular to an infrared imaging simulation method and system based on data analysis. According to the method, firstly, according to the difference condition of infrared radiation values of pixel points in bullet initial infrared imaging, all suspected bullet pixel points are screened out from all the pixel points; according to the infrared radiation values of the pixel points in the real bullet area, screening out each pixel point to be corrected; acquiring a corrected infrared radiation value of the pixel point to be corrected according to the infrared radiation value in the local area of the pixel point to be corrected; according to the corrected infrared radiation values of all the to-be-corrected pixel points, correcting the initial infrared image of the bullet to obtain a corrected infrared image of the bullet; and according to bullet correction infrared imaging, generating an infrared image simulation model. By deeply analyzing the influence of the particulate matters on the infrared radiation value, bullet correction infrared imaging is constructed to more accurately reflect the actual infrared radiation characteristics of the bullet, so that the accuracy of generating the infrared image simulation model is improved.

Description

Technical Field

[0001] The present invention relates to the field of infrared thermal imaging technology, and in particular to an infrared imaging simulation method and system based on data analysis. Background Art

[0002] Infrared imaging technology is a technology that converts the infrared radiation of the environment and the target into a visible image that can be identified, thereby revealing key information about the target and its background. In infrared imaging simulation, the first step is to accurately establish the relationship between the surface temperature of the object and the infrared radiation value it releases. Then, through meticulous image rendering and parameter fine-tuning, a realistic infrared image simulation model can be generated, which can provide important technical support and decision-making basis.

[0003] The existing technology directly generates a bullet infrared image simulation model based on the collected initial infrared image of the bullet. It does not fully consider that due to the uncontrollability of the bullet's flight environment, there are some tiny particles attached to the bullet surface. The particles will affect the reception of the real infrared radiation value released during the bullet's flight, resulting in inaccurate collection of the bullet's initial infrared image, affecting the accuracy of the infrared image simulation model. Summary of the invention

[0004] In order to solve the technical problem of inaccurate infrared imaging constructed by the prior art, the purpose of the present invention is to provide an infrared imaging simulation method and system based on data analysis, and the technical solution adopted is as follows: An infrared imaging simulation method based on data analysis, the method comprising: Acquire the initial infrared imaging of the bullet during its flight; According to the difference of the infrared radiation values ​​of the pixels in the initial infrared imaging of the bullet, each suspected bullet pixel is screened out from all the pixels; according to all the suspected bullet pixels in the initial infrared imaging of the bullet, each suspected bullet area is determined; according to the deviation of the suspected bullet area from the standard, the real bullet area is screened out; Filter out the pixels to be corrected according to the infrared radiation values ​​of the pixels in the real bullet area; obtain the corrected infrared radiation values ​​of the pixels to be corrected according to the infrared radiation values ​​in the local area of ​​the pixels to be corrected; correct the initial infrared imaging of the bullet according to the corrected infrared radiation values ​​of all the pixels to be corrected to obtain the corrected infrared imaging of the bullet; generate an infrared image simulation model according to the corrected infrared imaging of the bullet.

[0005] Furthermore, the method for obtaining the suspected bullet pixel point includes: In the initial infrared imaging of the bullet, the bullet probability of the pixel point is obtained according to the difference between the infrared radiation value of the pixel point and the overall infrared radiation value of the initial infrared imaging of the bullet; Each pixel point whose bullet possibility is greater than a preset infrared threshold is marked as each suspected bullet pixel point.

[0006] Furthermore, the method for obtaining the bullet probability includes: The average of the infrared radiation values ​​corresponding to all pixels in the initial infrared imaging of the bullet is calculated to obtain the overall infrared radiation value of the initial infrared imaging of the bullet; the difference between the infrared radiation value of the pixel and the overall infrared radiation value is calculated and normalized to obtain the bullet probability of the pixel.

[0007] Furthermore, the method for obtaining the real bullet area includes: The suspected bullet area and the preset standard bullet are respectively used as the test area; the cumulative value of the curvature values ​​corresponding to all feature points on the edge of the test area is calculated as the shape curvature value of the test area; the absolute value of the difference between the shape curvature values ​​of the suspected bullet area and the preset standard bullet is calculated and negatively correlated to obtain the true possibility of the suspected bullet area; The maximum true possibility is corresponded to the suspected bullet area as the real bullet area.

