A Radar Target Recognition Method Based on Time-Frequency Distribution Instantaneous Frequency Edge Features
A technology of instantaneous frequency and edge features, which is applied in the field of time-frequency distribution characteristics of radar high-resolution range images and instantaneous frequency edge characteristics, and can solve the problems that the recognition effect needs to be further improved, the amount of calculation is large, and the time-frequency distribution characteristics of HRRP are redundant.
Active Publication Date: 2021-07-06
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] Radar high-resolution range profile (HRRP) is a typical non-stationary signal. Traditional HRRP-based identification methods mostly use HRRP's simple time domain or frequency domain as identification features, although there are also time-frequency distribution features based on HRRP for identification. , but the HRRP time-frequency distribution features are redundant and the amount of calculation is large, and the recognition effect needs to be further improved
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0036] Step 1: Construct a training sample Y, and perform translation sensitivity and amplitude sensitivity elimination processing.
[0037] The HRRP data used in the present invention are field-measured data using high-resolution broadband radars by a domestic research institute, including "Jacques-42" medium-sized jet aircraft, "Certificate" small jet aircraft, and "An-26" small propeller aircraft. HRRP data for each target. The HRRP data for each target is a matrix with 520 rows and 256 columns. Among them, the number of rows of 520 means that there are 520 range images, and the number of columns of 256 means that each range image has 256 range units.
[0038] In order to explore the influence of the ratio of the number of training samples to the number of test samples (training-test ratio) on the recognition effect, the training-test ratios were 1:3, 1:2, 1:1, 2:1, and 3:1 respectively. Conduct recognition experiments. With a training-test ratio of 1:1, that is, each ta...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a radar target recognition method based on time-frequency distribution instantaneous frequency edge characteristics, belongs to the technical field of radar target recognition, and relates to technologies of radar high-resolution range image time-frequency distribution characteristics and instantaneous frequency edge characteristics. In this method, firstly, the radar range image is preprocessed to eliminate its translation sensitivity and amplitude sensitivity; then, the Wigner-Ville distribution of the range image is obtained, and then the cross-interference in the Wigner-Ville distribution is suppressed by time-frequency rearrangement technology Item; Next, obtain the instantaneous frequency edge features of the time-frequency distribution after the time-frequency rearrangement, and use the sum principal component analysis algorithm to obtain the feature matrix of the instantaneous frequency edge features; finally, use the K-nearest neighbor classifier to classify the test samples. In this way, the method not only utilizes the information of time and frequency changes of the range image, but also avoids the problems of information redundancy and large amount of calculation caused by directly using the time-frequency distribution as the recognition feature, and improves the target recognition rate.
Description
technical field [0001] The invention belongs to the technical field of radar target recognition, and relates to the technology of time-frequency distribution characteristics and instantaneous frequency edge characteristics of radar high-resolution range images. Background technique [0002] The frequency of a stationary signal is single and constant, and its distribution parameters or distribution laws do not change over time. The Fourier transform of the stationary signal can analyze its frequency domain information, and the frequency domain signal can also be transformed into the time domain through the inverse Fourier transform. The frequency and statistical characteristics of the unsteady signal (transient signal) will change with time, and its frequency will change. The Fourier transform gives the distribution of the signal frequency on the frequency spectrum, and gives the time information of the frequency, that is, the transform result only shows whether there is a c...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G01S7/41
CPCG01S7/41
Inventor 于雪莲顾成玲赵林森唐永昊曲学超
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA