Low-altitude target identification and tracking method and device

Abstract

The application provides a low-altitude target identification and tracking method and device, the method comprising: acquiring first image data of a target low-altitude area; determining a first low-altitude target and a first feature of the first low-altitude target according to the first image data; screening the first low-altitude target according to the first feature to obtain a second low-altitude target; acquiring second image data of the second low-altitude target; determining a second feature of the second low-altitude target according to the second image data; and screening the second low-altitude target according to the second feature to obtain a low-altitude target to be tracked. The low-altitude target identification and tracking method provided by the scheme greatly improves the identification and tracking accuracy and efficiency of the low-altitude target.

Description

Technical Field

[0001] This invention relates to the fields of radar technology and target recognition technology, and in particular to a method and apparatus for low-altitude target recognition and tracking. Background Technology

[0002] Real-time tracking and identification of low-altitude aircraft is of great significance for low-altitude defense, gaining battlefield initiative, accurately striking targets, and significantly improving the performance of future command and combat systems. Low-altitude small targets, such as small drones, birds, floating balloons, and plastic bags, pose varying degrees of threat to military and civilian airports and various military facilities. Accurate identification of aerial targets is crucial, making low-altitude target monitoring of paramount practical importance. However, current technologies are clearly insufficient in their accuracy when tracking generally small low-altitude targets, failing to meet practical needs. Summary of the Invention

[0003] This invention provides a method and apparatus for identifying and tracking low-altitude targets, which greatly improves the accuracy and efficiency of identifying and tracking low-altitude targets.

[0004] In a first aspect, embodiments of the present invention provide a low-altitude target identification and tracking method, comprising:

[0005] Acquire first image data of the target low-altitude region;

[0006] The first low-altitude target and the first feature of the first low-altitude target are determined based on the first image data;

[0007] Based on the first feature, the first low-altitude target is filtered to obtain the second low-altitude target;

[0008] Acquire the second image data of the second low-altitude target;

[0009] The second feature of the second low-altitude target is determined based on the second image data;

[0010] The second low-altitude target is filtered based on the second feature to obtain the low-altitude target to be tracked.

[0011] Optionally, the method further includes:

[0012] Based on the first feature, the time interval between acquiring the first image data and the second image data is determined.

[0013] Optionally, determining the time interval between acquiring the first image data and the second image data based on the first feature includes:

[0014] The first low-altitude target is counted based on the first feature to obtain a count value;

[0015] The interval duration is determined based on the count value.

[0016] Optionally, the interval duration is positively correlated with the count value.

[0017] Optionally, the step of filtering the first low-altitude target based on the first feature to obtain the second low-altitude target includes:

[0018] The first feature is matched with each of the first comparison features in the first feature library to obtain the first matching degree value;

[0019] Determine whether the first matching degree value is greater than the first threshold;

[0020] If so, then the first low-altitude target corresponding to the first matching degree value is removed;

[0021] If not, then the first low-altitude target corresponding to the first matching degree value shall be used as the second low-altitude target.

[0022] Optionally, the step of filtering the second low-altitude target based on the second feature to obtain the low-altitude target to be tracked includes:

[0023] The second feature is matched with each of the second alignment features in the second feature library to obtain the second matching degree value;

[0024] Determine whether the second matching degree value is greater than the second threshold;

[0025] If so, then the second low-altitude target corresponding to the second matching degree value shall be taken as the low-altitude target to be tracked;

[0026] If not, then the second low-altitude target corresponding to the second matching degree value is removed.

[0027] Optionally, before matching the second feature with each of the second comparison features in the second feature library, the method further includes:

[0028] The motion range of the second low-altitude target is determined based on the second feature;

[0029] Determine whether the range of motion is less than a third threshold;

[0030] If so, the second feature is matched with each of the second comparison features in the second feature library.

[0031] Secondly, embodiments of the present invention also provide a low-altitude target identification and tracking device, comprising: an acquisition module, a processing module, and a filtering module;

[0032] The acquisition module is used to acquire first image data of the target low-altitude area and second image data of the second low-altitude target determined by the processing module.

[0033] The processing module is configured to determine a first low-altitude target and a first feature of the first low-altitude target based on the first image data; and to determine a second feature of the second low-altitude target based on the second image data.

[0034] The filtering module is used to filter the first low-altitude target according to the first feature to obtain a second low-altitude target; and to filter the second low-altitude target according to the second feature to obtain a low-altitude target to be tracked.

