Single unmanned aerial vehicle target tracking method and system based on improved box particle filtering algorithm

Abstract

The application discloses a single unmanned aerial vehicle target tracking method and system based on an improved box particle filtering algorithm, and belongs to the field of unmanned aerial vehicle target tracking. The application improves the box particle filtering algorithm, the improved box particle filtering algorithm has low time complexity and high real-time performance, can realize more accurate and robust target tracking, and solves the problems of low accuracy and poor real-time performance of various traditional interval analysis methods in the updating process of the box particle filtering in the existing tracking algorithm under the condition of the single unmanned aerial vehicle.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle target tracking, and particularly relates to a single unmanned aerial vehicle target tracking method and system based on an improved box particle filter algorithm. BACKGROUND

[0002] In the field of unmanned aerial vehicle target tracking, unmanned aerial vehicles (UAVs) are widely used in aerial photography, agriculture, plant protection, express delivery, disaster rescue, observation of wild animals, monitoring of infectious diseases, surveying and mapping, news reporting, power inspection, and military fields. With the increasing application of unmanned aerial vehicles, the demand for unmanned aerial vehicle target tracking technology is also growing, especially the ability to track targets based on non-visual sensor data.

[0003] Unmanned aerial vehicle target tracking technology has a wide range of applications in military reconnaissance, environmental monitoring, traffic monitoring, and other fields. Existing target tracking algorithms, especially those based on vision, often struggle to maintain stable and accurate tracking in complex environments such as rapid movement, changes in lighting, and occlusions. In addition, the computing resources and energy supply of unmanned aerial vehicle platforms are limited, which puts higher requirements on the real-time performance and computational efficiency of tracking algorithms.

[0004] Traditional particle filter (PF) is flexible in handling non-linear and non-Gaussian problems, but the algorithm needs to generate a large number of random particles, which is less real-time. Moreover, as time goes on, particle filter will have the problem of particle degeneracy, that is, most of the particles have negligible weights, only a few particles carry almost all the weights, leading to a decrease in sample diversity and affecting tracking performance. SUMMARY

[0005] The present application provides a single unmanned aerial vehicle target tracking method and system based on an improved box particle filter algorithm, which improves the box particle filter algorithm. The improved box particle filter algorithm has low time complexity and high real-time performance, can achieve more accurate and robust target tracking, and solves the problem of low accuracy and poor real-time performance of traditional interval analysis methods in the updating process of the box particle filter in the existing tracking algorithm under the condition of a single unmanned aerial vehicle.

[0006] The first aspect of the present application provides a single unmanned aerial vehicle target tracking method based on an improved box particle filter algorithm, comprising the following steps:

[0007] Obtaining the measurement data returned by the non-visual sensor of the unmanned aerial vehicle;

[0008] Establishing a relative polar coordinate system of the unmanned aerial vehicle-target with the unmanned aerial vehicle as the origin, modifying the box particle information and state space boundary of the box particle filter algorithm according to the non-visual measurement data, so that the modified box particle interval and the measurement interval are both part of the spherical shell of the sphere.

[0009] During the update process of the box particle filtering algorithm, when the box particle shrinks, it is determined whether all or part of the eight vertices of each box particle interval are within the measurement interval. The coordinates of the vertices within the measurement interval and the boundary of the measurement interval are used to form a new spherical shell, thus obtaining the shrunken box particle.

[0010] The volume of each box particle after shrinkage is calculated as the weight of the box particle. After normalization, state estimation is performed. After reaching the tracking step number, the non-visual target tracking result of the UAV is obtained.

[0011] Optionally, in one embodiment of the present invention, the measurement data returned by the non-visual sensor includes: distance, azimuth angle, and pitch angle.

[0012] Optionally, in one embodiment of the present invention, modifying the box particle information and state space boundary of the box particle filtering algorithm based on non-visual measurement data includes:

[0013] Box particle information is composed of [X,Y,Z,X length ,Y length Z length Improved to The state space boundary is defined by [X] min ,X max ;Y min ,Y max Z min Z max Improved to Where X, Y, Z are the Cartesian coordinates of the box particle before the improvement, and X is the coordinate of the box particle in the original Cartesian system. length ,Y length Z length Given the side lengths of the box particle in each dimension, the improved box particle information R,θ, Let R be the coordinates of the box particle in the relative polar coordinate system. length ,θ length , Let X be the side lengths of the box particle in each dimension, and the improved state space boundary [X]. min ,X max ;Y min ,Y max Z min Z max [ ] represents the minimum and maximum values ​​of each dimension in the Cartesian coordinate system, and the improved state space boundary. These are the minimum and maximum values ​​of distance, azimuth, and elevation angles, respectively, in the relative polar coordinate system.