[0008] Furthermore, the method for obtaining the pixel to be corrected includes: According to the directional characteristics of the real bullet area, obtaining a first influence degree of particles in the real bullet area; Obtaining a second influence degree of the particulate matter at the pixel point according to a difference between the infrared radiation value of the pixel point and its local infrared radiation value; Forward fusion of the first influence degree of the particle corresponding to the pixel point and the second influence degree of the particle point to obtain the comprehensive influence degree of the particle at the pixel point; According to the comprehensive influence of the particles, each pixel point to be corrected is selected from all the pixel points in the real bullet area.

[0009] Furthermore, the method for obtaining the first impact degree of particulate matter includes: Using the principal component analysis method, the main direction of the real bullet area is taken as the flight direction of the real bullet area; the vertical ground direction is taken as the reference direction; the angle value between the flight direction and the reference direction is negatively correlated to obtain the first influence degree of the particles in the real bullet area.

[0010] Furthermore, the method for obtaining the second influence degree of the particulate matter includes: In the flight direction, the average of the infrared radiation values ​​corresponding to the previous pixel and the next pixel of the pixel is taken as the local infrared radiation value of the pixel; the absolute value of the difference between the infrared radiation value of the pixel and the local infrared radiation value is calculated to obtain the second influence degree of the particle matter of the pixel.

[0011] Furthermore, the method for obtaining the comprehensive impact of particulate matter includes: The product of the first influence degree of the particle corresponding to the pixel point and the second influence degree of the particle point is calculated and normalized to obtain the comprehensive influence degree of the particle point.

[0012] Furthermore, the method for obtaining the corrected infrared radiation value includes: In a preset local area of ​​the pixel to be corrected, each pixel except the pixel to be corrected is used as a reference pixel; and the average of the infrared radiation values ​​of all reference pixels is calculated as the corrected infrared radiation value of the pixel to be corrected.

[0013] The present invention proposes an infrared imaging simulation system based on data analysis, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the infrared imaging simulation method based on data analysis are implemented.

[0014] The present invention has the following beneficial effects: Considering that the surface temperature of bullets is usually higher than the surrounding environment, the infrared radiation value of the pixel points corresponding to the bullet will be relatively high. The suspected bullet pixel points are screened out from all the pixel points; the deviation of the suspected bullet area from the standard bullet is analyzed and further screened, and the suspected bullet area that meets the shape characteristics of the bullet is retained as the real bullet area. Considering the impact of particulate matter on bullets, the pixels to be corrected caused by the influence of tiny particles are screened out according to the infrared radiation values ​​of the pixels in the real bullet area. For the screened pixels to be corrected, it is necessary to obtain their corrected infrared radiation values ​​based on the infrared radiation values ​​in the local areas of these pixels to make them closer to the real values. After obtaining the corrected infrared radiation values ​​of all the pixels to be corrected, the initial infrared imaging of the bullet can be corrected as a whole, so that the corrected infrared imaging of the bullet more accurately reflects the actual infrared radiation characteristics of the bullet, thereby improving the accuracy of the generated infrared image simulation model. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] 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.

[0016] Figure 1 A flowchart of an infrared imaging simulation method based on data analysis provided by one embodiment of the present invention; Figure 2 A flow chart of a method for obtaining suspected bullet pixels provided by an embodiment of the present invention; Figure 3 A flow chart of a method for obtaining pixels to be corrected provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the infrared imaging simulation method and system based on data analysis proposed by the present invention, 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.

[0018] 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.

[0019] The specific scheme of an infrared imaging simulation method and system based on data analysis provided by the present invention is described in detail below with reference to the accompanying drawings.

[0020] The embodiment of the present invention provides an infrared imaging simulation method and system based on data analysis, please refer to Figure 1 , which shows a flow chart of an infrared imaging simulation method based on data analysis provided by an embodiment of the present invention, the method comprising the following steps: Step S1: Acquire the initial infrared image of the bullet during its flight.

