Height measuring method and height measuring device

Abstract

The invention relates to a height measuring method and a height measuring device. The height measuring method comprises the following steps: acquiring actually measured environment data and actually measured altitude of each station in a plurality of stations in an object area; calculating the theoretical height of the site according to the actually measured environment data; determining the height deviation between the actually measured altitude and the theoretical height; based on the actually measured environment data and the height deviations corresponding to the multiple sites, a preset space-time fusion algorithm is adopted, and predicted environment data and predicted height deviations of all grid points in the object area are determined; for any to-be-measured grid point in the object area, determining a prediction theoretical height according to the prediction environment data; and determining the height corresponding to the to-be-measured grid point according to the predicted theoretical height and the predicted height deviation corresponding to the to-be-measured grid point. According to the scheme, multi-source sensor data and a meteorological field correction technology can be fused, and the consistency of cross-platform high expression, the prediction precision and the safety and reliability of airspace management are remarkably improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a height measurement method and measuring device. Background Technology

[0002] With the rapid development of the low-altitude economy, the development and utilization of airspace resources are no longer limited to the mid-to-high altitude areas, but are gradually extending to the low-altitude and even ultra-low-altitude ranges. The demand for drones, general aviation and civil aviation to operate in the same airspace is increasing day by day.

[0003] However, there are significant differences in the measurement and expression of vertical altitude among drones, general aviation, and civil aviation: drones typically use a fusion of GNSS (Global Navigation Satellite System) / RTK (Real-Time Kinematic) and barometers for altimetry, or rely on millimeter-wave / lidar ranging technology, and their altitude information is mostly expressed in true altitude (AGL) or standard altitude (MSL); general aviation widely uses GNSS / Baro-VNAV or simplified barometric altimeters for altitude measurement, and the expression includes true altitude (AGL), MSL, and standard barometric altitude; civil aircraft in the terminal area usually rely on a barometric altimeter system that integrates GNSS / INS and an atmospheric data computer (ADC), and their altitude is generally expressed in corrected sea level pressure (SBP) form. This lack of uniformity in altitude expression has brought many confusions and coordination challenges to airspace management.

[0004] Furthermore, there are significant differences in altitude expression standards among different aircraft. The altitude accuracy of unmanned aerial vehicles (UAVs) is generally ±1~3m (under ideal GNSS conditions), but can deteriorate to over ±10m in urban canyons or complex electromagnetic environments. General aviation, constrained by weather conditions and equipment level, often has an altitude error of ±10~30m. Civil aviation, under different weather conditions and atmospheric pressure variations, can still experience deviations of ±20~50m when correcting for sea pressure altitude. This difference is particularly pronounced in low-altitude airspace (0–1000m). Due to the high density and maneuverability of low-altitude aircraft, even a deviation of tens of meters in altitude can easily lead to airspace management chaos, flight path planning and obstacle avoidance failures, resulting in a significant decrease in airspace safety and management controllability.

[0005] In response to the aforementioned problems of inconsistent methods and insufficient accuracy in altitude measurement, and the resulting chaos in airspace management, a new and unified method and system for altitude measurement is urgently needed. Summary of the Invention

[0006] The inventors discovered that existing technologies have the following drawbacks in height measurement and correction: Sparse sensor deployment: Due to cost and deployment conditions, ground meteorological sensors cannot be deployed on a large scale and densely, resulting in insufficient spatial resolution of key parameters such as temperature, humidity and air pressure. Single prediction model: Traditional methods often rely on simple barometric altitude formulas or single interpolation methods, which cannot make full use of time-series features and multi-source information, resulting in insufficient prediction accuracy; Lack of meteorological field correction mechanism: There is a physical coupling relationship between environmental parameters such as temperature and humidity and air pressure, but the existing scheme does not effectively utilize this relationship, making it difficult to correct the measured air pressure in real time; There is a lack of unified conversion for altitude representation: even with multi-source data, there is a lack of effective methods for unified conversion of different altitude forms (true altitude (AGL), altitude at sea level (MSL), corrected sea level pressure altitude (QNH), and standard pressure altitude), making it difficult to apply directly to vertical airspace management.

[0007] To address the aforementioned issues, this application provides an altitude measurement scheme that integrates multi-source sensor data with meteorological field correction technology. Under limited deployment conditions, it enables accurate extrapolation from sparse observations to dense fields. Furthermore, through a unified altitude conversion mechanism, it significantly improves the consistency of altitude representation across platforms, prediction accuracy, and the security and reliability of airspace management.

[0008] According to a first aspect of this application, a method for measuring height is provided, characterized in that it includes: The measured environmental data and measured altitude of each of the multiple stations in the target area are obtained. The target area includes multiple grid points, and the stations are grid points equipped with data acquisition modules. The multiple grid points include grid points to be measured. The theoretical height of the site is calculated based on the measured environmental data. Determine the altitude deviation between the measured altitude and the theoretical altitude; Based on the measured environmental data and height deviation corresponding to each of the multiple stations, a preset spatiotemporal fusion algorithm is used to determine the predicted environmental data and predicted height deviation of each grid point in the object area. For any grid point to be measured in the object region, the predicted theoretical height is determined based on the predicted environment data; and The height corresponding to the grid point to be measured is determined based on the deviation between the predicted theoretical height and the predicted height corresponding to the grid point to be measured.

[0009] According to a second aspect of this application, a height measuring device is provided, characterized in that it comprises: The acquisition module is used to acquire the measured environmental data and measured altitude of each of the multiple stations in the target area. The target area includes multiple grid points, and the stations are grid points equipped with data acquisition modules. The multiple grid points include grid points to be measured. The first calculation module is used to calculate the theoretical height of the site based on the measured environmental data; The first determining module is used to determine the altitude deviation between the measured altitude and the theoretical altitude; The second determining module is used to determine the predicted environmental data and predicted height deviation of each grid point in the object area based on the measured environmental data and the height deviation corresponding to each of the multiple stations, using a preset spatiotemporal fusion algorithm. The second calculation module is used to calculate the predicted theoretical height for any grid point to be tested in the object region based on the predicted environment data; and The third determining module is used to determine the height corresponding to the grid point to be measured based on the deviation between the predicted theoretical height and the predicted height corresponding to the grid point to be measured.

[0010] According to a third aspect of this application, an electronic device is provided, comprising: Processor; and A memory storing computer instructions that, when executed by the processor, cause the processor to perform the method described in the first aspect.

[0011] According to a fourth aspect of this application, a non-transitory computer storage medium is provided, which stores a computer program that, when executed by a plurality of processors, causes the processors to perform the method described in the first aspect.

[0012] According to the height measurement method and device provided in this application, acquisition modules are deployed in a portion of the grid points within the target area to acquire environmental and height data in real time. Then, based on the measured environmental and height data, the height deviation of the grid points where the acquisition modules are deployed is determined. Using a pre-defined spatiotemporal fusion algorithm, the environmental data and height deviation of each grid point in the target area are predicted, and the environmental data and height deviation are reconstructed from sparse to dense matrix. Finally, based on the predicted environmental data and predicted height deviation, the height of each grid point is determined. This application's solution helps to achieve unified expression and management of airspace vertical height, improving the coordination and utilization efficiency of airspace resources. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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 exceeding the scope of protection claimed by this application.

[0014] Figure 1 This is a flowchart of a height measurement method according to an embodiment of this application.

[0015] Figure 2 This is a schematic diagram of the structure of a multi-source sensor acquisition box according to an embodiment of this application.

[0016] Figure 3 This is a flowchart of a height measurement method according to another embodiment of this application.

[0017] Figure 4 This is a schematic diagram of a height measuring device according to an embodiment of this application.

[0018] Figure 5 This is a schematic diagram of a height measuring device according to another embodiment of this application.

[0019] Figure 6 This is a schematic diagram of the structure of an electronic device provided in this application. Detailed Implementation

[0020] 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, not all, of the embodiments of this application. 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.

[0021] Overall, this application provides a unified altitude measurement method based on the densification and bias correction of sparse environmental observations. Its core lies in using the International Standard Atmosphere (ISA) model as the physical benchmark, combining sparse measured altitude data and environmental data to construct a dense "environmental data prediction" and "altitude bias prediction" for the entire target area, thereby achieving a high-precision, physically consistent, and extrapolable unified altitude expression. Specifically, this application first acquires the measured environment and corresponding measured altitude of sparse stations through self-deployed acquisition modules; then, based on the ISA pressure-altitude formula, it calculates the theoretical altitude of each station and compares it with the measured altitude to obtain the altitude bias of sparse stations; next, it uses a pre-defined spatiotemporal fusion algorithm to capture the evolution of temporal environmental data, generalizing the sparse environmental data into spatiotemporally continuous dense environmental data, and generalizing the sparse altitude bias points into a spatiotemporally continuous dense altitude bias field; finally, at any grid point in the target area, a high-precision unified altitude is obtained through "ISA theoretical altitude + bias correction value". Furthermore, this application supports seamless conversion to various altitude systems such as AGL, MSL, QNH, or standard barometric altimeter.