[0014] A second aspect of the present invention provides a single UAV target tracking system based on an improved box particle filter algorithm, comprising:

[0015] The acquisition module is used to acquire measurement data transmitted back by the non-visual sensors of the drone;

[0016] An improved module is used to establish a relative polar coordinate system between the UAV and the target with the UAV as the origin. Based on non-visual measurement data, the box particle information and state space boundary of the box particle filter algorithm are modified so that the modified box particle interval and measurement interval are both part of a spherical shell.

[0017] The shrinking module is used to determine whether all or part of the eight vertices of each box particle interval are within the measurement interval during the box particle shrinking process of the box particle filter algorithm update. The vertex coordinates within the measurement interval and the boundary of the measurement interval are used to form a new spherical shell to obtain the shrunken box particle.

[0018] The tracking module calculates the volume of each box particle after shrinkage as the weight of the box particle, normalizes it, and performs state estimation. After reaching the required number of tracking steps, it obtains the non-visual target tracking result of the UAV.

[0019] Optionally, in one embodiment of the present invention, the measurement data returned by the non-visual sensor includes: distance, azimuth angle, and pitch angle.

[0020] Optionally, in one embodiment of the present invention, modifying the box particle information and state space boundary of the box particle filtering algorithm based on non-visual measurement data includes:

[0021] Box particle information is composed of [X,Y,Z,X length ,Y length Z length Improved to The state space boundary is defined by [X] min ,X max ;Y min ,Y max Z min Z max Improved to Where X, Y, Z are the Cartesian coordinates of the box particle before the improvement, and X is the coordinate of the box particle in the original Cartesian system. length ,Y length Z length Given the side lengths of the box particle in each dimension, the improved box particle information R,θ, Let R be the coordinates of the box particle in the relative polar coordinate system. length ,θ length , Let X be the side lengths of the box particle in each dimension, and the improved state space boundary [X]. min ,X max ;Y min ,Y max Z min Z maxare the minimum and maximum values of each dimension in the Cartesian coordinate system, respectively, and the improved state space boundary are the minimum and maximum values of the distance, azimuth angle and pitch angle in the relative polar coordinate system, respectively.

[0022] The third aspect of the present application provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to perform the single UAV target tracking method based on the improved box particle filtering algorithm as described in the above embodiments.

[0023] The fourth aspect of the present application provides a computer readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to perform the single UAV target tracking method based on the improved box particle filtering algorithm as described in the above embodiments.

[0024] The single UAV target tracking method and system based on the improved box particle filtering algorithm of the embodiments of the present application improve the box particle filtering algorithm in the state space boundary and the box particle initialization process, and the improved each box particle interval and measurement interval are part of the "spherical shell" of the spherical surface, so that in the updating process, the box particle contraction only needs to judge whether all or part of the eight vertexes of each box particle interval are in the measurement interval, and then the vertex coordinates in the measurement interval and the boundary of the measurement interval form a new "spherical shell", so as to obtain the contracted box particle. Since the obtained contracted box particle is also a spherical shell, the volume of each contracted box particle can be directly calculated as its weight by using mathematical method, and after normalization, the state estimation can be directly performed, thereby omitting the process of calculating the likelihood function and using the likelihood function to calculate the weight of each box particle, simplifying the algorithm process, and at the same time, since the improved contraction step only exists interval addition and subtraction, the precision loss existing in the interval contraction algorithm can be avoided. Therefore, the improved box particle filtering algorithm has low time complexity, high real-time performance, and can realize more accurate and robust target tracking.

