A target classification identification method and system, an electronic device, and a storage medium

Abstract

The application discloses a target classification identification method and system, electronic equipment and a storage medium, and relates to the technical field of radar target identification. The method comprises the following steps: acquiring radar intermediate frequency output data; the radar intermediate frequency output data is a radar data intermediate frequency sinusoidal wave signal; and the radar intermediate frequency output data comprises information of a target to be classified. The radar intermediate frequency output data is subjected to down-conversion processing to obtain a zero intermediate frequency signal. The Fourier transform method is used to obtain frequency domain characteristic data according to the zero intermediate frequency signal. It is judged whether the frequency domain characteristic data satisfies a preset threshold value. If yes, the short-time Fourier transform method is used to obtain time-frequency domain characteristic data according to the zero intermediate frequency signal, and the target to be classified is classified according to the time-frequency domain characteristic data to obtain a classification result of the target to be classified. If no, the target to be classified is classified according to the frequency domain characteristic data to obtain a classification result of the target to be classified. The application improves the accuracy of target classification identification.

Description

Technical Field

[0001] This invention relates to the field of radar target recognition technology, and in particular to a target classification and recognition method, system, electronic device and storage medium. Background Technology

[0002] Existing target recognition and classification methods mainly use time-domain or frequency-domain features of targets for target recognition alone, without utilizing time-frequency domain feature data that better reflects the changes of targets over time. When using time-domain or frequency-domain feature data, multiple features are not weighted and fused, resulting in low accuracy of target classification and recognition. Summary of the Invention

[0003] The purpose of this invention is to provide a target classification and recognition method, system, electronic device, and storage medium that improves the accuracy of target classification and recognition.

[0004] To achieve the above objectives, the present invention provides the following solution:

[0005] A target classification and recognition method, the method comprising:

[0006] Acquire radar intermediate frequency output data; the radar intermediate frequency output data is an intermediate frequency sine wave signal of radar data; the radar intermediate frequency output data includes information about the target to be classified;

[0007] The radar intermediate frequency output data is down-converted to obtain a zero intermediate frequency signal;

[0008] Frequency domain feature data are obtained from the zero intermediate frequency signal using the Fourier transform method.

[0009] Determine whether the frequency domain feature data meets a preset threshold;

[0010] If so, the short-time Fourier transform method is used to obtain time-frequency domain feature data based on the zero intermediate frequency signal, and the target to be classified is classified based on the time-frequency domain feature data to obtain the classification result of the target to be classified.

[0011] If not, the target to be classified is classified according to the frequency domain feature data to obtain the classification result of the target to be classified.

[0012] Optionally, the step of obtaining frequency domain feature data from the zero intermediate frequency signal using the Fourier transform method specifically includes:

[0013] The zero-IF signal is subjected to spectral transformation using the Fourier transform method to obtain multiple frequency points and corresponding amplitudes;

[0014] The frequency domain feature data is determined based on the frequency point corresponding to the maximum amplitude.

[0015] A target classification and recognition system, the system comprising:

[0016] The radar intermediate frequency output data acquisition module is used to acquire radar intermediate frequency output data; the radar intermediate frequency output data is an intermediate frequency sine wave signal of radar data; the radar intermediate frequency output data includes information about the target to be classified;

[0017] The zero intermediate frequency signal determination module is used to perform down-conversion processing on the radar intermediate frequency output data to obtain a zero intermediate frequency signal.

[0018] The frequency domain feature data determination module is used to obtain frequency domain feature data based on the zero intermediate frequency signal using the Fourier transform method.

[0019] The judgment module is used to determine whether the frequency domain feature data meets a preset threshold.

[0020] The first execution module is used to, if so, use the short-time Fourier transform method to obtain time-frequency domain feature data based on the zero intermediate frequency signal, and classify the target to be classified based on the time-frequency domain feature data to obtain the classification result of the target to be classified.

[0021] The second execution module is used to classify the target to be classified based on the frequency domain feature data if no, and obtain the classification result of the target to be classified.

[0022] Optionally, the frequency domain feature data determination module specifically includes:

[0023] The spectrum transformation unit is used to perform spectrum transformation on the zero intermediate frequency signal using the Fourier transform method to obtain multiple frequency points and corresponding amplitudes;

[0024] The frequency domain feature data determination unit is used to determine the frequency domain feature data based on the frequency point corresponding to the maximum amplitude.

[0025] An electronic device, comprising:

[0026] One or more processors;

[0027] A storage device on which one or more programs are stored;

[0028] When the one or more programs are executed by the one or more processors, the one or more processors implement the target classification and recognition method as described above.

[0029] A storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the target classification and recognition method as described above.