[0035] Optionally, the device also includes a duration determination module;

[0036] The duration determination module is used to perform the following operations:

[0037] Based on the first feature, the time interval between acquiring the first image data and the second image data is determined.

[0038] Thirdly, embodiments of the present invention also provide a computing device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the low-altitude target identification and tracking method described in any of the above claims.

[0039] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the low-altitude target identification and tracking method described in any of the preceding claims.

[0040] This invention provides a method and apparatus for identifying and tracking low-altitude targets. The method uses a secondary screening process to accurately identify small low-altitude targets, which greatly improves the accuracy and efficiency of low-altitude target identification and tracking, and enhances tracking precision. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a flowchart of a low-altitude target identification and tracking method provided in an embodiment of the present invention;

[0043] Figure 2This is a hardware architecture diagram of a computing device provided in an embodiment of the present invention;

[0044] Figure 3 This is a structural diagram of a low-altitude target identification and tracking device provided in an embodiment of the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0046] The following is the concept of the present invention, such as Figure 1 As shown, this embodiment of the invention provides a low-altitude target identification and tracking method, the method comprising:

[0047] Step 100: Acquire the first image data of the target low-altitude area;

[0048] Step 102: Determine the first low-altitude target and the first feature of the first low-altitude target based on the first image data;

[0049] Step 104: Filter the first low-altitude target according to the first feature to obtain the second low-altitude target;

[0050] Step 106: Acquire the second image data of the second low-altitude target;

[0051] Step 108: Determine the second feature of the second low-altitude target based on the second image data;

[0052] Step 110: Filter the second low-altitude targets according to the second feature to obtain the low-altitude targets to be tracked.

[0053] It should be noted that the low-altitude target recognition and tracking method in this embodiment of the invention can be implemented based on an FPGA processing device. The FPGA processing device involved in this invention mainly includes an FPGA development board, which includes a core processor, such as the Xilinx ZYNQ 7020SOC. This chip combines the functions of a processor and a programmable device, making it suitable for hardware and software co-design. In specific implementation, developers write Verilog HDL programs to call the logic devices in the FPGA, building the digital circuit modules required by the algorithm. Each module can perform data processing and logical operations in parallel, thereby accelerating the algorithm and achieving real-time online target recognition and tracking.

[0054] In this embodiment of the invention, monitoring equipment, such as radar (microwave, infrared, laser, etc.) and cameras, is pre-deployed in the low-altitude area of ​​the target, pointing towards the target low-altitude area, and the monitoring angle can be adjusted according to monitoring needs. The first image data collected by the monitoring equipment is sent to an FPGA processing unit. The FPGA processing unit identifies the first image data to determine the initial first low-altitude target, and filters it based on the first characteristics of the first low-altitude target, removing obvious interfering targets to obtain several second low-altitude targets. Then, second image data related to the second low-altitude targets is acquired and processed to achieve further filtering of the second low-altitude targets, thereby obtaining low-altitude targets with high confidence for continuous tracking. The solution of this invention uses an FPGA to build the processing core and then accurately identifies low-altitude targets through secondary filtering, greatly improving the accuracy and efficiency of low-altitude target identification and tracking.

[0055] The low-altitude targets in this invention mainly involve various types of unmanned aerial vehicles (UAVs), such as fixed-wing UAVs, rotary-wing UAVs, unmanned airships, paragliding UAVs, flapping-wing UAVs, unmanned helicopters, multi-rotor UAVs, etc., without being specifically limited.

[0056] The following description Figure 1 The execution method of each step is shown.

[0057] After step 102, the method further includes: determining the time interval between acquiring the first image data and the second image data based on the first feature.

[0058] In this embodiment of the invention, the monitoring device first collects the first feature of the low-altitude target in the target low-altitude area, and determines how long after the first feature to collect the second image data. This not only ensures that no low-altitude targets are missed, but also avoids the problem of reduced real-time performance caused by high-frequency acquisition.

[0059] In this embodiment of the invention, the first feature and the second feature can both include static features and dynamic features of the low-altitude target. The static features include, but are not limited to, shape outline, color, texture, and lighting. The dynamic features include, but are not limited to, speed, motion angle / angle change sequence, and motion range.

[0060] Specifically, based on the first feature, determining the time interval between acquiring the first image data and the second image data includes:

[0061] The first low-altitude target is counted based on the first feature to obtain the count value;

[0062] The interval duration is determined based on the count value.

[0063] In a preferred embodiment, the interval duration is positively correlated with the count value.

