Low-altitude relative height measurement method and device, electronic equipment and storage medium

Abstract

The invention provides a low-altitude relative height measurement method and device, electronic equipment and a storage medium, and relates to the technical field of data processing, and the method comprises the steps: obtaining measurement information collected by distance measurement equipment; performing anomaly detection based on the measurement information to determine whether abnormal measurement information exists; if the abnormal measurement information exists, inputting the abnormal measurement information into a pre-constructed abnormality correction model, and outputting target measurement information; the anomaly correction model is obtained by performing optimization iteration on unknown parameters through a Bayesian optimization mode; replacing the abnormal measurement information with the target measurement information; and performing data fusion based on the target measurement information to obtain a low-altitude relative height. In the mode, the measurement accuracy in different ground environments is improved, so that the method is suitable for different terrain environment conditions, and the accuracy of landing buffer control is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a method, device, electronic device and storage medium for measuring low-altitude relative height. Background Art

[0002] Precision airdrop refers to the process of transporting personnel and supplies to a predetermined area by an aircraft. After the personnel and supplies are dropped from a high altitude, they land safely with the help of parachutes and active load reduction methods. Among them, the active load reduction landing buffer technology requires precise control in the stage close to the ground, which requires precise measurement of the relative height from the active load reduction system to the ground.

[0003] However, affected by the environment, data jitter will inevitably occur during the process of relative height measurement, so it is impossible to ensure the measurement accuracy under different ground environments, resulting in the active load reduction landing buffer system receiving poor relative height information, and ultimately leading to deviation in landing buffer control. Summary of the Invention

[0004] In view of this, an object of the present invention is to provide a method, device, electronic device and storage medium for measuring low-altitude relative height, so as to improve the measurement accuracy under different ground environments, thereby adapting to different terrain environment conditions and improving the accuracy of landing buffer control.

[0005] In a first aspect, an embodiment of the present invention provides a method for measuring low-altitude relative height, including: acquiring measurement information collected by a ranging device; performing anomaly detection based on the measurement information to determine whether there is abnormal measurement information; if there is abnormal measurement information, inputting the abnormal measurement information into a pre-constructed anomaly correction model to output target measurement information; the anomaly correction model is obtained by optimizing and iterating unknown parameters through Bayesian optimization; replacing the abnormal measurement information with the target measurement information; performing data fusion based on the target measurement information to obtain the low-altitude relative height.

[0006] In a preferred embodiment of the present invention, the above-mentioned performing anomaly detection based on the measurement information to determine whether there is abnormal measurement information includes: converting the measurement information through a level conversion circuit to obtain initial measurement information; performing anomaly detection based on the initial measurement information to determine whether there is abnormal measurement information.

[0007] In a preferred embodiment of the present invention, the anomaly correction model is represented by the following formula: ; where is the model output, x is the independent variable, is the basis function, is a random variable subject to a Gaussian distribution, w i is the weight,N The number of basis functions.

[0008] In a preferred embodiment of the present invention, the basis function is a linear basis function; the basis function is represented by the following formula: ; where x j is the j th input sample, M is the number of samples, β j,i is the hyperparameter of the basis function; N One basis function corresponds to N ( M +1) hyperparameters and N weights, N ( M +1) hyperparameters and N weights are unknown parameters.

[0009] In a preferred embodiment of the present invention, the objective function for optimizing and iterating the unknown parameters by Bayesian optimization is: ; where y ( x j ) is the response value of the sample x j , Y ( x j ) is the model prediction value, b ( x j ) is y ( x j )'s average value.

[0010] In a preferred embodiment of the present invention, the abnormal correction model is constructed as follows: a data set is pre-constructed and corrected, and the maximum number of iterations is pre-set; the unknown parameters are optimized by Bayesian optimization; an initial abnormal correction model is constructed based on the corrected data set and unknown parameters; the initial abnormal correction model is verified based on the objective function; after verification, the unknown parameters are optimized again by Bayesian optimization until the maximum number of iterations is reached to obtain the abnormal correction model.

