基于毫米波雷达的脚踢动作识别

周晓昀; 张远辉; 陈邵靖; 郑超群

doi:10.11959/j.issn.1000-0801.2025264

您当前的位置：

首页 >

文章列表页 >

基于毫米波雷达的脚踢动作识别

更新时间：2026-01-21

- 基于毫米波雷达的脚踢动作识别
- Kick motion recognition based on millimeter-wave radar
- 电信科学 2026年页码：1-13
- 作者机构：
  
  中国计量大学机电工程学院，浙江杭州 310018
- 作者简介：
  
  [ "周晓昀（2001- ），女，中国计量大学机电工程学院硕士生，主要研究方向为毫米波雷达信号处理和深度学习。" ]
  [ "张远辉（1982- ），男，博士，中国计量大学机电工程学院副教授，主要研究方向为毫米波雷达算法、图像处理技术。" ]
  [ "陈邵靖（2003− ），男，中国计量大学机电工程学院硕士生，主要研究方向为毫米波雷达信号处理。" ]
  [ "郑超群（2001− ），男，中国计量大学机电工程学院硕士生，主要研究方向为毫米波雷达信号处理。" ]
- 基金信息：
  
  浙江省自然科学基金资助项目(LY19F010007)
- DOI：10.11959/j.issn.1000-0801.2025264
  中图分类号： TN958;TP393
- 修回：2025-09-06，
  
  录用：2025-10-17，
  
  网络出版：2026-01-05，
- 稿件说明：
移动端阅览
周晓昀,张远辉,陈邵靖等.基于毫米波雷达的脚踢动作识别[J].电信科学,

ZHOU Xiaoyun,ZHANG Yuanhui,CHEN Shaojing,et al.Kick motion recognition based on millimeter-wave radar[J].Telecommunications Science,
周晓昀,张远辉,陈邵靖等.基于毫米波雷达的脚踢动作识别[J].电信科学, DOI：10.11959/j.issn.1000−0801.2025264.

ZHOU Xiaoyun,ZHANG Yuanhui,CHEN Shaojing,et al.Kick motion recognition based on millimeter-wave radar[J].Telecommunications Science, DOI：10.11959/j.issn.1000−0801.2025264.

摘要

近年来，基于毫米波雷达的脚踢动作识别作为一种免手操作的人机交互技术，在智能家居和车载应用等领域展现出重要应用价值。然而，复杂环境下的静态干扰（如墙壁、石柱及天线耦合干扰）和动态干扰（如行人运动、肢体微动）仍对识别精度构成挑战。为实现高精度、稳健识别，提出一种融合干扰抑制与深度学习的识别方法。该方法通过向量均值相消与动目标显示（moving target indication，MTI）抑制静态干扰，并结合多普勒加权、恒虚警率（constant false alarm rate，CFAR）检测、密度聚类（density-based spatial clustering of applications with noise，DBSCAN）以及连通域约束消除动态干扰。随后，提取多帧距离-多普勒图（range-Doppler map，RDM）和距离-角度图（range-angle map，RAM）作为模型输入，构建基于卷积神经网络（convolutional neural network，CNN）、多头自注意力（multi-head self-attention，MHSA）以及简化时序卷积网络（simplified temporal convolutional network，STCN）的双流CNN-MHSA-STCN模型，用于完成动作识别。实验表明，该方法在自采数据集上的识别精度超过98%，在复杂环境中具备较高的精度与鲁棒性。

Abstract

In recent years

millimeter-wave radar-based kick motion recognition has attracted significant attention as a hands-free human-computer interaction technology

demonstrating considerable value in applications such as smart home systems and automotive interfaces. However

in complex environments

both static interference (e.g.

walls

pillars

and antenna coupling effects) and dynamic interference (e.g.

pedestrian movements and subtle limb motions) continue to present substantial challenges to recognition accuracy. To achieve high-precision and robust recognition

an integrated method combining interference suppression and deep learning was proposed. The method employed vector mean cancellation and moving target indication (MTI) to suppress static interference. In contrast

dynamic interference was mitigated through a combination of Doppler weighting

constant false alarm rate (CFAR) detection

density-based spatial clustering of applications with noise (DBSCAN)

and connected region constraint. Subsequently

multi-frame range-Doppler maps (RDM) and range-angle maps (RAM) were extracted to serve as model inputs. A dual-stream CNN-MHSA-STCN architecture was constructed

incorporating a convolutional neural network (CNN)

multi-head self-attention (MHSA)

and a simplified temporal convolutional network (STCN) for comprehensive motion recognition. Experimental results demonstrated that the proposed method achieved a recognition accuracy exceeding 98% on a self-collected dataset

while maintaining high precision and robustness in complex operational environments.

关键词

Keywords

references

CHEN Z M , TU H W , WU H Y . User-defined foot gestures for eyes-free interaction in smart shower rooms [J ] . International Journal of Human-Computer Interaction , 2023 , 39 ( 20 ): 4139 - 4161 .

PARK C , BAEK H I , CHAE Y , et al . Deep-learning-based kick motion recognition in millimeter waveband radar system [J ] . IEEE Sensors Journal , 2024 , 24 ( 19 ): 31395 - 31407 .

