A Low-Altitude UAV Trajectory Tracking Method and System Based on Multi-Source Data Fusion

Abstract

The present invention discloses a method and system for low-altitude UAV trajectory tracking with multi-source data fusion, including: Track data acquisition: divided into cooperative track data acquisition and non-cooperative data acquisition; Track data and track fusion: divided into two categories, namely cooperative track data and cooperative track fusion, and radar track data and radar track fusion processing; Track data and track fusion includes: data preprocessing, track data filtering and updating, and track data and track association; Cooperative track and radar track fusion: used for the association and fusion of cooperative tracks and radar standard tracks, including a track filtering sub-process and track and track association; Track management: used to maintain and manage all current tracks, including the maintenance and management of temporary tracks and stable tracks. The temporary tracks are mainly radar temporary tracks, and the stable tracks include stable cooperative target tracks and radar stable tracks. It can achieve the fusion tracking of UAV trajectories detected by multiple heterogeneous sensing devices.

Description

Technical Field

[0001] The present invention belongs to the field of low-altitude economy and unmanned aerial vehicle (UAV) applications, and particularly relates to a method and system for tracking the trajectories of low-altitude UAVs with multi-source data fusion. Background Art

[0002] The low-altitude economy is regarded as an important engine for future economic development. With the opening of low-altitude airspace and the expansion of UAV application fields, new challenges have been brought to national security, social security, and personal privacy protection. To develop the low-altitude economy represented by UAVs while also taking into account national and social security and personal privacy protection, UAV supervision technology is the key to solving the above problems. How to identify cooperative UAVs and non-cooperative UAVs and perform real-time tracking and prediction of their flight trajectories is the core technology for UAV supervision.

[0003] Currently, the means of detecting and tracking UAVs mainly include ADS-B identification technology, radar detection, and optoelectronic detection, etc. However, due to the limitations of technical principles and working conditions, a single detection technology cannot detect and track UAVs in all directions and throughout the process. Simultaneously using multiple detection devices to detect and track UAVs is a reliable solution. However, when using multiple devices for detection, due to different data sources (such as radar, ADS-B, data reported by cooperative UAV platforms, etc.), and each data source may also be mixed with interference data, multiple data sources for the same target often occur. Summary of the Invention

[0004] In order to solve the technical problems existing in the background art, the present invention aims to provide a method and system for tracking the trajectories of low-altitude UAVs with multi-source data fusion, which comprehensively organizes each single data and outputs unified, more complete, and more comprehensive data to achieve all-round and whole-process monitoring of UAVs in the target airspace.

[0005] To solve the technical problems, the technical solution of the present invention is as follows:

[0006] A system for tracking the trajectories of low-altitude UAVs with multi-source data fusion, the system includes: a track data acquisition module, a track data and track fusion module, a cooperative track and radar track fusion module, and a track management module;

[0007] The track data acquisition module includes: a cooperative track data acquisition unit and a non-cooperative data acquisition unit; the cooperative track data includes: ADS-B track data and UAV platform track data, and the non-cooperative track data includes: track data monitored by radar;

[0008] The track data and track fusion module includes a cooperative track data and cooperative track fusion unit, and a radar track data and radar track fusion unit; both are used for data preprocessing, track data filtering and updating, and track data and track association;

[0009] The cooperative track and radar track fusion module is used for associating and fusing cooperative tracks and radar standard tracks, and includes a track filtering sub-process and track and track association;

[0010] The track management module is used to maintain and manage all current tracks, including the maintenance and management of temporary tracks and stable tracks. The temporary tracks include radar temporary tracks, and the stable tracks include stable cooperative target tracks and radar stable tracks.

[0011] Furthermore, the track data includes: altitude, longitude, latitude, heading angle, speed, acquisition time, target batch number, and target identification information.

[0012] Furthermore, the cooperative track and radar track fusion module uses the nearest neighbor association criterion to determine whether two tracks are associated. If there is a certain radar track and there are N consecutive points, N≥3 and N is configurable, and all are associated with the same cooperative track, then the two tracks are considered to be associated.