[0021] First, install the infrared thermal imager in a suitable position so as to capture the initial infrared imaging of the bullet flight, and ensure that the lens of the infrared thermal imager maintains a certain angle and distance with the bullet flight trajectory to obtain the best infrared imaging effect. Fire the bullet and start the infrared thermal imager to capture it at the same time. The infrared thermal imager collects the bullet during the bullet flight according to the preset frequency, and obtains the original collected image corresponding to the bullet at each sampling moment. Since the original collected image has noise, the noise will affect the subsequent edge detection, so the original collected image is subjected to noise reduction operation to eliminate the influence of noise and some external interference, enhance the accuracy of subsequent analysis, and thus obtain the initial infrared imaging of the bullet. The embodiment of the present invention uses median filtering to reduce the noise of the image, and the implementer can set the noise reduction method according to the actual situation. In one embodiment of the present invention, sampling is performed according to the preset frequency, and each sampling is used as a sampling moment, and the preset frequency is 5 times / second.

[0022] It should be noted that, in order to facilitate calculation, all index data involved in the calculation in the embodiment of the present invention are subjected to data preprocessing to eliminate the dimension effect. The specific means of removing the dimension effect are technical means well known to those skilled in the art and are not limited here. It should be noted that the present invention collects images of the target bullet during its upward flight, and the initial infrared imaging of the bullet only includes one bullet, namely the target bullet.

[0023] Considering that when a bullet is flying at high speed, its surface may generate static electricity due to friction with the air, thereby attracting more tiny particles. These particles will interfere with the infrared imaging device's capture of the bullet's true infrared radiation value, causing a deviation between the bullet's initial infrared imaging and the bullet's actual infrared radiation characteristics. In order to correct this inaccurate infrared radiation value, it is first necessary to accurately identify the bullet area from the bullet's initial infrared imaging.

[0024] Step S2: based on the difference of infrared radiation values ​​of pixels in the initial infrared imaging of the bullet, each suspected bullet pixel is screened out from all pixels; based on all suspected bullet pixels in the initial infrared imaging of the bullet, each suspected bullet area is determined; based on the deviation of the suspected bullet area from the standard, the real bullet area is screened out.

[0025] Considering that the surface temperature of a bullet is usually higher than the surrounding environment, the infrared radiation value of the pixel corresponding to the bullet will be relatively high, and the suspected bullet pixel points are screened out from all the pixels; the deviation of the suspected bullet area from the standard bullet is analyzed, and further screening is performed to retain the suspected bullet area that meets the bullet shape characteristics as the real bullet area.

[0026] Considering that the bullet has a higher temperature than the environment due to air friction and other factors during its flight, this temperature difference is reflected in the initial infrared imaging of the bullet, specifically as a higher infrared radiation value for the corresponding pixel representing the bullet. In infrared imaging, each pixel has a corresponding infrared radiation value. By comparing the difference between the infrared radiation values ​​of the pixel and the initial infrared imaging of the bullet, the pixel reflecting the bullet is selected from all the pixels in the initial infrared imaging of the bullet. Please refer to Figure 2 , which shows a flow chart of a method for obtaining suspected bullet pixel points in one embodiment of the present invention. Preferably, in one embodiment of the present invention, the method for obtaining suspected bullet pixel points includes: Step S201: in the initial infrared imaging of the bullet, the bullet probability of the pixel is obtained according to the difference between the infrared radiation value of the pixel and the overall infrared radiation value of the initial infrared imaging of the bullet.

[0027] By constructing the bullet probability of the pixel point, the possibility of the pixel point corresponding to the bullet can be preliminarily reflected.

[0028] Preferably, in one embodiment of the present invention, the method for obtaining the bullet probability includes: Calculate the mean of the infrared radiation values ​​corresponding to all pixels in the initial infrared imaging of the bullet to obtain the overall infrared radiation value of the initial infrared imaging of the bullet; calculate the difference between the infrared radiation value of the pixel and the overall infrared radiation value and perform normalization processing to obtain the bullet probability of the pixel. It should be noted that the normalization method is: normalize using the norm normalization function to limit the value range to between 0 and 1. Normalization is a technical means well known to those skilled in the art, and the selection of the normalization function can be linear normalization or standard normalization, etc. The specific normalization method is not limited here.

[0029] For the above steps, first, calculate the mean of the infrared radiation values ​​of all pixels in the initial infrared imaging of the bullet to obtain the overall infrared radiation value of the initial infrared imaging of the bullet. The overall infrared radiation value reflects the temperature of the overall environment. Next, for each pixel, calculate the difference between its infrared radiation value and the overall infrared radiation value. This difference reflects the temperature difference of the pixel relative to the overall environment. In order to make this difference comparable, normalize it to obtain the bullet probability of the pixel. The higher the bullet probability of a pixel, the more likely it is to be the pixel corresponding to the bullet.