[0011] In a preferred embodiment of the present invention, data fusion based on target measurement information to obtain the low-altitude relative height includes: weighted fusion based on target measurement information to obtain the low-altitude relative height.

[0012] In a second aspect, an embodiment of the present invention further provides a low-altitude relative height measurement device, including: a measurement information acquisition module, configured to acquire measurement information collected by a ranging device; an anomaly detection module, configured to perform anomaly detection based on the measurement information to determine whether there is abnormal measurement information; a target measurement information output module, configured to, if there is abnormal measurement information, input the abnormal measurement information into a pre-constructed anomaly correction model and output target measurement information; the anomaly correction model is obtained by optimizing and iterating unknown parameters through Bayesian optimization; an abnormal measurement information replacement module, configured to replace the abnormal measurement information with the target measurement information; a data fusion module, configured to perform data fusion based on the target measurement information to obtain the low-altitude relative height.

[0013] In a third aspect, an embodiment of the present invention further provides an electronic device, including a processor and a memory, where the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the low-altitude relative height measurement method in the first aspect above.

[0014] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are called and executed by a processor, the computer-executable instructions cause the processor to implement the low-altitude relative height measurement method in the first aspect above.

[0015] The embodiments of the present invention bring the following beneficial effects: The embodiments of the present invention provide a low-altitude relative height measurement method, device, electronic device and storage medium. By acquiring the measurement information collected by the ranging device, performing anomaly detection based on the measurement information to determine whether there is abnormal measurement information, if there is abnormal measurement information, inputting the abnormal measurement information into a pre-constructed anomaly correction model to output target measurement information, the anomaly correction model is obtained by optimizing and iterating unknown parameters through Bayesian optimization, replacing the abnormal measurement information with the target measurement information, and performing data fusion based on the target measurement information to obtain the low-altitude relative height. In this way, the measurement accuracy in different ground environments is improved, so as to adapt to different terrain environment conditions and improve the accuracy of landing buffer control.

[0016] Other features and advantages of the present disclosure will be described in the following specification, or, some features and advantages can be inferred from the specification or determined without doubt, or can be known by implementing the above technologies of the present disclosure.

[0017] To make the above objects, features and advantages of the present disclosure more obvious and understandable, the following specific embodiments are given, and in conjunction with the accompanying drawings, the detailed description is as follows. Description of the Drawings

[0018] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 It is a flowchart of a low-altitude relative height measurement method provided by an embodiment of the present invention; Figure 2 It is a structural diagram of a low-altitude relative height measurement system provided by an embodiment of the present invention; Figure 3 It is a flowchart of another low-altitude relative height measurement method provided by an embodiment of the present invention; Figure 4 It is a schematic structural diagram of a low-altitude relative height measurement device provided by an embodiment of the present invention; Figure 5 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Specific Embodiments

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions of the present invention in conjunction with the drawings. Obviously, the described embodiments are some but not all of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0021] Precision airdrop refers to the process of transporting personnel and supplies to a predetermined area by an aircraft. After the personnel and supplies are dropped from a high altitude, they land safely by means of a parachute and an active load reduction method. Among them, the active load reduction landing buffer technology requires precise control in the stage close to the ground, which requires precise measurement of the relative height from the active load reduction system to the ground.

[0022] However, affected by the environment, short-term data fluctuations will inevitably occur during the process of relative height measurement. Therefore, it is impossible to ensure the measurement accuracy in different ground environments, resulting in the active load reduction landing buffer system receiving poor relative height information, and ultimately leading to deviations in landing buffer control.

