A method for inverting the height of aerial targets based on thermal infrared hyperspectral satellite data

Abstract

The present invention provides an aerial target altitude inversion method based on thermal infrared hyperspectral satellite data, which can be applied to the field of thermal infrared remote sensing technology. The method is applied to an altitude inversion system, which includes at least one altitude inversion model, and the method includes: obtaining thermal infrared hyperspectral satellite data for an aerial target object; determining the target object temperature, atmospheric condition information, and background ground object information according to the thermal infrared hyperspectral satellite data, wherein the atmospheric condition information represents the atmospheric conditions at the location of the aerial target object, and the background ground object information represents the information of the background ground objects below the location of the aerial target object; determining a target altitude inversion model corresponding to the thermal infrared hyperspectral satellite data from at least one altitude inversion model according to the atmospheric condition information, the background ground object information, and the target object temperature; inputting the thermal infrared hyperspectral satellite data into the target altitude inversion model, and outputting the target altitude for the aerial target object.

Description

Technical Field

[0001] The present invention relates to the field of thermal infrared remote sensing technology, and more specifically, to an aerial target altitude inversion method based on thermal infrared hyperspectral satellite data. Background Art

[0002] The height inversion of aerial targets refers to the further calculation of the relative distance between the target and the ground surface based on the determination of the target plane position. At present, the following two methods are mainly used to achieve height inversion. The first is to use ground-based radar observation. This method determines the target height by transmitting electromagnetic waves from ground radar stations and receiving reflected signals, but its detection distance is limited and the mode of actively transmitting electromagnetic waves has poor concealment. The second is to use space-based multi-view observation methods to invert aerial targets. The same aerial target is observed using multi-angle data from satellite platforms, and height inversion is achieved by analyzing image data from different perspectives. However, it requires multi-angle observation capabilities and has high requirements for the registration accuracy of the observation angles and the target morphology. In addition, aerial targets move quickly, and the displacement generated during multi-angle shooting will increase the measurement error and affect the inversion accuracy. Summary of the invention

[0003] In view of this, the present invention provides an aerial target altitude inversion method based on thermal infrared hyperspectral satellite data.

[0004] One aspect of the present invention provides an aerial target altitude inversion method based on thermal infrared hyperspectral satellite data, which is applied to an altitude inversion system, wherein the altitude inversion system includes at least one altitude inversion model; the method comprises:

[0005] Acquire thermal infrared hyperspectral satellite data for aerial targets;

[0006] Determine the target object temperature, atmospheric condition information, and background object information for the aerial target object based on the thermal infrared hyperspectral satellite data, wherein the atmospheric condition information represents the atmospheric conditions at the location of the aerial target object, and the background object information represents the information of the background objects below the location of the aerial target object;

[0007] Determine a target height inversion model corresponding to thermal infrared hyperspectral satellite data from at least one height inversion model according to atmospheric condition information, background object information and target object temperature;

[0008] The thermal infrared hyperspectral satellite data is input into the target height inversion model to output the target height for the aerial target object.

[0009] According to an embodiment of the present invention, determining a target height inversion model corresponding to thermal infrared hyperspectral satellite data from at least one height inversion model according to atmospheric condition information, background object information and target object temperature includes:

[0010] Determine, according to the atmospheric condition information, the background object information and the target object temperature, the target parameter value corresponding to each condition parameter in the condition parameter table, wherein the condition parameter table includes at least one condition parameter, each condition parameter corresponds to at least one parameter value, and the target parameter value is one of the at least one parameter value;

[0011] Determine the target condition type according to the target parameter value corresponding to each condition parameter;

[0012] According to the target condition type, a height inversion model corresponding to the target condition type is determined from at least one height inversion model to obtain a height inversion model.

[0013] According to an embodiment of the present invention, at least one condition parameter includes a preset target temperature, a preset target height, a preset background object type, a preset background object temperature, a preset atmospheric mode, a preset aerosol mode, and a preset visibility; the background object information includes the background object type and the background object temperature; the atmospheric condition information includes atmospheric mode information, aerosol mode information, and visibility information;

[0014] According to the atmospheric condition information, background object information and target object temperature, the target parameter value corresponding to each condition parameter in the condition parameter table is determined to include:

[0015] Determining a target parameter value corresponding to a preset target temperature from at least one parameter value corresponding to a preset temperature according to the target object temperature;

[0016] Determining a target parameter value corresponding to a preset background object type from at least one parameter value corresponding to a preset background object type according to the background object type;

[0017] Determining a target parameter value corresponding to a preset background temperature from at least one parameter value corresponding to a preset background temperature according to the background object temperature;

[0018] Determining a target parameter value corresponding to the preset atmospheric mode from at least one parameter value corresponding to the preset atmospheric mode according to the atmospheric mode information;

[0019] Determining a target parameter value corresponding to a preset aerosol mode from at least one parameter value corresponding to the preset aerosol mode according to the aerosol mode information;

[0020] A target parameter value corresponding to the preset visibility is determined from at least one parameter value corresponding to the preset visibility according to the visibility information.

[0021] According to an embodiment of the present invention, the target height inversion model includes a corresponding relationship between pixel brightness value and height; the thermal infrared hyperspectral satellite data includes pixel brightness value;

[0022] The thermal infrared hyperspectral satellite data is input into the target height inversion model, and the output target height for the aerial target object includes:

[0023] The thermal infrared hyperspectral satellite data is input into the target height inversion model, and the height corresponding to the pixel brightness value in the thermal infrared hyperspectral satellite data is determined according to the corresponding relationship between the pixel brightness value and the height, and the target height is obtained and output.

[0024] According to an embodiment of the present invention, at least one height inversion model method is trained using the following operations:

[0025] Obtaining a preset condition parameter table, wherein the condition parameter table includes at least one condition parameter, each condition parameter corresponds to at least one parameter value, and the at least one condition parameter includes a preset target temperature, a preset target height, a preset background object type, a preset background object temperature, a preset atmospheric mode, a preset aerosol mode, and a preset visibility;

[0026] Determine the sample parameter value of each condition parameter from at least one parameter value corresponding to each condition parameter, and obtain N condition types where N is a positive integer ≥ 1;

[0027] For the i-th condition type among the N condition types, determine the thermal infrared spectrum entrance pupil radiation data corresponding to the i-th condition type according to the sample parameter value of each condition parameter, wherein the thermal infrared spectrum entrance pupil radiation data includes the entrance pupil radiation brightness value corresponding to at least one wavelength, 1≤i≤N;

[0028] The regression model is trained using the ith condition type and the thermal infrared spectrum entrance pupil radiation data corresponding to the ith condition type to obtain the height inversion model corresponding to the ith condition type.

