Image enhancement method of resistor array infrared scene image based on image processing

Abstract

The invention relates to the technical field of infrared image enhancement, in particular to a resistance array infrared scene image enhancement method based on image processing, and the method comprises the steps: obtaining an infrared image of a resistance array; screening an initial abnormal resistance region; obtaining the influence degree of the initial abnormal resistance region by the adjacent resistance region; obtaining the possibility that the initial abnormal resistance region belongs to an abnormal resistance region, and screening out the abnormal resistance region and a normal resistance region; clustering pixel points in the background area to obtain a plurality of class clusters; obtaining the possibility that the class cluster belongs to an abnormal background sub-region, and screening out the abnormal background sub-region and a normal background sub-region; and obtaining a correction coefficient of a pixel point in the abnormal resistance region, and performing correction in combination with the normal background sub-region to obtain an enhanced infrared image. According to the invention, the influence of mixing of different resistor temperatures in the resistor array on the infrared image is reduced, and the display effect of the infrared image is improved.

Description

Technical Field

[0001] The invention relates to the technical field of infrared image enhancement, and in particular to an image enhancement method for resistor array infrared scene images based on image processing. Background Art

[0002] Resistor array infrared image enhancement technology is a technology used to improve the quality and resolution of infrared images. By enhancing different areas in the resistor array infrared image, the clarity and contrast of the infrared image are significantly improved, allowing subtle infrared radiation to be presented more accurately.

[0003] When enhancing infrared images, existing methods obtain the positions of the resistor area and the background area in the infrared image and increase the contrast between the two areas to achieve enhancement. Then, for the infrared image of the resistor array, since the current passing through the resistor during the operation of the resistor array will increase the temperature of the resistor, the temperature increase of the resistor area will radiate to other areas around the resistor, causing temperature mixing in some areas, which will appear abnormal in the infrared image. If the impact of the temperature mixing phenomenon on the infrared image is not analyzed, the display effect of the infrared image will be poor. Summary of the invention

[0004] In order to solve the above problems, the present invention provides an image enhancement method for resistor array infrared scene images based on image processing.

[0005] The image enhancement method of the resistor array infrared scene image based on image processing of the present invention adopts the following technical scheme: An embodiment of the present invention provides an image enhancement method for a resistor array infrared scene image based on image processing, the method comprising the following steps: Acquire an infrared image of the resistor array, wherein the infrared image includes a plurality of resistor areas and a background area; According to the gradient value of the resistance area, several initial abnormal resistance areas are screened; according to the distance between the initial abnormal resistance area and the adjacent resistance area, the deviation of the gradient direction and the area of ​​the adjacent resistance area, the degree of influence of each initial abnormal resistance area on each adjacent resistance area is obtained; according to the change of the gray value in the initial abnormal resistance area and the degree of influence, the possibility of each initial abnormal resistance area belonging to the abnormal resistance area is obtained, and the abnormal resistance area and the normal resistance area are screened; Cluster the pixels in the background area to obtain several clusters; obtain the possibility that each cluster belongs to the abnormal background sub-area based on the area ratio of the cluster in the background area and the grayscale difference between the cluster and the background area, and screen out the abnormal background sub-area and the normal background sub-area; According to the area of ​​the normal resistance area closest to the abnormal resistance area and the distance between the pixel point in the abnormal resistance area and the normal resistance area closest to the abnormal resistance area, the correction coefficient of each pixel point in each abnormal resistance area is obtained; according to the correction coefficient and the normal background sub-area, the grayscale values ​​of the pixels in the abnormal resistance area and the abnormal background sub-area are corrected respectively to obtain an enhanced infrared image.

[0006] Furthermore, after acquiring the infrared image of the resistor array, the method further includes: A resistor array image is obtained, and the resistor array image is input into a semantic segmentation network to obtain a plurality of first resistor regions; an area corresponding to each first resistor region in the resistor array image in the infrared image is used as a resistor region of the infrared image, and an area remaining in the infrared image except the resistor region is used as a background region of the infrared image.

[0007] Furthermore, the degree to which each initial abnormal resistance region is affected by each adjacent resistance region is obtained according to the distance between the initial abnormal resistance region and the adjacent resistance region, the deviation in the gradient direction, and the area of ​​the adjacent resistance region, including the following specific steps: For any initial abnormal resistance region, any adjacent resistance region of the initial abnormal resistance region is recorded as the first adjacent resistance region; the absolute value of the difference between the angle values ​​corresponding to the gradient directions of the initial abnormal resistance region and the first adjacent resistance region is taken as the deviation of the gradient direction between the first adjacent resistance region and the initial abnormal resistance region; the distance between the initial abnormal resistance region and the first adjacent resistance region, the deviation in the gradient direction, and the area of ​​the first adjacent resistance region are merged to obtain the degree of influence of the initial abnormal resistance region on the first adjacent resistance region; the distance between the initial abnormal resistance region and the first adjacent resistance region and the deviation in the gradient direction are inversely proportional to the degree of influence, and the area of ​​the first adjacent resistance region is directly proportional to the degree of influence.