[0023] Based on this, a low-altitude relative height measurement method, device, electronic device, and storage medium provided by an embodiment of the present invention can obtain measurement information collected by a ranging device, perform anomaly detection based on the measurement information to determine whether there is abnormal measurement information. If there is abnormal measurement information, the abnormal measurement information is input into a pre-constructed anomaly correction model to output target measurement information. The anomaly correction model is obtained by optimizing and iterating unknown parameters through the Bayesian optimization method. The abnormal measurement information is replaced with the target measurement information, and data fusion is performed based on the target measurement information to obtain the low-altitude relative height. In this way, the measurement accuracy in different ground environments is improved, so as to adapt to different terrain environment conditions and improve the accuracy of landing buffer control.

[0024] To facilitate the understanding of this embodiment, a low-altitude relative height measurement method disclosed by an embodiment of the present invention will be introduced in detail first.

[0025] Embodiment 1 An embodiment of the present invention provides a low-altitude relative height measurement method. Figure 1 It is a flowchart of a low-altitude relative height measurement method provided by an embodiment of the present invention. As Figure 1 shown, the low-altitude relative height measurement method may include the following steps: Step S101, obtain the measurement information collected by the ranging device.

[0026] Among them, the ranging device includes a laser rangefinder and a radio altimeter. The laser rangefinder and the radio altimeter have the characteristics of high accuracy and wide measurement range, and can jointly complete the low-altitude high-precision relative height measurement.

[0027] Among them, the measurement information includes the information collected by the laser rangefinder and the information collected by the radio altimeter. The measurement information may include information such as time, height, frequency, and air pressure.

[0028] Among them, the laser rangefinder and the radio altimeter can be fixed at the bottom of the aircraft to ensure that the measurement directions of both are perpendicular to the ground and adjusted to the same measurement range (such as 0-100 meters).

[0029] Among them, the sampling timings of the laser rangefinder and the radio altimeter can be synchronized through a hardware trigger signal (such as a 10Hz clock) to ensure that the data time is aligned.

[0030] Step S102, perform anomaly detection based on the measurement information to determine whether there is abnormal measurement information.

[0031] Specifically, anomaly detection based on measurement information to determine whether there is anomalous measurement information may include: converting the measurement information through a level conversion circuit to obtain initial measurement information; performing anomaly detection based on the initial measurement information to determine whether there is anomalous measurement information.

[0032] Among them, the anomalous measurement information may be the information collected by a laser rangefinder or the information collected by a radio altimeter.

[0033] Among them, anomaly detection and subsequent anomaly correction after level conversion can retain the original data and meet the requirements of multiple interfaces.

[0034] Among them, real-time monitoring of data fluctuations (such as the difference in measurement values for 3 consecutive times > 5% of the full scale) is performed to mark anomalous data points.

[0035] Among them, when the difference between a single measurement value and the previous data is significant (such as a jump exceeding 5% of the range), that is, when there is an amplitude mutation, it can be considered that there is anomalous measurement information in the data fluctuation. When non-physical fluctuations (such as oscillations within ±10 cm) occur continuously in a short period of time, that is, when high-frequency noise appears, it can be considered that there is anomalous measurement information in the data fluctuation. When the output value is zero or exceeds the sensor range (such as the laser rangefinder returning an invalid value in foggy weather), that is, when the signal is lost, it can be considered that there is anomalous measurement information in the data fluctuation.

[0036] Among them, the causes of anomalous measurement information may be rain and fog (laser scattering), electromagnetic interference (radio multipath effect), sensor response delay, circuit noise, etc.

[0037] Among them, for anomaly detection, real-time detection based on threshold discrimination can be performed as follows: (1) Calculation of the moving window mean: Take the mean of the nearest N sampling points (such as N = 5) and the standard deviation σ : ; where N represents the size of the moving window (number of samples), k represents the index of the current time point, represents the i-th altitude sampling value within the window (from the laser or radio altimeter), represents the arithmetic mean of the N sampling values within the window, represents the standard deviation of the data within the window, reflecting the degree of data dispersion, represents the threshold coefficient, which determines the looseness of anomaly determination (usually selected based on the normal distribution confidence interval).

[0038] (2) Dynamic threshold setting: Normal range: , if the current value exceeds the range, it is determined as anomalous measurement information.

[0039] Step S103: If there is abnormal measurement information, input the abnormal measurement information into a pre-constructed abnormal correction model to output target measurement information.

[0040] Among them, the abnormal correction model can be a Kriging surrogate model.

[0041] Among them, the abnormal correction model is obtained by optimizing and iterating unknown parameters through Bayesian optimization.

[0042] Among them, the abnormal correction model is represented by the following formula: ; where is the model output, x is the independent variable, is the basis function, is a random variable obeying a Gaussian distribution, w i is the weight, N is the number of basis functions.

[0043] Among them, the basis function is a linear basis function; the basis function is represented by the following formula: ; where x j is the j th input sample, M is the number of samples, β j,i is the hyperparameter of the basis function; N Each basis function corresponds to N ( M +1) hyperparameters and N weights, N ( M +1) hyperparameters and N weights are unknown parameters.

[0044] Among them, the objective function for optimizing and iterating unknown parameters through Bayesian optimization is: ; where y ( x j ) is the response value of sample x j , Y ( x j ) is the model prediction value, b ( x j ) is y ( x j )'s average value.

[0045] Step S104: Replace the abnormal measurement information with the target measurement information.

[0046] Among them, by replacing the abnormal measurement information, the accuracy of the low-altitude relative height can be ensured during subsequent data fusion.

[0047] Step S105: Perform data fusion based on the target measurement information to obtain the low-altitude relative height.

[0048] Among them, if there is no abnormal measurement information, directly perform data fusion through measurement to obtain the low-altitude relative height.

[0049] Among them, specifically, weighted fusion is performed based on the target measurement information to obtain the low-altitude relative height.

[0050] Among them, the target measurement information also includes the information collected by the laser rangefinder and the information collected by the radio altimeter. The information collected by the laser rangefinder and the information collected by the radio altimeter are weighted and fused to obtain the low-altitude relative height.

[0051] For example, different weights can be set for the information collected by the laser rangefinder and the information collected by the radio altimeter, and the corresponding weights are dynamically adjusted according to the actual confidence levels of the laser rangefinder and the radio altimeter. For example, the weight of the laser rangefinder is high on sunny days.

[0052] Furthermore, this low-altitude relative height measurement method can be applied to a low-altitude relative height measurement system. For the convenience of understanding, Figure 2 The following is a structural diagram of a low-altitude relative height measurement system provided by an embodiment of the present invention. As Figure 2 shown, the measurement information of the laser rangefinder and the radio altimeter can be input into a level conversion circuit, and after conversion, it is input into an algorithm processing core. After data fusion, the height data relative to the ground is obtained and cached in a Static Random-Access Memory (SRAM) to form relative height sample data. The height sample data is uploaded to the master control system through the level conversion circuit for landing buffer or active load reduction landing buffer determination. Further, the laser rangefinder, the radio altimeter, and the sample data are stored in a FLASH memory for status monitoring and data analysis.

[0053] Among them, the algorithm processing core is implemented through steps S103 - S105.

[0054] The low-altitude relative height measurement method provided by the embodiment of the present invention can obtain the measurement information collected by the ranging device, perform anomaly detection based on the measurement information to determine whether there is abnormal measurement information. If there is abnormal measurement information, the abnormal measurement information is input into the pre-constructed anomaly correction model to output the target measurement information. The anomaly correction model is obtained by optimizing and iterating the unknown parameters through the Bayesian optimization method. The abnormal measurement information is replaced with the target measurement information, and data fusion is performed based on the target measurement information to obtain the low-altitude relative height. In this way, the measurement accuracy in different ground environments is improved, so as to adapt to different terrain environment conditions and improve the accuracy of landing buffer control.

[0055] Embodiment 2 The embodiment of the present invention also provides another low-altitude relative height measurement method; this method is implemented on the basis of the method in the above embodiment; this method focuses on describing the construction method of the anomaly correction model.

[0056] Figure 3 is a flowchart of another low-altitude relative height measurement method provided by the embodiment of the present invention. As Figure 3 shown, the construction method of this anomaly correction model may include the following steps: Step S201, pre-construct a data set and correct the data set, and preset the maximum number of iterations.

[0057] Among them, a data set can be constructed according to the input variables and output variables. Specifically, the input variables (independent variable x): laser ranging value x1, radio altimeter value x2, historical height mean value x3; the output variable (response value y): true height value (obtained through high-precision GPS or ground calibration equipment); the form of the data set is: ; where M is the number of samples.

[0058] Among them, the Lasso regularization coefficient can be set to correct the data set, and its objective function = ; where is the regularization coefficient, and the regularization coefficient is selected as 0.01 through cross-validation. Parameter screening is performed to solve the Lasso regularization coefficient to obtain the sparse weight vector , eliminate irrelevant variables, and the corrected data set: , only significant variables are retained (such as x1 and x2).

[0059] Among them, the maximum number of iterations is set according to the computing resources and real-time requirements. For example, 100 times.

[0060] Step S202, optimize the unknown parameters by using the Bayesian optimization method.

[0061] Among them, regarding Bayesian optimization: Parameter space: , initialize the prior distribution .

[0062] Acquisition function (Expected Improvement, EI): ; among them, is the current optimal predicted value. Iteratively update the posterior distribution , and select the parameter combination with the largest EI.

[0063] Step S203, construct an initial anomaly correction model based on the corrected data set and unknown parameters.

[0064] Among them, the constructed initial anomaly correction model is the same as that in step S103, which will not be elaborated here.

[0065] Step S204, verify the initial anomaly correction model based on the objective function.

[0066] Among them, for verification: Root Mean Square Error (RMSE) verification: ; it can be set that RMSE is less than 0.5 meters.

[0067] Mean Relative Error (MRE) verification: ; it can be set that MRE is less than 2%.

[0068] Step S205, after verification, use the Bayesian optimization method again to optimize the unknown parameters until the maximum number of iterations is reached, and obtain the anomaly correction model.

[0069] The low-altitude relative height measurement method provided by the embodiments of the present invention corrects the data set by using the Lasso regularization method, and optimizes and iterates the unknown parameters by using the Bayesian optimization method to obtain the best anomaly correction model.

[0070] Embodiment 3 Corresponding to the above method embodiment, the embodiment of the present invention provides a low-altitude relative height measurement device, Figure 4 is a structural schematic diagram of a low-altitude relative height measurement device provided by the embodiment of the present invention, as Figure 4 shown. The low-altitude relative height measurement device may include: A measurement information acquisition module 301, configured to acquire measurement information collected by a ranging device.

[0071] An anomaly detection module 302, configured to perform anomaly detection based on the measurement information to determine whether there is abnormal measurement information; The target measurement information output module 303 is configured to, if there is abnormal measurement information, input the abnormal measurement information into a pre-constructed abnormal correction model and output the target measurement information; the abnormal correction model is obtained by optimizing and iterating unknown parameters through the Bayesian optimization method.

[0072] The abnormal measurement information replacement module 304 is configured to replace the abnormal measurement information with the target measurement information.

[0073] The data fusion module 305 is configured to perform data fusion based on the target measurement information to obtain the low-altitude relative height.

[0074] The low-altitude relative height measurement device provided by the embodiment of the present invention can obtain the measurement information collected by the ranging device, perform abnormal detection based on the measurement information to determine whether there is abnormal measurement information. If there is abnormal measurement information, input the abnormal measurement information into a pre-constructed abnormal correction model to output the target measurement information. The abnormal correction model is obtained by optimizing and iterating unknown parameters through the Bayesian optimization method, replace the abnormal measurement information with the target measurement information, and perform data fusion based on the target measurement information to obtain the low-altitude relative height. In this way, the measurement accuracy in different ground environments is improved, so as to adapt to different terrain environment conditions and improve the accuracy of landing buffer control.

