Target recognition method, storage medium and electronic apparatus

Abstract

A target recognition method, a storage medium and an electronic apparatus, the method comprising: acquiring the micro-Doppler frequency of a target on the basis of the Doppler frequency of the target, so as to construct a time-delay micro-Doppler trajectory map, the Doppler frequency and the micro-Doppler frequency having time delay characteristics; acquiring micro-Doppler energy spectrum features of the target on the basis of the time-delay micro-Doppler trajectory map; and recognizing the target on the basis of the micro-Doppler energy spectrum features.

Description

Target recognition method, storage medium and electronic device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application is based on Chinese patent application CN 202410210394.7, filed on February 26, 2024, entitled “Target Identification Method, Storage Medium and Electronic Device”, and claims the priority of that patent application, and all the contents disclosed therein are incorporated into this application by reference. Technical Field

[0003] The embodiments of the present disclosure relate to the field of target recognition, and in particular, to a target recognition method, a storage medium, and an electronic device. Background Art

[0004] Integrated telepresence is a key 6G technology and has been recognized by the ITU-R as one of the six application scenarios for IMT-2030. It has become a research hotspot in the industry over the past two years. In the communication perception processing process, the receiver antenna array captures the target echo signal, detects the amplitude and phase changes of the echo signal, and processes it in the Doppler domain to obtain information such as the target's distance, angle, and velocity, thereby continuously tracking the target. However, most telepresence prototypes lack the ability to determine target attributes. Specifically, the targets of interest are people, vehicles, drones, and other objects, and this information is often crucial. Due to the complexity of wireless communication environments, research on target attribute recognition technology based on wireless networks remains elusive. There is no effective method for simultaneously identifying the presence of a target and determining its attributes. Radar perception has relatively mature methods for determining target attributes. Leveraging the radar system's large aperture, frequency band, and bandwidth advantages, they achieve high-precision imaging of vehicles, ships, and other objects in the environment. However, due to limited communication bandwidth and the presence of significant interference within the frequency band, target recognition using communication perception cannot achieve the high accuracy of radar imaging. In the field of communication perception, the industry is limited to detecting targets. As for whether the target is a person, a car, or other flying objects, no judgment is made, or the target attributes are known in advance, and the subsequent judgment only needs to be made that the target appears.

[0005] Perception technology can use Doppler characteristics to identify moving targets, but target feature extraction and identification are challenging. The motion of a moving target can be broken down into main motion and micro-motion. For human motion, main motion refers to the movement of the torso, with all torso parts moving at the same translational velocity, and its Doppler is considered a constant. Micro-motion refers to the movement of different parts of the limbs, exhibiting a periodic oscillation effect and periodic Doppler variations. The motion of a drone's fuselage is considered main motion, while the periodic rotation of its blades is considered micro-motion. The entire vehicle body can be considered main motion, with its micro-motion being less noticeable than that of a person or drone.

[0006] In summary, in the related technologies, it is impossible to realize target attribute recognition in complex scenes.

[0007] Summary of the Invention

[0008] According to one embodiment of the present disclosure, a target identification method is provided, comprising: obtaining a micro-Doppler frequency of the target based on the Doppler frequency of the target to construct a time-delay micro-Doppler trajectory diagram, wherein the Doppler frequency and the micro-Doppler frequency have a time-delay characteristic; obtaining a micro-Doppler energy spectrum characteristic of the target based on the time-delay micro-Doppler trajectory diagram; and identifying the target based on the micro-Doppler energy spectrum characteristic.

[0009] According to another embodiment of the present disclosure, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when running.

[0010] According to another embodiment of the present disclosure, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any one of the above method embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] FIG1 is a hardware structure block diagram of a computer terminal of a target recognition method according to an embodiment of the present disclosure;

[0012] FIG2 is a flow chart of a target recognition method according to an embodiment of the present disclosure;

[0013] FIG3 is a flow chart of a target recognition method according to an embodiment of the present disclosure;

[0014] FIG4 is a schematic diagram of target Doppler spread calculation according to an embodiment of the present disclosure;

[0015] FIG5 is a delay-Doppler diagram of a person and a car at a certain moment in an embodiment of the present disclosure;

[0016] FIG6 is a schematic diagram of the zero-frequency energy ratio of micro-Doppler frequency domain data according to an embodiment of the present disclosure;

[0017] FIG7 is a delay-Doppler diagram of a vehicle and a drone at a certain moment in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] Hereinafter, the embodiments of the present disclosure will be described in detail with reference to the accompanying drawings and in combination with the embodiments.