[0008] Furthermore, the possibility of each initial abnormal resistance region belonging to the abnormal resistance region is obtained according to the change of the gray value in the initial abnormal resistance region and the degree of influence, and the specific steps include the following: For any initial abnormal resistance area, the variance of the grayscale values ​​of the pixels in the initial abnormal resistance area is used as the variation characteristic of the grayscale values ​​in the initial abnormal resistance area; the average value of the degree of influence of the initial abnormal resistance area by all adjacent resistance areas is obtained; the variation characteristic of the grayscale values ​​in the initial abnormal resistance area and the average value of the degree of influence of the initial abnormal resistance area by all adjacent resistance areas are merged to obtain the possibility that the initial abnormal resistance area belongs to the abnormal resistance area; the variation characteristic of the grayscale values ​​in the initial abnormal resistance area and the average value of the degree of influence of the initial abnormal resistance area by all adjacent resistance areas are directly proportional to the possibility that the initial abnormal resistance area belongs to the abnormal resistance area.

[0009] Furthermore, the screening out of abnormal resistance areas and normal resistance areas includes the following specific steps: A second threshold is preset, and the initial abnormal resistance region whose probability of belonging to the abnormal resistance region is greater than the second threshold is regarded as the abnormal resistance region, and vice versa, as the normal resistance region.

[0010] Furthermore, the possibility of each cluster belonging to the abnormal background sub-region is obtained according to the area ratio of the cluster in the background region and the grayscale performance difference between the cluster and the background region, and the specific steps include the following: For any cluster; the difference between the average grayscale value of the pixels in the cluster and the average grayscale value of the pixels in the background area is taken as the grayscale performance difference between the cluster and the background area; the area ratio of the cluster in the background area and the grayscale performance difference between the cluster and the background area are fused to obtain the possibility that the cluster belongs to the abnormal background sub-area; the area ratio of the cluster in the background area and the grayscale performance difference between the cluster and the background area are inversely proportional to the possibility that the cluster belongs to the abnormal background sub-area.

[0011] Furthermore, the correction coefficient of each pixel in each abnormal resistance region is obtained according to the area of ​​the normal resistance region closest to the abnormal resistance region and the distance between the pixel in the abnormal resistance region and the normal resistance region closest to the abnormal resistance region, and the specific steps include the following: For any abnormal resistance region, a normal resistance region closest to the abnormal resistance region is recorded as the first normal resistance region; for any pixel point in the abnormal resistance region, the distance between the pixel point in the abnormal resistance region and the central pixel point of the first normal resistance region is taken as the distance between the pixel point in the abnormal resistance region and the first normal resistance region; the area of ​​the first normal resistance region and the distance between the pixel point in the abnormal resistance region and the first normal resistance region are merged to obtain a correction coefficient of the pixel point in the abnormal resistance region; the area of ​​the first normal resistance region is directly proportional to the correction coefficient of the pixel point in the abnormal resistance region, and the distance between the pixel point in the abnormal resistance region and the first normal resistance region is inversely proportional to the correction coefficient of the pixel point in the abnormal resistance region; the correction coefficient is a normalized value.

[0012] Furthermore, the grayscale values ​​of pixels in the abnormal resistance region and the abnormal background subregion are corrected according to the correction coefficient and the normal background subregion to obtain an enhanced infrared image, which includes the following specific steps: The correction coefficient of each pixel in each abnormal resistance area is multiplied by the initial grayscale value of the pixel to obtain the corrected grayscale value of each pixel in each abnormal resistance area; the grayscale mean of the pixels in all normal background sub-areas is used as the corrected grayscale value of each pixel in the abnormal background sub-area; and the enhanced infrared image is obtained according to the corrected grayscale value.

[0013] Furthermore, clustering the pixels in the background area to obtain a number of clusters includes the following specific steps: K-means clustering is performed on the pixels in the background area, and the distance metric uses the absolute value of the difference in grayscale values ​​between pixels to obtain several clusters.

[0014] Furthermore, the method of screening a number of initial abnormal resistance regions according to the gradient value of the resistance region includes the following specific steps: A first threshold is preset, and a resistance region with a gradient value greater than the first threshold is taken as an initial abnormal resistance region, wherein the first threshold is 100.

[0015] The beneficial effects of the technical solution of the present invention are as follows: after acquiring the infrared image of the resistor array, the present invention acquires several resistor regions and background regions of the infrared image through the resistor array image, reduces interference between different regions, and enables better determination of abnormal regions in the subsequent process; acquires the degree of influence of each initial abnormal resistor region on each adjacent resistor region by analyzing the distance between the initial abnormal resistor region and the adjacent resistor region, the deviation in the gradient direction, and the area of ​​the adjacent resistor region, and then acquires the abnormal resistor region and the normal resistor region in combination with the change in the grayscale value in the initial abnormal resistor region, thereby improving the accuracy of determining the abnormal resistor region; acquires the possibility that each cluster belongs to the abnormal background sub-region by analyzing the area proportion of the cluster in the background region and the grayscale performance difference between the cluster and the background region, and screens out the abnormal background sub-region and the normal background sub-region; improves the accuracy of determining the abnormal resistor region and the abnormal background sub-region under the influence of temperature mixing, and finally acquires the correction coefficient of each pixel in each abnormal resistor region; and respectively corrects the grayscale values ​​of the pixels in the abnormal resistor region and the abnormal background sub-region according to the correction coefficient and the normal background sub-region, thereby acquiring the enhanced infrared image, reducing the influence of temperature mixing on the infrared image, and improving the display effect of the infrared image. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be 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.

