Deep learning clutter suppression improves multistatic ISAC target estimates
Original title: Multistatic ISAC with Deep Learning-Based Clutter Suppression for 5G and Beyond
Residual and attention networks beat conventional baselines on position and velocity under dense dynamic clutter.
A paper models distributed clutter in multistatic integrated sensing and communications that uses 5G and beyond signals of opportunity. Conventional clutter-suppression baselines show limited robustness when clutter is strong. Residual and attention-enhanced networks improve target position and velocity estimates across diverse clutter conditions.
- Multistatic receivers widen sensing coverage but clutter hurts range and Doppler estimates.
- Clutter is modeled as random scatterers with varying Doppler and radar cross section.
- Networks enhance target responses directly from clutter-contaminated observations.
From the original article
1 min read at arxiv.orgIntegrated sensing and communications (ISAC) systems using 5G and beyond signals of opportunity enable joint wireless sensing and communication using shared infrastructure and spectrum resources.
By Yalin E. Sagduyu · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.