[0025] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0026] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, taken in conjunction with the accompanying drawings, in which:

[0027] Figure 1 FIG. 1 is a flowchart of a single UAV target tracking method based on an improved box particle filtering algorithm according to an embodiment of the present application;

[0028] Figure 2A schematic diagram of the state space and box particles before improvement of an embodiment of the present application;

[0029] Figure 3 A schematic diagram of the state space and box particles after improvement of an embodiment of the present application;

[0030] Figure 4 A schematic diagram of the measurement interval space of an embodiment of the present application;

[0031] Figure 5 A flowchart of a classical box particle filter algorithm;

[0032] Figure 6 A flowchart of an improved box particle filter algorithm of an embodiment of the present application;

[0033] Figure 7 An example diagram of a single unmanned aerial vehicle target tracking system based on an improved box particle filter algorithm according to an embodiment of the present application;

[0034] Figure 8 A structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0035] Embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by reference to the accompanying drawings are exemplary and are intended to explain the present application, and cannot be understood as a limitation of the present application.

[0036] In the field of unmanned aerial vehicle target tracking, traditional visual tracking methods rely on image information captured by a camera, but in complex environments, such as low illumination, bad weather, or target occlusion, visual information can be unreliable or unavailable. Therefore, non-visual sensors, such as electromagnetic wave sensors, laser sensors, and IMU sensors, are valued for their robustness in complex environments. These sensors can provide information such as the distance, azimuth angle, and pitch angle of the target, providing a new solution for unmanned aerial vehicle target tracking.

[0037] Box Particle Filter (BPF) uses box particles instead of traditional point particles, each of which represents a cuboid interval in the state space, thereby reducing the number of particles required and reducing the computational complexity. However, in the actual application of unmanned aerial vehicle target tracking, the non-visual sensor on the unmanned aerial vehicle often returns the distance, azimuth and elevation angle information of the target at each time. Due to the existence of measurement noise, these information are often an interval rather than a specific value, so a "ball shell" part of the measurement interval of the sphere is formed, and the box particle interval is a cuboid. Therefore, in the updating and shrinking process, interval shrinking methods such as Gaussian elimination and constraint propagation are generally used to obtain the intersection part of the box particle and the measurement interval. Among them, Gaussian elimination has the problem of low accuracy, and constraint propagation will cause dimension disaster and affect the real-time performance of the code.

[0038] Therefore, in the shrinking process of the classical box particle filter, the mathematical logic is complex, the code complexity is high, and the real-time performance of the algorithm is relatively poor.

[0039] The present application provides an improved box particle filter algorithm for unmanned aerial vehicle non-visual target tracking, which is used to process the distance, azimuth, elevation angle and other measurement data returned by the non-visual sensor on the unmanned aerial vehicle, so as to realize more accurate and robust target tracking. In theory, there is no precision loss in the shrinking process and the real-time performance is greatly improved.

[0040] Specifically, Figure 1 A flowchart of a single unmanned aerial vehicle target tracking method based on an improved box particle filter algorithm according to an embodiment of the present application is provided.

[0041] As Figure 1 shown, the single unmanned aerial vehicle target tracking method based on the improved box particle filter algorithm includes the following steps:

[0042] In step S101, the measurement data returned by the non-visual sensor of the unmanned aerial vehicle is obtained.

[0043] In the embodiment of the present application, the measurement data returned by the non-visual sensor includes distance, azimuth and elevation angle.

[0044] In step S102, a relative polar coordinate system of the unmanned aerial vehicle-target is established with the unmanned aerial vehicle as the origin, and the box particle information and state space boundary of the box particle filter algorithm are modified according to the non-visual measurement data, so that the modified box particle interval and the measurement interval are both part of the ball shell of the sphere.

[0045] In the present application, the state space boundary and the box particle initialization process will be improved. A relative polar coordinate system of the unmanned aerial vehicle-target is established with the unmanned aerial vehicle as the origin, and the box particle information is obtained by [X, Y, Z, Xlength Y length Z length ] is improved to The state space boundary is improved from [X min X max ; Y min Y max ; Z min Z max ] to wherein X, Y, Z of the box particle information before improvement are the Cartesian coordinates of the box particle, X length Y length Z length are the edge lengths of each dimension of the box particle, and R, θ, are the coordinates of the box particle in the relative polar coordinate system, R length θ length , are the edge lengths of each dimension of the box particle, and the state space boundary [X min X max ; Y min Y max ; Z min Z max ] before improvement are the minimum and maximum values of each dimension in the Cartesian coordinate system, and the state space boundary are the minimum and maximum values of the distance, azimuth angle and pitch angle in the relative polar coordinate system. The schematic diagrams of the box particles and the measurement interval in the state space before and after improvement are shown in Figure 2 and Figure 3 .