[0030] Step S202: Mark each pixel point whose bullet possibility is greater than a preset infrared threshold as a suspected bullet pixel point.

[0031] For the above steps, after obtaining the bullet probability of each pixel, the bullet probability of all pixels is compared with the preset infrared threshold. If the bullet probability of a certain pixel is greater than the threshold, the pixel is considered to be a bullet pixel, and is subsequently processed as a suspected bullet pixel. In one embodiment of the present invention, the preset infrared threshold is 0.37 to distinguish suspected bullet pixels from background pixels. This threshold is determined based on experimental data or experience, and the implementer can set it according to the implementation scenario.

[0032] In order to preliminarily determine the area corresponding to the bullet, preferably, in one embodiment of the present invention, the method for obtaining the suspected bullet area includes: Using the connected domain analysis method, each connected domain is determined according to all the suspected bullet pixels in the initial infrared imaging of the bullet; morphological operations are performed on each connected domain to obtain each suspected bullet region in the initial infrared imaging of the bullet. It should be noted that the connected domain analysis method and morphological operations are prior arts well known to those skilled in the art and will not be described in detail here.

[0033] For the above steps, the purpose of the connected domain analysis method is to gather adjacent suspected bullet pixels in the initial infrared imaging of the bullet to form various connected regions. Each connected domain corresponds to a potential bullet region; after obtaining each connected domain, it is necessary to perform morphological operations on each connected domain. Morphological operations are a set of image processing techniques based on image shape, including expansion, erosion, opening operations and closing operations. The purpose of morphological operations is to adjust and optimize the shape of the connected domain. For example, the expansion operation can fill the empty spots or small cracks inside the connected domain; the erosion operation can remove the small protrusions or noise points on the edge of the connected domain; the opening operation can remove small objects while keeping the shape of larger objects unchanged; the closing operation can fill the small holes inside the object and smooth its boundaries. Through these operations, each suspected bullet region is obtained, which can make the suspected bullet region more complete and facilitate subsequent identification and extraction.

[0034] Considering the interference of thermal radiation from background objects, the non-bullet area is mistakenly identified as a suspected bullet area. By comparing the similarity between the shape of the suspected area and the preset standard bullet shape, the false detection area corresponding to the background object can be more effectively excluded, thereby improving the accuracy of real bullet area identification. Preferably, in one embodiment of the present invention, the method for obtaining the real bullet area includes: The suspected bullet area and the preset standard bullet are respectively used as the test area; the cumulative value of the curvature values ​​corresponding to all feature points on the edge of the test area is calculated as the shape curvature value of the test area; the absolute value of the difference between the shape curvature values ​​of the suspected bullet area and the preset standard bullet is calculated and negatively correlated to obtain the true possibility of each suspected bullet area; The suspected bullet area corresponding to the maximum true possibility is taken as the real bullet area. It should be noted that the method for obtaining edges, curvature values ​​and feature points is a prior art well known to those skilled in the art. The edge can be extracted by edge detection algorithm, the curvature value can be obtained by least square method, and the feature point can be obtained by SIFT corner point detection, which will not be elaborated here. The preset standard bullet in the present invention is based on the standard shape of the target bullet, and the implementer can set it according to the implementation scenario, which is not limited here. The negative correlation mapping of the present invention can be in the form of inverse proportion or negative exponential power, which is not limited here.

[0035] For the above steps, the suspected bullet area and the preset standard bullet are respectively used as the areas to be tested; for each area to be tested, the cumulative value of the curvature values ​​corresponding to all feature points on its edge is calculated as the shape curvature value of the area to be tested. The curvature value reflects the degree of curvature of the edge and is an important feature in shape analysis. The absolute value of the difference between the shape curvature values ​​of the suspected bullet area and the preset standard bullet is calculated, and negative correlation mapping is performed to obtain the true possibility of each suspected bullet area. Negative correlation mapping means that the smaller the difference, that is, the more similar the shape, the higher the true possibility obtained. In this way, each suspected bullet area will obtain a true possibility value related to its shape similarity. Since the initial infrared imaging of the bullet in this scene only includes one bullet, the suspected bullet area with the maximum true possibility is determined as the real bullet area, and the real bullet area more accurately reflects the area corresponding to the real bullet.

