Resistor array infrared imaging control method and system based on transfer learning

Abstract

The present invention relates to the field of image data processing technology, and in particular to a resistor array infrared imaging control method and system based on transfer learning, including: using a resistor array to obtain an infrared image, each resistor unit in the resistor array corresponds to a range in the infrared image, each pixel point in the infrared image corresponds to an infrared radiation data value, according to the number of pixels in the range corresponding to the resistor unit on the infrared image and the infrared radiation data corresponding to the pixel point, and the distance between the center points of the corresponding ranges of adjacent resistor units, the thermal radiation area and thermal crosstalk area of ​​each resistor unit are determined, according to the area of ​​the thermal crosstalk area, the degree of influence of the thermal crosstalk on the infrared image is determined, and the infrared imaging of the resistor array is controlled according to the degree of influence. The present invention analyzes the infrared image data generated based on transfer learning, generates a high-quality resistor array infrared image by controlling the current size, and reduces the influence of thermal crosstalk on the infrared image.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and in particular to a resistor array infrared imaging control method and system based on transfer learning. Background Art

[0002] Resistor array infrared imaging technology is a technology that generates infrared radiation by controlling the current in a resistor array, thereby forming an infrared image. The resistor array is composed of multiple resistor units, each of which can independently control its current value, thereby generating an infrared image on the array. It has a wide range of applications in many fields, such as infrared target simulators, infrared dual-band guidance systems, etc., especially in the generation of semi-physical simulation targets and environmental images. This technology can generate high-quality infrared images and provide strong support for simulation tests.

[0003] In the process of controlling the current in the resistor array to generate infrared radiation, different amounts of heat will be generated at the resistor when different degrees of current flow through the resistor. This heat will affect each other between the resistors, resulting in thermal crosstalk between adjacent resistors. That is, the heat generated by one resistor will be transferred to the adjacent resistor. This thermal crosstalk phenomenon will reduce the contrast and resolution of the imaging. Summary of the invention

[0004] The present invention provides a resistor array infrared imaging control method and system based on transfer learning to solve the existing problems.

[0005] The resistor array infrared imaging control method and system based on transfer learning of the present invention adopt the following technical solutions:

[0006] An embodiment of the present invention provides a resistor array infrared imaging control method based on transfer learning, the method comprising the following steps:

[0007] Acquiring an infrared image using a resistor array, wherein each resistor unit in the resistor array corresponds to a range in the infrared image, and each pixel point in the infrared image corresponds to an infrared radiation data value;

[0008] Determine the infrared radiation performance of each resistor unit according to the number of pixels within the corresponding range of the resistor unit on the infrared image and the infrared radiation data value corresponding to the pixel;

[0009] Determine the heat radiation area of ​​each resistor unit according to the change of the radiation data within the corresponding range of the resistor unit on the infrared image, the infrared radiation performance of each resistor unit and the distance between the center points of the corresponding ranges of adjacent resistor units;

[0010] The thermal crosstalk area of ​​each resistor unit is determined based on the difference between the thermal radiation data between adjacent pixels in the thermal radiation area of ​​the resistor unit, and the influence of the thermal crosstalk phenomenon of the resistor unit on the infrared image is determined based on the difference in the number of pixels and the corresponding thermal radiation values ​​of the pixels in the thermal crosstalk area of ​​each resistor unit, the area of ​​the thermal radiation area of ​​the resistor unit and the area of ​​the entire infrared image, and the infrared imaging of the resistor array is controlled according to the influence degree.

[0011] Furthermore, the specific method of determining the infrared radiation performance of each resistor unit includes:

[0012] Calculate the The sum of the infrared radiation data values ​​of all pixels in the range corresponding to the resistor unit is recorded as Infrared radiation performance of a resistor unit.