[0019] It should be noted that the terms "first", "second", etc. in the description and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0020] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking operation on a computer terminal as an example, FIG1 is a hardware structure block diagram of a computer terminal of the target recognition method of an embodiment of the present disclosure. As shown in FIG1 , the computer terminal may include one or more (only one is shown in FIG1 ) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the above-mentioned computer terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It will be understood by those skilled in the art that the structure shown in FIG1 is only for illustration and does not limit the structure of the above-mentioned computer terminal. For example, the computer terminal may also include more or fewer components than those shown in FIG1 , or have a configuration different from that shown in FIG1 .

[0021] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the target recognition method in the embodiment of the present disclosure. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implementing the above-mentioned method. The memory 104 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0022] The transmission device 106 is used to receive or transmit data via a network. Examples of such networks may include wireless networks provided by a computer terminal's communications provider. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0023] In an embodiment of the present disclosure, a target recognition method is provided, which can be applied to a wireless communication network. FIG2 is a flow chart of the target recognition method according to an embodiment of the present disclosure. As shown in FIG2 , the flow chart includes the following steps:

[0024] Step S202 : acquiring the micro-Doppler frequency of the target according to the Doppler frequency of the target to construct a time-delay micro-Doppler trajectory diagram, wherein the Doppler frequency and the micro-Doppler frequency have a time-delay characteristic.

[0025] In an exemplary embodiment, a micro-Doppler frequency of a target is obtained according to the Doppler frequency of the target to construct a time-delay micro-Doppler trajectory diagram, including: obtaining a range parameter and a Doppler frequency parameter of the target at different times according to the Doppler frequency; calculating a time delay parameter and a micro-Doppler frequency of the target according to the range parameter and the Doppler frequency parameter; and constructing a time-delay micro-Doppler trajectory diagram according to the time delay parameter and the micro-Doppler frequency.

[0026] In this disclosed embodiment, the target's range and Doppler frequency parameters are extracted from the target's Doppler frequency trajectory at different consecutive moments. The target's delay and micro-Doppler frequency are calculated based on the range and Doppler frequency parameters. A delay and micro-Doppler trajectory map is constructed based on the delay and micro-Doppler frequency.

[0027] In the disclosed embodiment, the target's delay parameter and micro-Doppler frequency are calculated based on the distance parameter and the Doppler frequency parameter. A window function can be used to implement the calculation process. The window function, window length, moving step size, and window function type are set according to actual conditions.

[0028] Step S204: acquiring the micro-Doppler energy spectrum characteristics of the target according to the time-delay micro-Doppler trajectory diagram.

[0029] In an exemplary embodiment, a micro-Doppler energy spectrum characteristic of a target is obtained based on a time-delay micro-Doppler trajectory diagram, including: extracting data points in the time-delay micro-Doppler trajectory diagram at preset intervals; performing Fourier transform on the data of the data points to obtain an energy spectrum distribution of the data points; and obtaining the micro-Doppler energy spectrum characteristic based on the ratio of the zero spectrum line energy in the energy spectrum distribution to the energy of all frequency points.

[0030] In the disclosed embodiments, uniform extraction of target trajectory data from the time-delay micro-Doppler trajectory map is achieved by extracting data points at preset intervals. Based on the image of the Doppler frequency variation with data packets in the target's micro-Doppler spectrum, data points are extracted at equal intervals from the time-delay micro-Doppler trajectory map. The preset interval can be set. A Fourier transform (FFT) is performed on the extracted data to obtain the energy spectrum distribution of the data points. The ratio of the zero-spectral line energy to the energy of all frequency points in the time-delay micro-Doppler trajectory map is calculated to obtain the target's micro-Doppler energy spectrum characteristics.

