EUVIMEDEUVIMED entdecken
Crossref

RF-ADMM-Net for Sparse Aperture ISAR Imaging Under Low Signal-to-Noise Ratio

Yu Wu, Ruize Li, Yanbo Mai, Shuanghui Zhang

IEEE Transactions on Aerospace and Electronic Systems · 2026 · 62 · 5446-5461

DOI: 10.1109/taes.2026.3658281 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Aerospace and Electronic Systems, 2026. Verfasst von Yu Wu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sparse aperture (SA) and low signal-to-noise ratio (SNR) echo are common challenges in inverse synthetic aperture radar (ISAR) systems. Compressive sensing (CS) methods are widely utilized to reconstruct ISAR images from sparse echoes. Combined with deep learning, unfolding nets based on different CS methods are proposed to obtain higher reconstruction accuracy in the SA case. However, these nets are not applicable for the sparse echo under low SNR; the denoising threshold is difficult to set appropriately for the balance between noise removal and structure preservation. To address the issue above, we proposed a random fields-based alternating direction method of multipliers net (RF-ADMM-Net). We design a segmentation method for the intermediate ISAR image based on a random field (RF) model, which can operate efficiently with better migration, robustness, and stability to noisy ISAR images. Furthermore, the segmentation is taken to assist the denoising layers in distinguishing the target region from the background area. The denoising layers set different thresholds for target and noise regions to retain more information of the target while thoroughly denoising. The experimental results based on both simulated and measured data indicate the applicability and robustness of the RF-Net to noisy ISAR images that suffer from SA and low SNR, and show high reconstruction accuracy for ISAR images under SA and low SNR of the RF-ADMM-Net.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wu, Y., Li, R., Mai, Y., & Zhang, S. (2026). RF-ADMM-Net for Sparse Aperture ISAR Imaging Under Low Signal-to-Noise Ratio. IEEE Transactions on Aerospace and Electronic Systems, 62, 5446-5461. https://doi.org/10.1109/taes.2026.3658281

Vancouver

Wu Y, Li R, Mai Y, Zhang S. RF-ADMM-Net for Sparse Aperture ISAR Imaging Under Low Signal-to-Noise Ratio. IEEE Transactions on Aerospace and Electronic Systems. 2026;62:5446-5461. doi:10.1109/taes.2026.3658281

BibTeX
@article{Wu2026,
  author = {Wu, Yu and Li, Ruize and Mai, Yanbo and Zhang, Shuanghui},
  title = {RF-ADMM-Net for Sparse Aperture ISAR Imaging Under Low Signal-to-Noise Ratio},
  journal = {IEEE Transactions on Aerospace and Electronic Systems},
  year = {2026},
  volume = {62},
  pages = {5446--5461},
  doi = {10.1109/taes.2026.3658281}
}
Kostenlos starten →