[0013] Furthermore, the determination of the heat radiation area of ​​each resistor unit includes a specific calculation method as follows:

[0014] Determine The heat radiation area boundaries of the four sides of the range corresponding to the resistance unit are recorded as the closed area surrounded by the heat radiation area boundaries of the four sides. The heat radiation area of ​​each resistor unit.

[0015] Furthermore, the determination The heat radiation area boundaries of the four sides of the range corresponding to the resistance unit include the following specific methods:

[0016] Calculate the The resistance unit corresponds to the The product of the ratio of the heat radiation area of ​​the edge between adjacent resistor units and the first distance is recorded as the second distance. The resistance unit corresponds to the The edge, order The edge and The shortest distance between the centers of the ranges corresponding to the resistor units is the second distance. The resistance unit corresponds to the The boundary of the radiation area corresponding to the strip edge;

[0017] According to The method for obtaining the boundary of the radiation area corresponding to the edge is used to determine the The thermal radiation area boundaries of the other three sides of the range corresponding to the resistor unit.

[0018] Furthermore, the The resistance unit corresponds to the The specific method of determining the ratio of the heat radiation area of ​​the edge to the area between adjacent resistance units and the first distance includes:

[0019] The first The resistance unit with the closest distance between the center point of the edge and the center point of the corresponding range of the resistance unit is recorded as The adjacent resistor units of the edge are constructed The resistor unit and The data sequence of infrared radiation data values ​​of the pixel points on the straight line between the center points of the corresponding range of the adjacent resistance units of the strip edge , get the data sequence The first-order difference sequence of ;

[0020] Calculate the data sequence of infrared radiation data values The number of negative numbers in the first-order difference sequence of The ratio of the number of all data in is recorded as the first ratio, and the The resistor unit and The distance between the center points of the corresponding range of adjacent resistance units on the edge is recorded as the first distance, and the first distance is calculated. The ratio of the infrared radiation performance of the resistor unit to the first distance is recorded as the second ratio, and the second ratio is normalized, and the product of the first ratio and the normalized second ratio is recorded as the first The resistance unit corresponds to the The ratio of the heat radiation area of ​​the strip edge to the area between adjacent resistor units.

[0021] Furthermore, the specific method of determining the thermal crosstalk area of ​​each resistor unit includes:

[0022] Determine The thermal crosstalk area boundaries of the four sides of the thermal radiation area of ​​the resistor unit are recorded as the area between the closed rectangular area surrounded by the thermal crosstalk area boundaries of all sides and the thermal radiation area. The thermal crosstalk area of ​​each resistor unit.

[0023] Furthermore, the determination The specific method of defining the thermal crosstalk area boundaries of the four sides of the thermal radiation area of ​​the resistor unit is as follows:

[0024] In the The upper boundary of the heat radiation area of ​​the first resistor unit is The center of the heat radiation area of ​​the resistor unit is traversed pixel by pixel, and the Pixels and The absolute value of the thermal radiation data difference of the pixel point is taken as the The judgment value of the pixel point is preset to the first threshold , taking the pixel points whose judgment values ​​are greater than the preset first threshold as the segmentation points, and taking the last segmentation point as the target point;

[0025] The first The upper boundary of the heat radiation area of ​​each resistor unit is moved downward in parallel to the target point, and the thermal crosstalk area boundary corresponding to the upper boundary is obtained;

[0026] According to the method of obtaining the thermal crosstalk area boundary corresponding to the upper boundary, determine the The other boundaries of the heat radiation area of ​​the resistor unit correspond to the thermal crosstalk area boundaries.

[0027] Furthermore, the determination of the influence degree of the thermal crosstalk phenomenon of the resistor unit on the infrared image includes the following specific methods:

[0028] Calculate the The product of the number of all pixels in the thermal crosstalk area of ​​the resistor unit and the variance of the infrared radiation data of all pixels is recorded as the first product. The ratio of the thermal radiation area of ​​the resistor unit to the area of ​​the entire infrared image is recorded as The heat radiation area ratio of each resistor unit is calculated by multiplying the first product and the The product of the heat radiation area proportions of the resistor units is taken as the The degree of influence of the thermal crosstalk area of ​​each resistor unit on the overall infrared image.