[0031] Step S206: Identify the target based on the micro-Doppler energy spectrum characteristics.

[0032] In an exemplary embodiment, identifying a target based on micro-Doppler energy spectrum characteristics includes: judging whether the target has micro-motion characteristics based on the micro-Doppler energy spectrum characteristics; if the micro-Doppler energy spectrum characteristics are greater than or equal to a second preset energy threshold, judging that the target has micro-motion characteristics; otherwise, judging that the target does not have micro-motion characteristics; and identifying the target based on the judgment result.

[0033] In the disclosed embodiment, if a target exhibits micro-motion characteristics, a preliminary determination is made as to whether the target is a person or a drone, and further target recognition is then performed to distinguish between people and drones. In the disclosed embodiment, further distinguishing between people and drones can be achieved using various methods, including but not limited to RCS value estimation, target height comparison, and spectral peak expansion determination.

[0034] In an exemplary embodiment, the target is identified based on the judgment result, including: when the target has micro-motion characteristics, the target is identified based on the radar cross-section RCS parameter of the target; when the RCS parameter is greater than a preset threshold, the target is identified as a human; when the RCS parameter is less than the preset threshold, the target is identified as a drone.

[0035] In an exemplary embodiment, the target is identified based on the judgment result, including: when the target has micro-motion characteristics, the height of the target is calculated based on the angle parameter and distance parameter of the target; when the height is less than a preset height threshold, the target is identified as a person; when the height is greater than the preset height threshold, the target is identified as a drone.

[0036] In an exemplary embodiment, the target is identified based on the judgment result, including: when the target has micro-motion characteristics, the target is identified based on the Doppler spectrum peak expansion of the target; when the Doppler spectrum peak expansion is greater than a preset expansion threshold, the target is identified as a person; when the Doppler spectrum peak expansion is less than the preset expansion threshold, the target is identified as a drone.

[0037] In the embodiment of the present disclosure, if the target does not have micro-motion characteristics, there are two cases: the target does not have micro-motion characteristics or the target has micro-motion characteristics, but the target is too far away, which exceeds the system's ability to perceive micro-motion.

[0038] In an exemplary embodiment, the target is identified based on the judgment result, including: when the target does not have micro-motion characteristics, the target is identified based on the distance parameter of the target; when the distance parameter is less than a preset distance threshold, the target is identified as a car; when the distance parameter is greater than a preset distance threshold and the height of the target is greater than a preset height threshold, the target is identified as a drone; when the distance parameter is greater than a preset distance threshold and the height of the target is less than a preset height threshold, the target is identified as a person.

[0039] In an exemplary embodiment, before step S202, the method further includes: receiving frequency domain data of the target according to perception, and calculating and obtaining perception parameters of the target; constructing a delay-Doppler frequency map of the target at different moments according to the perception parameters; and obtaining a Doppler frequency trajectory according to the delay-Doppler frequency map.

[0040] In the embodiment of the present disclosure, the target's perceived received frequency domain data may be various communication parameters of the communication system.

[0041] In an exemplary embodiment, the sensing parameter includes at least one of the following: an angle parameter of the target; a distance parameter of the target; a Doppler frequency parameter of the target; or a Doppler energy parameter of the target.

[0042] In an exemplary embodiment, after calculating and obtaining the perception parameters of the target based on the perception reception frequency domain data of the target, it also includes: comparing the Doppler energy parameter of the target with a first preset energy threshold, and if the Doppler energy parameter is greater than or equal to the first preset energy threshold, determining that the target is a valid target; otherwise, determining that the target is an invalid target.

[0043] In the embodiment of the present disclosure, invalid targets are eliminated by pre-screening targets, thereby greatly improving the efficiency and accuracy of target recognition.

