Unmanned aerial vehicle identification method based on multi-data source trajectory fitting

Abstract

The invention provides an unmanned aerial vehicle identification method based on multi-data-source trajectory fitting, and the method comprises the steps: obtaining and standardizing multi-source trajectory data, and eliminating the offset and scale difference between the data; performing quadratic polynomial fitting on the standardized data to obtain a trajectory fitting polynomial coefficient; calculating the Euclidean distance between the two groups of coefficients, and determining the similarity of the trajectory data; and finally, according to the similarity and a preset standard, judging whether the trajectory data is from the same unmanned aerial vehicle. According to the method, the accuracy and reliability of unmanned aerial vehicle monitoring are improved by integrating the ground radar and the primary radar and secondary radar data of the UTMISS platform. The method shows strong robustness and reliability in a complex airspace, effectively improves the accuracy of unmanned aerial vehicle identity recognition, and provides a powerful guarantee for unmanned aerial vehicle traffic management and airspace safety.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle monitoring and identification, and in particular to a method for unmanned aerial vehicle identification based on trajectory fitting of multiple data sources. Background Art

[0002] With the rapid development of drone technology, the demand for drone monitoring and management is becoming increasingly urgent. Traditional ground radar technology can detect the real-time location information of flying objects, but cannot determine their identity. In application scenarios such as drone traffic management, drone safety monitoring, and airspace management, traditional single data source monitoring methods often face problems such as insufficient information and low recognition rate.

[0003] It should be noted that the information disclosed in the above background technology section is only used for understanding the background of the present application, and therefore may include information that does not constitute prior art known to ordinary technicians in the field. Summary of the invention

[0004] The main purpose of the present invention is to solve the problems existing in the above-mentioned background technology and provide a drone identification method based on trajectory fitting of multiple data sources.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] In a first aspect of the present invention, a method for identifying a drone based on trajectory fitting of multiple data sources comprises the following steps:

[0007] S1. Obtaining drone trajectory data from multiple data sources, wherein the drone trajectory data from multiple data sources includes primary radar data from a ground radar system and secondary radar data from a UTMISS platform;

[0008] S2. Standardizing the drone trajectory data from the multiple data sources to eliminate offsets and scale differences between different data sources;

[0009] S3. Perform quadratic polynomial fitting on the standardized primary radar data and secondary radar data, respectively, to obtain two sets of trajectory fitting polynomial coefficients;

[0010] S4. Calculating the Euclidean distance between the two sets of trajectory fitting polynomial coefficients;

[0011] S5. determining the similarity of the two sets of trajectory data according to the calculated Euclidean value;

[0012] S6. Determine whether the two sets of trajectory data are from the same UAV based on the similarity between the two sets of trajectory data and a preset judgment criterion.

[0013] Furthermore, step S1 also includes cleaning the drone trajectory data from multiple data sources.

[0014] Furthermore, step S1 also includes preprocessing the primary radar data and the secondary radar data, wherein the preprocessing includes data screening, field normalization, sampling unification, and exception handling.

[0015] Further, step S1 includes:

[0016] Query the database for unfitted secondary radar data within a specified time period and group them by drone number;

[0017] For a set of acquired secondary radar data, determine the time period corresponding to the set of acquired secondary radar data, and retrieve the unsuccessfully fitted primary radar data from the database based on the time period;

[0018] Group the retrieved primary radar data according to the track number;

[0019] Traverse each set of primary radar data, select a set of data whose data volume meets the predetermined conditions, and ensure that the distance between the last point of the primary radar data and the secondary radar data is within a predetermined range;

[0020] In step S2, the filtered primary radar data and secondary radar data are standardized to eliminate data scale differences.

[0021] Further, in step S1, the acquired primary radar data and secondary radar data are organized into a two-dimensional matrix format, wherein each row represents a two-dimensional coordinate point of the UAV at a moment;

[0022] In step S2, the zscore function is applied to each row of the organized two-dimensional matrix to achieve data centering and scaling to the same scale range.

[0023] Furthermore, in step S2, the drone trajectory data from the multiple data sources are standardized using the zscore function.