[0029] Furthermore, the specific method of controlling the infrared imaging of the resistor array according to the degree of influence includes:

[0030] use The normalization function converts the The influence of the thermal crosstalk area of ​​each resistor unit on the overall infrared image is normalized to Within the range, preset the second threshold , when the normalized influence At that time, The current of the resistor unit remains unchanged. When the normalized influence When The current of each resistor unit is gradually reduced until the first adjustment current appears and the final normalized impact degree When it ends.

[0031] A resistor array infrared imaging control system based on transfer learning comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any step of the resistor array infrared imaging control method based on transfer learning is implemented.

[0032] The beneficial effects of the technical solution of the present invention are as follows: according to the number of pixels in the corresponding range of the resistor unit on the infrared image and the infrared radiation data value corresponding to the pixel, the infrared radiation performance of each resistor unit is determined, which is used to quantify the infrared radiation characteristics of each resistor unit and provide basic data for the subsequent determination of the thermal radiation area; according to the change of the radiation data of the resistor unit in the corresponding range on the infrared image, the infrared radiation performance of each resistor unit and the distance between the center points of the corresponding range of the adjacent resistor units, the thermal radiation area of ​​each resistor unit is determined, the contour of the thermal radiation area of ​​each resistor unit is accurately determined, and the thermal crosstalk area is further determined according to the thermal radiation area; according to the difference between the thermal radiation data between the adjacent pixels in the thermal radiation area of ​​the resistor unit, the thermal crosstalk area of ​​each resistor unit is determined, and according to the difference between the number of pixels and the thermal radiation value corresponding to the pixel in the thermal crosstalk area of ​​each resistor unit, the area of ​​the thermal radiation area of ​​the resistor unit and the area of ​​the entire infrared image, the degree of influence of the thermal crosstalk phenomenon of the resistor unit on the infrared image is determined, and the infrared imaging of the resistor array is controlled according to the degree of influence, and the clarity of the infrared image and the overall performance of the system are improved by reducing the influence of the thermal crosstalk on the infrared image, thereby improving the application effect and reliability of the infrared imaging system. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] 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.

[0034] Figure 1 It is a flow chart of the steps of the resistor array infrared imaging control method based on transfer learning of the present invention;

[0035] Figure 2 This is an example diagram of the thermal crosstalk area of ​​the resistor unit of the present invention. DETAILED DESCRIPTION

[0036] 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 specific implementation, structure, features and effects of the resistor array infrared imaging control method and system based on transfer learning proposed by the present invention 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.

[0037] 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.

[0038] The specific scheme of the resistor array infrared imaging control method based on transfer learning provided by the present invention is described in detail below with reference to the accompanying drawings.

[0039] See also Figure 1 , which shows a flow chart of a resistor array infrared imaging control method based on transfer learning provided by an embodiment of the present invention, the method comprising the following steps:

[0040] Step S001: using a resistor array to acquire an infrared image, wherein each resistor unit in the resistor array corresponds to a range in the infrared image; and each pixel point of the infrared image corresponds to an infrared radiation data value.

[0041] In order to implement the resistor array infrared imaging control method based on transfer learning proposed in this embodiment, it is first necessary to obtain the resistor array infrared image. The specific process is as follows:

[0042] Collect and prepare the source domain dataset required for resistor array infrared imaging. The source domain dataset can be a dataset of other infrared imaging tasks for pre-training deep learning models.

[0043] A deep learning model is pre-trained using the source domain dataset, and the pre-trained model is migrated to the resistor array infrared imaging task. The migrated model is fine-tuned to adapt to the new task requirements to obtain the adjusted model.