[0029] According to an embodiment of the present invention, the method further includes:

[0030] For each wavelength of the at least one wavelength, according to at least one entrance pupil radiation brightness value corresponding to the wavelength and the target height value corresponding to each entrance pupil radiation brightness value, determine the correlation between the wavelength and the height according to a preset formula to obtain a correlation analysis result, wherein the correlation analysis result includes a correlation coefficient between each wavelength and the height;

[0031] According to the correlation analysis results, the thermal infrared spectrum entrance pupil radiation data is optimized to obtain the optimized thermal infrared spectrum entrance pupil radiation data;

[0032] Among them, the regression model is trained using the i-th condition type and the thermal infrared spectrum entrance pupil radiation data corresponding to the i-th condition type, and the height inversion model corresponding to the i-th condition type is obtained, including:

[0033] The regression model is trained using the i-th condition type and the optimized thermal infrared spectrum entrance pupil radiation data corresponding to the i-th condition type to obtain the height inversion model corresponding to the i-th condition type.

[0034] According to an embodiment of the present invention, according to the correlation analysis result, the thermal infrared spectrum entrance pupil radiation data is optimized, and the optimized thermal infrared spectrum entrance pupil radiation data is obtained, including:

[0035] Determine a wavelength having a correlation coefficient greater than a preset threshold from at least one wavelength to obtain a target wavelength;

[0036] The entrance pupil radiation brightness value corresponding to the target wavelength is determined as the optimized thermal infrared spectrum entrance pupil radiation data.

[0037] According to an embodiment of the present invention, the preset formula may be the following formula (1):

[0038] (1);

[0039] Among them, r represents the correlation coefficient between wavelength and height, N is the number of condition types, X1 i Characterizes the target height value corresponding to the i-th condition type, X2 i Characterizes the entrance pupil radiation brightness value corresponding to the i-th condition type, Represents the average value of N target height values, Represents the average of N entrance pupil radiance values.

[0040] According to an embodiment of the present invention, determining the thermal infrared spectrum entrance pupil radiation data corresponding to the condition type according to the sample parameter value of each condition parameter includes:

[0041] For each wavelength of the at least one wavelength, determine the pupil radiation brightness value corresponding to the wavelength using formula (2);

[0042] (2);

[0043] in, represents the wavelength, It represents the upward transmittance from the aerial target position H to the top of the atmosphere, It represents the atmospheric upward transmittance from the ground surface to the aerial target position H; Indicates the radiant brightness of an aerial target; represents the radiance of the background object, represents the path radiance; It represents the projection area of ​​the aerial target in the observation direction. It is calculated based on the observed zenith angle and azimuth projection; Indicates the projection area of ​​the background object in the observation direction; represents the total area collected, ; Characterize the emissivity of background objects, Represents the background object temperature.

[0044] According to an embodiment of the present invention, the radiance of an aerial target Calculate using formula (3):

[0045] (3);

[0046] in, is the skin temperature of the aerial target, is the spectral emissivity of the air target's skin, is the first radiation constant, is the second radiation constant;

[0047] The radiance of background objects The following formula (4) is used for calculation:

[0048] ; (4).

[0049] Another aspect of the present invention provides an aerial target altitude inversion device based on thermal infrared hyperspectral satellite data, which is applied to an altitude inversion system, wherein the altitude inversion system includes at least one altitude inversion model; the device includes:

[0050] An acquisition module, used for acquiring thermal infrared hyperspectral satellite data for aerial target objects;

[0051] A first determination module is used to determine the target object temperature, atmospheric condition information, and background object information for the aerial target object based on the thermal infrared hyperspectral satellite data, wherein the atmospheric condition information represents the atmospheric conditions at the location of the aerial target object, and the background object information represents the information of the background objects below the location of the aerial target object;

[0052] A second determination module is used to determine a target height inversion model corresponding to the thermal infrared hyperspectral satellite data from at least one height inversion model according to the atmospheric condition information, the background object information and the target object temperature;

[0053] The height inversion module is used to input the thermal infrared hyperspectral satellite data into the target height inversion model and output the target height for the aerial target object.

[0054] Another aspect of the present invention provides an electronic device, comprising:

[0055] one or more processors;

[0056] a memory for storing one or more programs,

[0057] When the one or more programs are executed by the one or more processors, the one or more processors implement the above method.

[0058] Another aspect of the present invention provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above method when executed.

[0059] Another aspect of the present invention provides a computer program product, the computer program product comprising computer executable instructions, the instructions being used to implement the above method when being executed.

[0060] According to an embodiment of the present invention, thermal infrared hyperspectral satellite data is used to first determine the target object temperature, atmospheric condition information, and background object information of the aerial target object; then, based on the atmospheric condition information, background object information, and target object temperature, a target height inversion model that matches the target object is determined from at least one height inversion model; then, the thermal infrared hyperspectral satellite data is input into the target height inversion model to output a technical means of the target height of the aerial target object. Inversion of aerial target height based on thermal infrared hyperspectral satellite data belongs to passive imaging, has the advantages of being difficult to be discovered, strong concealment, all-day observation, and rich spectral information, improves the accuracy of height inversion, and at least partially overcomes the technical problems of poor concealment and large inversion errors in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0062] Figure 1 An exemplary system architecture to which the aerial target height inversion method according to an embodiment of the present invention can be applied is shown.

[0063] Figure 2 A flow chart of an aerial target height inversion method according to an embodiment of the present invention is shown.

[0064] Figure 3 A flow chart of a method for training a height inversion model according to an embodiment of the present invention is shown.

[0065] Figure 4 A schematic diagram of a method for constructing a height inversion model according to an embodiment of the present invention is shown.

