Height measuring method and device

Abstract

The invention provides a height measurement method and device, and the method comprises the following steps: S1, obtaining sample point data, the sample point data comprising feature data and label data of a sample point, the feature data comprising air pressure data, temperature data, humidity data and wind speed data of the sample point at any moment, and the label data comprising altitude data of the sample point, acquiring multiple groups of sample point data to form a sample data set; s2, constructing an initialized prediction model based on a LightGBM framework, and training the initialized prediction model based on the sample data set to obtain a final prediction model; and S3, acquiring air pressure data, temperature data, humidity data and wind speed data of a to-be-measured point at a certain moment, and inputting the data into the final prediction model to obtain an altitude prediction value of the to-be-measured point. According to the height measurement method and device provided by the invention, the altitude prediction model is established by using the LightGBM framework, the altitude is measured, and the accuracy of altitude measurement can be improved.

Description

Technical Field

[0001] The present application relates to the field of measurement technologies, and particularly to a height measurement method and device. Background Art

[0002] With the acceleration of the digitalization process and the intelligentization of transportation modes, the demand for high-precision positioning has become increasingly obvious. As a part of high-precision positioning, height positioning is of crucial significance.

[0003] There are many height measurement methods, mainly including mechanical measurement, GPS positioning measurement, laser ranging measurement, measurement based on inertial sensors, and measurement based on barometric sensors. Among them, mechanical measurement is cumbersome and labor-consuming; GPS height measurement has low accuracy and high cost; laser ranging can be blocked by obstacles above the ground such as trees and houses, and the measurement distance is limited; ordinary inertial sensors have cumulative errors and are difficult to measure with high precision over long distances, while high-precision inertial sensors have high costs. The height measurement method based on barometric sensors has advantages such as being convenient to use, having high accuracy, low cost, and wide applicability.

[0004] However, most height measurement methods based on barometric sensors use the barometric-height formula to calculate height. This method is relatively idealized, cannot fully conform to the actual situation, and relies on the sea-level atmospheric pressure data with low frequency and low accuracy from meteorological stations, which is insufficient to meet the requirements of high-precision height measurement.

[0005] Therefore, it is necessary to provide a technical solution to solve the problem of unsatisfactory height measurement in related technologies. Summary of the Invention

[0006] In order to solve the deficiencies of the prior art, the purpose of the present invention is to provide a height measurement method and device, which can improve the accuracy of height measurement.

[0007] To achieve the above purpose, the present invention adopts the following technical solutions:

[0008] A height measurement method includes the following steps:

[0009] S1. Obtain sample point data, where the sample point data includes the characteristic data and label data of the sample point. The characteristic data includes the barometric data, temperature data, humidity data, and wind speed data of any moment of the sample point, and the label data includes the altitude data of the sample point. Obtain multiple groups of sample point data to form a sample data set;

[0010] S2. Build an initial prediction model based on the LightGBM framework, and train the initial prediction model based on the sample data set to obtain a final prediction model;

[0011] S3. Obtain the barometric pressure data, temperature data, humidity data, and wind speed data of the point to be measured at a certain moment, and input the barometric pressure data, temperature data, humidity data, and wind speed data of the point to be measured into the final prediction model to obtain the predicted altitude value of the point to be measured.

[0012] Further, step S1 further includes:

[0013] S11. Measure the height from the ground of the sample point;

[0014] S12. Measure the reference barometric pressure at a specified height from the ground in the area below the sample point, and calculate the altitude at the position of the specified height from the ground in the area below the sample point according to the reference barometric pressure;

[0015] S13. Combine the height from the ground and the altitude at the position of the specified height from the ground in the area below the sample point to obtain the altitude of the sample point.

[0016] Further, S12 further includes:

[0017] Set multiple barometric pressure measurement points in the specified area below the sample point. The distance between each barometric pressure measurement point and the ground is equal to the specified height. Measure the barometric pressure value and the real-time temperature of each barometric pressure measurement point multiple times. Calculate the altitude of each barometric pressure measurement point according to the barometric pressure value and the real-time temperature of each barometric pressure measurement point, and perform an averaging process on the altitudes of each barometric pressure measurement point to obtain the altitude at the position of the specified height from the ground in the area below the sample point.