[0044] By inputting the desired infrared image features or labels, the model can calculate the corresponding resistor array current distribution, thereby generating the required infrared image, where each pixel of the infrared image corresponds to an infrared radiation data value, and each resistor unit in the resistor array corresponds to a range in the infrared image.

[0045] It should be noted that generating infrared images by training a model based on a source domain dataset is a prior art and will not be described in detail here.

[0046] At this point, the required resistor array infrared image is obtained through the above method.

[0047] Step S002: determining the infrared radiation performance of each resistor unit according to the number of pixels within the corresponding range of the resistor unit on the infrared image and the infrared radiation data values ​​corresponding to the pixels.

[0048] It should be noted that since different currents generate different amounts of heat when flowing through resistors, different resistor units have different infrared radiation performances on the overall infrared image, and there is mutual influence of infrared radiation between adjacent resistors, which makes the infrared radiation image of the resistor array abnormal. Therefore, it is necessary to obtain the infrared radiation performance of each resistor and divide the resistor array infrared image into resistor unit areas according to the infrared radiation performance of each resistor.

[0049] Get the position of each resistor unit in the resistor array and the corresponding range in the infrared image. The range corresponding to each resistor unit in the infrared image is a rectangular area. Determine the number of pixels in the corresponding range of each resistor unit on the infrared image and the infrared radiation data value corresponding to each pixel. Calculate the The sum of the infrared radiation data values ​​of all pixels in the range corresponding to the resistor unit is recorded as Infrared radiation performance of a resistor unit.

[0050] No. The calculation formula for the infrared radiation performance of a resistor unit can be expressed as:

[0051]

[0052] In the formula, Indicates Infrared radiation performance of each resistor unit; Indicates The number of pixels within the range corresponding to the resistor unit can be used to represent the area of ​​the range corresponding to the resistor unit; Indicates The resistance unit corresponds to the The infrared radiation data value of each pixel.

[0053] It should be noted that for the resistor unit, when different currents flow through it, different amounts of heat are generated. When the heat generated by the current passing through the resistor unit is greater and the area of ​​the resistor is larger, the infrared radiation of the resistor unit is stronger. The larger the value of .

[0054] So far, the infrared radiation performance of each resistor unit is obtained through the above method.

[0055] Step S003: determining the heat radiation area of ​​each resistor unit according to the change of the radiation data in the corresponding range of the resistor unit on the infrared image, the infrared radiation performance of each resistor unit and the distance between the center points of the corresponding ranges of adjacent resistor units.

[0056] It should be noted that due to the thermal crosstalk phenomenon between the resistor units, there is a part of the area between adjacent resistor units on the generated resistor array infrared image where the two resistors influence each other. It is necessary to divide the resistor array infrared image into resistor unit areas according to the infrared radiation performance of the resistor units to determine the thermal radiation area of ​​each resistor unit.

[0057] First The resistance unit corresponds to the For example, take the first The resistance unit with the closest distance between the center point of the edge and the center point of the corresponding range of the resistance unit is recorded as The adjacent resistor units of the edge are constructed The resistor unit and The data sequence of infrared radiation data values ​​of the pixel points on the straight line between the center points of the corresponding range of the adjacent resistance units of the strip edge , get the data sequence The first-order difference sequence of is used to count the number of negative numbers in the difference sequence.

[0058] It should be noted that due to the existence of current flowing through the resistance unit, the infrared radiation data of the center of each resistance unit is basically consistent, that is, in the infrared image, the infrared radiation data value of each pixel representing the center point of the resistance unit is the same. As the distance from the center point increases, the radiation gradually decreases. Therefore, the radiation data sequence between the center points of two adjacent resistance units gradually decreases when moving away from the first value, becomes less than the first value, and then gradually increases, and gradually approaches the last value when approaching the last value.