[0022] According to one aspect of this application, a method for measuring height is provided. Figure 1 This is a flowchart of a height measurement method according to an embodiment of this application. Figure 1 As shown, the method includes the following steps.

[0023] Step S101: Obtain the measured environmental data and measured altitude of each of the multiple stations in the target area.

[0024] In one embodiment, the object area is divided into multiple grid points, and the stations are grid points equipped with data acquisition modules.

[0025] In one specific embodiment, to extend sparse observations into a continuous prediction field, a regular grid can be established within the object region: (1) in, , For grid resolution; , Here are the coordinates of the bottom left corner of the region; m and n are the grid indices. Represents grid points.

[0026] In one embodiment, measured environmental data, including air pressure, temperature, and / or humidity (relative humidity), can be measured via the data acquisition module. Measured altitude can be measured either by an altimeter (e.g., GNSS / RTK) independent of the data acquisition module, or by the data acquisition module itself. In one specific embodiment, the data acquisition module may include a multi-source sensor acquisition box. Figure 2This is a schematic diagram of the structure of a multi-source sensor acquisition box according to an embodiment of this application. Figure 2 As shown, the multi-source sensor acquisition box includes a temperature sensor, a humidity sensor, and a barometer. The main controller can be a dedicated IoT (Internet of Things) chip, and it can also support technologies such as 4G Cat1 and GPS / BeiDou GNSS. Environmental temperature, humidity, and air pressure information are acquired via I2C connection to the temperature sensor, humidity sensor, and barometer, and then processed through the dedicated IoT chip. Since this is a device intended for long-term outdoor use, it needs to have extended functionality and low power consumption, thus requiring certain power management capabilities. The multi-source sensor acquisition box supports external power charging, battery level information acquisition, and power path selection.

[0027] Step S102: Calculate the theoretical height of the station based on the measured environmental data; Step S103: Determine the altitude deviation between the measured altitude and the theoretical altitude.

[0028] In one embodiment, at each station i in the target area, the measured air pressure P is known. i Temperature T i and humidity RH i The theoretical height can be calculated by following these steps: 1. The virtual temperature can be calculated using the following equation: (2) in, It represents the saturated vapor pressure, which is the maximum partial pressure of water vapor that air can hold at the current temperature. It is usually calculated from temperature using the Magnus formula. Indicates actual water vapor pressure, which refers to the actual partial pressure of water vapor in the air; Specific humidity refers to the ratio of the mass of water vapor in moist air to the total mass of moist air.

[0029] 2. The theoretical height of the ISA (using the virtual temperature corrected version of the ISA) can be calculated using the following formula: (3) in, .

[0030] In an optional embodiment, step S102 may include: Calculate the virtual temperature based on the measured environmental data; and The theoretical height of the station is calculated based on the virtual temperature.

[0031] In one embodiment, after obtaining the measured altitude and the theoretical altitude, the altitude deviation can be determined. In a specific embodiment, the altitude deviation can be calculated using the following equation: (4) in, This represents the measured altitude of station i. Indicating theoretical depth, This indicates a height deviation.

[0032] Step S104: Based on the measured environmental data and height deviation corresponding to each of the multiple stations, a preset spatiotemporal fusion algorithm is used to determine the predicted environmental data and predicted height deviation of each grid point in the object area.

[0033] In one embodiment, the spatiotemporal fusion algorithm combines regression kriging (RK) modeling with long short-term memory network (LSTM) modeling. By using regression kriging and LSTM to extrapolate and reconstruct the environmental data and height deviation of each grid point in the object region based on measured environmental data and height deviation, sparse environmental data is generalized into spatiotemporally continuous dense environmental data, and sparse height deviation points are generalized into spatiotemporally continuous dense height deviation fields.

[0034] In one specific embodiment, the algorithm takes "constructing a dense spatiotemporal data field with full coverage based on sparse observation point data" as its core objective. Through four key steps—spatial feature mining, spatial structure modeling, temporal dynamic prediction, and spatiotemporal information fusion—it achieves the transformation from discrete data to a continuous, high-precision data field. The specific technical path is as follows: I. Spatial Covariate Extraction: Constructing a Feature Support System To accurately characterize the spatial distribution patterns of the target variable, it is necessary to extract global spatial covariates that are intrinsically related to the target variable, forming a feature support system. The core variables include three categories: - Topographic feature variables: Based on elevation data extracted from the digital elevation model (DEM), reflecting the fundamental impact of topographic relief on the spatial distribution of the target variables; - Surface attribute variables: encompassing indicators derived from land cover types, such as building density and normalized difference vegetation index (NDVI), which characterize the differentiation of target variables caused by differences in underlying surface attributes; - Geographic location variables: These include distance parameters from key geographical elements such as coastlines, bodies of water, and major transportation routes, quantifying the constraining effect of location conditions on the target variable.

[0035] II. Regression Kriging (RK) Modeling: Analyzing Spatial Distribution Structure Regression Kriging (RK), as an optimization method for spatial interpolation, achieves accurate fitting of the spatial distribution of the target variable through a two-stage modeling process of "trend simulation + residual completion." The specific steps are as follows: 1. Trend term fitting: Random forest or generalized linear model (GLM) is used to construct the mapping relationship between spatial covariates and target variables. The spatial trend term of the target variable is output through model training to reflect the distribution law on a macro scale. 2. Residual interpolation: Calculate the difference between the observed value and the trend term (i.e., the residual), and use the ordinary kriging (OK) method to perform spatial interpolation on the residual to capture the spatial heterogeneity characteristics at the microscale; 3. Spatial prediction output: The trend term is superimposed with the interpolated residual to generate a spatial distribution field of the target variable that covers the entire domain, thus completing the densification of sparse points in the spatial dimension.

[0036] III. LSTM Model Building: Capturing Temporal Dynamics To address the temporal evolution characteristics of the target variable, an LSTM time series prediction model is constructed to achieve accurate prediction of the target variable at future times. The model design and training specifications are as follows: - Input and output definition: Using historical time series data of the target variable as input features, and the target variable value at a specific future moment as the model output, a time mapping relationship of "history-future" is constructed; - Training strategy configuration: Root mean square error (RMSE) is used as the model loss function to quantify the deviation between the predicted and true values; the Adam optimizer is selected to iteratively update the model parameters to improve convergence efficiency; an early stopping mechanism is introduced to terminate training when the validation set loss increases continuously, effectively avoiding model overfitting. - Time prediction output: The trained LSTM model outputs the prediction results of the target variable at future times, providing accurate data support in the time dimension for subsequent spatiotemporal fusion.

[0037] IV. Spatiotemporal Fusion: Generating High-Precision Dense Fields Based on the spatial dimension RK modeling results and the temporal dimension LSTM prediction results, an "observation-oriented" fusion strategy is adopted to achieve the complementarity and integration of spatiotemporal information, ultimately generating a global, continuous dense field of target variables. - Observational grid fusion rule: For grid points with actual measurement data, the time prediction result of the LSTM model is used as the main factor, and the RK spatial interpolation result of the grid point is combined for fine-tuning to make full use of the time dynamic accuracy advantage supported by the actual measurement data. - Unobserved grid point fusion rule: For grid points without actual data, the spatial distribution results output by the RK model are used as the core, and the regional temporal change trend predicted by the LSTM model is incorporated to make up for the lack of temporal dimension information when there is no observed data; - Final Dense Field Generation: By eliminating the systematic bias of a single model through the above fusion strategy, the final target variable bias correction field is constructed, forming a high-precision dense data field that combines spatial continuity and temporal dynamics.

[0038] This algorithm, through the technical route of "spatial covariate support - separate modeling of two models - observation-guided fusion", not only solves the problem of heterogeneity characterization in sparse point spatial interpolation, but also makes up for the shortcomings of traditional methods in terms of time dynamic prediction capability. It achieves a dual improvement in spatial accuracy and temporal accuracy, and provides a high-quality data foundation for subsequent analysis and applications based on dense fields.

[0039] In one embodiment, first environmental data and a first altitude deviation for each grid point are determined using measured environmental data, altitude deviation, and a regression Kriging model; second environmental data and a second altitude deviation for each grid point are determined using measured environmental data, altitude deviation, and an LSTM network model; predicted environmental data for each grid point in the target area are determined based on the first and / or second environmental data; and predicted altitude deviation for each grid point in the target area is determined based on the first and / or second altitude deviation. Specifically, after inferring the measured environmental data using a preset spatiotemporal fusion algorithm, predicted data for each parameter in the measured environmental data can be obtained. For example, if the measured environmental data includes temperature, humidity, and air pressure, after inferring the measured environmental data using the preset spatiotemporal fusion algorithm, predicted temperature, predicted humidity, and predicted air pressure for each grid point can be obtained accordingly.

[0040] In one specific embodiment, taking the prediction of altitude deviation as an example, the altitude deviation is predicted using a regression kriging model and an LSTM network model, and the result can be as follows: (5) in, This represents the height deviation at grid point (x, y) at time t. This indicates a high degree of bias in the predictions of the regression Kriging model. This indicates the high bias in the predictions made by the LSTM network model. This represents the adaptive weighting coefficient, which can be dynamically determined based on the distance between the grid point to be predicted and the observation station, as well as the estimated variance of the Kriging interpolation.

[0041] Step S105: For any grid point to be tested in the object area, calculate the predicted theoretical height based on the predicted environment data.

[0042] In one embodiment, for any grid point (x, y) to be measured in the object region, the theoretical ISA height can be calculated using the following equation (using the temperature and humidity at that point to correct for the virtual temperature): (6) in, The theoretical height of the grid point (x,y) at time t is represented by T, the predicted temperature is represented by RH, the predicted humidity is represented by P, and the measured or predicted air pressure is represented by P.

[0043] In one embodiment, the predicted environmental data includes predicted temperature, predicted humidity, and / or predicted air pressure. When calculating altitude and true altitude, predicted temperature, predicted humidity, and predicted air pressure can be used to calculate the predicted theoretical altitude; when calculating QNH altitude, predicted temperature, predicted humidity, and local QNH air pressure can be used to calculate the predicted theoretical QNH altitude; when calculating standard atmospheric pressure altitude, predicted temperature, predicted humidity, and standard atmospheric pressure can be used to calculate the predicted theoretical standard atmospheric pressure altitude.

[0044] In an optional embodiment, step S105 may include: The predicted theoretical altitude of the grid points to be measured is determined based on the predicted temperature, the predicted humidity, and / or the predicted air pressure. Based on the predicted temperature, the predicted humidity, and / or the local QNH pressure, determine the predicted theoretical QNH height of the grid points to be measured; and / or The predicted theoretical standard atmospheric pressure height of the grid points to be measured is determined based on the predicted temperature, the predicted humidity, and / or the standard atmospheric pressure.

[0045] By transforming the height of grid points into a consistent height representation, it is possible to ensure that all height representations share the same physical-data fusion benchmark, thereby achieving semantic uniformity.

[0046] Step S106: Determine the height corresponding to the grid point to be measured based on the deviation between the predicted theoretical height and the predicted height corresponding to the grid point to be measured.

[0047] After obtaining the predicted theoretical height, the height corresponding to the grid point to be measured can be determined based on the deviation between the predicted theoretical height and the predicted height corresponding to the grid point to be measured, as shown below: (7) in, Let represent the height of the grid point (x, y) at time t. Let represent the theoretical height of the grid point (x, y) at time t. This represents the height deviation of the grid point (x, y) at time t.

[0048] In one embodiment, after calculating the predicted theoretical altitude, the altitude corresponding to the grid point to be measured is determined by the predicted altitude deviation, which is the true altitude equal to the difference between the actual altitude and the elevation data of the digital elevation model (DEM); after calculating the predicted theoretical QNH altitude, the predicted altitude deviation is superimposed (assuming the deviation field is insensitive to changes in reference air pressure) to determine the altitude corresponding to the grid point to be measured; after calculating the predicted theoretical standard air pressure, the altitude corresponding to the grid point to be measured is determined by the predicted altitude deviation.

[0049] Figure 3 This is a flowchart of a height measurement method according to another embodiment of this application. Figure 1 compared to, Figure 3 Steps S301, S303, and S306 shown are... Figure 1 Steps S101 to S106 of the method shown are the same, except that before step S303, Figure 3 The method shown also includes: Step S302: Preprocess the measured environmental data.

[0050] In one embodiment, the raw observation sequences acquired from the data acquisition module (e.g., a multi-source sensor acquisition box) and external meteorological data require systematic data preprocessing and cleaning to ensure the integrity, consistency, and usability of the input data. This may include one or more of the following steps: 1) Timestamp unification and alignment Because different sensors have different sampling frequencies and timestamps, it is usually necessary to unify all raw data to the same time scale (such as minutes or hours). Assume that the raw time series of a certain sensor is... ,in, Sampling time, For the corresponding measured values ​​(e.g., temperature, humidity, or air pressure). The unified timeline is as follows: , The original observations are aligned to a unified time axis T through a resampling operation.

[0051] 2) Missing value detection and processing Sensors may produce missing values ​​due to environmental interference. For missing values, this application employs the following two-level method: Nearest neighbor interpolation: This method is mainly used when the time interval before and after a missing point is small (e.g., 1-2 sampling points). In a specific embodiment, linear interpolation can be used for numerical supplementation. (8) in, , and They represent , and The measured value at time.

[0052] Mean imputation: This method is mainly used for cases with large missing intervals. In a specific implementation, it uses the historical average of the same period or the weighted average of multiple sites to imput the missing values. (9) in, For the j-th adjacent station at time... The measured values ​​(which may include temperature, humidity, or air pressure) are used to calculate the weighted average or arithmetic mean to fill in the missing values. N is the number of reference stations, which usually refers to the number of neighboring stations (data acquisition modules) that are closest to the current missing point in space and whose data is valid (e.g., the 3 or 5 closest stations).

[0053] 3) Outlier detection and removal For data such as temperature, humidity, and air pressure, abrupt changes or invalid values ​​may occur, requiring the identification of outliers or invalid values ​​for correction or removal. In one embodiment, a statistical threshold method (e.g., Z-score detection) can be used to identify outliers or invalid values. (10) in, and These are the mean and standard deviation of the sequence, respectively. When ( If the threshold value is less than the preset threshold, it is considered an outlier and is corrected or removed.

[0054] 4) Numerical standardization and normalization In one embodiment, since temperature, humidity, and air pressure have different dimensions, they need to be unified to a dimensionless range for deep learning model training. In a specific embodiment, Z-score normalization can be used: (11) in, and These are the mean and standard deviation of the data, respectively. For a moment The measured value.

[0055] In an optional embodiment, step S307 may include: The measured environmental data is aligned to a unified time axis through a resampling operation. The missing measured environmental data of the multiple stations were filled by nearest neighbor interpolation and / or mean imputation. Detecting outliers in the measured environmental data; and / or The measured environmental data were subjected to numerical standardization and normalization.

[0056] According to one aspect of this application, a height measuring device is provided. Figure 4 This is a schematic diagram of a height measuring device according to one embodiment of this application. Figure 4 As shown, the device includes an acquisition module 401, a first calculation module 402, a first determination module 403, a second determination module 404, a second calculation module 405, and a third determination module 406. The acquisition module 401 acquires measured environmental data and measured altitude for each of multiple stations in a target area. The target area includes multiple grid points, and each station is a grid point equipped with a data acquisition module. The multiple grid points include grid points to be measured. The first calculation module 402 calculates the theoretical altitude of each station based on the measured environmental data. The first determination module 403 determines the theoretical altitude of each station. The first module 404 is used to determine the height deviation between the measured altitude and the theoretical altitude, based on the measured environmental data and the height deviation corresponding to each of the multiple stations, using a preset spatiotemporal fusion algorithm to determine the predicted environmental data and predicted height deviation for each grid point in the object area; the second module 405 is used to calculate the predicted theoretical altitude for any grid point to be measured in the object area based on the predicted environmental data; and the third module 406 is used to determine the altitude corresponding to the grid point to be measured based on the predicted theoretical altitude and the predicted height deviation corresponding to the grid point to be measured.

[0057] In an optional embodiment, the first computing module 402 may be used for: Calculate the virtual temperature based on the measured environmental data; and The theoretical height of the station is calculated based on the virtual temperature.

[0058] In an optional embodiment, the second determining module 404 may be used to: The first environmental data and the first height deviation of each grid point are determined by the measured environmental data, the height deviation and the regression Kriging model. The second environmental data and second height deviation of each grid point are determined using the measured environmental data, the height deviation, and the LSTM network model. Based on the first environmental data and / or the second environmental data, determine the predicted environmental data for each grid point in the object area; and The predicted height deviation of each grid point in the object region is determined based on the first height deviation and / or the second height deviation.

[0059] In an optional embodiment, the predicted environmental data includes predicted temperature, predicted humidity, and / or predicted air pressure, and the second calculation module 405 can be used for: The predicted theoretical altitude of the grid points to be measured is determined based on the predicted temperature, the predicted humidity, and / or the predicted air pressure. Based on the predicted temperature, the predicted humidity, and / or the local QNH pressure, determine the predicted theoretical QNH height of the grid points to be measured; and / or The predicted theoretical standard atmospheric pressure height of the grid points to be measured is determined based on the predicted temperature, the predicted humidity, and / or the standard atmospheric pressure.

[0060] Figure 5 This is a schematic diagram of a height measuring device according to another embodiment of this application. Figure 4 compared to, Figure 5 The modules 501 and 503 to 506 shown are... Figure 4 Modules 401 to 406 of the device shown are the same, except that, Figure 5 The device shown also includes: The preprocessing module 502 is used to preprocess the measured environmental data.

[0061] In an optional embodiment, the preprocessing module 502 can be used to: The measured environmental data is aligned to a unified time axis through a resampling operation. The missing measured environmental data of the multiple stations were filled by nearest neighbor interpolation and / or mean imputation. Detecting outliers in the measured environmental data; and / or The measured environmental data were subjected to numerical standardization and normalization.

[0062] According to the height measurement method and device provided in this application, acquisition modules are deployed in a portion of the grid points within the target area to acquire environmental and height data in real time. Then, based on the measured environmental and height data, the height deviation of the grid points where the acquisition modules are deployed is determined. Using a pre-defined spatiotemporal fusion algorithm, the environmental data and height deviation of each grid point in the target area are predicted, and the environmental data and height deviation are reconstructed from sparse to dense matrix. Finally, based on the predicted environmental data and predicted height deviation, the height of each grid point is determined. This application's solution helps to achieve unified expression and management of airspace vertical height, improving the coordination and utilization efficiency of airspace resources.

[0063] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0064] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0065] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be an electrical connection or other forms.

[0066] See Figure 6 , Figure 6 An electronic device is provided, including a processor and a memory. The memory stores computer instructions or one or more programs, which, when executed by the processor, cause the processor to execute the computer instructions to achieve the following: Figure 1 and Figure 3 The method and its detailed scheme are shown.

[0067] It should be understood that the above-described device embodiments are merely illustrative, and the device disclosed in this invention can be implemented in other ways. For example, the division of units / modules described in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, integrated into another system, or some features may be ignored or not executed.

[0068] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of the present invention can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0069] When the integrated unit / module is implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor or chip can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the on-chip cache, off-chip memory, and storage can be any suitable magnetic or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc.

[0070] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer electronic device (which may be a personal computer, server, or network electronic device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0071] This application also provides a computer-readable storage medium storing one or more computer programs, which, when executed by multiple processors, cause the processors to perform the following actions: Figure 1 and Figure 3 The method and its detailed scheme are shown.

[0072] This application also provides a computer program product, which includes a computer program that, when run on a computer, causes the computer to perform the methods of any of the above embodiments.

[0073] References to features, advantages, or similar language in this specification do not imply that all features and advantages achievable with this solution should be included or included in any single implementation thereof. Rather, references to features and advantages are understood to mean that a particular feature, advantage, or characteristic described in connection with an embodiment is included in at least one embodiment of this solution. Therefore, discussions of features, advantages, and similar language throughout this specification may, but do not necessarily, refer to the same embodiments.

[0074] Furthermore, the features, advantages, and characteristics described herein can be combined in any suitable manner in one or more embodiments. Based on the description herein, those skilled in the art will recognize that this solution can be implemented without one or more specific features or advantages of a particular embodiment. In other instances, additional features and advantages can be appreciated in specific embodiments not presented in all embodiments of this solution.