[0017] Figure 1 A flowchart of the steps of an image enhancement method for a resistor array infrared scene image based on image processing provided by one embodiment of the present invention; Figure 2 A flowchart of obtaining an enhanced infrared image provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the image enhancement method of the resistor array infrared scene image based on image processing proposed by the present invention, its specific implementation method, structure, features and effects are described in detail as follows in combination 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.

[0019] 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.

[0020] The specific scheme of the image enhancement method of the resistor array infrared scene image based on image processing provided by the present invention is described in detail below with reference to the accompanying drawings.

[0021] See also Figure 1 and Figure 2 , which shows a flowchart of the steps of an image enhancement method for a resistor array infrared scene image based on image processing and a flowchart of obtaining an enhanced infrared image provided by an embodiment of the present invention, the method comprising the following steps: Step S001: Acquire an infrared image of a resistor array, wherein the infrared image includes a plurality of resistor areas and a background area.

[0022] It should be noted that the main purpose of this embodiment is to determine the abnormal resistance area and abnormal background sub-area caused by temperature mixing in the infrared image of the resistor array, so as to correct these two areas and obtain an enhanced infrared image. Before starting the analysis, first obtain data.

[0023] Specifically, obtaining an infrared image of a resistor array, wherein the infrared image includes a plurality of resistor regions and a background region, comprises the following steps: First, a resistor array image and an infrared image of the resistor array are acquired.

[0024] Secondly, several resistance areas and background areas of the infrared image are obtained according to the resistance array image.

[0025] Specifically, the resistor array image and the infrared image of the resistor array are obtained as follows: The resistor array image and the infrared image of the resistor array are obtained by an infrared camera; it should be noted that the infrared camera can simultaneously capture the resistor array image and the infrared image of the resistor array, wherein the resistor array image is an RGB image, the infrared image of the resistor array is a grayscale image, the resistor array image and the infrared image of the resistor array are the same size, and the resistor distribution positions in the two images are the same.

[0026] It should be noted that during the operation of the resistor array, the current passing through the resistor will increase the temperature of the resistor. The temperature increase in the resistor area will radiate other areas around the resistor, that is, the background area, and increase its temperature. Due to different temperature performance, temperature mixing will occur in a small number of areas, making the resistor area and background area in the infrared image behave abnormally. To facilitate subsequent analysis, it is necessary to obtain the resistor area and background area from the infrared image. Since the resistor array image is an RGB image, it will not be affected by temperature like the infrared image. Therefore, the resistor area and background area in the infrared image are obtained by combining the resistor array image.

[0027] Specifically, according to the resistor array image, several resistor areas and background areas of the infrared image are obtained, as follows: The resistor array image is input into the semantic segmentation network to obtain several first resistor areas. It should be noted that the semantic segmentation network used in this embodiment is the DeepLabV3 network, which is a well-known technology and the specific results and training methods of the network are not repeated here. The area corresponding to each first resistor area in the resistor array image in the infrared image is used as the resistor area of ​​the infrared image, and the remaining area in the infrared image except the resistor area is used as the background area of ​​the infrared image.

[0028] So far, several resistance areas and background areas of the infrared image are obtained.

[0029] Step S002, according to the gradient value of the resistance area, several initial abnormal resistance areas are screened; according to the distance between the initial abnormal resistance area and the adjacent resistance area, the deviation of the gradient direction and the area of ​​the adjacent resistance area, the influence degree of each initial abnormal resistance area on each adjacent resistance area is obtained; according to the change of the gray value in the initial abnormal resistance area and the influence degree, the possibility of each initial abnormal resistance area belonging to the abnormal resistance area is obtained, and the abnormal resistance area and the normal resistance area are screened out.

[0030] It should be noted that when temperature mixing occurs in the resistance area, there will be normal temperature performance and abnormal temperature performance in the resistance area. The reflection in the infrared image is that the grayscale changes in the resistance area are large. The gradient information can characterize the degree and direction of the grayscale change. Therefore, it is necessary to obtain the gradient value and gradient direction of the resistance area for subsequent analysis.

[0031] Specifically, according to the gradient value of the resistance area, a number of initial abnormal resistance areas are screened, including the following steps: First, the gradient value and gradient direction of each resistance region are obtained.

[0032] Secondly, several initial abnormal resistance areas are screened according to the gradient values ​​of the resistance areas.

[0033] Specifically, the gradient value and gradient direction of each resistance region are obtained as follows: For any resistor region, the central pixel of the resistor region is obtained, and the gradient value of the central pixel is used as the gradient value of the resistor region, and the gradient direction of the central pixel is used as the gradient direction of the resistor region. It should be noted that when temperature mixing occurs in the resistor region, the grayscale in the resistor region changes greatly, and the gradient change of the central pixel of the resistor region is also obvious. Therefore, the gradient information of the central pixel of the resistor region is used here to replace the gradient information of the resistor region.

[0034] It should be noted that the gradient value of the resistance area is obtained above. The size of the gradient value can reflect the size of the grayscale change. The initial abnormal resistance area can be screened out by the size of the gradient value of the resistance area. The initial abnormal resistance area is a possible abnormal resistance area, which reduces the amount of data that needs to be analyzed later.