[0018] Further, based on the reference barometric pressure, calculate the altitude at the position of the specified height from the ground in the area below the sample point according to the following formula:

[0019]

[0020] In the formula, h represents the altitude at the position of the specified height from the ground in the area below the sample point, m represents the number of barometric pressure measurement points, n represents the number of measurements, t ij represents the real-time temperature at the jth measurement of the ith barometric pressure measurement point, p ij represents the barometric pressure value at the jth measurement of the ith barometric pressure measurement point, PB j represents the sea-level barometric pressure value collected by the meteorological station at the jth time.

[0021] Further, step S2 further includes:

[0022] S21. Use the grid search method to adjust the parameters of the initialized prediction model to obtain the optimal parameters, and substitute the optimal parameters into the initialized prediction model to obtain the updated prediction model;

[0023] S22. Use the cross-validation method to validate the updated prediction model, and judge the stability of the updated prediction model. If the stability of the updated prediction model does not meet the preset conditions, retrain the model. When the stability of the updated prediction model reaches the preset conditions, use the corresponding updated prediction model as the final prediction model.

[0024] Further, step S22 includes:

[0025] Randomly split the sample data set into k equal-sized parts, where k is a preset value. Each time, select k - 1 of them as the training set, and the remaining one as the validation set. Use the training set to train the updated prediction model until the performance of the updated prediction model is the best on the validation set or the loss no longer decreases.

[0026] Further, a height measurement device includes a sample point data storage unit for storing sample point data. The sample point data includes the feature data and label data of the sample point. The feature data includes the barometric pressure data, temperature data, humidity data, and wind speed data of the sample point at any moment. The label data includes the altitude data of the sample point. Obtain multiple groups of sample point data to form a sample data set;

[0027] A model construction unit for constructing an initial prediction model based on the LightGBM framework and training the initial prediction model based on the sample data set to obtain the final prediction model;

[0028] A data acquisition unit for obtaining the barometric pressure data, temperature data, humidity data, and wind speed data of the point to be measured at a certain moment;

[0029] A prediction unit for inputting the barometric pressure data, temperature data, humidity data, and wind speed data of the point to be measured into the final prediction model to obtain the predicted altitude value of the point to be measured.

[0030] Further, the height measurement device further includes a sample point data acquisition unit for collecting sample point data and storing the collected sample point data in the sample point data storage unit;

[0031] The sample point data acquisition unit includes a rangefinder and a barometer. The rangefinder is used to measure the height of the sample point from the ground, and the barometer is used to measure the reference barometric pressure at a specified height above the ground in the area below the sample point;

[0032] The sample point data acquisition unit calculates the altitude at a specified height above the ground in the area below the sample point based on the reference barometric pressure, and combines the height from the ground and the altitude at a specified height above the ground in the area below the sample point to obtain the altitude of the sample point.

[0033] Further, the sample point data acquisition unit acquires the air pressure values and real-time temperatures of at least two air pressure measurement points, where the air pressure measurement points are within a specified area below the sample point, and the distance between each air pressure measurement point and the ground is equal to the specified height.

[0034] The sample point data acquisition unit calculates the altitude of each air pressure measurement point based on the air pressure value and real-time temperature of each air pressure measurement point, and performs an averaging process on the altitudes of each air pressure measurement point to obtain the altitude at the position of the specified height from the ground in the area below the sample point.

[0035] Further, the sample point data acquisition unit calculates the altitude at the position of the specified height from the ground in the area below the sample point based on the reference air pressure according to the following formula:

[0036]

[0037] In the formula, h represents the altitude at the position of the specified height from the ground in the area below the sample point, m represents the number of air pressure measurement points, n represents the number of measurements, t ij represents the real-time temperature at the jth measurement of the ith air pressure measurement point, p ij represents the air pressure value at the jth measurement of the ith air pressure measurement point, PB j represents the sea-level air pressure value collected by the meteorological station at the jth time.