[0075] In some embodiments, the abnormal detection module is further configured to convert the measurement information through a level conversion circuit to obtain the initial measurement information; perform abnormal detection based on the initial measurement information to determine whether there is abnormal measurement information.

[0076] In some embodiments, the target measurement information output module is further configured to represent the abnormal correction model through the following formula: ; where is the model output, x is the independent variable, is the basis function, is a random variable subject to Gaussian distribution, w i is the weight, N is the number of basis functions.

[0077] In some embodiments, the target measurement information output module is further configured to the basis function is a linear basis function; represent the basis function through the following formula: ; where x j is the j th input sample, M is the number of samples, β j,i is the hyperparameter of the basis function; N each basis function corresponds to N (M +1) hyperparameters and N weights, N ( M +1) hyperparameters and N weights are unknown parameters.

[0078] In some embodiments, the objective measurement information output module is further configured to use the Bayesian optimization method to optimize and iterate the objective function of the unknown parameters as: ; where y ( x j ) is the response value of the sample x j , Y ( x j ) is the model prediction value, b ( x j ) is y ( x j )'s average value.

[0079] In some embodiments, the objective measurement information output module is further configured to pre-construct a data set and correct the data set, and pre-set the maximum number of iterations; use the Bayesian optimization method to optimize the unknown parameters; construct an initial anomaly correction model based on the corrected data set and the unknown parameters; verify the initial anomaly correction model based on the objective function; after verification, use the Bayesian optimization method to optimize the unknown parameters again until the maximum number of iterations is reached to obtain an anomaly correction model.

[0080] In some embodiments, the data fusion module is further configured to perform weighted fusion based on the objective measurement information to obtain the low-altitude relative height.

[0081] The device provided by the embodiments of the present invention has the same implementation principle and the same technical effects as those of the foregoing method embodiments. For the sake of brief description, for the parts not mentioned in the device embodiments, reference may be made to the corresponding contents in the foregoing method embodiments.

[0082] Embodiment 5 The embodiments of the present invention further provide an electronic device for running the above-mentioned low-altitude relative height measurement method; see Figure 5 for the structural schematic diagram of an electronic device shown. The electronic device includes a memory 500 and a processor 501. Among them, the memory 500 is used to store one or more computer instructions, and the one or more computer instructions are executed by the processor 501 to implement the above-mentioned low-altitude relative height measurement method.

[0083] Furthermore, Figure 5The electronic device shown also includes a bus 502 and a communication interface 503, and the processor 501, the communication interface 503, and the memory 500 are connected through the bus 502.

[0084] Among them, the memory 500 may include a high-speed random access memory (RAM, Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between this system network element and at least one other network element is realized through at least one communication interface 503 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used. The bus 502 can be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of easy representation, Figure 5 only a bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0085] The processor 501 may be an integrated circuit chip with signal processing capabilities. In the implementation process, the steps of the above method can be completed by the integrated logic circuit in the hardware of the processor 501 or the instructions in the form of software. The above-mentioned processor 501 can be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it can also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 500, and the processor 501 reads the information in the memory 500 and combines its hardware to complete the steps of the method in the foregoing embodiments.

[0086] An embodiment of the present invention also provides a computer-readable storage medium storing computer-executable instructions, which, when called and executed by a processor, cause the processor to implement the above-mentioned low-altitude relative altitude measurement method. For specific implementation, reference may be made to the method embodiment, which will not be elaborated herein.

[0087] A computer program product for implementing the low-altitude relative altitude measurement method provided by an embodiment of the present invention includes a computer-readable storage medium storing non-volatile program code executable by a processor. The instructions included in the program code are used to execute the method described in the foregoing method embodiment. For specific implementation, reference may be made to the method embodiment, which will not be elaborated herein.