[0064] In this embodiment of the invention, the first low-altitude target within the target low-altitude area may be flying solo, accompanied, or in groups, and the motion characteristics of the first low-altitude target differ significantly under different conditions. This invention determines the interval length based on these differences in motion characteristics.

[0065] More specifically, the first feature involved in this embodiment can be the location points of each first low-altitude target identified in the first image data, and the count value of the first low-altitude target can be determined by counting them.

[0066] In this embodiment of the invention, the movement speed is the main manifestation of the difference in the motion characteristics of low-altitude targets mentioned above. Specifically, a single low-altitude target (such as a drone) has a higher degree of freedom of motion and can fly at a faster speed / acceleration; while multiple low-altitude targets flying in swarms have a significantly lower movement speed than a single target due to the need to coordinate internal safety distances and consistency of actions. Based on the above findings, this invention sets the interval duration to be positively correlated with the count value. That is, when there are many drones in the target low-altitude area, it is determined that the subsequent movement speed of these drones is slow, or the change in movement speed is slow. In this case, the interval duration is appropriately increased, that is, a longer interval is elapsed after obtaining the first image data before obtaining the second image data, so that the difference between the first feature and the second feature is more obvious, which is beneficial for subsequent screening. Similarly, when there are few drones in the target low-altitude area, it is determined that the movement speed of the drones is fast, or the change in movement speed is rapid. In this case, the interval duration is appropriately decreased, that is, a shorter interval is elapsed after obtaining the first image data before obtaining the second image data. This setting can ensure that low-altitude targets are not lost (too long an interval can easily lead to target loss) and can make the difference between the first feature and the second feature more obvious, which is beneficial for subsequent screening.

[0067] In step 104, the first low-altitude target is filtered according to the first feature to obtain the second low-altitude target, including:

[0068] The first feature is matched with each of the first alignment features in the first feature library to obtain the first matching degree value;

[0069] Determine whether the first matching degree value is greater than the first threshold;

[0070] If so, then the first low-altitude target corresponding to the first matching degree value is removed;

[0071] If not, then the first low-altitude target corresponding to the first matching degree value shall be used as the second low-altitude target.

[0072] In this embodiment of the invention, several first comparison features are pre-established based on the static and dynamic features of various interfering objects that may appear in the target low-altitude area. If the first feature of the first low-altitude target is successfully matched with any first comparison feature in the first feature library (i.e., the first matching degree value is greater than the first threshold), it indicates that the first low-altitude target is an obvious interfering object, and it can be directly screened out. Other first low-altitude targets that fail to match are listed as second low-altitude targets and further screened in subsequent processes.

[0073] The interfering objects involved in this embodiment can be birds, hanging objects on buildings, the top shell of streetlights, floating balloons, plastic bags, etc. By pre-establishing several first comparison features based on the static and / or dynamic characteristics of these interfering objects, they can be easily eliminated. For example, the static shape of birds differs significantly from that of drones, and the motion characteristics of hanging objects and the top shell of streetlights differ significantly from those of drones.

[0074] In step 106, the second low-altitude targets are filtered according to the second feature to obtain the low-altitude targets to be tracked, including:

[0075] The second feature is matched with each of the second alignment features in the second feature library to obtain the second matching degree value;

[0076] Determine whether the second matching degree value is greater than the second threshold;

[0077] If so, then the second low-altitude target corresponding to the second matching degree value shall be taken as the low-altitude target to be tracked;

[0078] If not, then the second low-altitude target corresponding to the second matching degree value is removed.

[0079] In this embodiment of the invention, the second feature acquired after the waiting interval also includes the aforementioned static and dynamic features. Similarly, several second comparison features are pre-established based on the static and / or dynamic features of various low-altitude targets that may appear in the target low-altitude area. If the second feature of the second low-altitude target successfully matches any second comparison feature in the second feature library (i.e., the second matching degree value is greater than the second threshold), it indicates that the second low-altitude target is a tracking target, such as a drone, and it is tracked; otherwise, it is an obvious interference and can be directly filtered out.

[0080] For example, drones can typically achieve rapid vertical or near-vertical changes in altitude, a characteristic most interfering objects lack. Therefore, a corresponding second matching feature can be pre-established based on this dynamic feature. If a match is successful, it can be directly identified as a tracking target, such as a drone.