[0036] When dealing with the initial infrared imaging of bullets during flight, due to the complex environment, tiny particles are easily attached to the surface of the bullet, which will significantly affect the infrared imaging equipment's accurate capture of the actual infrared radiation characteristics of the bullet. In order to deal with this problem, measures are needed to correct this inaccurate infrared radiation value and ultimately generate an infrared image simulation model that can reflect the real infrared characteristics of the bullet.

[0037] Step S3: Filter out the pixels to be corrected according to the infrared radiation values ​​of the pixels in the real bullet area; obtain the corrected infrared radiation values ​​of the pixels to be corrected according to the infrared radiation values ​​of the local area of ​​the pixels to be corrected; correct the initial infrared imaging of the bullet according to the corrected infrared radiation values ​​of all the pixels to be corrected to obtain the corrected infrared imaging of the bullet; generate an infrared image simulation model according to the corrected infrared imaging of the bullet.

[0038] Taking into account the impact of particulate matter on bullets, the pixels to be corrected due to the influence of tiny particles are screened out according to the infrared radiation values ​​of the pixels in the real bullet area. For the screened pixels to be corrected, it is necessary to obtain their corrected infrared radiation values ​​according to the infrared radiation values ​​in the local areas of these pixels to make them closer to the real values. After obtaining the corrected infrared radiation values ​​of all the pixels to be corrected, the initial infrared imaging of the bullet can be corrected as a whole, so that the corrected infrared imaging of the bullet more accurately reflects the actual infrared radiation characteristics of the bullet, thereby improving the accuracy of the generated infrared image simulation model.

[0039] To determine the pixels affected by particles in the initial infrared image of the bullet, refer to Figure 3 , which shows a flow chart of a method for obtaining a pixel point to be corrected in one embodiment of the present invention. Preferably, in one embodiment of the present invention, the method for obtaining a pixel point to be corrected includes: Step S301: obtaining the first influence degree of particles in the real bullet area according to the directional characteristics of the real bullet area.

[0040] In order to evaluate the degree to which the real bullet area is affected by particles, the first degree of influence of particles is obtained by analyzing the influence of the angle between the bullet flight direction and the gravity direction on the attachment of particles.

[0041] Preferably, in one embodiment of the present invention, the method for obtaining the first impact degree of particulate matter includes: By using the principal component analysis method, the main direction of the real bullet area is used as the flight direction of the real bullet area; the vertical ground direction is used as the reference direction; the angle value between the flight direction and the reference direction is negatively correlated to obtain the first impact degree of the particles in the real bullet area. It should be noted that the extraction of the main direction by the principal component analysis method is an existing technology well known to those skilled in the art and will not be described in detail here.

[0042] In view of the above steps, the principal component analysis method is used to analyze the directional characteristics of the real bullet area and extract the main flight direction of the bullet. The principal component analysis method is a statistical method used to identify the principal components in the real bullet area. Here, it is used to determine the flight direction of the bullet, and the vertical ground direction is defined as the reference direction. This is to quantify the angle between the flight direction and the gravity direction, because gravity is an important factor affecting the adhesion of particles, and the angle value between the bullet flight direction and the reference direction is calculated. This angle value reflects the relative position relationship between the bullet flight direction and the gravity direction. The angle value is negatively correlated and mapped to obtain the first influence of particles. The higher the first influence of particles, the closer the bullet flight direction is to vertical downward, the more gravity helps the dust particles to adhere, and the greater the degree of influence of particles on the real bullet area.

[0043] In other embodiments of the present invention, a method for obtaining the first impact degree of particulate matter includes: In the edge of the area to be analyzed, each straight line segment is identified; the longest straight line segment is used as the main extension segment of the bullet; the straight line perpendicular to the ground is used as the reference straight line; the angle value between the main extension segment of the bullet and the reference straight line is negatively correlated and mapped to obtain the first impact degree of the particles in the real bullet area. It should be noted that the method for obtaining edges and straight line segments is a prior art well known to those skilled in the art and will not be described in detail here. The edge of the area to be analyzed can be extracted by an edge detection algorithm; and each straight line segment is identified using a Hough transform algorithm. The negative correlation mapping of the present invention can be in the form of inverse proportion or negative exponential power, which is not limited here.