[0066] Figure 5 A block diagram of an aerial target height inversion device according to an embodiment of the present invention is shown.

[0067] Figure 6 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0068] Below, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present invention. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of embodiments of the present invention. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of concepts of the present invention.

[0069] The terms used herein are only for describing specific embodiments and are not intended to limit the present invention. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0070] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0071] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0072] The target height inversion method is divided into active and passive methods according to the different data receiving methods. Active methods such as ground-based radar and laser calculate the target distance by analyzing the characteristics of the echo signal, but their detection distance is limited and they are easily exposed and interfered with. Passive methods mainly use the signals reflected or radiated by the target to achieve height measurement, saving energy and resource consumption, with less risk of exposure and interference, and are more suitable for long-distance aerial target height inversion tasks. At present, passive height inversion is mainly divided into multi-angle height inversion and single-angle height inversion.

[0073] Multi-angle height inversion uses the parallax principle at different angles. It is achieved by taking photos with remote sensors at different positions or angles, or by taking photos with a single remote sensor multiple times. The multi-angle height measurement has strict requirements on the accuracy of registration and requires shooting at larger angles. The aerial displacement of moving targets during multi-angle shooting will lead to large measurement errors, making it difficult to meet the height inversion requirements of aerial moving targets.

[0074] The single-angle height inversion task is more challenging due to the lack of parallax information. One example provides a monocular imaging height inversion method, which requires the target to have low spatial frequency characteristics and strong radiation intensity. Another example proposes a monocular height measurement method called the "external standard method". This method uses reference images in a pre-established image library to infer the distance based on the size of the target. However, this method is only applicable to the positioning of specific targets under specific conditions, and has relatively strict requirements on the target type and environment. In addition, there are cross-line of sight methods, dual-band methods, energy methods, infrared imaging tracking, sequential image processing and motion analysis methods. The above methods mainly use the infrared radiation characteristics or morphological characteristics of the target to carry out height inversion, without using the spectral information of infrared in different spectral bands.

[0075] In view of the above situation, the present invention proposes an aerial target altitude inversion method based on thermal infrared hyperspectral satellite data, which is applied to an altitude inversion system, wherein the altitude inversion system includes at least one altitude inversion model; the method includes: acquiring thermal infrared hyperspectral satellite data for an aerial target object; determining a target object temperature, atmospheric condition information, and background ground object information for the aerial target object based on the thermal infrared hyperspectral satellite data, wherein the atmospheric condition information represents the atmospheric conditions at the location of the aerial target object, and the background ground object information represents the information of background ground objects below the location of the aerial target object; determining a target altitude inversion model corresponding to the thermal infrared hyperspectral satellite data from at least one altitude inversion model based on the atmospheric condition information, the background ground object information, and the target object temperature; and inputting the thermal infrared hyperspectral satellite data into the target altitude inversion model to output a target altitude for the aerial target object.

[0076] Figure 1 An exemplary system architecture to which the aerial target height inversion method can be applied according to an embodiment of the present invention is shown. It should be noted that: Figure 1 The examples shown are merely examples of system architectures to which the embodiments of the present invention may be applied, to help those skilled in the art understand the technical content of the present invention, but do not mean that the embodiments of the present invention may not be used in other devices, systems, environments or scenarios.

[0077] like Figure 1As shown, the system architecture according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0078] The user may use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (only for example).

[0079] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0080] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0081] It should be noted that the aerial target height inversion method provided in the embodiment of the present invention can generally be executed by the server 105. Accordingly, the aerial target height inversion device provided in the embodiment of the present invention can generally be arranged in the server 105. The aerial target height inversion method provided in the embodiment of the present invention can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Correspondingly, the aerial target height inversion device provided in the embodiment of the present invention can also be arranged in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Alternatively, the aerial target height inversion method provided in the embodiment of the present invention can also be executed by the first terminal device 101, the second terminal device 102 or the third terminal device 103, or can also be executed by other terminal devices that are different from the first terminal device 101, the second terminal device 102 or the third terminal device 103. Correspondingly, the aerial target height inversion device provided in the embodiment of the present invention can also be set in the first terminal device 101, the second terminal device 102 or the third terminal device 103, or in other terminal devices different from the first terminal device 101, the second terminal device 102 or the third terminal device 103.

[0082] For example, the thermal infrared hyperspectral satellite data may be originally stored in any one of the first terminal device 101, the second terminal device 102 or the third terminal device 103 (for example, the first terminal device 101, but not limited thereto), or stored on an external storage device and may be imported into the first terminal device 101. Then, the first terminal device 101 may locally execute the aerial target altitude inversion method provided by the embodiment of the present invention, or send the thermal infrared hyperspectral satellite data to other terminal devices, servers, or server clusters, and the other terminal devices, servers, or server clusters that receive the thermal infrared hyperspectral satellite data may execute the aerial target altitude inversion method provided by the embodiment of the present invention.

[0083] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0084] Figure 2 A flow chart of an aerial target height inversion method according to an embodiment of the present invention is shown.

[0085] According to an embodiment of the present invention, an aerial target altitude inversion method is applied to an altitude inversion system, and the altitude inversion system includes at least one altitude inversion model.

[0086] like Figure 2 As shown, the aerial target altitude inversion method of this embodiment includes operations S210 to S240.

[0087] In operation S210 , thermal infrared hyperspectral satellite data for an aerial target object is acquired.

[0088] According to an embodiment of the present invention, thermal infrared hyperspectral satellite data is obtained by observing aerial target objects with a remote sensor.

[0089] According to an embodiment of the present invention, thermal infrared hyperspectral satellite data observed by a remote sensor can be sent to an altitude inversion system in real time, so that the altitude inversion system can measure the altitude of an aerial target object in real time.

[0090] According to an embodiment of the present invention, the thermal infrared hyperspectral satellite data observed by the remote sensor can be stored in a database. The user can input the data address of the thermal infrared hyperspectral satellite data for the aerial target object in the altitude inversion request interface of the altitude inversion system, and the altitude inversion system obtains the corresponding data from the database to measure the altitude of the aerial target.

