An infrared time-series feature reconstruction analysis method, system, device, medium and product

Abstract

The application discloses an infrared time sequence feature reconstruction analysis method, system, device, medium and product, relates to the technical field of infrared remote sensing modeling, and comprises the following steps: acquiring sparse infrared temperature observation data of an artificial target area containing a plurality of discrete time ground surface temperatures; constructing a thermodynamic differential equation based on an energy balance principle; iteratively inverting a to-be-inverted parameter in the thermodynamic differential equation based on the observation data by using a least square algorithm, obtaining an optimal to-be-inverted parameter when a preset ending condition is met; obtaining a continuous ground surface temperature sequence by integrating the differential equation based on the optimal to-be-inverted parameter; and extracting and reconstructing infrared time sequence features according to the continuous ground surface temperature sequence. The application introduces a thermodynamic differential equation as a constraint, fits limited remote sensing observation points into a continuous temperature change sequence with high time resolution, is suitable for thermal feature identification, energy saving monitoring and anomaly detection of artificial targets, and has strong adaptability, accuracy and practical value.

Description

Technical Field

[0001] This application relates to the field of infrared remote sensing modeling technology, and in particular to an infrared temporal feature reconstruction and analysis method, system, device, medium and product. Background Technology

[0002] In many fields such as environmental monitoring, urban planning, and energy management, accurate understanding of the thermal dynamics of man-made targets is crucial. Infrared remote sensing technology, as an effective monitoring method, can acquire relevant information by receiving the infrared radiation emitted by objects.

[0003] In infrared remote sensing monitoring, man-made targets exhibit complex temporal variations in infrared radiation due to their unique thermal properties (such as low heat capacity, high thermal conductivity, and complex surface materials) and unnatural heating / dissipation behaviors. However, limitations imposed by remote sensing platforms (e.g., Landsat's 16-day interval, GF-5's monthly interval, and MODIS's twice-daily interval), observation angles, and cloud interference result in sparse temporal sampling and discontinuous coverage in infrared remote sensing data. Temperature retrieval methods in related technologies (such as single-channel and atmospheric correction) are unable to reconstruct complete thermal dynamic information of man-made targets when faced with this type of data, posing challenges to urban thermal environment analysis, energy consumption assessment, and anomaly heat source identification.

[0004] Therefore, there is an urgent need for an infrared temporal feature reconstruction and analysis method to solve the problem of being unable to reconstruct complete thermal dynamic information of artificial targets using sparse infrared remote sensing data, thereby improving the accuracy and completeness of obtaining thermal dynamic information of artificial targets and providing reliable support for research and application in related fields. Summary of the Invention

[0005] The purpose of this application is to provide an infrared temporal feature reconstruction and analysis method, system, device, medium and product that can make full use of the constraint effect of physical model on the thermal characteristic changes of artificial targets, and combine limited sparse infrared temperature observation data to accurately reconstruct the complex infrared temporal features of artificial targets.

[0006] To achieve the above objectives, this application provides the following solution: Firstly, this application provides an infrared temporal feature reconstruction and analysis method, including: Acquire sparse infrared temperature observation data of the artificial target area; the sparse infrared temperature observation data includes the surface temperature at multiple discrete times; Based on the principle of energy balance, a thermodynamic differential equation for the artificial target area is constructed; the thermodynamic differential equation uses the surface temperature sequence as the unknown function and the surface heat capacity and sensible-latent heat coefficient as the parameters to be inverted. Based on the sparse infrared temperature observation data, the parameters to be inverted in the thermodynamic differential equation are iteratively inverted using the least squares algorithm until a preset termination condition is met, thereby obtaining the optimal surface heat capacity and the optimal sensible-latent heat coefficient. The preset termination condition includes that the sum of squares of the residuals between the surface temperature output by the thermodynamic differential equation and the surface temperature at the corresponding time in the sparse infrared temperature observation data is less than a preset residual sum of squares threshold, or that the relative change in surface heat capacity after a preset number of consecutive iterations is less than a preset heat capacity change threshold and the relative change in sensible-latent heat coefficient is less than a preset sensible-latent heat coefficient change threshold. Based on the optimal surface heat capacity and the optimal sensible heat-latent heat coefficient, a continuous surface temperature sequence is obtained by integrating the thermodynamic differential equation forward and backward. Based on the continuous surface temperature sequence, infrared temporal features are extracted and reconstructed; the infrared temporal features include diurnal temperature range, cooling rate, and thermal hysteresis index.