FRANK S , KUIJPER A . Robust driver foot tracking and foot gesture recognition using capacitive proximity sensing [J ] . Journal of Ambient Intelligence and Smart Environments , 2019 , 11 ( 3 ): 221 - 235 .

SAEZ B , MENDEZ J , MOLINA M , et al . Gesture recognition with ultrasounds and edge computing [J ] . IEEE Access , 2021 , 9 : 38999 - 39008 .

ZHANG Q , LIN Y Q , LIN Y B , et al . Hand pose estimation with mems-ultrasonic sensors [C ] // Proceedings of the SIGGRAPH Asia 2023 Conference Papers . New York : ACM , 2023 : 1 - 11 .

NOBLE F , XU M Q , ALAM F . Static hand gesture recognition using capacitive sensing and machine learning [J ] . Sensors , 2023 , 23 ( 7 ): 3419 .

LIU Y , GUO L C , MAKAROV V A , et al . Agile gesture recognition for capacitive sensing devices: adapting on-the-job [C ] // Proceedings of the 2023 International Joint Conference on Neural Networks (IJCNN) . Piscataway : IEEE Press , 2023 : 1 - 8 .

LI S B , LIU Y . Human motion recognition based on Nano-CMOS Image sensor [J ] . Mathematical Biosciences and Engineering , 2023 , 20 ( 6 ): 10135 - 10152 .

WANG Y H , YAN S , FU Y L , et al . UWB radar signal kick detection for tailgate unlocking based on spatio-temporal network [C ] // Proceedings of the 2024 IEEE International Conference on Mobility, Operations, Services and Technologies (MOST) . Piscataway : IEEE Press , 2024 : 135 - 142 .

SHANKAR Y , SANTRA A . Valid kick recognition in smart trunks based on hidden Markov model using Doppler radar [C ] // Proceedings of the 2019 International Radar Conference (RADAR) . Piscataway : IEEE Press , 2020 : 1 - 5 .

ZHANG H F , LIU K , ZHANG Y H , et al . TRANS-CNN-based gesture recognition for mmWave radar [J ] . Sensors , 2024 , 24 ( 6 ): 1800 .

LEI W T , JIANG X Y , XU L , et al . Continuous gesture recognition based on time sequence fusion using MIMO radar sensor and deep learning [J ] . Electronics , 2020 , 9 ( 5 ): 869 .

JIN B , MA X , ZHANG Z K , et al . Interference-robust millimeter-wave radar-based dynamic hand gesture recognition using 2-D CNN-transformer networks [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 2 ): 2741 - 2752 .

DEKKER B , JACOBS S , KOSSEN A S , et al . Gesture recognition with a low power FMCW radar and a deep convolutional neural network [C ] // Proceedings of the 2017 European Radar Conference (EURAD) . Piscataway : IEEE Press , 2018 : 163 - 166 .

赵学荣 , 王旋 , 刘彤 , 等 . 面向智慧博物馆的基于毫米波雷达稳健的手语识别 [J ] . 电信科学 , 2023 , 39 ( 8 ): 109 - 117 .

ZHAO X R , WANG X , LIU T , et al . mmWave radar based robust sign language recognition for the smart museum [J ] . Telecommunications Science , 2023 , 39 ( 8 ): 109 - 117 .

罗金燕 , 常俊 , 吴彭 , 等 . 基于残差网络的FMCW雷达人体行为识别 [J ] . 计算机科学 , 2023 , 50 ( S2 ): 174 - 179 .

LUO J Y , CHANG J , WU P , et al . Human behavior recognition of FMCW radar based on residual network [J ] . Computer Science , 2023 , 50 ( S2 ): 174 - 179 .

DIAO P S , ALVES T , POUSSOT B , et al . A review of radar detection fundamentals [J ] . IEEE Aerospace and Electronic Systems Magazine , 2024 , 39 ( 9 ): 4 - 24 .

SAHA P K , LOGOFATU D . Efficient approaches for density-based spatial clustering of applications with noise [C ] // Artificial Intelligence Applications and Innovations . Cham : Springer , 2021 : 184 - 195 .

BIJALWAN V , KHAN A M , BAEK H , et al . Interpretable human activity recognition with temporal convolutional networks and model-agnostic explanations [J ] . IEEE Sensors Journal , 2024 , 24 ( 17 ): 27607 - 27617 .

NAN M H , TRĂSCĂU M , FLOREA A M , et al . Comparison between recurrent networks and temporal convolutional networks approaches for skeleton-based action recognition [J ] . Sensors , 2021 , 21 ( 6 ): 2051 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [J ] . Advances in neural information processing systems , 2017 ( 30 ): 1 - 11 .

LIN T Y , GOYAL P , GIRSHICK R , et al . Focal loss for dense object detection [C ] // Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV) . Piscataway : IEEE Press , 2017 : 2999 - 3007 .

SONG S , KIM B , KIM S , et al . Foot gesture recognition using high-compression radar signature image and deep learning [J ] . Sensors , 2021 , 21 ( 11 ): 3937 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向智慧博物馆的基于毫米波雷达稳健的手语识别

OFDM系统中一种实用的干扰抑制信道估计算法

FemtoceII网络干扰抑制技术综述

分层异构无线网络中基于预编码的干扰抑制技术