[0044] Through the above steps, a target recognition method is provided. The method obtains the target's micro-Doppler frequency based on the target's Doppler frequency to construct a time-delay micro-Doppler trajectory diagram, where the Doppler frequency and micro-Doppler frequency have a time-delay characteristic. The target's micro-Doppler energy spectrum characteristics are obtained based on the time-delay micro-Doppler trajectory diagram. The target is then identified based on the micro-Doppler energy spectrum characteristics. This method solves the problem of the related art in being unable to identify target attributes in complex scenarios, achieving the effect of effectively identifying target attributes in complex scenarios.

[0045] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the embodiment of the present disclosure is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD-ROM), including a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the method described in the embodiment of the present disclosure.

[0046] In this embodiment, a target recognition device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments. The details already described will not be repeated here. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0047] The target identification device provided by the embodiment of the present disclosure includes a micro-Doppler trajectory construction module for obtaining the micro-Doppler frequency of the target based on the Doppler frequency of the target to construct a time-delay micro-Doppler trajectory diagram, wherein the Doppler frequency and the micro-Doppler frequency have a time-delay characteristic. The energy spectrum characteristic acquisition module is used to obtain the micro-Doppler energy spectrum characteristics of the target based on the time-delay micro-Doppler trajectory diagram. The identification module is used to identify the target based on the micro-Doppler energy spectrum characteristics. In actual implementation, there is no specific limitation on the naming and functional division of the various modules in the target identification device, as long as the steps of the target identification method of the embodiment of the present disclosure can be implemented.

[0048] It should be noted that the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0049] An embodiment of the present disclosure further provides a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when running.

[0050] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0051] An embodiment of the present disclosure further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0052] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0053] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail here.

[0054] Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of the present disclosure can be implemented using a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented using program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be performed in a different order than herein, or they can be made into individual integrated circuit modules, or multiple modules or steps can be made into a single integrated circuit module for implementation. Thus, the embodiments of the present disclosure are not limited to any specific combination of hardware and software.

[0055] In order to enable those skilled in the art to better understand the technical solutions of the embodiments of the present disclosure, the following is an elaboration of the technical solutions in combination with embodiments in different scenarios.

[0056] Example 1

[0057] Based on extensive data analysis in the early stages, we learned that the micro-Doppler phenomenon can be used to identify targets with micro-motion, such as moving people and flying drones. However, due to factors such as target distance and power, the micro-motion phenomenon is sometimes not obvious. According to measured data, targets with larger radar cross-sections (RCS) have more severe delay-Doppler spectrum peak expansion, manifesting as a "sharp peak" for drones and peaks for vehicles and people spanning multiple Doppler-range units. Target identification is achieved by integrating Doppler expansion with RCS estimation methods.

[0058] The present disclosure provides a target recognition method. FIG3 is a flow diagram of the target recognition method according to the present disclosure. As shown in FIG3 , the method includes the following steps:

[0059] Step S302: Acquire the target's sensing reception data, calculate and acquire the target's sensing parameters, and acquire the target's Doppler frequency trajectory.

[0060] The target's sensory reception data is acquired and the sensory parameters in the delay-Doppler plot at each moment are calculated based on this sensory reception data. These sensory parameters include target angle, target range, target Doppler frequency, and target Doppler energy. Based on the sensory data at consecutive moments, the target's trajectory, or Doppler frequency trajectory, is then correlated.

[0061] In the embodiment of the present disclosure, the sensed received data is the sensed received frequency domain data. In actual implementation, the sensed received frequency domain data may be a variety of communication parameters of the communication system.

[0062] The sensed received data is recorded as R, and the dimensions of the data dimensions of different receiving antenna types are antenna array i ant (1≤i ant ≤N ant ), subcarrier index i sub (1≤i sub ≤N sub ), data packet index i pac (1≤i pac ≤N pac ). Use the received data and the local sequence to calculate the channel frequency domain H = R * conj (S), where S is the transmitted signal frequency domain. Perform an N-point inverse Fourier transform (IFFT) on the subcarrier dimension to obtain the channel impulse response h = IFFT (H). Perform an N-point inverse Fourier transform on the packet dimension. pac The Doppler frequency Doppler of the received data is obtained by performing a point Fourier transform (FFT). The dimensions are antenna array, time delay, and Doppler frequency. pac Both represent positive integers.