[0007] Secondly, this application provides an infrared temporal feature reconstruction and analysis system, comprising: The data acquisition module is used to acquire sparse infrared temperature observation data of the artificial target area; the sparse infrared temperature observation data includes the surface temperature at multiple discrete times; The equation construction module is used to construct the thermodynamic differential equation of the artificial target area based on the principle of energy balance. The thermodynamic differential equation uses the surface temperature sequence as the unknown function and the surface heat capacity and sensible heat-latent heat coefficient as the parameters to be inverted. The parameter inversion module is used to perform iterative parameter inversion on the parameters to be inverted in the thermodynamic differential equation based on the sparse infrared temperature observation data using a least squares algorithm until a preset termination condition is met to end the iteration, thereby obtaining the optimal surface heat capacity and the optimal sensible-latent heat coefficient. The preset termination condition includes that the sum of squares of the residuals between the surface temperature output by the thermodynamic differential equation and the surface temperature at the corresponding time in the sparse infrared temperature observation data is less than a preset residual sum of squares threshold, or that the relative change in surface heat capacity after a preset number of consecutive iterations is less than a preset heat capacity change threshold and the relative change in sensible-latent heat coefficient is less than a preset sensible-latent heat coefficient change threshold. The continuous surface temperature sequence acquisition module is used to obtain the continuous surface temperature sequence by integrating the thermodynamic differential equation forward and backward based on the optimal surface heat capacity and the optimal sensible heat-latent heat coefficient. The infrared time series feature reconstruction module is used to extract and reconstruct infrared time series features based on the continuous surface temperature sequence; the infrared time series features include diurnal temperature range, cooling rate and thermal hysteresis index.

[0008] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the infrared temporal feature reconstruction analysis method described in any one of the above.

[0009] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the infrared temporal feature reconstruction and analysis method described in any one of the above descriptions.

[0010] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the infrared temporal feature reconstruction and analysis method described above.

[0011] According to the specific embodiments provided in this application, this application has the following technical effects: This application provides an infrared time-series feature reconstruction and analysis method, system, equipment, medium, and product. By acquiring sparse infrared temperature observation data of artificial target areas, it provides basic data for subsequent analysis, solving the data source problem and realizing the effective collection of raw monitoring data. By constructing thermodynamic differential equations based on the energy balance principle and establishing an analysis model based on scientific theory, it solves the problem of lacking a reasonable analysis model and realizes a mathematical description of the thermal characteristics changes of artificial targets. By using the least squares algorithm to iteratively invert the optimal parameters based on sparse data, it solves the problem of parameter determination and realizes the accurate solution of key parameters. By integrating the optimal parameters to obtain a continuous surface temperature sequence and extracting and reconstructing infrared time-series features, it solves the problem of difficulty in feature acquisition caused by data discontinuity and realizes the complete reconstruction of the infrared time-series features of artificial targets. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is an application environment diagram of an infrared temporal feature reconstruction and analysis method according to an embodiment of this application; Figure 2 A flowchart illustrating an infrared temporal feature reconstruction and analysis method provided in an embodiment of this application; Figure 3 A flowchart illustrating an infrared temporal feature reconstruction and analysis method provided in another embodiment of this application; Figure 4 This is a comparison chart of sparse observations and temporal reconstruction provided in an embodiment of this application; Figure 5 A functional module diagram of an infrared temporal feature reconstruction and analysis system provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0014] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0015] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0016] The infrared temporal feature reconstruction and analysis method provided in this application can be applied to, for example... Figure 1In the application environment shown, terminal 101 communicates with server 102 via a network. A data storage system can store the data that server 102 needs to process. The data storage system can be set up independently, integrated into server 102, or placed in the cloud or on other servers. Terminal 101 can send sparse infrared temperature observation data of the artificial target area to server 102. After receiving the sparse infrared temperature observation data of the artificial target area, server 102 constructs a thermodynamic differential equation for the artificial target area based on the principle of energy balance. The thermodynamic differential equation uses the surface temperature sequence as the unknown function and the surface heat capacity and sensible-latent heat coefficient as the parameters to be inverted. Based on the sparse infrared temperature observation data, the parameters to be inverted in the thermodynamic differential equation are iteratively inverted using a least squares algorithm until a preset termination condition is met, thus obtaining the optimal surface heat capacity and the optimal sensible-latent heat coefficient. The termination conditions include: the sum of squared residuals between the surface temperature output by the thermodynamic differential equation and the surface temperature at the corresponding time in the sparse infrared temperature observation data is less than a preset threshold for the sum of squared residuals; or the relative change in surface heat capacity after a preset number of consecutive iterations is less than a preset threshold for heat capacity change and the relative change in sensible-latent heat coefficient is less than a preset threshold for sensible-latent heat coefficient change. Based on the optimal surface heat capacity and optimal sensible-latent heat coefficient, a continuous surface temperature sequence is obtained by integrating the thermodynamic differential equation forward and backward. Based on the continuous surface temperature sequence, infrared temporal features are extracted and reconstructed. The infrared temporal features include diurnal temperature range, cooling rate, and thermal hysteresis index. The server 102 can feed back the obtained infrared temporal features to the terminal 101. In addition, in some embodiments, the infrared temporal feature reconstruction analysis method can also be implemented by the server 102 or the terminal 101 alone. For example, the terminal 101 can directly perform infrared temporal feature reconstruction analysis on the sparse infrared temperature observation data of the artificial target area, or the server 102 can obtain the sparse infrared temperature observation data of the artificial target area from the data storage system and perform infrared temporal feature reconstruction analysis on the sparse infrared temperature observation data of the artificial target area.

