UAV-to-ground target matching method, device and equipment based on spatiotemporal cues

Abstract

The present application relates to a method, device and equipment for matching ground targets of unmanned aerial vehicles based on spatiotemporal clues in the field of target matching technology. The method includes constructing a motion model of target A according to the actual trajectory of target A from time t0 to time t1, and estimating the predicted position of target A at time t2; calculating the predicted average speed, the actual average speed and the target motion azimuth deviation according to the actual position of target A at time t1 and the predicted position at time t2, and the actual position of target B at time t2, and constructing the actual average speed correlation function and the target motion azimuth deviation correlation function; determining the spatiotemporal similarity of targets A and B according to the actual average speed correlation function and the target motion azimuth deviation correlation function; when the spatiotemporal similarity is greater than a preset threshold, target A matches target B. The method uses the average speed and azimuth changes of the target to directly calculate the spatiotemporal similarity of the target at different times, thereby completing the target matching, and the method is simple and effective.

Description

Technical Field

[0001] The present application relates to the field of target matching technology, and in particular to a method, device and equipment for matching unmanned aerial vehicle (UAV) ground targets based on spatiotemporal cues. Background Art

[0002] Unmanned Aerial Vehicle (UAV) is highly favored in the military field due to its unique advantages such as zero risk of casualties, rapid response, flexible deployment, and relatively low cost. The coordinated relay tracking of multiple UAVs is to adapt to the new reconnaissance and attack mode of future intelligent warfare. The combat capability of a single UAV is limited and cannot meet the task requirements of monitoring multiple targets at the same time. When a UAV finds that there are multiple targets in the target group, other UAVs must relay tracking. In addition, the endurance of a single UAV is limited. Insufficient power, sudden failure or being shot down by the enemy during the execution of the mission will result in mission failure. At this time, other UAVs must perform relay tracking tasks.

[0003] In order to achieve multi-UAV coordinated relay tracking, the first problem to be solved is how to confirm whether the targets found by different observation platforms are the same, that is, the target matching problem. From the publicly published literature, most of the literature realizes target matching based on target images. These literatures regard the target matching problem as a similarity solving problem between two images. They only use the target image and ignore the motion information contained in the target itself. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device and equipment for UAV-to-ground target matching based on spatiotemporal cues to address the above technical issues. This method predicts the average speed correlation and azimuth deviation correlation of the target through the time and space information of the target, thereby calculating the spatiotemporal similarity of the target and achieving target matching.

[0005] A method for matching unmanned aerial vehicle (UAV) ground targets based on spatiotemporal cues, the method comprising:

[0006] The actual trajectory of target A observed by the first UAV from time t0 to time t1 and the actual position of target B observed by the second UAV at time t2 are obtained.

[0007] According to the actual trajectory of target A from time t0 to time t1, the motion model of target A is constructed.

[0008] The predicted position of target A at time t2 is predicted based on the motion model of target A.

[0009] According to the actual position of target A at time t1 and the predicted position at time t2, as well as the actual position of target B at time t2, the predicted average speed, the actual average speed and the target motion azimuth deviation are obtained; the predicted average speed is the average speed of target A from the actual position at time t1 to the predicted position at time t2; the actual average speed is the average speed from the actual position of target A at time t1 to the actual position of target B at time t2; the target motion azimuth deviation is the difference between the horizontal azimuth angle of target A between time t1 and time t2 and the horizontal azimuth angle from target A to target B.

[0010] According to the predicted average speed and the actual average speed, an actual average speed correlation function is obtained.

[0011] According to the target motion azimuth deviation, a target motion azimuth deviation correlation function is obtained.

[0012] The temporal and spatial similarity between target A and target B is determined according to the actual average speed correlation function and the target motion azimuth deviation correlation function.

[0013] When the spatiotemporal similarity is greater than a preset threshold, target A matches target B.

[0014] In one embodiment, the predicted average speed, the actual average speed, and the target motion azimuth deviation are obtained according to the actual position of target A at time t1 and the predicted position at time t2, as well as the actual position of target B at time t2, including:

[0015] According to the distance calculation formula between two points in space, the predicted distance between the actual position of target A at time t1 and the predicted position at time t2, as well as the actual distance between the actual position of target A at time t1 and the actual position of target B at time t2 are calculated.