[0091] In operation S220, the target object temperature, atmospheric condition information, and background object information for the aerial target object are determined based on the thermal infrared hyperspectral satellite data, wherein the atmospheric condition information represents the atmospheric conditions at the location of the aerial target object, and the background object information represents the information of the background objects below the location of the aerial target object.

[0092] According to an embodiment of the present invention, the atmospheric condition information may include atmospheric pattern information, aerosol pattern information and visibility information.

[0093] According to an embodiment of the present invention, the latitude and longitude information of the aerial target object can be determined based on the infrared hyperspectral satellite data, and the absolute position of the aerial target object can be determined based on the latitude and longitude information, thereby determining the atmospheric pattern information, aerosol pattern information, visibility information, etc. at the absolute position of the aerial target object.

[0094] According to an embodiment of the present invention, the background object information may include the background object type and the background object temperature.

[0095] According to an embodiment of the present invention, the type of background objects below the location of the aerial target object can be determined based on infrared hyperspectral satellite data, and the background object temperature can be determined based on the type of background objects and the temperature at the time of observation of the absolute position of the aerial target object.

[0096] It should be noted that the temperature of background objects is related to the observation time and season.

[0097] In operation S230, a target height inversion model corresponding to the thermal infrared hyperspectral satellite data is determined from at least one height inversion model according to the atmospheric condition information, the background object information, and the target object temperature.

[0098] According to an embodiment of the present invention, each height inversion model may correspond to a condition type, and the corresponding condition type may be determined according to atmospheric condition information, background object information and target object temperature, and then the target height inversion model may be determined according to the condition type.

[0099] According to an embodiment of the present invention, determining a target height inversion model corresponding to thermal infrared hyperspectral satellite data from at least one height inversion model according to atmospheric condition information, background object information and target object temperature includes: determining a target parameter value corresponding to each condition parameter in a condition parameter table according to atmospheric condition information, background object information and target object temperature, wherein the condition parameter table includes at least one condition parameter, each condition parameter corresponds to at least one parameter value, and the target parameter value is one of the at least one parameter value; determining a target condition type according to the target parameter value corresponding to each condition parameter; and determining a height inversion model corresponding to the target condition type from at least one height inversion model according to the target condition type to obtain a height inversion model.

[0100] For example, the condition references included in the condition parameter table may include: preset target temperature, preset target altitude, preset background object type, preset background object temperature, preset atmosphere mode, preset aerosol mode, preset visibility. Each condition parameter includes at least one parameter value, for example, the preset target temperature includes parameter value A, parameter value B, parameter value C, parameter value D; the preset target altitude includes parameter value a, parameter value b, parameter value c.

[0101] In one embodiment, the conditional parameter table may be as shown in Table 1.

[0102] Table 1

[0103] According to an embodiment of the present invention, determining the target parameter value corresponding to each condition parameter in the condition parameter table according to atmospheric condition information, background object information and target object temperature includes: determining the target parameter value corresponding to the preset target temperature from at least one parameter value corresponding to the preset temperature according to the target object temperature; determining the target parameter value corresponding to the preset background object type from at least one parameter value corresponding to the preset background object type according to the background object type; determining the target parameter value corresponding to the preset background temperature from at least one parameter value corresponding to the preset background temperature according to the background object temperature; determining the target parameter value corresponding to the preset atmospheric mode from at least one parameter value corresponding to the preset atmospheric mode according to atmospheric mode information; determining the target parameter value corresponding to the preset aerosol mode from at least one parameter value corresponding to the preset aerosol mode according to aerosol mode information; determining the target parameter value corresponding to the preset visibility from at least one parameter value corresponding to the preset visibility according to visibility information.

[0104] For example, the target parameter values ​​corresponding to each conditional parameter in the conditional parameter table may include: a target reference value corresponding to a preset target temperature, such as 500K, a target reference value corresponding to a preset target altitude, such as 2km, a target reference value corresponding to a preset background object type, such as a forest, a target reference value corresponding to a preset background object temperature, such as 275K, a target reference value corresponding to a preset atmospheric mode, such as tropical, a target reference value corresponding to a preset aerosol mode, such as ocean, and a target reference value corresponding to a preset visibility, such as 50km.

[0105] In operation S240 , the thermal infrared hyperspectral satellite data is input into a target height inversion model, and a target height for an aerial target object is output.

[0106] According to an embodiment of the present invention, the target height inversion model includes the correspondence between pixel brightness values ​​and heights; the thermal infrared hyperspectral satellite data includes pixel brightness values; the thermal infrared hyperspectral satellite data is input into the target height inversion model, and the target height for the aerial target object is output, including: inputting the thermal infrared hyperspectral satellite data into the target height inversion model, determining the height corresponding to the pixel brightness value in the thermal infrared hyperspectral satellite data according to the correspondence between the pixel brightness value and the height, obtaining the target height and outputting it.

[0107] The pixel brightness value (Digital Number, DN) is the digital representation of the quantified target radiation energy received by the sensor. Its size is related to the sensor's radiation resolution, ground object emission frequency, atmospheric transmittance, and scattering rate, and can reflect the ground object's emissivity.

[0108] According to an embodiment of the present invention, a technical means is adopted for determining the target object temperature, atmospheric condition information, and background object information for an aerial target object based on thermal infrared hyperspectral satellite data; then determining a target altitude inversion model corresponding to the thermal infrared hyperspectral satellite data from at least one altitude inversion model based on the atmospheric condition information, the background object information, and the target object temperature; and then inputting the thermal infrared hyperspectral satellite data into the target altitude inversion model to output the target altitude for the aerial target object. Since the aerial target altitude inversion based on thermal infrared hyperspectral satellite data belongs to passive imaging and is not easily discovered, it has the advantages of strong concealment, all-day observation, and rich spectral information, thereby achieving high inversion accuracy. Therefore, it at least partially overcomes the technical problems of poor concealment and large inversion errors in the related art.

[0109] Figure 3 A flow chart of a method for training a height inversion model according to an embodiment of the present invention is shown.

[0110] like Figure 3 As shown, the training method of the height inversion model of this embodiment includes operations S310 to S340.

[0111] In operation S310, a preset condition parameter table is obtained.

[0112] According to an embodiment of the present invention, the condition parameter table includes at least one condition parameter, and each condition parameter corresponds to at least one parameter value.