[0017] The terminal 101 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. The server 102 can be implemented using a standalone server or a server cluster consisting of multiple servers, or it can be a cloud server.

[0018] In one exemplary embodiment, such as Figure 2 As shown, an infrared temporal feature reconstruction and analysis method is provided. This method is executed by a computer device, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 102 as an example, the explanation includes the following steps 201 to 208. Wherein: Step 201: Obtain sparse infrared temperature observation data of the artificial target area; the sparse infrared temperature observation data includes the surface temperature at multiple discrete times.

[0019] Step 202: Based on the principle of energy balance, construct the thermodynamic differential equation for the artificial target area; the thermodynamic differential equation uses the surface temperature sequence as the unknown function and the surface heat capacity and sensible-latent heat coefficient as the parameters to be inverted.

[0020] Step 203: Based on the sparse infrared temperature observation data, the parameters to be inverted in the thermodynamic differential equation are iteratively inverted using the least squares algorithm until a preset termination condition is met to end the iteration, thereby obtaining the optimal surface heat capacity and the optimal sensible-latent heat coefficient. The preset termination condition includes that the sum of squares of the residuals between the surface temperature output by the thermodynamic differential equation and the surface temperature at the corresponding time in the sparse infrared temperature observation data is less than a preset residual sum of squares threshold, or that the relative change in surface heat capacity after a preset number of consecutive iterations is less than a preset heat capacity change threshold and the relative change in sensible-latent heat coefficient is less than a preset sensible-latent heat coefficient change threshold.

[0021] Step 204: Based on the optimal surface heat capacity and the optimal sensible heat-latent heat coefficient, a continuous surface temperature sequence is obtained by integrating the thermodynamic differential equation forward and backward.

[0022] Step 205: Based on the continuous surface temperature sequence, extract and reconstruct infrared time-series features; the infrared time-series features include diurnal temperature range, cooling rate, and thermal hysteresis index.

[0023] By implementing steps 201 to 205 above, this application can fully utilize the computing power of computer equipment to efficiently and accurately reconstruct and analyze the infrared temporal characteristics of artificial target areas. By acquiring sparse infrared temperature observation data and constructing thermodynamic differential equations based on the energy balance principle, this application can scientifically describe the thermal characteristic changes of artificial targets. Then, by using the least squares algorithm for parameter iterative inversion, key parameters are accurately solved. Finally, through integration and feature extraction, continuous thermal dynamic information of artificial targets and complete reconstruction of infrared temporal characteristics are achieved, providing reliable data support for applications such as urban thermal environment analysis and energy consumption assessment, effectively improving the accuracy and scientific rigor of research and decision-making in related fields.

[0024] In another exemplary embodiment of this application, the thermodynamic differential equation is: .

[0025] Where C represents the Earth's surface heat capacity; Represents the surface temperature at time t; Indicates surface albedo; Represents the total solar irradiance at time t; Let t represent the angle of solar incidence at time t; This represents the downward longwave radiation in the atmosphere at time t; Indicates the surface emissivity; This represents the Stefan-Boltzmann constant; Represents the sensible heat flux at time t; This represents the latent heat flux at time t.

[0026] In another exemplary embodiment of this application, based on the sparse infrared temperature observation data, the parameters to be inverted in the thermodynamic differential equation are iteratively inverted using a least squares algorithm until a preset termination condition is met to end the iteration, thereby obtaining the optimal surface heat capacity and the optimal sensible heat-latent heat coefficient, specifically including: Initialize the parameters to be inverted and the iteration step size, and use the sum of squared residuals between the surface temperature output by the thermodynamic differential equation and the surface temperature at the corresponding time in the sparse infrared temperature observation data as the objective function.

