太赫兹科学与电子信息学报2025，Vol.23Issue(8)：804-815,12.DOI:10.11805/TKYDA2025114
基于改进MobileViT模型的毫米波雷达动态手势识别方法
A dynamic hand gesture recognition method of mmWave radar based on improved MobileViT model
摘要
Abstract
Gesture recognition using millimeter-wave(mmWave)radar offers advantages such as contact-free operation,high detection accuracy,privacy preservation,and robust environmental adaptability,making it promising for industrial human-machine interaction and smart-home applications.However,existing mmWave-based dynamic-gesture recognition approaches suffer from high model complexity,large computational cost,low accuracy,and slow inference speed.To address these challenges,a lightweight gesture-recognition method is proposed based on an improved MobileViT network that maintains high accuracy while significantly reducing computational complexity for deployment on embedded devices.Firstly,dynamic-gesture echoes are captured with an mmWave radar.After suppressing device noise and background clutter,the data are reorganized into a 3-D matrix(sample points×chirps×frames).Range-time and Doppler-time maps are then generated via Fourier transform and fed into the enhanced MobileViT model for feature extraction and fusion,yielding the final gesture classification.Experimental results show that the proposed MobileViT model has only 0.167 M of parameter space complexity and 0.253 GFLOPs of computational complexity.Evaluated on a 12-class dynamic-gesture dataset,the method achieves 99.31%of recognition accuracy,demonstrating its effectiveness.关键词
手势识别/人机交互/毫米波雷达/轻量级神经网络Key words
gesture recognition/human-computer interaction/mmWave radar/lightweight neural network分类
信息技术与安全科学引用本文复制引用
葛志洲,张向群,申佳文,杜根远,刘锋涛..基于改进MobileViT模型的毫米波雷达动态手势识别方法[J].太赫兹科学与电子信息学报,2025,23(8):804-815,12.基金项目
河南省科技厅科技攻关资助项目(242102210067) （242102210067）
河南省重点研发资助项目(241111212500) （241111212500）
