一种基于双维度滤波和自适应定长化的FMCW雷达手势识别算法研究
Research on a Gesture Recognition Algorithm for FMCW Radar Based on Bidimensional Filtering and Adaptive Fixed Length
- 电子学报 2023年51卷第8期 页码：2179-2187
- 作者机构：
浙江大学信息与电子工程学院，浙江杭州 315000
- 作者简介：
[ "陈君毅 男，1997年1月出生，浙江嘉兴人.浙江大学硕士研究生.主要研究方向为毫米波雷达感知技术.E-mail: chen19858874807@163.com" ]
[ "蒋德琛 男，1997年3月出生，浙江宁波人.浙江大学硕士研究生.主要研究方向为毫米波雷达应用.E-mail: dechen_j@163.com" ]
- 基金信息：
DOI：10.12263/DZXB.20211410
中图分类号： TP391;收稿：2021-10-17，
修回：2022-05-17，
纸质出版：2023-08-25
- 稿件说明：
移动端阅览
陈君毅,蒋德琛,王智铭等.一种基于双维度滤波和自适应定长化的FMCW雷达手势识别算法研究[J].电子学报,2023,51(08):2179-2187.
CHEN Jun-yi,JIANG De-chen,WANG Zhi-ming,et al.Research on a Gesture Recognition Algorithm for FMCW Radar Based on Bidimensional Filtering and Adaptive Fixed Length[J].ACTA ELECTRONICA SINICA,2023,51(08):2179-2187.
陈君毅,蒋德琛,王智铭等.一种基于双维度滤波和自适应定长化的FMCW雷达手势识别算法研究[J].电子学报,2023,51(08):2179-2187. DOI： 10.12263/DZXB.20211410.
CHEN Jun-yi,JIANG De-chen,WANG Zhi-ming,et al.Research on a Gesture Recognition Algorithm for FMCW Radar Based on Bidimensional Filtering and Adaptive Fixed Length[J].ACTA ELECTRONICA SINICA,2023,51(08):2179-2187. DOI： 10.12263/DZXB.20211410.
摘要
本文提出了一种基于调频连续波（Frequency Modulated Continuous Wave，FMCW）雷达回波信号的手势识别算法：首先，提出一种双维度滤波算法，在距离和速度维度对手势回波信号进行滤波，有效地降低了系统的静态噪声；其次，将数据经过动目标检测（Moving Target Indicator，MTI）算法滤除时间维度噪声；然后，提出了时间自适应定长化的方法，在减少势信息损失的前提下保证了每个手势样本帧数的一致性；最后，建立距离多普勒网络（Range Doppler Net，RD-Net）进行训练分类.该算法在谷歌开源的deepsoli数据集中取得了98.28%的准确率，比数据集提出者的算法的准确率提升了11.11%.该算法在实时推理实验中取得了90.8%的准确率，具有更好的泛化能力.本文采集的数据集开源地址为
https://gitee.com/xiao_chens_classmates/Radar_Gesture_Data.git
https://gitee.com/xiao_chens_classmates/Radar_Gesture_Data.git
Abstract
This paper proposes a gesture recognition algorithm based on frequency modulated continuous wave (FMCW) radar echo signals. Firstly
a two-dimensional filtering algorithm is proposed to filter the gesture echo signals in the distance and speed dimensions
which effectively reduces the static noise of the system. Secondly
the data is filtered by the moving target indicator (MTI) algorithm to filter out the noise in the time dimension. Then a time-adaptive fixed-length method is proposed
which ensures the consistency of the frame number of each gesture sample on the premise of reducing the loss of gesture information. Finally
a range Doppler net (RD-Net) is established for training and classification. The algorithm achieved 98.28% accuracy in Google's open source deepsoli data set
which is 11.11% higher than the algorithm proposed by the data set. The algorithm achieves 90.8% accuracy in real-time reasoning experiments and has better generalization ability.
关键词
Keywords
references
CARD S K , MORAN T P , NEWELL A . The Psychology of Human-Computer Interaction [M ] . Boca Raton : CRC Press , 2018 .
