Radar target recognition method based on micro-Doppler feature extraction and deep learning

Abstract

The invention provides a radar target recognition method based on micro-Doppler feature extraction and deep learning. The new method can be divided into three stages of step 1, a micro-Doppler featureextraction stage: using an MSTFT-WVD algorithm to obtain a micro-Doppler feature time-frequency graph of a target; step 2, a classifier model training phase: dividing the time-frequency graph of theknown category information obtained in the first stage into a training data set and a test data set, utilizing an original deep learning model for training, and continuously adjusting parameters to obtain the optimal deep learning model for radar target recognition; step 3, an identification phase of an unknown target: using the MSTFT-WVD algorithm to obtain a micro-Doppler feature time-frequencygraph of the unknown target, inputting the time-frequency graph to the trained deep learning model in the second stage to obtain the category information of the unknown target. The radar target recognition method can achieve higher recognition accuracy rate.

Description

technical field [0001] The invention relates to the technical field of radar target recognition, in particular to a radar target recognition method based on micro-Doppler feature extraction and deep learning. Background technique [0002] The different tasks performed by different targets on the battlefield determine the difference in their threat levels, so the identification of battlefield targets is of great significance. At present, the vehicle-mounted radar of a certain type of radar reconnaissance vehicle installed by our army's armored troops is a pulse Doppler radar. The identification of the target is usually determined by humans. After the target is found, the scout listens to the target through the headset. Echo the audio signal to identify the target. This method has high requirements on the professional quality of scouts, especially for scouts who have not undergone long-term special training, it is more prone to misjudgment or misjudgment, the correct recognit...

AI Technical Summary

Problems solved by technology

[0007] (1) When using the time-frequency analysis method for micro-Doppler feature extraction, the results obtained by the linear time-frequency analysis method usually have the problem of low time-frequency resolution, such as STFT, Gabor transform and other methods; quadratic time-frequency analysis The results obtained by the method usually have the problem of cross-item interference, such as Wigner-Ville Distribution (WVD), Pseudo Wigner-Ville Distribution (PWVD), etc.; Problems with too high complexity, such as Reassigned Smoothed Pseudo Wigner-VilleDistribution (RSPWVD), etc.

[0008] (2

Images