[0016] The predicted average speed is obtained according to the predicted distance and the time interval between time t1 and time t2.

[0017] The actual average speed is obtained according to the actual distance and the time interval between time t1 and time t2.

[0018] According to the relationship between the slope of the line connecting the two points and the angle between the line and the horizontal axis, the predicted horizontal azimuth from the actual position of target A at time t1 to the predicted position at time t2, as well as the actual horizontal azimuths of the actual position of target A at time t1 and the actual position of target B at time t2 are calculated.

[0019] A target motion azimuth deviation is obtained according to the predicted horizontal azimuth angle and the actual horizontal azimuth angle.

[0020] In one embodiment, according to the predicted average speed and the actual average speed, an actual average speed correlation function is obtained, and the expression of the actual average speed correlation function in the step is:

[0021]

[0022] in is the actual average speed, μ1 is the predicted average speed, σ1 is the given variance, v lim is the known maximum moving speed of the target, and T=t2-t1 is the time interval.

[0023] In one embodiment, a target motion azimuth deviation correlation function is obtained according to the target motion azimuth deviation, and the expression of the target motion azimuth deviation correlation function in the step is:

[0024]

[0025] In one embodiment, determining the spatiotemporal similarity between target A and target B according to the actual average speed correlation function and the target motion azimuth deviation correlation function includes:

[0026] The actual average speed correlation function is multiplied by the target motion azimuth deviation correlation function to obtain the spatiotemporal similarity between target A and target B.

[0027] In one embodiment, a motion model of target A is constructed according to the actual trajectory of target A from time t0 to time t1. The motion model of target A in the step is:

[0028] X(k+T)=φ(k+T,k)X(k)

[0029] Among them, X(k+T) is the position of target A at the next moment, X(k) is the position of target A at the current moment, φ(k+T,k) is the state transfer matrix from the current moment k to the moment k+T, k is the current moment, and T is the time interval from the current moment to the next moment.

[0030] A UAV-to-ground target matching device based on spatiotemporal cues, the device comprising:

[0031] The target actual motion trajectory acquisition module is used to obtain the actual trajectory of target A observed by the first UAV from time t0 to time t1, and the actual position of target B observed by the second UAV at time t2.

[0032] The target A position prediction module at time t2 is used to construct a motion model of target A according to the actual trajectory of target A from time t0 to time t1; and predict the predicted position of target A at time t2 according to the motion model of target A.

[0033] The module for determining the correlation between average speed and azimuth deviation is used to obtain the predicted average speed, the actual average speed and the target motion azimuth deviation according to the actual position of target A at time t1 and the predicted position at time t2, as well as the actual position of target B at time t2; to obtain the actual average speed correlation function according to the predicted average speed and the actual average speed; to obtain the target motion azimuth deviation correlation function according to the target motion azimuth deviation; the predicted average speed is the average speed of target A from the actual position at time t1 to the predicted position at time t2; the actual average speed is the average speed from the actual position of target A at time t1 to the actual position of target B at time t2; the target motion azimuth deviation is the difference between the horizontal azimuth angle of target A between time t1 and time t2 and the horizontal azimuth angle from target A to target B.

[0034] The target matching module is used to determine the spatiotemporal similarity between target A and target B according to the actual average speed correlation function and the target motion azimuth deviation correlation function; when the spatiotemporal similarity is greater than a preset threshold, target A matches target B.

[0035] In one of the embodiments, the average speed correlation and azimuth deviation correlation determination module is also used to calculate the predicted distance between the actual position of target A at time t1 and the predicted position at time t2, and the actual distance between the actual position of target A at time t1 and the actual position of target B at time t2 according to the distance calculation formula between two points in space; obtain the predicted average speed according to the predicted distance and the time interval between time t1 and time t2; obtain the actual average speed according to the actual distance and the time interval between time t1 and time t2; calculate the predicted horizontal azimuth from the actual position of target A at time t1 to the predicted position at time t2, and the actual horizontal azimuth of the actual position of target A at time t1 and the actual position of target B at time t2 according to the relationship between the slope of the line connecting the two points and the angle between the line and the horizontal axis; obtain the target motion azimuth deviation according to the predicted horizontal azimuth and the actual horizontal azimuth.