[0063] The spectrum peak search algorithm is used to merge antenna data and construct steering vectors with different angle values, which are multiplied by the conjugate dot of the Doppler frequency: V(θ)=Doppler.*conj(a(θ))

[0064] The target angle θ is such that |V(θ)|=|V(θ)| m , the target distance is d=(Ts-T los )*2.44+d los , Ts is the arrival time of the target echo signal, Ts=1 / fs, fs is the sampling rate. los is the center distance between the transceiver panel, T los is the arrival time of the line-of-sight path signal. The target Doppler frequency range is [-f m / 2,f m / 2], f m＝ 1 / T d , T d is the packet interval, and the target energy is |V(θ)| m .

[0065] According to the perception data of different consecutive moments, the target association is completed before and after the moment, and the target energy threshold T1 is defined as the first preset energy threshold. The target is the target with an energy value greater than T1. pac ·T d The time duration is treated as a moment, and a delay-Doppler map can be generated at each moment. The target is extracted at each moment, and the Doppler frequency trajectory is obtained based on the correlation of targets at consecutive moments, completing target trajectory tracking. Target correlation refers to the distance between the target at the previous and next moments in the delay dimension (Ts dimension) and the frequency dimension (f dimension).

[0066] Step S304 : According to the Doppler frequency trajectory of the target, the time delay and micro-Doppler frequency of the target are obtained, and a time delay and micro-Doppler trajectory diagram is constructed.

[0067] The target's range and Doppler frequency parameters are extracted from the target's Doppler frequency trajectory at different times. The target's time delay and micro-Doppler frequency are calculated based on the range and Doppler frequency parameters. A time delay and micro-Doppler trajectory diagram is constructed based on the time delay and micro-Doppler frequency.

[0068] In the embodiment of the present disclosure, the distance-Doppler frequency (Ts, f) value of the target at different moments in the Doppler frequency trajectory of the target is extracted. The Ts value is the corresponding value of the target trajectory in the Ts dimension after being sorted in time order. The corresponding relationship between the distance and the delay data Ts is distance = delay * 2.44, and the f value is the corresponding value in the Doppler frequency dimension. The data of the corresponding Ts value is extracted from the Doppler frequency trajectory. According to the (Ts, f) value of the target, the data corresponding to the Ts value in all Ts dimensions is extracted on the channel impulse response h, and h′=h is obtained. Ts .

[0069] Calculate the delay parameters and micro-Doppler frequency, set the window function, window length, and moving step. The window function win is not limited to Kaiser window, Blackman window, and Hanning window, etc. The window length L (1<L<N pac ), moving step size step = 1, D after windowing h′ data L The number is floor((N d -L) / step)+1. Among them, D L Indicates the number of data packet dimensions. Calculating the delay parameter and micro-Doppler frequency involves two steps:

[0070] 1) Perform window function filtering on the data of each window, and the filtering is time domain filtering: D w =D L .*win

[0071] 2) Perform Fourier transform (FFT) on each window-filtered data in the packet dimension to obtain the micro-Doppler data of the target. The dimensions are packet index, micro-Doppler frequency, and micro-Doppler energy.

[0072] Step S306: Acquire the micro-Doppler energy spectrum characteristics of the target according to the time-delay micro-Doppler trajectory diagram.

[0073] Uniformly extract the target trajectory data in the time-delay micro-Doppler map, and extract data points in the time-delay micro-Doppler trajectory map according to preset intervals; perform Fourier transform on the data points to obtain the energy spectrum distribution of the data points; and obtain the micro-Doppler energy spectrum characteristics based on the ratio of the zero spectrum line energy in the energy spectrum distribution to the energy of all frequency points.

[0074] Based on the image of the target's micro-Doppler spectrum showing how the Doppler frequency changes with data packets, data points are extracted at equal intervals in the time-delay micro-Doppler trajectory diagram. The preset interval can be set. The extracted data are then Fourier transformed (FFT) to obtain the energy spectrum distribution of the data points. The ratio of the zero-spectral line energy to the energy of all frequency points in the time-delay micro-Doppler trajectory diagram is calculated, thus obtaining the target's micro-Doppler energy spectrum characteristics.