[0081] It should be noted that before performing the matching calculation, the motion sequences of each second low-altitude target can be obtained using existing means (such as the aforementioned radar and cameras equipped in the tracking system). The motion sequences can then be analyzed to determine if they exhibit rapid vertical or near-vertical changes in altitude, as described above. If so, the second feature and the associated second comparison feature are used to calculate the aforementioned second matching degree value. Specifically, the corresponding second comparison feature can be set according to the type of UAV, ensuring that the second comparison feature corresponds to the vertical altitude change characteristics of different types of UAVs. The type of UAV can be determined through the aforementioned first feature / second feature, and further details will not be elaborated upon here.

[0082] In a preferred embodiment, before matching the second feature with each of the second comparison features in the second feature library, the method further includes:

[0083] The motion range of the second low-altitude target is determined based on the second characteristic;

[0084] Determine if the range of motion is less than the third threshold;

[0085] If so, the second feature is matched with each second alignment feature in the second feature library.

[0086] In this embodiment of the invention, as described above, after obtaining the motion sequence of the second low-altitude target using existing methods, it is possible to analyze whether its motion trajectory points are within a motion range less than a third threshold. If so, it indicates that the second low-altitude target may be a hovering drone. Next, the second matching degree value between the motion range of the second low-altitude target and the associated second comparison feature (established based on the hovering features of different types of drones) is further calculated. At this point, a similar method to that described above can be used to screen and confirm the actual tracking target, triggering tracking processing.

[0087] For example, the second low-altitude targets identified through the aforementioned process include hovering drones and flying kites (or floating balloons fixed to the ground, especially objects with shapes similar to drones). Analysis revealed that their range of motion is less than the third threshold, thus classifying them as potential hovering drones. Next, several hovering comparison features (the second comparison features) corresponding to different types of drones are retrieved, and their second matching degree value with the range of motion is calculated. If a match is successful, the drone is identified as a hovering drone; otherwise, it is identified as interference.

[0088] like Figure 2 , Figure 3 As shown, this embodiment of the invention provides a low-altitude target identification and tracking device. The device embodiment can be implemented through software, hardware, or a combination of both. From a hardware perspective, as... Figure 2The diagram shown is a hardware architecture diagram of a computing device housing a low-altitude target identification and tracking device provided in an embodiment of the present invention. (Except for...) Figure 2 In addition to the processor, memory, network interface, and non-volatile memory shown, the computing device in the embodiment may also include other hardware, such as a forwarding chip responsible for processing packets. Taking software implementation as an example, such as... Figure 3 As shown, a device in a logical sense is formed by the CPU of its computing device reading the corresponding computer program from the non-volatile memory into memory and running it. This embodiment provides a low-altitude target identification and tracking device, including: an acquisition module 300, a processing module 302, and a filtering module 304;

[0089] The acquisition module 300 is used to acquire first image data of the target low-altitude region and second image data of the second low-altitude target determined by the processing module 302;

[0090] Processing module 302 is used to determine a first low-altitude target and a first feature of the first low-altitude target based on the first image data; and to determine a second feature of a second low-altitude target based on the second image data;

[0091] The filtering module 304 is used to filter the first low-altitude target according to the first feature to obtain the second low-altitude target; and to filter the second low-altitude target according to the second feature to obtain the low-altitude target to be tracked.

[0092] In some specific implementations, the acquisition module 300 can be used to perform the above steps 100 and 106, the processing module 302 can be used to perform the above steps 102 and 108, and the filtering module 304 can be used to perform the above steps 104 and 110.

[0093] In some specific embodiments, the device also includes a duration determination module;

[0094] The duration determination module is used to perform the following operations:

[0095] Based on the first feature, the time interval between acquiring the first image data and the second image data is determined.

[0096] More specifically, the duration determination module is also used to perform the following operations:

[0097] The first low-altitude target is counted based on the first feature to obtain the count value;

[0098] The interval duration is determined based on the count value; the interval duration is positively correlated with the count value.

[0099] In some specific implementations, the filtering module 304 is also used to perform the following operations:

[0100] The first feature is matched with each of the first alignment features in the first feature library to obtain the first matching degree value;

[0101] Determine whether the first matching degree value is greater than the first threshold;

[0102] If so, then the first low-altitude target corresponding to the first matching degree value is removed;

[0103] If not, then the first low-altitude target corresponding to the first matching degree value shall be used as the second low-altitude target.

[0104] In some specific implementations, the filtering module 304 is also used to perform the following operations:

[0105] The second feature is matched with each of the second alignment features in the second feature library to obtain the second matching degree value;

[0106] Determine whether the second matching degree value is greater than the second threshold;

[0107] If so, then the second low-altitude target corresponding to the second matching degree value shall be taken as the low-altitude target to be tracked;

[0108] If not, then the second low-altitude target corresponding to the second matching degree value is removed.