[0113] It should be noted that the conditional parameters in the conditional parameter table may be key influencing factors in the imaging process. For example, the conditional parameters may be preset target temperature, preset target height, preset background object type, preset background object temperature, preset atmospheric mode, preset aerosol mode, and preset visibility.

[0114] In one embodiment, the conditional parameter table may be the conditional parameter table shown in Table 1.

[0115] In operation S320, a sample parameter value of each condition parameter is determined from at least one parameter value corresponding to each condition parameter to obtain N condition types, where N is a positive integer ≥1.

[0116] Determine the sample parameter value of each conditional parameter from at least one parameter value corresponding to each conditional parameter, and obtain N condition types by extracting one parameter value from each conditional parameter as a sample parameter value. Do this N times to obtain N condition types.

[0117] For example, by combining one of the parameter values ​​in the preset target temperature in Table 1 with one of the parameter values ​​in the preset target height, one of the parameter values ​​in the preset background object type, one of the parameter values ​​in the preset background object temperature, one of the parameter values ​​in the preset atmospheric mode, one of the parameter values ​​in the preset aerosol mode, and one of the parameter values ​​in the preset visibility, different condition types can be obtained.

[0118] Specifically, the preset target temperature of 500K, the preset target altitude of 2km, the preset background object type of water, the preset background object temperature of 260K, the preset atmospheric mode of tropical, the preset aerosol mode of rural and the preset visibility of 5km in Table 1 are combined to obtain a condition type 1.

[0119] For another example, the preset target temperature in condition type 1 is adjusted to 600K to obtain condition type 2; for another example, the preset target temperature in condition type 1 is adjusted to 700K to obtain condition type. In this way, multiple different condition types can be obtained.

[0120] In operation S330, for the i-th condition type among N condition types, the thermal infrared spectrum entrance pupil radiation data corresponding to the i-th condition type is determined according to the sample parameter values ​​of each condition parameter, wherein the thermal infrared spectrum entrance pupil radiation data includes entrance pupil radiation brightness values ​​corresponding to at least one wavelength, 1≤i≤N.

[0121] In operation S340, a regression model is trained using the ith condition type and the thermal infrared spectrum entrance pupil radiation data corresponding to the ith condition type to obtain a height inversion model corresponding to the ith condition type.

[0122] According to an embodiment of the present invention, the regression model may adopt a random forest model.

[0123] In one embodiment, using the ith condition type and the thermal infrared spectrum entrance pupil radiation data corresponding to the ith condition type to train a regression model to obtain a height inversion model corresponding to the ith condition type may include: inputting the ith condition type and the thermal infrared spectrum entrance pupil radiation data corresponding to the ith condition type into the regression model to build and tune the model, including adjusting the hyperparameters of the model, such as the number of trees, the depth of the tree, the size of the feature subset, etc. The best hyperparameter combination is found by cross-validation to obtain the best model performance and obtain the height inversion model.

[0124] In another embodiment, using the i-th condition type and the thermal infrared spectrum entrance pupil radiation data corresponding to the i-th condition type to train a regression model to obtain a height inversion model corresponding to the i-th condition type may include: inputting the parameter value corresponding to the i-th condition type and the thermal infrared spectrum entrance pupil radiation data into the regression model for height inversion, and outputting a predicted height; calculating a loss value based on the predicted height and a preset target height parameter value corresponding to the i-th condition type; if the loss value does not reach a preset loss threshold, adjusting the hyperparameters of the regression model, such as the number of trees, the depth of the tree, the size of the feature subset, etc., and iterating the above operation until the loss value reaches the preset loss threshold, stopping the training, and obtaining the height inversion model.

[0125] According to an embodiment of the present invention, the loss value may be a mean square error (MSE), a root mean square error (RMSE), etc. between the predicted height and a preset target height parameter value.

[0126] According to an embodiment of the present invention, the above method also includes: for each wavelength of at least one wavelength, according to at least one entrance pupil radiation brightness value corresponding to the wavelength and the target height value corresponding to each entrance pupil radiation brightness value, determining the correlation between the wavelength and the height according to a preset formula, and obtaining a correlation analysis result, wherein the correlation analysis result includes the correlation coefficient between each wavelength and the height; according to the correlation analysis result, optimizing the thermal infrared spectrum entrance pupil radiation data to obtain optimized thermal infrared spectrum entrance pupil radiation data; wherein, using the i-th condition type and the thermal infrared spectrum entrance pupil radiation data corresponding to the i-th condition type to train a regression model to obtain a height inversion model corresponding to the i-th condition type includes: using the i-th condition type and the optimized thermal infrared spectrum entrance pupil radiation data corresponding to the i-th condition type to train a regression model to obtain a height inversion model corresponding to the i-th condition type.

[0127] In one embodiment, the correlation analysis may adopt a linear correlation analysis method, which is a statistical analysis method used to measure whether there is a linear correlation between two variables and the closeness of the linear correlation. For example, the correlation between each spectral channel and the target height may be measured by calculating the Pearson correlation coefficient, as shown in the following calculation formula (1):

[0128] (1);

[0129] Where r represents the correlation coefficient between wavelength and height, and the value range of r is between (-1, 1). If r>0, it indicates that the two variables are positively correlated; if r<0, it indicates that the two variables are negatively correlated. r indicates the strength of the correlation between the variables. The larger the value, the stronger the correlation between the two variables. N is the number of condition types. Represents the target height value corresponding to the i-th condition type, Characterizes the entrance pupil radiation brightness value corresponding to the i-th condition type, Represents the average value of N target height values, Represents the average value of N entrance pupil radiation brightness values. According to an embodiment of the present invention, based on the correlation analysis result, optimizing the thermal infrared spectrum entrance pupil radiation data, and obtaining the optimized thermal infrared spectrum entrance pupil radiation data includes: determining a wavelength having a correlation coefficient greater than a preset threshold from at least one wavelength to obtain a target wavelength; and determining the entrance pupil radiation brightness value corresponding to the target wavelength as the optimized thermal infrared spectrum entrance pupil radiation data.