[0027] Based on the parameters to be inverted in the i-th iteration, the partial derivatives of the objective function in the i-th iteration with respect to the surface heat capacity and the sensible-latent heat coefficient are calculated to obtain the Jacobian matrix of the i-th iteration.

[0028] The update equation for the i-th iteration is constructed using the Jacobian matrix and the iteration step size. Solving the update equation for the i-th iteration yields the parameters to be inverted in the i-th iteration.

[0029] Based on the updated parameters to be inverted in the i-th iteration, calculate the update objective function value for the i-th iteration.

[0030] If the updated objective function value of the i-th iteration is less than the objective function value of the i-th iteration, then the iteration step size is multiplied by one-half.

[0031] If the updated objective function value of the i-th iteration is greater than or equal to the objective function value of the i-th iteration, then the iteration step size is multiplied by two.

[0032] Let i = i + 1, return to the step of "Calculate the partial derivatives of the objective function of the i-th iteration with respect to the surface heat capacity and the sensible-latent heat coefficient based on the parameters to be inverted in the i-th iteration, and obtain the Jacobian matrix of the i-th iteration" until the preset termination condition is met to end the iteration and obtain the optimal surface heat capacity and the optimal sensible-latent heat coefficient.

[0033] In another exemplary embodiment of this application, based on the continuous surface temperature sequence, infrared temporal features are extracted and reconstructed, specifically including: The difference between the highest and lowest surface temperature values ​​within the continuous surface temperature sequence is taken as the daily temperature difference.

[0034] Within the continuous surface temperature sequence, the absolute value of the difference between the surface temperature at the first preset time after sunset and the surface temperature at the second preset time before sunrise is divided by the time interval to obtain the cooling rate.

[0035] The difference between the surface temperature at the peak temperature and the surface temperature at noon is taken as the thermal hysteresis index within the continuous surface temperature sequence.

[0036] In another exemplary embodiment of this application, the solar incidence angle is calculated using the following formula: .

[0037] .

[0038] .

[0039] in, Indicates the latitude of the artificial target area; Indicates the solar declination; n represents the Julian Day. represents the hour angle; t represents time t.

[0040] The sensible heat flux and latent heat flux are combined into a single empirical term using the following formula: .

[0041] in, The empirical term at time t is represented; A represents the apparent comprehensive coefficient of the land-atmosphere turbulent exchange; (unit: W·m) −2 ·K −1 ), wind speed, air density ρ, and specific heat at constant pressure c p Latent heat of water vapor Lv, momentum and heat / moisture transfer coefficient C H / C E The effects of surface roughness and humidity dependence can all be summarized into an equivalent constant (or slowly varying parameter). This represents the atmospheric temperature at time t.

[0042] In another exemplary embodiment of this application, obtaining sparse infrared temperature observation data of an artificial target region specifically includes: Acquire remote sensing images of an artificial target area at multiple discrete times.

[0043] Radiometric calibration and atmospheric correction were performed on the infrared bands of remote sensing images at multiple discrete times to obtain the ground-based radiance at each discrete time.

[0044] A wide-channel temperature-radiance lookup table is constructed using the Planck inverse function. The radiance at each discrete moment is converted into the corresponding surface temperature through the lookup table to obtain sparse infrared temperature observation data.

[0045] The following example illustrates this application using a specific infrared temporal feature reconstruction and analysis process.

[0046] This application discloses a data analysis method for reconstructing the infrared temporal features of sparsely observed artificial targets based on physical model constraints. This method is applicable to infrared data environments with discontinuous remote sensing observation times and low observation frequencies, especially for artificial target areas with non-natural thermal characteristics, such as buildings, facilities, infrastructure, and vehicles. By constructing a physical dynamic model based on thermal balance and heat conduction, and combining it with sparse remote sensing observation points, an optimization algorithm is used to fit thermal parameters and state variables, achieving dynamic reconstruction of the target's continuous temperature changes. This method can recover the infrared temporal features of the target and further extract key features such as thermal hysteresis, diurnal temperature range, and thermal response rate, making it suitable for various fields such as intelligent monitoring, thermal environment diagnosis, and energy consumption analysis. This method combines physical consistency and data adaptability, possessing broad engineering application value.

[0047] like Figure 3 As shown, the processing flow of the method in this application includes six major modules: data preprocessing, target region extraction, physical modeling, model optimization and parameter fitting, temperature time series reconstruction, accuracy verification and quality evaluation.

[0048] First, the target region is extracted from the remote sensing image. Radiometric calibration, atmospheric correction, and surface temperature inversion are performed on the infrared image to obtain the surface brightness temperature and radiance of the target region. The proposed thermodynamic physical model is then used as a constraint to fit the sparse observation data under physical constraints. This process requires model optimization, simplifying the model to an exponential function under clear weather conditions. Model parameters are estimated using data from multiple time points. Based on the estimated parameters, time-series reconstruction is performed on the newly observed sparse data. Finally, accuracy verification and quality evaluation are conducted.