[0030] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0031] This invention discloses a target classification and identification method, system, electronic device, and storage medium. The method includes: acquiring radar intermediate frequency (IF) output data; the radar IF output data is an IF sine wave signal of radar data; the radar IF output data includes information about the target to be classified. The radar IF output data is down-converted to obtain a zero IF signal. Frequency domain feature data is obtained from the zero IF signal using the Fourier transform method. Whether the frequency domain feature data meets a preset threshold is determined. If so, time-frequency domain feature data is obtained from the zero IF signal using the short-time Fourier transform method, and the target to be classified is classified based on the time-frequency domain feature data. This invention combines frequency domain feature data and time-frequency domain feature data for target classification and identification, which improves the accuracy of target classification and identification compared to existing methods that only rely on one type of feature data. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 This is a schematic diagram of the target classification and recognition method provided in Embodiment 1 of the present invention;

[0034] Figure 2 This is a schematic diagram of the target classification and recognition system provided in Embodiment 2 of the present invention. Detailed Implementation

[0035] 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 only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0036] The purpose of this invention is to provide a target classification and recognition method, system, electronic device, and storage medium, which aim to improve the accuracy of target classification and recognition.

[0037] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0038] Example 1

[0039] Figure 1 This is a schematic diagram of the target classification and recognition method provided in Embodiment 1 of the present invention. Figure 1 As shown, the target classification and recognition method in this embodiment includes:

[0040] Step 101: Acquire radar intermediate frequency output data; radar intermediate frequency output data is the intermediate frequency sine wave signal of radar data; radar intermediate frequency output data includes information about the target to be classified.

[0041] Step 102: Down-convert the radar intermediate frequency output data to obtain a zero intermediate frequency signal.

[0042] Step 103: Using the Fourier transform method, obtain frequency domain characteristic data based on the zero intermediate frequency signal.

[0043] Step 104: Determine whether the frequency domain feature data meets the preset threshold.

[0044] Step 105: If so, use the short-time Fourier transform method to obtain time-frequency domain feature data based on the zero intermediate frequency signal, and classify the target to be classified based on the time-frequency domain feature data to obtain the classification result of the target to be classified.

[0045] Step 106: If not, classify the target to be classified based on the frequency domain feature data to obtain the classification result of the target to be classified.

[0046] As an optional implementation, step 103 specifically includes:

[0047] The Fourier transform method is used to perform spectral transformation on the zero intermediate frequency signal to obtain multiple frequency points and their corresponding amplitudes.

[0048] The frequency domain characteristic data is determined based on the frequency point corresponding to the maximum amplitude.

[0049] Specifically, before classifying the target based on time-frequency domain feature data and before classifying the target based on frequency domain feature data, the following steps are also included:

[0050] Using the maximum likelihood estimation method, time-domain characteristic data are obtained based on the zero intermediate frequency signal.

[0051] Preliminary classification is performed based on time-domain feature data to obtain preliminary classification results for the target to be classified. Classification using frequency-domain feature data is time-consuming; therefore, the purpose of preliminary classification using time-domain feature data is to quickly provide users with a reference so they can begin making necessary decisions. Then, a final decision is made using the accurate classification results. Users can then proceed with the next step of specific classification based on the preliminary classification results.

[0052] As a specific embodiment, the above method will be explained with the target being a vehicle or a person:

[0053] Step 1: Acquire radar intermediate frequency output data (radar intermediate frequency output data is the intermediate frequency sine wave signal of the acquired radar data; in a specific embodiment, the radar data is road data acquired by radar), and perform down-conversion processing on the radar intermediate frequency output data to obtain a zero intermediate frequency signal containing target information (target information refers to amplitude, frequency, and phase).

[0054] The second step is to estimate the zero-IF signal based on the maximum likelihood estimation method, and obtain the amplitude 'a' of the zero-IF signal, which is the time-domain characteristic data of the target.

[0055] Step 3: Based on the Fourier transform method, the zero intermediate frequency signal is subjected to spectral transformation to obtain multiple frequency points and corresponding amplitudes. The frequency point corresponding to the maximum amplitude (a frequency component with the maximum energy) is selected as the frequency information of the zero intermediate frequency signal, and the frequency information is converted into velocity information b, which is the frequency domain feature data of the target.

[0056] Specifically, let the frequency be f. d Then b = c0 * f d / (2*f0). Where, f d Let f0 be the frequency value of the frequency component with the highest energy, f0 be the radar carrier frequency, and c0 be the speed of light in a vacuum, c0 = 3 * 10^25. 8 m / s.

[0057] Step 4: Based on the short-time Fourier transform method, perform time-frequency analysis on the zero intermediate frequency signal to obtain the time-frequency domain feature data c of the target.

[0058] Step 5: Perform preliminary classification of the target using time-domain data (preliminary classification refers to the initial determination of whether the radar intermediate frequency output data is collected as a vehicle or a person), and obtain a rough classification and identification result of whether the target is a vehicle or a person.

[0059] Step 6: Use the speed information b for secondary precise classification. If b is greater than 15 km / h, the target is identified as a vehicle; if b is less than 2 km / h, the target is identified as a person. If b is between 2 km / h and 15 km / h, further steps are needed to determine the target classification result.

[0060] Step 7: For echo data of b between 2km / h and 15km / h, if the time-frequency feature data c is an acceleration slope (determined by edge detection and zero-value detection), then the target is determined to be a car; otherwise, it is determined to be a person.

