A new method for radar emitter individual identification based on VMD and multi-image feature combination
Shuang Yu, Y. Zheng, Jing Wang, Jia‐Bin Huang · IET conference proceedings. · 2023
In order to solve the difficulty of extracting and selecting individual features manually in radar emitter individual identification, and further improve the accuracy of individual identification. A radar emitter individual identification method based on variational mode decomposition and multiple image features combination is proposed in this paper. Firstly, the radar signal is decomposed by variational mode decomposition. Then, the feature extraction in transform domain is performed on the obtained modal components, and they are reconstructed into VMD-Hilbert spectrum and VMD-envelope spectrum. Finally, the image is sent to the SEResNet50-based feature fusion and recognition network to realize radar emitter individual identification. Through the verification of the measured data, the recognition accuracy of six types of individuals can reach more than 90% when the signal-to-noise ratio is 20db, which has a relatively ideal recognition result and certain engineering application value.