[0038] The height measurement method and device provided by the present application use the LightGBM framework to establish an altitude prediction model, which can fit the non-linear relationships of factors related to altitude such as air pressure, temperature, humidity, and wind speed. Therefore, accurate prediction can be performed based on the air pressure data, temperature data, humidity data, and wind speed data of the point to be measured, and the altitude prediction value of the point to be measured can be obtained. According to the height measurement method provided by the embodiments of the present application, the accuracy of height measurement can be improved. Description of the Drawings

[0039] Figure 1 It is a flowchart of the height measurement method of the present application.

[0040] Figure 2 It is a flowchart of measuring the altitude of the sample point in the height measurement method of the present application.

[0041] Figure 3 It is a flowchart of optimizing the prediction model in the height measurement method of the present application.

[0042] Figure 4 It is a schematic diagram of the five-fold cross-validation method in the present application.

[0043] Figure 5 It is a schematic diagram of the structure of the height measurement device of the present application. Detailed implementation manners

[0044] The following will describe the present application in detail in conjunction with the specific embodiments shown in the accompanying drawings. However, these embodiments do not limit the present application, and any structural, methodical, or functional transformations made by those of ordinary skill in the art based on these embodiments are included within the protection scope of the present application.

[0045] As Figure 1 shown, the present application provides a height measurement method, including the following steps:

[0046] S1. Obtain sample point data. The sample point data includes the feature data and label data of the sample point. The feature data includes the barometric pressure data, temperature data, humidity data, and wind speed data at any moment of the sample point, and the label data includes the altitude data of the sample point. Obtain multiple groups of sample point data to form a sample data set;

[0047] S2. Build an initial prediction model based on the LightGBM framework and train the initial prediction model based on the sample data set to obtain a final prediction model;

[0048] S3. Obtain the barometric pressure data, temperature data, humidity data, and wind speed data of the point to be measured at a certain moment, and input the barometric pressure data, temperature data, humidity data, and wind speed data of the point to be measured into the final prediction model to obtain the predicted altitude value of the point to be measured.

[0049] According to the above description, the height measurement method provided by the embodiments of the present application uses the LightGBM algorithm to fit the non-linear relationships of factors related to altitude, such as barometric pressure, temperature, humidity, and wind speed. Therefore, the predicted altitude value of the point to be measured can be accurately predicted based on the barometric pressure data, temperature data, humidity data, and wind speed data of the point to be measured. According to the height measurement method provided by the embodiments of the present application, the accuracy of height measurement can be improved.

[0050] As Figure 2 shown, specifically, step S1 of the height measurement method further includes:

[0051] S11. Measure the height of the sample point from the ground;

[0052] S12. Measure the reference barometric pressure at a specified height from the ground in the area below the sample point, and calculate the altitude at the specified height from the ground in the area below the sample point based on the reference barometric pressure;

[0053] S13. Combine the height from the ground and the altitude at the specified height from the ground in the area below the sample point to obtain the altitude of the sample point.

[0054] According to the above description, in the altitude measurement method provided by the embodiments of the present application, when measuring the altitude of a sample point, the reference air pressure at a position at a specified height from the ground in the area below the sample point can be measured by a barometer, so as to improve the air pressure detection frequency in the area below the sample point at a position at a specified height from the ground, narrow the air pressure detection range, and improve the air pressure detection accuracy. According to the reference air pressure measured by the barometer at a position at a specified height from the ground in the area below the sample point, the altitude at a position at a specified height from the ground in the area below the sample point can be calculated more accurately. By combining the height of the sample point from the ground with the altitude at a position at a specified height from the ground in the area below the sample point, the altitude of the sample point can be accurately obtained, the reliability of the sample point data can be improved, and further the prediction model trained according to the sample data set can be made more accurate.

[0055] As an optional implementation manner, measurement means such as a laser rangefinder, an ultrasonic rangefinder, and an infrared rangefinder can be used to measure the height of the sample point from the ground. In the embodiments of the present application, a laser rangefinder is selected to measure the height of the sample point from the ground.

[0056] As an optional implementation manner, step S12 of the altitude measurement method further includes:

[0057] Set a plurality of air pressure measurement points in a specified area below the sample point. The distance between each air pressure measurement point and the ground is equal to the specified height. Measure the air pressure value and the real-time temperature of each air pressure measurement point multiple times. Calculate the altitude of each air pressure measurement point according to the air pressure value and the real-time temperature of each air pressure measurement point, and perform an averaging process on the altitudes of each air pressure measurement point to obtain the altitude at a position at a specified height from the ground in the area below the sample point. In this way, more accurate altitude data of the sample point can be obtained, and the reliability of the sample point data can be improved.

[0058] Specifically, according to the reference air pressure, the altitude at a position at a specified height from the ground in the area below the sample point is calculated based on the following formula:

[0059]

[0060] In the formula, h represents the altitude at a position at a specified height from the ground in the area below the sample point, m represents the number of the air pressure measurement points, n represents the number of measurements, t ij represents the real-time temperature at the jth measurement of the ith air pressure measurement point, p ij represents the air pressure value at the jth measurement of the ith air pressure measurement point, PB j represents the sea-level air pressure value collected by the weather station at the jth time.

[0061] When calculating the altitude of a sample point, the altitude of the sample point can be obtained by adding the height of the sample point from the ground to the altitude at the specified height position from the ground in the area below the sample point and then subtracting the height of the barometric measurement point from the ground, so as to obtain the altitude data of the sample point.

[0062] For obtaining the altitude at the specified height position from the ground in the area below the sample point in this application, a method of setting multiple barometric measurement points and performing multiple measurements is adopted, that is, obtaining the barometric pressure value of each barometric measurement point and the real-time temperature of each measurement, and obtaining the sea-level barometric pressure value, calculating the altitude of each barometric measurement point based on the above altitude calculation formula, and performing an averaging process on the obtained altitudes of each barometric measurement point to obtain the final altitude at the specified height position from the ground in the area below the sample point. Through the above settings, the accuracy and reliability of the altitude at the specified height position from the ground in the area below the sample point can be improved, thereby improving the accuracy of the height measurement method.

[0063] As an optional implementation method, the steps of constructing an initial prediction model based on the LightGBM framework include:

[0064] S201: Calculate the initial gradient value of the input sample;

[0065] S202: Build a decision tree until the leaf number limit is reached or all leaves cannot be split anymore;

[0066] S203: Construct a histogram of the input sample;

[0067] S204: Select the best split feature and split threshold according to the histogram;

[0068] S205: Establish a root node and split the input sample according to the best split feature and split threshold;

[0069] S206: Update the output value of the sample and update the gradient value of the sample;

[0070] S207: Repeat S202 - S205 until all decision trees are built, thereby building an initial prediction model.

[0071] As an alternative method, the height measurement method further includes:

[0072] S21: Use the grid search method to tune the parameters of the initial prediction model to obtain the optimal parameters, and substitute the optimal parameters into the initial prediction model to obtain an updated prediction model;

[0073] S22. Use the cross - validation method to verify the updated prediction model, and judge the stability of the updated prediction model. If the stability of the updated prediction model does not meet the preset conditions, retrain the model. When the stability of the updated prediction model reaches the preset conditions, use the corresponding updated prediction model as the final prediction model.

[0074] Specifically, use the grid search method and input all the parameter combinations set. The parameters include: learning_rate: learning rate, num_leaves: the number of leaves of each tree, max_depth: the maximum depth of the tree, min_data_in_leaf: the minimum number of records that a leaf may have, feature_fraction: the proportion of the total number of features selected, bagging_fraction: the proportion of data used in each iteration, bagging_freq: the sampling frequency of the sample data without repeated sampling. Only modify one parameter each time during the search process, and finally obtain the parameter combination that minimizes the error between the output result and the actual result. After traversing all parameter combinations, save the parameter combination with the minimum error as the optimal parameter combination, and substitute the optimal parameters into the initialized prediction model to obtain the updated prediction model.