[0024] Furthermore, in step S3, two sets of trajectory fitting polynomial coefficients obtained by performing quadratic polynomial fitting on the primary radar data and the secondary radar data are dense fitting coefficients denseFit and sparse fitting coefficients sparseFit, respectively.

[0025] Furthermore, in step S5, the calculated Euclidean distance is normalized to obtain a similarity percentage; in step S6, the calculated similarity percentage is compared with a preset threshold, and if the similarity percentage exceeds the threshold, it is determined that the two sets of trajectory data are from the same drone.

[0026] In a second aspect of the present invention, a computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the method for identifying drones based on trajectory fitting from multiple data sources.

[0027] In a third aspect of the present invention, a computer program product includes a computer program, characterized in that when the computer program is executed by a processor, the method for identifying a drone based on trajectory fitting of multiple data sources is implemented.

[0028] The present invention has the following beneficial effects:

[0029] In application scenarios such as drone traffic management, drone safety monitoring, and airspace management, traditional single data source monitoring methods often face problems such as insufficient information and low recognition rate. The present invention proposes a primary and secondary radar target fitting method, which combines the flight data obtained by the ground radar (primary radar) and the UTMISS (secondary radar) platform, and uses an algorithm to match the trajectory data to achieve the identification of the drone identity, overcoming the above-mentioned shortcomings of traditional technology. The present invention integrates multi-source data, uses the primary target information provided by the ground radar and the high-precision secondary radar data provided by the UTMISS platform to form a complete flight trajectory. Subsequently, the trajectory fitting algorithm is used to perform high-precision modeling and analysis on the flight path of the drone, thereby achieving effective identification of the drone identity. Especially in complex airspace environments, the multi-data source trajectory fitting method of the present invention shows strong robustness and reliability, can effectively deal with various interference and false alarm situations, and provides a strong guarantee for drone traffic management and airspace safety.

[0030] Other beneficial effects of the embodiments of the present invention will be further described below. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 Schematic diagram of the framework of a drone identification method based on trajectory fitting of multiple data sources according to an embodiment of the present invention.

[0032] Figure 2 The present invention is a flowchart of a method for identifying a drone based on trajectory fitting of multiple data sources according to an embodiment of the present invention.

[0033] Figure 3 The figure is a schematic diagram of trajectory fitting using primary radar data and secondary radar data to perform quadratic polynomial fitting according to an embodiment of the present invention.

[0034] Figure 4 This is a pseudo code of a drone identification algorithm based on trajectory fitting of multiple data sources according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The following is a detailed description of the embodiments of the present invention. It should be emphasized that the following description is only exemplary and is not intended to limit the scope and application of the present invention.

[0036] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0037] With the rapid development of drone technology, the demand for drone monitoring and management has increased significantly. Although traditional ground radar technology can provide real-time location information of flying objects, it has limitations in identifying their identities. In order to make up for this deficiency, the present invention proposes an innovative solution for drone identification by combining flight data obtained by ground radar (primary radar) and UTMISS (secondary radar) platforms, matching trajectory data through algorithms.

[0038] See also Figures 1 to 3 , an embodiment of the present invention provides a method for identifying a drone based on trajectory fitting of multiple data sources, comprising the following steps:

[0039] Step S1. Data acquisition: Acquire UAV trajectory data from multiple data sources, wherein the UAV trajectory data from multiple data sources includes primary radar data from a ground radar system and secondary radar data from a UTMISS platform.

[0040] In some embodiments, step S1 also includes cleaning the drone trajectory data from multiple data sources.

[0041] See also Figure 1 In a preferred embodiment, step S1 includes preprocessing the primary radar data and the secondary radar data, and the preprocessing includes data screening, field normalization, sampling unification and exception processing.

[0042] See also Figure 2 In a preferred embodiment, step S1 includes: querying the database for unfitted secondary radar data within a specified time period and grouping them by drone number; determining the corresponding time period for a group of acquired secondary radar data, and retrieving the unfitted primary radar data from the database based on the time period; grouping the retrieved primary radar data according to the track number; traversing each group of primary radar data, selecting a group of data whose data volume meets the predetermined conditions, and ensuring that the distance between the last point of the primary radar data and the secondary radar data is within a predetermined range.