[0130] According to an embodiment of the present invention, according to the correlation analysis result, the thermal infrared spectrum entrance pupil radiation data is optimized, and the optimized thermal infrared spectrum entrance pupil radiation data is obtained, including: sorting the wavelengths according to the correlation coefficient corresponding to each wavelength, selecting the wavelength before the preset position as the target wavelength, and determining the entrance pupil radiation brightness value corresponding to the target wavelength as the optimized thermal infrared spectrum entrance pupil radiation data. The wavelength before the preset position may include, for example, the first 10 wavelengths with the highest correlation coefficient.

[0131] According to an embodiment of the present invention, the key to calculating the entrance pupil radiation brightness is to consider the attenuation of infrared radiation by the atmosphere. The attenuation of infrared radiation is mainly related to the following three factors: ① absorption by water and carbon dioxide molecules in the atmosphere; ② scattering by different macromolecular structures and aerosol particles in the atmosphere; ③ attenuation under different meteorological conditions.

[0132] For example, for each wavelength of at least one wavelength, the entrance pupil radiation brightness value corresponding to the wavelength is determined using formula (2);

[0133] (2);

[0134] in, represents the wavelength, It represents the upward transmittance from the aerial target position H to the top of the atmosphere, It represents the atmospheric upward transmittance from the ground surface to the aerial target position H; Indicates the radiant brightness of an aerial target; represents the radiance of the background object, represents the path radiance; It represents the projection area of ​​the aerial target in the observation direction. It is calculated based on the observed zenith angle and azimuth projection; Indicates the projection area of ​​the background object in the observation direction; represents the total area collected, ; Characterize the emissivity of background objects, Represents the background object temperature.

[0135] According to an embodiment of the present invention, the emissivity of the background object can be selected according to the spectral band setting of the infrared hyperspectral remote sensor, such as 8-12.5 μm.

[0136] In formula (2) , , It is closely related to atmospheric conditions and can be solved using the atmospheric radiation transfer model MODTRAN (MODerate Resolution Atmospheric TRANsmission). The calculation needs to consider changes in atmospheric patterns, aerosol patterns, and visibility.

[0137] According to an embodiment of the present invention, the radiance of an aerial target Calculate using formula (3):

[0138] (3);

[0139] in, is the skin temperature of the aerial target, is the spectral emissivity of the air target's skin, is the first radiation constant, is the second radiation constant; the skin spectral emissivity of the aerial target can be obtained by actual measurement or by referring to classical literature.

[0140] The radiance of background objects The following formula (4) is used for calculation:

[0141] ; (4).

[0142] The embodiment of the present invention first calculates the spectral radiance of the aerial target, and then calculates the radiance of the background object based on the background object type and spectral emissivity data. On this basis, a thermal infrared hyperspectral entrance pupil radiance calculation method is established based on the radiation transmission process. For the thermal infrared hyperspectral entrance pupil radiance calculation method, the main sensitive factors of the imaging process are considered, and a lookup table of atmospheric conditions such as atmospheric mode, aerosol mode, visibility, etc. is established, that is, the above-mentioned conditional parameter table, and the corresponding entrance pupil radiation data is calculated according to the lookup table to form an entrance pupil radiation data set. Based on the data set, the correlation analysis between the target height and the radiance of each band is performed, and the sensitive bands are screened out accordingly. Then, a random forest or other regression model is used to construct a height inversion model based on the target height set and the sensitive band radiance set. This method solves the problem that it is difficult to invert the height of aerial targets based on a single thermal infrared hyperspectral satellite data, and improves the possibility of aerial target inversion.

[0143] Figure 4 A schematic diagram of a method for constructing a height inversion model according to an embodiment of the present invention is shown.

[0144] like Figure 4As shown, first, parameter values ​​are extracted according to the condition parameter table 410 to obtain N condition types, namely the first condition type 421, the second condition type 422, ..., and the Nth condition type 42N; then, the radiation brightness of the aerial target is calculated according to the first condition type 421 to obtain the radiation brightness 421_1 of the first aerial target, and the radiation brightness of the background object is calculated according to the first condition type 421 to obtain the radiation brightness 421_2 of the first background object. According to the radiation brightness 421_1 of the first aerial target and the radiation brightness 421_2 of the first background object, the first thermal infrared spectrum entrance pupil radiation data 421_3 is calculated according to the above formula (2); then, according to The second condition type 422 calculates the radiation brightness of the aerial target to obtain the radiation brightness 422_1 of the second aerial target. The radiation brightness of the background object is calculated according to the second condition type 422 to obtain the radiation brightness 422_2 of the second background object. The second thermal infrared spectrum entrance pupil radiation data 422_3 is calculated according to the radiation brightness 422_1 of the second aerial target and the radiation brightness 422_2 of the second background object in accordance with the above formula (2); ...; the radiation brightness of the aerial target is calculated according to the Nth condition type 42N to obtain the radiation brightness 42N_1 of the Nth aerial target. The radiation brightness of the background object is calculated according to the Nth condition type 42N to obtain the radiation brightness 422_2 of the Nth background object. N_2, according to the radiation brightness 42N_1 of the Nth aerial target and the radiation brightness 42N_2 of the Nth background object, the Nth thermal infrared spectrum entrance pupil radiation data 42N_3 is calculated according to the above formula (2); then, the first thermal infrared spectrum entrance pupil radiation data 421_3, the second thermal infrared spectrum entrance pupil radiation data 422_3, ..., the Nth thermal infrared spectrum entrance pupil radiation data 42N_3 are used to construct the entrance pupil radiation data set 430; according to the entrance pupil radiation data set 430, the sensitive band of the target height is screened to obtain the target wavelength 440; according to the target wavelength 440, the first thermal infrared spectrum entrance pupil radiation data 421_3, the second thermal infrared spectrum entrance pupil radiation data 422_3, ..., the Nth thermal infrared spectrum entrance pupil radiation data 42N_3 are respectively screened to obtain the target wavelength 440; The data 422_3, ..., and the Nth thermal infrared spectrum entrance pupil radiation data 42N_3 are optimized to obtain the optimized first thermal infrared spectrum entrance pupil radiation data 421_4, the second thermal infrared spectrum entrance pupil radiation data 422_4, ..., and the Nth thermal infrared spectrum entrance pupil radiation data 42N_4; then, the optimized first thermal infrared spectrum entrance pupil radiation data 421_4, the second thermal infrared spectrum entrance pupil radiation data 422_4, ..., and the Nth thermal infrared spectrum entrance pupil radiation data 42N_4 are used to construct models respectively to obtain the first height inversion model 421_5, the second height inversion model 422_5, ..., and the Nth height inversion model 42N_5.