[0109] More specifically, the filtering module 304 is also used to perform the following operations:

[0110] The motion range of the second low-altitude target is determined based on the second characteristic;

[0111] Determine if the range of motion is less than the third threshold;

[0112] If so, the second feature is matched with each of the second alignment features in the second feature library.

[0113] It is understood that the structures illustrated in the embodiments of the present invention do not constitute a specific limitation on a low-altitude target identification and tracking device. In other embodiments of the present invention, a low-altitude target identification and tracking device may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0114] The information interaction and execution process between the modules in the above-mentioned device are based on the same concept as the method embodiment of the present invention, and the specific details can be found in the description of the method embodiment of the present invention, and will not be repeated here.

[0115] This invention also provides a computing device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements a low-altitude target identification and tracking method according to any embodiment of this invention.

[0116] This invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform a low-altitude target identification and tracking method according to any embodiment of this invention.

[0117] Specifically, a system or apparatus equipped with a storage medium may be provided, on which software program code implementing the functions of any of the embodiments described above is stored, and the computer (or CPU or MPU) of the system or apparatus may read and execute the program code stored in the storage medium.

[0118] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute part of the present invention.

[0119] Examples of storage media used to provide program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.

[0120] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, system, or device.

[0121] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including, but not limited to, wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0122] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0123] Furthermore, it should be clear that not only can the program code read by the computer be executed, but also the operating system or other components operating on the computer can be instructed based on the program code to perform some or all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0124] Furthermore, it is understood that the program code read from the storage medium is written to the memory set in the expansion board inserted into the computer or to the memory set in the expansion module connected to the computer. Then, based on the instructions of the program code, the CPU or other components installed on the expansion board or expansion module execute some and all of the actual operations, thereby realizing the function of any of the above embodiments.

[0125] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0126] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as ROM, RAM, magnetic disk, or optical disk.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A low altitude target identification and tracking method, characterized by, In an FPGA processing device, comprising: obtaining first image data of a target low-altitude area; determining a first low-altitude target and a first feature of the first low-altitude target according to the first image data; screening the first low-altitude target according to the first feature to obtain a second low-altitude target; obtaining second image data of the second low-altitude target; wherein a count value is obtained by counting the first low-altitude target according to the first feature; an interval duration for obtaining the first image data and the second image data is determined according to the count value; the interval duration is positively correlated with the count value; determining a second feature of the second low-altitude target according to the second image data; screening the second low-altitude target according to the second feature to obtain a low-altitude target to be tracked; the screening the first low-altitude target according to the first feature to obtain a second low-altitude target comprises: matching the first feature with each first comparison feature in a first feature library to obtain a first matching degree value; determining whether the first matching degree value is greater than a first threshold value; if yes, eliminating the first low-altitude target corresponding to the first matching degree value, which is an interference object; if no, taking the first low-altitude target corresponding to the first matching degree value as the second low-altitude target.

2. The method of claim 1, wherein, the screening the second low-altitude target according to the second feature to obtain a low-altitude target to be tracked comprises: matching the second feature with each second comparison feature in a second feature library to obtain a second matching degree value; determining whether the second matching degree value is greater than a second threshold value; if yes, taking the second low-altitude target corresponding to the second matching degree value as the low-altitude target to be tracked; if no, eliminating the second low-altitude target corresponding to the second matching degree value.

3. The method of claim 2, wherein, before the matching the second feature with each second comparison feature in a second feature library, further comprising: determining a motion range of the second low-altitude target according to the second feature; determining whether the motion range is less than a third threshold value; if yes, matching the second feature with each second comparison feature in a second feature library.

4. A low altitude target identification and tracking apparatus, characterized by, for implementing the method as claimed in any one of claims 1 to 3, comprising an obtaining module, a processing module and a screening module; the obtaining module is configured to obtain first image data of a target low-altitude area, and obtain second image data of a second low-altitude target determined by the processing module; the processing module is configured to determine a first low-altitude target and a first feature of the first low-altitude target according to the first image data, and determine a second feature of the second low-altitude target according to the second image data; the screening module is configured to screen the first low-altitude target according to the first feature to obtain a second low-altitude target, and screen the second low-altitude target according to the second feature to obtain a low-altitude target to be tracked. 5.A computing device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method as claimed in any one of claims 1 to 3.

6. A computer-readable storage medium having stored thereon a computer program, which, when executed in a computer, causes the computer to perform the method of any one of claims 1-3.

Images