[0036] In one embodiment, the expression of the actual average speed correlation function in the average speed correlation and azimuth deviation correlation determination module is:

[0037]

[0038] in, is the actual average speed, μ1 is the predicted average speed, σ1 is the given variance, v lim is the known maximum moving speed of the target, and T=t2-t1 is the time interval.

[0039] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0040] The above-mentioned method, device and equipment for matching ground targets of unmanned aerial vehicles based on spatiotemporal clues include: constructing a motion model of target A according to the actual trajectory of target A observed by the first unmanned aerial vehicle from time t0 to time t1, and estimating the predicted position of target A at time t2; obtaining the predicted average speed, the actual average speed and the target motion azimuth deviation according to the actual position of target A at time t1 and the predicted position at time t2, and the actual position of target B observed by the second unmanned aerial vehicle at time t2; obtaining the actual average speed correlation function according to the predicted average speed and the actual average speed; obtaining the target motion azimuth deviation correlation function according to the target motion azimuth deviation; determining the spatiotemporal similarity between target A and target B according to the actual average speed correlation function and the target motion azimuth deviation correlation function; when the spatiotemporal similarity is greater than a preset threshold, target A matches target B. This method uses the average speed and azimuth changes of the target to directly calculate the spatiotemporal similarity of the target at different times, thereby completing the target matching, and the method is simple and effective. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is an application scenario diagram of a UAV-to-ground target matching method based on spatiotemporal cues in one embodiment;

[0042] Figure 2 The figure is a flow chart of a method for matching ground targets of unmanned aerial vehicles based on spatiotemporal cues in one embodiment;

[0043] Figure 3 A schematic diagram of target movement in one embodiment;

[0044] Figure 4 1 is a curve of an actual average speed correlation function and a target motion azimuth deviation correlation function in another embodiment, wherein (a) is a curve of an actual average speed correlation function, and (b) is a curve of a target motion azimuth deviation correlation function;

[0045] Figure 5 It is a structural block diagram of a UAV-to-ground target matching device based on spatiotemporal cues in one embodiment;

[0046] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0048] The UAV-to-ground target matching method based on spatiotemporal cues provided in this application can be applied to Figure 1 In the application environment shown, the first drone 102 and the second drone 104 observe the same ground target, and communicate the observed data with the server 106 through the network. The server 106 can be implemented by an independent server or a server cluster composed of multiple servers.

[0049] In one embodiment, Figure 2 As shown in the figure, a method for matching UAV to ground target based on spatiotemporal clues is provided. Figure 1 The server in the example is used to illustrate the following steps:

[0050] A method for matching unmanned aerial vehicle (UAV) ground targets based on spatiotemporal cues, the method comprising:

[0051] Step 200: Obtain the actual trajectory of target A observed by the first UAV from time t0 to time t1, and the actual position of target B observed by the second UAV at time t2.

[0052] Specifically, the target motion diagram is as follows: Figure 3 As shown, about Figure 3 Description: The actual trajectory of the target is A(t0)→A(t1)→B(t2), and the predicted trajectory of the target is Where A(t0)→A(t1) is the actual trajectory of target A observed by the first UAV from time t0 (initial time) to time t1, and B(t2) is the actual position of target B at time t2 observed by the second UAV. is the predicted position of target A at time t2.

[0053] Target A and Target B are observation results obtained by the first UAV and the second UAV observing the same ground target. The core task of this method is to determine whether Target A and Target B are the same target based on processing the observation data.

[0054] Step 202: construct a motion model of target A according to the actual trajectory of target A from time t0 to time t1.

[0055] Step 1: Get the target position. Given the actual trajectory of target A from t0 to t1, take three points p0, p1, and p2 in the actual trajectory, and its trajectory is p0[x p0 ,yp0 ]→p1[x p1 ,y p1 ]→p2[x p2 ,y p2 ].

[0056] Step 2: Calculate the relative distance between two adjacent points.

[0057]

[0058] Step 3: Calculate the relative orientation of two adjacent points.

[0059]

[0060] Step 4: According to the transformation of relative distance and relative orientation, establish the corresponding motion model.

[0061] If |Δp2-Δp1|≤δ P ,|α2-α1|≤δ α , then it is a uniform linear motion model. P is a given relative distance threshold, and its value is close to 0. α is a given relative orientation threshold, and its value is close to 0.

[0062] If |Δp2-Δp1|≥δ P ,|α2-α1|≤δ α , then it is a variable speed linear motion model.

