Metraipolis › archive › dc_c4e207ff4c27

A Universal Raw-IQ Radar Encoder for Cross-Sensor Human Sensing — arXiv:2611.04534

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04534
License (as archived)
CC0-1.0
Archived
2026-11-04T12:42:40.567Z
SHA-256 of the archived text
961d79827bf71fa579f85a112d4a4791ce0ab78fe3f5942417cb78309ad3e146
Stable URL of this page
https://metraipolis.com/documento/dc_c4e207ff4c27

How to cite

A Universal Raw-IQ Radar Encoder for Cross-Sensor Human Sensing — arXiv:2611.04534 — arXiv (en), https://arxiv.org/abs/2611.04534 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c4e207ff4c27 (Metraipolis archive dc_c4e207ff4c27, sha256 961d79827bf71fa579f85a112d4a4791ce0ab78fe3f5942417cb78309ad3e146)
BibTeX
@misc{dcc4e207ff4c27,
  title = {A Universal Raw-IQ Radar Encoder for Cross-Sensor Human Sensing — arXiv:2611.04534},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04534},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c4e207ff4c27; sha256 961d79827bf71fa579f85a112d4a4791ce0ab78fe3f5942417cb78309ad3e146},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04534. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Radar-based human sensing typically relies on end-to-end task-specific models trained on hand-chosen signal projections, which generalize poorly across unseen users, tasks, and hardware. We argue that the dominant signal processing choice, the micro-Doppler spectrogram, is a poor starting point for transfer because it keeps the Doppler axis, which carrier frequency rescales, and discards the angular axis, which carrier frequency leaves unchanged. We instead pretrain a convolutional beta-VAE without labels on clutter-removed raw radar measurements from four platforms spanning 60 and 77 GHz and 4 to 12 virtual antennas, aligned by a unified spectral interpolation grid. For every downstream benchmark the encoder stays frozen, and only a small supervised temporal classifier is trained on its embeddings. We compare against supervised models trained end to end on each benchmark and a pretrained radar foundation model across ten settings covering activity, gesture, sign-language, and gait recognition. When the test users and the radar are seen during training, our encoder is best on all five benchmarks. For users never seen in training, it leads on three of four benchmarks, by 4.8 to 23.2 points. On subject-disjoint gait recognition, it is best for each of the four held-out subjects and 8.3 points above the strongest baseline on average, even though its pretraining excluded every recording of this radar. Excluding the test radar from pretraining costs at most 5.3 points on any benchmark. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.04534 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T12:29:47.394Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).