[0043] Step S2. Data standardization: Standardize the drone trajectory data from the multiple data sources to eliminate the offset and scale differences between different data sources.

[0044] In some embodiments, the filtered primary radar data and secondary radar data are standardized to eliminate data scale differences.

[0045] In a preferred embodiment, the zscore function is used to standardize the drone trajectory data from the multiple data sources.

[0046] In a preferred embodiment, in the above step S1, the acquired primary radar data and secondary radar data are organized into a two-dimensional matrix format, where each row represents a two-dimensional coordinate point of the drone at a moment. In step S2, the zscore function is applied to each row of the organized two-dimensional matrix to achieve data centering and scaling to the same scale range.

[0047] Step S3. Trajectory fitting: Perform quadratic polynomial fitting on the standardized primary radar data and secondary radar data respectively to obtain two sets of trajectory fitting polynomial coefficients.

[0048] In a preferred embodiment, in step S3, two sets of trajectory fitting polynomial coefficients obtained by performing quadratic polynomial fitting on the primary radar data and the secondary radar data are sparse fitting coefficients sparseFit and dense fitting coefficients denseFit, respectively.

[0049] Figure 3 A schematic diagram of trajectory fitting of performing quadratic polynomial fitting on primary radar data and secondary radar data according to an embodiment of the present invention is shown.

[0050] Step S4. Similarity distance calculation: Calculate the Euclidean distance between the two sets of trajectory fitting polynomial coefficients.

[0051] Step S5. Similarity evaluation: Determine the similarity of two sets of trajectory data according to the calculated Euclidean.

[0052] In some embodiments, in step S5, the calculated Euclidean distance is normalized to obtain a similarity percentage.

[0053] Step S6. Identity recognition: Determine whether the two sets of trajectory data are from the same drone based on the similarity between the two sets of trajectory data and a preset judgment standard.

[0054] In some embodiments, in step S6, the calculated similarity percentage is compared with a preset threshold, and if the similarity percentage exceeds the threshold, it is determined that the two sets of trajectory data are from the same drone.

[0055] The present invention provides a method for identifying unmanned aerial vehicles (UAVs) based on trajectory fitting from multiple data sources, which innovatively combines data from ground radar (primary radar) and UTMISS (secondary radar) platforms, and realizes effective identification of the identity of UAVs by matching trajectory data with algorithms. The method of the present invention not only improves the accuracy and reliability of UAV monitoring, but is also particularly suitable for key application scenarios such as UAV traffic management, UAV safety monitoring, and airspace management. In the face of the common problems of insufficient information and low recognition rate of traditional single data source monitoring methods, the present invention integrates multi-source data and uses primary target information and high-precision secondary radar data to form a complete flight trajectory, which significantly improves the accuracy of recognition. In addition, the trajectory fitting algorithm used in the present invention performs high-precision modeling and analysis of the flight path of the UAV, further enhancing the robustness and reliability in complex airspace environments, effectively responding to various interferences and false alarms, and providing a strong guarantee for UAV traffic management and airspace safety, filling the gap in the prior art.

[0056] The specific embodiments of the present invention are further described below.

[0057] A drone identification method based on trajectory fitting of multiple data sources includes the following processing steps:

[0058] 1. Data processing engine

[0059] The data from the primary radar and secondary radar are preprocessed, including data screening, field normalization, sampling unification, exception handling and other steps to ensure high data quality.

[0060] 2. Fitting Engine

[0061] A trajectory fitting method for multiple data sources is proposed. Through the trajectory fitting algorithm, the processed data is matched and analyzed, and the primary radar and secondary radar data are combined to identify drones through trajectory fitting technology. The algorithm compares the polynomial fitting of the flight trajectory and calculates the Euclidean distance to determine whether the two sets of data come from the same flying object. In this process, the algorithm takes into account the error factors in actual flight and has a certain fault tolerance, thereby improving the robustness and accuracy of recognition.