[0063] If |α2-α1|>δ α , then it is a turning motion model.

[0064] Step 204: predicting the predicted position of target A at time t2 according to the motion model of target A;

[0065] Specifically, the target predicted position after time T is calculated based on the target motion model

[0066] Step 206: Based on the actual position of target A at time t1 and the predicted position at time t2, as well as the actual position of target B at time t2, the predicted average speed, the actual average speed and the target motion azimuth deviation are obtained.

[0067] The predicted average speed is the average speed of target A from its actual position at time t1 to its predicted position at time t2.

[0068] The actual average speed is the average speed from the actual position of target A at time t1 to the actual position of target B at time t2.

[0069] The target motion azimuth deviation is the difference between the horizontal azimuth of target A and the horizontal azimuth from target A to target B between time t1 and t2.

[0070] Step 208: Obtain a function related to the actual average speed according to the predicted average speed and the actual average speed.

[0071] The actual average speed correlation function is used to estimate the spatiotemporal correlation between target A and target B according to the relationship between the value of the actual average speed and the value of the expected average speed.

[0072] Step 210: Obtain a target motion direction deviation correlation function according to the target motion direction deviation.

[0073] The target motion azimuth deviation correlation function is used to estimate the spatiotemporal correlation between target A and target B based on the relationship between the value of the target motion azimuth deviation and the expected azimuth deviation.

[0074] Step 212: Determine the spatiotemporal similarity between target A and target B based on the actual average speed correlation function and the target motion azimuth deviation correlation function; when the spatiotemporal similarity is greater than a preset threshold, target A and target B match.

[0075] Preferably, the preset threshold δ=0.5.

[0076] In the above-mentioned UAV-to-ground target matching method based on spatiotemporal clues, the method includes: constructing a motion model of target A according to the actual trajectory of target A observed by the first UAV from time t0 to time t1, and estimating the predicted position of target A at time t2; obtaining the predicted average speed, the actual average speed and the target motion azimuth deviation according to the actual position of target A at time t1 and the predicted position at time t2, and the actual position of target B observed by the second UAV at time t2; obtaining the actual average speed correlation function according to the predicted average speed and the actual average speed; obtaining the target motion azimuth deviation correlation function according to the target motion azimuth deviation; determining the spatiotemporal similarity between target A and target B according to the actual average speed correlation function and the target motion azimuth deviation correlation function; when the spatiotemporal similarity is greater than a preset threshold, target A matches target B. This method uses the average speed and azimuth changes of the target to directly calculate the spatiotemporal similarity of the target at different times, thereby completing the target matching, and the method is simple and effective.

[0077] In one embodiment, step 206 includes: calculating the predicted distance between the actual position of target A at time t1 and the predicted position at time t2, and the actual distance between the actual position of target A at time t1 and the actual position of target B at time t2 according to the distance calculation formula between two points in space; obtaining the predicted average speed according to the predicted distance and the time interval between time t1 and time t2; obtaining the actual average speed according to the actual distance and the time interval between time t1 and time t2; calculating the predicted horizontal azimuth from the actual position of target A at time t1 to the predicted position at time t2, and the actual horizontal azimuth of the actual position of target A at time t1 and the actual position of target B at time t2 according to the relationship between the slope of the line connecting the two points and the angle between the line and the horizontal axis; obtaining the target motion azimuth deviation according to the predicted horizontal azimuth and the actual horizontal azimuth.

[0078] Specifically, the actual distance between the actual position A(t1) of target A at time t1 and the actual position B(t2) of target B at time t2 is:

[0079]

[0080] Where dist(A(t1), B(t2)) is the distance between the actual position A(t1) of target A at time t1 and the actual position B(t2) of target B at time t2. b2 ,y b2 ) is the coordinate of the actual position B(t2) of target B at time t2, (x a1 ,y a1 ) is the coordinate of the actual position A(t1) of target A at time t1.

[0081] The actual average speed between the actual position A(t1) of target A at time t1 and the actual position B(t2) of target B at time t2 is

[0082]

[0083] Wherein, T is the time interval between time t1 and time t2.

[0084] The actual position A(t1) of target A at time t1 and the predicted position at time t2 The predicted distance between two points is:

[0085]

[0086] in, The actual position A(t1) of target A at time t1 and the predicted position of target A at time t2 The distance between two points, For actual location The coordinates of .