[0059] Calculate the data sequence of infrared radiation data values The number of negative numbers in the first-order difference sequence of The ratio of the number of all data in is recorded as the first ratio, and the The resistor unit and The distance between the center points of the corresponding range of adjacent resistance units on the edge is recorded as the first distance, and the first distance is calculated. The ratio of the infrared radiation performance of the resistor unit to the first distance is recorded as the second ratio, and the second ratio is normalized, and the product of the first ratio and the normalized second ratio is recorded as the first The resistance unit corresponds to the The ratio of the heat radiation area of ​​the strip edge to the area between adjacent resistor units.

[0060] No. The resistance unit corresponds to the The calculation formula for the ratio of the heat radiation area of ​​the strip edge to the area between adjacent resistor units can be expressed as:

[0061]

[0062] In the formula, Indicates The resistance unit corresponds to the The ratio of the heat radiation area of ​​the strip edge to the area between adjacent resistor units; represents the first ratio, Indicates The number of negative numbers in the first-order difference sequence of the radiation data difference sequence of each resistor unit; Indicates The number of all data in the resistance unit radiation data difference sequence; is the second ratio; Indicates Infrared radiation performance of each resistor unit; is the first distance, indicating the The resistor unit and The distance between the center points of the corresponding ranges of adjacent resistance units of the strip edge; Represents the normalization function.

[0063] It should be noted that for The more resistance units there are, the stronger the infrared radiation performance is, and the smaller the distance between adjacent resistance units is, that is, When the value of is large, the heat radiation area of ​​the resistor unit accounts for a larger proportion of the area between adjacent resistor unit areas.

[0064] Calculate the The resistance unit corresponds to the The product of the ratio of the heat radiation area of ​​the edge between adjacent resistor units and the first distance is recorded as the second distance. The resistance unit corresponds to the The edge, order The edge and The shortest distance between the centers of the ranges corresponding to the resistor units is the second distance. The resistance unit corresponds to the The edge corresponds to the boundary of the radiation area.

[0065] According to The method for obtaining the boundary of the radiation area corresponding to the edge is used to determine the The heat radiation area boundaries of the other three sides of the range corresponding to the resistor unit are the closed area surrounded by the heat radiation area boundaries corresponding to all sides, which is recorded as the The heat radiation area of ​​each resistor unit.

[0066] It should be noted that when a certain side of a resistance unit has no adjacent resistance unit, it will not be moved.

[0067] So far, the heat radiation area of ​​each resistor unit is obtained through the above steps.

[0068] Step S004: Determine the thermal crosstalk area of ​​each resistor unit based on the difference between thermal radiation data between adjacent pixels in the thermal radiation area of ​​the resistor unit, and determine the degree of influence of the thermal crosstalk phenomenon of the resistor unit on the infrared image based on the difference in the number of pixels and the corresponding thermal radiation values ​​of the pixels in the thermal crosstalk area of ​​each resistor unit, the area of ​​the thermal radiation area of ​​the resistor unit and the area of ​​the entire infrared image, and control the infrared imaging of the resistor array based on the degree of influence.

[0069] It should be noted that the thermal crosstalk phenomenon between resistors generally occurs in the area where the heat transfer between two resistor units is adjacent, that is, the adjacent part of the two areas after the above-mentioned area division. In order to determine the impact of the thermal crosstalk phenomenon on the infrared image, it is necessary to analyze the image information displayed by the adjacent part of the area edge.

[0070] In the The upper boundary of the heat radiation area of ​​the first resistor unit is The center of the heat radiation area of ​​the resistor unit is traversed pixel by pixel, and the Pixels and The absolute value of the thermal radiation data difference of the pixel point is taken as the The judgment value of the pixel point is preset to the first threshold , the pixel points whose judgment values ​​are greater than the preset first threshold are used as segmentation points, and the last segmentation point is used as the target point.

[0071] It should be noted that since there will be a thermal crosstalk area near the edge of the resistor thermal radiation area, the difference in thermal radiation data between adjacent pixels in the same row will be unstable. Therefore, when the difference in thermal radiation data between adjacent pixels in the same row changes little, it is considered that there is no thermal crosstalk.