[0046] In step S103, in the updating process of the box particle filtering algorithm, when the box particle is contracted, it is judged whether all or part of the eight vertices of each box particle interval are in the measurement interval, a new spherical shell is formed by the vertex coordinates in the measurement interval and the boundary of the measurement interval, and the contracted box particle is obtained.

[0047] In step S104, the volume of each contracted box particle is calculated as the weight of the box particle, and after normalization, the state estimation is performed, and after the tracking step is reached, the unmanned aerial vehicle non-vision target tracking result is obtained.

[0048] As Figure 4As shown, the improved each box particle interval and the measurement interval are all part of a spherical shell, so in the updating process, when the box particle shrinks, only need to determine whether each box particle interval eight vertexes are all or part in the measurement interval, then the vertex coordinates in the measurement interval and the boundary of the measurement interval form a new spherical shell, so as to obtain the shrinked box particle. Since the obtained shrinked box particle is also a spherical shell, the volume of each shrinked box particle can be directly calculated as its weight by using mathematical method, and after normalization, the state estimation can be directly performed, the process of calculating the likelihood function and using the likelihood function to calculate the weight of each box particle is omitted, the algorithm process is simplified, and meanwhile, since the improved shrink step only exists interval addition and subtraction, the precision loss existing in the interval shrink algorithm can be avoided. However, in the improved algorithm, after the state transition, the box particle will be slightly deformed, which leads to the inconsistent volume of the front and rear box particles. However, since the volume of the box particle and the volume difference caused by the deformation are very different, the newly generated error is small enough to be negligible compared with the error of the interval analysis algorithm.

[0049] The classical box particle filtering algorithm and the algorithm flow of the present application are as shown in Figure 5 and Figure 6 . In the classical box particle filtering algorithm, the prediction step is a one-time iteration process, and the shrink step is also a one-time iteration process, so the time complexity of the whole algorithm is o (n 3 ). In the improved box particle filtering algorithm, only the prediction step is a one-time iteration process in the whole process, so the time complexity of the improved algorithm is o (n 2 ), which is improved by one order of magnitude compared with the former.

[0050] Compared with the extended Kalman filter, the present application has lower requirements for initial conditions on the basis of ensuring real-time, and has no linearization error because of no linearization process of the nonlinear system, so the tracking accuracy is higher.

[0051] Compared with the unscented Kalman filter, the present application is less sensitive to noise, and has low requirements for user experience because of no need to introduce self-set sigma points.

[0052] Compared with the classical box particle filter, the present application has lower time complexity and higher real-time.

[0053] According to the single unmanned aerial vehicle target tracking method based on the improved box particle filtering algorithm provided by the embodiments of the present application, the mathematical logic is complex and the code complexity is high in the shrink process of the classical box particle filter, which leads to relatively poor real-time of the algorithm. The improved box particle filtering algorithm is provided, and the time complexity of the algorithm is reduced from o (n 3 ) to o (n2 This significantly improves the real-time performance of the algorithm.

[0054] Next, referring to the accompanying drawings, a single UAV target tracking method system based on an improved box particle filter algorithm according to an embodiment of the present invention is described.

[0055] Figure 7 This is an example diagram of a single UAV target tracking method system based on an improved box particle filter algorithm according to an embodiment of the present invention.

[0056] like Figure 7 As shown, the single UAV target tracking method system 10 based on the improved box particle filter algorithm includes: an acquisition module 100, an improvement module 200, a shrinking module 300, and a tracking module 400.

[0057] The algorithm comprises several modules: Acquisition module 100, which acquires measurement data transmitted from the UAV's non-visual sensors; Improvement module 200, which establishes a relative polar coordinate system between the UAV and the target, using the UAV as the origin, and modifies the box particle information and state space boundaries of the box particle filter algorithm based on the non-visual measurement data, ensuring that both the modified box particle intervals and the measurement interval are part of a spherical shell; Contraction module 300, which, during the update process of the box particle filter algorithm, determines whether all or part of the eight vertices of each box particle interval are within the measurement interval during contraction, and forms a new spherical shell by combining the vertex coordinates within the measurement interval with the boundary of the measurement interval, thus obtaining the contracted box particles; and Tracking module 400, which calculates the volume of each contracted box particle as its weight, normalizes it, performs state estimation, and obtains the UAV non-visual target tracking result after reaching a certain number of tracking steps.