[0087] The actual position A(t1) of target A at time t1 and the predicted position at time t2 The predicted average speed μ1 between two points is:

[0088]

[0089] The relationship between the slope of the line connecting points A(t1) and B(t2) and the angle between the line and the horizontal axis is: the angle between the line connecting points A(t1) and B(t2) and the horizontal axis is equal to the inverse tangent of the slope of the line connecting points A(t1) and B(t2). Based on the coordinates of the actual position A(t1) of target A at time t1 to the actual position B(t2) of target B at time t2, the angle between the line connecting points A(t1) and B(t2) and the horizontal axis is calculated, which is the actual azimuth angle θ(t1, t2) from the actual position A(t1) of target A at time t1 to the actual position B(t2) of target B at time t2:

[0090]

[0091] A(t1) and The relationship between the slope of the line connecting two points and the angle between the line and the horizontal axis is: A(t1) and The angle between the line connecting the two points and the horizontal axis is equal to A(t1) and The inverse tangent of the slope of the line connecting the two points. Based on the actual position A(t1) of the target A at time t1 and the predicted position at time t2 The coordinates of target A are used to calculate the actual position A(t1) of target A at time t1 and the predicted position at time t2. The predicted horizontal azimuth for:

[0092]

[0093] The deviation of the target motion direction is:

[0094] In one embodiment, the expression of the actual average speed related function in step 208 is:

[0095]

[0096] in, is the actual average speed, μ1 is the predicted average speed, σ1 is the given variance, and the corresponding value is usually selected based on experience; v lim is the known maximum speed of the target; T = t2-t1 time interval; e is a mathematical constant, approximately equal to 2.718281828.

[0097] In one embodiment, the expression of the target motion azimuth deviation correlation function in step 210 is:

[0098]

[0099] Among them, σ1 is the given variance, and the corresponding value is usually selected based on experience; Δθ is the angle change; μ2 is the expected angle change, and μ2=0 is preferred; T=t2-t1 is the time interval; e is a mathematical constant, which is approximately equal to 2.718281828.

[0100] The curves of the actual average speed correlation function and the target motion azimuth deviation correlation function are as follows: Figure 4 Described, wherein (a) is the actual average speed related function curve, and (b) is the target motion azimuth deviation related function curve.

[0101] In one embodiment, step 212 includes: multiplying the actual average speed correlation function with the target motion azimuth deviation correlation function to obtain the spatiotemporal similarity between target A and target B.

[0102] Specifically, the spatiotemporal similarity R between target A discovered by the first UAV at time [t0, t1] and target B discovered by the second UAV at time t2 is 1,2 for:

[0103] In one embodiment, the motion model of target A in step 200 is:

[0104] X(k+T)=φ(k+T,k)X(k) (10)

[0105] Among them, X(k+T) is the position of target A at the next moment, X(k) is the position of target A at the current moment, φ(k+T,k) is the state transfer matrix from the current moment k to the moment k+T, k is the current moment, and T is the time interval from the current moment to the next moment.

[0106] It should be understood that although Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0107] In one embodiment, Figure 5 As shown, a UAV ground target matching device based on time-space clues is provided, including: a target actual motion trajectory acquisition module, a target A position prediction module at time t2, an average speed correlation and azimuth deviation correlation determination module and a target matching module, wherein:

[0108] The target actual motion trajectory acquisition module is used to obtain the actual trajectory of target A observed by the first drone from time t0 to time t1, and the actual position of target B observed by the second drone at time t2.

[0109] The target A position prediction module at time t2 is used to construct a motion model of target A according to the actual trajectory of target A from time t0 to time t1; and predict the predicted position of target A at time t2 according to the motion model of target A.

[0110] The module for determining the correlation between average speed and azimuth deviation is used to obtain the predicted average speed, the actual average speed and the target motion azimuth deviation according to the actual position of target A at time t1 and the predicted position at time t2, as well as the actual position of target B at time t2; to obtain the actual average speed correlation function according to the predicted average speed and the actual average speed; to obtain the target motion azimuth deviation correlation function according to the target motion azimuth deviation; the predicted average speed is the average speed of target A from the actual position at time t1 to the predicted position at time t2; the actual average speed is the average speed from the actual position of target A at time t1 to the actual position of target B at time t2; the target motion azimuth deviation is the difference between the horizontal azimuth angle of target A from time t1 to time t2 and the horizontal azimuth angle from target A to target B.

