Non-intrusive Human Pose Sensing: A Comparative Review of Wi-Fi, Radar, and Inertial Sensing
DOI:
https://doi.org/10.62051/5e8szh21Keywords:
Non-intrusive human sensing; Wi-Fi sensing; Radar; Wearable sensors; Qualitative benchmarking.Abstract
Non-intrusive human sensing has gained rapid momentum across smart homes, rehabilitation, safety monitoring and other applications. However, heterogeneous evaluation practices hinder fair cross-technology comparison. Thus, this paper focuses on three representative technologies—wearable sensors, radar sensing, and Wi-Fi sensing and consolidates reported findings onto a unified six-dimensional scheme: Accuracy, Response Speed, Cost, Privacy, Convenience, and Coverage. Those heterogeneous metrics are qualitatively mapped to high, medium, Low and visualized with radar charts. Based on these diagrams, this paper introduces a scenario requirement versus technology performance overlap procedure for scenario selection: the preferred option minimizes performance waste relative to the scenario’s needs while satisfying all critical-dimension requirements. An example of industrial robot collision detection demonstrates the workflow’s practicality and reusability. The paper also discusses limitations of the review methodology and future improvements, such as developing decision-making software. In conclusion, this paper provides a structured and actionable path for qualitative benchmarking and scenario-driven technology selection in non-intrusive human sensing.
Downloads
References
[1] Taylor L, Ding X, Clifton D, et al. Wearable vital signs monitoring for patients with asthma: A review. IEEE Sensors Journal, 2023, 23 (3): 1734 - 1751. DOI: https://doi.org/10.1109/JSEN.2022.3224411
[2] Yi X, Zhou Y, Habermann M, et al. Real-time 3D human translation and pose estimation with 6 IMUs. arXiv preprint arXiv: 2105. 04605, 2021.
[3] Islam S M M. Radar-based remote physiological sensing: Progress, challenges, and opportunities. Frontiers in Physiology, 2022, 13: 955208. DOI: https://doi.org/10.3389/fphys.2022.955208
[4] Arasteh E, Doclo S, Pollin S. Ultra-wideband radar for simultaneous and unobtrusive monitoring of respiratory and cardiovascular parameters: A systematic review. Sensors, 2023, 23 (6): 1301. DOI: https://doi.org/10.3390/s23187665
[5] Zhou Y, Xu C, Zhao L, et al. CSI-Former: Pay more attention to pose estimation with WiFi. Entropy, 2023, 25 (1): 20. DOI: https://doi.org/10.3390/e25010020
[6] Yan K, Wang F, Qian B, et al. Person-in-WiFi 3D: End-to-end multi-person 3D pose estimation with Wi-Fi. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. DOI: https://doi.org/10.1109/CVPR52733.2024.00098
[7] Geng J, Huang D, De la Torre F. DensePose from WiFi. arXiv preprint arXiv:2301.00250, 2023.
[8] Yan K, Wang F, et al. DT-POSE: Improving Wi-Fi-based 3D human pose estimation via diffusion transformer. arXiv preprint arXiv:2502.14777, 2025.
[9] Song Y, Jin T, Dai Y, et al. Through-wall human pose reconstruction via UWB MIMO radar and 3D CNN. Remote Sensing, 2021, 13 (2): 241. DOI: https://doi.org/10.3390/rs13020241
[10] Zhang Y, Huang R, Zhao X, et al. MD-Pose: Human pose estimation for single-channel UWB radar. IEEE Transactions on Biometrics, Behavior, and Identity Science, 2023, 5: 449 - 463. DOI: https://doi.org/10.1109/TBIOM.2023.3265206
[11] Natarajan A, Su H-W, Heneghan C, et al. Measurement of respiratory rate using wearable devices and applications to COVID-19 detection. npj Digital Medicine, 2021, 4: 136. DOI: https://doi.org/10.1038/s41746-021-00493-6
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Transactions on Computer Science and Intelligent Systems Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