[0075] Step S308 : analyzing the target micro-motion characteristics according to the target's micro-Doppler energy spectrum characteristics.

[0076] The target's micro-motion characteristics are analyzed based on the target's micro-Doppler energy spectrum characteristics. A second preset energy threshold, T2, is set. If the target's micro-Doppler zero-spectrum line energy ratio is greater than T2, i.e., the micro-Doppler energy spectrum characteristics are greater than the second preset energy threshold, then the target's micro-motion characteristics are not obvious or do not have micro-motion characteristics. Conversely, if the target's micro-Doppler zero-spectrum line energy ratio is less than or equal to T2, then the target has micro-motion characteristics.

[0077] Step S310 : Target recognition is completed based on the target micro-motion characteristics, combined with the target's RCS estimation value and Doppler spread.

[0078] Based on the target's micro-motion characteristics, combined with its estimated RCS and Doppler spread, the system can identify people, vehicles, and drones. For targets with micro-motion, the micro-Doppler frequency approximates a sinusoidal curve, with the spectral energy of the micro-Doppler frequency curve primarily concentrated outside the zero frequency. For targets without micro-motion, the micro-Doppler frequency approximates a straight line, with the spectral energy of the micro-Doppler frequency curve primarily concentrated at the zero frequency.

[0079] 1) If the target has micro-motion characteristics, it is preliminarily determined to be a person or a drone, and further target recognition is performed to distinguish between people and drones.

[0080] The first way to distinguish is to estimate the RCS value of the target. The RCS is determined by the following formula:

[0081] Among them, E T is the transmission power, E R is the received power, d is the distance between the target and the base station, and λ is the wavelength of the sensing signal. The RCS of a person is about 1, and the RCS of a drone is about 0.02. If the target If the value is greater than the threshold of 0.1 (adjustable), it is judged as a person, and if it is less than 0.1, it is judged as a drone.

[0082] The second method of identification: Calculate the target's altitude based on the time delay-Doppler spectrum data, as well as parameters such as the target's angle and distance. A threshold value, T3, is set as the default altitude threshold. If the target's altitude is greater than T3, it is identified as a drone; if it is less than T3, it is identified as a person.

[0083] The third way to distinguish: Since the RCS of a person is much larger than that of a drone, the spectrum peak expansion of a person is much larger than that of a drone in the delay-Doppler spectrum. The expansion refers to the expansion in the delay dimension. The expansion amount is calculated as follows:

[0084] FIG4 is a schematic diagram of the target Doppler spread calculation according to an embodiment of the present disclosure. As shown in FIG4 , the intersection points of the delay-Doppler spectrum target peak and the noise floor threshold T1 in the delay direction are points C and D, respectively. The target energy maximum point A is projected to point B. The target energy spread is defined as: Spread = max(|BD|,|BC|)

[0085] Among them, |BD|, |BC| are the Doppler spreads in the delay direction.

[0086] If the target Doppler spread Spread is greater than the preset spread threshold T4, it is a person, otherwise it is a drone.

[0087] 2) If the target does not have micro-motion characteristics, there are two cases: the target does not have micro-motion characteristics or the target has micro-motion characteristics, but the target is too far away, which exceeds the system's ability to perceive micro-motion. Define the preset distance threshold T5:

[0088] If the target distance is less than T5, the target is a car;

[0089] If the target's distance is greater than T5, the target's altitude is calculated based on the raw delay-Doppler spectrum data, as well as parameters such as the target's angle and distance. If the target's altitude is greater than a preset altitude threshold, T3, it is considered a drone; if it is less than T3, it is considered a person. Alternatively, if the target's Doppler spread is greater than a preset spread threshold, T4, it is considered a person; otherwise, it is considered a drone.

[0090] Example 2

[0091] In the second embodiment, target recognition of people and vehicles is performed for a certain fixed image scene.