[0013] Furthermore, the track data and track fusion, and the cooperative track and radar track fusion together form a two-level fusion; in the cooperative track data and track fusion unit, the cooperative track data and cooperative track process association fusion processing are carried out. In the radar track data and radar track fusion unit, the radar data and radar track association fusion processing are carried out; in the cooperative track and radar track fusion module, the cooperative track and radar track association fusion are completed to form a multi-source unified target track monitoring;

[0014] Among them, the track data and track fusion processing flow: preprocess the track data, then perform track filtering and updating, and then perform track data and track association processing;

[0015] The track data preprocessing includes: data parsing, parsing the data from different detection devices or systems such as ADS-B devices, unmanned aircraft cloud platforms, and radars according to the data protocol and converting them into a unified data format; data spatio-temporal conversion, including time alignment processing and track data coordinate system conversion. The unified track data coordinate system is a rectangular coordinate system with a set reference position as the origin; data cleaning is to filter out invalid data and interference data, including judging whether data items are missing, judging whether it exceeds the equipment monitoring airspace range, judging the time difference, and processing duplicate data.

[0016] Further, when associating the cooperative track data with the cooperative track, it is associated with the cooperative track through the target identifier of the cooperative data. If associated, the cooperative target track is updated; if not associated, a new starting point of the cooperative target track is generated. When associating the radar track data with the radar track, it is associated with the radar track according to the target batch number. If associated, the radar target track is updated; if not associated, it is associated with the radar target temporary track.

[0017] The association between the track data and the track is carried out in a rectangular coordinate system centered on the reference position point.

[0018] For the track filtering update, the velocities and coordinates in the x, y, and z directions are calculated through a filtering algorithm, and the heading angle and flight speed are predicted based on the filtered x, y, and z data, and then updated into the corresponding tracks.

[0019] Further, in the fusion of the cooperative track and the radar track, if more than N consecutive points of the cooperative target track are associated with the radar stable target track, the cooperative target track is associated with the radar stable target track, and the cooperative track data is associated with the radar stable target track.

[0020] Further, in the three processes of the fusion of cooperative track data and track, the fusion of radar data and track, and the fusion of cooperative track and radar track, the α-β filter is used for track filtering update. When updating the track with the α-β filter, the x and y axes of the track are filtered first, and then the z axis is filtered.

[0021] A low-altitude UAV trajectory tracking method for multi-source data fusion, characterized in that the method is applied to any one of the above systems, and the method includes:

[0022] S1: Obtain track monitoring data, judge the track data type. If it is radar track data, jump to step S2; if it is cooperative track data, jump to step S4.

[0023] S2: First perform filtering processing on the radar track data, and then judge whether there is an associated radar stable track. If not associated, jump to step S3; if associated, further judge whether it is a cooperative target track. If so, fuse and update the track with the cooperative target track to obtain the cooperative target track; if not, obtain the radar stable track.

[0024] S3: Judge whether it is associated with the radar temporary track. If so, convert the temporary track into a stable track to obtain the radar stable track; if not, obtain a new track starting point to obtain the radar temporary track.

[0025] S4: First, perform cooperative track filtering on the cooperative track data, and then determine whether it is associated with the cooperative track. If not, generate a new starting point for the cooperative target to obtain the cooperative target track. If it is associated, determine whether there is an associated stable radar track. If not, obtain the cooperative target track. If so, jump to step S5;

[0026] S5: Mark the radar track as the track of the cooperative target, and then determine whether the cooperative track data is an outlier. If so, delete the outlier data to obtain the cooperative target track. If not, directly obtain the cooperative target track.

[0027] Compared with the prior art, the advantages of the present invention are as follows:

[0028] 1. A two - stage fusion processing method for track data and track fusion technology: Hierarchical fusion reduces the complexity of the fusion processing and improves the compatibility and expandability of the fusion system. Moreover, it has a fast fusion processing speed and high accuracy of the fusion result;

[0029] 2. Application of distributed fusion processing technology: In the process of data acquisition and track data and track fusion, a distributed fusion processing method is adopted to separately process the cooperative track data and track fusion, radar track data and radar fusion, and finally perform the fusion of the cooperative track and the radar track, which is beneficial to distinguish cooperative targets from non - cooperative targets.