RAUTARAY S S , AGRAWAL A . Vision based hand gesture recognition for human computer interaction: A survey [J ] . Artificial Intelligence Review , 2015 , 43 ( 1 ): 1 - 54 .
陆霖霖 , 江春华 , 郝宗波 . 基于不同光照条件的人体手势识别新方法 [J ] . 计算机应用 , 2015 , 35 ( S1 ): 273 - 277, 291 .
LU L L , JIANG C H , HAO Z B . Human gesture recognition new approach based on different light conditions [J ] . Journal of Computer Applications , 2015 , 35 ( S1 ): 273 - 277, 291 . (in Chinese)
YEO H S , FLAMICH G , SCHREMPF P , et al . RadarCat: radar categorization for input & interaction [C ] // Proceedings of the 29th Annual Symposium on User Interface Software and Technology . New York : ACM , 2016 : 833 - 841 .
YEO H S , MINAMI R , RODRIGUEZ K , et al . Exploring tangible interactions with radar sensing [J ] . Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies , 2018 , 2 ( 4 ): 1 - 25 .
HOF E , SANDEROVICH A , SALAMA M , et al . Face verification using mmWave radar sensor [C ] // 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) . Fukuoka : IEEE , 2020 : 320 - 324 .
TAHMOUSH D , SILVIOUS J . Radar micro-Doppler for long range front-view gait recognition [C ] // 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems . Washington : IEEE , 2009 : 1 - 6 .
VANDERSMISSEN B , KNUDDE N , JALALVAND A , et al . Indoor person identification using a low-power FMCW radar [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2018 , 56 ( 7 ): 3941 - 3952 .
LIEN J , GILLIAN N , et al . Soli: Ubiquitous gesture sensing with millimeter wave radar [J ] . ACM Transactions on Graphics , 2016 , 35 ( 4 ): 1 - 19 .
SUH J S , RYU S , HAN B , et al . 24 GHz FMCW radar system for real-time hand gesture recognition using LSTM [C ] // 2018 Asia-Pacific Microwave Conference (APMC) . Kyoto : IEEE , 2018 : 860 - 862 .
SMITH K A , CSECH C , MURDOCH D , et al . Gesture recognition using mm-wave sensor for human-car interface [J ] . IEEE Sensors Letters , 2018 , 2 ( 2 ): 1 - 4 .
王勇 , 吴金君 , 田增山 , 等 . 基于FMCW雷达的多维参数手势识别算法 [J ] . 电子与信息学报 , 2019 , 41 ( 4 ): 822 - 829 .
WANG Y , WU J J , TIAN Z S , et al . Gesture recognition with multi-dimensional parameter using FMCW radar [J ] . Journal of Electronics & Information Technology , 2019 , 41 ( 4 ): 822 - 829 . (in Chinese)
夏朝阳 , 周成龙 , 介钧誉 , 等 . 基于多通道调频连续波毫米波雷达的微动手势识别 [J ] . 电子与信息学报 , 2020 , 42 ( 1 ): 164 - 172 .
XIA Z Y , ZHOU C L , JIE J Y , et al . Micro-motion gesture recognition based on multi-channel frequency modulated continuous wave millimeter wave radar [J ] . Journal of Electronics & Information Technology , 2020 , 42 ( 1 ): 164 - 172 . (in Chinese)
WANG S W , SONG J , LIEN J , et al . Interacting with soli: Exploring fine-grained dynamic gesture recognition in the radio-frequency spectrum [C ] // Proceedings of the 29th Annual Symposium on User Interface Software and Technology . New York : ACM , 2016 : 851 - 860 .
YU F , KOLTUN V . Multi-scale context aggregation by dilated convolutions [EB/OL ] . ( 2015 )[2021 ] . https://arxiv.org/abs/1511.07122 https://arxiv.org/abs/1511.07122 .
KINGMA D P , BA J . Adam: A method for stochastic optimization [EB/OL ] . ( 2014 )[2021 ] . https://arxiv.org/abs/1412.6980 https://arxiv.org/abs/1412.6980 .
0
浏览量
13
下载量
0
CSCD
- 网络PDF下载
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
- 技术支持由北京北大方正电子有限公司提供 京ICP备09064830号-19
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies