Super-Resolution Approach for Low-Cost and Low-Resolution Radars
IEEE Transactions on Aerospace and Electronic Systems · 2026 · 62 · 7326-7344
DOI: 10.1109/taes.2026.3670095 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Aerospace and Electronic Systems, 2026. Verfasst von Netanel Blumenfeld und 2 weiteren Autor:innen. Die Arbeit nennt 73 Literaturangaben. Gefördert von: Israel Science Foundation.
Abstract (Originalsprache)
Low-cost radars have emerged as attractive alternatives to optical sensors for consumer applications due to their robustness and inherent privacy. However, their limited spatial resolution constrains their applicability to tasks requiring fine motion analysis. This work proposes a deep learning-based super-resolution (SR) framework that enhances radar range-Doppler maps with task-specific fidelity. The proposed approach integrates a spatially adaptive feature modulation network and introduces classification-guided training that selectively refines gesture-relevant features. Unlike conventional image SR techniques focused on perceptual quality, the proposed approach jointly optimizes SR and classification objectives to improve radar-based hand gesture recognition (HGR). Three scalable architectures, SuperGestNet, MultiSuperGestNet, and RecursiveSuperGestNet, are proposed, offering tradeoffs between accuracy, computational complexity, and memory. Experiments on real radar data demonstrate substantial improvements in HGR accuracy over conventional SR methods and baseline classifiers, even surpassing high-resolution models in some settings. This task-aware SR paradigm enables the practical deployment of low-cost, low-resolution radars for various consumer applications.
Förderung
- Israel Science Foundation
Zitieren
APA
Blumenfeld, N., Stainvas, I., & Bilik, I. (2026). Super-Resolution Approach for Low-Cost and Low-Resolution Radars. IEEE Transactions on Aerospace and Electronic Systems, 62, 7326-7344. https://doi.org/10.1109/taes.2026.3670095
Vancouver
Blumenfeld N, Stainvas I, Bilik I. Super-Resolution Approach for Low-Cost and Low-Resolution Radars. IEEE Transactions on Aerospace and Electronic Systems. 2026;62:7326-7344. doi:10.1109/taes.2026.3670095
BibTeX
@article{Blumenfeld2026,
author = {Blumenfeld, Netanel and Stainvas, Inna and Bilik, Igal},
title = {Super-Resolution Approach for Low-Cost and Low-Resolution Radars},
journal = {IEEE Transactions on Aerospace and Electronic Systems},
year = {2026},
volume = {62},
pages = {7326--7344},
doi = {10.1109/taes.2026.3670095}
}
EUVIMED