Extracting micro-Doppler (m-D) curves from time-frequency distributions (TFD) often encounters difficulties due to signal overlap, component discontinuity, and high noise levels. These challenges limit the effectiveness of such extractions in accurately representing the underlying signal characteristics. Addressing these limitations, this article introduces a deep learning approach—the recurrent self-attention separation network (RSS Net). The network separates independent m-D curves by dividing the TFD of multicomponent signals into distinct masks for each signal component. These masks can be integrated with traditional methods or directly used for such estimations. We have compared and analyzed the performance of both approaches under various conditions. The network's effectiveness has been validated through extensive testing on the m-D curves of spatial conical targets in complex scenarios. Our experimental results emphatically demonstrate the network's superior performance over existing methodologies.
Micro-Doppler Separation Based on RSS Net
IEEE Transactions on Aerospace and Electronic Systems ; 61 , 2 ; 4573-4583
01.04.2025
6207890 byte
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
A kinect-based human micro-doppler simulator
IEEE | 2015
|CORRESPONDENCE - Separation of Target Rigid Body and Micro-Doppler Effects in ISAR Imaging
Online Contents | 2006
|