[0088] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, which will not be elaborated herein.

[0089] In several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings, direct couplings, or communication connections between each other can be through some communication interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0090] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0091] In addition, in each embodiment of the present invention, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0092] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0093] Finally, it should be noted that the above-mentioned embodiments are only specific implementation manners of the present invention, used to illustrate the technical solution of the present invention, rather than limiting it. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that any technician familiar with the technical field of the present invention can still modify the technical solutions recorded in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes, or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for measuring the relative height at low altitude, characterized in that, The method includes: Obtaining measurement information collected by a ranging device; Performing anomaly detection based on the measurement information to determine whether there is anomalous measurement information; If there is the anomalous measurement information, inputting the anomalous measurement information into a pre-constructed anomaly correction model to output target measurement information; the anomaly correction model is obtained by optimizing and iterating unknown parameters through a Bayesian optimization method; Replacing the anomalous measurement information with the target measurement information; Performing data fusion based on the target measurement information to obtain the low-altitude relative height.

2. The method according to claim 1, wherein The performing anomaly detection based on the measurement information to determine whether there is anomalous measurement information includes: Converting the measurement information through a level conversion circuit to obtain initial measurement information; Performing anomaly detection based on the initial measurement information to determine whether there is anomalous measurement information.

3. The method according to claim 1, wherein The abnormal correction model is represented by the following formula: ; where is the model output, x is the independent variable, is the basis function, is a random variable subject to a Gaussian distribution, w i is the weight, N is the number of the basis functions.

4. The method according to claim 3, characterized in that, The basis function is a linear basis function; the basis function is represented by the following arithmetic expression: ； Among them, x j is the j th input sample, M is the number of samples, β j,i is the hyperparameter of the basis function; N Each of the N ( M + 1) hyperparameters and N weights, N ( M + 1) hyperparameters and N weights are the unknown parameters.

5. The method according to claim 4, characterized in that The objective function for optimizing and iterating the unknown parameters through the Bayesian optimization method is as follows: ; where, y ( x j ) is the response value of the sample x j , Y ( x j ) is the model prediction value, b ( x j ) is the y ( x j ) average value.

6. The method according to claim 5, wherein The construction method of the anomaly correction model is: Pre-constructing a data set and correcting the data set, and presetting a maximum number of iterations; Optimizing the unknown parameters by a Bayesian optimization method; Constructing an initial anomaly correction model based on the corrected data set and the unknown parameters; Validating the initial anomaly correction model based on the objective function; After validation, optimizing the unknown parameters again by a Bayesian optimization method until the maximum number of iterations is reached to obtain the anomaly correction model.

7. The method according to claim 1, wherein The performing data fusion based on the target measurement information to obtain the low-altitude relative height includes: Performing weighted fusion based on the target measurement information to obtain the low-altitude relative height.

8. A low-altitude relative height measurement device, characterized in that, The device includes: A measurement information acquisition module, configured to obtain measurement information collected by a ranging device; An anomaly detection module, configured to perform anomaly detection based on the measurement information to determine whether there is anomalous measurement information; A target measurement information output module, configured to, if there is the anomalous measurement information, input the anomalous measurement information into a pre-constructed anomaly correction model to output target measurement information; the anomaly correction model is obtained by optimizing and iterating unknown parameters through a Bayesian optimization method; An anomalous measurement information replacement module, configured to replace the anomalous measurement information with the target measurement information; A data fusion module, configured to perform data fusion based on the target measurement information to obtain the low-altitude relative height.

9. An electronic device, characterized in that, Including a processor and a memory, the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the low-altitude relative height measurement method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are called and executed by a processor, the computer-executable instructions cause the processor to implement the low-altitude relative height measurement method according to any one of claims 1 to 7.

Images