Micro Gesture Recognition with Multi-Dimensional Feature Fusion and CQ-MobileNetV3 Using FMCW Radar
Sensors · 13.11.2025 · 25 (22) · 6949
DOI: 10.3390/s25226949 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 13.11.2025. Verfasst von Wei Xue und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation, China University of Geosciences, Wuhan 430074, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Radar-based gesture recognition technology has gained increasing attention in the context of contactless human–computer interaction (HCI). Micro gestures have smaller motion amplitudes and shorter duration compared with traditional gestures, which increases the difficulty of motion feature extraction. In addition, improving recognition accuracy while maintaining low computational and storage costs is also a challenge. In this paper, a micro gesture recognition method combining multi-dimensional feature fusion and a lightweight CQ-MobileNetV3 network is proposed. For feature extraction, the range–time map, velocity–time map, and angle–time map of gestures are first constructed. Then, normalization and adaptive filtering are performed to refine the three maps. Finally, the three refined maps are fused to form a range–velocity–angle–time map, which can accurately describe the motion characteristics of gestures. For recognition, a lightweight CQ-MobileNetV3 network is designed. First, the network structure of MobileNetV3 is optimized to reduce computational complexity. Then, the improved convolutional block attention module (CBAM) and the improved self-attention (SA) module are constructed and integrated into different bottleneck blocks to improve recognition accuracy. A series of experiments are conducted with a 77 GHz frequency-modulated continuous wave (FMCW) radar. The results indicate that CQ-MobileNetV3 achieves a recognition accuracy of 97.16% for 14 micro gestures, with a parameter count of 0.207 M and a computational complexity of 0.027 GFLOPs, surpassing several other deep neural networks.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Automation, China University of Geosciences, Wuhan 430074, China.
- Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems, Wuhan 430074, China.
- Engineering Research Center of Intelligent Technology for Geo-Exploration, Ministry of Education, Wuhan 430074, China.
ORCID-Profile: Li Liu
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Xue, W., Wang, R., Wei, J., & Liu, L. (2025). Micro Gesture Recognition with Multi-Dimensional Feature Fusion and CQ-MobileNetV3 Using FMCW Radar. Sensors, 25(22), 6949. https://doi.org/10.3390/s25226949
Vancouver
Xue W, Wang R, Wei J, Liu L. Micro Gesture Recognition with Multi-Dimensional Feature Fusion and CQ-MobileNetV3 Using FMCW Radar. Sensors. 2025;25(22):6949. doi:10.3390/s25226949
BibTeX
@article{Xue2025,
author = {Xue, Wei and Wang, Rui and Wei, Jianyun and Liu, Li},
title = {Micro Gesture Recognition with Multi-Dimensional Feature Fusion and CQ-MobileNetV3 Using FMCW Radar},
journal = {Sensors},
year = {2025},
volume = {25},
number = {22},
pages = {6949},
doi = {10.3390/s25226949}
}
EUVIMED