[0092] Assume that people move randomly in the environment, and occasionally vehicles pass through their paths. The base station signal frequency is 4.9 GHz, the bandwidth is 100 MHz, the sensing signal period is 5 ms, the number of sensing symbols sent in each period is 1, and 100 packets of data are received each time. The modulation sequence is the remote interference management (RIM) sequence used by 3GPP. The transmitted signal beam is 65° horizontally and 6° vertically. The base station panel array has 8 horizontal and 4 vertical arrays, and the base station panel array is dual-polarized. The target's delay-Doppler spectrum is calculated to obtain the delay-Doppler map of the person and vehicle at a certain moment. Figure 5 shows the delay-Doppler map of the person and vehicle at a certain moment.

[0093] In this embodiment, the target's range-Doppler frequency value at each moment in the target trajectory graph is extracted. A window length of L = 60 and a sliding step size of step = 1 are set in the packet dimension. A window function is applied to the data in each window, using a Blackman window. The filtered data is then subjected to an FFT to generate a delay-micro-Doppler graph.

[0094] In the disclosed embodiment, data of each target in the micro-Doppler image is extracted, and FFT is performed to divide the spectral energy in different frequency bands to determine the proportion of zero-frequency energy in the micro-Doppler data spectrum. The proportion is 0.4% for target 2, which has micro-motion characteristics. In the present embodiment, target 2 is a person.

[0095] FIG6 is a schematic diagram of the zero-frequency energy ratio of micro-Doppler frequency domain data according to an embodiment of the present disclosure. As shown in FIG6 , the main energy is distributed outside the zero frequency.

[0096] Example 3

[0097] In the third embodiment, target recognition of drones and cars is performed for a scene in a fixed image.

[0098] The base station's signal frequency is 4.9 GHz, with a bandwidth of 100 MHz. The sensing signal period is 5 ms, with one sensing symbol sent per period. The modulation sequence is the RIM sequence used by 3GPP. The transmit signal beamform is 65° horizontally and 6° vertically. The base station's panel array has eight horizontal and four vertical arrays, using dual polarization. The sensing targets include vehicles and drones. The drone flew away from the base station in a specified direction, while vehicles were traveling on the highway.

[0099] Calculate the delay-Doppler spectrum of the target. FIG7 is a delay-Doppler spectrum of a vehicle and a UAV at a certain moment in an embodiment of the present disclosure. As shown in FIG7 , two targets are marked in the figure.

[0100] The range-Doppler frequency values ​​for the trajectories of target 1 and target 2 are extracted separately. In the packet dimension, a window length of L = 60 and a sliding step size of step = 1 are set. The data in each window is filtered using a Blackman window to obtain a delay-micro-Doppler map.

[0101] The micro-Doppler graphs of target 1 and target 2 are plotted on the same graph. The micro-Doppler curve of target 1 shows periodic changes, while the micro-Doppler curve of target 2 is approximately a gently changing straight line.

[0102] The micro-Doppler curves of target 1 and target 2 are extracted respectively, and FFT is performed. After calculation, the zero frequency of target 1 accounts for 0.4%, and the zero frequency of target 2 accounts for 99%. In this embodiment, target 1 is a drone and target 2 is a vehicle.

[0103] In summary, the disclosed embodiments provide a target recognition method that integrates micro-Doppler, spectral peak expansion, and RCS estimation to accurately identify people, vehicles, and drones. This method is efficient and reliable, achieving the goal of not only detecting but also identifying targets in synaesthesia. The target recognition method provided by the disclosed embodiments solves the problem of identifying and judging target attributes in synaesthesia systems in complex wireless environments, significantly expanding the perception capabilities of communication perception systems.

[0104] The above description is merely a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Those skilled in the art will appreciate that various modifications and variations of the present disclosure are possible. Any modifications, equivalent substitutions, or improvements made within the principles of the present disclosure should be included within the scope of protection of the present disclosure.

Claims

1. A target recognition method, comprising: Acquiring a micro-Doppler frequency of the target according to the Doppler frequency of the target to construct a time-delay micro-Doppler trajectory diagram, wherein the Doppler frequency and the micro-Doppler frequency have a time-delay characteristic; Acquiring a micro-Doppler energy spectrum characteristic of the target according to the time-delay micro-Doppler trajectory diagram; The target is identified according to the micro-Doppler energy spectrum characteristics.