[0072] It should be noted that, in this embodiment, the first threshold The value of is 3, which can be adjusted according to actual conditions and is not specifically limited in this embodiment.

[0073] The first The upper boundary of the heat radiation area of ​​each resistor unit is moved downward in parallel to the target point to obtain the thermal crosstalk area boundary corresponding to the upper boundary.

[0074] According to the method of obtaining the thermal crosstalk area boundary corresponding to the upper boundary, determine the The thermal crosstalk area boundaries corresponding to the other boundaries of the thermal radiation area of ​​the resistor unit are the area between the closed rectangular area surrounded by the thermal crosstalk area boundaries of all sides and the thermal radiation area, which is recorded as The thermal crosstalk area of ​​each resistor unit.

[0075] Figure 2 An example diagram of the thermal crosstalk area, where the black dotted line is the thermal crosstalk area boundary and the gray area is the thermal crosstalk area.

[0076] According to the above steps, the thermal crosstalk area of ​​each resistor unit is obtained.

[0077] Calculate the The product of the number of all pixels in the thermal crosstalk area of ​​the resistor unit and the variance of the infrared radiation data of all pixels is recorded as the first product. The ratio of the thermal radiation area of ​​the resistor unit to the area of ​​the entire infrared image is recorded as The heat radiation area ratio of each resistor unit is calculated by multiplying the first product and the The product of the heat radiation area proportions of the resistor units is taken as the The degree of influence of the thermal crosstalk area of ​​each resistor unit on the overall infrared image.

[0078] No. The calculation formula of the influence of the thermal crosstalk area of ​​each resistor unit on the overall infrared image can be expressed as:

[0079]

[0080] In the formula, Indicates The degree of influence of the thermal crosstalk area of ​​each resistor unit on the overall infrared image; is the first product; Indicates The number of all pixels in the thermal crosstalk area of ​​a resistor unit; Indicates The variance of the infrared radiation data values ​​of all pixels in the thermal crosstalk area of ​​the resistor unit; Indicates The proportion of heat radiation area of ​​each resistor unit; Indicates The heat radiation area of ​​each resistor unit; Represents the area of ​​the entire infrared image.

[0081] It should be noted that If it is larger, the The thermal crosstalk area of ​​each resistor unit is large, and the infrared radiation data in the thermal crosstalk area is quite different. When the heat radiation area of ​​a resistor unit accounts for a large proportion, it means that the thermal crosstalk area of ​​the resistor unit has a greater impact on the overall infrared image.

[0082] Repeat the above steps to obtain the influence of the thermal crosstalk area of ​​each resistor unit on the overall infrared image.

[0083] use The normalization function converts the The influence of the thermal crosstalk area of ​​each resistor unit on the overall infrared image is normalized to Within the range, preset the second threshold , when the normalized influence When , it means that the thermal crosstalk area has a greater impact on the overall image, making the infrared imaging effect of the resistor array poor. When the normalized impact degree When the thermal crosstalk area has little impact on the overall image, The current through the resistor unit remains unchanged.

[0084] So when the normalized impact When The current of each resistor unit is reduced, so that the infrared radiation data generated by it is reduced, reducing the impact of the thermal crosstalk of the resistor unit on the overall infrared image, until the impact degree after the final normalization after the current adjustment appears for the first time At this time, the thermal crosstalk area has less impact on the overall image, and the infrared imaging effect is better.

[0085] It should be noted that the second threshold value in this embodiment The value of is 0.6, which can be adjusted according to actual conditions and is not specifically limited in this embodiment.

[0086] Through the above steps, the control of the resistor array infrared imaging is completed.

[0087] An embodiment of the present invention also provides a resistance array infrared imaging control system based on transfer learning, which includes 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 method described in steps S001 to S004 are implemented.