[0075] As an optional implementation, in step S22 of the altitude measurement method, the cross - validation method is adopted. The sample data set is randomly split into k equal - sized parts, where k is a preset value. Each time, k - 1 of them are selected as the training set, and the remaining one is used as the validation set. Use the training set to train the updated prediction model until the performance of the updated prediction model is best on the validation set or the loss no longer decreases.

[0076] As Figure 4 shown, specifically, the cross - validation method adopted in the embodiment of the present application is the five - fold cross - validation method. That is, first randomly split the sample data set into 5 equal - sized parts, and successively use four of the sample data sets as the training set, and use the remaining one as the validation set. Use the training set to train the updated prediction model until the performance of the updated prediction model is best on the validation set or the loss no longer decreases. Through the above settings, the validation set and the training set form complementary sets and alternate cyclically, which can improve the processing effect and efficiency of the sample data, thereby improving the accuracy of the prediction model. In addition, the seven - fold cross - validation method and the ten - fold cross - validation method can also be selected according to the size of the training set and the training cost.

[0077] According to the above description, the present application tunes the parameters of the prediction model through the grid search method and uses the cross - validation method for verification, so that the trained prediction model can achieve the optimal model prediction effect, thereby improving the accuracy of the altitude prediction of the measurement point.

[0078] AsFigure 5 As shown in the figure, the present application also provides a height measurement device 100, which includes a sample point data storage unit 11, a model construction unit 12, a data acquisition unit 13, and a prediction unit 14.

[0079] Among them, the sample point data storage unit 11 is used to store sample point data. The sample point data includes feature data and label data of the sample point. The feature data includes barometric pressure data, temperature data, humidity data, and wind speed data at any moment of the sample point. The label data includes altitude data of the sample point. Multiple groups of sample point data are obtained to form a sample data set.

[0080] The model construction unit 12 is used to construct an initial prediction model based on the LightGBM framework and train the initial prediction model based on the sample data set to obtain a final prediction model.

[0081] The data acquisition unit 13 is used to obtain barometric pressure data, temperature data, humidity data, and wind speed data of the point to be measured at a certain moment.

[0082] The prediction unit 14 is used to input the barometric pressure data, temperature data, humidity data, and wind speed data of the point to be measured into the final prediction model to obtain a predicted altitude value of the point to be measured.

[0083] According to the above description, the height measurement device 100 provided by the embodiment of the present application can train a prediction model constructed based on the LightGBM framework based on sample point data, and based on the trained prediction model, predict according to the barometric pressure data, temperature data, humidity data, and wind speed data of the point to be measured, so as to obtain a predicted altitude value of the point to be measured. In this way, the altitude of the point to be measured can be accurately measured.

[0084] As an alternative, the height measurement device 100 further includes a sample point data acquisition unit 15. The sample point data acquisition unit 15 is used to acquire sample point data and store the acquired sample point data in the sample point data storage unit 11.

[0085] Through the above settings, the height measurement device 100 of the present application is based on the LightGBM framework. Through the cooperation of the sample point data storage unit 11, the model construction unit 12, the data acquisition unit 13, the prediction unit 14, and the sample point data acquisition unit 15, the accuracy of predicting the altitude of the point to be measured can be improved.

[0086] Specifically, the sample point data acquisition unit 15 includes a rangefinder and a barometer. The rangefinder is used to measure the height of the sample point from the ground, and the barometer is used to measure the reference air pressure at a specified height from the ground in the area below the sample point. The sample point data acquisition unit 15 calculates the altitude at the specified height from the ground in the area below the sample point based on the reference air pressure, and combines the height from the ground and the altitude at the specified height from the ground in the area below the sample point to obtain the altitude of the sample point.

[0087] As an alternative implementation, the sample point data acquisition unit 15 acquires the air pressure values and real-time temperatures of at least two air pressure measurement points. The air pressure measurement points are within a specified area below the sample point, and the distance between each air pressure measurement point and the ground is equal to the specified height.

[0088] As an alternative implementation, the sample point data acquisition unit 15 calculates the altitude at the specified height from the ground in the area below the sample point based on the reference air pressure according to the following formula:

[0089]

[0090] In the formula, h represents the altitude at the specified height from the ground in the area below the sample point, m represents the number of air pressure measurement points, n represents the number of measurements, t ij represents the real-time temperature at the jth measurement of the ith air pressure measurement point, p ij represents the air pressure value at the jth measurement of the ith air pressure measurement point, PB j represents the sea-level air pressure value collected by the weather station at the jth time.

[0091] The sample point data acquisition unit 15 of the present application acquires the air pressure values and real-time temperatures of multiple air pressure measurement points, calculates the altitude of each air pressure measurement point based on the air pressure values and real-time temperatures of each air pressure measurement point, obtains the altitude at the specified height from the ground in the area below the sample point by averaging the altitudes of each air pressure measurement point, and combines the height from the ground to obtain the altitude of the sample point.

[0092] The present application provides an embodiment to predict the altitudes of locations 1-20, and the prediction results are shown in Table 1.

[0093]

[0094]

[0095] Table 1

[0096] As can be seen from Table 1, the errors between the predicted altitude heights and the true altitude heights of locations 1-20 are small, and the accuracy of the predicted altitude heights of locations 1-20 is high.

[0097] The altitude measurement method and device provided by this application use the LightGBM framework to establish an altitude prediction model, which can fit the non-linear relationships of factors related to altitude such as air pressure, temperature, humidity, and wind speed. Therefore, accurate predictions can be made based on the air pressure data, temperature data, humidity data, and wind speed data of the point to be measured, and the altitude prediction value of the point to be measured can be obtained. According to the altitude measurement method provided by the embodiments of this application, the accuracy of altitude measurement can be improved.

[0098] The above-disclosed are only the preferred embodiments of this application, but they are not intended to limit the scope of the rights of this application. Those of ordinary skill in the art can understand that within the spirit and scope of this application and the appended claims, changes, modifications, substitutions, combinations, and simplifications should all be equivalent replacement methods and still fall within the scope covered by the invention.

Claims

1. A height measurement method, comprising the following steps: S1. Obtain sample point data, where the sample point data includes the feature data and label data of the sample point. The feature data includes the air pressure data, temperature data, humidity data, and wind speed data at any moment of the sample point, and the label data includes the altitude data of the sample point. Obtain multiple groups of sample point data to form a sample data set; S2. Construct an initial prediction model based on the LightGBM framework, and train the initial prediction model based on the sample data set to obtain a final prediction model; S3. Obtain the air pressure data, temperature data, humidity data, and wind speed data of the point to be measured at a certain moment, and input the air pressure data, temperature data, humidity data, and wind speed data of the point to be measured into the final prediction model to obtain the altitude prediction value of the point to be measured.

2. The height measurement method according to claim 1, wherein the step S1 further includes: S11. Measure the height from the ground of the sample point; S12. Measure the reference air pressure at a position with a specified height from the ground in the area below the sample point, and calculate the altitude at the position with a specified height from the ground in the area below the sample point according to the reference air pressure; S13. Combine the height from the ground and the altitude at the position with a specified height from the ground in the area below the sample point to obtain the altitude of the sample point.

3. The height measurement method according to claim 2, characterized in that, The step S12 further includes: Set multiple air pressure measurement points in a specified area below the sample point. The distance between each air pressure measurement point and the ground is equal to the specified height. Measure the air pressure value and real-time temperature of each air pressure measurement point multiple times, calculate the altitude of each air pressure measurement point according to the air pressure value and real-time temperature of each air pressure measurement point, and perform an averaging process on the altitudes of each air pressure measurement point to obtain the altitude at the position with a specified height from the ground in the area below the sample point.