[0035] Specifically, according to the gradient value of the resistance area, several initial abnormal resistance areas are screened, as follows: A first threshold is preset. This embodiment is described with the first threshold being 100. A resistance region with a gradient value greater than the first threshold is regarded as an initial abnormal resistance region. Otherwise, it is not regarded as an initial abnormal resistance region.

[0036] It should be noted that since the initial abnormal resistance area reflects the area formed by a resistor in the infrared image, the surrounding adjacent resistors will also affect the initial abnormal resistance area during the normal operation of the resistor array. If the influence of the surrounding adjacent resistors is not analyzed, it will interfere with the subsequent determination of the abnormal resistance area. Since the influence is mainly related to the area of ​​the adjacent resistance area, the distance between the resistance areas and the deviation of the gradient direction, if the area of ​​the adjacent resistance area is larger, it means that the resistance corresponding to the adjacent resistance area itself is larger. During the normal operation of the resistor array, the influence of its heating on the initial abnormal resistance area will be greater. If the distance between the adjacent resistance area and the initial abnormal resistance area is close, it means that the resistances corresponding to the two areas are also similar, and the influence of the heating of the adjacent resistance on the initial abnormal resistance area will also be greater. At the same time, if the gradient direction deviation of the adjacent resistance area and the initial abnormal resistance area is similar, it means that the temperature change direction of the two areas is relatively consistent, which can also reflect the influence of the heating of the adjacent resistance on the initial abnormal resistance area. Therefore, by analyzing the area of ​​the adjacent resistance area, the distance between the areas and the deviation of the gradient direction, the degree of influence of the initial abnormal resistance area on the surrounding adjacent resistance areas can be obtained.

[0037] Preferably, the degree to which each initial abnormal resistance region is affected by each adjacent resistance region is obtained according to the distance between the initial abnormal resistance region and the adjacent resistance region, the deviation in the gradient direction, and the area of ​​the adjacent resistance region, as follows: For any initial abnormal resistance region, any adjacent resistance region of the initial abnormal resistance region is recorded as the first adjacent resistance region; the absolute value of the difference between the angle values ​​corresponding to the gradient directions of the initial abnormal resistance region and the first adjacent resistance region is taken as the deviation of the gradient direction between the first adjacent resistance region and the initial abnormal resistance region; the distance between the initial abnormal resistance region and the first adjacent resistance region, the deviation in the gradient direction, and the area of ​​the first adjacent resistance region are merged to obtain the degree of influence of the initial abnormal resistance region on the first adjacent resistance region; the distance between the initial abnormal resistance region and the first adjacent resistance region and the deviation in the gradient direction are inversely proportional to the degree of influence, and the area of ​​the first adjacent resistance region is directly proportional to the degree of influence.

[0038] As a specific example, the specific method for obtaining the impact degree is as follows: The first Any adjacent resistance region of the initial abnormal resistance region is recorded as the first adjacent resistance region; it should be noted that the first adjacent resistance region may be the initial abnormal resistance region or may not be the initial abnormal resistance region, that is, the resistance region.

[0039] In the formula, is the number of pixels in the first adjacent resistor region; For the The distance between the center pixel of the initial abnormal resistance region and the first adjacent resistance region; For the The absolute value of the difference between the angle values ​​corresponding to the gradient direction of the initial abnormal resistance region and the first adjacent resistance region. It should be noted that the angle value corresponding to the gradient direction is 0° to the right of the horizontal direction and the positive direction is counterclockwise; is the first preset hyperparameter, the purpose of which is to prevent the denominator from being 0. to give a narrative; For the The degree to which an initial abnormal resistance region is affected by the first adjacent resistance region.

[0040] It should be noted that since the influence is mainly related to the area of ​​the adjacent resistance area, the distance between the resistance areas and the deviation of the gradient direction, the above formula obtains the degree of influence of the initial abnormal resistance area on the surrounding adjacent resistance areas by analyzing the area of ​​the adjacent resistance area, the distance between the areas and the deviation of the gradient direction. The larger it is, the larger the corresponding resistance of the first adjacent resistance area is, and the greater its influence on the initial abnormal resistance area is. The smaller it is, the closer the distance between the first adjacent resistance region and the initial abnormal resistance region is, and the greater the impact on the initial abnormal resistance region is; The smaller it is, the more it means that the gradient directions corresponding to the first adjacent resistance region and the initial abnormal resistance region are approximately the same, that is, the deviation of the gradient direction is smaller, and the influence of the first adjacent resistance region on the initial abnormal resistance region is greater.

[0041] It should be noted that the main purpose of this embodiment is to determine the abnormal resistance area and abnormal background sub-area caused by temperature mixing in the infrared image, so as to correct them and obtain an enhanced infrared image. When the temperature mixing phenomenon occurs in the resistance area, the grayscale changes in the resistance area are large, and the degree of influence by the surrounding adjacent resistance areas is also large. Therefore, by analyzing the grayscale changes of the initial abnormal resistance area and the degree of influence by the surrounding adjacent resistance areas, the possibility that the initial abnormal resistance area belongs to the abnormal resistance area can be obtained.

[0042] Specifically, according to the change and influence degree of the gray value in the initial abnormal resistance region, the possibility of each initial abnormal resistance region belonging to the abnormal resistance region is obtained, and the abnormal resistance region and the normal resistance region are screened out, including the steps of: First, according to the change and influence degree of the gray value in the initial abnormal resistance region, the possibility of each initial abnormal resistance region belonging to the abnormal resistance region is obtained.