[0075] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this application. Furthermore, any changes or modifications made by those skilled in the art based on the ideas of this application, and on the specific implementation methods and application scope of this application, are all within the scope of protection of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method of measuring height, characterized by, The method comprises: acquiring measured environmental data and measured altitude of each of a plurality of stations in an object area, wherein the object area comprises a plurality of grid points, the stations are grid points provided with a data collection module, and the plurality of grid points comprise to-be-measured grid points; calculating a theoretical height of the stations according to the measured environmental data; determining a height deviation between the measured altitude and the theoretical height; based on the measured environmental data and the height deviation of each of the plurality of stations, respectively determining predicted environmental data and predicted height deviation of each grid point in the object area by using a preset spatio-temporal fusion algorithm; for any to-be-measured grid point in the object area, determining a predicted theoretical height according to the predicted environmental data; and determining a height corresponding to the to-be-measured grid point according to the predicted theoretical height and the predicted height deviation corresponding to the to-be-measured grid point. The predicted environmental data comprises predicted temperature, predicted humidity and / or predicted air pressure, and the determination of the predicted theoretical height according to the predicted environmental data for any to-be-measured grid point in the object area comprises:

2. The method of claim 1, wherein, determining a predicted theoretical altitude of the to-be-measured grid point according to the predicted temperature, the predicted humidity and / or the predicted air pressure; determining a predicted theoretical QNH height of the to-be-measured grid point according to the predicted temperature, the predicted humidity and / or a local QNH air pressure; and / or determining a predicted theoretical standard air pressure height of the to-be-measured grid point according to the predicted temperature, the predicted humidity and / or a standard atmospheric pressure. The determination of the predicted environmental data and the predicted height deviation of each grid point in the object area based on the measured environmental data and the height deviation of each of the plurality of stations by using the preset spatio-temporal fusion algorithm comprises:

3. The method of claim 1, wherein, determining first environmental data and first height deviation of each grid point by using the measured environmental data, the height deviation and a regression Kriging model; determining second environmental data and second height deviation of each grid point by using the measured environmental data, the height deviation and an LSTM network model; determining predicted environmental data of each grid point in the object area according to the first environmental data and / or the second environmental data; and determining predicted height deviation of each grid point in the object area according to the first height deviation and / or the second height deviation. Before the calculation of the theoretical height of the stations according to the measured environmental data, the method further comprises:

4. The measuring method according to any one of claims 1 to 3, characterized in that, preprocessing the measured environmental data. The preprocessing of the measured environmental data comprises:

5. The method of claim 4, wherein, aligning the measured environmental data to a unified time axis by resampling operation; filling in missing measured environmental data of the plurality of stations by using a neighboring interpolation method and / or a mean filling method; detecting outliers in the measured environmental data; and / or performing numerical standardization and normalization processing on the measured environmental data. The calculation of the theoretical height of the stations according to the measured environmental data comprises:

6. The method according to any one of claims 1 to 3, wherein calculating a virtual temperature according to the measured environmental data; and calculating the theoretical height of the stations according to the virtual temperature. ​ 7. The method according to any one of claims 1 to 3, wherein The measured environment data includes air pressure, temperature and / or humidity, and the data collection module includes a multi-source sensing collection box for collecting the measured environment data of the corresponding station.

8. A height measuring device, characterized by Comprise: An acquisition module is configured to acquire measured environment data and measured altitude of each station in a plurality of stations in an object region, wherein the object region comprises a plurality of grid points, the station is a grid point provided with a data collection module, and the plurality of grid points comprise to-be-measured grid points; A first calculation module is configured to calculate a theoretical height of the station according to the measured environment data; A first determination module is configured to determine a height deviation between the measured altitude and the theoretical height; A second determination module is configured to determine predicted environment data and predicted height deviation of each grid point in the object region based on the measured environment data and the height deviation of each station in the plurality of stations respectively by using a preset space-time fusion algorithm; A second calculation module is configured to calculate a predicted theoretical height according to the predicted environment data for any to-be-measured grid point in the object region; and A third determination module is configured to determine a height corresponding to the to-be-measured grid point according to the predicted theoretical height and the predicted height deviation corresponding to the to-be-measured grid point.

9. An electronic device, comprising: The computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the method in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the method in any one of claims 1 to 7.

Images