4. The height measurement method according to claim 3, wherein calculate the altitude at the position with a specified height from the ground in the area below the sample point based on the following formula according to the reference air pressure: Where h represents the altitude at a specified height above the ground in the area below the sample point, m represents the number of the barometric measurement points, n represents the number of measurements, t ij represents the real-time temperature at the i-th barometric measurement point for the j-th measurement, p ij represents the barometric pressure value at the i-th barometric measurement point for the j-th measurement, PB j represents the sea-level barometric pressure value collected by the weather station for the j-th time.

5. The height measurement method according to claim 1, characterized in that, The step S2 further includes: S21. Use the grid search method to adjust the parameters of the initial prediction model to obtain the optimal parameters, and substitute the optimal parameters into the initial prediction model to obtain an updated prediction model; S22. Use the cross-validation method to verify the updated prediction model, judge the stability of the updated prediction model. If the stability of the updated prediction model does not meet the preset conditions, retrain the model. When the stability of the updated prediction model reaches the preset conditions, use the corresponding updated prediction model as the final prediction model.

6. The height measurement method according to claim 5, wherein the step S22 includes: Randomly split the sample data set into k parts of equal size, where k is a preset value. Each time, select k - 1 of them as the training set, and the remaining one as the validation set. Use the training set to train the updated prediction model until the performance of the updated prediction model is optimal on the validation set or the loss no longer decreases.

7. A height measuring device, characterized in that, The device includes: A sample point data storage unit for storing sample point data, where the sample point data includes feature data and label data of the sample point. The feature data includes barometric pressure data, temperature data, humidity data, and wind speed data at any moment of the sample point, and the label data includes the altitude data of the sample point. Obtain multiple groups of sample point data to form a sample data set; A model construction unit for constructing an initial prediction model based on the LightGBM framework and training the initial prediction model based on the sample data set to obtain a final prediction model; A data acquisition unit for obtaining barometric pressure data, temperature data, humidity data, and wind speed data of a point to be measured at a certain moment; A prediction unit for inputting the barometric pressure data, temperature data, humidity data, and wind speed data of the point to be measured into the final prediction model to obtain a predicted altitude value of the point to be measured.

8. The height measuring device according to claim 7, characterized in that, The device further includes: A sample point data acquisition unit for acquiring sample point data and storing the acquired sample point data in the sample point data storage unit; The sample point data acquisition unit includes a rangefinder and a barometer. The rangefinder is used to measure the height of the sample point from the ground, and the barometer is used to measure the reference barometric pressure at a specified height from the ground in the area below the sample point; The sample point data acquisition unit calculates the altitude at a specified height from the ground in the area below the sample point based on the reference barometric pressure, and combines the height from the ground and the altitude at a specified height from the ground in the area below the sample point to obtain the altitude of the sample point.

9. The height measurement device according to claim 8, wherein The sample point data acquisition unit acquires the barometric pressure values and real-time temperatures of at least two barometric pressure measurement points within a specified area below the sample point, and the distance between each barometric pressure measurement point and the ground is equal to the specified height; The sample point data acquisition unit calculates the altitude of each barometric pressure measurement point based on the barometric pressure value and real-time temperature of each barometric pressure measurement point, and performs an averaging process on the altitudes of each barometric pressure measurement point to obtain the altitude at a specified height from the ground in the area below the sample point.

10. The height measurement device according to claim 9, wherein The sample point data acquisition unit calculates the altitude at a specified height from the ground in the area below the sample point based on the reference barometric pressure according to the following formula: Where h represents the altitude at a specified height above the ground in the area below the sample point, m represents the number of barometric measurement points, n represents the number of measurements, and t ij represents the real-time temperature at the i-th barometric measurement point during the j-th measurement, and p ij represents the barometric pressure value at the i-th barometric measurement point during the j-th measurement, and PB j represents the sea-level barometric pressure value collected by the weather station during the j-th collection.

Images