[0043] Secondly, according to the possibility of belonging to the abnormal resistance area, several abnormal resistance areas and several normal resistance areas are screened out.

[0044] Preferably, the possibility that each initial abnormal resistance region belongs to the abnormal resistance region is obtained according to the change and influence degree of the gray value in the initial abnormal resistance region, as follows: For any initial abnormal resistance area, the variance of the grayscale values ​​of the pixels in the initial abnormal resistance area is used as the variation characteristic of the grayscale values ​​in the initial abnormal resistance area; the average value of the degree of influence of the initial abnormal resistance area by all adjacent resistance areas is obtained; the variation characteristic of the grayscale values ​​in the initial abnormal resistance area and the average value of the degree of influence of the initial abnormal resistance area by all adjacent resistance areas are merged to obtain the possibility that the initial abnormal resistance area belongs to the abnormal resistance area; the variation characteristic of the grayscale values ​​in the initial abnormal resistance area and the average value of the degree of influence of the initial abnormal resistance area by all adjacent resistance areas are directly proportional to the possibility that the initial abnormal resistance area belongs to the abnormal resistance area.

[0045] As a specific example, the specific method for obtaining the possibility of belonging to the abnormal resistance area is as follows: In the formula, For the The variance of the grayscale value of the pixel points in the initial abnormal resistance area; For the The average value of the degree to which an initial abnormal resistance area is affected by all adjacent resistance areas; is the hyperbolic tangent function, used for normalization; For the The possibility that the initial abnormal resistance area belongs to the abnormal resistance area.

[0046] It should be noted that, due to the temperature mixing phenomenon in the resistance area, the grayscale changes in the resistance area are large, and the degree of influence by the surrounding adjacent resistance areas is also large. Therefore, the above formula obtains the possibility that the initial abnormal resistance area belongs to the abnormal resistance area by analyzing the grayscale changes in the initial abnormal resistance area and the degree of influence by the surrounding adjacent resistance areas. The larger the The more chaotic the grayscale value distribution of the pixels in the initial abnormal resistance area is, the greater the grayscale change is. The greater the probability that the initial abnormal resistance area belongs to the abnormal resistance area, the greater the probability that the initial abnormal resistance area belongs to the abnormal resistance area. The larger the The initial abnormal resistance area is greatly affected by the surrounding adjacent resistance areas. The greater the probability that the initial abnormal resistance area belongs to the abnormal resistance area.

[0047] It should be noted that the above steps analyze the possibility that the initial abnormal resistance area belongs to the abnormal resistance area. By setting a suitable threshold, the abnormal resistance area and the normal resistance area can be screened out, so as to better correct the abnormal area in the future and obtain the enhanced infrared image.

[0048] Specifically, according to the possibility of belonging to the abnormal resistance area, several abnormal resistance areas and several normal resistance areas are screened out, as follows: A second threshold is preset. This embodiment is described with the second threshold being 0.7. An initial abnormal resistance region whose probability of belonging to the abnormal resistance region is greater than the second threshold is regarded as an abnormal resistance region, and vice versa, as a normal resistance region.

[0049] At this point, several abnormal resistance areas and several normal resistance areas are screened out.

[0050] Step S003, cluster the pixels in the background area to obtain several clusters; according to the area ratio of the cluster in the background area and the difference in grayscale performance between the cluster and the background area, obtain the possibility that each cluster belongs to the abnormal background sub-area, and screen out the abnormal background sub-area and the normal background sub-area.

[0051] It should be noted that the main purpose of this embodiment is to determine the abnormal resistance area and abnormal background sub-area caused by temperature mixing in the infrared image, so as to correct them and obtain an enhanced infrared image. The above analysis has analyzed the possibility that the initial abnormal resistance area belongs to the abnormal resistance area. Next, the background area is analyzed to obtain the abnormal background sub-area. Since there is a temperature mixing phenomenon in the background area, there are more normal areas in the background area and only a small number of abnormal areas. Therefore, in order to facilitate the subsequent better determination of the abnormal background sub-area, it is necessary to first cluster the background area and analyze the smaller local area.

[0052] Specifically, the pixels in the background area are clustered to obtain several clusters, as follows: K-means clustering is performed on the pixels in the background area, and the distance measurement adopts the absolute value of the difference in grayscale values ​​between the pixels to obtain several clusters; it should be noted that since there are many different grayscale values ​​in the background area, corresponding to the actual situation, there are many temperatures in the background area of ​​the resistor array. Considering comprehensively, the K value of K-means clustering in this embodiment is 5.

[0053] It should be noted that the background area is divided by clustering operation to obtain several clusters. Next, we can analyze whether these clusters belong to abnormal background sub-areas. When temperature mixing occurs in the background area, there are more normal areas and only a small number of abnormal areas. That is, if temperature mixing occurs in a cluster, the area of ​​the cluster accounts for a small proportion of the entire background area. At the same time, the grayscale performance of the pixels in the cluster is close to that of the entire background area. Therefore, by analyzing the proportion of clusters in the background area and the difference in grayscale performance between clusters and background areas, the possibility of clusters belonging to abnormal background sub-areas is obtained.