[0088] This embodiment determines the infrared radiation performance of each resistor unit according to the number of pixels in the corresponding range of the resistor unit on the infrared image and the infrared radiation data value corresponding to the pixel, so as to quantify the infrared radiation characteristics of each resistor unit and provide basic data for the subsequent determination of the thermal radiation area; determines the thermal radiation area of ​​each resistor unit according to the change of the radiation data of the resistor unit in the corresponding range on the infrared image, the infrared radiation performance of each resistor unit and the distance between the center points of the corresponding range of the adjacent resistor units, accurately determines the thermal radiation area contour of each resistor unit, and further determines the thermal crosstalk area according to the thermal radiation area; determines the thermal crosstalk area of ​​each resistor unit according to the difference between the thermal radiation data of adjacent pixels in the thermal radiation area of ​​the resistor unit, and determines the degree of influence of the thermal crosstalk phenomenon of the resistor unit on the infrared image according to the difference between the number of pixels and the thermal radiation value corresponding to the pixel in the thermal crosstalk area of ​​each resistor unit, the area of ​​the thermal radiation area of ​​the resistor unit and the area of ​​the entire infrared image, and controls the infrared imaging of the resistor array according to the degree of influence, and improves the clarity of the infrared image and the overall performance of the system by reducing the influence of the thermal crosstalk on the infrared image, thereby improving the application effect and reliability of the infrared imaging system.

[0089] 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. A resistor array infrared imaging control method based on transfer learning, characterized in that: The method comprises the following steps: Acquiring an infrared image using a resistor array, wherein each resistor unit in the resistor array corresponds to a range in the infrared image, and each pixel point in the infrared image corresponds to an infrared radiation data value; Determine the infrared radiation performance of each resistor unit according to the number of pixels within the corresponding range of the resistor unit on the infrared image and the infrared radiation data value corresponding to the pixel; Determine the heat radiation area of ​​each resistor unit according to the change of the radiation data within the corresponding range of the resistor unit on the infrared image, the infrared radiation performance of each resistor unit and the distance between the center points of the corresponding ranges of adjacent resistor units; According to the difference between the thermal radiation data between adjacent pixels in the thermal radiation area of ​​the resistor unit, the thermal crosstalk area of ​​each resistor unit is determined, and according to the difference between the number of pixels and the thermal radiation values ​​corresponding to the pixels in the thermal crosstalk area of ​​each resistor unit, the area of ​​the thermal radiation area of ​​the resistor unit and the area of ​​the entire infrared image, the influence of the thermal crosstalk phenomenon of the resistor unit on the infrared image is determined, and the infrared imaging of the resistor array is controlled according to the influence degree; The specific calculation method for determining the heat radiation area of ​​each resistor unit is as follows: Determine The heat radiation area boundaries of the four sides of the range corresponding to the resistance unit are recorded as the closed area surrounded by the heat radiation area boundaries of the four sides. The heat radiation area of ​​each resistor unit; The specific method of determining the thermal crosstalk area of ​​each resistor unit includes: Determine The thermal crosstalk area boundaries of the four sides of the thermal radiation area of ​​the resistor unit are recorded as the area between the closed rectangular area surrounded by the thermal crosstalk area boundaries of all sides and the thermal radiation area. Thermal crosstalk area of ​​each resistor unit; The specific method of determining the influence degree of the thermal crosstalk phenomenon of the resistor unit on the infrared image includes: Calculate the The product of the number of all pixels in the thermal crosstalk area of ​​the resistor unit and the variance of the infrared radiation data of all pixels is recorded as the first product. The ratio of the thermal radiation area of ​​the resistor unit to the area of ​​the entire infrared image is recorded as The heat radiation area ratio of each resistor unit is calculated by multiplying the first product and the The product of the heat radiation area proportions of the resistor units is taken as the The degree of influence of the thermal crosstalk area of ​​each resistor unit on the overall infrared image.