[0058] Optionally, in one embodiment of the present invention, the measurement data returned by the non-visual sensor includes: distance, azimuth angle, and pitch angle.

[0059] Optionally, in one embodiment of the present invention, modifying the box particle information and state space boundary of the box particle filtering algorithm based on non-visual measurement data includes:

[0060] Box particle information is composed of [X,Y,Z,X length ,Y length Z length Improved to The state space boundary is defined by [X] min ,X max ;Y min ,Y max Z min Z max Improved to Where X, Y, Z are the Cartesian coordinates of the box particle before the improvement, and X is the coordinate of the box particle in the original Cartesian system.length Y length Z length R, θ, φ are the edge length of the box particle in each dimension, the improved box particle information R, θ, φ are the coordinates of the box particle in the relative polar coordinate system, R length , θ length , R, θ, φ are the edge length of the box particle in each dimension, the improved state space boundary min X max ; Y min Y max ; Z min Z max X, Y, Z are the minimum and maximum values of each dimension in the Cartesian coordinate system, and the improved state space boundary X, Y, Z are the minimum and maximum values of the distance, azimuth angle and pitch angle in the relative polar coordinate system.

[0061] It should be noted that the foregoing description of the single unmanned aerial vehicle target tracking method based on the improved box particle filtering algorithm embodiment is also applicable to the single unmanned aerial vehicle target tracking system based on the improved box particle filtering algorithm of this embodiment, which will not be repeated here.

[0062] Figure 8 The electronic device provided by the application embodiment is shown in the structural schematic diagram. The electronic device can include:

[0063] The memory 801, the processor 802 and the computer program stored in the memory 801 and executable on the processor 802.

[0064] The processor 802 implements the single unmanned aerial vehicle target tracking method based on the improved box particle filtering algorithm provided in the above embodiments when executing the program.

[0065] Further, the electronic device further includes:

[0066] The communication interface 803 is used for communication between the memory 801 and the processor 802.

[0067] The memory 801 is used to store the computer program executable on the processor 802.

[0068] The memory 801 can include a high-speed RAM memory, and can also include a non-volatile memory, such as at least one disk memory.

[0069] If the memory 801, the processor 802 and the communication interface 803 are implemented independently, the communication interface 803, the memory 801 and the processor 802 can be connected with each other through a bus and complete communication between each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 8 Only one thick line is used to represent the bus in the figure, but it does not mean that there is only one bus or only one type of bus.

[0070] Optionally, in a specific implementation, if the memory 801, the processor 802 and the communication interface 803 are integrated on a chip, the memory 801, the processor 802 and the communication interface 803 can complete communication between each other through an internal interface.

[0071] The processor 802 can be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present application.

[0072] The embodiment also provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the single unmanned aerial vehicle target tracking method based on the improved box particle filtering algorithm.

[0073] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples without contradiction.

[0074] Furthermore, the terms "first", "second", etc. are used herein only to describe different steps or features and do not imply a relative importance or a specific order of steps or features. Thus, features defined with "first", "second" etc. can include one or more of the features implicitly or explicitly. In the description of the application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise expressly specified.

[0075] Any process or method descriptions or blocks in flow charts described herein and elsewhere can be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps in the process. Alternate implementations are included within the scope of the preferred embodiments of the present application in which the functions performed by the various processes described herein and elsewhere are allocated differently among the components of the preferred embodiments, such as according to the functions performed by the various components, in a substantially simultaneous manner, or according to a different order.

[0076] It should be understood that aspects of the present application can be implemented in hardware, software, firmware or combinations thereof. In the above embodiments, the various steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As such, if implemented in hardware and in another embodiment, the hardware can include any or a combination of the following technologies, which are all well known in the art: a discrete logic circuit having logic gates for implementing logic functions upon an application of data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0077] Those of skill in the art would understand that information and signals can be represented using any of a variety of technologies and techniques. Further, those of skill in the art would understand that the preferred embodiments of the present application can be implemented by a variety of means, including as an apparatus, a machine, a computer, or a software program. Furthermore, unless specifically stated otherwise, as apparent from the preceding discussion, it is appreciated that, throughout this specification discussions utilizing terms such as "processing," "computing," "calculating," "determining," "displaying," "generating," "identifying," "associating," "selecting," "compiling," "receiving," "outputting," "accessing," "instructing," "generating," "estimating," "predicting," "providing," "determining," or the like, refer to actions and processes of a computer system or similar electronic computing device.