[0044] For the above steps, the straight line segment reflects the main part of the bullet profile, and the longest straight line segment is selected as the main extension line segment of the bullet. This line segment can best represent the flight direction of the bullet. The straight line perpendicular to the ground is defined as the reference straight line. In the image coordinate system of the present invention, the Y axis represents the straight line perpendicular to the ground, that is, the Y axis is used as the reference straight line, and the angle value between the main extension line segment of the bullet and the reference straight line is calculated. This angle value reflects the relative position relationship between the flight direction of the bullet and the vertical direction of the ground. When the angle value is smaller, that is, the closer the bullet is to vertical downward flight, the more gravity helps the dust particles to adhere, so the first influence degree of the particulate matter is higher.

[0045] Step S302: Obtain a second influence degree of the particulate matter at the pixel point according to the difference between the infrared radiation value of the pixel point and its local infrared radiation value.

[0046] The degree to which the pixel is affected by the particles is evaluated by constructing the second influence degree of the particles.

[0047] Preferably, in one embodiment of the present invention, the method for obtaining the second impact degree of particulate matter includes: In the flight direction, the average of the infrared radiation values ​​corresponding to the previous pixel and the next pixel of the pixel is taken as the local infrared radiation value of the pixel; the absolute value of the difference between the infrared radiation value of the pixel and the local infrared radiation value is calculated to obtain the second influence degree of the particle matter of the pixel.

[0048] For the above steps, for each pixel point in the direction of the bullet's flight, select its previous pixel point and next pixel point. Calculate the average of the infrared radiation values ​​corresponding to these two adjacent pixels as the local infrared radiation value of the current pixel point. Calculate the absolute value of the difference between the infrared radiation value of the current pixel point and the local infrared radiation value to obtain the second influence degree of the particles at the pixel point. The greater the second influence degree of the particles, the greater the difference between the infrared radiation value of the current pixel point and the local area, and the more likely it is to be significantly affected by the particles.

[0049] Step S303: forwardly fuse the first influence degree of the particle corresponding to the pixel point and the second influence degree of the particle, and obtain the comprehensive influence degree of the particle at the pixel point.

[0050] By constructing the comprehensive impact of particles, the degree to which pixels are affected by particles can be comprehensively evaluated.

[0051] It should be noted that forward fusion is an existing technology well known to those skilled in the art, and forward fusion can adopt simple product, arithmetic mean or other suitable fusion methods. In one embodiment of the present invention, the product of the first influence degree of the particle corresponding to the pixel point and the second influence degree of the particle is calculated and normalized to obtain the comprehensive influence degree of the particle at the pixel point. It should be noted that the normalization method adopted is: normalization is performed using the norm normalization function, and the numerical range is limited to between 0 and 1. Among them, normalization is a technical means well known to those skilled in the art, and the choice of normalization function can be linear normalization or standard normalization, etc. The specific normalization method is not limited here.

[0052] For the above steps, for each pixel, the product of the first influence of the particles and the second influence of the particles is calculated. This product reflects the joint effect between the two influences, that is, when both are high, the product will also be high, indicating that the pixel is more affected by the particles. The normalized value is used as the comprehensive influence of the particles of the pixel. The larger the comprehensive influence of the particles, the higher the degree of influence of the particles on the pixel.

[0053] Step S304: Filter out the pixels to be corrected from all the pixels in the real bullet area according to the comprehensive influence of the particles.

[0054] Based on the comprehensive impact of particles, the pixels that are greatly affected by particles are identified from the real bullet area and marked as pixels to be corrected. These pixels to be corrected will have their infrared radiation values ​​corrected in subsequent steps.

[0055] Preferably, in one embodiment of the present invention, the method for selecting each pixel to be corrected includes: In the real bullet area, each pixel point whose particle comprehensive influence is greater than the preset particle influence threshold is marked as each pixel point to be corrected. In one embodiment of the present invention, the preset particle influence threshold is 0.47, which can be set by the implementer according to the implementation scenario.

[0056] For the above steps, the preset particle impact threshold is used to determine whether the pixel is affected by particles large enough to be marked as a pixel to be corrected. In the real bullet area, all pixels are traversed and their comprehensive particle impact is checked. For pixels whose comprehensive particle impact is greater than the preset particle impact threshold, they are marked as pixels to be corrected. These pixels are considered to be areas that are greatly affected by particles and need to correct the infrared radiation values.