[0145] Figure 5 A block diagram of an aerial target height inversion device according to an embodiment of the present invention is shown.

[0146] According to an embodiment of the present invention, the aerial target altitude inversion device is applied to an altitude inversion system, and the altitude inversion system includes at least one altitude inversion model.

[0147] like Figure 5 As shown, the aerial target altitude inversion device includes an acquisition module 510 , a first determination module 520 , a second determination module 530 and an altitude inversion module 540 .

[0148] The acquisition module 510 is used to acquire thermal infrared hyperspectral satellite data for aerial target objects.

[0149] The first determination module 520 is used to determine the target object temperature, atmospheric condition information, and background object information for the aerial target object based on the thermal infrared hyperspectral satellite data, wherein the atmospheric condition information represents the atmospheric conditions at the location of the aerial target object, and the background object information represents the information of the background objects below the location of the aerial target object.

[0150] The second determination module 530 is used to determine a target altitude inversion model corresponding to the thermal infrared hyperspectral satellite data from at least one altitude inversion model according to the atmospheric condition information, the background object information and the target object temperature.

[0151] The height inversion module 540 is used to input the thermal infrared hyperspectral satellite data into the target height inversion model and output the target height for the aerial target object.

[0152] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging the circuit, or by any one of the three implementation methods of software, hardware, and firmware, or by a proper combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be executed.

[0153] For example, any multiple of the acquisition module 510, the first determination module 520, the second determination module 530, and the height inversion module 540 can be combined in one module / unit / subunit for implementation, or any one of the modules / units / subunits can be split into multiple modules / units / subunits. Alternatively, at least part of the functions of one or more of these modules / units / subunits can be combined with at least part of the functions of other modules / units / subunits and implemented in one module / unit / subunit. According to an embodiment of the present invention, at least one of the acquisition module 510, the first determination module 520, the second determination module 530, and the height inversion module 540 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, at least one of the acquisition module 510, the first determination module 520, the second determination module 530 and the height inversion module 540 may be at least partially implemented as a computer program module, and when the computer program module is executed, a corresponding function may be performed.

[0154] It should be noted that the aerial target altitude inversion device part in the embodiment of the present invention corresponds to the aerial target altitude inversion method part in the embodiment of the present invention. The description of the aerial target altitude inversion device part specifically refers to the aerial target altitude inversion method part, which will not be repeated here.

[0155] Figure 6 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present invention is shown. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0156] like Figure 6 As shown, the electronic device according to an embodiment of the present invention includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 to a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include an onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0157] In RAM 603, various programs and data required for the operation of the electronic device are stored. The processor 601, ROM 602 and RAM 603 are connected to each other via a bus 604. The processor 601 performs various operations of the method flow according to the embodiment of the present invention by executing the programs in ROM 602 and / or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603. The processor 601 can also perform various operations of the method flow according to the embodiment of the present invention by executing the programs stored in the one or more memories.

[0158] According to an embodiment of the present invention, the electronic device may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The system may further include one or more of the following components connected to the input / output (I / O) interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

[0159] According to an embodiment of the present invention, the method flow according to an embodiment of the present invention can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, the above-mentioned functions defined in the system of the embodiment of the present invention are executed. According to an embodiment of the present invention, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0160] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiment; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present invention is implemented.

[0161] According to an embodiment of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device.

[0162] For example, according to an embodiment of the present invention, the computer-readable storage medium may include the ROM 602 and / or the RAM 603 described above and / or one or more memories other than the ROM 602 and the RAM 603 .

[0163] An embodiment of the present invention also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method provided by the embodiment of the present invention. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the method provided by the embodiment of the present invention.

[0164] When the computer program is executed by the processor 601, the above functions defined in the system / device of the embodiment of the present invention are executed. According to the embodiment of the present invention, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0165] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0166] According to an embodiment of the present invention, the program code for executing the computer program provided by the embodiment of the present invention can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0167] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments and / or claims of the present invention can be combined and / or combined in various ways, even if such a combination or combination is not explicitly recorded in the present invention. In particular, without departing from the spirit and teaching of the present invention, the features described in the various embodiments and / or claims of the present invention may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present invention.

[0168] The embodiments of the present invention are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present invention. Although each embodiment is described above, it does not mean that the measures in each embodiment cannot be used in combination. The scope of the present invention is defined by the attached claims and their equivalents. Without departing from the scope of the present invention, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

Claims

1. A method for inverting the height of aerial targets based on thermal infrared hyperspectral satellite data, characterized in that: Applied to a height inversion system, the height inversion system comprising at least one height inversion model; The aerial target height inversion method comprises: Acquire thermal infrared hyperspectral satellite data for aerial targets; Determine the target object temperature, atmospheric condition information, and background object information for the aerial target object according to the thermal infrared hyperspectral satellite data, wherein the atmospheric condition information represents the atmospheric condition at the location of the aerial target object, and the background object information represents the information of the background objects below the location of the aerial target object; Determine, from at least one of the height inversion models, a target height inversion model corresponding to the thermal infrared hyperspectral satellite data according to the atmospheric condition information, the background object information and the target object temperature; Inputting the thermal infrared hyperspectral satellite data into the target height inversion model, and outputting the target height for the aerial target object; Wherein, at least one of the height inversion models is trained by the following operations: Obtaining a preset condition parameter table, wherein the condition parameter table includes at least one condition parameter, each of the condition parameters corresponds to at least one parameter value, and the at least one condition parameter includes a preset target temperature, a preset target height, a preset background object type, a preset background object temperature, a preset atmospheric mode, a preset aerosol mode, and a preset visibility; Determine a sample parameter value of each of the conditional parameters from at least one parameter value corresponding to each of the conditional parameters, and obtain N condition types where N is a positive integer ≥ 1; For the i-th condition type among the N condition types, determine the thermal infrared spectrum entrance pupil radiation data corresponding to the i-th condition type according to the sample parameter value of each of the condition parameters, wherein the thermal infrared spectrum entrance pupil radiation data includes the entrance pupil radiation brightness value corresponding to at least one wavelength, 1≤i≤N; and The regression model is trained using the i-th condition type and the thermal infrared spectrum entrance pupil radiation data corresponding to the i-th condition type to obtain a height inversion model corresponding to the i-th condition type.

2. The aerial target height inversion method according to claim 1, characterized in that: Determining a target height inversion model corresponding to the thermal infrared hyperspectral satellite data from at least one of the height inversion models according to the atmospheric condition information, the background object information and the target object temperature comprises: Determine, according to the atmospheric condition information, the background object information and the target object temperature, a target parameter value corresponding to each condition parameter in the condition parameter table, wherein the condition parameter table includes at least one condition parameter, each of the condition parameters corresponds to at least one parameter value, and the target parameter value is one of the at least one parameter value; Determine the target condition type according to the target parameter value corresponding to each of the condition parameters; According to the target condition type, a height inversion model corresponding to the target condition type is determined from at least one of the height inversion models to obtain the height inversion model.

3. The aerial target height inversion method according to claim 2, characterized in that: The at least one condition parameter includes a preset target temperature, a preset target altitude, a preset background object type, a preset background object temperature, a preset atmospheric mode, a preset aerosol mode, and a preset visibility; The background object information includes the background object type and the background object temperature; the atmospheric condition information includes atmospheric mode information, aerosol mode information and visibility information; Determining the target parameter value corresponding to each condition parameter in the condition parameter table according to the atmospheric condition information, the background object information and the target object temperature includes: Determining a target parameter value corresponding to the preset target temperature from at least one parameter value corresponding to the preset target temperature according to the target object temperature; Determining, according to the background object type, a target parameter value corresponding to the preset background object type from at least one parameter value corresponding to the preset background object type; Determining a target parameter value corresponding to the preset background temperature from at least one parameter value corresponding to the preset background temperature according to the background object temperature; Determining a target parameter value corresponding to the preset atmospheric mode from at least one parameter value corresponding to the preset atmospheric mode according to the atmospheric mode information; determining, according to the aerosol mode information, a target parameter value corresponding to the preset aerosol mode from at least one parameter value corresponding to the preset aerosol mode; A target parameter value corresponding to the preset visibility is determined from at least one parameter value corresponding to the preset visibility according to the visibility information.

4. The aerial target height inversion method according to claim 1, characterized in that: The target height inversion model includes the corresponding relationship between pixel brightness value and height; the thermal infrared hyperspectral satellite data includes pixel brightness value; Inputting the thermal infrared hyperspectral satellite data into the target height inversion model, and outputting the target height for the aerial target object comprises: The thermal infrared hyperspectral satellite data is input into the target height inversion model, and the height corresponding to the pixel brightness value in the thermal infrared hyperspectral satellite data is determined according to the corresponding relationship between the pixel brightness value and the height, and the target height is obtained and output.

5. The aerial target height inversion method according to claim 1, characterized in that: The aerial target height inversion method also includes: For each wavelength of at least one wavelength, according to at least one entrance pupil radiation brightness value corresponding to the wavelength and the target height value corresponding to each entrance pupil radiation brightness value, determine the correlation between the wavelength and the height according to a preset formula to obtain a correlation analysis result, wherein the correlation analysis result includes a correlation coefficient between each of the wavelengths and the height; According to the correlation analysis result, optimizing the thermal infrared spectrum entrance pupil radiation data to obtain optimized thermal infrared spectrum entrance pupil radiation data; Wherein, the training of the regression model using the i-th condition type and the thermal infrared spectrum entrance pupil radiation data corresponding to the i-th condition type to obtain the height inversion model corresponding to the i-th condition type includes: The regression model is trained using the i-th condition type and the optimized thermal infrared spectrum entrance pupil radiation data corresponding to the i-th condition type to obtain a height inversion model corresponding to the i-th condition type.

6. The aerial target height inversion method according to claim 5, characterized in that: The step of optimizing the thermal infrared spectrum entrance pupil radiation data according to the correlation analysis result to obtain the optimized thermal infrared spectrum entrance pupil radiation data comprises: Determine a wavelength whose correlation coefficient is greater than a preset threshold from the at least one wavelength to obtain a target wavelength; Determine the entrance pupil radiation brightness value corresponding to the target wavelength as optimized thermal infrared spectrum entrance pupil radiation data.

7. The aerial target height inversion method according to claim 5, characterized in that: The preset formula is the following formula (1): （1）； Among them, r represents the correlation coefficient between wavelength and height, N is the number of condition types, X1 i Characterizes the target height value corresponding to the i-th condition type, X2 i Characterizes the entrance pupil radiation brightness value corresponding to the i-th condition type, Represents the average value of N target height values, Represents the average of N entrance pupil radiance values.

8. The aerial target height inversion method according to claim 1, characterized in that: Determining the thermal infrared spectrum entrance pupil radiation data corresponding to the i-th condition type according to the sample parameter value of each condition parameter includes: For each wavelength of at least one wavelength, determine the entrance pupil radiance value corresponding to the wavelength using formula (2); （2）； in, represents the wavelength, It represents the upward transmittance from the aerial target position H to the top of the atmosphere, It represents the atmospheric upward transmittance from the ground surface to the aerial target position H; Indicates the radiant brightness of an aerial target; represents the radiance of the background object, represents the path radiance; It represents the projection area of ​​the aerial target in the observation direction. It is calculated based on the observed zenith angle and azimuth projection; Indicates the projection area of ​​the background object in the observation direction; represents the total area collected, ; Characterize the emissivity of background objects, Represents the background object temperature.

9. The aerial target height inversion method according to claim 8, characterized in that: The radiance of the aerial target Calculate using formula (3): （3）； in, is the skin temperature of the aerial target, is the spectral emissivity of the skin of the aerial target, c1 is the first radiation constant, and c2 is the second radiation constant; The radiance of the background object The following formula (4) is used for calculation: ；（4）。

Images