[0061] Example 2

[0062] Figure 2This is a schematic diagram of the target classification and recognition system provided in Embodiment 2 of the present invention. Figure 2 As shown, the target classification and recognition system in this embodiment includes:

[0063] The radar intermediate frequency output data acquisition module 201 is used to acquire radar intermediate frequency output data; the radar intermediate frequency output data is the intermediate frequency sine wave signal of radar data; the radar intermediate frequency output data includes information about the target to be classified.

[0064] The zero intermediate frequency signal determination module 202 is used to perform down-conversion processing on the radar intermediate frequency output data to obtain the zero intermediate frequency signal.

[0065] The frequency domain feature data determination module 203 is used to obtain frequency domain feature data based on the zero intermediate frequency signal using the Fourier transform method.

[0066] The judgment module 204 is used to determine whether the frequency domain feature data meets the preset threshold.

[0067] The first execution module 205 is used to, if so, use the short-time Fourier transform method to obtain time-frequency domain feature data based on the zero intermediate frequency signal, and classify the target to be classified based on the time-frequency domain feature data to obtain the classification result of the target to be classified.

[0068] The second execution module 206 is used to classify the target to be classified based on the frequency domain feature data if no, and obtain the classification result of the target to be classified.

[0069] As an optional implementation, the frequency domain feature data determination module 203 specifically includes:

[0070] The spectrum transformation unit is used to perform spectrum transformation on the zero intermediate frequency signal using the Fourier transform method to obtain multiple frequency points and corresponding amplitudes.

[0071] The frequency domain feature data determination unit is used to determine frequency domain feature data based on the frequency point corresponding to the maximum amplitude.

[0072] Example 3

[0073] An electronic device, comprising:

[0074] One or more processors.

[0075] A storage device on which one or more programs are stored.

[0076] When one or more programs are executed by one or more processors, the one or more processors implement the target classification and recognition method as in Example 1.

[0077] Example 4

[0078] A storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the target classification and recognition method as described in Example 1.

[0079] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0080] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A target classification and recognition method, characterized in that, The method includes: Acquire radar intermediate frequency output data; the radar intermediate frequency output data is an intermediate frequency sine wave signal of radar data; the radar intermediate frequency output data includes information about the target to be classified; The radar intermediate frequency output data is down-converted to obtain a zero intermediate frequency signal; Frequency domain feature data are obtained from the zero intermediate frequency signal using the Fourier transform method. Determine whether the frequency domain feature data meets a preset threshold; If so, the short-time Fourier transform method is used to obtain time-frequency domain feature data based on the zero intermediate frequency signal, and the target to be classified is classified based on the time-frequency domain feature data to obtain the classification result of the target to be classified. If not, the target to be classified is classified according to the frequency domain feature data to obtain the classification result of the target to be classified; Before classifying the target based on the time-frequency domain feature data and classifying the target based on the frequency domain feature data, the method further includes: Using the maximum likelihood estimation method, time-domain characteristic data are obtained based on the zero intermediate frequency signal.

2. The target classification and recognition method according to claim 1, characterized in that, The process of obtaining frequency domain feature data from the zero-IF signal using the Fourier transform method specifically includes: The zero-IF signal is subjected to spectral transformation using the Fourier transform method to obtain multiple frequency points and corresponding amplitudes; The frequency domain feature data is determined based on the frequency point corresponding to the maximum amplitude.

3. A target classification and recognition system, characterized in that, The system includes: The radar intermediate frequency output data acquisition module is used to acquire radar intermediate frequency output data; the radar intermediate frequency output data is an intermediate frequency sine wave signal of radar data; the radar intermediate frequency output data includes information about the target to be classified; The zero intermediate frequency signal determination module is used to perform down-conversion processing on the radar intermediate frequency output data to obtain a zero intermediate frequency signal. The frequency domain feature data determination module is used to obtain frequency domain feature data based on the zero intermediate frequency signal using the Fourier transform method. The judgment module is used to determine whether the frequency domain feature data meets a preset threshold. The first execution module is used to, if so, use the short-time Fourier transform method to obtain time-frequency domain feature data based on the zero intermediate frequency signal, and classify the target to be classified based on the time-frequency domain feature data to obtain the classification result of the target to be classified. The second execution module is used to classify the target to be classified based on the frequency domain feature data if no, and obtain the classification result of the target to be classified. Before classifying the target based on the time-frequency domain feature data and classifying the target based on the frequency domain feature data, the method further includes: Using the maximum likelihood estimation method, time-domain characteristic data are obtained based on the zero intermediate frequency signal.

4. The target classification and recognition system according to claim 3, characterized in that, The frequency domain feature data determination module specifically includes: The spectrum transformation unit is used to perform spectrum transformation on the zero intermediate frequency signal using the Fourier transform method to obtain multiple frequency points and corresponding amplitudes; The frequency domain feature data determination unit is used to determine the frequency domain feature data based on the frequency point corresponding to the maximum amplitude.

5. An electronic device, characterized in that, include: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the target classification and recognition method as described in any one of claims 1 to 2.

6. A storage medium, characterized in that, It stores a computer program, wherein the computer program, when executed by a processor, implements the target classification and recognition method as described in any one of claims 1 to 2.

Images