[0054] Specifically, according to the area ratio of the cluster in the background area and the grayscale performance difference between the cluster and the background area, the possibility of each cluster belonging to the abnormal background sub-area is obtained, and the abnormal background sub-area and the normal background sub-area are screened out, including the following steps: First, based on the area ratio of the cluster in the background area and the grayscale difference between the cluster and the background area, the possibility of each cluster belonging to the abnormal background sub-area is obtained.

[0055] Secondly, according to the possibility of belonging to the abnormal background sub-region, several abnormal background sub-regions and several normal background sub-regions are screened out.

[0056] Preferably, the possibility of each cluster belonging to the abnormal background sub-region is obtained according to the area ratio of the cluster in the background region and the grayscale performance difference between the cluster and the background region, as follows: For any cluster; the difference between the average grayscale value of the pixels in the cluster and the average grayscale value of the pixels in the background area is taken as the grayscale performance difference between the cluster and the background area; the area ratio of the cluster in the background area and the grayscale performance difference between the cluster and the background area are fused to obtain the possibility that the cluster belongs to the abnormal background sub-area; the area ratio of the cluster in the background area and the grayscale performance difference between the cluster and the background area are inversely proportional to the possibility that the cluster belongs to the abnormal background sub-area.

[0057] As a specific example, the specific method for obtaining the possibility of belonging to the abnormal background sub-region is as follows: In the formula, For the The proportion of the number of pixels in the cluster in the background area is specifically: The ratio of the number of pixels in a cluster to the number of pixels in the background area; For the The average gray value of pixels in a cluster; is the average gray value of pixels in the background area; To take the average value; is the second preset hyperparameter, the purpose of which is to prevent the denominator from being 0. to give a narrative; is the hyperbolic tangent function, used for normalization; For the The probability that a cluster belongs to the abnormal background sub-region.

[0058] It should be noted that when temperature mixing occurs in the background area, there are more normal areas in the background area and only a small number of abnormal areas. That is, if temperature mixing occurs in a cluster, the area of ​​the cluster accounts for a smaller proportion of the entire background area. At the same time, the grayscale performance of the pixels in the cluster is close to that of the entire background area. Therefore, the above formula obtains the possibility that the cluster belongs to the abnormal background sub-area by analyzing the proportion of the cluster in the background area and the difference in grayscale performance between the cluster and the background area. The smaller the size, the smaller the area of ​​the cluster in the background area, and the greater the possibility that the cluster belongs to the abnormal background sub-area. The smaller it is, the closer the average grayscale value of the cluster is to the average grayscale value of the background area, that is, the smaller the difference in grayscale performance between the cluster and the background area, and the greater the possibility that the cluster belongs to the abnormal background sub-area.

[0059] It should be noted that the above steps analyze the possibility that the cluster belongs to the abnormal background sub-region respectively. By setting a suitable threshold, the abnormal background sub-region and the normal background sub-region can be screened out, so that the abnormal region can be better corrected later to obtain the enhanced infrared image.

[0060] Specifically, according to the possibility of belonging to the abnormal background sub-region, several abnormal background sub-regions and several normal background sub-regions are screened out, as follows: The region where the cluster whose probability of belonging to the abnormal background sub-region is greater than the preset second threshold is located is regarded as the abnormal background sub-region, otherwise, it is regarded as the normal background sub-region.

[0061] At this point, several abnormal background sub-regions and several normal background sub-regions are screened out.

[0062] Step S004, obtaining a correction coefficient for each pixel in each abnormal resistance area according to the area of ​​the normal resistance area closest to the abnormal resistance area and the distance between the pixel in the abnormal resistance area and the normal resistance area closest to the abnormal resistance area; and correcting the grayscale values ​​of the pixels in the abnormal resistance area and the abnormal background sub-area according to the correction coefficient and the normal background sub-area, respectively, to obtain an enhanced infrared image.

[0063] It should be noted that the main purpose of this embodiment is to determine the abnormal resistance area and abnormal background sub-area caused by temperature mixing in the infrared image, so as to correct them and obtain an enhanced infrared image. The abnormal resistance area and the normal resistance area are obtained as above, and then the abnormal resistance area is corrected. Since the abnormal resistance area is mainly affected by the similar resistance, this embodiment is analyzed in combination with the normal resistance area closest to it. If the normal resistance area is larger than the abnormal resistance area, the greater the degree of influence on the abnormal resistance area, the greater the corresponding correction coefficient should be. At the same time, if the distance between the normal resistance area and the abnormal resistance area is closer, the greater the degree of influence on the abnormal resistance area, the greater the corresponding correction coefficient should be. The correction coefficient of each pixel in the abnormal resistance area is obtained by the distance between the normal resistance area and the abnormal resistance area and the area of ​​the normal resistance area.

[0064] Preferably, the correction coefficient of each pixel point in each abnormal resistance region is obtained according to the area of ​​the normal resistance region closest to the abnormal resistance region and the distance between the pixel point in the abnormal resistance region and the normal resistance region closest to the abnormal resistance region, as follows: For any abnormal resistance region, a normal resistance region closest to the abnormal resistance region is recorded as the first normal resistance region; for any pixel point in the abnormal resistance region, the distance between the pixel point in the abnormal resistance region and the central pixel point of the first normal resistance region is taken as the distance between the pixel point in the abnormal resistance region and the first normal resistance region; the area of ​​the first normal resistance region and the distance between the pixel point in the abnormal resistance region and the first normal resistance region are merged to obtain a correction coefficient of the pixel point in the abnormal resistance region; the area of ​​the first normal resistance region is directly proportional to the correction coefficient of the pixel point in the abnormal resistance region, and the distance between the pixel point in the abnormal resistance region and the first normal resistance region is inversely proportional to the correction coefficient of the pixel point in the abnormal resistance region; the correction coefficient is a normalized value.

