TY - JOUR
T1 - Dimension Scaling SR-Net for Super-Resolution Radar Range Profiles
AU - Wang, Ziwen
AU - Wang, Jianping
AU - Li, Pucheng
AU - Ding, Zegang
N1 - Publisher Copyright:
© 1965-2011 IEEE.
PY - 2025
Y1 - 2025
N2 - High-resolution radar range profile (RRP) is crucial for accurate target recognition and scene perception. To get a high-resolution RRP, many methods have been developed, such as multiple signal classification, orthogonal matching pursuit, and a few deep learning-based approaches. Although they break through the Rayleigh resolution limit determined by radar signal bandwidth, these methods either get limited super-resolution capability or work well just in high signal to noise ratio (SNR) scenarios. To overcome these limitations, in this article, an interpretable unfolded neural network for super-resolution RRP super-resolution network with dimension scaling (DSSR-Net) is proposed by integrating the advantages of both model-guided and data-driven models. Specifically, DSSR-Net is designed based on a sparse representation model with dimension scaling, and then trained on a training dataset. Through dimension scaling, DSSR-Net lifts the radar signal into high-dimensional space to extract subtle features of closely spaced objects and suppress the noise of the high-dimensional features. It improves the super-resolving power of closely spaced objects and lowers the SNR requirement of radar signals compared to existing methods. The superiority of the proposed algorithm for super-resolution RRP reconstruction is verified via experiments with both synthetic and measured data.
AB - High-resolution radar range profile (RRP) is crucial for accurate target recognition and scene perception. To get a high-resolution RRP, many methods have been developed, such as multiple signal classification, orthogonal matching pursuit, and a few deep learning-based approaches. Although they break through the Rayleigh resolution limit determined by radar signal bandwidth, these methods either get limited super-resolution capability or work well just in high signal to noise ratio (SNR) scenarios. To overcome these limitations, in this article, an interpretable unfolded neural network for super-resolution RRP super-resolution network with dimension scaling (DSSR-Net) is proposed by integrating the advantages of both model-guided and data-driven models. Specifically, DSSR-Net is designed based on a sparse representation model with dimension scaling, and then trained on a training dataset. Through dimension scaling, DSSR-Net lifts the radar signal into high-dimensional space to extract subtle features of closely spaced objects and suppress the noise of the high-dimensional features. It improves the super-resolving power of closely spaced objects and lowers the SNR requirement of radar signals compared to existing methods. The superiority of the proposed algorithm for super-resolution RRP reconstruction is verified via experiments with both synthetic and measured data.
KW - Dimension scaling
KW - high-resolution radar range profiles (RRP)
KW - interpretable neural network
KW - super-resolution
UR - https://www.scopus.com/pages/publications/105017607216
U2 - 10.1109/TAES.2025.3614600
DO - 10.1109/TAES.2025.3614600
M3 - Article
AN - SCOPUS:105017607216
SN - 0018-9251
VL - 61
SP - 18638
EP - 18652
JO - IEEE Transactions on Aerospace and Electronic Systems
JF - IEEE Transactions on Aerospace and Electronic Systems
IS - 6
ER -