EUVIMEDEUVIMED entdecken
Crossref

Doppler-Domain Warping and Resampling for Semi-Static Human Occupancy Detection Using Low-Resolution SIMO FMCW Radar

Huy Trinh, Elliot Creager, George Shaker

IEEE Transactions on Radar Systems · 2026 · 4 · 855-870

DOI: 10.1109/trs.2026.3680942 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Radar Systems, 2026. Verfasst von Huy Trinh und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: Mitacs, Natural Sciences and Engineering Research Council of Canada.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Radar-based human activity recognition is a promising privacy-preserving alternative to vision and wearable sensors, especially in sensitive environments such as long-term-care (LTC) facilities. However, reliable detection of quasi-static human presence, where subtle micromotions such as small postural sway, breathing, small limb readjustments, etc., concentrate their energy around near-zero Doppler using low-resolution radar, remains challenging. In this work, we propose range-angle-based semi-static occupancy (RASSO), an invertible Doppler-domain nonlinear remapping layer that resamples the slow-time fast Fourier transform (FFT) (Doppler) axis to densify the sampling grid around near-zero Doppler before adaptive Capon beamforming. This produces range-azimuth (RA) feature maps with higher signal-to-noise ratios (SNRs), resulting in sharpened target peaks and reduced background variance. On a real dataset collected in a nursing home using short-range single-input and multiple-output (SIMO) frequency-modulated continuous-wave (FMCW) radar, RASSO consistently yields higher contrast RA maps that are easier to threshold and more informative for downstream models. Under cell-averaging constant false alarm rate (CA-CFAR), RASSO-enhanced RA (RASSO-RA) achieves the highest detection-curve area under the curve (AUC = 0.981) and the best recall at false alarm rates (FARs) of 1% and 5% (0.920 and 0.947), compared to conventional Capon beam formation and a recent state-of-the-art baseline. Training on RASSO-RA further improves data-driven methods: a frame-based SimpleCNN reaches 95%–99% accuracy across subjects, while a sequence-based convolutional neural network (CNN)-long short-term memory (LSTM) achieves 99.4%–99.6% accuracy, with paired session-level bootstrap analysis confirming statistically significant macro-F1 improvements of 2.6–3.6 percentage points (95% confidence intervals strictly above zero) over the nonwarped baseline.

Förderung

  • Mitacs
  • Natural Sciences and Engineering Research Council of Canada

Zitieren

APA

Trinh, H., Creager, E., & Shaker, G. (2026). Doppler-Domain Warping and Resampling for Semi-Static Human Occupancy Detection Using Low-Resolution SIMO FMCW Radar. IEEE Transactions on Radar Systems, 4, 855-870. https://doi.org/10.1109/trs.2026.3680942

Vancouver

Trinh H, Creager E, Shaker G. Doppler-Domain Warping and Resampling for Semi-Static Human Occupancy Detection Using Low-Resolution SIMO FMCW Radar. IEEE Transactions on Radar Systems. 2026;4:855-870. doi:10.1109/trs.2026.3680942

BibTeX
@article{Trinh2026,
  author = {Trinh, Huy and Creager, Elliot and Shaker, George},
  title = {Doppler-Domain Warping and Resampling for Semi-Static Human Occupancy Detection Using Low-Resolution SIMO FMCW Radar},
  journal = {IEEE Transactions on Radar Systems},
  year = {2026},
  volume = {4},
  pages = {855--870},
  doi = {10.1109/trs.2026.3680942}
}
Kostenlos starten →