Claims

1. A single unmanned aerial vehicle target tracking method based on an improved box particle filtering algorithm, characterized in that, The method comprises the following steps: acquiring measurement data returned by a non-vision sensor of the UAV; establishing a relative polar coordinate system of the UAV-target with the UAV as the origin, and modifying box particle information and state space boundaries of the box particle filter algorithm according to the non-vision measurement data, so that the modified box particle interval and the measurement interval are both part of a spherical shell of a sphere; in the updating process of the box particle filter algorithm, judging whether all or part of eight vertexes of each box particle interval are in the measurement interval when the box particle is contracted, forming a new spherical shell with the vertex coordinates in the measurement interval and the boundaries of the measurement interval, and obtaining the contracted box particle; calculating the volume of each contracted box particle as the weight of the box particle, performing state estimation after normalization, and obtaining the UAV non-vision target tracking result after reaching the tracking step number; the modifying of the box particle information and the state space boundaries of the box particle filter algorithm according to the non-vision measurement data comprises: The box particle information is improved from X , Y , Z , X length , Y length , Z length ] to , and the state space boundary is improved from X min , X max ; Y min , Y max ; Z min , Z max ] to , wherein X , Y , Z of the box particle information before improvement are Cartesian coordinates of the box particle, X length , Y length , Z length are the edge lengths of the box particle in each dimension, and the box particle information after improvement is , which are the coordinates of the box particle in the relative polar coordinate system, are the edge lengths of the box particle in each dimension, the state space boundary before improvement is X min , X max ; Y min , Y max ; Z min , Z max , which are the minimum and maximum values of each dimension in the Cartesian coordinate system, and the state space boundary after improvement is , which are the minimum and maximum values of the distance, azimuth angle and elevation angle in the relative polar coordinate system.

2. The method of claim 1, wherein, the measurement data returned by the non-vision sensor comprises: distance, azimuth angle and pitch angle.

3. A single unmanned aerial vehicle target tracking system based on an improved box particle filter algorithm, characterized in that, The method comprises: an acquisition module, configured to acquire measurement data returned by a non-vision sensor of the UAV; an improvement module, configured to establish a relative polar coordinate system of the UAV-target with the UAV as the origin, and modify box particle information and state space boundaries of the box particle filter algorithm according to the non-vision measurement data, so that the modified box particle interval and the measurement interval are both part of a spherical shell of a sphere; the modifying of the box particle information and the state space boundaries of the box particle filter algorithm according to the non-vision measurement data comprises: The box particle information is improved from X , Y , Z , X length , Y length , Z length ] to , and the state space boundary is improved from X min , X max ; Y min , Y max ; Z min , Z max ] to , wherein the X , Y , Z of the box particle information before improvement are Cartesian coordinates of the box particle, X length , Y length , Z length are the edge lengths of the box particle in each dimension, the box particle information after improvement is , which is the coordinate of the box particle in the relative polar coordinate system, are the edge lengths of the box particle in each dimension, the state space boundary before improvement is X min , X max ; Y min , Y max ; Z min , Z max , which are the minimum and maximum values of each dimension in the Cartesian coordinate system, and the state space boundary after improvement is , which are the minimum and maximum values of the distance, azimuth angle and pitch angle in the relative polar coordinate system. a contraction module, configured to, in the updating process of the box particle filter algorithm, judge whether all or part of eight vertexes of each box particle interval are in the measurement interval when the box particle is contracted, form a new spherical shell with the vertex coordinates in the measurement interval and the boundaries of the measurement interval, and obtain the contracted box particle; a tracking module, configured to calculate the volume of each contracted box particle as the weight of the box particle, perform state estimation after normalization, and obtain the UAV non-vision target tracking result after reaching the tracking step number.

4. The system of claim 3, wherein, the measurement data returned by the non-vision sensor comprises: distance, azimuth angle and pitch angle.

5. An electronic device, comprising: The method comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the single-UAV target tracking method based on the improved box particle filter algorithm according to any one of claims 1-2.

6. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the single-UAV target tracking method based on the improved box particle filter algorithm according to any one of claims 1-2.

Images