2. The resistor array infrared imaging control method based on transfer learning according to claim 1 is characterized in that: The specific method of determining the infrared radiation performance of each resistor unit includes: Calculate the The sum of the infrared radiation data values ​​of all pixels in the range corresponding to the resistor unit is recorded as Infrared radiation performance of a resistor unit.

3. The resistor array infrared imaging control method based on transfer learning according to claim 1, characterized in that: The determination The heat radiation area boundaries of the four sides of the range corresponding to the resistance unit include the following specific methods: Calculate the The resistance unit corresponds to the The product of the ratio of the heat radiation area of ​​the edge between adjacent resistor units and the first distance is recorded as the second distance. The resistance unit corresponds to the The edge, order The edge and The shortest distance between the centers of the ranges corresponding to the resistor units is the second distance. The resistance unit corresponds to the The boundary of the radiation area corresponding to the strip edge; According to The method for obtaining the boundary of the radiation area corresponding to the edge is used to determine the The thermal radiation area boundaries of the other three sides of the range corresponding to the resistor unit.

4. The resistor array infrared imaging control method based on transfer learning according to claim 3 is characterized in that: The said The resistance unit corresponds to the The specific method of determining the ratio of the heat radiation area of ​​the edge to the area between adjacent resistance units and the first distance includes: The first The resistance unit with the closest distance between the center point of the edge and the center point of the corresponding range of the resistance unit is recorded as The adjacent resistor units of the edge are constructed The resistor unit and The data sequence of infrared radiation data values ​​of the pixel points on the straight line between the center points of the corresponding range of the adjacent resistance units of the strip edge , get the data sequence The first-order difference sequence of ; Calculate the data sequence of infrared radiation data values The number of negative numbers in the first-order difference sequence of The ratio of the number of all data in is recorded as the first ratio, and the The resistor unit and The distance between the center points of the corresponding range of adjacent resistance units on the edge is recorded as the first distance, and the first distance is calculated. The ratio of the infrared radiation performance of the resistor unit to the first distance is recorded as the second ratio, and the second ratio is normalized, and the product of the first ratio and the normalized second ratio is recorded as the first The resistance unit corresponds to the The ratio of the heat radiation area of ​​the strip edge to the area between adjacent resistor units.

5. The resistor array infrared imaging control method based on transfer learning according to claim 1, characterized in that: The determination The specific method of defining the thermal crosstalk area boundaries of the four sides of the thermal radiation area of ​​the resistor unit is as follows: In the The upper boundary of the heat radiation area of ​​the first resistor unit is The center of the heat radiation area of ​​the resistor unit is traversed pixel by pixel, and the Pixels and The absolute value of the thermal radiation data difference of the pixel point is taken as the The judgment value of the pixel point is preset to the first threshold , taking the pixel points whose judgment values ​​are greater than the preset first threshold as the segmentation points, and taking the last segmentation point as the target point; The first The upper boundary of the heat radiation area of ​​each resistor unit is moved downward in parallel to the target point, and the thermal crosstalk area boundary corresponding to the upper boundary is obtained; According to the method of obtaining the thermal crosstalk area boundary corresponding to the upper boundary, determine the The other boundaries of the heat radiation area of ​​the resistor unit correspond to the thermal crosstalk area boundaries.

6. The resistor array infrared imaging control method based on transfer learning according to claim 1, characterized in that: The specific method of controlling the infrared imaging of the resistor array according to the degree of influence is as follows: use The normalization function converts the The influence of the thermal crosstalk area of ​​each resistor unit on the overall infrared image is normalized to Within the range, preset the second threshold , when the normalized influence At that time, The current of the resistor unit remains unchanged. When the normalized influence When The current of each resistor unit is gradually reduced until the first adjustment current appears and the final normalized impact degree When it ends.

7. A resistor array infrared imaging control system based on transfer learning, 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 resistor array infrared imaging control method based on transfer learning as described in any one of claims 1 to 6 are implemented.

Images