[0049] This application achieves the above objectives through the following technical steps: Step 1: Target identification and region extraction.

[0050] Using high-resolution remote sensing imagery or existing classification maps, artificial target areas (such as rooftops, roads, facilities, etc.) are identified, and their infrared brightness temperature or radiance values ​​at different time points are extracted. Ground-based radiance is extracted using radiometric calibration and atmospheric correction techniques for satellite images. A wide-channel temperature-radiance lookup table is constructed using the Planck inverse function, and infrared brightness temperature is extracted through this lookup table technique. First, the target area is extracted from the remote sensing image. Radiometric calibration, atmospheric correction, and surface temperature inversion are performed on the infrared image to obtain the surface brightness temperature and radiance of the target area. The proposed thermodynamic physical model is used as a constraint to fit the sparse observation data under physical constraints. This process requires model optimization and parameter estimation. Based on the estimated parameters, time-series reconstruction is performed on the newly observed sparse data, and finally, accuracy verification and quality evaluation are conducted.

[0051] As an alternative implementation, sparse observation data can also come from drones or ground-based infrared equipment.

[0052] Step 2: Construct a physical thermal equilibrium differential model.

[0053] Based on the theories of energy balance and heat conduction, a physical thermal balance differential model describing the thermal changes on the surface of an artificial target is established. The purpose of this model is to improve the fitting accuracy of the sparse data-driven dynamic fitting (step 3). The model's formula is shown below: .

[0054] Where C represents the Earth's surface heat capacity (J·m³) -2 ·K -1 ); Represents the surface temperature at time t; Indicates surface albedo; Represents the total solar irradiance (incident radiation intensity) at time t; Let t represent the angle of solar incidence at time t; This represents the downward longwave radiation in the atmosphere at time t; Indicates the surface emissivity; This represents the Stefan-Boltzmann constant; Represents the sensible heat flux at time t; This represents the latent heat flux at time t; if no flux observation is available, it can be grouped into empirical or fitted terms.

[0055] The heat capacity C value varies greatly for different land features such as cities, bare soil, and vegetation, and can be used as an important feature parameter for classification or model fitting.

[0056] Step 3: Boundary condition modeling and prior information introduction.

[0057] The parameters of the thermal equilibrium differential model in step 2 are initialized using existing data as prior knowledge for model calculation. Prior thermal parameter constraints are introduced based on the material library and environmental conditions to improve reconstruction accuracy and physical plausibility.

[0058] For the angle of solar incidence The calculation uses the methods for calculating time and latitude / longitude location: .

[0059] .

[0060] .

[0061] in, Indicates the latitude of the artificial target area; represents the solar declination; n represents the Julian day (the day of the year). t represents the hour angle; t represents time t; t is solar time (hours).

[0062] A database of thermal radiation parameters and a spectral library of typical materials (such as metals, concrete, and asphalt) are introduced, such as an emissivity spectrum library, to assign values ​​to surface albedo α and surface emissivity ε.

[0063] By incorporating atmospheric parameters such as ERA5 environmental data, prior knowledge of atmospheric radiation is provided, including downward-flowing longwave radiation L↓(t) and total solar irradiance S(t). The time-varying function S(t) is derived from observational or meteorological data: S(t) = S0. cos(θ(t)): can be calculated from the solar altitude angle; S0 represents the maximum total solar radiation at the bottom of the atmosphere, which refers to the total solar radiation on the plane perpendicular to the sunlight after atmospheric attenuation. Cloud cover: different scenarios can be set (sunny day, intermittent clouds, full clouds).

[0064] The combined sensible and latent heat fluxes (H(t) and LE(t)) are expressed as an empirical term HLE(t), which is approximately proportional to the difference between surface temperature and atmospheric temperature, and is expressed as follows: .

[0065] in, The empirical term at time t is represented; A represents the apparent comprehensive coefficient of the land-atmosphere turbulent exchange; (unit: W·m) −2 ·K −1 ), wind speed, air density ρ, and specific heat at constant pressure c p Latent heat of water vapor Lv, momentum and heat / moisture transfer coefficient C H / C E The effects of surface roughness and humidity dependence can all be summarized into an equivalent constant (or slowly varying parameter). The atmospheric temperature at time t is represented by T(t), which is the temperature at the time of observation and is obtained by inversion from remote sensing observation data.

[0066] Step 4: Sparse data-driven dynamic fitting.