[0030] 3. Flexible use of the adaptive α - β filtering algorithm multiple times: The α - β filtering does not depend on the specific model of the system and has the advantages of good stability and fast calculation speed. Using the α - β filtering algorithm three times can not only process dynamic data and track complex targets, but also ensure the speed and performance of the system;

[0031] 4. Intelligent track maintenance and management technology: During the flight of the UAV, it may occur that some track data of the device is lost, or the UAV lands. For data loss, the data of the last point in the track can be combined with AI reasoning to estimate the approximate position after the lost time period.

[0032] A UAV track tracking method based on multi - source data fusion provided by the present invention, compared with the prior art, can achieve efficient fusion of data from multi - source heterogeneous detection devices, accurately track and predict the UAV track, and at the same time accurately distinguish cooperative UAV tracks and non - cooperative UAV tracks. It can effectively realize the effective supervision of UAVs and the prediction of their flight risks, which is beneficial to promoting the rapid development of the low - altitude economy on the premise of ensuring national, social security and personal privacy. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 Shows a diagram of a UAV track tracking method based on multi - source data fusion provided by an embodiment of the present invention;

[0034] Figure 2 Shows the specific method processing flow chart provided by the embodiments of the present invention. Detailed implementation manners

[0035] The following describes the detailed implementation manners of the present invention in combination with embodiments:

[0036] It should be noted that the structures, ratios, sizes, etc. shown in this specification are only used to cooperate with the content disclosed in the specification for those skilled in this technology to understand and read, and are not used to limit the limited conditions under which the present invention can be implemented. Any modification of the structure, change of the proportional relationship or adjustment of the size, without affecting the effects that the present invention can produce and the purposes that can be achieved, should still fall within the scope covered by the technical content disclosed in the present invention.

[0037] At the same time, the terms such as "up", "down", "left", "right", "middle" and "one" cited in this specification are only for the convenience of clear narration, and are not used to limit the scope in which the present invention can be implemented. The change or adjustment of their relative relationships, without substantial change in the technical content, should also be regarded as the scope in which the present invention can be implemented.

[0038] Embodiment 1:

[0039] As Figure 1 shown, a UAV trajectory tracking method based on multi-source data fusion mainly adopts secondary data fusion processing and combines the α-β filtering algorithm. The whole processing flow includes four sub-processes: trajectory data acquisition, trajectory data and trajectory fusion, cooperative trajectory and radar trajectory fusion, and trajectory management; it can fuse multi-source heterogeneous trajectory data from the ADS-B system, UAV platform, radar detection, etc., and realize the tracking and prediction of UAV trajectories.

[0040] The trajectory data acquisition includes cooperative trajectory data acquisition and non-cooperative data acquisition. The cooperative trajectory data mainly includes ADS-B trajectory data and UAV platform trajectory data, and the non-cooperative trajectory data is the trajectory data monitored by the radar; the trajectory data includes: altitude, longitude, latitude, heading angle, speed, acquisition time, target batch number (radar trajectory data) and target identification (cooperative trajectory data) information.

[0041] The above-mentioned track data and track fusion include cooperative track data and track fusion processing, and radar track data and radar track fusion processing; the cooperative track data and track fusion processing is mainly used for the association processing of cooperative track data and cooperative tracks, including data preprocessing, track filtering and updating, and data and track fusion; the radar track data and radar track fusion processing is mainly used for the association processing of radar track data and radar tracks, including data preprocessing, track filtering and updating, and data and track fusion.

[0042] For the above-mentioned cooperative track and radar track fusion processing, the nearest neighbor association criterion is used to judge whether two tracks are associated. If there is a certain radar track, and there are N consecutive points (N≥3 and N is configurable) that are all associated with the same cooperative track, then the two tracks are considered to be associated.

[0043] The above-mentioned track management is used to maintain and manage all tracks of the system, including the maintenance and management of temporary tracks and stable tracks. Temporary tracks include temporary cooperative tracks and temporary radar tracks, and stable tracks include stable cooperative tracks and stable radar tracks.

[0044] Furthermore, a two-level fusion processing method is adopted for track data and track fusion;

[0045] First, in the cooperative track data and track fusion processing flow, the association fusion processing of cooperative track data and cooperative track processes is carried out, and in the radar track data and track processing flow, the association fusion of radar data and radar tracks is carried out; then, in the cooperative track and radar track fusion processing flow, the association fusion of cooperative tracks and radar tracks is completed to form a unified target multi-source surveillance track.