[0065] As a specific example, the specific method for obtaining the correction coefficient is as follows: Will be with The normal resistance region closest to the abnormal resistance region is recorded as the first normal resistance region.

[0066] In the formula, is the number of pixels in the first normal resistance area; For the In the abnormal resistance area The distance between a pixel point and the central pixel point of the first normal resistance area; is a linear normalization function; For the In the abnormal resistance area Correction factor for each pixel.

[0067] It should be noted that since the abnormal resistance area is mainly affected by the adjacent resistance, the above formula is analyzed in combination with the nearest normal resistance area. The larger the value, the larger the area of ​​the first normal resistance region is. The greater the influence of an abnormal resistance area, the larger the corresponding correction coefficient should be; The smaller the value, the closer the first normal resistance area is to the second The closer the distance between the two abnormal resistance areas is, the closer the first normal resistance area is to the second The greater the impact of an abnormal resistance area, the larger the corresponding correction coefficient should be.

[0068] It should be noted that the correction coefficient of each pixel in the abnormal resistance area and the normal background sub-area are obtained above. The grayscale value of the pixel in the abnormal background sub-area can be corrected by the correction coefficient, and the grayscale value of the pixel in the abnormal background sub-area can be corrected by the grayscale value of the pixel in the normal background sub-area, thereby obtaining an enhanced infrared image.

[0069] Specifically, according to the correction coefficient and the normal background sub-region, the grayscale values ​​of the pixels in the abnormal resistance region and the abnormal background sub-region are corrected respectively to obtain the enhanced infrared image, as follows: The correction coefficient of each pixel in each abnormal resistance area is multiplied by the initial grayscale value of the pixel to obtain the corrected grayscale value of each pixel in each abnormal resistance area; the grayscale mean of the pixels in all normal background sub-areas is used as the corrected grayscale value of each pixel in the abnormal background sub-area; and the enhanced infrared image is obtained according to the corrected grayscale value.

[0070] It should be noted that the correction coefficient of each pixel in the abnormal resistance area is obtained above. By correcting the initial grayscale value of the pixel through the correction coefficient, the influence of the temperature mixing phenomenon can be reduced and the display effect of the resistance area can be enhanced. Since the background area is not a critical area, this embodiment uses the grayscale mean of the pixel in the normal background sub-area as the corrected grayscale value of each pixel in the abnormal background sub-area, and finally obtains the enhanced infrared image.

[0071] Through the above steps, the image enhancement method of the resistor array infrared scene image based on image processing is completed.

[0072] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An image enhancement method for a resistor array infrared scene image based on image processing, characterized in that: The method comprises the following steps: Acquire an infrared image of the resistor array, wherein the infrared image includes a plurality of resistor regions and a background region; According to the gradient value of the resistance area, several initial abnormal resistance areas are screened; according to the distance between the initial abnormal resistance area and the adjacent resistance area, the deviation of the gradient direction and the area of ​​the adjacent resistance area, the degree of influence of each initial abnormal resistance area on each adjacent resistance area is obtained; according to the change of the gray value in the initial abnormal resistance area and the degree of influence, the possibility of each initial abnormal resistance area belonging to the abnormal resistance area is obtained, and the abnormal resistance area and the normal resistance area are screened; Cluster the pixels in the background area to obtain several clusters; obtain the possibility that each cluster belongs to the abnormal background sub-area based on the area ratio of the cluster in the background area and the grayscale difference between the cluster and the background area, and screen out the abnormal background sub-area and the normal background sub-area; According to the area of ​​the normal resistance area closest to the abnormal resistance area and the distance between the pixel point in the abnormal resistance area and the normal resistance area closest to the abnormal resistance area, the correction coefficient of each pixel point in each abnormal resistance area is obtained; according to the correction coefficient and the normal background sub-area, the grayscale values ​​of the pixels in the abnormal resistance area and the abnormal background sub-area are corrected respectively to obtain an enhanced infrared image.

2. The image enhancement method of the resistor array infrared scene image based on image processing according to claim 1 is characterized in that: After acquiring the infrared image of the resistor array, the method further includes: A resistor array image is obtained, and the resistor array image is input into a semantic segmentation network to obtain a plurality of first resistor regions; an area corresponding to each first resistor region in the resistor array image in the infrared image is used as a resistor region of the infrared image, and an area remaining in the infrared image except the resistor region is used as a background region of the infrared image.