[0057] In order to determine the infrared radiation value of the pixel point to be corrected that is closer to the actual infrared radiation characteristics of the bullet, preferably, in one embodiment of the present invention, the method for obtaining the corrected infrared radiation value includes: In the preset local area of ​​the pixel to be corrected, each pixel except the pixel to be corrected is used as a reference pixel; the average of the infrared radiation values ​​of all reference pixels is calculated as the corrected infrared radiation value of the pixel to be corrected. In one embodiment of the present invention, the pixel is taken as the central pixel, and a pixel with a size of 3 is constructed. 3, and the center of the preset local area is the central pixel point.

[0058] According to the above steps, the average value of the infrared radiation values ​​of all reference pixels is calculated. This average value reflects the average infrared radiation characteristics of the local area around the pixel to be corrected. The calculated average infrared radiation value is used as the corrected infrared radiation value of the pixel to be corrected. This value is used to replace the infrared radiation value of the pixel to be corrected in the original infrared imaging, so that it is closer to the actual infrared radiation characteristics of the bullet.

[0059] In order to make the bullet-corrected infrared imaging more accurately reflect the actual infrared radiation characteristics of the bullet, preferably, in one embodiment of the present invention, the method for acquiring the bullet-corrected infrared imaging includes: The corrected infrared radiation value of the pixel to be corrected is replaced with the position of the corresponding pixel in the initial infrared imaging of the bullet to obtain the corrected infrared imaging of the bullet.

[0060] For the above steps, in the initial infrared imaging of the bullet, find the pixel corresponding to the position of the pixel to be corrected, and replace its original infrared radiation value with the corrected infrared radiation value calculated previously. After traversing all the pixels to be corrected and completing the replacement of the infrared radiation value, a more accurate corrected infrared imaging of the bullet can be obtained.

[0061] After establishing the correlation between the surface temperature of the object and the infrared radiation value, the next step is to generate a realistic infrared image simulation model. It should be noted that the method of constructing an infrared image simulation model is a prior art well known to those skilled in the art. Here, a brief description is given of the generation of an infrared image simulation model based on bullet-corrected infrared imaging: Parameter fine-tuning: The initially drawn bullet-corrected infrared imaging may also require parameter fine-tuning to make it more realistic. This includes adjusting image brightness, contrast, color and other parameters, as well as considering environmental factors such as atmospheric attenuation, background radiation, etc., which affect the bullet-corrected infrared imaging. Model verification: Finally, the generated bullet-corrected infrared imaging simulation model needs to be verified. This is usually done by comparing it with the actual infrared imaging results to ensure the accuracy and reliability of the infrared image simulation model.

[0062] The present invention proposes an infrared imaging simulation system based on data analysis, comprising a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of an infrared imaging simulation method based on data analysis are implemented.

[0063] In summary, the embodiment of the present invention provides an infrared imaging simulation method and system based on data analysis. The present invention first selects each suspected bullet pixel from all pixels according to the difference in the infrared radiation value of the pixel in the initial infrared imaging of the bullet; selects each pixel to be corrected according to the infrared radiation value of the pixel in the real bullet area; obtains the corrected infrared radiation value of the pixel to be corrected according to the infrared radiation value of the local area of ​​the pixel to be corrected; corrects the initial infrared imaging of the bullet according to the corrected infrared radiation values ​​of all pixels to be corrected, and obtains the corrected infrared imaging of the bullet; generates an infrared image simulation model according to the corrected infrared imaging of the bullet. The present invention constructs a corrected infrared imaging of the bullet to more accurately reflect the actual infrared radiation characteristics of the bullet by deeply analyzing the influence of particulate matter on the infrared radiation value, thereby improving the accuracy of generating the infrared image simulation model.

[0064] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. 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.

[0065] 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.