[0111] The target matching module is used to determine the spatiotemporal similarity between target A and target B based on the actual average speed correlation function and the target motion azimuth deviation correlation function; when the spatiotemporal similarity is greater than a preset threshold, target A and target B are matched.

[0112] In one of the embodiments, the average speed correlation and azimuth deviation correlation determination module is also used to calculate the predicted distance between the actual position of target A at time t1 and the predicted position at time t2, and the actual distance between the actual position of target A at time t1 and the actual position of target B at time t2 according to the distance calculation formula between two points in space; obtain the predicted average speed according to the predicted distance and the time interval between time t1 and time t2; obtain the actual average speed according to the actual distance and the time interval between time t1 and time t2; calculate the predicted horizontal azimuth from the actual position of target A at time t1 to the predicted position at time t2, and the actual horizontal azimuth of the actual position of target A at time t1 and the actual position of target B at time t2 according to the relationship between the slope of the line connecting the two points and the angle between the line and the horizontal axis; obtain the target motion azimuth deviation according to the predicted horizontal azimuth and the actual horizontal azimuth.

[0113] In one of the embodiments, the expression of the actual average speed correlation function in the average speed correlation and azimuth deviation correlation determination module is as shown in formula (8).

[0114] In one of the embodiments, the expression of the target motion azimuth deviation correlation function in the average speed correlation and azimuth deviation correlation determination module is as shown in formula (9).

[0115] In one of the embodiments, the target matching module is further used to multiply the actual average speed correlation function with the target motion azimuth deviation correlation function to obtain the spatiotemporal similarity between target A and target B.

[0116] In one embodiment, the motion model of target A in the target actual motion trajectory acquisition module is as shown in formula (10).

[0117] For the specific definition of the drone-to-ground target matching device based on spatiotemporal cues, please refer to the definition of the drone-to-ground target matching method based on spatiotemporal cues above, which will not be repeated here. Each module in the above-mentioned drone-to-ground target matching device based on spatiotemporal cues can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0118] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 6As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for matching unmanned aerial vehicle targets to the ground based on spatiotemporal clues is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0119] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0120] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the above method embodiment when executing the computer program.

[0121] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0122] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0123] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for matching UAV to ground targets based on spatiotemporal cues, characterized in that: The method comprises: Obtain the actual trajectory of target A from time t0 to time t1 observed by the first UAV, and the actual position of target B at time t2 observed by the second UAV; According to the actual trajectory of target A from time t0 to time t1, the motion model of target A is constructed; Predict the predicted position of target A at time t2 based on the motion model of target A; According to the actual position of target A at time t1 and the predicted position at time t2, as well as the actual position of target B at time t2, the predicted average speed, the actual average speed and the target motion azimuth deviation are obtained; the predicted average speed is the average speed of target A from the actual position at time t1 to the predicted position at time t2; the actual average speed is the average speed from the actual position of target A at time t1 to the actual position of target B at time t2; the target motion azimuth deviation is the difference between the horizontal azimuth angle of target A between time t1 and time t2 and the horizontal azimuth angle from target A to target B; Obtaining an actual average speed correlation function according to the predicted average speed and the actual average speed; According to the target motion azimuth deviation, a target motion azimuth deviation correlation function is obtained; Determining the spatiotemporal similarity between target A and target B according to the actual average speed correlation function and the target motion azimuth deviation correlation function; When the spatiotemporal similarity is greater than a preset threshold, target A matches target B.

2. The method according to claim 1, characterized in that According to the actual position of target A at time t1 and the predicted position at time t2, as well as the actual position of target B at time t2, the predicted average speed, the actual average speed and the target motion azimuth deviation are obtained, including: According to the distance calculation formula between two points in space, the predicted distance between the actual position of target A at time t1 and the predicted position at time t2, as well as the actual distance between the actual position of target A at time t1 and the actual position of target B at time t2 are calculated; Obtaining a predicted average speed according to the predicted distance and the time interval between time t1 and time t2; According to the actual distance and the time interval between time t1 and time t2, the actual average speed is obtained; Calculate the predicted horizontal azimuth from the actual position of target A at time t1 to the predicted position at time t2, and the actual horizontal azimuth of the actual position of target A at time t1 and the actual position of target B at time t2 according to the relationship between the slope of the line connecting the two points and the angle between the line and the horizontal axis; A target motion azimuth deviation is obtained according to the predicted horizontal azimuth angle and the actual horizontal azimuth angle.

