基于雷达的多输入多输出手势识别的自适应轨迹恒误报率镜像滤波器和仰角评估

T. Tseng, Jian-Jiun Ding
{"title":"基于雷达的多输入多输出手势识别的自适应轨迹恒误报率镜像滤波器和仰角评估","authors":"T. Tseng, Jian-Jiun Ding","doi":"10.3390/electronics13040682","DOIUrl":null,"url":null,"abstract":"Gesture recognition technology has been quickly developed in the field of human–computer interaction. The multiple-input multiple-output (MIMO) radar is popular in gesture recognition because of its notable spatial resolution. This work proposes a MIMO radar-based hand gesture recognition algorithm with low complexity. We leverage low-complexity adaptive signal processing to extract trajectory information and minimize noise to create a system that can be applied in real-world applications with small training datasets. First, a spectrum analysis is utilized on range-Doppler maps (RDMs), and a cell-averaging constant false alarm rate (CA-CFAR) with mirror filters is applied to improve the robustness of noise. Then, the features related to the distance, speed, direction, and elevation angle of the moving object are determined using the proposed adaptive signal analysis techniques. For classification, the random forest algorithm is implemented. The proposed system can precisely distinguish and identify eight gestures, including waving, moving to the left or right, patting, pushing, pulling, and rotating clockwise or anti-clockwise, with an accuracy of 95%. Experiments demonstrate the capability of the proposed hand gesture recognition system to classify different movements precisely.","PeriodicalId":504598,"journal":{"name":"Electronics","volume":"343 6‐7","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Adaptive Trajectories’ Constant False Alarm Rate Mirror Filters and Elevation Angle Evaluation for Multiple-Input Multiple-Output Radar-Based Hand Gesture Recognition\",\"authors\":\"T. Tseng, Jian-Jiun Ding\",\"doi\":\"10.3390/electronics13040682\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Gesture recognition technology has been quickly developed in the field of human–computer interaction. The multiple-input multiple-output (MIMO) radar is popular in gesture recognition because of its notable spatial resolution. This work proposes a MIMO radar-based hand gesture recognition algorithm with low complexity. We leverage low-complexity adaptive signal processing to extract trajectory information and minimize noise to create a system that can be applied in real-world applications with small training datasets. First, a spectrum analysis is utilized on range-Doppler maps (RDMs), and a cell-averaging constant false alarm rate (CA-CFAR) with mirror filters is applied to improve the robustness of noise. Then, the features related to the distance, speed, direction, and elevation angle of the moving object are determined using the proposed adaptive signal analysis techniques. For classification, the random forest algorithm is implemented. The proposed system can precisely distinguish and identify eight gestures, including waving, moving to the left or right, patting, pushing, pulling, and rotating clockwise or anti-clockwise, with an accuracy of 95%. Experiments demonstrate the capability of the proposed hand gesture recognition system to classify different movements precisely.\",\"PeriodicalId\":504598,\"journal\":{\"name\":\"Electronics\",\"volume\":\"343 6‐7\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-02-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Electronics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/electronics13040682\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Electronics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/electronics13040682","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

手势识别技术在人机交互领域得到了迅速发展。多输入多输出(MIMO)雷达因其显著的空间分辨率而在手势识别领域大受欢迎。本研究提出了一种基于 MIMO 雷达的低复杂度手势识别算法。我们利用低复杂度自适应信号处理来提取轨迹信息,并将噪声降到最低,从而创建了一个可在实际应用中使用小型训练数据集的系统。首先,对测距-多普勒图(RDM)进行频谱分析,并应用带有镜像滤波器的单元平均恒定误报率(CA-CFAR)来提高噪声的鲁棒性。然后,利用所提出的自适应信号分析技术确定与移动物体的距离、速度、方向和仰角相关的特征。在分类方面,采用了随机森林算法。所提出的系统可以精确区分和识别八种手势,包括挥手、向左或向右移动、拍打、推、拉、顺时针或逆时针旋转,准确率达到 95%。实验证明了所提出的手势识别系统能够精确地对不同的动作进行分类。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Adaptive Trajectories’ Constant False Alarm Rate Mirror Filters and Elevation Angle Evaluation for Multiple-Input Multiple-Output Radar-Based Hand Gesture Recognition
Gesture recognition technology has been quickly developed in the field of human–computer interaction. The multiple-input multiple-output (MIMO) radar is popular in gesture recognition because of its notable spatial resolution. This work proposes a MIMO radar-based hand gesture recognition algorithm with low complexity. We leverage low-complexity adaptive signal processing to extract trajectory information and minimize noise to create a system that can be applied in real-world applications with small training datasets. First, a spectrum analysis is utilized on range-Doppler maps (RDMs), and a cell-averaging constant false alarm rate (CA-CFAR) with mirror filters is applied to improve the robustness of noise. Then, the features related to the distance, speed, direction, and elevation angle of the moving object are determined using the proposed adaptive signal analysis techniques. For classification, the random forest algorithm is implemented. The proposed system can precisely distinguish and identify eight gestures, including waving, moving to the left or right, patting, pushing, pulling, and rotating clockwise or anti-clockwise, with an accuracy of 95%. Experiments demonstrate the capability of the proposed hand gesture recognition system to classify different movements precisely.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信