[0046] Furthermore, the track data and track fusion processing flow is to first perform data budget processing on the track data, then perform track filtering and updating on the track, and then perform the association processing of track data and track.

[0047] The preprocessing of the collaborative track data includes the protocol parsing of multi-source heterogeneous data from ADS-B, UAV cloud platforms, and radars, data filtering and cleaning, and data spatio-temporal conversion to unify the data format and spatio-temporal background. The data spatio-temporal conversion is to realize the spatio-temporal union of position coordinate data and convert the position data into a rectangular coordinate system with the reference position as the origin, and the reference position can be configured and modified in the system. The data cleaning is to filter out invalid data and interference data, including judging whether data items are missing, whether they exceed the monitoring airspace range of the device, the time difference, and processing duplicate data. Among them: (1) Data parsing: For data from different detection devices or systems (such as ADS-B devices, UAV cloud platforms, and radars), parse according to their data protocols and convert them into a unified data format (Protobuf format is adopted in the implementation). (2) Data spatio-temporal conversion: including time alignment processing and track data coordinate system conversion. The unified track data coordinate system is a rectangular coordinate system with the set reference position as the origin. (3) Data cleaning: Filter out invalid data and interference data, including judging whether data items are missing, whether they exceed the monitoring airspace range of the device, the time difference, and processing duplicate data.

[0048] Further, when associating the collaborative track data with the collaborative track, it is associated with the collaborative track through the target identifier of the collaborative data. If associated, the collaborative target track is updated; if not associated, a new starting point of the collaborative target track is generated.

[0049] When associating the radar track data with the radar track, it is associated with the radar track according to the target batch number. If associated, the radar target track is updated; if not associated, it is associated with the temporary radar target track.

[0050] The association between the described track data and the track is carried out in a rectangular coordinate system centered on the reference position point (i.e., x, y, z coordinates).

[0051] The described track filtering and updating is to calculate the speeds and coordinates in the x, y, and z directions through a filtering algorithm, predict the heading angle, flight speed, etc. based on the filtered x, y, z data, and then update them into the corresponding tracks.

[0052] Further, for the fusion of the collaborative track and the radar track, the nearest neighbor association criterion is used to judge whether the two tracks are associated. If more than N consecutive points of the collaborative target track are associated with the stable radar target track, the collaborative target track is associated with the stable radar target track, and the collaborative track data is associated with the stable radar target track.

[0053] Further, the UAV trajectory tracking method uses the multiple α-β filtering algorithm for trajectory filtering and updating. The α-β filter is used for trajectory filtering and updating in the three processes of cooperative trajectory data and trajectory fusion, radar data and radar trajectory fusion, and cooperative trajectory and radar trajectory fusion. When performing α-β filtering and updating on the trajectory, the x and y axes of the trajectory are filtered first, and then the z axis is filtered.

[0054] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0055] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, so that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0056] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0057] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0058] The above has described the preferred embodiments of the present invention in detail. However, the present invention is not limited to the above embodiments, and various changes can be made without departing from the spirit of the present invention within the scope of knowledge possessed by those of ordinary skill in the art.

[0059] Many other changes and modifications can be made without departing from the concept and scope of the present invention. It should be understood that the present invention is not limited to specific embodiments, and the scope of the present invention is defined by the appended claims.