Claims

1. An infrared imaging simulation method based on data analysis, characterized in that: The method comprises: Acquire the initial infrared imaging of the bullet during its flight; According to the difference of the infrared radiation values ​​of the pixels in the initial infrared imaging of the bullet, each suspected bullet pixel is screened out from all the pixels; according to all the suspected bullet pixels in the initial infrared imaging of the bullet, each suspected bullet area is determined; according to the deviation of the suspected bullet area from the standard, the real bullet area is screened out; Filter out the pixels to be corrected according to the infrared radiation values ​​of the pixels in the real bullet area; obtain the corrected infrared radiation values ​​of the pixels to be corrected according to the infrared radiation values ​​in the local area of ​​the pixels to be corrected; correct the initial infrared imaging of the bullet according to the corrected infrared radiation values ​​of all the pixels to be corrected to obtain the corrected infrared imaging of the bullet; generate an infrared image simulation model according to the corrected infrared imaging of the bullet.

2. The infrared imaging simulation method based on data analysis according to claim 1, characterized in that: The method for obtaining the suspected bullet pixel point comprises: In the initial infrared imaging of the bullet, the bullet probability of the pixel point is obtained according to the difference between the infrared radiation value of the pixel point and the overall infrared radiation value of the initial infrared imaging of the bullet; Each pixel point whose bullet possibility is greater than a preset infrared threshold is marked as each suspected bullet pixel point.

3. The infrared imaging simulation method based on data analysis according to claim 2, characterized in that: The method for obtaining the bullet probability includes: The average of the infrared radiation values ​​corresponding to all pixels in the initial infrared imaging of the bullet is calculated to obtain the overall infrared radiation value of the initial infrared imaging of the bullet; the difference between the infrared radiation value of the pixel and the overall infrared radiation value is calculated and normalized to obtain the bullet probability of the pixel.

4. The infrared imaging simulation method based on data analysis according to claim 1, characterized in that: The method for obtaining the real bullet area comprises: The suspected bullet area and the preset standard bullet are respectively used as the test area; the cumulative value of the curvature values ​​corresponding to all feature points on the edge of the test area is calculated as the shape curvature value of the test area; the absolute value of the difference between the shape curvature values ​​of the suspected bullet area and the preset standard bullet is calculated and negatively correlated to obtain the true possibility of the suspected bullet area; The maximum true possibility is corresponded to the suspected bullet area as the real bullet area.

5. The infrared imaging simulation method based on data analysis according to claim 1, characterized in that: The method for obtaining the pixel to be corrected comprises: According to the directional characteristics of the real bullet area, obtaining a first influence degree of particles in the real bullet area; Obtaining a second influence degree of the particulate matter at the pixel point according to a difference between the infrared radiation value of the pixel point and its local infrared radiation value; Forward fusion of the first influence degree of the particle corresponding to the pixel point and the second influence degree of the particle point to obtain the comprehensive influence degree of the particle at the pixel point; According to the comprehensive influence of the particles, each pixel point to be corrected is selected from all the pixel points in the real bullet area.

6. The infrared imaging simulation method based on data analysis according to claim 5, characterized in that: The method for obtaining the first impact degree of the particulate matter includes: Using the principal component analysis method, the main direction of the real bullet area is taken as the flight direction of the real bullet area; the vertical ground direction is taken as the reference direction; the angle value between the flight direction and the reference direction is negatively correlated to obtain the first influence degree of the particles in the real bullet area.

7. The infrared imaging simulation method based on data analysis according to claim 6, characterized in that: The method for obtaining the second influence degree of the particulate matter includes: In the flight direction, the average of the infrared radiation values ​​corresponding to the previous pixel and the next pixel of the pixel is taken as the local infrared radiation value of the pixel; the absolute value of the difference between the infrared radiation value of the pixel and the local infrared radiation value is calculated to obtain the second influence degree of the particle matter of the pixel.

8. The infrared imaging simulation method based on data analysis according to claim 5, characterized in that: The method for obtaining the comprehensive impact of particulate matter includes: The product of the first influence degree of the particle corresponding to the pixel point and the second influence degree of the particle point is calculated and normalized to obtain the comprehensive influence degree of the particle point.

9. The infrared imaging simulation method based on data analysis according to claim 1, characterized in that: The method for obtaining the corrected infrared radiation value includes: In a preset local area of ​​the pixel to be corrected, each pixel except the pixel to be corrected is used as a reference pixel; and the average of the infrared radiation values ​​of all reference pixels is calculated as the corrected infrared radiation value of the pixel to be corrected.

10. An infrared imaging simulation system based on data analysis, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the infrared imaging simulation method based on data analysis as described in any one of claims 1 to 9 are implemented.

Images