EUVIMEDEUVIMED entdecken
Crossref

Venus++: Reliable Large-Scale mmWave Radar Data Generation via Few 2D Videos for Lying Pose Gesture Recognition

Yue Ling, Dong Zhao, Kaikai Deng, Zixiao He, Kangwen Yin, Huadong Ma

IEEE Transactions on Mobile Computing · 2026-12 · 25 (12) · 22999-23016

DOI: 10.1109/tmc.2026.3725299 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-12. Verfasst von Yue Ling und 5 weiteren Autor:innen. Die Arbeit nennt 65 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Natural Science Foundation, China Postdoctoral Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Millimeter-wave (mmWave) radar enables privacy-preserving gesture recognition but is limited by a lack of training data, particularly for lying postures. Existing mmWave radar data generation methods are ineffective due to the insufficient availability of 2D video data. To this end, we propose a novel system, Venus++ , that generates realistic radar data for lying postures using few 2D videos, but it faces three key challenges: i) simulating diverse reflected signals, ii) overcoming limited real-world data leading to low data fidelity, and iii) reducing low-quality or redundant generated samples. Venus++ consists of three main components: (i) a gesture sequence generation and signal simulation network , which combines several key modules, movement information extractor , spatio-temporal latent diffusion model , and mmWave signal simulator , to generate various gesture vertex sequences under certain conditions and simulate signal propagation characteristics for obtaining coarse radar data; (ii) a meta-learning domain adaptation network generates realistic radar data with few real-world data via “meta-learning” strategy; and (iii) a newly introduced quality assessment network that evaluates both fidelity and diversity of the generated samples, retaining only high-quality and diverse data for reliable downstream recognition. Extensive experiments on both generated and self-collected datasets demonstrate that Venus++ significantly outperforms state-of-the-art methods in recognizing gestures performed in lying postures.

Förderung

  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation
  • China Postdoctoral Science Foundation

Zitieren

APA

Ling, Y., Zhao, D., Deng, K., He, Z., Yin, K., & Ma, H. (2026). Venus++: Reliable Large-Scale mmWave Radar Data Generation via Few 2D Videos for Lying Pose Gesture Recognition. IEEE Transactions on Mobile Computing, 25(12), 22999-23016. https://doi.org/10.1109/tmc.2026.3725299

Vancouver

Ling Y, Zhao D, Deng K, He Z, Yin K, Ma H. Venus++: Reliable Large-Scale mmWave Radar Data Generation via Few 2D Videos for Lying Pose Gesture Recognition. IEEE Transactions on Mobile Computing. 2026;25(12):22999-23016. doi:10.1109/tmc.2026.3725299

BibTeX
@article{Ling2026,
  author = {Ling, Yue and Zhao, Dong and Deng, Kaikai and He, Zixiao and Yin, Kangwen and Ma, Huadong},
  title = {Venus++: Reliable Large-Scale mmWave Radar Data Generation via Few 2D Videos for Lying Pose Gesture Recognition},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {12},
  pages = {22999--23016},
  doi = {10.1109/tmc.2026.3725299}
}
Kostenlos starten →