[0062] Data standardization: The zscore function is used to standardize the trajectory data to solve the problems of offset and scale differences between different data sources.

[0063] Quadratic polynomial fitting algorithm: A quadratic polynomial fitting method is used to accurately fit the standardized trajectory data and calculate the Euclidean distance between the fitting polynomial coefficients.

[0064] Similarity calculation and judgment: By calculating the Euclidean distance between the coefficients of the two sets of trajectory fitting polynomials and normalizing them into a similarity percentage, we can determine whether they are the same drone.

[0065] Examples

[0066] Query the database for the unfitted secondary radar data in the last 2 minutes and group them by drone number. Take out a set of secondary radar data and obtain the time period of the set of data. According to the time, retrieve the unfitted primary radar data from the database, group them by track number, traverse each set of primary radar data, and filter out the primary radar data with more than 20 data and the distance between the last point of the primary radar data and the secondary radar data within a certain range.

[0067] The two sets of trajectory data are standardized to centralize and scale the data to the same range, reducing the impact of data offset and scale differences on the results. The two sets of drone trajectory data data1 and data2 are in the format of a two-dimensional matrix, with each row containing a two-dimensional coordinate point at a time. The two sets of trajectory data are fitted with quadratic polynomials to obtain the fitted polynomial coefficients. The Euclidean distance between the two sets of trajectory fitting polynomial coefficients is calculated, and the similarity percentage is calculated based on the distance. According to the calculated similarity percentage, it is determined whether the two sets of trajectory data are from the same drone.

[0068] The pseudo code of the drone identification algorithm based on trajectory fitting of multiple data sources is as follows Figure 4 shown.

[0069] The specific processing steps are as follows:

[0070] Data Standardization

[0071] The drone trajectory data is standardized to eliminate the impact of data scale differences. Each set of trajectory data is standardized using the zscore function to ensure that the data has zero mean and unit variance. This step can improve the accuracy and robustness of subsequent polynomial fitting.

[0072] Quadratic polynomial fitting

[0073] The standardized trajectory data are fitted with quadratic polynomials to capture the key features of the trajectory. The polyfit function is used to fit the quadratic polynomial coefficients denseFit and sparseFit of the trajectory data. This step uses polynomial fitting technology to map the trajectory data into a set of mathematical features to facilitate subsequent similarity calculations.

[0074] Similarity calculation

[0075] Calculate the Euclidean distance between the coefficients of two fitted polynomials and normalize the distance to a similarity percentage.

[0076] Compared with traditional technologies, the present invention innovatively integrates the data of ground radar (primary radar) and UTMISS (secondary radar) platforms, accurately matches the trajectory data through algorithms, and effectively realizes the accurate identification of the drone's identity. In the face of the shortcomings of traditional monitoring methods in information acquisition and recognition rate, the present invention uses multi-source data fusion technology to combine primary target information and high-precision secondary radar data to form a complete flight trajectory. By applying a trajectory fitting algorithm to perform high-precision modeling and analysis of the drone's flight path, the present invention demonstrates excellent robustness and reliability in complex airspace environments, effectively handles various interferences and false alarms, and provides solid technical support for drone traffic management and airspace safety. In general, the method of the present invention not only significantly improves the accuracy and reliability of monitoring, but also particularly enhances the application capabilities in key areas such as drone traffic management, safety monitoring, and airspace management.

[0077] An embodiment of the present invention further provides a storage medium for storing a computer program, which at least performs the above method when executed.

[0078] An embodiment of the present invention further provides a control device, comprising a processor and a storage medium for storing a computer program; wherein the processor is configured to execute at least the method described above when executing the computer program.

[0079] An embodiment of the present invention further provides a processor, wherein the processor executes a computer program and at least executes the method described above.

[0080] The storage medium can be implemented by any type of non-volatile storage device, or a combination thereof. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The storage medium described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0081] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0082] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0083] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0084] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, etc. Various media that can store program codes.

[0085] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0086] The methods disclosed in the several method embodiments provided by the present invention can be arbitrarily combined without conflict to obtain new method embodiments.