[0067] The sparse observation points Tobs(ti) obtained by remote sensing are fused with the heat conduction equation in the model. Through least squares fitting under physical constraints, the thermal parameters are inverted and the continuous-time temperature sequence T(t) is reconstructed.

[0068] After initialization using the above steps, the unknown parameters are the surface heat capacity C and the empirical term HLE(t) combining sensible and latent heat fluxes. Using Tobs(ti) from at least two sets of observation points, a complete equation can be constructed to solve for these two unknowns. This solution process employs the least squares algorithm. Once these two unknowns are determined, the time-series temperature T(t) can be output using the model formula. Parameter estimation can be completed by fitting data from a finite number of observation points (such as GF5 VIMI daytime / nighttime products and infrared observation data from multiple JB transit points). Multiple sets of observation data are used to estimate the model coefficients; the time-series temperature is calculated based on the model coefficients; to ensure the stability and accuracy of the results, at least two sets of observation data are used to regress the model parameters and reconstruct the entire diurnal variation curve.

[0069] Step 5: Result verification.

[0070] It outputs a continuous-time infrared temperature sequence T(t), extracts time-series characteristic parameters (such as daily temperature difference, cooling rate, thermal hysteresis, etc.), and can analyze the sensitivity to observation errors.

[0071] like Figure 4 As shown, the differences and fitting effects between sparse observation points and continuous temperature curves are illustrated.

[0072] This application also provides the following two specific application scenarios: Scenario 1: Identification of thermal hysteresis in road asphalt.

[0073] Intermittent sampling of road areas is performed using high temporal resolution ground infrared cameras or drones. Based on this method, a thermal model is constructed to reconstruct the temperature changes throughout the day and identify the differences in heat flux response of different materials (such as cement / asphalt).

[0074] Scenario 2: Abnormal thermal monitoring of ships at sea.

[0075] Intermittent remote sensing observations were deployed near ships anchored at sea. The reconstruction results were used to identify temperature changes during non-observation periods, infrared contrast between the ships and the seawater background, and the reversal time of the infrared contrast.

[0076] The specific methods and limitations of existing infrared temporal feature reconstruction analysis are shown in Table 1 below.

[0077] Table 1. Comparison of Existing Infrared Temporal Feature Reconstruction and Analysis Methods and Their Limitations

[0078] This application: 1. Introduces a thermodynamic differential model: using heat capacity, radiation balance, and heat flux terms to model artificial targets, improving physical plausibility. 2. Applicable to sparse data: enabling time-series recovery under conditions of sparse remote sensing observation time and limited data points. 3. Integrates prior knowledge: combining multi-source information such as ground feature material libraries and solar orbit parameters to improve model robustness. 4. Strong multi-platform adaptability: applicable to Landsat, MODIS, AIRS, GF series, and UAV infrared platforms. 5. Outputs thermal behavior indicators: supporting further extraction of infrared behavior parameters such as heating rate, thermal hysteresis, and cooling time.

[0079] Based on the same inventive concept, this application also provides an infrared temporal feature reconstruction and analysis system for implementing the infrared temporal feature reconstruction and analysis method described above. The solution provided by this system is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more infrared temporal feature reconstruction and analysis system embodiments provided below can be found in the limitations of the infrared temporal feature reconstruction and analysis method described above, and will not be repeated here.

[0080] In one exemplary embodiment, such as Figure 5 As shown, an infrared temporal feature reconstruction and analysis system is provided, including: The data acquisition module 301 is used to acquire sparse infrared temperature observation data of the artificial target area; the sparse infrared temperature observation data includes the surface temperature at multiple discrete times.

[0081] The equation construction module 302 is used to construct the thermodynamic differential equation of the artificial target area based on the principle of energy balance; the thermodynamic differential equation uses the surface temperature sequence as the unknown function and the surface heat capacity and sensible heat-latent heat coefficient as the parameters to be inverted.

[0082] The parameter inversion module 303 is used to perform parameter iterative inversion on the parameters to be inverted in the thermodynamic differential equation based on the sparse infrared temperature observation data using a least squares algorithm until a preset termination condition is met to end the iteration, thereby obtaining the optimal surface heat capacity and the optimal sensible heat-latent heat coefficient. The preset termination condition includes that the sum of squares of the residuals between the surface temperature output by the thermodynamic differential equation and the surface temperature at the corresponding time in the sparse infrared temperature observation data is less than a preset residual sum of squares threshold, or that the relative change in surface heat capacity after a preset number of consecutive iterations is less than a preset heat capacity change threshold and the relative change in sensible heat-latent heat coefficient is less than a preset sensible heat-latent heat coefficient change threshold.