3. The image enhancement method of the resistor array infrared scene image based on image processing according to claim 1 is characterized in that: The method of obtaining the degree of influence of each initial abnormal resistance region on each adjacent resistance region according to the distance between the initial abnormal resistance region and the adjacent resistance region, the deviation of the gradient direction and the area of ​​the adjacent resistance region includes the following specific steps: For any initial abnormal resistance region, any adjacent resistance region of the initial abnormal resistance region is recorded as a first adjacent resistance region; the absolute value of the difference between the angle values ​​corresponding to the gradient directions of the initial abnormal resistance region and the first adjacent resistance region is taken as the deviation of the gradient direction of the first adjacent resistance region from the initial abnormal resistance region; The distance between the initial abnormal resistance region and the first adjacent resistance region, the deviation of the gradient direction, and the area of ​​the first adjacent resistance region are integrated to obtain the degree of influence of the initial abnormal resistance region on the first adjacent resistance region; The distance between the initial abnormal resistance region and the first adjacent resistance region and the deviation of the gradient direction are inversely proportional to the degree of influence, and the area of ​​the first adjacent resistance region is directly proportional to the degree of influence.

4. The image enhancement method of the resistor array infrared scene image based on image processing according to claim 1 is characterized in that: The method of obtaining the possibility that each initial abnormal resistance region belongs to the abnormal resistance region according to the change of the gray value in the initial abnormal resistance region and the influence degree includes the following specific steps: For any initial abnormal resistance area, the variance of the grayscale values ​​of the pixels in the initial abnormal resistance area is used as the variation characteristic of the grayscale values ​​in the initial abnormal resistance area; the average value of the degree of influence of the initial abnormal resistance area by all adjacent resistance areas is obtained; the variation characteristic of the grayscale values ​​in the initial abnormal resistance area and the average value of the degree of influence of the initial abnormal resistance area by all adjacent resistance areas are merged to obtain the possibility that the initial abnormal resistance area belongs to the abnormal resistance area; the variation characteristic of the grayscale values ​​in the initial abnormal resistance area and the average value of the degree of influence of the initial abnormal resistance area by all adjacent resistance areas are directly proportional to the possibility that the initial abnormal resistance area belongs to the abnormal resistance area.

5. The image enhancement method of the resistor array infrared scene image based on image processing according to claim 1 is characterized in that: The specific steps of screening out the abnormal resistance area and the normal resistance area are as follows: A second threshold is preset, and the initial abnormal resistance region whose probability of belonging to the abnormal resistance region is greater than the second threshold is regarded as the abnormal resistance region, and vice versa, as the normal resistance region.

6. The image enhancement method of the resistor array infrared scene image based on image processing according to claim 1, characterized in that: The specific steps of obtaining the possibility that each cluster belongs to the abnormal background sub-region according to the area ratio of the cluster in the background region and the grayscale performance difference between the cluster and the background region are as follows: For any cluster; the difference between the average grayscale value of the pixels in the cluster and the average grayscale value of the pixels in the background area is taken as the grayscale performance difference between the cluster and the background area; the area ratio of the cluster in the background area and the grayscale performance difference between the cluster and the background area are fused to obtain the possibility that the cluster belongs to the abnormal background sub-area; the area ratio of the cluster in the background area and the grayscale performance difference between the cluster and the background area are inversely proportional to the possibility that the cluster belongs to the abnormal background sub-area.

7. The image enhancement method of the resistor array infrared scene image based on image processing according to claim 1, characterized in that: The method of obtaining the correction coefficient of each pixel point in each abnormal resistance region according to the area of ​​the normal resistance region closest to the abnormal resistance region and the distance between the pixel point in the abnormal resistance region and the normal resistance region closest to the abnormal resistance region comprises the following specific steps: For any abnormal resistance region, a normal resistance region closest to the abnormal resistance region is recorded as the first normal resistance region; for any pixel point in the abnormal resistance region, the distance between the pixel point in the abnormal resistance region and the central pixel point of the first normal resistance region is taken as the distance between the pixel point in the abnormal resistance region and the first normal resistance region; the area of ​​the first normal resistance region and the distance between the pixel point in the abnormal resistance region and the first normal resistance region are merged to obtain a correction coefficient of the pixel point in the abnormal resistance region; The area of ​​the first normal resistance region is directly proportional to the correction coefficient of the pixel point in the abnormal resistance region, and the distance between the pixel point in the abnormal resistance region and the first normal resistance region is inversely proportional to the correction coefficient of the pixel point in the abnormal resistance region; the correction coefficient is a normalized value.

8. The image enhancement method of resistor array infrared scene image based on image processing according to claim 1, characterized in that: The grayscale values ​​of pixels in the abnormal resistance region and the abnormal background subregion are corrected according to the correction coefficient and the normal background subregion to obtain an enhanced infrared image, and the specific steps include the following: The correction coefficient of each pixel in each abnormal resistance area is multiplied by the initial grayscale value of the pixel to obtain the corrected grayscale value of each pixel in each abnormal resistance area; the grayscale mean of the pixels in all normal background sub-areas is used as the corrected grayscale value of each pixel in the abnormal background sub-area; and the enhanced infrared image is obtained according to the corrected grayscale value.

9. The image enhancement method of resistor array infrared scene image based on image processing according to claim 1, characterized in that: The pixel points in the background area are clustered to obtain a number of clusters, and the specific steps include the following: K-means clustering is performed on the pixels in the background area, and the distance metric uses the absolute value of the difference in grayscale values ​​between pixels to obtain several clusters.

10. The image enhancement method of resistor array infrared scene image based on image processing according to claim 1, characterized in that: The specific steps of screening a number of initial abnormal resistance areas according to the gradient value of the resistance area are as follows: A first threshold is preset, and a resistance region with a gradient value greater than the first threshold is taken as an initial abnormal resistance region, wherein the first threshold is 100.

Images