[0087] The features disclosed in several product embodiments provided by the present invention can be arbitrarily combined without conflict to obtain new product embodiments.

[0088] The features disclosed in several method or device embodiments provided by the present invention can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0089] The above contents are further detailed descriptions of the present invention in combination with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art of the present invention, several equivalent substitutions or obvious variations can be made without departing from the concept of the present invention, and the performance or use is the same, which should be regarded as belonging to the protection scope of the present invention.

Claims

1. A drone identification method based on trajectory fitting of multiple data sources, characterized in that: The following steps are involved: S1. Obtaining drone trajectory data from multiple data sources, wherein the drone trajectory data from multiple data sources includes primary radar data from a ground radar system and secondary radar data from a UTMISS platform; S2. Standardizing the drone trajectory data from the multiple data sources to eliminate offsets and scale differences between different data sources; S3. Perform quadratic polynomial fitting on the standardized primary radar data and secondary radar data, respectively, to obtain two sets of trajectory fitting polynomial coefficients; S4. Calculating the Euclidean distance between the two sets of trajectory fitting polynomial coefficients; S5. determining the similarity of the two sets of trajectory data according to the calculated Euclidean value; S6. Determine whether the two sets of trajectory data are from the same UAV based on the similarity between the two sets of trajectory data and a preset judgment criterion.

2. The method for identifying unmanned aerial vehicles based on trajectory fitting of multiple data sources as claimed in claim 1, characterized in that: Step S1 also includes cleaning the drone trajectory data from multiple data sources.

3. The method for identifying unmanned aerial vehicles based on trajectory fitting of multiple data sources according to claim 1 or 2, characterized in that: Step S1 also includes preprocessing the primary radar data and the secondary radar data, wherein the preprocessing includes data screening, field normalization, sampling unification, and exception handling.

4. The method for identifying unmanned aerial vehicles based on trajectory fitting of multiple data sources according to any one of claims 1 to 3, characterized in that: Step S1 includes: Query the database for unfitted secondary radar data within a specified time period and group them by drone number; For a set of acquired secondary radar data, determine the corresponding time period, and retrieve the unsuccessfully fitted primary radar data from the database based on the time period; Group the retrieved primary radar data according to the track number; Traverse each set of primary radar data, select a set of data whose data volume meets the predetermined conditions, and ensure that the distance between the last point of the primary radar data and the secondary radar data is within a predetermined range; In step S2, the filtered primary radar data and secondary radar data are standardized to eliminate data scale differences.

5. The method for identifying unmanned aerial vehicles based on trajectory fitting of multiple data sources according to any one of claims 1 to 4, characterized in that: In step S1, the acquired primary radar data and secondary radar data are organized into a two-dimensional matrix format, where each row represents a two-dimensional coordinate point of the UAV at a moment; In step S2, the zscore function is applied to each row of the organized two-dimensional matrix to achieve data centering and scaling to the same scale range.

6. The method for identifying unmanned aerial vehicles based on trajectory fitting of multiple data sources according to any one of claims 1 to 5, characterized in that: In step S2, the zscore function is used to standardize the drone trajectory data from the multiple data sources.

7. The method for identifying unmanned aerial vehicles based on trajectory fitting of multiple data sources according to any one of claims 1 to 6, characterized in that: In step S3, two sets of trajectory fitting polynomial coefficients obtained by performing quadratic polynomial fitting on the primary radar data and the secondary radar data are sparse fitting coefficients sparseFit and dense fitting coefficients denseFit respectively.

8. The method for identifying unmanned aerial vehicles based on trajectory fitting of multiple data sources according to any one of claims 1 to 7, characterized in that: In step S5, the calculated Euclidean distance is normalized to obtain a similarity percentage; in step S6, the calculated similarity percentage is compared with a preset threshold, and if the similarity percentage exceeds the threshold, it is determined that the two sets of trajectory data are from the same drone.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for identifying a drone based on trajectory fitting of multiple data sources as described in any one of claims 1 to 8 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for identifying a drone based on trajectory fitting of multiple data sources as described in any one of claims 1 to 8 is implemented.

Images