3. The method according to claim 1, characterized in that According to the predicted average speed and the actual average speed, an actual average speed correlation function is obtained. The expression of the actual average speed correlation function in the step is: in, is the actual average speed, μ1 is the predicted average speed, σ1 is the given variance, v lim is the known maximum moving speed of the target, and T=t2-t1 is the time interval.

4. The method according to claim 1, characterized in that: According to the target motion azimuth deviation, a target motion azimuth deviation correlation function is obtained. The expression of the target motion azimuth deviation correlation function in the step is: Among them, σ1 is the given variance, Δθ is the angle change; μ2 is the expected angle change; T=t2-t1 is the time interval.

5. The method according to claim 1, characterized in that Determining the spatiotemporal similarity between target A and target B according to the actual average speed correlation function and the target motion azimuth deviation correlation function includes: The actual average speed correlation function is multiplied by the target motion azimuth deviation correlation function to obtain the spatiotemporal similarity between target A and target B.

6. The method according to claim 1, characterized in that According to the actual trajectory of target A from time t0 to time t1, a motion model of target A is constructed. The motion model of target A in the step is: X(k+T)=φ(k+T,k)X(k) Among them, X(k+T) is the position of target A at the next moment, X(k) is the position of target A at the current moment, φ(k+T,k) is the state transfer matrix from the current moment k to the moment k+T, k is the current moment, and T is the time interval from the current moment to the next moment.

7. A UAV-to-ground target matching device based on spatiotemporal cues, characterized in that: The device comprises: The target actual motion trajectory acquisition module is used to obtain the actual trajectory of target A from time t0 to time t1 observed by the first UAV, and the actual position of target B at time t2 observed by the second UAV; The target A position prediction module at time t2 is used to construct a motion model of target A according to the actual trajectory of target A from time t0 to time t1; and predict the predicted position of target A at time t2 according to the motion model of target A; The module for determining the correlation between average speed and azimuth deviation is used to obtain the predicted average speed, the actual average speed and the target motion azimuth deviation according to the actual position of target A at time t1 and the predicted position at time t2, and the actual position of target B at time t2; obtain the actual average speed correlation function according to the predicted average speed and the actual average speed; obtain the target motion azimuth deviation correlation function according to the target motion azimuth deviation; the predicted average speed is the average speed of target A from the actual position at time t1 to the predicted position at time t2; the actual average speed is the average speed from the actual position of target A at time t1 to the actual position of target B at time t2; the target motion azimuth deviation is the difference between the horizontal azimuth angle of target A from time t1 to time t2 and the horizontal azimuth angle from target A to target B; The target matching module is used to determine the spatiotemporal similarity between target A and target B according to the actual average speed correlation function and the target motion azimuth deviation correlation function; when the spatiotemporal similarity is greater than a preset threshold, target A matches target B.

8. The device according to claim 7, characterized in that The average speed correlation and azimuth deviation correlation determination module is also used to calculate the predicted distance between the actual position of target A at time t1 and the predicted position at time t2, and the actual distance between the actual position of target A at time t1 and the actual position of target B at time t2 according to the distance calculation formula between two points in space; obtain the predicted average speed according to the predicted distance and the time interval between time t1 and time t2; obtain the actual average speed according to the actual distance and the time interval between time t1 and time t2; calculate the predicted horizontal azimuth from the actual position of target A at time t1 to the predicted position at time t2, and the actual horizontal azimuth of the actual position of target A at time t1 and the actual position of target B at time t2 according to the relationship between the slope of the line connecting the two points and the angle between the line and the horizontal axis; obtain the target motion azimuth deviation according to the predicted horizontal azimuth and the actual horizontal azimuth.

9. The device according to claim 7, characterized in that The expression of the actual average speed correlation function in the average speed correlation and azimuth deviation correlation determination module is: in, is the actual average speed, μ1 is the predicted average speed, σ1 is the given variance, v lim is the known maximum moving speed of the target, and T=t2-t1 is the time interval.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

Images