Claims

1. A low-altitude UAV trajectory tracking system for multi-source data fusion, characterized in that The system includes: a track data acquisition module, a track data and track fusion module, a cooperative track and radar track fusion module, and a track management module; The track data acquisition module includes: a cooperative track data acquisition unit and a non-cooperative track data acquisition unit; the cooperative track data includes: ADS-B track data and UAV platform track data, and the non-cooperative track data includes: track data monitored by radar; The track data and track fusion module includes a cooperative track data and cooperative track fusion unit, and a radar track data and radar track fusion unit; both are used for data preprocessing, track data filtering and updating, and track data and track association; two modules of track data and track fusion, and cooperative track and radar track fusion together constitute two-level fusion; in the cooperative track data and track fusion unit, cooperative track data and cooperative track process association fusion processing are carried out, and in the radar track data and radar track fusion unit, radar data and radar track association fusion processing are carried out; in the cooperative track and radar track fusion module, cooperative track and radar track association fusion is completed to form multi-source unified target track monitoring; among them, the track data and track fusion processing process: preprocess the track data, then perform track filtering and updating, and then perform track data and track association processing; the track data preprocessing includes: data parsing, parsing and converting the data from different detection devices or systems such as ADS-B devices, UAV cloud platforms and radars according to the data protocol into a unified data format; data spatio-temporal conversion, including time alignment processing and track data coordinate system conversion, and the unified track data coordinate system is a rectangular coordinate system with a set reference position as the origin; data cleaning to filter invalid data and interference data, including judging whether data items are missing, judging whether it exceeds the device monitoring airspace range, judging the time difference and processing duplicate data; The cooperative track and radar track fusion module is used for associating and fusing cooperative tracks and radar tracks, including a track filtering sub-process and track and track association; the cooperative track and radar track fusion module uses the nearest neighbor association criterion to judge whether two tracks are associated. If there is a certain radar track and there are N consecutive points, N≥3 and N is configurable, all of which are associated with the same cooperative track, then the two tracks are considered to be associated; The track management module is used to maintain and manage all current tracks, including the maintenance and management of temporary tracks and stable tracks. The temporary tracks include radar temporary tracks, and the stable tracks include stable cooperative target tracks and radar stable tracks.

2. The low-altitude UAV trajectory tracking system for multi-source data fusion according to claim 1, wherein The track data includes: altitude, longitude, latitude, heading angle, speed, acquisition time, target batch number, and target identification information.

3. A low-altitude UAV trajectory tracking system for multi-source data fusion according to claim 1, characterized in that, When associating the collaborative track data with the collaborative track, it is associated with the collaborative track through the target identifier of the collaborative data. If associated, the collaborative target track is updated; if not associated, a new starting point of the collaborative target track is generated. When associating the radar track data with the radar track, it is associated with the radar track according to the target batch number. If associated, the radar target track is updated; if not associated, it is associated with the temporary radar target track. The association between the track data and the track is carried out in a rectangular coordinate system centered on the reference position point. For the track filtering update, the velocities and coordinates in the x, y, and z directions are calculated through a filtering algorithm, and the heading angle and flight speed are predicted based on the filtered x, y, and z data, and then updated into the corresponding track.

4. A low-altitude UAV trajectory tracking system for multi-source data fusion according to claim 1, characterized in that, In the fusion of the collaborative track and the radar track, if more than N consecutive points of the collaborative target track are associated with the stable radar target track, the collaborative target track is associated with the stable radar target track, and the collaborative track data is associated with the stable radar target track.

5. A low-altitude UAV trajectory tracking system for multi-source data fusion according to claim 1, characterized in that, In the three processes of the fusion of collaborative track data and track, the fusion of radar data and track, and the fusion of collaborative track and radar track, α-β filtering is used for track filtering update. When updating the track by α-β filtering, the x and y axes of the track are filtered first, and then the z axis is filtered.

6. A method for tracking the trajectory of low-altitude unmanned aerial vehicles with multi-source data fusion, characterized in that, The method is applied to the system according to any one of claims 1-5, and the method includes: S1: Obtain track monitoring data, judge the type of track data. If it is radar track data, jump to step S2; if it is collaborative track data, jump to step S4. S2: First perform filtering processing on the radar track data, and then judge whether there is an associated stable radar track. If not associated, jump to step S3; if associated, further judge whether it is a collaborative target track. If so, fuse and update the track with the collaborative target track to obtain the collaborative target track; if not, obtain the stable radar track. S3: Judge whether it is associated with the temporary radar track. If so, convert the temporary track into a stable track to obtain the stable radar track; if not, obtain a new track starting point to obtain the temporary radar track. S4: First perform collaborative track filtering processing on the collaborative track data, and then judge whether it is associated with the collaborative track. If not associated, generate a new starting point of the collaborative target to obtain the collaborative target track; if associated, judge whether there is an associated stable radar track. If not, obtain the collaborative target track; if so, jump to step S5. S5: Mark the radar track as the track of the collaborative target, and then judge whether the collaborative track data is an outlier point. If so, delete the outlier point data to obtain the collaborative target track; if not, directly obtain the collaborative target track.

Images