Wang Haili, Zhang Muye, Zhang Linghao, Zhu Xiaoxiao, Cao Qixin
The State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai 200240, China.
SJTU Paris Elite Institute of Technology, Shanghai Jiao Tong University, Shanghai 200240, China.
Sensors (Basel). 2025 Jul 4;25(13):4169. doi: 10.3390/s25134169.
Robust and efficient contactless human-machine interaction is critical for integrated sensor systems in clinical settings, demanding low-power solutions adaptable to edge computing platforms. This paper presents a real-time hand gesture recognition system using a low-power Frequency-Modulated Continuous Wave (FMCW) radar sensor, featuring a novel Multiple Feature Fusion (MFF) framework optimized for deployment on edge devices. The proposed system integrates velocity profiles, angular variations, and spatial-temporal features through a dual-stage processing architecture: an adaptive energy thresholding detector segments gestures, followed by an attention-enhanced neural classifier. Innovations include dynamic clutter suppression and multi-path cancellation optimized for complex clinical environments. Experimental validation demonstrates high performance, achieving 98% detection recall and 93.87% classification accuracy under LOSO cross-validation. On embedded hardware, the system processes at 28 FPS, showing higher robustness against environmental noise and lower computational overhead compared with existing methods. This low-power, edge-based solution is highly suitable for applications like sterile medical control and patient monitoring, advancing contactless interaction in healthcare by addressing efficiency and robustness challenges in radar sensing for edge computing.
强大且高效的非接触式人机交互对于临床环境中的集成传感器系统至关重要，这需要适用于边缘计算平台的低功耗解决方案。本文提出了一种使用低功耗调频连续波（FMCW）雷达传感器的实时手势识别系统，其具有针对边缘设备部署进行优化的新型多特征融合（MFF）框架。所提出的系统通过双阶段处理架构集成速度剖面、角度变化和时空特征：自适应能量阈值检测器对手势进行分割，随后是注意力增强神经分类器。创新之处包括针对复杂临床环境优化的动态杂波抑制和多径消除。实验验证表明该系统具有高性能，在留一法交叉验证下实现了98%的检测召回率和93.87%的分类准确率。在嵌入式硬件上，该系统以28帧/秒的速度进行处理，与现有方法相比，对环境噪声具有更高的鲁棒性且计算开销更低。这种基于边缘的低功耗解决方案非常适合无菌医疗控制和患者监测等应用，通过解决边缘计算雷达传感中的效率和鲁棒性挑战，推动了医疗保健中的非接触式交互。
