EUVIMEDEUVIMED entdecken
Crossref

Deep Radar Perception Network With RTK Supervision for Slow-Moving UAV Detection

Ziyi Jiang, Feng Ke, Yikui Zhai, Jianhong Zhou, Pasquale Coscia, Angelo Genovese, Xiu Yin Zhang

IEEE Transactions on Instrumentation and Measurement · 2026 · 75 · 2510318-2510318

DOI: 10.1109/tim.2026.3687291 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Instrumentation and Measurement, 2026. Verfasst von Ziyi Jiang und 6 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Gefördert von: Guangdong S&T Program, the Science and Technology (S&T) Program of Guangdong Province, S&T Program of Guangzhou.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable detection of slow-moving unmanned aerial vehicles (UAVs) under low signal-to-noise ratio (SNR) conditions remains a core challenge for the next-generation intelligent sensing systems. We propose AirSentinel, a novel deep radar perception network to leverage frame-synchronized real-time kinematic (RTK)-derived geocoordinates for supervised learning, bridging the gap between image- and radar-based methods. To address the challenge of weak feature discrimination and energy leakage in radar data, we propose a local search and guard band (LSGB) mechanism that identifies Doppler peaks across coherent processing intervals (CPIs). We further propose an information weight calibration adapter (IWCA) and a global temporal modeling head to facilitate feature alignment across views and capture long-range temporal dependencies, respectively. To mitigate data scarcity, an object transformation and generation scheme is introduced, significantly boosting data diversity and annotation efficiency. Extensive experiments on the newly curated radarUAV-24K dataset demonstrate that AirSentinel outperforms state-of-the-art methods in both accuracy and real-time performance. This work establishes a robust paradigm for radar-based object detection, with implications for autonomous monitoring and urban airspace security.

Förderung

  • Guangdong S&T Program
  • the Science and Technology (S&T) Program of Guangdong Province
  • S&T Program of Guangzhou
  • Guangxi Key Research and Development Program

Zitieren

APA

Jiang, Z., Ke, F., Zhai, Y., Zhou, J., Coscia, P., Genovese, A., & Zhang, X. Y. (2026). Deep Radar Perception Network With RTK Supervision for Slow-Moving UAV Detection. IEEE Transactions on Instrumentation and Measurement, 75, 2510318-2510318. https://doi.org/10.1109/tim.2026.3687291

Vancouver

Jiang Z, Ke F, Zhai Y, Zhou J, Coscia P, Genovese A, et al. Deep Radar Perception Network With RTK Supervision for Slow-Moving UAV Detection. IEEE Transactions on Instrumentation and Measurement. 2026;75:2510318-2510318. doi:10.1109/tim.2026.3687291

BibTeX
@article{Jiang2026,
  author = {Jiang, Ziyi and Ke, Feng and Zhai, Yikui and Zhou, Jianhong and Coscia, Pasquale and Genovese, Angelo and Zhang, Xiu Yin},
  title = {Deep Radar Perception Network With RTK Supervision for Slow-Moving UAV Detection},
  journal = {IEEE Transactions on Instrumentation and Measurement},
  year = {2026},
  volume = {75},
  pages = {2510318--2510318},
  doi = {10.1109/tim.2026.3687291}
}
Kostenlos starten →