• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

结合动态时间规整与多传感器进行3D手势识别

Combined Dynamic Time Warping with Multiple Sensors for 3D Gesture Recognition.

作者信息

Choi Hyo-Rim, Kim TaeYong

机构信息

Department of Advanced Imaging Science, Chung-Ang University, Heukseok-dong, Dongjak-gu, Seoul 156-756, Korea.

出版信息

Sensors (Basel). 2017 Aug 17;17(8):1893. doi: 10.3390/s17081893.

DOI:10.3390/s17081893
PMID:28817094
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC5579764/
Abstract

Cyber-physical systems, which closely integrate physical systems and humans, can be applied to a wider range of applications through user movement analysis. In three-dimensional (3D) gesture recognition, multiple sensors are required to recognize various natural gestures. Several studies have been undertaken in the field of gesture recognition; however, gesture recognition was conducted based on data captured from various independent sensors, which rendered the capture and combination of real-time data complicated. In this study, a 3D gesture recognition method using combined information obtained from multiple sensors is proposed. The proposed method can robustly perform gesture recognition regardless of a user's location and movement directions by providing viewpoint-weighted values and/or motion-weighted values. In the proposed method, the viewpoint-weighted dynamic time warping with multiple sensors has enhanced performance by preventing joint measurement errors and noise due to sensor measurement tolerance, which has resulted in the enhancement of recognition performance by comparing multiple joint sequences effectively.

摘要

网络物理系统将物理系统与人类紧密结合，通过用户运动分析可应用于更广泛的领域。在三维（3D）手势识别中，需要多个传感器来识别各种自然手势。手势识别领域已经开展了多项研究；然而，手势识别是基于从各种独立传感器捕获的数据进行的，这使得实时数据的捕获和组合变得复杂。在本研究中，提出了一种利用从多个传感器获得的组合信息的3D手势识别方法。通过提供视点加权值和/或运动加权值，该方法可以在不考虑用户位置和运动方向的情况下稳健地执行手势识别。在所提出的方法中，具有多个传感器的视点加权动态时间规整通过防止由于传感器测量容差引起的关节测量误差和噪声而提高了性能，这通过有效地比较多个关节序列提高了识别性能。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/3142159e2da8/sensors-17-01893-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/46252b966158/sensors-17-01893-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/2bedcb440518/sensors-17-01893-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/e460b5e3209d/sensors-17-01893-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/9bf6cf1c26ca/sensors-17-01893-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/173b4e88c3f1/sensors-17-01893-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/2de1fe274437/sensors-17-01893-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/3daa62cb3fae/sensors-17-01893-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/7659944f28ea/sensors-17-01893-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/af4f523a5381/sensors-17-01893-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/7a719e1892f8/sensors-17-01893-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/934fce5eb813/sensors-17-01893-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/4b70e06deb81/sensors-17-01893-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/3142159e2da8/sensors-17-01893-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/46252b966158/sensors-17-01893-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/2bedcb440518/sensors-17-01893-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/e460b5e3209d/sensors-17-01893-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/9bf6cf1c26ca/sensors-17-01893-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/173b4e88c3f1/sensors-17-01893-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/2de1fe274437/sensors-17-01893-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/3daa62cb3fae/sensors-17-01893-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/7659944f28ea/sensors-17-01893-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/af4f523a5381/sensors-17-01893-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/7a719e1892f8/sensors-17-01893-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/934fce5eb813/sensors-17-01893-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/4b70e06deb81/sensors-17-01893-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ee07/5579764/3142159e2da8/sensors-17-01893-g013.jpg

相似文献

1
Combined Dynamic Time Warping with Multiple Sensors for 3D Gesture Recognition.结合动态时间规整与多传感器进行3D手势识别
Sensors (Basel). 2017 Aug 17;17(8):1893. doi: 10.3390/s17081893.
2
Inertial Sensor-Based Touch and Shake Metaphor for Expressive Control of 3D Virtual Avatars.基于惯性传感器的触摸与摇晃隐喻，用于对3D虚拟化身进行表情控制。
Sensors (Basel). 2015 Jun 18;15(6):14435-57. doi: 10.3390/s150614435.
3
A Differential Evolution Approach to Optimize Weights of Dynamic Time Warping for Multi-Sensor Based Gesture Recognition.基于动态时间规整的多传感器手势识别的差分进化权重优化方法。
Sensors (Basel). 2019 Feb 27;19(5):1007. doi: 10.3390/s19051007.
4
Depth camera-based 3D hand gesture controls with immersive tactile feedback for natural mid-air gesture interactions.基于深度摄像头的3D手势控制，具备沉浸式触觉反馈，用于自然的空中手势交互。
Sensors (Basel). 2015 Jan 8;15(1):1022-46. doi: 10.3390/s150101022.
5
Tracking and Classification of In-Air Hand Gesture Based on Thermal Guided Joint Filter.基于热引导关节滤波器的空中手势跟踪与分类。
Sensors (Basel). 2017 Jan 17;17(1):166. doi: 10.3390/s17010166.
6
HAGR-D: A Novel Approach for Gesture Recognition with Depth Maps.HAGR-D：一种利用深度图进行手势识别的新方法。
Sensors (Basel). 2015 Nov 12;15(11):28646-64. doi: 10.3390/s151128646.
7
Continuous dynamic gesture spotting algorithm based on Dempster-Shafer Theory in the augmented reality human computer interaction.增强现实人机交互中基于Dempster-Shafer理论的连续动态手势识别算法
Int J Med Robot. 2018 Oct;14(5):e1931. doi: 10.1002/rcs.1931. Epub 2018 Jun 28.
8
Dynamic gesture recognition based on multiple sensors fusion technology.基于多传感器融合技术的动态手势识别
Annu Int Conf IEEE Eng Med Biol Soc. 2009;2009:7014-7. doi: 10.1109/IEMBS.2009.5333326.
9
Smart-Data-Glove-Based Gesture Recognition for Amphibious Communication.基于智能数据手套的两栖通信手势识别
Micromachines (Basel). 2023 Oct 31;14(11):2050. doi: 10.3390/mi14112050.
10
IMU Sensor-Based Hand Gesture Recognition for Human-Machine Interfaces.基于惯性测量单元传感器的人机界面手势识别。
Sensors (Basel). 2019 Sep 4;19(18):3827. doi: 10.3390/s19183827.

引用本文的文献

1
Distributed intelligence in industrial and automotive cyber-physical systems: a review.工业与汽车网络物理系统中的分布式智能：综述
Front Robot AI. 2024 Oct 28;11:1430740. doi: 10.3389/frobt.2024.1430740. eCollection 2024.
2
A Differential Evolution Approach to Optimize Weights of Dynamic Time Warping for Multi-Sensor Based Gesture Recognition.基于动态时间规整的多传感器手势识别的差分进化权重优化方法。
Sensors (Basel). 2019 Feb 27;19(5):1007. doi: 10.3390/s19051007.
3
MFA-Net: Motion Feature Augmented Network for Dynamic Hand Gesture Recognition from Skeletal Data.

本文引用的文献

1
Accuracy of the Microsoft Kinect sensor for measuring movement in people with Parkinson's disease.微软Kinect传感器在测量帕金森病患者运动方面的准确性。
Gait Posture. 2014 Apr;39(4):1062-8. doi: 10.1016/j.gaitpost.2014.01.008. Epub 2014 Jan 22.
2
Accuracy and resolution of Kinect depth data for indoor mapping applications.用于室内制图应用的 Kinect 深度数据的准确性和分辨率。
Sensors (Basel). 2012;12(2):1437-54. doi: 10.3390/s120201437. Epub 2012 Feb 1.
MFA-Net：基于运动特征增强的骨骼数据动态手势识别网络。
Sensors (Basel). 2019 Jan 10;19(2):239. doi: 10.3390/s19020239.