[0083] The continuous surface temperature sequence acquisition module 304 is used to obtain the continuous surface temperature sequence by integrating the thermodynamic differential equation forward and backward based on the optimal surface heat capacity and the optimal sensible heat-latent heat coefficient.

[0084] The infrared time series feature reconstruction module 305 is used to extract and reconstruct infrared time series features based on the continuous surface temperature sequence; the infrared time series features include daily temperature difference, cooling rate and thermal hysteresis index.

[0085] In summary, this application has the following beneficial effects: Efficient utilization of sparse data: The complete temperature curve of the target can be reconstructed with only a few time points of infrared observation.

[0086] Physical consistency guarantee: Physical constraints are constructed through thermodynamic equations to effectively suppress model drift and error accumulation.

[0087] Enhanced target characteristic recognition: The reconstruction results can be used to analyze changes in the material, structure, and usage status of artificial targets.

[0088] Highly adaptable: Suitable for various infrared remote sensing data sources such as Landsat, MODIS, GF, and AIRS.

[0089] This application proposes a data analysis method for reconstructing the infrared temporal features of sparsely observed artificial targets based on physical model constraints. Combining a thermodynamic model and optimization algorithms, it achieves continuous recovery of infrared temperature variations of artificial targets even under sparse data conditions, demonstrating significant practical application value. The proposed method is adaptable to different observation platforms and ground cover types, balancing physical rigor with engineering feasibility, and exhibits significant innovation and potential for widespread application.

[0090] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 6As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores infrared temporal feature reconstruction and analysis data. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements an infrared temporal feature reconstruction and analysis method.

[0091] Those skilled in the art will understand that Figure 6 The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0092] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0093] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0094] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0095] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0096] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0097] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0098] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for reconstructing and analyzing infrared temporal features, characterized in that, The infrared temporal feature reconstruction and analysis method includes: Acquire sparse infrared temperature observation data of the artificial target area; the sparse infrared temperature observation data includes the surface temperature at multiple discrete times; Based on the principle of energy balance, a thermodynamic differential equation for the artificial target area is constructed; the thermodynamic differential equation uses the surface temperature sequence as the unknown function and the surface heat capacity and sensible-latent heat coefficient as the parameters to be inverted. Based on the sparse infrared temperature observation data, the parameters to be inverted in the thermodynamic differential equation are iteratively inverted using the least squares algorithm until a preset termination condition is met, thereby obtaining the optimal surface heat capacity and the optimal sensible-latent heat coefficient. The preset termination condition includes that the sum of squares of the residuals between the surface temperature output by the thermodynamic differential equation and the surface temperature at the corresponding time in the sparse infrared temperature observation data is less than a preset residual sum of squares threshold, or that the relative change in surface heat capacity after a preset number of consecutive iterations is less than a preset heat capacity change threshold and the relative change in sensible-latent heat coefficient is less than a preset sensible-latent heat coefficient change threshold. Based on the optimal surface heat capacity and the optimal sensible heat-latent heat coefficient, a continuous surface temperature sequence is obtained by integrating the thermodynamic differential equation forward and backward. Based on the continuous surface temperature sequence, infrared temporal features are extracted and reconstructed; the infrared temporal features include diurnal temperature range, cooling rate, and thermal hysteresis index.

2. The infrared temporal feature reconstruction and analysis method according to claim 1, characterized in that, The thermodynamic differential equation is: ； Where C represents the Earth's surface heat capacity; Represents the surface temperature at time t; Indicates surface albedo; Represents the total solar irradiance at time t; Let t represent the angle of solar incidence at time t; This represents the downward longwave radiation in the atmosphere at time t; Indicates the surface emissivity; This represents the Stefan-Boltzmann constant; Represents the sensible heat flux at time t; This represents the latent heat flux at time t.

3. The infrared temporal feature reconstruction and analysis method according to claim 1, characterized in that, Based on the sparse infrared temperature observation data, the parameters to be inverted in the thermodynamic differential equation are iteratively inverted using a least squares algorithm until a preset termination condition is met, thus obtaining the optimal surface heat capacity and the optimal sensible-latent heat coefficient, specifically including: Initialize the parameters to be inverted and the iteration step size, and use the sum of squared residuals between the surface temperature output by the thermodynamic differential equation and the surface temperature at the corresponding time in the sparse infrared temperature observation data as the objective function; Based on the parameters to be inverted in the i-th iteration, the partial derivatives of the objective function in the i-th iteration with respect to the surface heat capacity and the sensible-latent heat coefficient are calculated to obtain the Jacobian matrix of the i-th iteration. The update equation for the i-th iteration is constructed using the Jacobian matrix and the iteration step size. Solving the update equation for the i-th iteration yields the updated inversion parameters for the i-th iteration. Based on the updated parameters to be inverted in the i-th iteration, calculate the update objective function value for the i-th iteration; If the updated objective function value of the i-th iteration is less than the objective function value of the i-th iteration, then the iteration step size is multiplied by one-half; If the updated objective function value of the i-th iteration is greater than or equal to the objective function value of the i-th iteration, then the iteration step size is multiplied by two. Let i = i + 1, return to the step of "Calculate the partial derivatives of the objective function of the i-th iteration with respect to the surface heat capacity and sensible-latent heat coefficient based on the parameters to be inverted in the i-th iteration, and obtain the Jacobian matrix of the i-th iteration" until the preset termination condition is met to end the iteration and obtain the optimal surface heat capacity and optimal sensible-latent heat coefficient.

4. The infrared temporal feature reconstruction and analysis method according to claim 1, characterized in that, Based on the continuous surface temperature sequence, infrared temporal features are extracted and reconstructed, specifically including: The difference between the highest and lowest surface temperature values ​​within the continuous surface temperature sequence is taken as the daily temperature difference. Within the continuous surface temperature sequence, the absolute value of the difference between the surface temperature at the first preset time after sunset and the surface temperature at the second preset time before sunrise is divided by the time interval to obtain the cooling rate. The difference between the surface temperature at the peak temperature and the surface temperature at noon is taken as the thermal hysteresis index within the continuous surface temperature sequence.

5. The infrared temporal feature reconstruction and analysis method according to claim 2, characterized in that, The angle of solar incidence is calculated using the following formula: ； ； ； in, Indicates the latitude of the artificial target area; Indicates the solar declination; n represents the Julian Day. The time angle is represented by t; t represents time t. The sensible heat flux and latent heat flux are combined into a single empirical term using the following formula: ； in, The empirical term at time t is represented; A represents the apparent comprehensive coefficient of the earth-atmosphere turbulent exchange. This represents the atmospheric temperature at time t.

6. The infrared temporal feature reconstruction and analysis method according to claim 1, characterized in that, Acquiring sparse infrared temperature observation data of artificial target regions, specifically including: Acquire remote sensing images of an artificial target area at multiple discrete times; Radiometric calibration and atmospheric correction were performed on the infrared bands of remote sensing images at multiple discrete times to obtain the ground radiance at each discrete time. A wide-channel temperature-radiance lookup table is constructed using the Planck inverse function. The radiance at each discrete moment is converted into the corresponding surface temperature through the lookup table to obtain sparse infrared temperature observation data.

7. An infrared temporal feature reconstruction and analysis system, characterized in that, The infrared time-series feature reconstruction and analysis system applies the infrared time-series feature reconstruction and analysis method according to any one of claims 1-6, and the infrared time-series feature reconstruction and analysis system comprises: The data acquisition module is used to acquire sparse infrared temperature observation data of the artificial target area; the sparse infrared temperature observation data includes the surface temperature at multiple discrete times; The equation construction module is used to construct the thermodynamic differential equation of the artificial target area based on the principle of energy balance. The thermodynamic differential equation uses the surface temperature sequence as the unknown function and the surface heat capacity and sensible heat-latent heat coefficient as the parameters to be inverted. The parameter inversion module is used to perform iterative parameter inversion on the parameters to be inverted in the thermodynamic differential equation based on the sparse infrared temperature observation data using a least squares algorithm until a preset termination condition is met to end the iteration, thereby obtaining the optimal surface heat capacity and the optimal sensible-latent heat coefficient. The preset termination condition includes that the sum of squares of the residuals between the surface temperature output by the thermodynamic differential equation and the surface temperature at the corresponding time in the sparse infrared temperature observation data is less than a preset residual sum of squares threshold, or that the relative change in surface heat capacity after a preset number of consecutive iterations is less than a preset heat capacity change threshold and the relative change in sensible-latent heat coefficient is less than a preset sensible-latent heat coefficient change threshold. The continuous surface temperature sequence acquisition module is used to obtain the continuous surface temperature sequence by integrating the thermodynamic differential equation forward and backward based on the optimal surface heat capacity and the optimal sensible heat-latent heat coefficient. The infrared time series feature reconstruction module is used to extract and reconstruct infrared time series features based on the continuous surface temperature sequence; the infrared time series features include diurnal temperature range, cooling rate and thermal hysteresis index.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the infrared temporal feature reconstruction analysis method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the infrared temporal feature reconstruction and analysis method according to any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the infrared temporal feature reconstruction and analysis method according to any one of claims 1-6.

Images