2. The method according to claim 1, wherein The step of obtaining the micro-Doppler frequency of the target according to the Doppler frequency of the target to construct a time-delay micro-Doppler trajectory diagram includes: According to the Doppler frequency, obtaining the distance parameter and the Doppler frequency parameter of the target at different times; Calculating the target's time delay parameter and the micro-Doppler frequency according to the distance parameter and the Doppler frequency parameter; The time-delay micro-Doppler trajectory diagram is constructed according to the time delay parameter and the micro-Doppler frequency.

3. The method according to claim 1, wherein The acquiring of the micro-Doppler energy spectrum characteristics of the target according to the time-delay micro-Doppler trajectory diagram includes: extracting data points in the time-delay micro-Doppler trajectory diagram according to a preset interval; Performing Fourier transform on the data of the data point to obtain the energy spectrum distribution of the data point; The micro-Doppler energy spectrum feature is obtained according to the ratio of the zero spectrum line energy in the energy spectrum distribution to the energy of all frequency points.

4. The method according to claim 1, wherein The identifying the target according to the micro-Doppler energy spectrum feature includes: determining, based on the micro-Doppler energy spectrum characteristic, whether the target has a micro-motion characteristic; if the micro-Doppler energy spectrum characteristic is less than or equal to a second preset energy threshold, determining that the target has the micro-motion characteristic; otherwise, determining that the target does not have the micro-motion characteristic; The target is identified according to the judgment result.

5. The method according to claim 4, wherein The identifying the target according to the judgment result includes: In the case where the target has micro-motion characteristics, identifying the target according to the radar cross section RCS parameter of the target; When the RCS parameter is greater than a preset threshold, the target is identified as a person; when the RCS parameter is less than the preset threshold, the target is identified as a drone.

6. The method according to claim 4, wherein: The identifying the target according to the judgment result includes: In the case where the target has a micro-motion characteristic, calculating and obtaining the height of the target according to the angle parameter and the distance parameter of the target; When the height is less than a preset height threshold, the target is identified as a person; when the height is greater than the preset height threshold, the target is identified as a drone.

7. The method according to claim 4, wherein: The identifying the target according to the judgment result includes: In the case where the target has micro-motion characteristics, identifying the target according to the Doppler spectrum peak expansion of the target; When the Doppler spectrum peak expansion is greater than a preset expansion threshold, the target is identified as a person; when the Doppler spectrum peak expansion is less than the preset expansion threshold, the target is identified as a drone.

8. The method according to claim 4, wherein The identifying the target according to the judgment result includes: In a case where the target does not have micro-motion characteristics, identifying the target according to a distance parameter of the target; When the distance parameter is less than a preset distance threshold, the target is identified as a car; when the distance parameter is greater than the preset distance threshold and the height of the target is greater than a preset height threshold, the target is identified as a drone; when the distance parameter is greater than the preset distance threshold and the height of the target is less than a preset height threshold, the target is identified as a person.

9. The method according to claim 1, wherein: Before acquiring the micro-Doppler frequency of the target according to the Doppler frequency of the target, the method further includes: Receive frequency domain data of the target and calculate and obtain the target's perception parameters; constructing delay-Doppler frequency maps of the target at different times according to the sensing parameters; The Doppler frequency trajectory is obtained according to the delay Doppler frequency map.

10. The method according to claim 9, wherein: The perception parameter includes at least one of the following: Angle parameter of the target; a distance parameter of the target; Doppler frequency parameter of the target; The Doppler energy parameter of the target.

11. The method according to claim 9, wherein After receiving frequency domain data according to the perception of the target and calculating and obtaining the perception parameters of the target, the method further includes: The Doppler energy parameter of the target is compared with a first preset energy threshold. If the Doppler energy parameter is greater than or equal to the first preset energy threshold, the target is determined to be a valid target; otherwise, the target is determined to be an invalid target.

12. A computer-readable storage medium having a computer program stored therein, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

13. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 11 when executing the computer program.

Images